In order to improve the accuracy of bearing fault diagnosis under a small sample, variable load, and noise conditions, a new fault diagnosis method based on an image information fusion and Vision Transformer (ViT) transfer learning model is proposed in this paper. Firstly, the method applies continuous wavelet transform (CWT), Gramian angular summation field (GASF), and Gramian angular difference field (GADF) to the time series data, and generates three grayscale images. Then, the generated three grayscale images are merged into an information fusion image (IFI) using image processing techniques. Finally, the obtained IFIs are fed into the advanced ViT model and trained based on transfer learning. In order to verify the effectiveness and superiority of the proposed method, the rolling bearing dataset from Case Western Reserve University (CWRU) is used to carry out experimental studies under different working conditions. Experimental results show that the method proposed in this paper is superior to other traditional methods in terms of accuracy, and the effect of ViT model based on transfer learning (TLViT) training is better than that of the Resnet50 model based on transfer learning training (TLResnet50) under variable loads and small sample conditions. In addition, the experimental results also prove that the IFI with multiple image information has better anti-noise ability than the single information image. Therefore, the method proposed in this paper can improve the accuracy of bearing fault diagnosis under small sample, variable load and noise conditions, and provide a new method for bearing fault diagnosis.

In order to meet stringent temperature-control requirements in a high-speed airflow wind tunnel (HAWT) for thermal simulation under complicated work conditions such as thermal strength experiment of aero engine blade and dynamic calibration of high temperature thermal coupler, this paper proposes a novel cascade fuzzy-PID (C-Fuzzy-PID) compound control method for regulating the fuel-oil flow rate in the inner loop and temperature in the outer loop. The mathematical models that characterize the dynamics of the heat airflow temperature in the combustor and the fuel-oil flow rate for combustion are derived, upon which the improved PID control laws for the inner and outer loops are described. The former employs a fuzzy-PID controller with a predictor for controlling flow rate in the inner loop, which effectively overcomes influences according to its characteristics of large inertia and transport lag in fuel-oil supply system on the temperature responses. The latter combines disturbance compensation and a fuzzy-PID feedback law to suppress influences due to factors such as change in work conditions, disturbances, and time-varying parameter variations. The C-Fuzzy-PID method has been numerically investigated by comparing simulation results against two traditional PID-based methods, as well as experimentally validated confirming that the proposed control algorithm has strong robustness and excellent adaptability for temperature control of an HAWT.

To address the problems of limited identification accuracy and poor generalization ability of bearing fault diagnosis models, a convolutional neural network model for bearing fault diagnosis based on convolutional block attention module and multi-channel feature fusion (CBAM-MFFCNN) is proposed. The method uses signal processing technology to convert one-dimensional vibration signal into three types of two-dimensional time-frequency images, and constructs a network with multi-channel input to learn the three types of images at the same time. To realize the accurate fault diagnosis of bearings in strong noise environment, the structural parameters of the network are optimized. By adding different degrees of Gaussian white noise to the vibration signal, the convolution kernel size and the step of the first layer of the model are optimized. In order to improve the feature extraction ability and generalization performance of the model, the variable load dataset is constructed for training and testing. Experiments are conducted based on the Case Western Reserve University (CWRU) bearing datasets, the experimental results show that compared with the single channel diagnosis model, CBAM-MFFCNN can not only realize accurate identification of bearing fault, but also achieve 100% identification accuracy in fault degree testing.

Accurate diagnosis of the damage location of the frame structure is very important for the overall damage assessment and subsequent maintenance of the frame structure. However, the frame structure generally works in the noise environment, which increases the difficulty of health monitoring and fault diagnosis of frame structure based on vibration data. In order to realize the accurate damage location diagnosis of structural frame under noise environment, this paper proposes a fault diagnosis method based on wavelet denoising, convolutional neural network, Inception module, and long short-term memory (LSTM) on the basis of complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). In order to verify the effectiveness and superiority of the method proposed in this paper, the 4-story steel frame model of the University of British Columbia is taken as the research object, and the experiments are carried out with the method proposed in this paper, and under the same conditions, the comparative experiments are carried out with other similar methods. The experimental results show that the method proposed in this paper not only has high accuracy, but also has strong anti-noise ability, and its performance is better than other similar methods. Therefore, the fault diagnosis method proposed in this paper can effectively perform the accurate diagnosis of damage location of frame structure under noise environment.

A bearing fault diagnosis method based on the Markov transition field (MTF) and SEnet (SE)-IShufflenetV2 model is proposed in this paper due to the problems of complex working conditions, low fault diagnosis accuracy, and poor generalization of rolling bearing. Firstly, MTF is used to encode one-dimensional time series vibration signals and convert them into time-dependent and unique two-dimensional feature images. Then, the generated two-dimensional dataset is fed into the SE-IShufflenetV2 model for training to achieve fault feature extraction and classification. This paper selects the bearing fault datasets from Case Western Reserve University and Paderborn University to experimentally verify the effectiveness and superiority of the proposed method. The generalization performance of the proposed method is tested under the variable load condition and different signal-to-noise ratios (SNRs). The experimental results show that the average accuracy of the proposed method under different working conditions is 99.2% without adding noise. The accuracy under different working conditions from 0 to 1 HP is 100%. When the SNR is 0 dB, the average accuracy of the proposed method can still reach 98.7% under varying working conditions. Therefore, the bearing fault diagnosis method proposed in this paper is characterized by high accuracy, strong anti-noise ability, and generalization. Moreover, the proposed method can also overcome the influence of variable working conditions on diagnosis accuracy, providing method support for the accurate diagnosis of bearing faults under strong noise and variable working conditions.

Because the gearbox in transmission systems is prone to failure and the fault signal is not obvious, the fault end cannot be located. In this paper, a gearbox fault diagnosis method grounded on improved complete ensemble empirical mode decomposition with adaptive noise, a multiscale permutation entropy and adaptive wavelet thresholding (ICEEMDAN-MPE-AWT) denoising method and an SE-ResNeXt50 transfer learning model are proposed. Initially, the vibration signal is denoised by ICEEMDAN-MPE-AWT, the denoised vibration signal is then converted into a Gram angle field (GAF) diagram, and then the parameters are transferred by the fine-tuning transfer learning strategy. Finally, a GAF diagram is input into the model for training to achieve fault extraction and classification. In this paper, the open gear dataset of Southeast University is used for experimental research. The experimental results show that when using the ICEEMDAN-MPE-AWT and when the signal-to-noise ratio (SNR) of the experimental data is −4 dB, the average accuracy of the GASF+TSE-ResNeXt50 and the GASF+TSE-ResNeXt18 can reach 98.8% and 97.5%, respectively. When the SNR is 6 dB, the accuracy of the above two models reaches 100% and 99.3%, respectively. Moreover, when compared to alternative approaches, the noise reduction method in this paper can better remove noise interference so that the model can better extract fault features. Therefore, the method proposed in this article shows significant improvement in noise reduction and fault classification accuracy compared to other methods.