Prediction of reactor performance in CATSOL-based sulphur recovery unit by ANN

Abstract

For the prediction Artificial Neural Network has been used, which is inspired from human biological neural network. Artificial Neural Network tool has very vast application in almost every field. ANN is a very powerful tool in the field of AI and spreading over in every field of Computer Science, IT, Refinery, Medical, etc. We have used MATLAB software for the use of built-in neural network toolbox. MATLAB platform is very user friendly and includes all the important transfer functions, training functions which helps in comparison of results with each other and allow us to predict the best result using ANN. Further, this describes application of ANN in CATSOL process. After complete study about ANN and CATSOL process, our experimental results of using different transfer functions and training functions are shown which results in the overall best network for the CATSOL process.