1,329
Archived Theses
0
DOIs Assigned
0%
DOI Rate
Discipline
Planning and scheduling in supply chain environment within process industry
Process manufacturing is common in the food, beverage, chemical, pharmaceutical and consumer packaged goods industries. There is a continuous stream of input materials and output products. The structural characteristics of the process industry are sequence dependent setup times, high changeover costs, numerous flavored and colored product types with the complicated changeover rules, limited shelf life restricting the storage duration and delivery conditions for each perishable raw material, intermediate and final product. In this environment, efficient planning and scheduling of the supply chain is of vital importance and has become one of the most challenging problems in practice. This dissertation concerns planning and scheduling problems in the process industry. The main goal is to develop mathematical formulations of the supply chain problems. In this thesis, the characteristics of the process industry are analyzed. The major trends and research opportunities are explored from the existing literature. The existing models in the literature do not address many realistic aspects of the planning and scheduling problems in the process industry. Starting from this point of view, a production and distribution problem is studied in the soft drink industry. A mixed-integer linear programming model is introduced and, due to the high complexity in production and distribution structure, a hybrid solution methodology is developed to solve the realistic problems. The operational scheduling represents the realization of tactical planning decisions in operational level. Having created a plan for defining the production tasks has to be sequenced ensures that the planning activities are indeed applicable. The integration of planning and scheduling can be an effective way to make more applicable decisions. Accordingly, a production and distribution problem is studied in the dairy industry. A mixed-integer linear programming formulation is introduced to integrate tactical planning and operational scheduling decisions and, a heuristic approach is proposed to decompose the different time buckets of the decisions. In real life, intermediates are more perishable than final products. The final products can survive for long shelf life periods, but the lifetimes of the intermediates are only restricted with several hours. The perishability should not be only included in inventory level or shelf life of final products, it should also be realized that the perishability limits the intermediate storage and affects run-lengths of production. A scheduling problem is studied in the make-and-pack production process. A stochastic mixed-integer linear programming model is introduced to schedule the production. A simulation of the production process is introduced to evaluate the proposed production schedule in terms of the production waste, mostly caused by the variability in lifetime of intermediates. In summary, the industry specific characteristics, incorporation of the decision levels providing interrelated feedbacks to each other and perishability issues are recent challenges confronted by the process industry. These challenges require specific models to support decision making in supply chain. In response, this thesis develops mathematical models and optimization approaches applicable to different processes industries and can easily be modified for process specific operating conditions.
Group technology and cellular manufacturing with artificial neural networks
Group Technology (GT) / Cellular Manufacturing (CM) is a useful way of increasing the productivity in manufacturing high quality products, improving the flexibility of manufacturing systems and decreasing the costs. Cell Formation (CF) is the key step for GT. CF can identify part families and machine groups. Several kinds of methods can be used in CF. Artifial Neural Networks (ANNs) are very suitable for CF and have been widely applied in CF due to their robust and adaptive nature.In the thesis, a review of different kinds of ANNs from the literature which are used in CF, is presented. An application of Self Organizing Map (SOM) and Competitive Neural Network (CNN) within a new methodology for grouping binary and nonbinary (fuzzy) problem sets simultaneously is made. 15 problem sets gathered from the literature are used as binary problem sets and 6 problem sets gathered from the literature are used as nonbinary problem sets. A performance measure which is created by taking the aritmetic average of five different well-known performance measures from the literature is proposed and used to evaluate and compare the cell solutions. Also, the performance measures in the articles the problem sets are taken from, are used once more to evaluate and compare the cell solutions. SOM and CNN results are compared with the results in the literature. In the last part of the application, different numbers of cells are tested to see whether there is a better cell configuration than the article has found. Matlab 7.5 is used to code the neural networks and find the best groupings.
A literature review on six sigma
In this study, the roots, historical development, theoretical background, and future expectations of six sigma quality improvement approach, which emerged in manufacturing industries in the mid 1980s, are analyzed within the framework of an academic literature review. In this context, firstly the historical developments of quality phenomenon in the Western World, Japan, and Turkey are explored, and the theoretical basis of this quality system is identified. Then, the academic journals covered by Science Citation Index (SCI) Expanded are searched without time limits with keyword ?six sigma?. Almost all of the articles in the resulting set are examined in full-text; and a comparative statistical analysis is conducted. This analysis is based upon factors that are derived directly from the contents of the articles. Analysis results are used in order to determine the current situation, up-to-date trends, and historical transformations in the literature, therefore the implementations of six sigma. The results are discussed in detail and ideas about the future implementations of six sigma are given.The literature study shows that although no consensus is built up on either the definition or the implementation of six sigma, it is believed that it will maintain its importance in the following years.
Advanced analysis system for optimized changeover operations
In this study changeover operations are discussed in scope of Lean Manufacturing and Shigeo Shingo?s approach called SMED (Single Minute Exchange of Dies) is explained. SMED approach is analyzed in terms of sustainability and a new analysis system is introduced to develop optimal changeover procedure which tries to provide a sustainable changeover process. On this way the new analysis system is handled under two main headlines; Macro analysis (using conventional SMED approach) and Micro analysis (using MTM / Method Measurement Time Systems). Macro and micro analysis results are documented as changeover procedures which provide the manual for operators to perform the best organized changeover operation.Keywords: SMED (Single Minute Exchange of Dies), Lean Manufacturing, sustainability, changeover, MTM (Method Time Measurement), Time Study, Change
Capacity planning in a textile company
This thesis provides the opportunity of launching the capacity planning system in a company in the textile sector. The objective of this project is handling the demand fluctuations by utilizing regular time working capacity and subcontractor capacity for each product group in a predetermined planning period and giving the customer realistic due dates. To fulfill this target, it is essential to keep the company?s and subcontractor?s production costs at the minimum while meeting the due dates at optimum.In order to achieve these goals a hybrid approach involving a two phased solution methodology is carried out. First an allocation problem is solved using mathematical programming following the assignment of jobs to the facilities under given capacity constraints. Afterwards, a detailed simulation model of the production floor is run to determine in which order the jobs will be processed on these facilities. The output of the mathematical programming model is used as an input for the simulation model. The use of analytical modeling and simulation together as a hybrid approach leads to a mathematically optimal and a realistically feasible solution.
Comparison of control charts for autocorrelated data
As a result of improvements in measurement techniques, sampling intervals become shorter, and this causes serial correlation in data. Also, in some process industries like chemical manufacturing and refinery operations serial correlation is inherent in consecutive measurements. To deal with this challenge, the traditional control charts are improved or new control charts are developed in the last few decades. Residual control charts such as X residual and EWMA residual are widely used control charts for autocorrelated data. In recent years, EWMAST, ARMAST, and DFTC charts have been also introduced for this type of data. To compare the performances of control charts have attracted interest of researchers. In the relevant literature, although there have been a lot of comparison studies, in only few of them the first-order autoregressive moving average (ARMA(1,1)) process have been investigated.The objective of this research is to compare performances of Shewhart X, CUSUM, X residual, EWMA residual, EWMAST, ARMAST, and DFTC charts for ARMA(1,1) process when the mean shifts. Performance criterion used for this comparison is the average run length (ARL).
Product reliability
This study presents product reliability on component basis and investigates the possible effects on warranty which constitutes a non-technical issue. Product reliability is a key factor which is used in considering the warranty period. It plays a significant role that a mistake in warranty forecasting costs a lot for companies.The objective is to empirically examine the nature of general reliability of manufactured goods and define a statement about them, based on findings of practicing in an electronics company. In this regard reliability will be stated from the actual manufacturing point of view. A case study was conducted as an application to consider how product reliability results in manufacturing industry. LCD TVs were undertaken to examine. To test reliability, a parametric Weibull model was exploited and hazard rates of products were estimated with linear regression method. For this research, the lifetime data obtained by service departments, censored both left and right, were used in MINITAB14 to produce the reliability results.The results of the analysis build up the basis for evaluating the performance of LCDs in means of service. By the help of it, upcoming failures were forecasted and defined when and how many of them could occur in say six months, a year or two years. The time at which a particular percentage of the production will have failed can be determined
Solving mixed-model assembly line sequencing problem using adaptive genetic algorithms
The focus of this M.Sc study is to introduce adaptive Genetic Algorithm (GA) based approaches for single- and multi-objective mixed-model assembly line sequencing problems (MMALSP), which deal with the determination of production launching orders so that the variations in part consumption rates (VPC) are minimized. In addition to this objective, minimization of total utility work (UW) and cost for sequence-dependent setups (SC) are also considered in multi-objective version of the MMALSP.In order to solve single-objective MMALSPs, an adaptive GA based approach which incorporates adaptive parameter control techniques into a pure GA is proposed. The proposed approach, integrates an adaptive elitist strategy and a scheme for varying probability of mutation according to the feedback taken from the algorithm. Using this approach, the MMALSP is solved under the objective of minimizing VPC in a four level assembly environment, i.e. product, subassembly, component and raw material.Later, by modifying the adaptive parameter control techniques and integrating them into a Pareto Stratum ? Niche Cubicle GA, a multi-objective MMALSP with three objective functions (i.e., minimization of VPC, UW and SC) is solved. Finally, to evaluate the performance of the proposed approach, various sets of experiments have been carried out.
Araç rotalama problemi tipleri için kesin ve sezgisel algoritmalar
As the world is globalizing, distribution of goods and services becomes an inevitable part of both trade and daily life. Distribution of goods and services from a supply point to various demand points is called logistics. A complete logistics system includes transporting materials from a number of suppliers to the factory plant for manufacturing, transporting the products to warehouses and finally distributing them to the customers. Both the supply and distribution procedures require effective transportation planning. Good transportation planning can save a company a considerable amount of its total distribution costs.Vehicle Routing Problem (VRP) basically considers transportation planning and has received a lot of attention in operations research literature due to its commercial value. VRP consists of designing m vehicle routes to minimize total cost, each starting and ending at the depot such that each customer is visited exactly once. Since VRP was first introduced in literature, many variations have appeared by including additional assumptions into the problem.In this dissertation, three of the variants of VRP, which are faced quite often in real life distribution problems, are considered. These are heterogeneous VRP (HVRP), split delivery VRP (SDVRP) and VRP with time windows (VRPTW). A novel Threshold Algorithm is developed for HVRP, SDVRP and small scale VRPTW. For large scale VRPTW, a SetCovering Algorithm is developed.In order to see the efficiency and performance of these algorithms, they are tested on the literature benchmark problems. The results of the computational experiments indicate that the proposed methodologies are useful tools especially for large scale real life problems where fast decision making is of crucial importance. In addition to performance tests, the proposed methodologies are employed to solve the real life fresh goods distribution problem of a retail chain store. The results achieved are presented to the firm and new distribution strategies are offered.
An integrated multi-criteria decision making methodology for risky investment projects evaluation
The aim of this research is to propose a novel methodology for risky investment projects evaluation. The proposed methodology consists of three main stages. The first stage of the methodology includes opportunity and pre-feasibility studies. The aim of this stage is to give prominence to project ideas which have the highest chance of attaining the goals planned by entrepreneurs and investors. Therefore, in the first stage, the investment projects are classified by using a multi-criteria sorting (MCS) method which does not require a training sample, and takes into account the inherent risk and uncertainty associated with the values of evaluation criteria. This MCS method named as PROMSORT was proposed for financial classification problems. In the scope of this dissertation, this method has been adapted to the investment project evaluation and selection problems.After assigning of the project alternatives to the groups, the second stage of the proposed methodology begins. In this stage, a new net present value (NPV) formulation that eliminates the weakness of using the traditional formulation of NPV has been developed. In uncertain and risky environments, the risky project parameters are determined by probability distributions by using simulation models. For that reason, in the second stage, a computer simulation model for new NPV formulation has been developed by using computer simulation software. Also, the second simulation model has been developed in order to calculate the expected cash flows for each project in each period.The budgets of the enterprises are generally not enough to implement all of the investment proposals which have high expected utility level at the same time. In these cases, the enterprises prefer to implement the investment project proposals at the number allowed by the size of their budgets. Besides the lack of budget, the other reasons of this complexity may be some technical limitations such as earliest and latest start dates and precedence relations.However, in today?s high competitive environments, enterprises have to act well-planned. The first step of acting well-planned is to determine a planning horizon and to predict how much budget to allocate for carrying out investment projects each period over that planning horizon. In this new case, the main objective of enterprises is to maximize the expected utility of all investment projects which are carried out over the planning horizon. In the third stage of the proposed methodology, this type of problem is called as optimal project selection and scheduling problem. The last original contribution of this dissertation is to construct multi-objective mathematical models such as multi-objective linear programming model and fuzzy multi-objective linear programming models in order to solve this problem.
Facility layout optimization using simulation in an automative company
The aim of this study is to transform an assembly line in an automotive company on which only one type of a car can be operated, into a flexible assembly line on which different types of cars can be operated at the same time.In this company, two different car models will start being produced on the same assembly line instead of one. Therefore, some changes in the system are needed to be made. In the first stage of this thesis, current production system, facility layout and transportation activities are examined and problems of the system are determined. In the system, there is not an effective material handling and stock control system and parts are being damaged and delays are occurring during the transportation. In order to solve these problems and make production system more flexible, some improvements are proposed. A pull system which controls production between departments and quantity of work in progress is developed. Facility layout for new coming models is also designed and in order to perform transportation operations in more effective way with minimum cost, AGV (automatic guided vehicle) system is suggested instead of forklifts.In this thesis, also a simulation study was developed to see at what degree the improvements increase the system performance and to find the optimum value of decision variables by using ARENA 10.0.
Implementation of Kaizen Blitz approach in an electronics firm
In this thesis implementation of the Kaizen Blitz approach, known as one of the principles of the total quality control applications and lean manufacturing, in an electronic company is presented. First, problems faced by the company before the execution of this approach are defined, and then implementation steps and expected improvements that will result from carrying out the Kaizen Blitz approach are given in detail.
A hbyrid genetic algorithm for mixed-model assembly line balancing problem with parallel workstation assignment
In this thesis, we deal with the mixed-model assembly line balancing problem (MMALBP) of type-1, which consists of finding a number of stations for a predetemined cycle time as well as a line balance such that a capacity- or even cost-oriented objective is optimized. Various exact and approximation approaches have been developed to deal with MMALBP of type-1. Due to the NP-hard structure of the problem none of the optimum seeking methods have been proven to be practical to solve large scale problems. Moreover, approximation methods may lack the capability of exploring the solution space effectively. Over the last years, hybrid meta heuristics which combine the various algorithmic ideas of meta-heuristics concerning overcome these shortages have been reported.In this thesis, we propose an effective hybrid genetic algorithm, which is able to address some particular features such as parallel workstations and zoning constraints of the assembly process for MMALBP of type-1. For the hybridization of genetic algorithm three well known heuristics, Kilbridge and Wester Heuristic, Phase-I of Moodie and Young Method, and Ranked Positional Weight Tecnique are used. The original versions of them only address the simple assembly line balancing problem, where one single model is assembled, no parallel workstations are allowed and zoning constraints are not considerd. Therefore, we modified Kilbridge and Wester and Phase-I of Moodie and Young Methods for applying these heuristics to MMALBP. Comparative experiments are carried out to evaluate the performances of modified versions of the these heuristics, simulated annealing, pure genetic algorithm, ANTBAL and the proposed procudure on a benchmark data set including 20 MMALBPs of type 1. The proposed hybrid genetic algorithm outperformed the other heuristics and pure genetic algorithm. Although the proposed hybrid genetic algorithm explored the same performance with ANTBAL, it requires less computational effort than ANTBAL.
An integrated inventory-routing system with limited vehicle capacity and storage constraint
This study is concerned with the inventory routing problem with limited vehicle capacity and storage constraint.. The inventory routing problem attempts to coordinate inventory management and vehicle routing in such a way that the cost is minimized over the long run.A mathematical model for coordinating inventory and vehicle routing decisions in an inbound commodity collection system composed of a central warehouse and suppliers is presented. A heuristic is developed due to difficulties on solving large problems with Lingo. Computational results which are obtained from the heuristic are compared with solution of Lingo for small instances. Computational tests are performed on a set of randomly generated problem instances. Computational results are obtained in short time for large and complex models with developed heuristic
A framework based on quality function deployment for requirements analysis in enterprise modelling
Competitiveness and globalization force enterprises to quickly adapt to changing conditions of markets. Enterprises employ some modelling methodologies to organize their strategic knowledge to cope with this change, which results in an enterprise model. Requirements discovery and analysis is the most important phase in creating the enterprise model because any mistake in the requirements discovery deteriorates the validity of the model, resulting in user dissatisfaction. Quality Function Deployment (QFD) is a well-known and integrated approach used in converting the requirements of users into final product specifications. This thesis modifies QFD for enterprise modelling, and proposes Enterprise-QFD, which provides a common platform that can be integrated with any methodology for discovering and analyzing enterprise requirements. The study synthesizes enterprise modelling, requirements analysis and modelling, and QFD concepts and proposes an approach based on modern QFD to analyze the requirements of an enterprise from the long term goals to the functional, informational, organizational, and resource characteristics. The modified QFD tables involve some required columns added and unnecessary ones deleted based on enterprise modelling. A novel matrix content and sequence is also proposed. In the scope of the study, Enterprise-QFD is applied to a small business company processing steel products with real evaluations and the findings to show the usability of the method. After the requirements are analyzed and modelled by Enterprise-QFD, the findings are transferred to the requirements model of CIMOSA, a complicated enterprise reference architecture. The results show that Enterprise-QFD generates the infrastructure for further modelling of enterprise architectures concerning both functional characteristics of enterprise and needs of stakeholders.
Using the extended value stream mapping tool in lean six sigma methodologies for lean supply chains
Various tools and techniques have been developed to improve the flows of value streams in manufacturing facilities. But the effectiveness of lean implementation is usually constrained by business partners. Supply chain management focuses on cutting overall costs. For shorter lead times, lower costs, and higher levels of customer satisfaction in the whole supply chain lean flows need to be created throughout the supply chain.This study presents the implementation of an effective lean tool: extended value stream mapping in the methodology of DMAIC the Lean Six Sigma framework in order to achive the lean supply chain of overall value stream from raw material suppliers to the end customers. A case study is also presented for total lead time reduction and on time delivery increase of a product family using the extended value stream mapping to apply lean tools.
A hybrid approach to setting order promising times in a supply chain network
This M.Sc study suggests a hybrid approach for setting realistic order promising times for a produce-order manufacturing company operating within a supply chain environment.The proposed hybrid approach combines the analytical and simulation modeling to bring together the advantages of both approaches. In first step, an analytic model minimizing the overall costs of production, distribution, transportation, inventory holding, and shortage costs subject to the various kinds of constraints is developed to generate optimum production and distribution plans. In the second step, another analytic model which incorporates these production plans as constraints is developed to generate optimal scheduling decisions. In the last stage, a simulation model which reflects the dynamic and stochastic nature of manufacturing environment is utilized to evaluate realistically the effects of these scheduling decisions. Mainly, this simulation model helped to set realistic order promising times for customers.
Six sigma and an application in construction sector
Six Sigma is known as one of the quality control principles and a lot of studies have been done about Six Sigma until today. These studies were related to improvement of processes, customer satisfaction, reducing cost, production time etc. In this thesis, implementation of DMAIC (Define-Measure-Analyze-Improve-Control), known as Six Sigma methodology is studied in a construction sector company.Firstly, the problem is defined according to DMAIC methodology. Then, the necessary measurements are done and analyzed by using statistical techniques. After that, necessary improvements are determined by factorial experiment method and results of executed improvement are controlled.
The six sigma and an application in a manufacturing firm
There are many different opinions on what Six Sigma is. The most well known description for the matter concerned is that Six Sigma is a technical method used by engineers and statisticians in order to fine-tune the quality of the products or the processes. Statistics and measures are key ingredients of Six Sigma methodology.Methodology of Six Sigma has two models. These ones are DMAIC (Define, Measure, Analyze, Improve, Control) and DCOV (Define, Characterize, Optimize, Verify). The DMAIC is the one of most-widely known and applied model of the Six Sigma problem solving approach.In this study, capturing customer priorities is taken into consideration within the context of Six Sigma DMAIC directives in statistical perspective on the basis of the voice of customer. A case study regarding faucet manufacturing company is made for the matter concerned. The customer requirements are determined by using the data regarding statistical defect analysis and the amount of products and making benchmarking.Keywords: Six Sigma, Six Sigma Improvement Models, DMAIC, DCOV, Selection of The Six Sigma Tools.
An efficient way of single and multiple containers loading by resizing the boxes
This thesis presents efficient ways of loading boxes into containers by resizing them. Two different problems are determined to apply the proposed method. First problem contains filling a single container with only one type of boxes. It is objected to pack maximum products in the container. In second one, customers give orders of different products and thus different boxes are tried to be filled efficiently in one or multiple containers in a fashion of blocks for purpose of minimizing the volume of the block areas and increasing the remained space for the next orders. Also a procedure and its sub-procedures and policies are defined to create more customer satisfaction. Two mathematical models are formed to solve the problems and three stages are defined in appliance of each. At first stage, the model is modified to the reduced form which has integer linear properties and applied to the current box sizes. Second stage uses the original model which has integer nonlinear properties and may not get global optimal solutions although operates in less time for the solution. Third stage contains reduced form of the model as the first stage. This time all candidates for box sizes are applied and global optimal solutions are found. At the end, a comparison for all stages and 2D visualizing of the solutions are given in order.
Tabu search based solution approaches for lot streaming problems in flow shops
Lot streaming (LS) splits the production lot into sublots, and schedules these sublots in an overlapping way on the machines in order to accelerate the process of orders and improve the overall system performance.In this thesis, a number of LS problems all of which aim to minimize makespan in multi machine flow shops are investigated. First problem considers a single-product case in stochastic flow shops. For this problem, a solution approach that integrates tabu search (TS) and simulation is proposed. Sublot size configurations are searched via TS and stochastic behavior of the system is handled by simulation.Remaining three problems differ from each other by sublot types and divisibility of sublot sizes and deal with multi-product cases in deterministic flow shops. Entire problem is partitioned into sequencing and sublot allocation sub-problems. For sequencing sub-problem, a number of simple and efficient sequencing heuristics developed for general flow shops are modified according to LS requirements. For sublot allocation sub-problem, mixed integer programming (MIP) based approaches are proposed. For entire problem, a hybrid solution approach which uses the best sequencing heuristic (i.e., NEH(D,TPLS)) in sequencing sub-problem and applies MIP-based approaches for sublot allocation sub-problem, is proposed. Proposed hybrid approach not only gives efficient results for small/medium sized problems in short computation times but also solves large-sized problems in reasonable times. Finally, to improve solution quality in small/medium sized problems, same approach is also integrated to a solution procedure where initial sequence is taken as NEH(D,TPLS) and alternative sequences are evaluated via TS.
Resource constrained parallel machine scheduling problems with machine eligibility restrictions: Mathematical and constraint programming based approaches
The research in this dissertation is motivated by a real-world scheduling problem in the injection molding department of an electrical appliance company and investigates three resource-constrained parallel machine scheduling problems with machine eligibility restrictions.The first problem assumes that processing times of all jobs are equal and aims to minimize total flow time. For this problem, two heuristic algorithms are proposed. The first one is a Lagrangian-based solution approach embedded into a subgradient optimization procedure. The second one is a problem specific heuristic. The performances of the proposed algorithms are evaluated by means of randomly generated test instances with different problem parameters.The second problem allows arbitrary processing times and aims to minimize makespan. For this problem, three optimization models, namely, integer programming (IP), constraint programming (CP), and combined IP/CP models, are developed. Four different CP search algorithms have been evaluated. The proposed models are then tested through medium size test problems and the efficiency of the proposed IP/CP combined model is demonstrated.The last problem considers the real case with 36 machines and real die-machine compatibility data. For this problem, IP/IP and IP/CP iterative approaches are proposed. Both approaches have a common loading phase where an IP model assigns the jobs to the machines. Subsequently, in the scheduling phase, two alternative models, namely, IP and CP are developed to construct the final schedule. The proposed approaches are evaluated by the test problems generated on real data, and the efficiency of IP/CP iterative approach is investigated.
A design of multi-criteria based decision support system for employee performance evaluation: A real world application
Today, successful companies focus on two things: employees and customers. In a constantly changing business environment, success of the companies depends largely on the human resources strategy they follow. In this context, an effective employee performance evaluation system has a very important role in achieving a sustainable competitive advantage. In this study, a decision support system was developed to evaluate employee performance. The proposed system includes the Analytic Hierarchy Process (AHP), a multi-criteria decision-making technique, and K-means algorithm, which is a clustering algorithm. A user-friendly interface has been developed to improve the practicability of the proposed decision support system. An application is presented to reveal the viability of the proposed system. Keywords:
Plastic injection parameter optimization strategies for mold set-up reductions via soft computing techniques in a multi product system
For changeover time reduction, the famous methodology, named single minute exchange of dies (SMED), introduced by Shigeo Shingo, has been applied in production plants for years in lean manufacturing scope. The main philosophy of this technique can be summarized as "make it simple and keep it simple". However, this simplification is not possible for all the steps of a changeover. In the last part of a changeover, which is also named as trial runs and adjustment, injection parameters are manipulated to resolve quality issues that occur during trial productions after the mold is changed. This session requires a deep knowledge and experience, hence, only dedicated personnel called setup experts can handle this session. In this dissertation, two popular soft computing techniques, fuzzy inference system (FIS) and multilayer neural networks (MLNN), are used to capture this domain expertise. The primary objective is to distribute the domain experience to non-expert plastic injection personnel to eliminate expert scarcity and to increase flexibility. A systematic elimination of defect cases is presented to define the core scope that handles all the possible quality issues and their solutions with fewer rules. Proposed soft computing solutions are implemented in a well-known international wiring device manufacturing plant together with a project team of setup experts and production staff. The results show that both FIS and MLNN could generate correct defect resolution actions on injection parameters.
Solving assembly line balancing problem with positional constraints and worker assignments using mathematical programming and heuristic solution approaches
There are many studies in the literature on assembly line balancing (ALB) problems. The ALB problems differ from each other in various aspects. In this thesis, we consider the ALB problem with hierarchical worker assignment, positional constraints, station paralleling options, and task assignment restrictions. The objective of this ALB problem is to decide on the number of parallel stations to be opened in each work stage and to assign tasks and workers to stations such that the sum of station opening costs and worker costs is minimized. To solve this problem, we initially propose an integer programming (IP) model, and then develop a simulated annealing (SA) algorithm to obtain high-quality solutions in reasonable computational times. For the SA algorithm firstly, a modified version of the Rank Positional Weight heuristic is developed to generate an initial solution. To generate new different solutions from the current solution, four kinds of neighborhood search structures are used which are single_transfer, two_transfer, swap and stage separation. In order to enhance the solution quality of SA algorithm, it is hybridized with a local search. We use a giant leap procedure to investigate an inferior or unvisited search space for the probability of finding a better solution. To find the optimal parameters of the SA algorithm, we employ the Taguchi method. Thus, the solution quality and the running time of the SA algorithm improve. A set of test problems are solved using both the proposed IP model and SA algorithm. The computational results show the effectiveness of SA algorithm.
Development of a decision support tool for analytic customer relationship management integrating data mining and multi criteria decision making methods
In recent years, there is an enormous interest in sharing a wide range of experiences and opinions regarding various products and services in blogs, social media platforms and websites specialized on customer reviews. The customer reviews derived from those platforms involve valuable information for potential customers, who might read and evaluate the comments of experienced customers before making a purchase decision on a specific product or service. Furthermore, the companies may measure customer satisfaction regarding to their products or services through online customer reviews and use this information in customer relationship management applications. In this thesis, a decision support tool, which can be used by potential customers and companies, is developed to measure and evaluate the customer satisfaction level on a specific product or service and to enable potential customers ranking the products/services according to this evaluation. The decision support system mainly consists of two phases. In the first phase, sentiment analysis is employed to convert the online customer reviews into customer satisfaction scores. In the second phase, the alternatives are ranked by using a novel multi criteria decision making (MCDM) methodology according to the performance scores obtained in the first level. The MCDM methodology developed in the second phase integrates intuitionistic fuzzy (IF) ELECTRE and VIKOR methods in a novel way. The system utilizes intuitionistic fuzzy sets (IFSs) to effectively represent the customer reviews including hesitant expressions in decision matrix. The applicability of the developed decision support system is explored by a case study, in which customer reviews about hotel experiences are evaluated using lexicon based sentiment analysis and alternative hotels are ranked according to the findings from the sentiment analysis by the IF ELECTRE integrated with VIKOR methodology.
İzmir'de bir hastanenin acil servis departmanı için bir simülasyon optimizasyonu çalışması
The long waiting times of patients and congestion are the most important problems of emergency departments (EDs) in the hospitals. In this thesis, for an ED of a hospital in İzmir, the aim is to find the optimal allocation of resources while minimizing the average overall flow time of patients (length of stay) and keeping the utilization ratios of doctors and nurses at the target levels. First of all, the simulation model of the ED is developed to evaluate the current system performance. Secondly, the data obtained from the simulation model is used in Nested Box-Behnken Design for building metamodels. Lastly, Derringer-Suich multi response optimization procedure is applied to minimize average overall flow time of patients and to keep utilization ratios of doctors and nurses at target levels. This study will provide help for healthcare decision makers to find the optimal configuration of resources in ED while considering to satisfy multi objectives simultaneously.
Applications of operations research techniques for operational decisions in healthcare industry
This thesis addresses two common scheduling problems that are encountered in the health care industry, the patient admission scheduling (PAS) problem and nurse rostering problem (NRP). The PAS automatically assigns elective patients to beds for the duration of their stays considering medical needs and preferences. Both static and dynamic versions are studied in this dissertation. For the static version where patient admissions are known in advance, a mixed integer programming (MIP) based heuristics are proposed. The problem is decomposed into a set of smaller problems and iteratively solved. A similar approach is also proposed for the dynamic version which several real life applications such as existence of the emergency patients, operating room constraints, and patient delays are additionally considered. The approach on the PAS generates schedules within fifteen percent gaps from best known solutions in faster times. The DPAS solution reports six new best-known solutions on test data. The last problem in the thesis, NRP, is a complex scheduling problem in which nurses must be assigned to shifts according to a set of constraints. Two variants of the problem are studied. While one of the versions deals with common constraints such as shift requests and cover needs, the other version extends the previous one with skills and departmental assignments. The standard version is solved via a hybrid of MIP-based heuristics and meta-heuristics approaches to provide powerful schedules. A mat-heuristic algorithm is proposed for the extended version. Computational experiments show that the hybrid algorithm obtains seven new best-known results and the mat-heuristic approach reports six new best-known solutions on instances when a stand-alone IP solver is not able to provide schedules.
Optimization for supply chain management-SCM using vehicle routing problem-VRP and an application in FMCG industry
Distribution management is an operational level activity for supply chain management.The most important model in distribution management is the vehicle routing problem. Avehicle routing problem involves determining for each vehicle, which of the customerswill be visited and what route will be followed so that the total delivery cost isminimised. In today?s business environment, the task of optimal routing a fleet ofvehicles is becoming an obvious necessity.FMCG is an acronym for Fast Moving Consumer Goods, means `things you buy on aregular basis at places like your local supermarket?. In the FMCG industry on any givenday, many delivery drivers or route sales representatives are on the road makingdeliveries to the customers. Vehicle routing in this industry is a very large problem anddifficult to solve manually.In this thesis we do a vehicle routing application in FMCG industry. Territory Planner isused to optimize the delivery routes.
Productivity improvement application in an automotive company
The specific topics covered in this study are on two main issues: time study and productivity in manufacturing industry. It is clear that the current productivity measure of the system must be defined at first in order to improve the productivity of any manufacturing system. There are several methods that have been used to measure the work, but only one of them can present observer the actual values: time study. Due to this, time study is selected as a way to measure the current and proposed production system among four formal work measurement techniques- predetermined time standards, standard elemental times, work sampling and stop-watch time study- By using the intuitional approach, current production system is analyzed and a new production system, which provides higher productivity, is proposed. The results are used to define the cycle times of the two production systems, and consequently the partial productivity is defined in terms of pieces produced by a worker per day.
Target costing and new product design in a manufacturing company
Increased competition and increased costs of designing made it important for the firms to identify the right products and the right methods for manufacturing the products. Firms should focus on customers and identify customer demands directly to design the right products. Several management methods and techniques that are currently available improve one or more functions or processes in an industry and do not take the complete product life cycle into consideration.On the other hand target costing is a method / philosophy that takes financial, manufacturing and customer aspects into consideration during designing phase and helps firms in making product design decisions to increase the profit / value of the company. It uses various techniques to identify customer demands, to decrease costs of manufacturing and finally to achieve strategic goals. Target Costing forms an integral part of total product design / redesign based on strategic plans. The current report details the process of target costing along with some associated techniques and applies the process to the designing of the DEKORPAN Towel Radiators.
Joint optimization of spare parts inventory and maintenance policies using hybrid genetic algorithms
In general, the maintenance and spare parts inventory policies are treated either separately or sequentially in industry. Since the stock level of spare parts is often dependent on the maintenance policies, it is a better practice to deal with these problems simultaneously. In this study, a simulation optimization approach using hybrid genetic algorithms (HGA) has been proposed for the joint optimization of preventive maintenance and spare provisioning policies of a manufacturing system operating in automotive sector. The HGA is formed using the probabilistic acceptance rule of the Simulated Annealing (SA) within the Genetic Algorithm (GA) framework. The cost function is evaluated by integrating the GA with a simulation model of the motor block manufacturing line, which represents the manufacturing system behaviour with its maintenance, and inventory related aspects. Next, to further improve the performance of the GA developed, a set of experiments has been performed to identify appropriate values for the GA parameters (i.e. the size of the population, the crossover probability, and the mutation probability). Finally, various comparative experiments have been carried out to evaluate performance of both the pure GA and HGA.
An application of activity based costing as a decision tool
Hard competition in today?s trade conditions in all markets all around the world, make companies to analyze their profitability frequently. In this hard competition, all companies firstly try to protect their profitability and than try to get more profit from their business, without loosing any market share. Nowadays, managers see the reality that financial numbers are the results and can not be managed directly. To remain competitive in the market, activities and processes must be managed and improved. The best way of managing and improving business starts with analyzing the current situation. For this reason, different techniques started to be used for analyzing profitability. By the help of these techniques, continuous improvement get started to be used in today?s management mentality. In this study, one of the commonly used profitability analyzing tool and decision making tool called Activity Based Costing will be explained with model studies and real studies. Information about Activity Based Costing method and other costing methods will be given. In addition, an alternative method will be used to compare the results and to make a better decision. The aim of doing this study is to analyze the profitability of a worldwide company?s all customers for whole year activity. By the help of this analysis decisions will be taken to improve profitability and to improve the business of the company, without loosing any market share. Keywords: Activity Based Costing, Activity Based Management, Cost Management, Traditional Cost Management, Modern Cost Management, Direct Costing.
Fuzzy analytic hierarchy based approach for supplier selection in a washing machine company
Supplier selection is one of the most important decision making problems which includes both qualitative and quantitative factors which may conflict with each other. The objective of a supplier selection problem is to identify suppliers with the highest potential for meeting a firm?s needs consistently and at an acceptable cost. In this study, supplier selection problem of a washing machine company in Manisa is investigated and a fuzzy analytic hierarchy process based methodology is used to select the best supplier firm providing the most customer satisfaction for the criteria determined. The study is carried out in three phases: In the first phase, the main attributes and sub-attributes for supplier selection are defined to design the hierarchy structure. The main attributes, which are supplier, product performance and service performance, are determined based on literature survey and the experience of the expert. In the second phase, the weights of the main attributes, sub-attributes and alternatives are calculated. Linguistic variables and triangular fuzzy numbers are used for the preferences of one criterion over another in making pair-wise comparisons. In the last phase, the priority weights for main attributes, sub-attributes and alternatives are combined to determine the priority weights of the three alternative suppliers. The supplier with the highest priority weight is selected as the best supplier. Macros in Excel are used to calculate the priority weights of the alternatives based on the questionnaire forms used to facilitate comparisons of main attributes, subattributes and alternatives.
Multi-period, multi-product aggregate planning model in an industrial firm
This study is about modeling the long-term planning system of an industrial firm and implementation of this aggregate planning model. Planning activities are vital for a firm that desires to be competitive in modern industrial conditions. The most productive use of inputs to make the desired output is necessary to minimize the total cost and achieve the maximum profit. Long term decisions about input variables of a firm can be given by aggregate plans that reflect the real systems. This study is written with the aim of finding the best model of aggregate planning activity in an industrial firm. Firstly, planning activity in general and aggregate planning procedure in detail are studied. Then, the most common aggregate planning techniques and necessary input data like costs relevant with aggregate planning or issues of forecasting the demand are considered. Lastly, implementation of one of these aggregate planning techniques that is most convenient for the firm is considered for the planning system of the industrial firm and the models are solved in a linear programming language to find the objective function that is minimizing the total cost of the industrial system.
Neural network based optimization in production scheduling
Although a large number of approaches such as mathematical programming, dispatching rules, expert systems, and neighborhood search to the modeling and solution of scheduling problems have been reported in the literature, over the last decade, there has been an explosion of interest in using artificial neural networks (ANNs) for the solution of various scheduling problems. The objective of this research is to utilize ANNs to deal with two different scheduling problems. The first problem considered is the classical identical parallel machine scheduling problem with makespan minimization. A dynamical gradient type neural network, which employs a penalty function approach with time varying coefficients, is proposed for the solution of the problem. Simulation outcomes of the proposed approach are compared with those of the longest processing time rule and with the optimal solutions, for different sizes of scheduling problems. The second problem is the scheduling of an independent jobs set with sequence-dependent setups and distinct due dates on nonidentical multi-machines to minimize the total weighted earliness and tardiness. The original mixed integer formulation of the problem is modified by adding one more constraint to the model to prevent the assignment of two jobs at the same time to the first position. For this problem, an interconnected neural network model which is composed of two maximum, three piecewise linear and one log-sigmoid neural networks is proposed. The proposed approach is tested on a scheduling problem and the results are compared with optimum results of the linear programming solver.
Evaluating transport potential of turkey in relationship with European Union and a model suggestion for a modal shift from roads to railways
On account of Turkey?s geopolitics importance, there has a relation between Europe and Asia like a bridge. In this perspective, we evaluate the transport potential of Turkey in the view of accession to European Union in this study. We also evaluate road and railway developments in European Union and Turkey. The main purpose of this study is to forecast the level of road freight transport up to the year of 2015 in order to investigate the modal shift from road transport to railway transport. The aim of forecast is to analyze the development of increasing road freight transport in Turkey. Forecasting is based on Multiple Regression Analysis and Trend Analysis using annual data of the level of road freight transport from the year 1983 to 2004 and factors which are considered to affect the road freight transport in Turkey. Moreover, the existence of statistical relationships of these factors between each other and with road freight transport will be investigated. The statistical program MINITAB 14 is used to do this.
Strategic and tactical planning in collaborative supply chains: Fuzzy modeling approach
Strategic and tactical planning in collaborative supply chain systems are dealt with in this dissertation. In this concern, two important supply chain planning problems; distribution network design and integrated production-distribution problems are focused on, and fuzzy multi-objective linear programming models are developed to address these problems. Because of the uncertain nature of the parameters and decision makers? aspiration levels for the goals, fuzzy modeling approaches are employed in the models. An interactive fuzzy goal programming based solution approach is also proposed in this dissertation and applied to the models developed. In order to confirm the viability of the proposed solution approach and the models developed, numerical examples are presented. Solutions of the models are performed using several different fuzzy multi-objective modeling approaches along with the proposed approach, and the results are compared. Results of the computational experiments point out that distribution network design and integrated production-distribution problems in supply chains can be handled in a more flexible, robust and realistic way through the proposed solution approach. Interactive nature of the proposed approach provides the learning process about the system. Furthermore, the decision maker controls the search direction during the solution procedure and, as a result, the efficient solution is obtained based on decision maker?s preferences. Results of the computational experiments also confirm our assertion that fuzzy multi-objective modeling approaches can effectively be used in centralized and decentralized supply chain structures, and in strategic and tactical decision levels to the aim of providing more realistic and efficient collaborative supply chain models.
Vehicle scheduling problem with sequence dependent trips
In this study, we consider a vehicle scheduling problem with sequence dependent trip times. The problem is assigning vehicles to a set of trips with fixed ready times and deadlines, while minimizing cost. The trip time for a vehicle between any two places is also known deterministically. A number of different types of vehicles are available for transportation, each with different capacities, fixed and variable costs. The costs for regular and overtime utilization also vary for different types of vehicles. The problem resembles the Tactical Fixed Job Scheduling Problem where ready times and deadlines of jobs are known in advance, and the objective is to minimize the cost of machines to perform all the jobs. A job cannot be processed unless a machine is available at its ready time. The problem is formulated as an Integer Programming Model. A spread time constraint determines the regular time usage of the vehicles. The formulation is coded in LINGO 8.0 and GAMS 20.2 with CPLEX solver. Due to the complex nature of the problem, it is observed that the optimal solution of even middle-size instances is very time consuming. Hence, we develop three different heuristic approaches for the problem, each one having two different types based on overtime usage allowances. The algorithms are coded in C programmer Language using DEV C++ Compiler. The average behaviour of the algorithms is investigated through computational experiments. Lower bound values for the problem are found using GAMS developing some approaches, and the performances of the algorithms are compared based on these bounds. The problems whose number of trip is more than a hundred have been solved in a very short time. The least solution of heuristic approaches is actually 10% greater than optimum solution. Key Words: Tactical Fixed Job Scheduling, Spread Time Constraints, Integer Programming, Heuristics.
An application of multi-objective aggregate production planning in a consumer electronics manufacturing company
Aggregate Production Planning is a planning technique that can be used to determine the optimum levels of the production rate, workforce levels and inventory. This thesis presents an application of aggregate production planning for television manufacturing company with multiple objectives. The mathematical models are constructed by using multiple objective decision making methods in order to determine the production rates for each products in each periods, inventory levels, backorder level, workforce levels and hiring and lay-off levels in each final assembly lines. Four different models had been developed by using both techniques called Goal Programming and Sequential Multi-objective Linear Programming. In order to generate the solutions LINGO 8.0 software was used. Consequently, after obtaining the results, proposed models were compared to each other.
Improvement of material requirements planning processes by using problem solving technique: A case in the automotive sector
In today?s competitive markets, firms have to change their products, production systems, processes and themselves continuously in order to survive. By changing and improving these factors, cost, time and effort savings are obtained. The aim of this study is to improve material requirements planning processes of a firm in an automotive industry by using Problem Solving Technique. In the direction of this aim, packaging material requirements planning procedure was improved by passing from classic consumption based planning to requirement planning. Process improvement, Pagos database and specifications, material requirements planning and SAP R/3 were observed in the research stage. At the same time, actual material planning processes and problem of the firm were examined in SAP - Pagos pool. After researching these main subjects, the most convenient improvement type, flow diagram and project management tool that would minimize labor were determined. Pagos database that packaging bill of materials stored was actualized and synchronized with SAP R/3 MM module. By following project management tool MS Project, MRP processes of packaging were improved.
Financial restructuring and determination of a firm value including privatization process
The aim of this thesis is to attempt to address privatization procedure needs by drawing on the literature learned and insights gained from a wide diversity of country backgrounds and privatization experiences including restructuring and value assessment. That process provides a constructive and pragmatic dialogue on the key aspects of privatization and benefitted from a wealth of country presentations, as well as technical papers prepared by experts. Analytical hierarchy process is used in order to find ratio of the selected evaluations. Then I can evaluate value of the company. Consequently, governments have to prove its commitment to open the economy to private economy activity by reducing public sector involvement. A wide ranging privatization program which is legally and institutionally equipped to efficiently and effectively transfer ownership in state-owned enterprises to private entrepreneurs has to be established.
Design of manufacturing cells for uncertain production requirements
Cellular manufacturing has been seen as an effective strategy to the changing worldwide competition. Most of the existing cell design methods ignore the existence of stochastic production requirements and routing flexibility. In this study, a simulation based Fuzzy Goal Programming model is proposed for solving cell formation problems considering stochastic production requirements and routing flexibility. The model covers the objectives of minimizing the number of exceptional elements, maximizing system utilization, minimizing mean tardiness and minimizing the percentage of tardy jobs. The simple additive method and max-min method are used to handle fuzzy goals. A tabu search based solution methodology is used for solution of the proposed models and the results are presented.
Project management based production improvement; Hold list management by using ERP system
The consumer electronics industry is one of the most competitive sectors in the world. To stay ahead of competitors, companies must constantly move into new markets emerging around the world. Meanwhile, to keep pace with consumer demand for exciting products at attractive prices, manufacturers must take full advantage of low-cost studies. The main difficulty for low cost studies is the lost time and manpower because of the problems which have not defined priorities. The aim of this thesis is to implement an automatic hold list program to define the priorities of the problems. In the direction of this aim, a module has been created in SAP which is the one of the biggest Enterprises Resource Planning Program in the world and illustrated with a case study in the one of the biggest electronics company of Turkey. Furthermore, the propositions about the future of the program are given.
Multi-criteria based novel strategic sourcing methodologies
Supplier selection is one of the most vital actions of companies in a supply chain. With the recent trend in JIT philosophy, there is an emphasis on strategic sourcing that establishes long-term relationship suppliers. Strategic sourcing decisions not only include the evaluation and selection of the potential strategic suppliers but also deal with developing the long-term strategic partnership with these suppliers, increasing the supplier performance via supplier development programs and providing continuous feedback to them. This research presents two methodologies for strategic sourcing problems. The first methodology helps the decision maker to classify suppliers into different categories, identify the differences in performances across supplier classes and monitor the suppliers? performances. The proposed methodology offers to use a multi-criteria sorting (MCS) procedure to determine supplier classes and reduce the number of suppliers. This research also proposes a new MCS methodology, which is named as PROMSORT. In this dissertation, another focus is placed on developing a fuzzy MCS methodology. Secondly, this dissertation presents an integrated multi-criteria decision making methodology for strategic sourcing. The proposed methodology introduces an interactive fuzzy goal programming model for the order allocation problem. In order to demonstrate the applicability of the proposed methodologies for the strategic supplier selection and order allocation problem, numerical strategic sourcing problems are presented. The results of the computational experiments indicate that the proposed methodologies are useful tools for firms to select the strategic partners, manage their supplier base and allocate the orders to the most appropriate suppliers.
Solving simple and mixed-model assembly line balancing problems using hybrid meta-heuristic approaches
Application of q-learning algorithm to bicriteria dynamic scheduling problem
Most of research in manufacturing scheduling is concerned with the minimization of a single criterion. However, scheduling problems often involve more than one objective and therefore require multi criteria analysis. This thesis deals with bicriteria dynamic scheduling problems. The main purpose of this study is to find out a compromising solution for the system objectives. The Q-learning algorithm, an agent based approach, is proposed to find a good schedule for the systems. The proposed methodology consists of three phases. In the first phase, selected dispatching rules are performed on the system under different conditions for both of the objectives. In the second phase, learning potential of the Q-agent is investigated. In the third phase, Q-learning agent is trained to minimize the system objectives on dynamic scheduling problem. Dispatching rules which are involved in the learning process are determined according to results in the first phase. In this thesis, bicriteria dynamic scheduling problem is investigated on a single machine and a flow shop separately. Furthermore, the performance of the Q-learning agent is evaluated and compared to other dispatching rules by using a new ranking method which is also presented in this thesis. Keywords: Reinforcement learning
Benchmarking and quality improvement -an application of quality function deployment in a firm-
Nowadays, it is nearly getting necessary to adopt fast growing industrial developments and demands for the companies in manufacturing or service market. In order to stay in competitive market, the companies try new approaches and put the successful ones into application. One of the widely used approaches is, today, Quality Function Deployment (QFD). In this study, the basic steps of Quality Function Deployment approach is presented. Also an example of application of QFD to a television manufacturing company is given as a project. Therefore, this research attempts to build the benchmarking from the ?voice? of the customer. The comprehensive methodology I propose here is called the quality benchmarking deployment (QBD) technique. The case study findings demonstrated that QFD could be successfully applied in combo CRT television projects as a strategic tool to facilitate marketing and manufacturing decisions. As a result of extensive literature review and the case study observations; this study also points out the limitations and breakthroughs of the QFD methodology. Finally, critical success factors are proposed to improve the performance of the QFD methodology in projects. Keywords: Benchmarking, Competitive Benchmarking, Quality Function Deployment, Quality Improvement, Voice of Customer, Customer Satisfaction, Analytic Hierarchy Process
Finite capacity planning in MRP systems; problems and issues
MRP-MRPII systems at production planning and control and implementations in a packaging company
Good customer service begins with a high quality manufacturing process. Software that tracks the production system cycle enables management to control the product. One such software, Material Requirements Planning (MRP) provides complete scheduling capability of addressing a wide range of production scenarios. MRP became popular in the 1970s. It automated the production line. MRPII, the second generation, coordinates all the resources involved in making a product, including projected sales, personnel, plant capacity and distribution. MRPII offers management a tool that covers personnel, equipment, material, facilities and customer requirements. These entire features contribute to the success of manufacturing a high quality product. In this study, firstly some general information about MRP and MRPII systems have been given, and then, in a packaging company (BARAN AMABALAJ A.S.), implementation steps and implementation results of MRPII software package MFG/PRO which is created by QAD, have been analyzed. Then material requirements plans for selected items are created by using data of a company.