Optimization of a multistage liquid desiccant dehumidifier by neural networks & particle swarm techniques

Abstract

To overcome the inconsistent and limited dehumidification by single stage dehumidification system, a novel multistage, reciprocating dynamic liquid desiccant dehumidification system has been proposed to dehumidify larger space consistently. Experimental investigation on the proposed unit has been conducted by varying air velocity, cam shaft speed, and inlet relative humidity (RH). System's performance in terms of moisture removal rate (MRR), dehumidification efficiency (DE) and energy consumed has been compared with that of a single stage system. It is observed that multistage system performed better than the single stage system in terms higher MRR and efficiency. To optimise the system performance, neural network-based Particle Swarm optimization (PSO) has been employed. Inertia weight distribution for PSO has been obtained by the statistical Taguchi method. PSO optimized results for randomly distributed weights have been compared with the Taguchi given weights. It is found that the performance of the PSO with this method is better than the former in terms of optimized paramters. PSO predicted optimum input variables are found as air velocity of 8.2 m/s, inlet RH of 90% and cam speed of 15.16 rpm. The maximum performance parameters obtained are MRR of 7.549 g/s, Dehumidification efficiency of 0.762 and energy consumption of 2165.4 Watts. Confirmation experiments indicated that PSO predicted results are in well agreement with the experimental results with a maximum deviation of 1.8%. Current work predicts and optimizes the dehumidification performance which minimizes experimentation time and also the cost involved.