Performance of Machine Learning Algorithms in Fault Diagnosis for Manufacturing Systems: A Comparative Analysis

This study presents a comparative analysis of various machine learning algorithms to evaluate their performance in diagnosing faults within automated manufacturing systems. The primary objective is to identify the most effective model for classifying equipment failures based on historical data. Several algorithms were selected, including support vector machines (SVM), Decision trees, boosting, random forest, k-nearest neighbors (KNN), stacking, and artificial neural networks. The research began with the collection of a dataset using an Arduino-based system with sensors (temperature, electrical current, differential pressure, vibration, and sound) to monitor the equipment’s operational condition. Faults were intentionally induced in a motor, an electrovalve, and a pneumatic cylinder. The data were then processed in a Python environment, undergoing normalization and dimensionality reduction. The models were evaluated through cross-validation and compared using metrics such as precision, recall, F1-score, and accuracy. Results indicated that all models performed well, with the SVM algorithm showing the best overall performance, with an average fault diagnosis accuracy of 91.62% when trained on the full dataset and 66.83% under extreme class imbalance. In contrast, decision trees demonstrated lower generalization ability. This study provides insights for future fault diagnosis research using machine learning and offers recommendations for implementing such technologies in industrial environments.