Optimisation of Operator Support Systems through Artificial Intelligence for the Cast Steel Industry: A Case for Optimisation of the Oxygen Blowing Process Based on Machine Learning Algorithms

Álvaro Ojeda Roldán,Luis Enrique Acevedo Galicia,Martin Schlautmann,Fernando Dorado Navas,Alejandro Del Real Torres,Doru Stefan Andreiana,Gert Gassner,Mikko Heiskanen,Carlos Leyva Guerrero

doi:10.3390/jmmp6020034

Abstract

The processes involved in the metallurgical industry consume significant amounts of energy and materials, so improving their control would result in considerable improvements in the efficient use of these resources. This study is part of the MORSE H2020 Project, and it aims to implement an operator support system that improves the efficiency of the oxygen blowing process of a real cast steel foundry. For this purpose, a machine learning agent is developed according to a reinforcement learning method suitable for the dynamics of the oxygen blowing process in the cast steel factory. This reinforcement learning agent is trained with both historical data provided by the company and data generated by an external model. The trained agent will be the basis of the operator support system that will be integrated into the factory, allowing the agent to continue improving with new and real experience. The results show that the suggestions of the agent improve as it gains experience, and consequently the efficiency of the process also improves. As a result, the success rate of the process increases by 12%.

Highlights

The fourth industrial revolution, called Industry 4.0, has increased the digitisation and automation of many industrial sectors through the development of smart factories [1].The objective is to enhance production through processes optimisation, environmental protection and data management, among other factors [2]
In the exploitation period, which corresponds to the second half of the training with the model, the agent exploits the knowledge gained during the first half of the training in order to achieve the target state
The agent was developed based on the process dynamics and its objectives

Summary

Introduction

The objective is to enhance production through processes optimisation, environmental protection and data management, among other factors [2]. To this end, the integration of AI-based techniques is playing an important role, highlighting a machine learning (ML). Thanks to its capability for learning from interaction, this ML paradigm has become a clear alternative to classic control methods to control industrial processes [3]. In many cases, RL control methods enhance process efficiencies [4,5], such as welding with robot manipulators [6] and controlling cooling water systems [7] and chemical processes [8]. Most techniques used in the steelmaking processes are based on the know-how and professional experience of experts in the sector [9]

Methods

Results

Conclusion