A big step ahead in Metal Science and Technology through the application of Artificial Intelligence

Colla, Valentina

doi:10.1016/j.ifacol.2022.09.234

Cited by 6 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One way to perform this identification is by using artificial intelligence, particularly Artificial Neural Networks (ANNs), due to their ability to map the model that relates inputs and outputs. The application of such concepts, also present in this project, contributes to avoiding unnecessary losses in the processes (COLLA, 2022;. Escribano et al (2012) applied various Artificial Intelligence Algorithms, such as artificial neural networks and regression trees, to model the behavior of the cold rolling mill, and they obtained satisfactory results.…”

Section: Introductionmentioning

confidence: 91%

Redes neurais artificiais na modelagem de laminadores de encruamento

Rodrigues,

Dos Santos

2023

CadUniFOA

View full text Add to dashboard Cite

Para garantir a competitividade industrial, incluindo o mercado siderúrgico, é necessário otimizar despesas e aumentar a produtividade. Portanto, evitar incidentes relacionados à automação e à manutenção de equipamentos é um fator chave para garantir produção ininterrupta. Além disso, a perda de material deve ser minimizada. Nesse contexto, existe uma oportunidade para incorporar melhorias no controle de um laminador de encruamento, assegurando que a tensão mecânica aplicada à chapa de aço permaneça dentro das especificações. Para alcançar um controle eficiente, é necessário que o controlador envie o sinal apropriado para a planta. Este artigo explora diferentes arquiteturas de redes neurais artificiais para modelar essa planta. Uma melhoria moderada foi observada no modelo, e o modelo neural permite treinamento contínuo para se adaptar ao fenômeno real.

show abstract

Section: Introductionmentioning

confidence: 91%

Redes neurais artificiais na modelagem de laminadores de encruamento

Rodrigues,

Dos Santos

2023

CadUniFOA

View full text Add to dashboard Cite

show abstract

“…

In the last decade, an increasing interest is observed toward an interdisciplinary research field named "Materials Informatics", which lies between materials engineering and data science and supports discovery, characterization, design, and development of materials through artificial intelligence (AI) and machine learning (ML) approaches [1,2] and mechanical behavior of metals and alloys, and connected technological developments are sensibly impacted by this category of approaches. [3] They can, indeed, help metallurgical industry in sustaining the ever-increasing pressure toward the production of materials facing extreme conditions and/or providing optimal trade-off among weight, strength, ductility, corrosion resistance, toughness, as well as production costs and environmental compatibility.

…”

mentioning

confidence: 99%

A Deep Learning‐Based Approach to the Estimation of Jominy Profile of Medium‐Carbon Quench Hardenable Steels

Colla,

Vannucci,

Matino

et al. 2023

steel research int.

Self Cite

View full text Add to dashboard Cite

The possibility to estimate the Jominy profile of steel based on its chemical composition is of utmost importance and high practical relevance for industries, at enables a preliminary assessment of the suitability of a specific steel grade to a particular application or to the requirements of a customer, by saving time and resources as the Jominy end‐quench test is costly and time consuming. More importantly, an estimator can be used in steel grade design, by supporting the investigation of the most suitable chemistry to meet some given specifications. The paper proposes a novel approach to estimate the hardenability profile of medium Carbon quench hardenable steels, which exploits the potential of deep learning to correlate the steel metallurgy to the entire shape of the curve rather than to its single points, by thus being adaptable to a wide range of steel grades while providing very accurate estimates. Moreover, the proposed approach is suitable implement a transfer learning paradigm, as it can exploit the knowledge acquired by training on a specific dataset to adapt the model to different steel grades for which less data or data holding different features are available.This article is protected by copyright. All rights reserved.

show abstract

Robotic Systems in the European Steel Industry: State-of-Art and Use Cases

Vannucci,

Matino,

Murri

et al. 2024

Topics in Mining, Metallurgy and Materials Engineering

View full text Add to dashboard Cite

The current digital and technological transformation affecting the European steel industry is carried out through the continuous and progressive application of Key Enabling Technologies (KETs) according to the Industry 4.0 paradigm. Among these technologies, robotic systems and autonomous vehicles (UAV/UGV), are increasingly applied in steel plants with the aim of improving health and safety in workplaces. Dangerous operations related to monitoring, maintenance and safety are often performed by using such systems in order to avoid workers’ exposure to accidents and injuries. Therefore, robotic applications and autonomous vehicles, which are suitably equipped with artificial vision and innovative sensors, are integrated in the daily operations by supporting humans and interacting with them according to well defined procedures, in order to minimise potential and dangerous events. The present chapter assesses the state-of-art for this technology, by analysing both the literature and European-funded projects, and investigates two specific use-cases related to different applications in steel plants with specific focus on the workforce impact in terms of implications in work organisation and operational procedure. Moreover, changed work patterns (e.g., behaviours, tasks, decision-making, training, skills, etc.) are also discussed considering human experience as a fundamental aspect.

show abstract

A big step ahead in Metal Science and Technology through the application of Artificial Intelligence

Cited by 6 publications

References 38 publications

Redes neurais artificiais na modelagem de laminadores de encruamento

Redes neurais artificiais na modelagem de laminadores de encruamento

A Deep Learning‐Based Approach to the Estimation of Jominy Profile of Medium‐Carbon Quench Hardenable Steels

Robotic Systems in the European Steel Industry: State-of-Art and Use Cases

Contact Info

Product

Resources

About