Due to the long-term operation of planetary gearboxes in strong noise environments and changing working conditions, the collected vibration signals exhibit weak fault characteristics and variable signal patterns, making them difficult to identify. Intelligent fault diagnosis of planetary gearboxes under these conditions remains a challenging task. In order to achieve high diagnostic accuracy and strong model generalization performance, a fault diagnosis method using a graph neural network with a multi-scale time-spatial information fusion mechanism is proposed. The method first uses convolution kernels of different scales to extract features from the original vibration signal, reducing the masking effect of strong noise signals on valuable information and enhancing its feature expression ability. A channel attention mechanism is then constructed to adaptively assign different weights among different channels to features of different scales, enhancing features in segments of information containing crucial fault characteristics. Finally, the multi-scale features of the convolution module output are used to construct graph data with spatial structure information for graph convolution learning. This approach allows for the full utilization and deep fusion of multi-dimensional time domain information and spatial correlation information, effectively improving the accuracy of diagnosis and the generalization performance of the model. The proposed method was verified using a fault dataset of wind power equipment with planetary gearbox structure. The average diagnosis accuracy of the proposed method was found to reach 98.85% and 91.29% under cross-load and cross-speed conditions, respectively. These results are superior to other intelligent diagnosis methods, including deep convolutional neural networks with wide first-layer kernels (WDCNN), long short-term memory network (LSTM), residual network (ResNet), and multi-scale convolution neural network (MSCNN). Therefore, the strong generalization performance and superiority of the proposed method were confirmed.

The turbo-electric drive compressor with exhaust energy recovery function is the development trend of high-power fuel cell air management system. However, the turbo-electric drive compressor has problems such as low pressure ratio and low energy recovery rate under off-design conditions. In this paper, a high-power fuel cell system was taken as the research object. According to the intake and exhaust parameters of the stack, the three-dimensional aerodynamic design of the turbine expander and the compressor was completed. An electrochemical-flow heat transfer one-dimensional coupling model including the fuel cell stack and the turbo-electric drive compressor was established. The accuracy of the model was verified by the stack test data. Based on this model, the influence of turbine flow characteristics and valve adjustment methods on the exhaust energy recovery rate under full operating conditions was further studied. The results show that under the condition of small and medium load, the exhaust energy recovery rate increases by 5.26 percentage points for every 0.1 reduction of turbine flow coefficient. However, small flow coefficient will cause high stack pressure at the design point, so it is necessary to increase the pressure relief of bypass valve, which leads to the high complexity of the system and big exhaust energy loss. When the turbine flow coefficient is 1, a better energy recovery rate can be obtained under all working conditions. In addition, the valve preposition scheme is better than the postposition scheme, and the valve preposition can increase the energy recovery rate by 6.25% under off-design conditions. Combined with the scheme of turbine flow coefficient of 1 and valve preposition, the exhaust energy recovery rate of the turbo-electric drive compressor is 33.07% and 27.31% respectively at the design flow point and 50% design flow point.