Forecasting copper electrorefining cathode rejection by means of recurrent neural networks with attention mechanism

Simple item page
dc.contributor.authorCorrea Hucke, Pedro Pablo
dc.contributor.authorCipriano, Aldo
dc.contributor.authorNuñez Retamal, Felipe Eduardo
dc.contributor.authorSalas, Juan Carlos
dc.contributor.authorLöbel Díaz, Hans-Albert
dc.date.accessioned2022-05-18T14:39:47Z
dc.date.available2022-05-18T14:39:47Z
dc.date.issued2021
dc.description.abstractElectrolytic refining is the last step of pyrometallurgical copper production. Here, smelted copper is converted into high-quality cathodes through electrolysis. Cathodes that do not meet the physical quality standards are rejected and further reprocessed or sold at a minimum profit. Prediction of cathodic rejection is therefore of utmost importance to accurately forecast the electrorefining cycle economic production. Several attempts have been made to estimate this process outcomes, mostly based on physical models of the underlying electrochemical reactions. However, they do not stand the complexity of real operations. Data-driven methods, such as deep learning, allow modeling complex non-linear processes by learning representations directly from the data.We study the use of several recurrent neural network models to estimate the cathodic rejection of a cathodic cycle, using a series of operational measurements throughout the process. We provide an ARMAX model as a benchmark. Basic recurrent neural network models are analyzed first: a vanilla RNN and an LSTM model provide an initial approach. These are further composed into an Encoder-Decoder model, that uses an attention mechanism to selectively weight the input steps that provide most information upon inference. This model obtains 5.45% relative error, improving by 81.4% the proposed benchmark. Finally, we study the attention mechanism’s output to distinguish the most relevant electrorefining process steps. We identify the initial state as a critical state in predicting cathodic rejection. This information can be used as an input for decision support systems or control strategies to reduce cathodic rejection and improve electrolytic refining’s profitability.
dc.fechaingreso.objetodigital2024-04-11
dc.fuente.origenIEEE
dc.identifier.doi10.1109/ACCESS.2021.3074780
dc.identifier.issn2169-3536
dc.identifier.urihttps://doi.org/10.1109/ACCESS.2021.3074780
dc.identifier.urihttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9410222
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/64153
dc.information.autorucEscuela de ingeniería ; Correa Hucke, Pedro Pablo ; S/I ; 222854
dc.information.autorucEscuela de ingeniería ; Cipriano Zamorano, Aldo ; S/I ; 99102
dc.information.autorucEscuela de ingeniería ; Nuñez Retamal, Felipe Eduardo ; S/I ; 131441
dc.information.autorucEscuela de ingeniería ; Salas Morales, Juan Carlos ; S/I ; 1020223
dc.information.autorucEscuela de ingeniería ; Lobel Diaz, Hans Albert ; S/I ; 131278
dc.language.isoen
dc.nota.accesoContenido completo
dc.pagina.final79088
dc.pagina.inicio79080
dc.revistaIEEE Access
dc.rightsacceso abierto
dc.subjectRecurrent neural networks
dc.subjectForecasting
dc.subjectCathodes
dc.subjectCopper
dc.subjectPredictive models
dc.subjectBiological system modeling
dc.subjectComputer architecture
dc.titleForecasting copper electrorefining cathode rejection by means of recurrent neural networks with attention mechanismes_ES
dc.titleForecasting copper electrorefining cathode rejection by means of recurrent neural networks with attention mechanism
dc.typeartículo
dc.volumen9
sipa.codpersvinculados222854
sipa.codpersvinculados99102
sipa.codpersvinculados131441
sipa.codpersvinculados1020223
sipa.codpersvinculados131278
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Forecasting_Copper_Electrorefining_Cathode_Rejection_by_Means_of_Recurrent_Neural_Networks_With_Attention_Mechanism.pdf
Size:
1.77 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas