Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models
The maintenance paradigm has evolved over the last few years and companies that want to remain competitive in the market need to provide condition-based maintenance (CBM). The diagnosis and prognosis of the health status of equipment, predictive maintenance (PdM), are fundamental strategies to perfo...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/6/2651 |
| _version_ | 1797612099839459328 |
|---|---|
| author | Alexandre Martins Balduíno Mateus Inácio Fonseca José Torres Farinha João Rodrigues Mateus Mendes António Marques Cardoso |
| author_facet | Alexandre Martins Balduíno Mateus Inácio Fonseca José Torres Farinha João Rodrigues Mateus Mendes António Marques Cardoso |
| author_sort | Alexandre Martins |
| collection | DOAJ |
| description | The maintenance paradigm has evolved over the last few years and companies that want to remain competitive in the market need to provide condition-based maintenance (CBM). The diagnosis and prognosis of the health status of equipment, predictive maintenance (PdM), are fundamental strategies to perform informed maintenance, increasing the company’s profit. This article aims to present a diagnosis and prognosis methodology using a hidden Markov model (HMM) classifier to recognise the equipment status in real time and a deep neural network (DNN), specifically a gated recurrent unit (GRU), to determine this same status in a future of one week. The data collected by the sensors go through several phases, starting by cleaning them. After that, temporal windows are created in order to generate statistical features of the time domain to better understand the equipment’s behaviour. These features go through a normalisation to produce inputs for a feature extraction process, via a principal component analysis (PCA). After the dimensional reduction and obtaining new features with more information, a clustering is performed by the K-means algorithm, in order to group similar data. These clusters enter the HMM classifier as observable states. After training using the <i>Baum–Welch</i> algorithm, the <i>Viterbi</i> algorithm is used to find the best path of hidden states that represent the diagnosis of the equipment, containing three states: state 1—“State of Good Operation”; state 2—“Warning State”; state 3—“Failure State”. Once the equipment diagnosis is complete, the GRU model is used to predict the future, both of the observable states as well as the hidden states coming out from the HMM. Thus, through this network, it is possible to directly obtain the health states 7 days ahead, without the necessity to run the whole methodology from scratch. |
| first_indexed | 2024-03-11T06:36:40Z |
| format | Article |
| id | doaj.art-3f533c3a9d5140159a59f78710460842 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T06:36:40Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-3f533c3a9d5140159a59f787104608422023-11-17T10:49:04ZengMDPI AGEnergies1996-10732023-03-01166265110.3390/en16062651Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov ModelsAlexandre Martins0Balduíno Mateus1Inácio Fonseca2José Torres Farinha3João Rodrigues4Mateus Mendes5António Marques Cardoso6EIGeS—Research Centre in Industrial Engineering, Management and Sustainability, Lusófona University, Campo Grande, 376, 1749-024 Lisboa, PortugalEIGeS—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, PortugalInstituto Superior de Engenharia de Coimbra, Polytechnic of Coimbra, 3045-093 Coimbra, PortugalEIGeS—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, PortugalCISE—Electromechatronic Systems Research Centre, University of Beira Interior, 62001-001 Covilhã, PortugalThe maintenance paradigm has evolved over the last few years and companies that want to remain competitive in the market need to provide condition-based maintenance (CBM). The diagnosis and prognosis of the health status of equipment, predictive maintenance (PdM), are fundamental strategies to perform informed maintenance, increasing the company’s profit. This article aims to present a diagnosis and prognosis methodology using a hidden Markov model (HMM) classifier to recognise the equipment status in real time and a deep neural network (DNN), specifically a gated recurrent unit (GRU), to determine this same status in a future of one week. The data collected by the sensors go through several phases, starting by cleaning them. After that, temporal windows are created in order to generate statistical features of the time domain to better understand the equipment’s behaviour. These features go through a normalisation to produce inputs for a feature extraction process, via a principal component analysis (PCA). After the dimensional reduction and obtaining new features with more information, a clustering is performed by the K-means algorithm, in order to group similar data. These clusters enter the HMM classifier as observable states. After training using the <i>Baum–Welch</i> algorithm, the <i>Viterbi</i> algorithm is used to find the best path of hidden states that represent the diagnosis of the equipment, containing three states: state 1—“State of Good Operation”; state 2—“Warning State”; state 3—“Failure State”. Once the equipment diagnosis is complete, the GRU model is used to predict the future, both of the observable states as well as the hidden states coming out from the HMM. Thus, through this network, it is possible to directly obtain the health states 7 days ahead, without the necessity to run the whole methodology from scratch.https://www.mdpi.com/1996-1073/16/6/2651maintenancediagnosisprognosisdeep neural networkhidden Markov modelsmachine learning |
| spellingShingle | Alexandre Martins Balduíno Mateus Inácio Fonseca José Torres Farinha João Rodrigues Mateus Mendes António Marques Cardoso Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models Energies maintenance diagnosis prognosis deep neural network hidden Markov models machine learning |
| title | Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models |
| title_full | Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models |
| title_fullStr | Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models |
| title_full_unstemmed | Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models |
| title_short | Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models |
| title_sort | predicting the health status of a pulp press based on deep neural networks and hidden markov models |
| topic | maintenance diagnosis prognosis deep neural network hidden Markov models machine learning |
| url | https://www.mdpi.com/1996-1073/16/6/2651 |
| work_keys_str_mv | AT alexandremartins predictingthehealthstatusofapulppressbasedondeepneuralnetworksandhiddenmarkovmodels AT balduinomateus predictingthehealthstatusofapulppressbasedondeepneuralnetworksandhiddenmarkovmodels AT inaciofonseca predictingthehealthstatusofapulppressbasedondeepneuralnetworksandhiddenmarkovmodels AT josetorresfarinha predictingthehealthstatusofapulppressbasedondeepneuralnetworksandhiddenmarkovmodels AT joaorodrigues predictingthehealthstatusofapulppressbasedondeepneuralnetworksandhiddenmarkovmodels AT mateusmendes predictingthehealthstatusofapulppressbasedondeepneuralnetworksandhiddenmarkovmodels AT antoniomarquescardoso predictingthehealthstatusofapulppressbasedondeepneuralnetworksandhiddenmarkovmodels |