ENERGY 2023 - The Thirteenth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies - Machine Learning and Optimisation to Improve Energy Utilisation

Aug 3, 2026

Upload by Ezra

The work addresses rising energy demand and supply-chain uncertainty by targeting improved energy efficiency in material processing industries. Heat treatment can consume large shares of total energy, especially during pre-heating and treatment operations in ferrous-based production, and this drives the need for more intelligent control. The approach models industrial processes using machine learning, then applies an optimization framework to select operating parameters that maximize output quality while minimizing energy use.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages6

Reading Time15 min

AccessFree to download

Abstract

Introduction

Literature

ENERGY 2023 : The Thirteenth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies Machine Learning and Optimisation to Improve Energy Utilisation Srinath Ramagiri Brunel University Kingston Ln, Uxbridge UB8 3PH London, United Kingdom e-mail: [srinath.ramagiri@brunel.ac.uk](srinath.ramagiri@brunel.ac.uk) Arman Zonuzi University of Sheffield Brunel Way, Catcliffe, Rotherham S60 5WG United Kingdom e-mail: [arman.zonuzi@namrc.co.uk](arman.zonuzi@namrc.co.uk) Shehan Lowe University of Sheffield Brunel Way, Catcliffe, Rotherham S60 5WG United Kingdom e-mail: [shehan.lowe@namrc.co.uk](shehan.lowe@namrc.co.uk) Evelyne El Masri Brunel University Kingston Ln, Uxbridge UB8 3PH London, United Kingdom e-mail: [evelyne.elmasri@brunel.ac.uk](evelyne.elmasri@brunel.ac.uk) Ahmed Teyeb Brunel University Kingston Ln, Uxbridge UB8 3PH London, United Kingdom e-mail: [ahmed.teyeb@brunel.ac.uk](ahmed.teyeb@brunel.ac.uk) Tat-Hean Gan Brunel University Kingston Ln, Uxbridge UB8 3PH London, United Kingdom e-mail: [tat-hean.gan@brunel.ac.uk](tat-hean.gan@brunel.ac.uk) Abstract— The world is moving towards a conservative approach to fulfilling its energy needs due to inevitable uncertainty and disruptions in the supply chain. In addition, climate change, the availability of materials, and making them sustainable through recycling are other topics of high interest. Energy is a common item among all the industries, and demand for it keeps increasing due to developmental activities. In this work, we aim to improve the efficiency of utilising the available energy in the material processing industries. Mining the ore, extracting the material of interest, melting the material, and manufacturing the required components are typical processes in these industries. The manufacturing of the components also includes a heat treatment process. For example, the heat treatment process demands 20% of the total energy in a non-ferrous foundry. Pre-heating and heat treatment operations consume a significant amount of energy in the ferrous-based industry. We intend to investigate the processes in these industries and create a machine-learning model of the processes involved. Later, we use the machine learning models to build an optimization framework that provides the optimal process operating parameters to achieve the best output while using the least amount of energy. Keywords- machine-learning; Optimisation; heat-treatment; energy-efficiency. I. INTRODUCTION Heat treatment processes are an important stage in materials processing in which component properties are modified to suit a particular application. In this process, mechanical and physical properties, such as ductility, hardness, toughness, wear resistance, and strength are changed without changing the designed shape and size of the component [1] . In general, heat treatment processes are carried out to improve strength in the case of loaded members and wear resistance in the case of moving parts, however, it can also be used to improve the machinability, formability of materials. The changes in the properties of the material are made possible thanks to the changes which occur at molecular structure/microstructure level. The structure of the material is a function of two factors; (1) Grain size (2) Grain structure. These two components of microstructure of a material define its mechanical and physical properties. Also, heat treatment process is often coupled with pre and post heating process which enable us to utilize energy effectively besides improving the product performance. In total, it can be observed that there are several parameters involved in heat treatment process such as, chemical composition of alloy, dimensions and shape of the component to be heat treated, micro structural, physical and mechanical properties, energy required for the heat treatment process, etc. Depending on specific objective, some of the parame

FAQs

Why is energy utilisation efficiency important for material processing industries?

Energy demand keeps increasing while supply-chain disruptions and climate-related constraints affect energy planning. Improving process efficiency reduces energy consumption during energy-intensive steps like heat treatment.

What role does heat treatment play in the studied industries?

Heat treatment modifies component properties such as ductility and hardness without changing shape and size. Pre-heating and heat treatment operations consume a significant amount of energy, making them key targets for optimisation.

How do machine learning models and optimisation work together in the proposed approach?

Machine learning models learn the relationships between process parameters and outcomes. An optimisation framework then uses these models to recommend operating parameters that achieve the best output with the least energy use.

Aug 3, 2026

Upload by Ezra