This paper presents a fault detection method based on locally linear embedding (LLE) for the high-speed train traction systems. The method maps high-dimensional complex data into low-dimensional data, analyzes the spatial characteristics of these data within their local neighborhoods, and achieves overall system state monitoring and fault prediction. The paper provides a detailed introduction to the theoretical foundation of LLE fault detection, including techniques such as local linear embedding, fault feature extraction, and analysis, and discusses the roles of these techniques in practical applications. Through the construction of simulation models and experimental data, the effectiveness and robustness of the proposed method are verified.
This paper proposes a hierarchical path-planning algorithm based on a combination of graphical search algorithms and optimization methods. In the global path planning layer, by using the Hybrid A* algorithm, we can quickly obtain an optimal path that can avoid all static obstacles on the map. In the local path planning layer, the global path is optimized by numerical nonlinear numerical optimization to generate a feasible path that satisfies the safety constraints. By processing global path planning and local path planning separately, the computational complexity of path planning can be effectively reduced, and the efficiency and accuracy of the path planning can be improved. Secondly, the hybrid planning algorithm can generate high-quality paths with both safety and flexibility. We simulate and verify the algorithm, and the results show that the method has practical applications in autonomous driving.
KEYWORDS: Principal component analysis, Neural networks, Convolutional neural networks, Detection and tracking algorithms, Mathematical modeling, Sensors, Data processing, Control systems, Data modeling
Traction systems provide the traction power of high-speed trains. Because the complex operation mechanism of train under actual working conditions and the measured data are nonlinear and non-Gaussian, and the sampling frequency of the sensor is high in actual working conditions. Directly using a neural network or the multivariate statistical method is challenging to obtain the ideal fault detection (FD) result. Therefore, this paper proposes a data-driven method based on broad learning system (BLS) and convolutional neural network (CNN) assisted principal component analysis (PCA). Two neural networks are used to enhance the robustness of the algorithm, so that the proposed method has better fault detection ability in nonlinear and non-Gaussian systems. The advantage of this method is that it does not require the establishment of a complex high-speed train data model. Instead, by processing the collected data, the proposed algorithm can ensure good fault detection capabilities. Finally, the effectiveness and feasibility of the proposed method are verified on the simulation platform of traction drive control system (TDCS).
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.