Strategic framework for anfis and bim use on risk management at natural gas pipeline project

Risk management and assessment is a multi-criteria decision-making problem involving various factors, according to literature research and expert opinions. In order to establish effective models and resolve the relationship between these criteria's; Researchers and Academics have presented a wide range of methods or models in the literature. In order to overcome the most strategic issue that affects the project performance scales, such as Risk Management, the most appropriate method and criterion selection is required. Risk management and assessments of industrial facility works in the world and in Turkey are far away from the desired level. In general, the risk score is evaluated over the decision matrix, which is one of the traditional methods, and reduction or mitigation plans apply accordingly. In this study; In the TANAP project, which is called the Mega project around the world, a model has been presented through risk management and assessment. The model offered is; A case study conducted using the multi-criteria Adaptive Neuro Fuzzy Inference System (ANFIS), which provides the rating of 104 recorded risk types covering the design and construction processes. Combining the structures and advantages of adaptive networks with fuzzy inference methodology has shown that a more comprehensive and effective risk management and assessment made. It has been shown with Root mean square error (RMSE) and Mean Absolute Percentage Error (MAPE) performance indicators that it gives better results in artificial intelligence supported risk management or assessment created with Adaptive Neuro Fuzzy Inference System. In the last stage of the study; Risks that defined by omni-class classes transferred to 3D visuals with color and linguistic expressions in order to increase visualization and information sharing with the help of BIM Navisworks/Dynamo software, and Risk maps created and the study concluded. The main contribution of this study; is the approach of artificial intelligence to evaluate and rate the risk correctly with hybrid learning method and then to obtain risk maps by integrating them into BIM as visual and linguistic term expressions. The practical significance of this study; the proposed approach enables the development of Artificial intelligence based Adaptive Neuro Fuzzy Inference System v (ANFIS) and BIM-based risk management software to improve risk identification, analysis and management during the project development and construction process. This research provides evidence that traditional techniques can be aligned with ANFIS and BIM for risk management. A key advantage of the proposed method is that it combines the benefits of ANFIS and BIM for lifecycle project risk management and has minimum disruption to existing work processes and maximum performance impact.