This invention relates to the field of motor operating status detection technology, and discloses a detection method,
system, electronic device, and storage medium that combines motor feedback and torque threshold analysis. The method collects multi-dimensional operating data such as torque, current, speed, and temperature during motor operation, performs time-synchronized
processing on the multi-
source data, and extracts related characteristic parameters such as torque-current
correlation coefficient, torque change rate, speed
response delay, and
phase difference. A dynamic torque
threshold model is constructed based on sliding window statistics, and an adaptive
detection threshold is generated by combining environmental correction and wear compensation mechanisms. A multi-
source data fusion
algorithm is used to calculate the comprehensive anomaly probability, enabling abnormal motor operating status determination and graded early warning. Simultaneously, an adaptive model update mechanism is introduced to continuously optimize the
threshold model. This solution can improve the accuracy and stability of motor
anomaly detection, reduce
false alarm and false negative rates, and is suitable for motor
condition monitoring and
predictive maintenance in industrial scenarios such as industrial robots,
new energy vehicles, and CNC equipment.