ELECTRONIC COMPONENT FAULT DETETCTION USING MACHINE LEARNING

This project focuses on the development of an electronic component fault detection system using machine learning techniques. Traditional methods for detecting faults in electronic components often rely on manual testing, threshold-based classifiers, or statistical anomaly detection, which can be time-consuming, error-prone, and limited in their ability to identify complex or early-stage faults. The proposed system aims to address these limitations by leveraging machine learning algorithms, such as Support Vector Machines (SVM), Random Forest, and Artificial Neural Networks (ANN), to automatically analyse key electrical parameters like voltage, current, and resistance. Through feature extraction and pre-processing, followed by a train-test split, the system is trained on labelled datasets containing both healthy and faulty components. The model is optimized through hyperparameter tuning techniques like Grid Search and Bayesian Optimization. The performance of the proposed system is evaluated by comparing it to traditional fault detection methods, using metrics such as confusion matrices and ROC curves. This machine learning-based approach offers a more accurate, adaptable, and scalable solution for fault detection in electronic systems. It minimizes human intervention, reduces diagnosis time, and can be extended to various types of electronic components without requiring hardware modifications.

KEYWORDS: Electronic Component Fault Detection, Machine Learning, Support Vector Machines (SVM), Random Forest, Artificial Neural Networks (ANN), Feature Extraction, Data Pre-processing, Model Training, Hyperparameter Tuning, Threshold-based Classifier, Statistical Anomaly Detection, Fault Diagnosis, Performance Comparison, Confusion Matrix, ROC Curve, Predictive Maintenance, Electronics Testing, Automation in Fault Detection, Adaptive Systems, System Reliability, Fault Classification