• Ramesh Kumar Prajapati
• Mohd. Ayub Ansari

Artificial intelligence, which uses Artificial neural networks (ANN) are a powerful technique that has been used as a mathematical model to process information by receiving external inputs based on the structure's information and performing functional activities similar to those of biological neural network structures.The methods used in ANN involve non-parametric algorithms which are similar to and also mimic the cognitive functions of the human brain, for example, learning and problem-solving. Techniques based on ANN modelling are currently extensively used in a number of areas of chemical engineering, science, and technology, including water and wastewater treatment, for the simulation and optimization of complex problems. It consumes less time as compared to other models, viz. transfer models, which are quicker and much more reliable in computation for designing a membrane separation. These are quite useful in cases where researchers do not have thorough feedback about the physical and chemical rules that govern systems as compared to other mathematical techniques which have been derived from applied linear algebra, such as principal component analysis (PCA). So, these tools are being used as powerful modelling tools that are applicable in the study of non-linear relationships between different features and parameters with great precision. ANN-based methods may be used in the determination of the complex relationship between input and output variables for optimising a process. In the present review, ANN modelling methods have been described that govern the estimation of membrane performance characteristics such as the permeate flux and rejection over the entire range of the process variables, such as feed concentration, temperature, pressure, pH, and superficial flow velocity, etc. These membranes are used in membrane separation such as nano filtration (NF), reverse osmosis (RO), microfiltration (MF), ultra filtration (UF), as well as in catalytic properties, extraction of metals such as nickel, etc. The data of ANN has been compared with other mathematical models such as response surface methodology (RSM) for the treatment of brackish water and green emulsion liquid membrane (GELM) used in the extraction of nickel from waste water.

Chemical engineering; membrane; modeling; artificial neural networks; artificial intelligence; separation.

"Artificial Intelligence in Membrane Science-A Review", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.1066-1083, April-2019, Available :http://www.jetir.org/papers/JETIR1904U36.pdf

"Artificial Intelligence in Membrane Science-A Review", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp1066-1083, April-2019, Available at : http://www.jetir.org/papers/JETIR1904U36.pdf