A fault diagnosis algorithm of the dedicated equipment based on LSTM mechanism

With the rapid development of information technology, industrial equipment gradually develops in the direction of intelligentization, integration, and systematization. However, with the continuous updating and iteration of industrial equipment, the previous fault diagnosis methods can not be fully adapted to the current industrial equipment. This paper presents a fault diagnosis model based on a long short-term memory network (LSTM) for dedicated equipment fault diagnosis. First, the data is preprocessed according to the mechanism of the equipment. Then, the convolutional neural network and LSTM are used to extract spatial and temporal features of the data. Convolutional Block Attention Module (CBAM) mechanism can make the model better extract the characteristics of the data. In this paper, the data collected by the dedicated equipment’s hardware-in-loop platform are used to verify the model and compare the proposed model with other neural network models. The results demonstrate the greater accuracy of this method.