Fault diagnosis is critical to maintaining the performance of rotating machinery and ensuring the safe operation of the equipment. Convolutional neural networks (CNNs) have recently shown great potential with excellent automatic feature learning and nonlinear mapping abilities in the field of rotating machinery fault diagnosis. However, the CNN-based methods still suffer from some defects, such as inadequate data utilization and uneconomical computational efficiency, which limits further improvement of diagnosis performance. Therefore, this paper proposes a fault diagnosis method based on multi-sensor fusion and Convolutional Neural Network with Efficient Channel Attention (ECA-CNN). First, multi-sensor vibration signals are sampled, converted, and channel fused into multi-channel images with rich and comprehensive features. Then, the efficient channel attention mechanism is introduced into CNN to increase the feature learning ability by adaptively scoring and assigning weights to the channel features. The ECA-CNN is proposed to learn representative fault features from multi-sensor fusion data to achieve fault identification. Finally, two experimental cases on the bearing and gearbox datasets prove that the proposed method has excellent performance, strong generalization capability, and high computational efficiency.

In order to improve the output performance of the rotating traveling wave ultrasonic motor and study the optimal pre-pressures under different loads, the theoretical calculation and experimental verification on a TRUM-70H ultrasonic motor were carried out. The dynamic model of an ultrasonic motor is established, and the influence of pre-pressure on the mechanical properties of the ultrasonic motor is analyzed. Taking the TRUM-70H ultrasonic motor as the object of study, the relationship between the optimum pre-pressure and the load torque is analyzed. A multi-functional testing platform for an ultrasonic motor is built to verify the theoretical derivation results, and the reason for the error is also pointed out. According to the conclusion, the pre-pressure should be selected according to the load when the ultrasonic motors are assembled. The results show that there is a coupling relationship between the pre-pressure and the load torque on the speed of the ultrasonic motor. In the effective working range of the ultrasonic motor, the optimum pre-pressure is approximately linearly positively correlated with the load torque. When the pre-pressure is set according to the actual load demand during assembly, the output efficiency of the ultrasonic motor can be improved.

To achieve multi-mode fault sample generation and fault diagnosis of bearings in a complex operating environment with scarce labeled data. Combining a semi-supervised generative adversarial network (SGAN) and an auxiliary classifier generative adversarial network (ACGAN), a semi-supervised auxiliary classifier generative adversarial network (SACGAN) is constructed in this paper. The network structure and the loss function are improved. A fault diagnosis method based on STFT-SACGAN is also proposed. The method uses a short-time Fourier transform (STFT) to convert one-dimensional time-domain vibration signals of bearings into two-dimensional time-frequency images, which are used as the input of SACGAN. Two multi-mode fault data generation and intelligent diagnosis cases for bearings are studied. The experimental results show that the proposed method generates high-quality multi-mode fault samples with high fault diagnosis accuracy, generalization, and stability.