ANN assisted sensor fusion model to predict tool wear during hard turning with minimal fluid application. (1st January 2013)

• Record Type: Journal Article
• Authors: Sam Paul, P.; Varadarajan, A.S.
• Is Part Of: International journal of machining and machinability of materials. Volume 13:Number 4(2013)
• Page Start: 398
• Page End: 413
• Publication Date: 2013-01-01
• Subjects: hard turning -- tool wear -- artificial neural network -- ANN -- regression analysis -- sensor fusion -- minimal fluid application; Machining -- Periodicals; Metals -- Machinability -- Periodicals; 671.35
• Languages: English
• ISSNs: 1748-5711

Abstract

Accurate prediction of tool wear can be made possible if factors like cutting force, cutting temperature, acoustic emission signals and vibration signals are used effectively and collectively. Each of these factors predicts tool wear in their own characteristic fashion – high cutting temperature is an index of flank wear and crater wear, whereas variation in cutting force indicates fracture type of tool failure more effectively. Even though each of these factors can be used individually, a more accurate prediction will be possible by considering the indices of tool wear collectively rather than individually. In the present work, an attempt was made to fuse cutting force, cutting temperature and displacement of tool vibration along with cutting velocity, feed and depth of cut to predict tool wear during turning of AISI 4340 steel of 46 HRC with minimal fluid application using hard metal insert with sculptured rake face. A regression and an ANN model were developed to fuse the cutting force, cutting temperature and displacement of tool vibration signals to predict tool flank wear. From the results, it was observed that the model based on ANN was found to be superior to the regression model in its ability to predict tool wear.