电子测量与仪器学报

王瑞峰,王智.基于DRSN-BiLSTM的S700K转辙机故障诊断[J].电子测量与仪器学报,2024,38(11):70-78

基于DRSN-BiLSTM的S700K转辙机故障诊断

Fault Diagnosis of S700K switch machine basedon DRSN-BiLSTM hybrid model

DOI：

英文关键词:DRSN BiLSTM S700K switch machine fault diagnosis

基金项目:国家自然科学基金(61763025)项目资助

作者	单位
王瑞峰	兰州交通大学自动化与电气工程学院兰州730070
王智	兰州交通大学自动化与电气工程学院兰州730070

Author	Institution
Wang Ruifeng	School of Automation and Electrical Engineering，Lanzhou Jiaotong University, Lanzhou 730070,China
Wang Zhi	School of Automation and Electrical Engineering，Lanzhou Jiaotong University, Lanzhou 730070,China

摘要点击次数: 445

全文下载次数: 1216

中文摘要:

在铁路系统中，转辙机是确保列车安全顺畅运行的关键设备。S700K转辙机的故障诊断对于预防事故和维护铁路运营至关重要。为了解决传统诊断方法在速度和准确性上的不足，提出了一种融合深度残差收缩网络(DRSN)与双向长短期记忆神经网络(BiLSTM)的诊断模型。首先，对转辙机功率曲线进行预处理；其次，利用DRSN对预处理数据进行自动特征学习，并压缩数据长度，提高诊断的快速性，其注意力机制和软阈值化降低了噪声特征的影响，并且DRSN网络结构有助于克服网络退化和过拟合的问题；随后，利用BiLSTM的双向结构捕捉时间序列数据中复杂的关系；最后使用Softmax分类器进行故障分类。仿真结果表明DRSN-BiLSTM模型的准确率、精确率、召回率均超过了98.3%，并且该模型故障诊断的准确率相较于DRSN、深度神经网络(DNN)和卷积神经网络(CNN)等模型至少提高了1.47%，并且在添加15~40 db高斯白噪声情况下准确率保持在92.7%以上，较其余模型至少提升2%。该模型在确保训练过程的高效性的同时提升了转辙机故障诊断准确率，并且在噪声环境下展现出了优秀的鲁棒性。

英文摘要:

In the railway system, the switch machine is a critical device to ensure the safe and smooth operation of trains. Fault diagnosis of the S700K switch machine is crucial for accident prevention and the maintenance of railway operations. To address the shortcomings of traditional diagnostic methods in terms of speed and accuracy, a diagnostic model integrating a deep residual shrinking network with a bidirectional long short-term memory network is proposed. First, the power curve of the switch machine is preprocessed. Next, DRSN is used to automatically learn features from the preprocessed data and compress the data length, improving the speed of diagnosis. Its attention mechanism and soft thresholding reduce the influence of noise features, and the DRSN structure helps to overcome network degradation and overfitting issues. Following that, the bidirectional structure of BiLSTM is utilized to capture complex relationships in the time-series data. Finally, a Softmax classifier is employed for fault classification. Simulation results show that the accuracy, precision, and recall rates of the DRSN-BiLSTM model all exceed 98.3%. Compared with models such as DRSN, deep neural network, and convolutional neural network, the diagnostic accuracy of this model is improved by at least 1.47%. Even when Gaussian white noise in the range of 15~40 dB is added, the accuracy remains above 92.7%, an improvement of at least 2% over other models. This model not only ensures the efficiency of the training process but also improves the accuracy of point machine fault diagnosis and demonstrates excellent robustness in noisy environments.

查看全文查看/发表评论下载PDF阅读器