Skip navigation
Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMahadeva R.-
dc.contributor.authorManik, Gaurav-
dc.contributor.authorVerma O.P.-
dc.contributor.authorGoel A.-
dc.contributor.authorKumar S.-
dc.contributor.editorPant M.-
dc.contributor.editorSharma T.K.-
dc.contributor.editorVerma O.P.-
dc.contributor.editorSingla R.-
dc.contributor.editorSikander A.-
dc.identifier.citationAdvances in Intelligent Systems and Computing, 2020, 1209- 1219-
dc.description.abstractNowadays, among various water treatment and desalination technologies such as reverse osmosis (RO), multi-effect distillation (MED), and multi-stage flash (MSF), RO is an appropriate and suitable technology in the world. It is extremely used technology (>60%) around the globe. It is quite popular in separation and filtering process, especially for drinking water services as well as industrial applications. Modelling and simulation of such plants are necessary for better analysis and understanding with minimum effort, energy, and time. It involves various machine learning techniques such as an artificial neural network (ANN), support vector machine (SVM). Among these techniques, ANN is one of the best and reliable techniques, which provides good results. ANN may be learned through numerous training algorithms such as back-propagation (BP), particle swarm optimization (PSO); PSO-ANN learning algorithm generated the optimal values of initial weights and biases and to train the network. In this article, experimental datasets of RO plants have been collected from the literature and the regression coefficient (R) along with minimum mean square error (MSE) are evaluated. Four input variables (temperature T (°C), pressure P (MPa), feed concentration C (Mg/L), and pH) and three output variables (water recovery (%), total dissolved solids (TDS) rejection (%), and specific energy consumption (SEC) (kWh/m )) are considered for analysis. The simulated results observed better regression coefficients (R) (0.98557, 0.96016, and 0.97118) with minimum MSE (0.5502%, 0.9389%, and 1.5755%), respectively, corresponding to output variables of the RO plant. -
dc.relation.ispartofAdvances in Intelligent Systems and Computing-
dc.relation.ispartofProceedings of 3rd International Conference on Soft Computing: Theories and Applications, SoCTA 2020-
dc.subjectArtificial neural network (ANN)-
dc.subjectModelling and simulation-
dc.subjectParticle swarm optimization (PSO)-
dc.subjectReverse osmosis-
dc.subjectComputation theory-
dc.subjectEnergy utilization-
dc.subjectLearning systems-
dc.subjectMean square error-
dc.subjectNeural networks-
dc.subjectPotable water-
dc.subjectReverse osmosis-
dc.subjectSoft computing-
dc.subjectSupport vector machines-
dc.subjectWater treatment-
dc.subjectDesalination technologies-
dc.titleModelling and Simulation of Reverse Osmosis System Using PSO-ANN Prediction Technique-
dc.typeConference Paper-
dc.affiliationMahadeva, R., Department of Polymer and Process Engineering, Indian Institute of Technology Roorkee, Roorkee, Uttarakhand 247667, India-
dc.affiliationManik, G., Department of Polymer and Process Engineering, Indian Institute of Technology Roorkee, Roorkee, Uttarakhan-
dc.description.correspondingauthorManik, G.; Department of Polymer and Process Engineering, India; email:
dc.identifier.conferencedetailsProceedings of 3rd International Conference on Soft Computing: Theories and Applications, SoCTA 2020,21-23 December 2018-
Appears in Collections:Conference Publications [PE]

Files in This Item:
There are no files associated with this item.
Show simple item record

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.