A Review of Intelligent Fault Diagnosis for High-Speed Trains: Qualitative Approaches

Abstract

For ensuring the safety and reliability of high-speed trains, fault diagnosis (FD) technique plays an important role. Benefiting from the rapid developments of artificial intelligence, intelligent FD (IFD) strategies have obtained much attention in the field of academics and applications, where the qualitative approach is an important branch. Therefore, this survey will present a comprehensive review of these qualitative approaches from both theoretical and practical aspects. The primary task of this paper is to review the current development of these qualitative IFD techniques and then to present some of the latest results. Another major focus of our research is to introduce the background of high-speed trains, like the composition of the core subsystems, system structure, etc., based on which it becomes convenient for researchers to extract the diagnostic knowledge of high-speed trains, where the purpose is to understand how to use these types of knowledge. By reasonable utilization of the knowledge, it is hopeful to address various challenges caused by the coupling among subsystems of high-speed trains. Furthermore, future research trends for qualitative IFD approaches are also presented.

Condition Assessment of Industrial Gas Turbine Compressor Using a Drift Soft Sensor Based in Autoencoder

“…The way decisions are nowadays made in the industry is changing thanks to increasing data availability [19] and the development of intelligent tools for condition and fault assessment [20]. In commercial industrial gas turbines, data are captured by several sensors located along the machine and are then sent back to the engineering office where they are analyzed and processed to diagnose any unexpected event.…”

Subway Gearbox Fault Diagnosis Algorithm Based on Adaptive Spline Impact Suppression

“…This algorithm is superior to the traditional VMD method and further extends the application of VMD for compound fault diagnosis. Many scholars have also applied neural networks for fault diagnosis [ 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 ], and the improved algorithms have shown good results. In addition, there are also many decomposition methods based on signal processing, including local mean decomposition [ 36 , 37 , 38 , 39 , 40 ], Fourier decomposition [ 41 ], and other methods, which are widely used in gearbox fault diagnosis.…”

Gearbox Failure Diagnosis Using a Multisensor Data-Fusion Machine-Learning-Based Approach

“…Several relevant proposals were recently published to design increasingly reliable monitoring systems [21] thanks to new signal-processing techniques such as linear prediction coefficients (LPC), mel-frequency cepstral coefficients (MFCC), and machine learning. Meiying et al [16] proposed to combine a CNN and LSTM for health assessment and failure diagnosis.…”