Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Interest
Topics
Details

Details

  • Name

    Hélio Cristiano Castro
  • Role

    Senior Researcher
  • Since

    18th November 2020
001
Publications

2024

Digital Factory for Product Customization: A Proposal for a Decentralized Production System

Authors
Castro H.; Câmara F.; Câmara E.; Ávila P.;

Publication
Lecture Notes in Mechanical Engineering

Abstract
The digitalization and evolution of information technologies within the industry 4.0 have allowed the creation of the virtual model of the production system, called Digital Twin, with the capacity to simulate different scenarios, providing support for better decision-making. This tool not only represents a virtual copy of the physical world that obtains information about the state of the value chain but also illustrates a system capable of changing the development of productive activity towards personalized production, extending product versatility. Decentralized production seeks to respond to these needs because it allows the agglomeration of several services with different geographic locations, promoting the sharing of resources. This paper proposes an architecture for the development of a digital platform of personalization and decentralization of production based on sharing of sustainable resources. With a single tool, it is possible to define the entire production line for a product.

2024

Development and Analysis of Predictive Models for Industry 4.0 with an Open-Source Tool

Authors
Castro H.; Câmara E.; Câmara F.; Ávila P.;

Publication
Lecture Notes in Mechanical Engineering

Abstract
Industry 4.0 brought modernization to the productive system through the network integration of the constituent entities that, combined with the evolution of information technologies, allowed an increase in productivity, product quality, production cost optimization, and product customization to customer needs. In this paper a model was created using the open-source tool Knime that, based on a set of data provided by Bosch, parameterized the model with several pre-processing techniques, resource selection, and minimization of over-fitting, allowing the development of a final improved model for internal product failure prediction at Bosch production line. The study shows that model efficiency improved with the application of resource selection and reduction techniques, with Logistic Regression and PCA resource selection techniques standing out, obtaining a Recall of 100% and precision and accuracy, both with 99.43%.

2024

Energy and Circular Economy: Nexus beyond Concepts

Authors
Martins, FF; Castro, H; Smitková, M; Felgueiras, C; Caetano, N;

Publication
SUSTAINABILITY

Abstract
Energy and materials are increasingly important in industrialized countries, and they impact the economy, sustainability, and people's future. The purpose of this work was to study the relationship between energy and the circular economy using methods such as Pearson's correlation and a principal component analysis. Thus, 12 strong correlations were found, with 5 of them between the following relevant variables from two different subjects: the correlations of the raw material consumption, the domestic material consumption, and the material import dependency with the final energy consumption in transport (0.81, 0.92, and 0.81); the correlation of the circular material use rate with the final energy consumption in households (0.70); and the correlation of the material import dependency with the final energy consumption in industry (0.89). The time series forecast was only conclusive for the waste generated, showing that it will increase in the next 10 years.

2024

Product Customization based on Digital Twin and Cloud Manufacturing within a Decentralized Production System

Authors
Castro, H; Camara, F; Avila, P; Ferreira, L; Cruz Cunha, M;

Publication
Procedia Computer Science

Abstract
Industry 4.0 represents a turning point in the thinking of the production model since it is based on digitalized production systems with the aim of improving productivity, product quality, and delivery time to the customer. The digitalization and evolution of information technology allowed the emulation of production system virtual models, namely in the concept of Digital Twin (DT), with the ability to simulate different scenarios providing support for better decision making. This concept not only represents a virtual copy of the physical world that obtains information about the state of the value chain but also illustrates a system capable of changing the development of the production activity according to the fulfillment of the intended business goals. In literature, the concept of the Digital Twin is exhaustively treated as a stand-alone factory (one digital factory represents one physical factory) and underestimates the possibility of a DT oriented to a customized product (a project) that requires decentralized production systems. This paper brings to discussion the relevance of product customized applying DT to smart customization, and the inclusion of decentralized production systems supported by Cloud Manufacturing. © 2024 The Author(s). Published by Elsevier B.V.

2024

Artificial Intelligence Models: A literature review addressing Industry 4.0 approach

Authors
Castro, H; Camara, E; Avila, P; Cruz Cunha, M; Ferreira, L;

Publication
Procedia Computer Science

Abstract
Industry 4.0 has brought modernization to the production system through the network integration of the constituent entities which, combined with the evolution of information technology, has enabled an increase in productivity, product quality, optimization of production costs, and product customization to customer needs. Despite the complexity of human thought, artificial intelligence tries to replicate it in algorithms, creating models capable of processing databases with a high volume of information, and generating valuable information for decision making. Within this area, there are subfields, such as Machine Learning and Deep Learning, which, through mathematical models, define patterns to predict output data from known input data. In addition to this type of algorithm, there are metaheuristic models capable of optimizing the parameters required in Machine Learning and Deep Learning algorithms. These intelligent systems have applications in various areas such as industry, construction, health, logistics processes, and maintenance management, among others. This paper focuses on Artificial Intelligence models addressing Industry 4.0 approach. © 2024 The Author(s). Published by Elsevier B.V.

Supervised
thesis

2023

Digitalização do processo de verificação de qualidade utilizando ferramentas LOW-CODE

Author
BRUNO EDUARDO FERRAZ DE SOUSA

Institution
IPP-ISEP

2023

Modelos de inteligência artificial aplicados na indústria 4.0

Author
EDUARDO FERNANDO GONÇALVES OSÓRIO BIANCHI DA CÂMARA

Institution
IPP-ISEP

2023

A Digitalização e a Descentralização da Produção na Indústria 4.0: Digital Twin

Author
FERNANDO JOSÉ GONÇALVES OSÓRIO BIANCHI DA CÂMARA

Institution
IPP-ISEP

2023

Aplicação de Sistema Ciberfísico em Design Aberto: Integração de Sistemas de Controlo Versáteis e Abertos

Author
JOÃO NELSON ALVES DA SILVA

Institution
IPP-ISEP

2023

Desenvolvimento de uma Proposta de Modelo de Gestão e Produção Ágil Orientado a Comunidades de Projetos Abertos (Open Design)

Author
FRANCISCA ISABEL MARTINS MADUREIRA

Institution
IPP-ISEP