Fault Diagnosis of a Switch Machine to Prevent High-Speed Railway Accidents Combining Bi-Directional Long Short-Term Memory with the Multiple Learning Classification Based on Associations Model

Abstract

The fault diagnosis of a switch machine is vital for high-speed railway operations because switch machines play an important role in the safe operation of high-speed railways, which often have faults because of their complicated working conditions. To improve the accuracy of turnout fault diagnosis for high-speed railways and prevent accidents from occurring, a combination of bi-directional long short-term memory (BiLSTM) with the multiple learning classification based on associations (MLCBA) model using the operation and maintenance text data of switch machines is proposed in this research. Due to the small probability of faults for a switch machine, it is difficult to form a diagnosis with the small amount of sample data, and more fault text features can be extracted with feedforward in a BiLSTM model. Then, the high-quality rules of the text data can be acquired by replacing the SoftMax classification with MLCBA in the output of the BiLSTM model. In this way, the identification of switch machine faults in a high-speed railway can be realized, and the experimental results show that the Accuracy and Recall of the fault diagnosis can reach 95.66% and 96.29%, respectively, as shown in the analysis of the ZYJ7 turnout fault text data of a Chinese railway bureau from five recent years. Therefore, the combined BiLSTM and MLCBA model can not only realize the accurate diagnosis of small-probability turnout faults but can also prevent high-speed railway accidents from occurring and ensure the safe operation of high-speed railways.

Fault Diagnosis Method for Railway Signal Equipment Based on Data Enhancement and an Improved Attention Mechanism

“…Shang [22] introduced long short-term memory (LSTM) and a BP neural network into a vehicle equipment fault diagnosis model, where LSTM learned the temporal characteristic information from the vehicle equipment fault text data while a Bayesian regularization (BR) algorithm optimized the generalization ability of the BP neural network model for completing the learning process with fault data samples and achieving unknown sample-based fault type diagnosis. Drawing upon bidirectional long short-term memory's (BiLSTM) advantages in extracting temporal features from fault text, Lin [23] constructed a railway switch fault diagnosis model by combining BiLSTM with a model based on correlation (MLCBA), thereby enabling intelligent diagnosis of switch faults.…”

“…Firstly, considering that h n encompasses feature information in both positive and negative directions, the output h ′ n of the BiLSTM layer is derived by aggregating h n based on Equation (23):…”

Improved Oversampling Algorithm for Imbalanced Data Based on K-Nearest Neighbor and Interpolation Process Optimization

“…If the nearest neighbor sample y ij corresponding to the "Danger" sample x i also belongs to "Danger", the new sample will be synthesized by interpolation using (3).…”

“…However, it is often the case that minority class samples contain crucial information. For example, in the monitoring and maintenance of railway signal equipment, the fault of the equipment belongs to a minority of events, but if the fault prediction and judgment are misjudged as no fault, the best maintenance time may be missed, resulting in significant personnel and property losses [3].…”