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

Abstract

The effective extraction of key features in non-stationary signals measurement is crucial in numerous engineering fields, including fault diagnosis, geological exploration, and state detection. To accomplish a more accurate and efficient extraction of key feature information from non-stationary signals, we design a novel approach based on variational mode decomposition (VMD) optimization by northern goshawk optimization (NGO) algorithm, convolutional neural network (CNN), and long short-term memory network (LSTM). First, NGO is used to optimize multiple intrinsic mode functions of VMD and reconstruct the signal according to the linear correlation method. Subsequently, the features of moving root mean square, moving kurtosis, and upper envelope are calculated, thereby constructing the feature matrix. Finally, the CNN-LSTM model is established with the chosen optimal hyperparameters prior to the training phase. The experimental results demonstrate that the proposed NGO-VMD-CNN-LSTM method, with a high accuracy reaching 98.22%, can more accurately extract the key information of typical non-stationary signals.

Particle accelerator power system early fault diagnosis based on deep learning and multi-sensor feature fusion

“…Although it outperforms individual methods in both classification and regression tasks [25], it may suffer from issues such as insufficient mapping of high-dimensional data, convergence difficulties, and weak resistance to interference. In references [26][27][28][29][30], improvements were made by incorporating residual modules, Bayesian optimization, multiscale feature extraction modules, etc, on the basis of CNN-LSTM. These enhancements have led to improved accuracy, noise resistance, and other performance metrics in specific problems.…”