FailurePredictionThroughTestingDataUsingMachine Learning Classification:ASmartPlugTopCaseStudy

Smart plug tops (SPTs) with sensing capabilities are increasingly important for real-time monitoring and diagnostics in internal combustion engines. However, the proliferation of electronic devices and system complexity can cause failures requiring investigation. This research uses machine learning (ML) to categorize various failures. The method involves collecting sensor data during SPT testing, which is then linked to failures identified through lifetime analysis. ML model uses features such as voltage levels, charge times, current levels, etc. The model is refined using a training and validation method to accurately predict various types of failures, such as electric discharge on the transformer secondary winding, damping diode breakdown, and short circuits between windings. A key challenge is the limited number of failure samples, as failures occurring rarely during the lifetime analysis. Hence, an upsampling technique was applied to improve this imbalanced dataset. The classification algorithm's performance is evaluated by accuracy, precision, recall, and F1-score. The results enable early detection of problem symptoms during acceptance testing and classification of failure probabilities.