TY  - EJOU
AU  - Manghai, T. M. Alamelu 
AU  - Jegadeeshwaran, R. 

TI  - Feature-Based Vibration Monitoring of a Hydraulic Brake System Using Machine Learning
T2  - Structural Durability \& Health Monitoring

PY  - 2017
VL  - 11
IS  - 2
SN  - 1930-2991

AB  - Hydraulic brakes in automobiles are an important control component used not only for the safety of the passenger but also for others moving on the road. Therefore, monitoring the condition of the brake components is inevitable. The brake elements can be monitored by studying the vibration characteristics obtained from the brake system using a proper signal processing technique through machine learning approaches. The vibration signals were captured using an accelerometer sensor under a various fault condition. The acquired vibration signals were processed for extracting meaningful information as features. The condition of the brake system can be predicted using a feature based machine learning approach through the extracted features. This study focuses on a mechatronics system for data acquisitions and a signal processing technique for extracting features such as statistical, histogram and wavelets. Comparative results have been carried out using an experimental study for finding the effectiveness of the suggested signal processing techniques for monitoring the condition of the brake system. 
KW  - Vibration signals
KW  - statistical features
KW  -  histogram features
KW  -  wavelet decomposition
KW  -  machine learning
KW  -  decision tree

DO  - 10.3970/sdhm.2017.011.149