Investigation of Intelligent Controllers for A Non Linear Chemical Process
Loading...
Date
item.page.authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The neutralization of pH is a typical problem found in a variety of industries, including pharmaceuticals, biotechnology, and chemical processing. High performance and robust pH control is often diand#64259;cult to achieve due to its nonlinear characteristics. Numerous schemes have been employed to handle this non-linear process, but these schemes failed in terms of certain aspects. This thesis tries to explore the potential of using soft computing methodologies in the design of Fractional Order Proportional Integral (FOPI) controller of pH neutralization process and their advantages over conventional methods. FOPI controller comprising the fractional concept in basic Proportional Integral (PI) controller, being one of the most commonly used controllers in industrial applications, needs eand#64259;cient methods of tuning to control the diand#64256;erent parameters of the pH neutralization process. This work asserts that the conventional approach of FOPI tuning is not very eand#64259;cient due to the presence of non-linearity in the pH neutralization process. Designing and tuning a FOPI controller in pH neutralization process appears to be conceptually easy, but can be hard in practice if good transient response characteristics are needed to be achieved. The research concentrated on five main contributions for the optimal tuning of the parameters of FOPI controller, such as Harmony Search Algorithm (HSA) control, Artificial Bee Colony (ABC) control, Biogeography Based Optimization (BBO) control, Cuckoo Search Algorithm (CSA) control and the proposed neuro-fuzzy control, in the pH neutralization process to enhance the eand#64256;ective operation of the system. The drawbacks associated with the existing optimization techniques were increased time consumption, high cost and may lag the search either in local optima and avoidance of global optimization. Hence, to overcome these limitations, intelligent neuro-fuzzy technique is developed, which is the integration of Fuzzy Inference System (FIS) and Artificial Neural Network (ANN). The analysis of the neuro