Development of an Expert System Shell Based on Genetic Algorithms for the Selection of the Energy Best Available Technologies and their Optimal Operating Conditions for the Process Industry

Abstract

The development of genetic algorithms started almost three decades ago in an attempt to imitate the mechanics of natural systems. Since their inception, they have been applied successfully as optimization methods, and as expert systems, in many diverse applications. In this paper, a genetic-algorithm-based expert system shell is presented that, when combined with a proper database comprising the available energysaving technologies for the process industry, is able to perform the following tasks: (a) identify the best available technologies (BATs) among the available ones for a given process industry, and (b) calculate their optimal design parameters in such a way that they comply with the energy requirements of the process. By the term BAT is meant the available energy-saving technology, among the existing ones in the market, that is the best for the case.

A Review of Evaluation, Optimization and Synthesis of Energy Systems: Methodology and Application to Thermal Power Plants

“…To realize automatic and computer-aided synthesis using these guidelines, a number of knowledge-based expert systems have been developed for various processes and systems, such as chemical processes [180][181][182], thermal processes [183][184][185] and renewable energy supply systems [186]. Expert systems apply various logical inference procedures, e.g., means-end analysis [187] and case-based reasoning [188], to reproduce engineers' design maps, thus suggest the best-suited process for a particular application.…”

Conceptual design of biomass-fired cogeneration plant through a knowledge-based system

“…This kind of problem can be well approached through an artificial intelligence technique known as knowledge-based system. 1 Knowledge-based systems (KBS) have been successfully applied to different engineering designs [5][6][7] and energy system designs [8][9][10][11]. This technique is also suited for analytic tasks, such as diagnostics [12].…”