Global optimization algorithms applied to solve a multi-variable inverse artificial neural network to improve the performance of an absorption heat transformer with energy recycling

摘要

In this research, global optimization algorithms were applied to solve the inverse artificial neural network (ANNi) for obtaining the best inputs values of an absorption heat transformer with energy recycling (AHTER) and improving its performance. The ANNi was obtained by inverting an artificial neural network (ANN) which architecture was 16 input variables, 3 neurons in the hidden layer and 1 output variable. The ANNi's aim was optimizing 1, 2, 3, and up to 4 manipulated input variables, as well as calculating the other 12 input variables not manipulated in the system (AHTER) considering a coefficient of performance (COP) desired. The Cuckoo Search (CS), Particle Swarm Optimization (PSO), Genetic Algorithm (GA) and Simulated Annealing (SA) algorithms were used to find the optimal inputs. The results showed that the four algorithms used (ANNi-CS, ANNi-PSO, ANNi-GA, and ANNi-SA) satisfactorily optimize of 1 up to 16 inputs of the ANNi. However, the algorithms of ANNi-CS and ANNi-SA were slightly faster with acceptable accuracy. Additionally, they were carried out two analyses using different COPs values. These analyses showed that both algorithms optimize the AHTER's inputs for different COP, as well as R > 0.988 were obtained with the COP experimental data against COP obtained data by both ANNi models. (C) 2019 Elsevier B.V. All rights reserved.