Prediction of Optimum Cutting Conditions in Dry Turning Operations of S45C Mild Steel using AIS and PSO Intelligent Algorithm

Minhat, Mohamad and Abd Rahman, Md Nizam and Abbas, Adnan Jameel (2014) Prediction of Optimum Cutting Conditions in Dry Turning Operations of S45C Mild Steel using AIS and PSO Intelligent Algorithm. In: international symposium on Research in Innovation and Sustainability 2014 (ISoRIS2014), 15-16 October 2014, Malacca.

[img] PDF (Prediction of Optimum Cutting Conditions in Dry Turning Operations of S45C Mild Steel using AIS and PSO Intelligent Algorithm)
Adnan_jameel_ISORIS14_CONFERENCE.pdf - Published Version
Restricted to Repository staff only until 1 April 2020.

Download (256kB) | Request a copy

Abstract

This study presents an approach for modeling and predicting the cutting zone temperature, surface roughness and cutting time when dry turning S45C mild steel is used with SPG 422 tungsten carbide tools. The suggested system is based on Particle Swarm Optimization (PSO) and Artificial Immune System (AIS) intelligent algorithms. S45C Mild steel bars are machined at different cutting conditions (cutting speeds, feed rates and depths of cut) without the use of cutting fluid. AIS and PSO results have been experimentally trained to find cutting zone temperature, surface roughness and cutting time by using the parameters directly on a CNC turning machine. The tests were conducted on a CNC turning machine type HAAS AUTOMATION SL 20. An infrared camera (Flir E60), a lathe tool dynamometer model USL-15 and a portable surface roughness device were respectively used to measure temperatures, cutting forces and surface roughness. The results predicted by AIS and PSO were compared with the experimental values derived from the testing data set. Testing results indicated that the predicted and experimental results are approximately similar and that suggested system can be used to estimate the cutting temperature, surface roughness and cutting time in the turning operation with high accuracy. Experimental results showed that the average accuracy of the AIS algorithm is 94.37 %, whereas that of the PSO algorithm is 92.84 % which indicated that the two percentages are convergent.

Item Type: Conference or Workshop Item (Paper)
Subjects: T Technology > TJ Mechanical engineering and machinery
T Technology > TS Manufactures
Divisions: Faculty of Manufacturing Engineering > Department of Manufacturing Process
Depositing User: Dr. Mohamad Minhat
Date Deposited: 19 Nov 2014 01:34
Last Modified: 28 May 2015 04:32
URI: http://eprints.utem.edu.my/id/eprint/13546
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item