A new acceptance sampling approach for incoming inspection: An application in the white good industry

Companies are looking for ways for gaining competitive advantage with regard to customer expectations in globalizing world. Customers expect companies to provide qualified and economic goods or service. Due to this reason companies focus on the quality improvement. Quality is essential for customer satisfaction which eventually leads to customer loyalty. Customers can easily share both favorable opinions and criticism of your product quality on social sites. Therefore quality products make an important contribution to long-term revenue and profitability. Effective quality improvement can be instrumental in increasing productivity and reducing cost. Poor quality increases costs. If a company does not have an effective quality control system in place, company has to incur cost of analyzing nonconforming goods or services to determine the root causes and retesting products after reworking them. In some cases, company may scrap defective products and incur additional production costs to replace them. If defective products reach customers, producer will have to pay for returns and replacements. There are two general aspects of the qualified products. First of them is stability and capability of the production line, second is the qualified supplied parts. The traditional definition of the quality is based on the that products and services must meet the requirements of those who use them however according to modern definitions quality is inversely proportional to variability. Statistical process control(SPC) is useful in achieving process stability and improving capability through the reduction of variability. Control chart, which is handled in this study detailed, is one of the primary technique of the SPC and very useful for online proces monitoring. Control charts can be classified into two general types. If the quality characteristics can be measured and expressed as a number and it is usually called a variable and control charts for this characterictics are called variable control charts. In some cases products may judge as either conforming and nonconforming and control charts for such quality characteristis are called attributes control charts. Both of them are presented in this study detailed. Process capability analysis(PCA) which refers to the uniformity is the an other important tool in applying SPC. The variability of the critical to quality characteristics in the process is the measure of the uniformity of the output. To be sure that whether the process is proper or not to meet the spesifications, capability analysis are performed after keeping process under control by control charts. Process capability analysis can be conducted by histograms, control charts and design experiments. Process capability ratio is a simple and quantative way to express process capability and also this ratio was included in the proposed acceptance sampling plan. Acceptance sampling takes place in the scope of this study to control the quality of the supplied parts. Acceptance sampling which is a procedure used for sentencing incoming batches, is useful when the cost of testing is high compared to the cost of passing a defective item or when testing is destructive. It is a compromise between doing 100% inspection and no inspection at all. Acceptance sampling can be done on attributes or measurements of the product. The aim of this study is to reduce tthe ratio of failures which was detected at production line and production losses due to supplier related quality failures and to provide the usage of the resource efficiently during incoming inspection process. New acceptance sampling plan is propesed in the scope of the study. Classification of the supplied part as critical to quality, critical to safety and noncritical materials makes different this method. Proposed plan is varied across the variables and attributes. At the first step of the proposed method, materials are evaluated according to below conditions: Is it the first shipment of materialIs there any increasing at the order of the supplier Is there any negative seasonal effect on the parts? If the parts meet the one of the above conditions, the parts are evaluated according to special sampling plan which was created based on the tightened sampling. Otherwise process flow chart is followed up in respect of material classification. Acceptance sampling for variables contains three different plans based on the material classification. Shifting rules between normal, tightened and reduced sampling plans are also different for each material class. Supplier quality performances are also included the shifting rules. Parts per million ratio is used to compare the performance of the suppliers. Acceptable quality level(AQL) is another parameter for proposed plan. Tables which are used to determine acceptable and rejectable numbers are created according to AQL. Due to the contracts between company, where the proposed sampling plan was conducted, and suppliers AQL for attributess and variables are 0,025 and 0,01 respectively for this study. Proposed plan for variables is based on the capability of supplier process and AQL. Cpk value was considered as a capability index. Process flow chart for this plan is also presented. There is not any difference for shifting rules between material classification. Proposed plan was conducted at a refrigerator factory during incoming inspection. Focussed materials were specified according to pareto chart of the rejected parts quantities of the previous year. Expert opinion was assessed to select the relevant sampling plan. Results of the proposed sampling plan was compared with the current incoming inspection procedure. Ratio of the nonconforming parts which were detected at production line was decreased sharply by proposed plan. Lot rejectios from the line and production losses were prevented because of that control operators were able to detect the serial failures during acceptance sampling. Instead of the 100% inspection of the less material type, acceptance sampling was performed for various materials. Although, this situation caused more labour cost than current procedure; due to prevention of the production losses, proposed plan became economic. As a proposal for the next studies, sampling plan can be extent for the different stage of the production line and an expert system can be created to make easier the usage of the plan.