Research on Fault Diagnosis Method of Electric Valve Based on Convolutional Gated Recurrent Unit and Support vector machine

Ensuring the safe operation of nuclear facilities has always been an important research topic in the development of nuclear energy. Therefore, a variety of methods have been proposed in the world for fault diagnosis of nuclear facilities to assist operators. In order to make full use of the characteristic information of time series data and improve the accuracy of fault diagnosis of electric valves in nuclear facilities, this paper proposes a new convolutional gated recurrent unit and support vector machine (CGRU_SVM) fault diagnosis network model. This model uses the convolution kernel to extract the features of the data, then uses the gated recurrent unit (GRU) to extract the timing features, and finally inputs the processed feature information into the support vector machine (SVM) for classification. Experiments have shown that the accuracy of this method for fault diagnosis of electric valves can reach more than 99.9%, for the failure to detect nuclear facilities electric valves, electric valves guarantee safe and reliable operation of guiding significance.