Synthesizing Chemical Plant Operation Procedures using Knowledge, Dynamic Simulation and Deep Reinforcement Learning
This addresses the challenge of supporting human operators in complex chemical plants for more efficient and stable operations, though it appears incremental as it builds on existing technologies like deep reinforcement learning.
The paper tackles the problem of synthesizing operation procedures for chemical plants by integrating automated reasoning and deep reinforcement learning with a simulator and external knowledge, resulting in a procedure that achieves a much faster recovery from a malfunction compared to standard PID control.
Chemical plants are complex and dynamical systems consisting of many components for manipulation and sensing, whose state transitions depend on various factors such as time, disturbance, and operation procedures. For the purpose of supporting human operators of chemical plants, we are developing an AI system that can semi-automatically synthesize operation procedures for efficient and stable operation. Our system can provide not only appropriate operation procedures but also reasons why the procedures are considered to be valid. This is achieved by integrating automated reasoning and deep reinforcement learning technologies with a chemical plant simulator and external knowledge. Our preliminary experimental results demonstrate that it can synthesize a procedure that achieves a much faster recovery from a malfunction compared to standard PID control.