Title: Two phase approach for performance analysis and optimisation of industrial systems using uncertain data
Authors: Komal; S.P. Sharma
Addresses: Department of Mathematics, School of Physical Sciences, Doon University, Dehradun-248001, Uttarakhand, India ' Department of Mathematics, Indian Institute of Technology Roorkee (IITR), Roorkee-247667, Uttarakhand, India
Abstract: In real life situation, it is difficult to achieve optimum performance of industrial systems for desired industrial goals using available resources. This is due to the complexity of industrial systems and nonlinearity in their behaviour. In this paper, a two-phase approach has been developed for achieving optimum performance of any industrial system. In the first phase of the presented approach, system performance is analysed in terms of six well known reliability indices by applying fuzzy lambda-tau (FLT) and genetic algorithms-based lambda-tau (GABLT) techniques utilising available uncertain data. In the second phase, a fuzzy multi-objective optimisation problem (FMOOP) has been formulated using first phase results. The obtained FMOOP is further reformulated to an equivalent crisp optimisation problem by taking care of preferences as suggested by decision maker (DM)/management personnel and then solved by using genetic algorithms (GA). The presented two-phase approach is applied to a bleaching system of a paper mill. A decision support system has been developed for achieving system optimum performance. The obtained results may be used for planning the future course of action to optimise system performance.
Keywords: performance optimisation; system behaviour; reliability indices; GABLT technique; fuzzy multi-objective optimisation problem; FMOOP; genetic algorithm.
International Journal of Operational Research, 2018 Vol.31 No.1, pp.88 - 111
Available online: 23 Nov 2017 *Full-text access for editors Access for subscribers Free access Comment on this article