基于连续小波变换和 MTL-SEResNet 的断路器故障程度评估

考虑到万能式断路器触头系统机械故障是一个从轻微到重度的演变过程，准确识别其运行状态可以大大提高断路器的可靠性。提出一种单信号输入和多任务输出的MTL-SEResNet网络模型以兼顾故障诊断和程度评估。首先采用连续小波变换对触头系统振动信号进行时频分析，得到相应的二维时频图像；其次将SENet结构引入到改进的ResNet18中，利用多任务学习共享机制构建MTL-SEResNet网络模型；并通过调整故障分类和程度评估两个任务损失函数的权重比例，对模型进行优化；最后，通过模拟的触头系统的故障数据对所提方法进行实验验证。结果表明，模型的性能更佳，类型及程度准确率分别为99.78%和99.36%,可以有效地实现万能式断路器故障程度评估。

Fault degree evaluation of circuit breaker based on continuouswavelet transform and MTL-SEResNet

The mechanical fault of the contact system for a conventional circuit breaker is a process from slight to severe. The accurateidentification of its operating state can greatly improve the reliability of the circuit breaker. In this article, a single signal input andmulti-task output MTL-SEResNet model is proposed for fault diagnosis and degree evaluation. Firstly, the raw vibration signals of thecontact system are analyzed using a continuous wavelet transform. And the corresponding two-dimensional time-frequency images areobtained. Secondly, the improved ResNet18 network is combined with the SENet structure, and the multi-task learning sharingmechanism is used to formulate the MTL-SEResNet model. The model is optimized by adjusting the weight ratio of the two task lossfunctions for fault classification and degree evaluation. Finally, the proposed method is verified by experiments with simulated fault dataof the contact system. The results show that the proposed model has better performance with 99. 78% and 99. 36% accuracy in type anddegree, respectively, which can effectively evaluate the fault degree of the conventional circuit breaker.