Neuro-Fuzzy Approach for Fault Prediction of Mechanical Bearing Faults Using Vibration Analysis

Electrical machines play an important role in modern industry. It has brought significant technological advancements, particularly in integrating information technology with physical devices. This fusion has led to the emergence of smart devices and the Internet of Things, transforming industrial operations. However, despite the popularity of predictive maintenance, there remains a notable gap in fault prediction algorithms for electrical machines. This paper proposes a signal spectrum-based machine learning approach for fault prediction, specifically focusing on mechanical bearing faults. Comparing traditional neural network algorithms with a novel approach integrating fuzzy logic, the study demonstrates that the fuzzy-neuro network model outperforms traditional neural networks, achieving a validation accuracy of 99.98% compared to 89.91%. Incorporating fuzzy logic within the neural network framework offers advantages in handling complex fault combinations, showing promise for applications requiring higher accuracy in fault detection.