Search

The torsional vibrations of traction drive shafting system of EMU is one of key factors on heavily influence the running smoothness,safety and reliability of high-speed train. The torsional vibrations of a typical traction drive shafting system of EMU are investigated. After a concise introduction,the traction drive shafting system is simplified and equivalent to a lumped-parameters model with five moment of inertias and four torsional stiffness coefficients. Then,considering the meshing relationship of driving and driven gears,an undamped free torsional vibration equation of this lumped model is established by using direct stiffness method. At last,the natural frequency and mode shapes of this shafting system are obtained with the help of MATLAB software. On the other hand,a MATLAB/Simulink simulation model is also constructed according to above lumped-parameters model equation. And subsequently,the acceleration and displacement Bode plots of shafting system are calculated from this simulation model,these amplitude-frequency results are very useful to verify the natural frequencies obtained directly from the lumped model equation. Results show that the established lumped mass model is available to simulate the torsional vibration characteristics of traction drive shafting system,and the torsional resonance and fatigue problems may mainly happen on the driving side of shafting system. The research works are very useful for the future study on the dynamic design and optimization of traction drive shafting system of EMU.

Electric motors play a crucial role in ship systems. Detecting potential issues with electric motors is a critical aspect of ship fault diagnosis. Fault diagnosis in motors is often challenging due to limited and noisy vibration signals. Existing deep learning methods struggle to extract the underlying correlation between samples while being susceptible to noise interference during the feature extraction process. To overcome these issues, this study proposes an intelligent bimodal fusion attention residual model. Firstly, the vibration signal to be encoded undergoes demodulation and is divided into high and low frequencies using the IEEMD (Improved Ensemble Empirical Mode Decomposition) composed of the EEMD (Ensemble Empirical Mode Decomposition) and the MASM (the Mean of the Standardized Accumulated Modes). Subsequently, the high-frequency component is effectively denoised using the wavelet packet threshold method. Secondly, current data and vibration signals are transformed into two-dimensional images using the Gramian Angular Summation Field (GASF) and aggregated into a bimodal Gramian Angle Field diagram. Finally, the proposed model incorporates the Self-Attention Squeeze-and-Excitation Networks (SE) mechanism with the Swish activation function and utilizes the ResNeXt architecture with a Dropout layer to identify and diagnose faults in the multi-mode fusion dataset of motors under various working conditions. Based on the experimental results, a comprehensive discussion and analysis were conducted to evaluate the performance of the proposed intelligent bimodal fusion attention residual model. The results demonstrated that, in comparison to traditional methods and other deep learning models, the proposed model effectively utilized multimodal data, thereby enhancing the accuracy and robustness of fault diagnosis. The introduction of attention mechanisms and residual learning enable the model to focus more effectively on crucial modal data and learn the correlations between modalities, thus improving the overall performance of fault diagnosis. [ABSTRACT FROM AUTHOR]