Advanced method for recognizing and measuring key information in non-stationary signals using variational mode decomposition and CNN-LSTM-SVM algorithms

In order to address the issue of insufficient ability to identify and measure the key information of non-stationary signals collected in practical industrial fields such as logistics transportation, state detection, and fault diagnosis, this paper proposes a method to identify and measure the key information based on variational mode decomposition (VMD), convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and support vector machine (SVM). First, the non-stationary signal is reconstructed by using VMD and linear correlation decomposition. Second, the feature matrix is constructed according to the upper envelope feature, moving kurtosis, and moving root mean square. Finally, CNN-LSTM-SVM is input to identify and measure the key features. The experimental results demonstrate that the proposed method exhibits an outstanding performance on both synthetic and actual collected signals, with recognition accuracies of 99.17% and 99.02%, respectively.