Using soft computing methods as an effective tool in predicting surface roughness
The aim of this research is to compare between two different approaches in predicting and modeling the surface roughness in high speed hard turning: regression analysis approach and soft computing approach. Three different soft computing techniques have been applied: Support vector machine (SVM,) Ex...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
The Institute of Electrical and Electronics Engineers, Inc.
2016
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/46494/ http://irep.iium.edu.my/46494/ http://irep.iium.edu.my/46494/ http://irep.iium.edu.my/46494/1/46494_using_soft_computing.pdf http://irep.iium.edu.my/46494/4/46494-Using%20soft%20computing%20methods%20as%20an%20effective%20tool%20in%20predicting%20surface%20roughness_SCOPUS.pdf |
| Summary: | The aim of this research is to compare between two different approaches in predicting and modeling the surface roughness in high speed hard turning: regression analysis approach and soft computing approach. Three different soft computing techniques have been applied: Support vector machine (SVM,) Extreme learning machine (ELM) and Artificial neural network (ANN). A set of sparse experimental have been conducted in turning hardened steel (AISI 4340) by using mixed ceramic tools made up of aluminum oxide and titanium carbide as cutting tool. Design for experiment (DoE) 8.0 software and JMP Software have been used to design the experiment and to analyses the results statistically. Full Factorial Design (FFD) has been applied for the experiment design. The experimental work was conducted under dry cutting conditions with three cutting parameters: cutting speed, feed rate, and negative rake angle with a constant depth of cut. The results show a better and more accurate estimation for the soft computing methods |
|---|