Development of a Prediction Model for Optimized Surface Roughness in Face Milling Operation Using Recurrent Neural Network Technique

Rao, Karthik M C and Malaghan, Rashmi L and Kumar, Arun S and Rao, Srikantha S (2015) Development of a Prediction Model for Optimized Surface Roughness in Face Milling Operation Using Recurrent Neural Network Technique. International Journal of Applied Engineering Research, 10 (11). pp. 10474-10480. ISSN 0973-4562

[img] PDF
Development of a Prediction Model for Optimized Surface Roughness in Face Milling Operation Using Recurrent Neural Network Technique.pdf - Published Version
Restricted to Registered users only

Download (847kB) | Request a copy
Official URL: http://www.ripublication.com

Abstract

Amelioration demand for quality in metal cutting related products has resulted in the manufacturing industries to cornerstone on ceaselessenhancement in quality control measures as applied to machining process. Meticulous prediction of surface quality for a particular material during face milling operation is highly important for the purpose of controlling product quality and production rate. Scrutiny concerns with development of an intelligent strategy to predict and optimize the cutting parameters for better quality of surface finish. The technique has been developed to measure the force during the face milling operation. The measured cutting force is used to predict the quality of the surface finish along with the cutting parameters through artificial neural networks. Optimization of the cutting parameters has been carried out through the desirability criteria. Power consumption of each motor has been studied and their best usage utilization suggested for optimization

Item Type: Article
Uncontrolled Keywords: Artificial Neural networks, Cutting Force, Face Milling, Optimization, Surface Roughness.
Subjects: Engineering > MIT Manipal > Mechatronics
Depositing User: MIT Library
Date Deposited: 18 Jul 2017 08:32
Last Modified: 18 Jul 2017 08:32
URI: http://eprints.manipal.edu/id/eprint/149387

Actions (login required)

View Item View Item