IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v16y2023i6p2651-d1094400.html
   My bibliography  Save this article

Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models

Author

Listed:
  • Alexandre Martins

    (EIGeS—Research Centre in Industrial Engineering, Management and Sustainability, Lusófona University, Campo Grande, 376, 1749-024 Lisboa, Portugal
    CISE—Electromechatronic Systems Research Centre, University of Beira Interior, 62001-001 Covilhã, Portugal)

  • Balduíno Mateus

    (EIGeS—Research Centre in Industrial Engineering, Management and Sustainability, Lusófona University, Campo Grande, 376, 1749-024 Lisboa, Portugal
    CISE—Electromechatronic Systems Research Centre, University of Beira Interior, 62001-001 Covilhã, Portugal)

  • Inácio Fonseca

    (Instituto Superior de Engenharia de Coimbra, Polytechnic of Coimbra, 3045-093 Coimbra, Portugal)

  • José Torres Farinha

    (Instituto Superior de Engenharia de Coimbra, Polytechnic of Coimbra, 3045-093 Coimbra, Portugal
    Centre for Mechanical Engineering, Materials and Processes—CEMMPRE, University of Coimbra, 3030-788 Coimbra, Portugal)

  • João Rodrigues

    (EIGeS—Research Centre in Industrial Engineering, Management and Sustainability, Lusófona University, Campo Grande, 376, 1749-024 Lisboa, Portugal
    CISE—Electromechatronic Systems Research Centre, University of Beira Interior, 62001-001 Covilhã, Portugal)

  • Mateus Mendes

    (Instituto Superior de Engenharia de Coimbra, Polytechnic of Coimbra, 3045-093 Coimbra, Portugal)

  • António Marques Cardoso

    (CISE—Electromechatronic Systems Research Centre, University of Beira Interior, 62001-001 Covilhã, Portugal)

Abstract

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 Baum–Welch algorithm, the Viterbi 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.

Suggested Citation

  • Alexandre Martins & Balduíno Mateus & Inácio Fonseca & José Torres Farinha & João Rodrigues & Mateus Mendes & António Marques Cardoso, 2023. "Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models," Energies, MDPI, vol. 16(6), pages 1-26, March.
    • Handle: RePEc:gam:jeners:v:16:y:2023:i:6:p:2651-:d:1094400
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/16/6/2651/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/16/6/2651/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Sang M. Lee & DonHee Lee & Youn Sung Kim, 2019. "The quality management ecosystem for predictive maintenance in the Industry 4.0 era," International Journal of Quality Innovation, Springer, vol. 5(1), pages 1-11, December.
    2. João Antunes Rodrigues & Alexandre Martins & Mateus Mendes & José Torres Farinha & Ricardo J. G. Mateus & Antonio J. Marques Cardoso, 2022. "Automatic Risk Assessment for an Industrial Asset Using Unsupervised and Supervised Learning," Energies, MDPI, vol. 15(24), pages 1-17, December.
    3. Ales Jandera & Tomas Skovranek, 2022. "Customer Behaviour Hidden Markov Model," Mathematics, MDPI, vol. 10(8), pages 1-10, April.
    4. Yaping Li & Haiyan Li & Zhen Chen & Ying Zhu, 2022. "An Improved Hidden Markov Model for Monitoring the Process with Autocorrelated Observations," Energies, MDPI, vol. 15(5), pages 1-13, February.
    5. Hamzeh Soltanali & Mehdi Khojastehpour & José Torres Farinha & José Edmundo de Almeida e Pais, 2021. "An Integrated Fuzzy Fault Tree Model with Bayesian Network-Based Maintenance Optimization of Complex Equipment in Automotive Manufacturing," Energies, MDPI, vol. 14(22), pages 1-21, November.
    6. van Staden, Heletjé E. & Boute, Robert N., 2021. "The effect of multi-sensor data on condition-based maintenance policies," European Journal of Operational Research, Elsevier, vol. 290(2), pages 585-600.
    7. Wang, Yun & Zou, Runmin & Liu, Fang & Zhang, Lingjun & Liu, Qianyi, 2021. "A review of wind speed and wind power forecasting with deep neural networks," Applied Energy, Elsevier, vol. 304(C).
    8. Liu, Xiaolei & Lin, Zi & Feng, Ziming, 2021. "Short-term offshore wind speed forecast by seasonal ARIMA - A comparison against GRU and LSTM," Energy, Elsevier, vol. 227(C).
    9. Hamzeh Soltanali & Mehdi Khojastehpour & José Edmundo de Almeida e Pais & José Torres Farinha, 2022. "Sustainable Food Production: An Intelligent Fault Diagnosis Framework for Analyzing the Risk of Critical Processes," Sustainability, MDPI, vol. 14(3), pages 1-22, January.
    10. Balduíno César Mateus & Mateus Mendes & José Torres Farinha & Rui Assis & António Marques Cardoso, 2021. "Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press," Energies, MDPI, vol. 14(21), pages 1-21, October.
    11. José Edmundo de Almeida Pais & Hugo D. N. Raposo & José Torres Farinha & Antonio J. Marques Cardoso & Pedro Alexandre Marques, 2021. "Optimizing the Life Cycle of Physical Assets through an Integrated Life Cycle Assessment Method," Energies, MDPI, vol. 14(19), pages 1-24, September.
    12. Oakley, Jordan L. & Wilson, Kevin J. & Philipson, Pete, 2022. "A condition-based maintenance policy for continuously monitored multi-component systems with economic and stochastic dependence," Reliability Engineering and System Safety, Elsevier, vol. 222(C).
    13. Soleimani, Morteza & Campean, Felician & Neagu, Daniel, 2021. "Integration of Hidden Markov Modelling and Bayesian Network for fault detection and prediction of complex engineered systems," Reliability Engineering and System Safety, Elsevier, vol. 215(C).
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Balduíno César Mateus & José Torres Farinha & Mateus Mendes, 2024. "Fault Detection and Prediction for Power Transformers Using Fuzzy Logic and Neural Networks," Energies, MDPI, vol. 17(2), pages 1-18, January.
    2. Ruiqi Tian & Santiago Gomez-Rosero & Miriam A. M. Capretz, 2023. "Health Prognostics Classification with Autoencoders for Predictive Maintenance of HVAC Systems," Energies, MDPI, vol. 16(20), pages 1-21, October.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Li, Min & Yang, Yi & He, Zhaoshuang & Guo, Xinbo & Zhang, Ruisheng & Huang, Bingqing, 2023. "A wind speed forecasting model based on multi-objective algorithm and interpretability learning," Energy, Elsevier, vol. 269(C).
    2. Bashir, Hassan & Sibtain, Muhammad & Hanay, Özge & Azam, Muhammad Imran & Qurat-ul-Ain, & Saleem, Snoober, 2023. "Decomposition and Harris hawks optimized multivariate wind speed forecasting utilizing sequence2sequence-based spatiotemporal attention," Energy, Elsevier, vol. 278(PB).
    3. Dokur, Emrah & Erdogan, Nuh & Salari, Mahdi Ebrahimi & Karakuzu, Cihan & Murphy, Jimmy, 2022. "Offshore wind speed short-term forecasting based on a hybrid method: Swarm decomposition and meta-extreme learning machine," Energy, Elsevier, vol. 248(C).
    4. Wen, Songkang & Li, Yanting & Su, Yan, 2022. "A new hybrid model for power forecasting of a wind farm using spatial–temporal correlations," Renewable Energy, Elsevier, vol. 198(C), pages 155-168.
    5. Li, Jiale & Song, Zihao & Wang, Xuefei & Wang, Yanru & Jia, Yaya, 2022. "A novel offshore wind farm typhoon wind speed prediction model based on PSO–Bi-LSTM improved by VMD," Energy, Elsevier, vol. 251(C).
    6. Ana Lagos & Joaquín E. Caicedo & Gustavo Coria & Andrés Romero Quete & Maximiliano Martínez & Gastón Suvire & Jesús Riquelme, 2022. "State-of-the-Art Using Bibliometric Analysis of Wind-Speed and -Power Forecasting Methods Applied in Power Systems," Energies, MDPI, vol. 15(18), pages 1-40, September.
    7. Dai, Xiaoran & Liu, Guo-Ping & Hu, Wenshan, 2023. "An online-learning-enabled self-attention-based model for ultra-short-term wind power forecasting," Energy, Elsevier, vol. 272(C).
    8. Wu, Binrong & Wang, Lin & Zeng, Yu-Rong, 2022. "Interpretable wind speed prediction with multivariate time series and temporal fusion transformers," Energy, Elsevier, vol. 252(C).
    9. Dong, Xiaochong & Sun, Yingyun & Dong, Lei & Li, Jian & Li, Yan & Di, Lei, 2023. "Transferable wind power probabilistic forecasting based on multi-domain adversarial networks," Energy, Elsevier, vol. 285(C).
    10. Wu, Zhou & Zeng, Shaoxiong & Jiang, Ruiqi & Zhang, Haoran & Yang, Zhile, 2023. "Explainable temporal dependence in multi-step wind power forecast via decomposition based chain echo state networks," Energy, Elsevier, vol. 270(C).
    11. Parri, Srihari & Teeparthi, Kiran & Kosana, Vishalteja, 2023. "A hybrid VMD based contextual feature representation approach for wind speed forecasting," Renewable Energy, Elsevier, vol. 219(P1).
    12. João Antunes Rodrigues & José Torres Farinha & Mateus Mendes & Ricardo J. G. Mateus & António J. Marques Cardoso, 2022. "Comparison of Different Features and Neural Networks for Predicting Industrial Paper Press Condition," Energies, MDPI, vol. 15(17), pages 1-16, August.
    13. Omoyele, Olalekan & Hoffmann, Maximilian & Koivisto, Matti & Larrañeta, Miguel & Weinand, Jann Michael & Linßen, Jochen & Stolten, Detlef, 2024. "Increasing the resolution of solar and wind time series for energy system modeling: A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 189(PB).
    14. Zhang, Yagang & Wang, Hui & Wang, Jingchao & Cheng, Xiaodan & Wang, Tong & Zhao, Zheng, 2024. "Ensemble optimization approach based on hybrid mode decomposition and intelligent technology for wind power prediction system," Energy, Elsevier, vol. 292(C).
    15. Azizi, Fariba & Salari, Nooshin, 2023. "A novel condition-based maintenance framework for parallel manufacturing systems based on bivariate birth/birth–death processes," Reliability Engineering and System Safety, Elsevier, vol. 229(C).
    16. Ding, Song & Cai, Zhijian & Qin, Xinghuan & Shen, Xingao, 2024. "Comparative assessment and policy analysis of forecasting quarterly renewable energy demand: Fresh evidence from an innovative seasonal approach with superior matching algorithms," Applied Energy, Elsevier, vol. 367(C).
    17. Linlin Yu & Jiafeng Wu & Yuming Cheng & Gaojun Meng & Shuyu Chen & Yang Lu & Ke Xu, 2024. "Control Strategy for Wind Farms-Energy Storage Participation in Primary Frequency Regulation Considering Wind Turbine Operation State," Energies, MDPI, vol. 17(14), pages 1-13, July.
    18. Yang, Weijia & Sparrow, Sarah N. & Wallom, David C.H., 2024. "A comparative climate-resilient energy design: Wildfire Resilient Load Forecasting Model using multi-factor deep learning methods," Applied Energy, Elsevier, vol. 368(C).
    19. Shengli Liao & Xudong Tian & Benxi Liu & Tian Liu & Huaying Su & Binbin Zhou, 2022. "Short-Term Wind Power Prediction Based on LightGBM and Meteorological Reanalysis," Energies, MDPI, vol. 15(17), pages 1-21, August.
    20. Wang, Xiaodi & Hao, Yan & Yang, Wendong, 2024. "Novel wind power ensemble forecasting system based on mixed-frequency modeling and interpretable base model selection strategy," Energy, Elsevier, vol. 297(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:16:y:2023:i:6:p:2651-:d:1094400. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.