Onwubolu, Godfrey C. (2008) Modelling and predicting surface roughness in turning operations using hybrid differential evolution and the group method of data handling networks. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 222 (7). pp. 785-795. ISSN 0954-4054
Full text not available from this repository.Abstract
This paper presents a hybrid modelling approach, based on the group method of data handling (GMDH) and the differential evolution (DE) population-based algorithm, for modelling and predicting surface roughness in turning operations. Turning operations have been performed on a mild steel workpiece with a high-speed steel (HSS) tool over a wide range of cutting conditions. The results of the hybrid DE-GMDH approach are compared with the results obtained by the standard GMDH algorithm and its variants. Three case studies were examined, from which it can be concluded that the DE-GMDH algorithm generalizes best (based on the EPI value) when the input variables include the cutting conditions of speed, feed, and depth of cut, as well as the feed force and cutting force. Results presented show that the proposed DE-GMDH algorithm appears to perform better than the standard GMDH algorithm and the polynomial neural network (PNN) model for the surface roughness problem. Consequently, such a self-organizing modelling approach is useful in both modelling and prediction in an advanced manufacturing system where it is necessary to model and predict the surface roughness during machining operations. Application of such heuristics can play a major role in reducing production costs.
| Item Type: | Journal Article |
|---|---|
| Subjects: | Q Science > Q Science (General) |
| Divisions: | Faculty of Science, Technology and Environment (FSTE) > School of Engineering and Physics |
| Depositing User: | Ms Neha Harakh |
| Date Deposited: | 11 Jan 2008 00:12 |
| Last Modified: | 16 Jul 2012 08:49 |
| URI: | https://repository.usp.ac.fj/id/eprint/203 |
Actions (login required)
 |
View Item |