Hybrid CNN–MLP for Robust Fault Diagnosis in Induction Motors Using Physics-Guided Spectral Augmentation

The diagnosis of faults in induction motors, such as broken rotor bars, is critical for preventing costly emergency shutdowns and production losses. The complexity of this task lies in the diversity of induction motor operating regimes. Specifically, a change in load alters the signal’s frequency composition and, consequently, the values of fault diagnostic features. Developing a reliable diagnostic model requires data covering the entire range of motor loads, but the volume of available experimental data is often limited. This work investigates a data augmentation method based on the physical relationship between the frequency content of diagnostic signals and the motor’s operating regime. The method enables stretching and compression of the signal in the spectral domain while preserving Fourier transform symmetry and energy consistency, facilitating the generation of synthetic data for various load regimes. We evaluated the method on experimental data from a 0.37 kW induction motor with broken rotor bars. The synthetic data were used to train three diagnostic models: a Multilayer Perceptron (MLP), a Convolutional Neural Network (CNN), and a hybrid CNN-MLP model. Results indicate that the proposed augmentation method enhances classification quality across different load levels. The hybrid CNN-MLP model achieved the best performance, with an F1-score of 0.98 when augmentation was employed. These findings demonstrate the practical efficacy of physics-guided spectral augmentation for induction motor fault diagnosis.