Soft Computing Techniques for the Prediction of Hybrid Composites
C. Kavitha
C. Kavitha, Department of Mathematics, Sathyabama Institute of Science and Technology, Chennai, Tamil Nadu, India.
Manuscript received on January 13, 2020. | Revised Manuscript received on January 24, 2020. | Manuscript published on February 10, 2020. | PP: 2717-2720 | Volume-9 Issue-4, February 2020. | Retrieval Number: D1928029420/2020©BEIESP | DOI: 10.35940/ijitee.D1928.029420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Soft computing techniques such as Artificial Neural Networks and Fuzzy logic are widely used in application of manufacturing technology. Surface roughness plays a vital role for quality of the product using machining parameters. Soft computing techniques are applied to predict the surface roughness in an economical manner. In this paper, prediction of surface roughness is evaluated using ANFIS [Adaptive Neuro-Fuzzy Inference System] methodology for the cutting parameters of end-milling process for machining the halloysite nanotubes (HNTs) with aluminium reinforced epoxy hybrid composite material. Experimental datas are used to analyse the relationship between the input parameter such as depth of cut (d), cutting speed (S), feed-rate (f) and output parameters as surface roughness. Datas are classified into training and testing with different types of membership functions. The observed results accurately predict the output which was not used in training and it is almost very close to the actual output obtained in the experimental work. Moreover it was found that gbellmf is helpful for better prediction with minimum error.
Keywords: ANFIS, Hallosyite Nanotubes, Surface Roughness, Depth of cut, Cutting Speed and Feed rate.
Scope of the Article: Soft Computing