Browsing by Author "Pereira, M. Teresa"
Now showing 1 - 7 of 7
Results Per Page
Sort Options
- Definition of a decision support model for calculating the economic production lot sizePublication . Pereira, M. Teresa; Magalhães, Hugo; Ferreira, Fernanda A.; Barreiras, AlcindaThis paper proposes a Decision Support System (DSS) for Calculating the Economic Production Lot Size. The focus is on the analysis of improvement of manufacturing productivity in the packaging industry, specifically in a metal packaging company. Through combining different SKUs (Stock Keeping Units) in the same production order, as opposed to the current single SKU orders production paradigm of, it is possible to increase the overall equipment effectiveness (OEE). This study identified the most critical OEE products within the company portfolio. One critical OEE was selected from within company’s strategic fitting process for the assessment of all relevant parameters set for the manufacturing process so that no product variant was disregarded. Evaluation of the improvement achieved by the new production paradigm was possible through a DSS tool developed to combine different SKUs in due production order, taking into account real data from customers’ orders. Following the tool development, it was possible to proceed with simulations for various review periods. As this study is an iterative process, the results obtained within each simulation enabled an improved definition for subsequent analysis focusing on the goal set - improving the OEE without increasing stock value. Finally, results were evaluated and the operational and economic benefits of combining different SKUs within the same production order were unequivocal, representing an OEE increase of 20% and a maximum decrease of 367,215€ in stock value.
- Development of a cost estimation model in a furniture manufacturerPublication . Reis, Francico; Amaral, António; Oliveira, Marisa; Ferreira, Fernanda A.; Pereira, M. TeresaThis work was developed to improve the costing process of new products within the Product Development Department of a furniture manufacturer. It consisted of creating a parametric cost estimation model based on applying simple and multiple linear regressions, considering the existing data of the products produced and their respective costs. The proposed model considers the cost estimation of creating a product that covers the materials and operations costs. The suitability of the different independent variables was studied by applying simple and multiple linear regressions. A set of functions that return an estimate of the cost as a function of these predictor variables was obtained. The model built with the functions obtained provides the materials and operations cost estimation. The results indicated that 75% of the tests performed show an estimation error of less than 2% in the total cost of a product. Incorporating this model in a tool with the purpose of cost estimation brings the ability to predict prices faster, improving the internal process of obtaining costing and enhancing the analytical capacity of the team in the relentless pursuit of cost minimization and value creation.
- Development of a decision support system for freight forecastingPublication . Martins, João P.; Ramos, Filipe R.; Pereira, M. Teresa; Oliveira, Marisa; Ferreira, Fernanda A.The transportation of goods is critical to supply chains, directly influencing efficiency, cost management, and competitiveness. Accurate freight cost forecasting is essential for decision-making, enabling businesses to allocate resources effectively, reduce financial uncertainties, and ensure timely deliveries. This study, conducted in the After-Sales department of a global company, aimed to analyse freight costs per shipment and develop a predictive system based on predefined parameters. Historical data were examined using analytical techniques and time series metrics to identify suitable forecasting methodologies. Specific algorithms, including classical methodologies (exponential smoothing models) and hybrid deep learning models (BJ-DNN model), were tested to evaluate predictive accuracy. Results showed prediction errors ranging from 17% to 56% for exponential smoothing models and from 5% to 27% for BJ-DNN models, demonstrating the superior performance of hybrid approaches. These findings emphasize the potential of predictive models to enhance freight cost forecasting, minimizing error margins and optimizing resource allocation. This research provides a foundation for refining these methodologies, contributing to improved freight cost management and operational efficiency.
- A hybrid strategy for oven optimization in aerospace manufacturing: lean principles and mathematical modellingPublication . Pereira, M. Teresa; Pereira, Marisa G.; Ferreira, Fernanda A.; Silva, Francisco G.; Guimarães, AndréAdopting the Lean philosophy is essential for reducing costs and increasing productivity in industrial environments, where equipment efficiency plays a pivotal role. This study focuses on optimizing the use of an oven, a critical equipment, in the aircraft parts manufacturing process, in a company producing composite components for aerospace applications. A mathematical model based on the classic two-dimensional knapsack problem was developed to address inefficiencies in space utilization and workflow inconsistencies. The model was implemented to determine the optimal parts’ allocation, maximizing oven occupancy while ensuring efficient workflows. The study introduces a hybrid strategy that combines a structured allocation system with vertical shelving units to streamline part storage and improve the kiln-loading process. Extensive experiments validated the model’s performance, demonstrating its ability to support Lean principles by enhancing productivity and reducing costs in the aeronautical industry. This work underscores the importance of mathematical modelling for optimizing manufacturing processes and meeting the increasing demands of modern production environments.
- Optimization of metal sheet cutting processes using integer linear programming: reducing waste and enhancing production efficiencyPublication . Pereira, Marisa G.; Pereira, M. Teresa; Fernandes, Miguel A.; Silva, Francisco G.; Guimarães, André; Ferreira, Fernanda A.This paper presents an optimization approach for metal sheet cutting processes using Integer Linear Programming (ILP). It addresses the critical challenges of material waste and inefficiencies inherent in traditional manual cutting methods. The primary objective was to develop and implement an ILP-based model to automate and optimize cutting plans, thereby minimizing material waste and enhancing production efficiency. The proposed model extends existing optimization frameworks by incorporating constraints and decision variables tailored to the Two-Dimensional Strip Packing Problem (2D-SPP). Implemented in Python with libraries such as PuLP for mathematical modeling and Matplotlib for result visualization, the model was validated using real-world datasets. Results demonstrated substantial improvements, achieving material utilization rates of up to 87.94%. These findings underscore the effectiveness of ILP in addressing complex industrial challenges, offering a systematic approach to waste reduction and workflow optimization. The paper concludes by evaluating the model’s practical implications and its potential scalability for broader industrial applications.
- Proposal of process confirmation methodology through lean principles in logistics companyPublication . Silva, Bruna S. Martins da ; Pereira, M. Teresa ; Ferreira, Fernanda A.; Oliveira, MarisaNowadays, the challenges in this logistics sector influence companies to invest in means and resources to make their logistics processes more efficient, with higher quality and lower cost, without compromising the supply chain processes and business evolution requirements. Therefore, as part of the Process Improvement role carried out in a retail company, the Process Confirmation methodology has been developed in a structured and expeditious manner to ensure compliance with processes in the logistics area. Moreover, this methodology aims to link the process design phase and the consequent creation of standards to the search for improvements phase in a circular logic, ensuring continuous improvement to keep up with the increasing complexity of processes. This study presents the literature background supporting the model and its methodological flow, defining each step for real-world application and viability. The methodology encompasses process mapping tools, standards creation, criticality analysis, and process confirmation, as well as the dissemination, analysis, and treatment of results. Consequently, as a result of the methodology, it will be verified that the level of process compliance in logistics can be improved through process confirmation.
- A VRP model to support last mile maritime containersPublication . Pereira, M. Teresa; Ferreirinha, Luís; Ferreira, Fernanda A.; Oliveira, MarisaDue to the constant and hasty development of the process of economic globalization, the transport network has become increasingly complex. This causes significative changes in the manner of cargo transport, which leads to satisfy the costumer’s needs first and only then try to achieve an effective and efficient low-cost distribution. The decision support system developed allows to allocate the closest truck, with capacity, and give the respective quotes automatically, based on predefined criteria and optimization. The result will have a high impact on the parties’ performance: better management of infrastructures used, on the footprint, time of service, customer’ level service, reduction of empty kilometres, less cost and reduction of the receipt period. This investigation has the main goal of developing an online Inland Container Transport (ICT) Decision Support System (DSS). Maritime container distribution and collecting processes is a routing problem, in regions which are oriented to container seaports or inland terminals. Therefore, the problem to be investigated is closely related to the vehicle routing problem with backhauls (VRPB) that finds an optimal set of orders (or routes) with deliveries (linehauls) and pickups (backhauls).