Induction motors (IMs) are vital to industrial operations but are prone to electrical and mechanical faults such as bearing damage, stator winding issues, and broken rotor bars. Conventional fault diagnosis methods often rely on single-source data, which limits detection accuracy under dynamic conditions. This study presents an AI-based multi-source fault diagnosis approach using data from vibration, current, sound, and thermal sensors collected under varied load and speed conditions. Raw data was preprocessed, and features were extracted across time, frequency, and time-frequency domains for machine learning (ML) classification. For deep learning (DL), the sensor data was transformed into scalograms and fused with thermal images, which were then used to train a 2D convolutional neural network (CNN). ML models achieved up to 96% accuracy on individual sensors but showed reduced performance with data fusion. In contrast, the CNN with fused data achieved 99.2% accuracy. These results confirm the effectiveness of sensor fusion and deep learning in enhancing fault detection reliability and suggest a promising direction for intelligent predictive maintenance systems.

Predictive maintenance is increasingly important in rotating machinery to prevent unexpected failures, reduce downtime, and improve operational efficiency. This study compares the efficacy of traditional machine learning (ML) and deep learning (DL) techniques in diagnosing bearing faults under varying load and speed conditions. Two classification tasks were conducted: a simpler three-class task that distinguishes healthy bearings, inner race faults, and outer race faults, and a more complex nine-class task that includes faults of varying severity in the inner and outer races. In this study, the machine learning algorithm ensemble bagged trees, achieved maximum accuracies of 93.04% for the three-class and 87.13% for the nine-class classifications, followed by neural network, SVM, KNN, decision tree, and other algorithms. For deep learning, the CNN model, trained on scalograms (time–frequency images generated by continuous wavelet transform), demonstrated superior performance, reaching up to 100% accuracy in both classification tasks after six training epochs for the nine-class classifications. While CNNs take longer training time, their superior accuracy and capability to automatically extract complex features make the investment worthwhile. Consequently, the results demonstrate that the CNN model trained on CWT-based scalogram images achieved remarkably high classification accuracy, confirming that deep learning methods can outperform traditional ML algorithms in handling complex, non-linear, and dynamic diagnostic scenarios.