@article { author = {Rahmanidoust, Mohammad and Zheng, Jianguo and Yazdanparast, Reza and Nematollahi, Iman and Akbari, Elahe}, title = {A real-time framework for performance optimization of safety culture in the oil and gas industry under deep uncertainty: A case study}, journal = {Journal of Industrial and Systems Engineering}, volume = {12}, number = {2}, pages = {255-282}, year = {2019}, publisher = {Iranian Institute of Industrial Engineering}, issn = {1735-8272}, eissn = {2717-3380}, doi = {}, abstract = {This study proposes a real-time framework for performance optimization of proactive safety culture in the oil and gas industry. Safety culture indicators were extracted from the literature using a comprehensive literature review. The proposed framework is based on fuzzy data envelopment analysis (FDEA), artificial neural networks (ANN), and statistical methods. It is able to evaluate the real-time performance of any safety-critical plant in the oil and gas industry and determines the current status of each indicator. The required data were collected using a questionnaire which was distributed as a self-administered survey to 210 employees in Shiraz Petrochemical Company and 174 surveys were returned with a high response rate. The application of fuzzy logic along with stochastic efficiency frontier analysis has empowered the proposed hybrid framework to deal with deep uncertainty, and result in more reliable findings. The obtained results can help safety managers to improve the proactive safety culture of the organization. They also can use the presented framework for periodic safety evaluations and determine the effectiveness of the implemented correction plans. To the best of our knowledge, this is the first study that presents a real-time framework for performance optimization of safety culture under deep uncertainty in the oil and gas industry.}, keywords = {Proactive safety culture,efficiency frontier analysis,Performance Optimization,safety-critical industry,Fuzzy Data Envelopment Analysis,Artificial Neural Networks}, url = {https://www.jise.ir/article_88445.html}, eprint = {https://www.jise.ir/article_88445_0cd7443fd5f61a8cb279aa42fb2ebef6.pdf} }