Condition monitoring has emerged as an important technique in manufacturing industries for predictive maintenance and on-line monitoring of the processes and equipment. Because of the accessibility of sensors and sign handling innovation, actualizing condition observing frameworks in an assembling domain has turned out to be simple. In this investigation, a straightforward gadget used to quantify the sharpness of the rough particles of the crushing wheel is planned and created with a target of distinguishing the pounding wheel conditions. The sharpness of the crushing wheel is one of the significant variables for accomplishing the required surface geometry in the completed work-piece. Crushing wheel conditions are set up utilizing the pounding wheel life cycle plot, for the whole granulating cycle. A test arrangement has been built up to catch AE flag in an auto-feed surface granulating procedure utilizing Aluminium Oxide pounding wheel. AE time-area highlights are extricated utilizing AE-WIN programming. Highlight choice has been done by breaking down the sign in the time area. RMS and Energy highlights are found to have great connection with crushing wheel conditions. Factual AI classifiers, for example, Artificial Neural Network, Fuzzy frameworks, and Neuro-Fuzzy frameworks are utilized to anticipate the crushing wheel conditions. Results shows, ANN and Fuzzy and Neuro-Fuzzy frameworks can foresee the pounding wheel condition with great precision.
Atul Singh and Ashok Sharma. “The Experiment for Establishing Setup to Acquire the AE Signatures from the Surface Grinding Process” United International Journal for Research & Technology (UIJRT) 1.1 (2019): 01-09.