Application of PCA-LSTM algorithm in predicting component faults in CNC machining centers

Abstract In order to further explore the relationship between component failures and CNC machining center failures, a method of predicting component failures in advance was proposed to reduce the likelihood of machining center failures and improve CNC machining efficiency. In this paper, the principal component analysis method is used to optimize the Long short-term memory neural network to build a network model to study and predict the fault status of NC machining center components in work. The use of Principal Component Analysis (PCA) to extract the main features of machine tool faults can improve the speed of iterative training networks during the machining process and reduce the input dimension and prediction difficulty of LSTM. The extracted data is used as input for the LSTM network. The fault type is output. The comparison of diagnostic results between PCA-LSTM, LSTM, and BP neural networks shows that PCA-LSTM is a high-precision prediction model. The root mean square difference is reduced to 1.572. The predicted error results can effectively reflect the changes that occur in the machining center components with the occurrence of faults. It can be seen that it is feasible to use PCA-LSTM as a tool for predicting the faults of CNC machining center components.