This paper presents a multi-processor hardware-in-the-loop (HIL) fault injection strategy for real time simulation of faults in traction control system (TCS). TCS models are solved for the implementation in CPU and Field-programmable gate array (FPGA). A timing optimization method based on static timing analysis (STA) is proposed to deal with timing error induced by real time fault injection. A multi-processor based HIL platform is constructed, and the pipeline of fault injection unit (FIU) is designed for the proposed platform. The HIL experimental results validate the effectiveness and applicability of the proposed strategy.

Long-term operation may lead to performance degradation of the traction drive systems. It will naturally increase the difficulty of fault detection (FD). To ensure the safe and stable operation of the traction drive system, datadriven FD has received considerable attention, especially deep learning methods. By exploiting the idea of transfer learning, this paper proposes a new FD method for traction converter faults in traction drive systems of high-speed trains. Its structure consists of a federal neural network based on a variational auto-encoder (VAE). The significant advantages of the proposed FD method based on transfer learning are summarized as follows: (1) FD is still valid for the systems with performance degradation. (2) It can also realize the FD function even if the physical model and related parameters are not provided. (3) The proposed framework can adaptively adjust the model parameters by storing and reusing the prior knowledge in the neural network. Finally, the effectiveness of proposed method is demonstrated through the platform of traction drive control system (TDCS).

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.

The efficient fault detection (FD) of traction control systems (TCSs) is crucial for ensuring the safe operation of high-speed trains. Transient faults (TFs) can arise due to prolonged operation and harsh environmental conditions, often being masked by background noise, particularly during dynamic operating conditions. Moreover, acquiring a sufficient number of samples across the entire scenario presents a challenging task, resulting in imbalanced data for FD. To address these limitations, an unsupervised transfer learning (TL) method via federated Cycle-Flow adversarial networks (CFANs) is proposed to effectively detect TFs under various operating conditions. Firstly, a CFAN is specifically designed for extracting latent features and reconstructing data in the source domain. Subsequently, a transfer learning framework employing federated CFANs collectively adjusts the modified knowledge resulting from domain alterations. Finally, the designed federated CFANs execute transient FD by constructing residuals in the target domain. The efficacy of the proposed methodology is demonstrated through comparative experiments.

Diagnosing compound faults in electric traction systems (ETS) is challenging due to scarce labeled data, which renders standard supervised learning ineffective for unseen faults. Additionally, signal degradation caused by noise and complex pattern coupling further impede identification. To address these challenges, this paper proposes a zero-shot attribute transfer framework (ZSATF) for compound fault diagnosis without training examples of the target fault categories, in which attributes serve as a knowledge bridge between seen and unseen faults. Specifically, a temporal multi-resolution diffusion (TMrD) network is first introduced to reconstruct clean signals from noisy environments. Subsequently, an attribute refiner enhances the representation and inter-attribute relationships of fault patterns. Finally, an attribute-guided feature alignment (AgFA) module projects signal features into the refined attribute space, enabling the identification of unseen compound faults by matching features with attribute-based definitions. Experimental results on CRH2 traction data demonstrate that ZSATF outperforms existing fault diagnosis methods.