The long-short-term memory (LSTM) recurrent neural network is proposed to accomplish fault detection and identification tasks based on the commonly available measurement signals by considering the signals from multiple track circuits in a geographic area.
Abstract:
Timely detection and identification of faults in railway track circuits are crucial for the safety and availability of railway networks. In this paper, the use of the long-short-term memory (LSTM) recurrent neural network is proposed to accomplish these tasks based on the commonly available measurement signals. By considering the signals from multiple track circuits in a geographic area, faults are diagnosed from their spatial and temporal dependences. A generative model is used to show that the LSTM network can learn these dependences directly from the data. The network correctly classifies 99.7% of the test input sequences, with no false positive fault detections. In addition, the t-Distributed Stochastic Neighbor Embedding (t-SNE) method is used to examine the resulting network, further showing that it has learned the relevant dependences in the data. Finally, we compare our LSTM network with a convolutional network trained on the same task. From this comparison, we conclude that the LSTM network architecture is better suited for the railway track circuit fault detection and identification tasks than the convolutional network.
reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of
any copyrighted component of this work in other works.
TL;DR: Experimental results and comprehensive comparison analysis have demonstrated the superiority of the proposed MSCNN approach, thus providing an end-to-end learning-based fault diagnosis system for WT gearbox without additional signal processing and diagnostic expertise.
TL;DR: Experimental results on the wheelset bearing dataset show that the proposed multiattention mechanism can significantly improve the discriminant feature representation, thus the MA1DCNN outperforms eight state-of-the-arts networks.
TL;DR: A method for data-based line trip fault prediction in power systems using long short-term memory (LSTM) networks and support vector machine (SVM) is proposed, which proves the method’s improvements compared with current data mining methods.
TL;DR: The survey validates the universal applicability of deep learning to various types of input in PHM, including vibration, imagery, time-series and structured data and suggests the possibility of transfer learning across PHM applications.
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
TL;DR: A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
TL;DR: This paper first reviews basic backpropagation, a simple method which is now being widely used in areas like pattern recognition and fault diagnosis, and describes further extensions of this method, to deal with systems other than neural networks, systems involving simultaneous equations or true recurrent networks, and other practical issues which arise with this method.
Q1. What is the reason why a recurrent neural network is a natural choice?
For detecting temporal dependencies, a Recurrent Neural Network (RNN) is a natural choice, since the recurrent connections in the network allow it to store memories of past events.
Q2. What is the purpose of a track circuit?
To enable the safe operation of a railway network, track circuits are used to detect the absence of a train in a section of railway track.
Q3. What is the idea behind having multiple layers?
The idea behind having multiple layers is that each subsequent layer uses the outputs of the previous layer to form higher level abstractions of the data.
Q4. How does the network learn to distinguish between the different dependencies?
since the fault categories differ only based on their spatial and temporal dependencies and the network manages to correctly classify them in 99.7% of the trials, it has learned to distinguish between these dependencies.
Q5. What is the ideal size of the network?
In general, the ideal size of the network is based on the complexity of the problem, the amount of availabletraining data and the available computational resources.
Q6. What is the way to test the network?
After the training is complete, the network weights that resulted in the best performance on the validation data set are used to test the network.
Q7. What is the target for this classificationt(T)?
The target for this classificationt(T ) is the healthy state, unless the sequence contains a fault for which the severity at that time-step T is above 0.15.
Q8. What causes the receiver to be energized?
This causes the current flow through the receiver to decrease to a level where the relay is no longer energized and the section is reported as occupied.
Q9. What is the main reason for the use of convolutional networks?
On this problem, convolutional networks achieve state of the art performance by using raw pixel values, instead of using hand-crafted feature detectors as inputs [4].