Analysis and optimization of a transcritical power cycle with regenerator using artificial neural networks and genetic algorithms

This article presents a parametric study for and optimization of a transcritical power cycle. First, thermal efficiency, exergy efficiency, and specific network are selected as objective functions for parametric optimization. In order to optimize these functions, a procedure based on artificial neural networks (ANNs) and genetic algorithms (GAs) is proposed. This procedure comprises three steps. Step 1 is to find thermal efficiency, exergy efficiency, and specific network for different values of inlet turbine pressure, inlet turbine temperature, and fraction of the maximum power using the robust numerical code, engineering equation solver. In step 2, three distinct multi-layer perceptron ANNs based on the data obtained from step 1 are trained. In step 3, three distinct GAs are used to optimize the thermal efficiency, exergy efficiency, and specific network. The variables and fitness functions in these algorithms constitute, respectively, the inputs and outputs of the corresponding trained neural networks. For the purpose of validation of this study, for a special case, the results were compared with a previously reported case and were found to be in good agreement. Also in this article, this optimization process is applied to four different working fluids. Several interesting features among optimal objective functions and decision variables involved in the transcritical power cycle are identified.

artificial neural network, exergy efficiency, genetic algorithm, optimization, specific net output, thermal efficiency, transcritical power cycle