本发明公开了一种电机故障诊断方法、装置、电子设备及存储介质。该方法包括：采集电机的运行参数；基于短时傅里叶算法和小波分析算法对所述运行参数进行处理，得到时频域特征；将所述运行参数和所述时频域特征进行融合，得到融合后的特征向量；将所述融合后的特征向量输入至训练好的长短期记忆神经网络中，识别出不同部位的故障特征；将所述不同部位的故障特征输入至训练好的支持向量机中，得到故障诊断结果。本发明能够有效且快速地对电机进行故障诊断。

The invention discloses a motor fault diagnosis method, a device, an electronic device and a storage medium. The method includes: collecting the running parameters of the motor; The operating parameters are processed based on short-time Fourier algorithm and wavelet analysis algorithm, and the time-frequency domain characteristics are obtained. The operation parameters and the time-frequency domain features are fused to obtain the fused feature vector; The fused feature vector is input into the trained long and short term memory neural network to identify the fault characteristics of different parts. The fault characteristics of the different parts are input into the trained support vector machine, and the fault diagnosis results are obtained. The invention can diagnose the motor fault effectively and quickly.