电动拖拉机驱动电机系统故障诊断模型研究

Electric Tractor Drive Motor System Fault Diagnosis Model Research

驱动电机系统的故障可能导致电动拖拉机失控或发生意外情况,从而危及驾驶员和周围环境的安全,准确诊断故障可以帮助驾驶员及时采取措施,避免潜在的危险。为了进一步提高电动拖拉机驱动电机系统的故障诊断准确率,基于驱动电机系统的数据特征及故障类型,以BP人工神经网络模型为基础,通过PSO-BP优化后的人工神经网络模型构建电动拖拉机电机驱动电机系统故障诊断模型,并对传统BP神经网络模型的阈值和权重进行优化,以更快地收敛到全局最优解。通过采集驱动电机系统的数据,对基于PSO-BP故障诊断模型进行试验验证,结果表明:模型对5种故障状态诊断准确率较高,特别是退磁故障和IGBT故障这两种复杂的故障类型。研究内容能够为电动拖拉机驱动电机系统的故障诊断提供一种有效的方法和技术支持,可提高诊断准确率、保障驾驶员和周围环境的安全,提高了工作效率,降低了维修成本。

Failure of an electric tractor drive motor system can lead to loss of vehicle control or unexpected situations that can endanger the driver and the surrounding environment.Accurate fault diagnosis can help the driver to take timely action to avoid potential danger.In order to further improve the fault diagnosis accuracy of electric tractor drive motor system,based on the data characteristics and fault types of the drive motor system,this paper constructs the fault diagnosis model of electric tractor motor drive motor system based on BP artificial neural network model with PSO-BP optimized artificial neural network model,optimizes the threshold and weights of the traditional BP neural network model,and faster convergence to the global optimal solution.The experimental validation of the PSO-BP fault diagnosis model based on the drive motor system by collecting data from the drive motor system shows that the model has a high accuracy in diagnosing five fault states,especially in the two complex fault types of demagnetization fault and IGBT fault.The research content can provide an effective method and technical support for the fault diagnosis of electric tractor drive motor system,improve the diagnosis accuracy,guarantee the safety of the driver and the surrounding environment,improve the efficiency and reduce the maintenance cost.