Anticipating Future Behavior of an Industrial Press Using LSTM Networks
Predictive maintenance is very important in industrial plants to support decisions aiming to maximize maintenance investments and equipment’s availability. This paper presents predictive models based on long short-term memory neural networks, applied to a dataset of sensor readings. The aim is to fo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/13/6101 |
| _version_ | 1797528177601413120 |
|---|---|
| author | Balduíno César Mateus Mateus Mendes José Torres Farinha António Marques Cardoso |
| author_facet | Balduíno César Mateus Mateus Mendes José Torres Farinha António Marques Cardoso |
| author_sort | Balduíno César Mateus |
| collection | DOAJ |
| description | Predictive maintenance is very important in industrial plants to support decisions aiming to maximize maintenance investments and equipment’s availability. This paper presents predictive models based on long short-term memory neural networks, applied to a dataset of sensor readings. The aim is to forecast future equipment statuses based on data from an industrial paper press. The datasets contain data from a three-year period. Data are pre-processed and the neural networks are optimized to minimize prediction errors. The results show that it is possible to predict future behavior up to one month in advance with reasonable confidence. Based on these results, it is possible to anticipate and optimize maintenance decisions, as well as continue research to improve the reliability of the model. |
| first_indexed | 2024-03-10T09:54:28Z |
| format | Article |
| id | doaj.art-1ab0014a13b544248228cdc14ea07b78 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T09:54:28Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1ab0014a13b544248228cdc14ea07b782023-11-22T02:28:22ZengMDPI AGApplied Sciences2076-34172021-06-011113610110.3390/app11136101Anticipating Future Behavior of an Industrial Press Using LSTM NetworksBalduíno César Mateus0Mateus Mendes1José Torres Farinha2António Marques Cardoso3EIGeS—Research Centre in Industrial Engineering, Management and Sustainability, Lusófona University, Campo Grande, 376, 1749-024 Lisboa, PortugalPolytechnic of Coimbra, ISEC, 3045-093 Coimbra, PortugalPolytechnic of Coimbra, ISEC, 3045-093 Coimbra, PortugalCISE—Electromechatronic Systems Research Centre, University of Beira Interior, Calçada Fonte do Lameiro, P–62001-001 Covilhã, PortugalPredictive maintenance is very important in industrial plants to support decisions aiming to maximize maintenance investments and equipment’s availability. This paper presents predictive models based on long short-term memory neural networks, applied to a dataset of sensor readings. The aim is to forecast future equipment statuses based on data from an industrial paper press. The datasets contain data from a three-year period. Data are pre-processed and the neural networks are optimized to minimize prediction errors. The results show that it is possible to predict future behavior up to one month in advance with reasonable confidence. Based on these results, it is possible to anticipate and optimize maintenance decisions, as well as continue research to improve the reliability of the model.https://www.mdpi.com/2076-3417/11/13/6101time series predictionLSTM predictiondeep learning predictionpredictive maintenance |
| spellingShingle | Balduíno César Mateus Mateus Mendes José Torres Farinha António Marques Cardoso Anticipating Future Behavior of an Industrial Press Using LSTM Networks Applied Sciences time series prediction LSTM prediction deep learning prediction predictive maintenance |
| title | Anticipating Future Behavior of an Industrial Press Using LSTM Networks |
| title_full | Anticipating Future Behavior of an Industrial Press Using LSTM Networks |
| title_fullStr | Anticipating Future Behavior of an Industrial Press Using LSTM Networks |
| title_full_unstemmed | Anticipating Future Behavior of an Industrial Press Using LSTM Networks |
| title_short | Anticipating Future Behavior of an Industrial Press Using LSTM Networks |
| title_sort | anticipating future behavior of an industrial press using lstm networks |
| topic | time series prediction LSTM prediction deep learning prediction predictive maintenance |
| url | https://www.mdpi.com/2076-3417/11/13/6101 |
| work_keys_str_mv | AT balduinocesarmateus anticipatingfuturebehaviorofanindustrialpressusinglstmnetworks AT mateusmendes anticipatingfuturebehaviorofanindustrialpressusinglstmnetworks AT josetorresfarinha anticipatingfuturebehaviorofanindustrialpressusinglstmnetworks AT antoniomarquescardoso anticipatingfuturebehaviorofanindustrialpressusinglstmnetworks |