Optimal Decision Support System Using Multilayer Neural Networks for Incinerator Control

In the field of industrial control, there has been a significant increase in the use of AI based techniques. For various control problems there has been successful implementation of different Intelligent techniques like Fuzzy Logic, Artificial Neural Network and other Hybrids. One of the major byproducts recovered from crude oil is sulfur. Sulfur is recovered from crude oil using the Modified Clause process, upto 98 percent of the sulfur can be recovered by this method. The remaining 2 percent of the sulfur is one of the major constituents of waste gases and is released into the atmosphere. Waste gases cannot be directly released into the atmosphere as it has sulfur compounds and other harmful constituents. Oxidizing waste gases before releasing it into the atmosphere makes it safe for the environment. Oxidization of waste gases is done by the process of incineration. The incineration process requires fuel gas to achieve this. To use minimum fuel gas and to maximize oxidization, the incinerator needs to be optimized. This paper presents a neural network which is modeled for optimal control of incinerator in Sulfur Recovery Block of refineries. An Artificial Neural Network based Inverse Plant is modeled to achieve optimal control. The Neural Network model was developed by using the neural network tool box in MATLAB.