Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press
The accuracy of a predictive system is critical for predictive maintenance and to support the right decisions at the right times. Statistical models, such as ARIMA and SARIMA, are unable to describe the stochastic nature of the data. Neural networks, such as long short-term memory (LSTM) and the gat...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/21/6958 |
| _version_ | 1797512646418759680 |
|---|---|
| author | Balduíno César Mateus Mateus Mendes José Torres Farinha Rui Assis António Marques Cardoso |
| author_facet | Balduíno César Mateus Mateus Mendes José Torres Farinha Rui Assis António Marques Cardoso |
| author_sort | Balduíno César Mateus |
| collection | DOAJ |
| description | The accuracy of a predictive system is critical for predictive maintenance and to support the right decisions at the right times. Statistical models, such as ARIMA and SARIMA, are unable to describe the stochastic nature of the data. Neural networks, such as long short-term memory (LSTM) and the gated recurrent unit (GRU), are good predictors for univariate and multivariate data. The present paper describes a case study where the performances of long short-term memory and gated recurrent units are compared, based on different hyperparameters. In general, gated recurrent units exhibit better performance, based on a case study on pulp paper presses. The final result demonstrates that, to maximize the equipment availability, gated recurrent units, as demonstrated in the paper, are the best options. |
| first_indexed | 2024-03-10T06:03:44Z |
| format | Article |
| id | doaj.art-7de9e1b39c8f490c82767493d3dc258e |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T06:03:44Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-7de9e1b39c8f490c82767493d3dc258e2023-11-22T20:41:28ZengMDPI AGEnergies1996-10732021-10-011421695810.3390/en14216958Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper PressBalduíno César Mateus0Mateus Mendes1José Torres Farinha2Rui Assis3António Marques Cardoso4EIGeS—Research Centre in Industrial Engineering, Management and Sustainability, Lusófona University, Campo Grande, 376, 1749-024 Lisboa, PortugalInstituto Superior de Engenharia de Coimbra, Polytechnic of Coimbra, 3045-093 Coimbra, PortugalInstitute of Systems and Robotics, University of Coimbra, 3004-531 Coimbra, PortugalEIGeS—Research Centre in Industrial Engineering, Management and Sustainability, Lusófona University, Campo Grande, 376, 1749-024 Lisboa, PortugalCISE—Electromechatronic Systems Research Centre, University of Beira Interior, Calçada Fonte do Lameiro, 62001-001 Covilhã, PortugalThe accuracy of a predictive system is critical for predictive maintenance and to support the right decisions at the right times. Statistical models, such as ARIMA and SARIMA, are unable to describe the stochastic nature of the data. Neural networks, such as long short-term memory (LSTM) and the gated recurrent unit (GRU), are good predictors for univariate and multivariate data. The present paper describes a case study where the performances of long short-term memory and gated recurrent units are compared, based on different hyperparameters. In general, gated recurrent units exhibit better performance, based on a case study on pulp paper presses. The final result demonstrates that, to maximize the equipment availability, gated recurrent units, as demonstrated in the paper, are the best options.https://www.mdpi.com/1996-1073/14/21/6958LSTMrecurrent neural networkGRUpaper presspredictive maintenance |
| spellingShingle | Balduíno César Mateus Mateus Mendes José Torres Farinha Rui Assis António Marques Cardoso Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press Energies LSTM recurrent neural network GRU paper press predictive maintenance |
| title | Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press |
| title_full | Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press |
| title_fullStr | Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press |
| title_full_unstemmed | Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press |
| title_short | Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press |
| title_sort | comparing lstm and gru models to predict the condition of a pulp paper press |
| topic | LSTM recurrent neural network GRU paper press predictive maintenance |
| url | https://www.mdpi.com/1996-1073/14/21/6958 |
| work_keys_str_mv | AT balduinocesarmateus comparinglstmandgrumodelstopredicttheconditionofapulppaperpress AT mateusmendes comparinglstmandgrumodelstopredicttheconditionofapulppaperpress AT josetorresfarinha comparinglstmandgrumodelstopredicttheconditionofapulppaperpress AT ruiassis comparinglstmandgrumodelstopredicttheconditionofapulppaperpress AT antoniomarquescardoso comparinglstmandgrumodelstopredicttheconditionofapulppaperpress |