Integration of the Intelligent Optimisation Algorithms with the Artificial Neural Networks to predict the performance of a counter flow wet cooling tower with rotational packing

Abstract

The present study investigated a counter-flow cooling tower performance by integrating the Artificial Neural Networks and Intelligent Optimisation Algorithms (ANN-IOAs). For this purpose, two scenarios were evaluated. In the first scenario, inlet air wet-bulb temperature (T_aw), inlet air dry bulb temperature (T_ad), water to the air mass flow rate ratio (m_w/m_a), and rotor speed (υ) were the input parameters for the ANNs, while the output temperature (T_wo) was the ANNs output. In the second scenario, the same input parameters applied for the first scenario were used as input variables and the tower efficiency (ε) was considered as an output parameter. The well-known IOAs methods, namely, Genetic Algorithm (GA), Particle Swarm Optimisation (PSO) and Bees Algorithm (BA), were used to optimise the ANNs for both scenarios. The obtained results showed remarkable accuracy for the proposed ANNs. The designed ANN model based on the BA method predicted the most efficient results. A sensitivity analysis was performed to study the most effective input parameters on the output temperature and the tower efficiency. Finally, for demonstrating the accuracy of the proposed ANN models for each case, a fair comparison is made between the proposed ANN models and regression models.

KEYWORDS:

• Artificial Neural Networks (ANNs)
• counter-flow wet cooling tower
• Genetic Algorithm (GA)
• Particle Swarm Optimisation (PSO)
• Bees Algorithm (BA)
• rotational packing

Disclosure statement

No potential conflict of interest was reported by the author(s).