Bearings are widely applied in rotating machinery of nuclear power plants (NPPs). Data-driven fault diagnosis technology is critical to ensuring the reliable operation of rotating machinery. Aiming at the problem of poor model generalization ability caused by discrepant data distribution of monitoring signals under various working conditions, a deep transfer learning method based on fully categorized alignment subdomain adaptation (FCA-SAN) is proposed in this paper. Firstly, the bearing vibration signals of the source and target operating conditions are preprocessed and converted into time-frequency domain images suitable for model input. Subsequently, a pre-trained deep convolutional neural network (DCNN) model is adopted as the feature extractor, which is combined with FCA-SAN to extract transferable features across different working conditions. The subdomain adaptation method reduces the data distribution discrepancy more fine-grained by aligning the feature distribution of different working conditions, thereby effectively improving the model generalization ability. Finally, the experimental results show that, compared with the traditional method, the proposed subdomain adaptation method reaches the highest fault diagnosis accuracy in different transfer tasks, which demonstrates the potential application value in rotating machinery of NPPs.

The traditional legs rehabilitation exercise system driven by motor makes patients hard to achieve ideal rehabilitation effects. This paper presents a novel legs rehabilitation exercise system driven by pneumatic muscle actuator. The components and control structures of the system were designed according to the requirements of rehabilitation exercise of legs joints. The system consists of pneumatic device and electrical device. The pneumatic device is composed of air supply, control valves and joints drivers which mainly include pneumatic muscle actuators, chain wheel, and bracket. The pneumatic muscle actuators are used for actuating legs joints rotational movement or creating resistance to motion of legs joints. With the control structures, the system completes the continuous passive motion or active resistance motion for the joints of hip, knee and ankle. The experiments verified that the movement of joints in continuous passive motion is smooth, the resistance of joints in active resistance motion is adaptive, yielding and adjustable, and the setting of training parameters is convenient. This provides the beneficial reference in designing new effective legs rehabilitation exercise system.