Fault Diagnosis of Active Magnetic Bearing–Rotor System via Vibration Images

As important sources in fault diagnosis of rotary machinery, vibration signals are usually processed in the time or frequency domain as features to distinguish different classes of faults. However, these kinds of processing methods always ignore the corresponding relations among multiple signals, resulting in information loss. In this paper, a new fault description strategy named vibration image is proposed, based on which three new kinds of features are extracted, containing coupling information between different channels of vibration signals. Additionally, a new feature fusion method called two-layer AdaBoost is designed to train the fault recognition model, which avoids overfitting when the dataset is not large enough. Features based on vibration images combined with two-layer AdaBoost are adopted to diagnose faults of rotary machinery. Taking an active magnetic bearing-rotor system as the experimental platform, a dataset with four classes of faults is collected and our algorithm achieves good performance. Meanwhile, features based on vibration images and two-layer AdaBoost are both proved to be efficient separately.