Publication Type : Conference Paper
Publisher : Trends in Manufacturing and Engineering Management
Source : Trends in Manufacturing and Engineering Management (Lecture Notes in Mechanical Engineering), Springer Singapore, Singapore (2021)
Url : https://link.springer.com/chapter/10.1007/978-981-15-4745-4_45
ISBN : 9789811547454
Keywords : Acoustic emission (AE), ANN, Grinding, Machine learning classifiers
Campus : Coimbatore
School : School of Engineering
Department : Mechanical Engineering
Year : 2021
Abstract : Grinding is one of the important secondary manufacturing processes used to improve the dimensional accuracy, surface finish and geometric form of the component. Grinding wheel consists of abrasive particles, which perform the metal removal function. The sharpness of the grinding wheel is one of the important factors for achieving the required surface geometry in the component. In this study, a simple device used to measure the sharpness of the abrasive particles of the grinding wheel is designed and fabricated. Aluminium oxide grinding wheel conditions are established using the sharpness of the abrasive grinding wheel. Grinding process is monitored using acoustic emission (AE) Sensor. AE features are extracted in time domain and dominated features which contain useful information about the grinding wheel that are identified. A correlation between grinding wheel condition and AE feature is established using ANN-based machine learning classifier.
Cite this Research Publication : J. Revant, Kumar, R. Sree, K. Ramesh Kumar, and Mouli, D. S. B., “Acoustic Emission-Based Grinding Wheel Sharpness Monitoring Using Machine Learning Classifier”, in Trends in Manufacturing and Engineering Management (Lecture Notes in Mechanical Engineering), Singapore, 2021.