In recent years, artificial neural networks have been widely used in the fault diagnosis of rolling bearings. To realize real-time diagnosis with high accuracy of the fault of a rolling bearing, in this paper, a bearing fault diagnosis model was designed based on the combination of VMD and ANN, which ensures a higher fault prediction accuracy with less computational time. This paper works from two aspects, including fault feature extraction and neural network structural parameter optimization to obtain an ANN bearing fault diagnosis model with high performance. The raw vibration signals of 10 fault types were divided into training, verification and testing datasets by the random step increment slip method. The variational mode decomposition method was used to decompose the raw vibration signal into several intrinsic mode functions. A new definition of the energy of each intrinsic mode function based on discrete Fourier transform and information entropy method were used as the input for the artificial neural network. Furthermore, the structural parameters of the artificial neural network were designed to obtain a high-performance neural network. The artificial neural network used in this paper had three hidden layers and 13 neurons in each hidden layer. Compared with several machine and deep learning algorithms, the artificial neural network can better fulfill the classification task of rolling bearing fault types with a mean prediction accuracy of 99.3% and computation time of 2.4 s based on a small training dataset.

The filtered-x recursive least square (FxRLS) algorithm is widely used in the active noise control system and has achieved great success in some complex de-noising environments, such as the cabin in vehicles and aircraft. However, its performance is sensitive to some user-defined parameters such as the forgetting factor and initial gain. Once these parameters are not selected properly, the de-noising effect of FxRLS will deteriorate. Moreover, the tracking performance of FxRLS for mutation is still restricted to a certain extent. To solve the above problems, this paper proposes a new proportional FxRLS (PFxRLS) algorithm. The forgetting factor and initial gain sensitivity are successfully reduced without introducing new turning parameters. The de-noising level and tracking performance have also been improved. Moreover, the momentum technique is introduced in PFxRLS to further improve its robustness and de-noising level. To ensure stability, its convergence condition is also discussed in this paper. The effectiveness of the proposed algorithms is illustrated by simulations and experiments with different user-defined parameters and time-varying noise environments.

This paper presents an application of Structural Health Monitoring System based on Fiber Bragg Grating sensors (FBGs) dedicated to wing-bending moment. A numerical calculation of bending moment is proposed to the application of real-time wing-bending moment monitoring. With the advantage of anti-electromagnetic interference, small size and light weight, Fiber Bragg grating (FBG) sensors have been applied in structural health monitoring system (SHMS). An experiment was performed in full-scale fatigue test of an aircraft, and the wings of aircraft were subjected to specific loading conditions, and the strain data was collected by FBGs’ demodulation. The relationship matrix K between the strain and the wing-bending moment was established. It is a new approach for the wing-bending moment real-time monitoring with the simple FBG strain collection modulation.

Diversified noise sources pose great challenges in the engineering of an ANC (active noise control) system design. To solve this problem, this paper proposes an ANC method based on VMD (variational mode decomposition) and Ensemble Learning. VMD is used to extract IMFs (Intrinsic Model Functions) of different types of noise and obtain the approximate entropy of each IMF. Clustering analysis on the output of VMD is conducted based on the PCA (principal component analysis) dimension reduction method and k-means++ method to get classification results for different noises. On the basis of the clustering results, different GBDT (gradient boosting decision tree) regressors are constructed for different noise types, in order to create a high-performance ANC system for multiple noise sources. To verify the effectiveness of the proposed method, this paper designed four simulation schemes for the ANC: obstacle-free rectangular enclosed space, rectangular enclosed space with obstacle, obstacle-free trapezoidal enclosed space and trapezoidal enclosed space with obstacle. When machine gun noise is used as an example, noise attenuation by the proposed method in four simulation schemes is −23.27 dB, −21.6 dB, −19.08 dB and −15.48 dB respectively.