Optimal Predictive Maintenance Technique for Manufacturing Semiconductors using Machine Learning

As global competitiveness in the semiconductor sector intensifies, companies must continue to improve manufacturing techniques and productivity in order to sustain competitive advantages. In this research paper, we have used machine learning (ML) techniques on computational data collected from the sensors in the manufacturing unit to predict the wafer failure in the manufacturing of the semiconductors and then lower the equipment failure by enabling predictive maintenance and thereby increasing productivity. Training time has been greatly reduced through the proposed feature selection process with maintaining high accuracy. Logistic Regression, Random Forest Classifier, Support Vector Machine, Decision Tree Classifier, Extreme Gradient Boost, and Neural Networks are some of the model-building techniques that are performed in this work. Numerous case studies were undertaken to examine accuracy and precision. Random Forest Classifier surpassed all the other models with an accuracy of over 93.62%. Numerical results also show that the ML techniques can be implemented to predict wafer failure, perform predictive maintenance and increase the productivity of manufacturing the semiconductors.