Towards a CPS Solution for Modeling and Control of Phosphoric Acid Quality

Industries are leveraging advanced technologies like digital twins, cyber-physical systems (CPS), and Distribution Control Systems (DCS) to enhance efficiency and maintain competitiveness. Digital twins offer real-time representations of assets, enabling predictive maintenance and decision-making, while CPS integrate hardware and software for process automation and quality improvement. DCS provide centralized control and real-time monitoring, further optimizing operations. This paper aims to develop a predictive model for P<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>O<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">5</inf>concentration in phosphoric acid production using DCS data and laboratory measures in order to elevate and transform the traditional DCS in-to a modern, intelligent CPS that integrates physical processes with computational capabilities, enhancing efficiency, reliability, and responsiveness. Ac-curate prediction of P<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> O<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">5</inf>concentration is vital for product quality and process efficiency, yet challenging due to complex influencing factors. Machine learning techniques will be evaluated to identify the best performing model. The results will contribute to better production control and decision-making, with implications for improving industrial standards and sustainability.