PROJECT TITLE :

An Adaptive, Advanced Control Strategy for KPI-Based Optimization of Industrial Processes

ABSTRACT:

The necessity to deal with speedy modification in an environmentally and economically friendly manner has led to renewed interest in knowledge-driven, online process optimization. Though various strategies, such as economic model predictive management (EMPC), are on the market to achieve this goal, they require that the process model be available and comparatively correct and that there be no process changes. Recently, the focus has shifted to using economic key performance indices (KPIs) to style supervisory controllers to control the method. In order to accomplish this, accurate models of the highly nonlinear KPIs are required. A answer to this downside is to develop a 2-step management strategy consisting of a static, offline element and a dynamic, online component. This paper proposes the utilization of a linear, BILIMOD methodology combined with a self-partitioning algorithm for the static part and gradient-based mostly optimization technique for the dynamic component. So as to accommodate method changes, the static model parameters are updated. The proposed new controller strategy is tested on the wastewater treatment process. It is shown that the proposed technique can quickly and effectively achieve the desired optimal point with minimal disturbance to the method.