Prediction and Analysis of Dew Point Indirect Evaporative Cooler Performance by Artificial Neural Network Method

The artificial neural network method has been widely applied to the performance prediction of fillers and evaporative coolers, but its application dew point indirect coolers is rare. To fill this research gap, a novel model for cooler based on back propagation was established using Matlab2018. Simulation test date in moderately humid region Yulin City (Shaanxi Province, China) finds that: root mean square error evaporation efficiency 3.1367, r2 0.9659, which within acceptable range. However, relative individual data (sample 7) little bit large, close 10%. In order improve accuracy model, an optimized particle swarm optimization established. generally smaller than that BP especially sample 7. It concluded more suitable solving problem cooling units.