Fault Identification of Bearing Vibration Signals Under Different Loads Based on Isolation Forest Algorithm

With the continuous development of industrial equipment, vibration signals have become an important tool for monitoring the operational status of machinery, widely used in fault diagnosis and health monitoring. Traditional anomaly detection methods face significant limitations when handling high-dimensional vibration signals. To improve the accuracy and robustness of anomaly detection in vibration signals, this study proposes an anomaly detection method based on the Isolation Forest (IF) algorithm. This research utilizes performance test data of asynchronous motor bearings from a motor factory. The dataset includes vibration signals, temperature signals, and voltage signals under different load conditions. The Isolation Forest algorithm is applied to detect anomalies in vibration signals, accurately identifying potential fault signals. Results show that the Isolation Forest algorithm achieves remarkable effectiveness in detecting abnormal bearing vibration signals under various load conditions.