An Improved Fault Diagnosis Strategy for Induction Motors Using Weighted Probability Ensemble Deep Learning

2024-12-24

AI Summary

To address early fault diagnosis of industrial induction motor bearings, rotors, and stators, this paper proposes a Weighted Probabilistic Ensemble Deep Learning (WPEDL) framework—the first to enable end-to-end joint diagnosis using dual-modal vibration and current signals. Methodologically, the framework integrates short-time Fourier transform (STFT)-derived time-frequency features with convolutional neural network (CNN) feature extraction capabilities, and employs dynamic probabilistic weighting to ensemble multiple base models, thereby enhancing generalization and robustness. Evaluated on a hybrid dataset comprising 52,000 STFT images, WPEDL achieves an overall classification accuracy of 98.89%, with individual fault-class accuracies exceeding 99.0%—reaching up to 99.60% for stator faults diagnosed via current signals. This work pioneers the integration of dual-modal sensing and probabilistic ensemble learning in early motor fault diagnosis, delivering a high-accuracy, interpretable solution for intelligent industrial equipment maintenance.

Technology Category

• Machine Learning: Ensemble Methods
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Early detection of faults in induction motors is crucial for ensuring uninterrupted operations in industrial settings. Among the various fault types encountered in induction motors, bearing, rotor, and stator faults are the most prevalent. This paper introduces a Weighted Probability Ensemble Deep Learning (WPEDL) methodology, tailored for effectively diagnosing induction motor faults using high-dimensional data extracted from vibration and current features. The Short-Time Fourier Transform (STFT) is employed to extract features from both vibration and current signals. The performance of the WPEDL fault diagnosis method is compared against conventional deep learning models, demonstrating the superior efficacy of the proposed system. The multi-class fault diagnosis system based on WPEDL achieves high accuracies across different fault types: 99.05% for bearing (vibrational signal), 99.10%, and 99.50% for rotor (current and vibration signal), and 99.60%, and 99.52% for stator faults (current and vibration signal) respectively. To evaluate the robustness of our multi-class classification decisions, tests have been conducted on a combined dataset of 52,000 STFT images encompassing all three faults. Our proposed model outperforms other models, achieving an accuracy of 98.89%. The findings underscore the effectiveness and reliability of the WPEDL approach for early-stage fault diagnosis in IMs, offering promising insights for enhancing industrial operational efficiency and reliability.

Problem

• Induction Motor
• Early Fault Detection
• Condition Monitoring

Innovation

• WPEDL
• STFT Feature Extraction
• Induction Motor Fault Detection