Recognition of Key Information in Non-Stationary Signals Based on Wavelet Threshold Denoising and Back Propagation Neural Network Optimized by Manta Ray Foraging Optimization Algorithm

Abstract

The identification of key information hidden in non-stationary signals is challenging in various fields such as logistics and transportation, biomedicine, and fault diagnosis. To facilitate this identification, we propose a back propagation neural network (BPNN) classification and recognition algorithm based on wavelet threshold denoising (WTD) and manta ray foraging optimization (MRFO) algorithm for the first time.The algorithm first performs WTD on the original signals to obtain denoised signals. Subsequently, the MRFO algorithm is utilized to optimize the initial weights and thresholds of the BPNN. On the base of this, the optimization model is finally obtained to classify and recognize the key information in the non-stationary signals. The comparative experimental results indicate that the proposed WTD-MRFO-BPNN algorithm can be utilized to availably recognize the key information hidden in non-stationary signals. The recognition accuracy reaches 97.25%.

High accuracy key feature extraction approach for the non-stationary signals measurement based on NGO-VMD noise reduction and CNN-LSTM

“…Step 2: The correlation coefficients between each mode component IMFi and the original signal are calculated using equation (26). The IMFi components are then sorted in descending order of magnitude of correlation coefficients and recorded as IMF i *…”

“…Subsequently, the non-stationary signals undergo decomposed using VMD technique, and the reconstructed signals are screened by the linear correlation method. The features of moving root mean square, moving kurtosis, and upper envelope [26] are calculated. Then the calculation results are used to construct the feature matrix, which is then fed into the CNN-LSTM for training, and key information of typical non-stationary signals is extracted.…”