Environmental noise and transmission components can cause significant interference in vibration signals, rendering the extraction of bearing fault features challenging in service scenarios. Traditional fault diagnosis methods rely heavily on professional domain knowledge, prior models, and signal preprocessing methods. The accuracy of fault diagnosis depends on the quality of the fault-sensitive features extracted by vibration signal preprocessing methods. An improved convolutional neural network (CNN) end-to-end intelligent fault diagnosis model based on raw vibration data (RVDCNN) is proposed. The time-domain vibration signal of the transmission bearing is converted into a continuous two-dimensional numerical matrix, and a two-dimensional CNN model is constructed through network structure optimization. The original time-domain vibration signal numerical matrix of the bearing is trained and tested to extract and learn abstract fault features of different fault types, and then the fault classification of the bearing is achieved. To verify the generalizability of the RVDCNN intelligent fault diagnosis model, it is applied to the recognition of rolling bearings in the two-speed mechanical automatic transmission of electric vehicles, achieving recognition accuracy of 99.11% for seven types of bearings.

Two-speed transmissions can regulate the motor operating point by changing the transmission ratio of drive systems and are an effective approach to improving both dynamic performance and energy efficiency of battery electric vehicles. However, existing gear shift strategies rarely consider the impact of transmission operating states on shift rationality and system stability, leading to limited adaptability under complex driving conditions. To address this issue, a hierarchical fuzzy evaluation and gear shift strategy matching method based on transmission operating states is proposed. First, three basic strategies are designed. Then, shift frequency and gear duty ratio are introduced to characterize transmission behavior, and a hierarchical decision framework consisting of driving demand evaluation, transmission behavior evaluation, and strategy matching is constructed to enable adaptive selection among different strategies. Furthermore, a fuzzy shift frequency correction strategy is proposed to adjust shift thresholds online, thereby reducing frequent and unnecessary shifting. Finally, simulations are conducted under multiple typical driving cycles based on a vehicle model, and experimental validation is carried out using a high-speed dual motor load test bench. The results demonstrate that the proposed strategy can effectively balance dynamic performance and energy efficiency while reducing unnecessary shifts.