Hybrid CNN-BiLSTM-MHSA Model for Accurate Fault Diagnosis of Rotor Motor Bearings

Abstract

Rotor motor fault diagnosis in Unmanned Aerial Vehicles (UAVs) presents significant challenges under variable speeds. Recent advances in deep learning offer promising solutions. To address challenges in extracting spatial, temporal, and hierarchical features from raw vibration signals, a hybrid CNN-BiLSTM-MHSA model is developed. This model leverages Convolutional Neural Networks (CNNs) to identify spatial patterns, a Bidirectional Long Short-Term Memory (BiLSTM) network to capture long- and short-term temporal dependencies, and a Multi-Head Self-Attention (MHSA) mechanism to highlight essential diagnostic features. Experiments on raw rotor motor vibration data preprocessed with Butterworth band-stop filters were conducted under laboratory and real-world conditions. The proposed model achieves 99.33% accuracy in identifying faulty bearings, outperforming traditional models like CNN (93.33%) and LSTM (62.00%) and recent advances including CNN-LSTM (98.87%), the Attention Recurrent Autoencoder hybrid Model (ARAE) (66.00%), Lightweight Time-focused Model Network (LTFM-Net) (96.67%), and Wavelet Denoising CNN-LSTM (WDCNN-LSTM) (96.00%). The model’s high accuracy and stability under varying conditions underscore its robustness, making it a reliable solution for rolling bearing fault diagnosis in rotor motors, particularly for dynamic UAV applications.