Fault diagnosis method for continuous casting machine’s sector segment based on SG-PCA-LSTM

Abstract To address challenges such as the high variability of variables and difficulties in feature extraction during the casting process of the continuous casting machine’s sector segment, a fault diagnosis method based on SG-PCA-LSTM is proposed. This method aims to overcome the issue of fault features obscured by noise in the total tension time series by employing the SG smoothing algorithm for filtering and denoising. By leveraging the inter-segment data correlation and the advantage of PCA in extracting fault feature information, combined with the powerful learning capability of LSTM in modeling, a Principal Component Analysis - Long Short-Term Memory (PCA-LSTM) fault diagnosis model is established. Through comparative analysis against different diagnostic methods in terms of recognition rate, false positive rate, etc., the results obtained by this method are compared against those obtained by using other algorithms. Experimental results demonstrate that the proposed method exhibits good overall performance in terms of accuracy and training time.