A comparative study on modelling material removal rate by ANFIS and polynomial methods in electrical discharge machining process

(BQ) The study sheds light on the powerful learning capability of ANFIS models and its superiority over the conventional polynomial models in terms of modelling complex non-linear machining processes
Nội dung trích xuất từ tài liệu:
A comparative study on modelling material removal rate by ANFIS and polynomial methods in electrical discharge machining process Computers & Industrial Engineering 79 (2015) 27–41 Contents lists available at ScienceDirect Computers & Industrial Engineering journal homepage: www.elsevier.com/locate/caie A comparative study on modelling material removal rate by ANFIS and polynomial methods in electrical discharge machining process Khalid Al-Ghamdi, Osman Taylan ⇑ King Abdulaziz University, Faculty of Engineering, Department of Industrial Engineering, P.O. Box 80204, Jeddah 21589, Saudi Arabia a r t i c l e i n f o Article history: Received 27 April 2013 Received in revised form 26 October 2014 Accepted 29 October 2014 Available online 7 November 2014 Keywords: EDM MRR Polynomial model Neuro-fuzzy model Non-conventional machining a b s t r a c t Due to the controversy associated with modelling Electrical Discharge Machining (EDM) processes based on physical laws; this task is predominantly accomplished using empirical modelling methods. The modelling studies reported in the literature deal predominantly with quantitative parameters i.e. ones with numerical levels. In fact, modelling categorical parameters has been devoted a scant attention. This study reports the results of an EDM experiment conducted on the Ti–6Al–4V alloy. Its aim was to model the relationship between the Material Removal Rate (MRR) and the parameters of the process, namely, current, pulse on-time and pulse off-time along with a categorical factor (electrode material). The modelling process was accomplished using adaptive neuro-fuzzy inference system (ANFIS) and polynomial modelling approaches. In fact, one purpose of this study was to compare the performance of these modelling approaches as no study was found contrasting their prediction capability in the literature. Regarding the polynomial model, two numerical parameters (current and pulse on-time) were declared significant in the ANOVA together with the electrode material and its interaction with pulse on-time. Thus, they were all incorporated in the developed polynomial model. Furthermore, five ANFIS models with 6, 9, 19, 21 and 51 rules were developed utilizing the first order Sugeno fuzzy approach by backpropagation neural networks training algorithm. Of these, the ANFIS model with 21 rules was the best. This model also outperformed the polynomial model remarkably in terms of predicting error, residuals range and the correlation coefficient between the experimental and predicted MRR values. The study sheds light on the powerful learning capability of ANFIS models and its superiority over the conventional polynomial models in terms of modelling complex non-linear machining processes. Ó 2014 Elsevier Ltd. All rights reserved. 1. Introduction Recent years have witnessed remarkable increase in the demand for the titanium based alloys owing to their high strength-weight ratio, excellent fracture and corrosion resistance and superior mechanical properties at elevated temperature. An extensive utilization of these alloys has been observed in the aerospace industry (Armendia, Garay, Iriarte, & Arrazola, 2010; Moiseev, 2005). Indeed, many of the aero-engine components are produced using these alloys due, in no small part, to their relatively lightweight which helps to reduce the aircraft’s overall weight thereby moderating fuel consumption (Singh & Khamba, 2007). Moreover, titanium alloys are noticeably replacing the traditionally used materials in aerospace industry such as aluminium (Lütjering & Williams, 2007). They are also used increasingly in other indus⇑ Corresponding author. Tel.: +966 500031056; fax: +966 26952486. E-mail addresses: kaaalghamdi@kau.edu.sa (K. Al-Ghamdi), otaylan@kau.edu.sa (O. Taylan). http://dx.doi.org/10.1016/j.cie.2014.10.023 0360-8352/Ó 2014 Elsevier Ltd. All rights reserved. trial and commercial applications such as, chemical processing, pollution control, surgical implantation, nuclear waste storage, food processing and petroleum refining. A major hindrance for the wider use of titanium alloys is the difficulties associated with machining them conventionally. Being chemically reactive to almost all tool materials, they tend to weld the cutting tools while machining thereby accelerating tool failure (Hartung, Kramer, & Von Turkovich, 1982). The damage to cutting tools is compounded by the fact that the heat generated at the tool-work-piece interface while machining is concentrated at the tool’s cutting edges. This heat cannot be transferred through the work-piece due to the poor thermal conductivity of titanium alloys. Moreover, a very high mechanical stress is accumulated on the immediate vicinity of the cutting edge as a result of high strength and hardness that these alloys retain at elevated temperature poses a further impediment to their machine-ability (Che-Haron & Jawaid, 2005; Trent & Wright, 2000). Ezugwu and Wang (1997) asserted that it was due to the limitations associated with machining these alloys that large companies such as Rolls-Royce and General Electric invested large 28 K. Al-Ghamdi, O. Taylan / Computers & Industrial Engineering 79 (2015) 27–41 sums of money in developing techniques to deal with them. Ezugwu, Bonney, Da Silva, and Cakir (2007) argued that, despite these limitations, machining will remain the favoured option for manufacturing complex titanium alloys at a competitive cost in the foreseeable future. Non-conventional machining processes provide effective alternatives to the conventional ones in dealing with the technical difficulties associated with machining titanium alloys. Of these, Electrical Discharge Machining (EDM) is the most widely known and used process for the manufacture of engineering components (Aspinwall, Soo, Berrisford, & Walder, 2008). In this process, the material removal takes place as a result of the discharge of energy between a tool and a work ...