Abstract
Electrical drive systems are the core of high-speed trains, providing energy transmission from electric power to traction force. Therefore, their safety and reliability topics are always active in practice. Among the current research, fault injection (FI) and fault diagnosis (FD) are representative techniques, where FI is an important way to recur faults, and FD ensures the recurring faults can be successfully detected as soon as possible. In this paper, a tutorial on a hardware-implemented (HIL) platform that blends FI and FD techniques is given for electrical drive systems of high-speed trains. The main contributions of this work are fourfold: (1) An HIL platform is elaborated for realistic simulation of faults, which provides the test and verification environment for FD tasks. (2) Basics of both the static and dynamic FD methods are reviewed, whose purpose is to guide the engineers and researchers. (3) Multiple performance indexes are defined for comprehensively evaluating the FD approaches from the application viewpoints. (4) It is an integrated platform making the FI and FD work together. Finally, a summary of FD research based on the HIL platform is made.
Highlights
Over the past five decades, the rapid development of high-speed trains relying on multiple electrical traction units has been witnessed [1,2,3]
An acceptable trade off between missing alarm ratios (MARs) and false alarm ratios (FARs) should be at least achieved for FDD in traction systems of high-speed trains
When a fault fi(k) appears in electrical drive systems, unexpected deviations will be reflected in z such that z f (k) = z(k) + Ωi fi(k) where k represents the sampling step, Ωi is the matrix signifying the fault direction, fi describes the deviational magnitude caused by fi and the subscript “ f ” means different faulty conditions [24]
Summary
Over the past five decades, the rapid development of high-speed trains relying on multiple electrical traction units has been witnessed [1,2,3]. The software-based method is targeted to applications in operating systems, and it cannot inject faults into the inaccessible location of software Unlike the former two methods, the detailed simulation model is crucial for the emulation-based method, which leads to a maximum amount of observability and controllability, whereas model development is time-consuming and inaccurate. The current FD methods for electrical drive systems of high-speed trains can be definitely divided into three categories: signal analysis-based, model-based and data-driven methods [5,19]. Data-driven FD methods for electrical drive systems of high-speed trains have been intensively developed and widely accepted because of their simplicity of design and ease of implementation [24].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
