Simulation of thermodynamic systems using soft computing techniques

Abstract

An exact thermodynamical analysis of systems is only possible under several assumptions; each of them brings an uncertainty in the solution. Without these assumptions, a thermodynamical analysis of a real application requires thousands of nonlinear equations, whose solution is either almost impossible or takes too much computational time and effort. To overcome this obstacle, the artificial neural network (ANN) and fuzzy logic are magic tools, in particular to analyse the systems for arbitrary input and output patterns. This paper deals with the ANN and fuzzy logic analysis of various thermodynamic systems. The first is an efficiency and emission modelling of a stationary natural gas engine using an ANN model, which is able to obtain the effect of various operational parameters such as charge-pressure and temperature, air fuel equivalence ratio, combustion-start and duration and combustion form on the engine efficiency and NO, emission. The second is a cogeneration power plant with three gas turbines, one steam turbine and a district heating system. The effects of ambient-pressure and temperature, relative humidity, wind-velocity and direction on the plant power are investigated using the ANN model, which is based on the measured data from the plant. The last example is a dryer machine. The dryer machine is modelled first as a thermodynamical system. Then a fuzzy logic model is developed to predict the drying time and the power demand depending on condensation pressure and -temperature and evaporation pressure. All models studied here give very accurate and fast estimations which are comparable with the experimental results. Copyright (c) 2005 John Wiley & Sons, Ltd.