PC-Gym: Benchmark Environments For Process Control Problems

2024/10/29 by Maximilian Bloor, Bloor, Maximilian, José Torraca +15 · 4 citations
Engineering · #Advanced Manufacturing and Logistics Optimization #FOS: Electrical engineering #Manufacturing Process and Optimization #Scheduling and Optimization Algorithms #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2410.22093

openalex publication_date 2024/10/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

PC-Gym is an open-source tool for developing and evaluating reinforcement learning (RL) algorithms in chemical process control. It features environments that simulate various chemical processes, incorporating nonlinear dynamics, disturbances, and constraints. The tool includes customizable constraint handling, disturbance generation, reward function design, and enables comparison of RL algorithms against Nonlinear Model Predictive Control (NMPC) across different scenarios. Case studies demonstrate the framework's effectiveness in evaluating RL approaches for systems like continuously stirred tank reactors, multistage extraction processes, and crystallization reactors. The results reveal performance gaps between RL algorithms and NMPC oracles, highlighting areas for improvement and enabling benchmarking. By providing a standardized platform, PC-Gym aims to accelerate research at the intersection of machine learning, control, and process systems engineering. By connecting theoretical RL advances with practical industrial process control applications, offering researchers a tool for exploring data-driven control solutions.

Cited by

• Survey and Tutorial of Reinforcement Learning Methods in Process Systems Engineering
• Numbers Beat Words: A Rigorous On-Premise Benchmark for Coupled MIMO Controller Tuning
• TalkToAgent: A Human-centric Explanation of Reinforcement Learning Agents with Large Language Models
• Safe Deployment of Offline Reinforcement Learning via Input Convex Action Correction

Related

• SMPL: Simulated Industrial Manufacturing and Process Control Learning Environments
• Control-Informed Reinforcement Learning for Chemical Processes
• Deep Reinforcement Learning for Process Synthesis
• Safe Deployment of Offline Reinforcement Learning via Input Convex Action Correction
• Accelerating process control and optimization via machine learning: A review