Modeling of a hybrid stirling engine/desalination system using an advanced machine learning approach

Abstract

In this study, the performance of a hybrid power/freshwater generation system is modeled using a coupled artificial neural network (ANN) model with a pelican algorithm (PA). The proposed system is composed of a Stirling engine fixed to a solar dish, a desalination unit, and a thermoelectric cooler. The Stirling engine is used to generate the electricity required to operate the electrical-powered components of the system as well as to preheat the saline water. The thermoelectric cooler is used to supply the saline water with additional heat as well as to cool the condensation surface of the desalination unit. The performance of the proposed system in terms of water yield, generated power, and system efficiency was considered as the model’s output; while the solar irradiance and dish diameter were considered as the model’s inputs. In addition to the pelican algorithm, a conventional gradient descent optimizer was employed as an internal optimizer of the ANN model. The prediction accuracy of the two models was compared based on different accuracy measures. The ANN-PA outperformed the conventional ANN model in predicting the water yield, generated power, and system efficiency. The computed root mean square errors of the ANN and ANN-PA models were (1.982 L, 104.863 W, and 1.227%) and (0.019 L, 1.673 W, and 0.047%) for water yield, generated power, and system efficiency, respectively.