Fuzzy Sets and Systems 148 (2004) 487–504 www.elsevier.com/locate/fss Design of a genetic-fuzzy system to predict surface nish and power requirement in grinding Arup Kumar Nandi, Dilip Kumar Pratihar ∗ Central Mechanical Engineering Research Institute, Durgapur -713 209, W.B., India Received 20 December 2001; received in revised form 26 September 2003; accepted 9 October 2003 Abstract We have developed, in this paper, a genetic-fuzzy system, in which a genetic algorithm (GA) is used to improve the performance of a fuzzy logic controller (FLC). The performance of an FLC depends on its knowledge base (KB), which consists of both the data base (membership function distributions of the variables) as well as rule base. In the developed genetic-fuzzy system, the KB of the FLC is optimized, o-line, using a GA. Three approaches are developed, in the present work. In the rst approach, the membership function distributions of the variables are assumed to be triangular, whereas a second-order polynomial function and a third-order polynomial function are used in the second and third approaches, respectively. The results of these approaches are compared for making prediction of surface nish and power requirement in grinding, a machining process used to generate smooth surface on the job. For some of the test cases, comparisons are also made of the results predicted by the genetic-fuzzy system with those obtained through the real experiments. c  2003 Elsevier B.V. All rights reserved. Keywords: Application-production research; Genetic-fuzzy system; Prediction; Grinding; Surface nish; Power requirement 1. Introduction Fuzzy logic controller (FLC), a successful application of fuzzy set theory [22], is a powerful tool for dealing with imprecision and uncertainty [6]. The FLCs have been developed by various researchers after realizing their potential in solving real-world complex problems. Now-a-days, the FLCs are used in many consumer products also, particularly in Japan, Korea, Europe and USA. The performance of an FLC depends on its knowledge base (KB). The input and output variables of * Corresponding author. Department of Mechanical Engineering, Indian Institute of Technology, Kharagpur-721 302, W.B., India. Tel.: +91-3222282992; fax: +91-3222282278. E-mail addresses: nandiarup@yahoo.com (A.K. Nandi), dkpra@mech.iitkgp.ernet.in, dilippratihar@mailcity.com (D.K. Pratihar). 0165-0114/$ - see front matter c  2003 Elsevier B.V. All rights reserved. doi:10.1016/j.fss.2003.10.001