Authors: Dr. Aakash Mehra, Prof. Neha Verma
Abstract: Machine learning (ML) techniques are increasingly being integrated into Computer-Aided Manufacturing (CAM) to enhance the predictive capability and automation of machining processes. Surface roughness is a critical metric in manufacturing, impacting product quality, performance, and cost. Traditional predictive models often fall short in capturing complex, nonlinear interactions among process parameters. This paper presents a comprehensive review and implementation strategy of machine learning algorithms—such as artificial neural networks (ANN), support vector machines (SVM), and decision trees—for predicting surface roughness in milling, turning, and grinding processes. The integration of ML within CAM environments enhances adaptability, real-time optimization, and closed-loop control, leading to superior surface finish and reduced production costs. Key challenges in data collection, model training, and real-time deployment are discussed along with recommendations for future developments in smart manufacturing systems
Keywords: Surface Roughness, Machine Learning, CAM, Artificial Neural Networks, SVM, Smart Manufacturing, Process Optimization
Full Issue
| View or download the full issue | PDF 29-33 |