Reliability Analysis of Safety Critical Systems: A Case Study of Railway Systems.

The failure of safety‐critical systems may lead to severe risks to human lives, or critical assets. Due to this, researchers are putting their tireless efforts to detect and diagnose the faults with better accuracy to increase the reliability. Methods for fault detection and diagnosis (FDD), based on artificial intelligence, prove to be more promising, as they are capable of capturing the practical scenarios. This paper proposes an effective method for FDD, which is based on artificial intelligence. A real case study of the traction system of high‐speed trains (HSTs) is considered to show the effectiveness of the approach. The approach utilizes statistical features and an improved broad learning system to enhance fault detection and preventive measures. The proposed method aims to deliver real‐time cautionary signals and ensure safer operations in HST systems. [ABSTRACT FROM AUTHOR]