The reinforcement learning-based multi-agent cooperative approach for the adaptive speed regulation on a metallurgical pickling line

TL;DR

This paper introduces a multi-agent reinforcement learning system combined with mathematical modeling to improve productivity and safety in metallurgical pickling lines, demonstrating significant real-world industrial benefits.

Contribution

It presents a novel integration of Deep Q-Learning with data augmentation techniques for adaptive speed regulation in heavy industry processes.

Findings

Significant productivity improvements achieved.

Enhanced safety and reliability in process control.

Effective handling of data scarcity through LSTM and CGAN.

Abstract

We present a holistic data-driven approach to the problem of productivity increase on the example of a metallurgical pickling line. The proposed approach combines mathematical modeling as a base algorithm and a cooperative Multi-Agent Reinforcement Learning (MARL) system implemented such as to enhance the performance by multiple criteria while also meeting safety and reliability requirements and taking into account the unexpected volatility of certain technological processes. We demonstrate how Deep Q-Learning can be applied to a real-life task in a heavy industry, resulting in significant improvement of previously existing automation systems.The problem of input data scarcity is solved by a two-step combination of LSTM and CGAN, which helps to embrace both the tabular representation of the data and its sequential properties. Offline RL training, a necessity in this setting, has become possible through the sophisticated probabilistic kinematic environment.