Piston Slap Condition Monitoring and Fault Diagnosis Using Machine Learning Approach

Abstract

Various internal combustion (IC) engine condition monitoring techniques exist for early fault detection and diagnosis to ensure smooth operation, increased durability, low emissions, and prevent breakdowns. A fault, such as piston slap, can damage critical components like the piston, piston rings, and cylinder liner and is among those faults that may lead to such consequences. This research has been conducted to monitor piston slap conditions by analyzing the engine vibration and acoustic emission (AE) signals. An experimental setup has been established for acquiring vibration and AE sensor signatures for various piston slap severity conditions. Time-domain features are extracted from vibration and AE sensor signatures, and among them, the best features are selected using one-way analysis of variance (ANOVA) to create machine learning (ML) models. Apart from individual sensor feature classification, the feature fusion method increases the prediction accuracy. ML algorithms used in this study for building the prediction models are classification and regression trees (CART), random forest, and support vector machine (SVM). Performance comparisons of these trained models are made using different performance measures. It is observed that about 94.95% of maximum classification accuracy is obtained in predicting the piston slap severity at different speeds and load conditions.