Machine Learning-Based Modelling and Predictive Maintenance of Turning Operation under Cooling/Lubrication for Manufacturing Systems

• Published in: Advances in materials science and engineering Vol. 2022; pp. 1 - 10
• Main Authors: Singh, Gurpreet, Appadurai, Jothi Prabha, Perumal, Varatharaju, Kavita, K., Ch Anil Kumar, T., Prasad, DVSSSV, Azhagu Jaisudhan Pazhani, A., Umamaheswari, K.
• Format: Journal Article
• Language: English
• Published: New York Hindawi 2022; Hindawi Limited; Wiley
• Subjects: Algorithms; Artificial intelligence; Compressed air; Cooling systems; Cutting force; Cutting parameters; Cutting speed; Datasets; Feed rate; Gaussian process; Lubricants & lubrication; Lubrication systems; Machine learning; Machine tools; Manufacturing; Metal cutting; Polynomials; Predictive maintenance; Regression; Support vector machines; Turning (machining)
• ISSN: 1687-8434; 1687-8442
• DOI: 10.1155/2022/9289320

Cutting force is one of the significant parameters in the metal cutting process. The metal cutting process is the primary in the production and manufacturing industry to produce high-quality products. Every production and manufacturing needs to develop a technology, i.e., a cooling or lubrication system at the cutting zone while doing the metal cutting process. This current work focuses on developing the machine learning algorithm by using three different types of regression processes, namely, polynomial regression process (PR), support vector regression (SVR), and gaussian process regression (GPR). These three processes are developed to predict the machine learning force, cutting power, and cutting pressure by controlling primary factors (cutting speed, depth of cut, and feed rate). The cooling or lubrication process also affects the machining process. We need to maintain the minimum qualifications to perform under minimum quality lubrication (MQL) and high-pressure coolant (HPC). The ANN algorithm was used to run different parameters, and these parameters are optimized for cutting force.