Abstract
This paper presents method of vibration based continuous monitoring system and analysis using machine learning approach. The reliable and effective performance of a braking system is fundamental operation of most vehicles. This study provides insight of fault diagnosis of hydraulic braking system by vibration analysis. A hydraulic brake system test rig was fabricated. The vibration signals were acquired from a piezoelectric transducer for both good as well as faulty conditions of brakes. The statistical parameters are extracted and the good features that discriminate different faulty conditions were formed using decision tree. This study presents the data model (J48, C4.5 decision tree algorithm) for fault diagnosis through descriptive statistical features extracted from vibration signals of good and faulty conditions of hydraulic brakes. The classification results of decision tree algorithm for fault diagnosis of a hydraulic brake system are presented. The model built can be used for condition monitoring of hydraulic brake system. The classification accuracy for decision tree algorithm using statistical features is found to be 97.45%.
Keywords: C4.5 decision tree algorithm, statistical features, confusion matrix.
21