Health Monitoring of Dry Clutch System Using Deep Learning Approach

Abstract

Clutch is one of the most significant components in automobiles. To improve passenger safety, reliability and economy of automobiles, advanced supervision and fault diagnostics are required. Condition Monitoring is one of the key divisions that can be used to track the reliability of clutch and allied components. The state of the clutch elements can be monitored with the help of vibration signals which contain valuable information required for classification. Specific drawbacks of traditional fault diagnosis techniques like high reliability on human intelligence and the requirement of profes-sional expertise, have made researchers look for intelligent fault diagnosis techniques. In this article, the classification performance of the deep learning technique (employing images plotted from vibration signals) is compared with the machine learning technique (using features extracted from vibration signals) to identify the most viable solution for condition monitoring of the clutch system. The overall experimentation is carried out in two phases, namely the deep learning phase and the machine learning phase. Overall, the effectiveness of the pre-trained networks was assessed and compared with machine learning algorithms. Based on the comparative study, the best-performing technique is recommended for real-time application.