Trustworthy AI for Process Automation on a Chylla-Haase Polymerization Reactor

TL;DR

This paper introduces a genetic programming reinforcement learning approach to generate simple, interpretable control policies for a chemical reactor, improving temperature regulation while ensuring ease of validation and implementation.

Contribution

It presents a novel application of GPRL to create low-complexity, human-interpretable control policies for CSTRs, enhancing control performance and practical deployability.

Findings

Generated policies achieve high temperature control accuracy.

Policies are easy to validate and implement in existing control systems.

Empirical evaluation shows improved reactor temperature regulation.

Abstract

In this paper, genetic programming reinforcement learning (GPRL) is utilized to generate human-interpretable control policies for a Chylla-Haase polymerization reactor. Such continuously stirred tank reactors (CSTRs) with jacket cooling are widely used in the chemical industry, in the production of fine chemicals, pigments, polymers, and medical products. Despite appearing rather simple, controlling CSTRs in real-world applications is quite a challenging problem to tackle. GPRL utilizes already existing data from the reactor and generates fully automatically a set of optimized simplistic control strategies, so-called policies, the domain expert can choose from. Note that these policies are white-box models of low complexity, which makes them easy to validate and implement in the target control system, e.g., SIMATIC PCS 7. However, despite its low complexity the automatically-generated policy yields a high performance in terms of reactor temperature control deviation, which we empirically evaluate on the original reactor template.