A fault diagnosis method for universal circuit breaker accessories based on deep learning

Abstract

The invention is a fault diagnosis method for universal circuit breaker accessories based on deep learning. The method is used for fault diagnosis of opening and closing accessories of low-voltage universal circuit breakers. Considering the characteristics of the current signal of the opening and closing coil, an adaptive one-dimensional depth Convolutional neural network, and set the convolution kernel of the first convolutional layer of the model to a wide convolution kernel to expand the receptive field area; then, use the feature extraction layer to perform adaptive feature extraction on the current signal; finally, use Softmax The classifier outputs fault diagnosis results. The fault diagnosis results of the opening and closing accessories show that the invention can not only effectively identify the same fault under different closing phase angles, but also maintain a high fault identification rate in the generalization experiment, and can effectively overcome the problem of closing phase angles. The impact of changes on fault diagnosis results.

Description

technical field [0001] The invention relates to a fault diagnosis method for opening and closing accessories of a low-voltage universal circuit breaker, and more specifically relates to a fault diagnosis method for opening and closing accessories of a universal circuit breaker based on deep learning. Background technique [0002] The universal circuit breaker is a protection and control device in the low-voltage power distribution system. Its health status has a huge impact on the performance and stability of the power distribution system, so its daily maintenance is very important. The opening and closing accessories are the key components of the circuit breaker, and their normal operation is the key guarantee for the reliable operation of the circuit breaker. However, during the long-term operation of the circuit breaker, different types of mechanical failures often occur in the opening and closing accessories, which affect the normal operation of the circuit breaker. In ...

AI Technical Summary

Problems solved by technology

[0004] In view of the randomness of the closing phase angle of the coil circuit of the low-voltage universal circuit breaker, there will be differences in the current signals under the same operating state. Using traditional fault diagnosis methods may cause inaccurate extraction of current signal fault features, resulting in a decrease in fault recognition rate. , the object of the present invention is to provide a method for fault diagnosis of universal circuit breaker accessories based on deep learning. The method takes into account the characteristics of the current signal of the opening and closing coil, and adopts an adaptive one-dimensional deep convolutional neural network (Adaptive One- Dimensional Deep Convolutional Neural Networks with WideFirst-Layer Kernel, AW-1DCNN), and set the convolution kernel of the first convolutional layer of the model to a wide convolution kernel to expand the receptive field area; then, use the feature extraction layer to correct the current Adaptive feature extraction is performed on the signal; finally, the Softmax classifier is used to output the fault diagnosis result

Images