Optimizing Industrial Process Control with Artificial Intelligence: A Case Study of the Feedback Procon Level and Flow Process

Abstract

Artificial Intelligence (AI) techniques have brought about transformative changes across various industries, and the field of industrial process control is no exception. This paper presents an innovative approach centered around the development of an artificial neural network known as ANN-PID. This network emulates the decision-making process akin to that of a human operator for configuring parameters in a water Flow PID controller. At the heart of this approach lies a multi-layer perceptual neural network (MLP). The research entails training the ANN-PID model using real-time process data, aiming to optimize process parameters and elevate the efficacy of industrial process control. Through rigorous experimental tests conducted on the Feedback 38-003 Procon Level and Flow with Temperature process, the study confirms the prowess of the ANN-PID system in enhancing control performance when compared to traditional control methods. These findings represent a significant contribution to the evolution of intelligent control systems within industrial settings, ushering in novel opportunities for the automation and optimization of intricate processes.