ESTiG - Publicações em Proceedings Indexadas à WoS/Scopus
URI permanente para esta coleção:
Navegar
Entradas recentes
- Enhancing inventory management decisions in a bakery: a case studyPublication . Cardoso, João; Leitão, Paulo; Geraldes, Carla A.S. ; .This work aims to establish assertive inventory policies for the raw materials in a Portuguese bakery. The demand behaviour of some items was analysed, using the ABC classification, and 14 main items were prioritised. Using Holt-Winters’ additive method, the demand for these items was forecast until the end of 2023. With these forecast data, the paper presents a simulation and comparison between two different inventory policies, the continuous review model and the periodic review model, and also presents an estimate of current inventory costs. As expected, the periodic review model presented higher inventory costs than the continuous review model, due to the higher safety stocks needed. The results of this paper are a starting point for the company to decide what inventory management method fits better.
- Improving the production process of a bakery: a simulation approachPublication . Geraldes, Carla A.S. ; Setti, Fabiana; Almeida, João P.; .The present study brings forward a simulation-based study of the production process of a Portuguese bakery. The main goal is to analyse different production processes and propose improvements, through the use of discrete event simulation. A relevant set of data was collected, and four productive processes were selected to be modelled using Simio software (Simulation Modelling based on Intelligent Objects). The analysis of the developed models highlighted the need for improvements and different scenarios were created to this purpose. Among the obtained results, it was found that the adoption of mixed production scenarios allowed the increase of the production level while maintaining the current existing resources. In conclusion, this study high-lighted the ability of the simulation technique to analyse manufacturing processes, throughout the creation of different scenarios, providing insights on the production process optimising the companies’ productive performance.
- Lean agile’s contributions to automotive industryPublication . Juventino, Grace; Silva, Wellington; Pimentel, Cristiane; Almeida, João P.; Geraldes, Carla A.S. ; .The automotive industry deals with complex processes. Becoming aware of the importance of agile management they are contributing to a creative fusion known as “leagile”. However, this concept needs further study and investigation. This work presents a systematic literature review on Lean Agile implementation in the automotive industry. Thirty-three publications were reviewed and characterized according to the year of publication, country of origin, industrial sector, used tools and their contributions to the automotive sector. The results show that 50% of the articles were published after 2018. The countries with the most publications are India, Portugal, and United Kingdom. The most cited tools are Value Stream Mapping (VSM), Just in Time (JIT) and 5S (23%). This study confirms the growing use of “leagile” in the automotive industry and the growing potential for research development in the area.
- Reconfigurable conveyor transfer system using IEC-61499 function blocksPublication . Mendonça, Leonardo; Funchal, Gustavo Silva; Fagundes, Frederico; Leitão, PauloIn the 4th Industrial Revolution era, automation processes operate in a more modular, flexible, and reconfigurable manner, leveraging decentralized decision-making and distributed control. The IEC-61499 Function Block (FB) technology offers a suitable approach to implementing distributed automation control systems. This paper describes the development of a dynamic and on-the-fly reconfiguration control system based on the IEC-61499 standard, applied in a conveyor transfer system case study to automatically adapt its operation to face changes in the number and position of the conveyor modules. The developed control system considers a Python-based FB network using the DINASORE framework. The experimental tests showed promising results regarding the ability of the system to adapt to condition changes automatically and on-the-fly, as well as scalability and robustness.
- Distributed machine learning and multi-agent systems for enhanced attack detection and resilience in iot networksPublication . Funchal, Gustavo Silva; Pedrosa, Tiago; Prieta, Fernando de la; Leitão, PauloThe exponential growth of connected devices, including sensors, mobile devices, and various Internet of Things (IoT) devices, has resulted in a substantial increase in data generation. Traditionally, data analysis involves transferring data to cloud computing systems, leading to latency issues and excessive network traffic. Edge computing emerges as a promising solution by bringing processing closer to the data sources. However, edge computing faces challenges, particularly in terms of limited computational power, which can create constraints in the execution of machine learning (ML) tasks. This paper aims to analyze strategies for distributing ML tasks among multiple nodes based on multi-agent systems (MAS) technology to have a collaborative approach and compare these strategies to provide an overview of best practices for achieving the optimal performance in intrusion detection for Industrial Internet of Things (IIoT). In this way, the well-known CICIoT2023 data set was used, and centralized and distributed ML techniques were implemented, and evaluated. The distributed edge ML approach achieved promising results, presenting an improvement of between 7.73% and 32.18% in the correction of wrong predictions of detection of attacks on IoT devices, significantly improving the precision and recall of the applied techniques.
- Real-time rule-based monitoring tool to achieve zero defect manufacturingPublication . Costa, Jullo; Oliveira Júnior, Alexandre de; Barbosa, José; Alves, Gleifer; Borges, Andre; Garcia, Gisela; Pires, Rui; Leitão, PauloThe demands of innovative production systems are shifting from mass production to the creation of smaller quantities with a focus on high quality. To achieve these evolving demands, Zero Defect Manufacturing has emerged as a key paradigm. This approach requires an innovative architectural monitoring tool where real-time data is continuously gathered and analysed to predict defects and assess their potential impacts. It also necessitates the seamless integration of diverse data sources, advanced processing algorithms, and Digital Twins to align with industrial requirements. In this paper we present a real-time, rule-based monitoring tool applied to a real-world car manufacturing use case. The tool successfully generated early alerts for quality deviations, enabling production engineers to shift from a reactive to a proactive approach by detecting potential quality issues early in the process.
- Exploring automotive quality correlations through explainable machine learning what-if simulationPublication . Oliveira Júnior, Alexandre de; Calvo-Rolle, JoséLuis; Pires, Rui; Leitão, PauloHigh-dimensional variability in manufacturing processes presents significant challenges for quality control, demanding predictive strategies capable of capturing complex parameter dependencies. Machine learning (ML) offers robust mechanisms for this purpose, but reliance on black-box models often limits interpretability and hinders producing stakeholders’ identification of meaningful correlations for model optimization. This paper introduces an interactive what-if simulation platform designed to explore structural quality correlations in automotive assembly through explainable ML techniques, enhancing transparency and enabling uncertainty quantification. The platform is based on a modular Digital Twin (DT) architecture aligned with the ISO 23247 standard, guiding expert and non-expert users through correlation-driven feature selection, regression modelling and SHapley Additive exPlanations (SHAP) based post-hoc explanations. A case study using real inspection data from a vehicle assembly line demonstrates the tool’s capacity to support variable relevance assessment, dimensionality reduction, and model interpretability. Furthermore, an uncertainty-aware SHAP analysis enhances confidence in the model’s prediction stability, reinforcing the platform’s suitability for quality-driven decision support and integration into future DT ecosystems.
- Chatbots as strategic tools in organizationsPublication . Lopes, Isabel Maria; Guarda, Teresa; Oliveira, Pedro; Ribeiro, Maria Isabel; Fernandes, AntónioThe growing importance of artificial intelligence (AI) in the business and sci-entific context is evident. Organizations must begin to coexist and use AI as any other tool that increases their efficiency and effectiveness. Based on this, this research work focuses on the application of chatbots to improve operation-al efficiency and transform customer service. The main objective of this work is to have a perception of the real impact that chatbots have on companies, that is, to see the benefits and main challenges associated with their use. The main question of the study addresses the positive and negative impacts of imple-menting chatbots in companies, focusing on three fundamental areas: the first focuses on customer service, the second on the effectiveness of internal proce-dures and the third on interpersonal interactions in the business context. This study is justified by the need for companies to adapt to emerging technologies to increase competitiveness and efficiency, in addition to responding promptly to market demands. The study, no matter how much its authors try to reach the whole, is impossible. Thus, limitations of this study are pointed out, as well as suggestions for future work.
- Topology optimization of a junction in a biaxial geogrid under in-isolation tensile loadingPublication . Paiva, L.; Pinho-Lopes, Margarida; Valente, R.; Paula, António MiguelThe finite element method is a powerful tool that can be used to analyse problems including complex geometries and material properties. In this study, the generalpurpose finite element software ABAQUS was used to investigate the load-strain response of a biaxial geogrid under in-isolation tensile loading. A 3D model was developed, accounting for different thickness of geogrid elements and their nonlinear response. Then, TOSCA module was used to investigate an alternative design of a junction profile. The geogrid was submitted to uniaxial and biaxial tensile loading, simulating a wide-width tensile test and a biaxial wide-width tensile test. Validation was performed by comparing the numerical model with experimental data. Optimization results showed that it was possible to reduce the junction volume profile by 53% with a compromise of 3% in maximum bearing capacity.
- Hyperbolic models to represent the effect of mechanical damage and abrasion on the short-term tensile response of a geocompositePublication . Lombardi, G.; Pinho-Lopes, Margarida; Paula, António Miguel; Bastos, AntónioThe objective of this study was to analyse the short-term tensile response of a geocomposite (a geotextile and a geogrid overlapped) and apply hyperbolic models to describe its load-strain tensile curves. Data from specimens submitted to mechanical damage, abrasion, and mechanical damaged followed by abrasion were analysed. Reduction factors were proposed by comparing data from damaged specimens with those from undamaged specimens. The experimental results were compared with those fitted by the constitutive models to validate the model. The constitutive models demonstrated good fitting capacity. For any mechanical condition, the model parameters could be estimated by relating the experimental tensile properties of the geocomposite with adjustment coefficients, which allowed for describing the tensile load-strain curves with good accuracy. The reduction factors for the specimens subjected to mechanical damage followed by abrasion were lower than the values which would be obtained if the damages were considered individually.