Repository logo

Browsing by Issue Date, starting with "2022-10-12"

Filter results by year or month
Now showing 1 - 2 of 2
  • Use of agricultural wastes to design natural products for the prevention of cardiovascular diseases
    Publication . Costa, Mariana; Grosso, Clara; Ramalhosa, Maria João; Ferraz, Ricardo; Soares, Cristina
    Cardiovascular diseases (CVDs), or risk factors for CVD, such as diabetes, hypertension and hypercholesterolemia, are the leading cause of death worldwide. Therefore, the use of agricultural by-products as a source of functional ingredients, particularly those from crop plants, has received significant interest. For example, the banana (Musa spp.) is a common food crop worldwide and is the primary production on Madeira Island in Portugal. In this work, banana peels and puree were incorporated into sweet food products as butter and sugar substitutes, enhancing the nutritional content. The results show that the final product’s dietary fibre and phenolic content increased, while the lipidic and total sugar content decreased. The obtained results show that banana peels have a great potential to be developed into beneficial functional foods and nutraceuticals.
    2022-10-12Journal article Open access Show more
  • Using an Artificial Neural Network Approach to Predict Machining Time
    Publication . Rodrigues, André; Silva, Francisco; Sousa, Vitor F. C.; Pinto, Arnaldo; Pinto Ferreira, Luís; Pereira, Maria Teresa Ribeiro
    One of the most critical factors in producing plastic injection molds is the cost estimation of machining services, which significantly affects the final mold price. These services’ costs are determined according to the machining time, which is usually a long and expensive operation. If it is considered that the injection mold parts are all different, it can be understood that the correct and quick estimation of machining times is of great importance for a company’s success. This article presents a proposal to apply artificial neural networks in machining time estimation for standard injection mold parts. For this purpose, a large set of parts was considered to shape the artificial intelligence model, and machining times were calculated to collect enough data for training the neural networks. The influences of the network architecture, input data, and the variables used in the network’s training were studied to find the neural network with greatest prediction accuracy. The application of neural networks in this work proved to be a quick and efficient way to predict cutting times with a percent error of 2.52% in the best case. The present work can strongly contribute to the research in this and similar sectors, as recent research does not usually focus on the direct prediction of machining times relating to overall production cost. This tool can be used in a quick and efficient manner to obtain information on the total machining cost of mold parts, with the possibility of being applied to other industry sectors
    2022-10-12Journal article Open access Show more