Browsing by Author "Carrillo, Ana"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item Data Driven Performance Prediction in Steel Making(2022-01-18) Boto, Fernando; Murua, Maialen; Gutierrez, Teresa; Casado, Sara; Carrillo, Ana; Arteaga, Asier; Tecnalia Research & Innovation; FACTORY; CIRMETAL; PROMETALThis work presents three data-driven models based on process data, to estimate different indicators related to process performance in a steel production process. The generated models allow the optimization of the process parameters to achieve optimal performance and quality levels. A new approach based on ensembles has been developed with feature selection methods and four state-of-the-art regression approximations (random forest, gradient boosting, xgboost and neural networks). The results show that the proposed approach makes the prediction more stable reducing the variance for all cases, even in one case, slightly reducing the bias. Furthermore, from the four machine learning paradigms presented, random forest is the one with the best results in a quantitative way, obtaining a coefficient of determination of 0.98 as a maximum, depending on the target sub-process.Item Distributed product design and manufacturing based on KBE(2006) Mendikoa, Inigo; Sorli, Mikel; Barbero, Jose I.; Carrillo, Ana; RENOVABLES OFFSHORE; Tecnalia Research & Innovation; PROMETAL; CIRMETALCollaborative design and manufacturing through the Internet is becoming more necessary as enterprises are distributing their activities throughout the world. The approach presented in this paper deals with techniques that can support multi distributed clients and provide a dynamic database service, making possible a dynamic distributed design and manufacturing process, focusing on the product and process knowledge management from the whole value chain. The core application of the system presented in this paper manages the distributed design and manufacturing process through the internet among different teams.Item IMAGE: A middleware for heterogeneous simulations interoperability(2005) Rodriguez, Nancy; Jessel, Jean Pierre; Torguet, Patrice; Carrillo, Ana; Delteil, Jacques; Depauw, Jan; CIRMETALMiddlewares are used to simplify the integration of applications with different hardware and software requirements. Currently, a wide variety of middleware technologies are made available off-the-shelf to alleviate some of the complexity of developing distributed simulations. In our project, IMAGE, we have designed a middleware-based architecture to support coupling of existent heterogeneous simulators. This paper discusses the IMAGE middleware design based on a combined CCM/HLA technology.Item Knowledge based distributed product design and manufacturing(IEEE Computer Society, 2005) Mendikoa, Iñigo; Sorli, Mikel; Barbero, Jose I.; Carrillo, Ana; RENOVABLES OFFSHORE; Tecnalia Research & Innovation; PROMETAL; CIRMETALCurrently most of the design and manufacturing management systems of an enterprise deal with local and static database systems and do not consider all the involved product/process knowledge from the whole value chain. The approach presented in this paper mainly focus on those techniques that can support multi distributed clients and provide a dynamic database service, thus making possible a dynamic distributed design and manufacturing process. The core application of the system presented manages the distributed design and manufacturing process through the internet between different teams, including the management of all the relevant product knowledge for design and manufacturing processes.Item Optimisation of total roll power using genetic algorithms in a compact strip production plant(2013) Marquez, Itziar; Arribas, Maribel; Carrillo, Ana; Arana, Jose Luis; CIRMETALThe application of optimisation techniques to hot rolling models can lead to the more efficient use of these models. In this work, a genetic algorithm has been used in order to design new hot rolling schedules with lower energy consumption through a reduction in the total roll power. Firstly, mean flow stress has been modelled for several Nb microalloyed steels produced in a compact strip production plant taking into account recrystallisation and precipitation models. The selected mean flow stress model has been validated against the values obtained from the industrial hot rolling forces using the Sims approach. Secondly, the model has been integrated with a genetic optimisation algorithm and new reductions have been proposed in order to decrease the total rolling power, maintaining all the requirements. The reductions achieved can be up to 10 %.