An optimized PSO-ANN model for improved prediction of water treatment desalination plant performance

An accurate prediction of the performance of water treatment desalination plants could directly improve the global socio-economic balance. In this regard, many researchers have been engaged in the various artificial intelligence applied soft computing techniques to predict actual process outcomes. Inspired by the significance of such techniques, an optimized Particle Swarm Optimization based Artificial Neural Network (PSO-ANN) technique has been proposed herewith to predict an accurate performance of the reverse osmosis (RO) based water treatment desalination plants. Literature suggests that the improvements of the soft computing models depend on their modeling parameters. Therefore, we have included an extended list of nine modeling parameters with a systematic indepth investigation to explore their optimal values. Finally, the model's simulations results (R2 = 99.1%, Error = 0.006) were found superior to the existing ANN models (R2 = 98.8%, Error = 0.060), with the same experimental datasets. Additionally, the simulation results recommend that among many parameters considered, the number of hidden layer nodes (n), swarm sizes (SS), and the weight of inertia (ω) play a major role in the model optimization. This study for a more accurate prediction of the plant's performance shall pave the way for the process design and control engineers to improve the plant efficiency further.