Utilization of Artificial Intelligence in Modern Process Industries

author.DisplayName
R&D, Modcon Systems, Akko, Israel

Many challenges are involved in process optimization to increase the chemical yield and product quality in chemical and petroleum industries. Chemical and refinery processes can be expressed by linear models. Process control in modern process management shifted from corrective actions, when discrepancies occur, towards predictive prevention, to foresee and prevent any loss-making events. Today, process managements is not restricted to the process only, but also includes the cost of raw materials, price of final products, energy consumption, logistics etc..

Traditionally, petroleum industries use controllers, ranging from proportional controllers to advanced predictive based controllers, like Model Predictive Controllers (MPC). Most of these systems require careful analysis of the process dynamics, development of abstract mathematical models and derivation of a control law, which meet certain design criteria. However, drawbacks of this well-proven technology mainly relate to complexity of dynamic models and their continuous maintenance requirements to accommodate feedstock changes, process improvements and deviations in product demands because of changing global economies.

Petroleum industry can generate high value by optimizing their assets from analytics of machine and processes data that they acquired from operations and productions. Modern machine and deep learning technologies enable simply interacting with the process and incrementally improving control behaviour.

ANACON provides process engineers a set of modern AI tools, enabling connectivity, validation and prediction of main KPI’s. This enables taking correct decisions to maintain and improve effective industrial processes management. Software calculates and predicts physical chemical properties in different process streams, and proposes process properties, which accomplish the calculated predictions.

Process analysers provide online analytic data, which is verified and validated against laboratory results and predicted products quality. Integration of these three technologies will afford a tool that allows the simulated process’ “digital twin” to continuously be updated to allow highest possible efficiency of the process at lowest cost.









Powered by Eventact EMS