Neural network based human reliability analysis method in production systems

Nowadays, many accidents, malfunctions, and quality defects are happening in production systems due to Human Errors Probability (HEP). Human Reliability Analysis (HRA) methods have been proposed to measure the HEP based on Performance Shaping Factors (PSFs), but these methods do not have a procedure to select the effective PSFs and consider the PSFs dependency. In this paper, we propose an Artificial Neural Network based Human Reliability Analysis (ANNHRA) in cooperation with Response Surface Method (RSM). This framework uses the advantage Systematic Human Error Reduction and Prediction Approach (SHERPA) method to quantify the PSFs and the ANN and RSM to consider the PSFs dependency and select the most effective PSFs. This framework decreases the time and cost and increases the accuracy of HRA. The proposed framework has been applied to a real case and the provided results show that human reliability can be calculated more effectively using ANNHRA framework.

Keywords:

Human reliability analysis , Error Prediction , Performance shaping factors , cognitive factors