Fault Detection and Prediction for a Wood Chip Screw Conveyor

• Autorzy: Henriques Lucas , Farinha Torres , Mendes Mateus

Identyfikatory

DOI

10.17531/ein/189323

• Języki publikacji: EN

Abstrakty

EN

Equipment maintenance is a key aspect to maximize its availability. Nowadays, much of the functioning and condition monitoring data from industrial machines is collected through sensors and stored, for off-line analysis. The present work focuses on data analysis of a screw conveyor of a biomass industry. The screw velocity and load were monitored and analysed, in order to detect and predict possible faults. A machine learning approach was used to detect anomalies, where different algorithms were tested with the data available, in order to train an anomaly classifier. The anomaly classifier was able to accurately identify most anomalies, based on historical data, temporal patterns and information of the maintenance interventions performed. The research carried out allowed to conclude that the Extra Trees Classifier algorithm achieved the best performance, among all algorithms tested, with 0.7974 F-score in the test set. The anomaly classifier has been shown to achieve remarkable accuracy in identifying anomalies. This research not only improves understanding of the performance of screw conveyors in biomass industries, but also highlights the practical utility of employing machine learning for proactive fault detection.

Słowa kluczowe

EN

industrial equipment; machine learning; predictive maintenance; screw conveyor

• Wydawca: Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne
• Czasopismo: Eksploatacja i Niezawodność
• Rocznik: 2024
• Tom: Vol. 26, no. 3
• Strony: art. no. 189323
• Opis fizyczny: Bibliogr. 33 poz., rys., tab., wykr.

Twórcy

autor

Henriques Lucas

• Polytechnic University of Coimbra, Portugal

autor

Farinha Torres

• Polytechnic University of Coimbra, Portugal
• RCM2+ - Research Centre for Asset Management and Systems Engineering

• https://orcid.org/0000-0002-9694-8079

autor

Mendes Mateus

• Polytechnic University of Coimbra, Portugal
• RCM2+ - Research Centre for Asset Management and Systems Engineering

• https://orcid.org/0000-0003-[phone]

Bibliografia

• 1. Wen, Q., Gao, J., Song, X., Sun, L., Xu, H. & Zhu, S. RobustSTL: A robust seasonal-trend decomposition algorithm for long time series. Proceedings Of The AAAI Conference On Artificial Intelligence. 33, 5409-5416 (2019) https://doi.org/10.1609/aaai.v33i01.33015409
• 2. Bandara, K., Bergmeir, C. & Hewamalage, H. LSTM-MSNet: Leveraging forecasts on sets of related time series with multiple seasonal patterns. IEEE Transactions On Neural Networks And Learning Systems. 32, 1586-1599 (2020) https://doi.org/10.1109/TNNLS.2020.2985720
• 3. Curtis, A., Smith, T., Ziganshin, B. & Elefteriades, J. The mystery of the Z-score. Aorta. 4, 124-130 (2016) https://doi.org/10.12945/j.aorta.2016.16.014
• 4. Mudersbach, C. & Jensen, J. Nonstationary extreme value analysis of annual max- imum water levels for designing coastal structures on the German North Sea coast- line. Journal Of Flood Risk Management. 3, 52-62 (2010) https://doi.org/10.1111/j.1753-318X.2009.01054.x
• 5. Pezo, L., Jovanović, A., Pezo, M., Čolović, R. & Lončar, B. Modified screw conveyor-mixers-Discrete element modeling approach. Advanced Powder Technology. 26, 1391-1399 (2015) https://doi.org/10.1016/j.apt.2015.07.016
• 6. Sudarso, L. & Rachmat, R. Design of Belt Conveyor for Sandblasting Material Handling System. Jurnal Teknik Mesin Dan Mekatronika (Journal Of Mechanical Engineering And Mechatronics). 5, 28-37 (2020) https://doi.org/10.33021/jmem.v5i1.942
• 7. Karwat, B., Rubacha, P. & Stan'czyk, E. Optimization of a screw conveyor's ex- ploitation parameters. Eksploatacja I Niezawodno's'c. 23 (2021) https://doi.org/10.17531/ein.2021.2.8
• 8. Jebb, A., Tay, L., Wang, W. & Huang, Q. Time series analysis for psychological research: examining and forecasting change. Frontiers In Psychology. 6 pp. 727 (2015) https://doi.org/10.3389/fpsyg.2015.00727
• 9. Deulgaonkar, V., Walimbe, A., Mahurkar, S., Patil, S. & Kakade, S. Failure Anal- ysis of Industrial Screw Conveyors. Journal Of Failure Analysis And Prevention. 23, 1693-1700 (2023) https://doi.org/10.1007/s11668-023-01719-3
• 10. Geurts, P., Ernst, D. & Wehenkel, L. Extremely randomized trees. Machine Learn- ing. 63, 3-42 (2006) https://doi.org/10.1007/s10994-006-6226-1
• 11. Jamlos, M., Jamlos, M., Mustafa, W., Othman, N., Rohani, M., Saidi, S., Sarip,M. & Nawi, M.Reduced graphene oxide uwb array sensor: high performance for brain tumor imaging and detection. Nanomaterials. 13, 27 (2022) https://doi.org/10.3390/nano13010027
• 12. Zaica, A., Visan, A., Paun, A., Gageanu, P., Bunduchi, G., Zaica, A., Stefan, V. & Manea, D. The coating process of corn grains using a treatment machine with brush screw conveyor. Proceedings Of The 44th International Symposium On Agricultural Engineering: Actual Tasks On Agricultural Engineering. pp. 23-26 (2016)
• 13. Ali, M. PyCaret: An open source, low-code machine learning library in Python. (2020,4), https://www.pycaret.org, PyCaret version 1.0.0
• 14. Hadi, S., Al Azis, A., Viyus, V., Puspitasari, E., Firdaus, A. & Setiawan, A. Plan- ning for Maintenance and Repair of Continuous Ship Unloader Using the IRRO Method. Logic: Jurnal Rancang Bangun Dan Teknologi. 21, 52-63 (2021) https://doi.org/10.31940/logic.v21i1.2383
• 15. Geca, J. Performance comparison of machine learning algorithms for predictive maintenance. Informatyka, Automatyka, Pomiary W Gospodarce I Ochronie S'rodowiska. 10 pp. 32-35 (2020,9),https://www.mendeley.com/catalogue/32e41dca-742c-3e16-bd55-26f68a0da004, https://doi.org/10.35784/iapgos.1834
• 16. Wilcox, R. The regression smoother LOWESS: A confidence band that allows heteroscedasticity and has some specified simultaneous probability coverage. Journal Of Modern Applied Statistical Methods. 16, 3 (2017) https://doi.org/10.22237/jmasm/1509494580
• 17. Martins, A., Mateus, B., Fonseca, I., Farinha, J., Rodrigues, J., Mendes, M. & Cardoso, A. Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models. Energies. 16 (2023),https://www.mdpi.com/1996-1073/16/6/2651, https://doi.org/10.3390/en16062651
• 18. Rodrigues, J., Martins, A., Mendes, M., Farinha, J., Mateus, R. & Cardoso,A. Automatic Risk Assessment for an Industrial Asset Using Unsupervised and Supervised Learning. Energies. 15 (2022), https://www.mdpi.com/1996- 1073/15/24/9387 https://doi.org/10.3390/en15249387
• 19. Fukuda, K., Stanley, H. & Amaral, L. Heuristic segmentation of a nonstationary time series. Physical Review E. 69, 021108 (2004) https://doi.org/10.1103/PhysRevE.69.021108
• 20. Tatarintsev, M., Korchagin, S., Nikitin, P., Gorokhova, R., Bystrenina, I. & Serdechnyy, D. Analysis of the forecast price as a factor of sustainable development of agriculture. Agronomy. 11, 1235 (2021) https://doi.org/10.3390/agronomy11061235
• 21. Hossain, Z., Rahman, A., Hossain, M. & Karami, J. Over-differencing and forecasting with non-stationary time series data. Dhaka University Journal Of Science. 67, 21-26 (2019) https://doi.org/10.3329/dujs.v67i1.54568
• 22. Bourke, P. Interpolation methods. Miscellaneous: Projection, Modelling, Render-ing. 1 (1999), doi: 10.1213/ANE.0000000000002864. PMID: 29481436.
• 23. Garcia, S., Luengo, J. & Herrera, F. Data preprocessing in data mining. (Springer, 2015) https://doi.org/10.1007/978-3-319-10247-4
• 24. Swanson, L. Linking maintenance strategies to performance. International Journal Of Production Economics. 70, 237-244 (2001), https://doi.org/10.1016/S0925-5273(00)00067-0
• 25. Zareiforoush, H., Komarizadeh, M., Alizadeh, M., Masoomi, M. & Tavakoli, H.Performance evaluation of screw augers in paddy grains handling. International Agrophysics. 24 pp. 389-396 (2010,1)
• 26. Strauß, P., Schmitz, M., Wostmann, R. & Deuse, J. Enabling of Predictive Maintenance in the Brownfield through Low-Cost Sensors, an IIoT-Architecture and Machine Learning. 2018 IEEE International Conference On Big Data (Big Data). pp. 1474-1483 (2018) https://doi.org/10.1109/BigData.2018.8622076
• 27. Cavallo, C. All About Screw Conveyors - Types, Design, and Uses. (Thomasnet), (last access on: 2021-10-01) https://www.thomasnet.com/articles/materials- handling/all-about-screw-conveyors/
• 28. Evstratov, V., Rud, A. & Belousov, K. Process Modelling Vertical Screw Trans-port of Bulk Material Flow. Procedia Engineering. 129 pp. 397-402 (2015),https://www.sciencedirect.com/science/article/pii/S1877705815040187, International Conference on Industrial Engineering (ICIE-2015) https://doi.org/10.1016/j.proeng.2015.12.134
• 29. Tian, Y., Yuan, P., Yang, F., Gu, J., Chen, M., Tang, J., Su, Y., Ding, T., Zhang, K. & Cheng, Q. Research on the Principle of a New Flexible Screw Conveyor and Its Power Consumption. Applied Sciences. 8 (2018), https://doi.org/10.3390/app8071038
• 30. Waje, S., Thorat, B. & Mujumdar, A. Screw Conveyor Dryer: Process and Equip-ment Design. Drying Technology - DRY TECHNOL. 25 pp. 241-247 (2007,2) https://doi.org/10.1080/07373930601161112
• 31. Gobdc Planning For Every Eventuality: Instituting a Multi-Faceted Mainte- nance Program. (Gobdc), https://www.gobdc.com/planning-for-every-eventuality-instituting-a-multi-faceted-maintenance-program/
• 32. Sehrawat, D. & Gill, N. Smart sensors: Analysis of different types of IoT sen-sors. 2019 3rd International Conference On Trends In Electronics And Informatics (ICOEI). pp. 523-528 (2019) https://doi.org/10.1109/ICOEI.2019.8862778
• 33. Kanawaday, A. & Sane, A. Machine learning for predictive maintenance of in-dustrial machines using IoT sensor data. 2017 8th IEEE International Conference On Software Engineering And Service Science (ICSESS). pp. 87-90 (2017), https://doi.org/10.1109/ICSESS.2017.8342870