Universal circuit breaker accessory fault diagnosis method based on deep learning

Abstract

The invention discloses a universal circuit breaker accessory fault diagnosis method based on deep learning. The method is used for fault diagnosis of a low-voltage universal circuit breaker switch-on-off accessory. By considering the feature of the switch-on-off coil current signal, a self-adaptive one-dimensional deep convolution neural network is adopted, and a receptive field region is enlarged by setting a convolution kernel of the first layer of convolution layer of the model as the wide convolution; and then the self-adaptive feature extraction is performed on the current signal by utilizing a feature extraction layer; and finally, a Softmax classifier is used for outputting a fault diagnosis result. The fault diagnosis of the switch-on-off accessory shows that the same fault is effectively identified under different switch-on phase angles, and high fault recognition rate still can be maintained in a generalization experiment, and the influence on the fault diagnosis result by the switch-on phase angle change can be effectively overcome.

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