Abstract
In this study, a multi-layered artificial neural network (ANN) algorithm was developed and trained to predict the performance of a solar powered liquid desiccant air conditioning (LDAC) system particularly the adiabatic packed tower dehumidifier using Lithium Bromide (LiBr) desiccant. A reinforced technique of supervised learning based on error correction principle rule coupled with perceptron convergence theorem was applied to create the algorithm. The parameters such as temperature, flow rates and humidity ratio of both air and desiccant fluid were fed as inputs to the ANN algorithm and their respective outputs used to determine dehumidifier effectiveness and moisture removal rate (MRR). The ANN model when subjected to validity tests using vapour pressure of LiBr desiccant solution at specific random temperatures and concentrations, gave astounding outcomes with precise estimation to R2 values of 0.9999 for all desiccant concentration levels. Due to the variation in solar radiation, the MRR and effectiveness fluctuated with the change in desiccant and air temperatures, giving maximum differences of 0.2 g/s and 1.8% respectively between the predicted and measured values depicting a perfect match. With respect to humidity ratio, MRR was accurately predicted by ANN algorithm with maximum difference of 3.4969% while the mean variation was −0.5957%. With respect to air temperature, the dehumidifier effectiveness was perfectly predicted by the ANN algorithm to an average accuracy of 0.53% and extreme positive deviation of 4.14%. The MRR was replicated to a mean variation of 0.013% and highest point difference of 0.08%. In all the above cases, the mean and maximum differences between the ANN model and experimental values were far below the allowable limit of ± 5%, hence the algorithm was deemed to be successful and could find use in air conditioning scenarios. The ANN algorithm’s capability and flexibility test of processing unforeseen inputs was accurate with negligible deviations and prospects of predicting the desiccant’s vapour pressure, dehumidifier effectiveness and MRR within all ranges of temperature and concentration which then eliminates the need for use of charts.
Multilayered artificial neural network for performance prediction of an adiabatic solar liquid desiccant dehumidifier
