Prediction of fusion-based tool wear with signals from inbuilt sensor turning tool. (17th April 2019)

• Record Type: Journal Article
• Authors: Paul, P. Sam; Shylu, D.S.; Varadarajan, A.S.
• Is Part Of: International journal of advanced mechatronic systems. Volume 7:Number 6(2017)
• Page Start: 368
• Page End: 377
• Publication Date: 2019-04-17
• Subjects: cutting force -- cutting temperature -- tool vibration -- tool wear -- hard turning -- artificial neural network -- ANN -- linear regression -- sensor fusion; Mechatronics -- Periodicals; 629.89
• Languages: English
• ISSNs: 1756-8412

Abstract

In metal cutting, tool wear is a critical parameter which can lead to machine down time, product discards and problems to human personnel. High cutting force, excessive cutting temperature and tool vibration of considerable magnitude form indications of tool wear. In this investigation, an attempt was made to fabricate a tool holder with inbuilt sensors that can sense these signals during turning of AISI 4340 steel having a hardness of 46 HRC using multicoated hard metal inserts with sculptured rake face. The signals received from tool with inbuilt sensors were synthesised by an artificial neural network model that can be trained to predict tool flank wear as a fusion product during turning of hardened steel. Cutting experiments were conducted to check and test the experimental, predicted results. From the results, it was found that the signals obtained from the tool with inbuilt sensors matched well with the signals of the dynamometer and also the predictions of the fusion model developed matched well with the experimental results. This scheme is simple in construction, cost effective and holds promise as a means for tool condition monitoring during automated turning operations.