Developing and Implementation of an Optimization Technique for Solar Chimney Power Plant With Machine Learning

Abstract

Green energy has seen a huge surge of interest recently due to various environmental and financial reasons. To extract the most out of a renewable system and to go greener, new approaches are evolving. In this paper, the capability of Artificial Neural Network and Adaptive Neuro-Fuzzy Inference System in geometrical optimization of a solar chimney power plant (SCPP) to enhance generated power is investigated to reduce the time cost and errors when optimization is performed with numerical or experimental methods. It is seen that both properly constructed artificial neural networks (ANN) and adaptive-network-based fuzzy inference system (ANFIS) optimized geometries give higher performance than the numerical results. Also, to validate the accuracy of the ANN and ANFIS predictions, the obtained results are compared with the numerical results. Both soft computing methods over predict the power output values with MRE values of 12.36% and 7.25% for ANN and ANFIS, respectively. It is seen that by utilizing ANN and ANFIS algorithms, more power can be extracted from the SCPP system compared to conventional computational fluid dynamics (CFD) optimized geometry with trying a lot more geometries in a notably less time when it is compared with the numerical technique. It is worth mentioning that the optimization method that is developed can be implemented to all engineering problems that need geometric optimization to maximize or minimize the objective function.