Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Machine Learning Approaches for Diagnostics and Prognostics of Industrial Systems Using Open Source Data from PHM Data Challenges: A Review (2312.16810v3)

Published 28 Dec 2023 in cs.LG and cs.AI

Abstract: In the field of Prognostics and Health Management (PHM), recent years have witnessed a significant surge in the application of ML. Despite this growth, the field grapples with a lack of unified guidelines and systematic approaches for effectively implementing these ML techniques and comprehensive analysis regarding industrial open-source data across varied scenarios. To address these gaps, this paper provides a comprehensive review of ML approaches for diagnostics and prognostics of industrial systems using open-source datasets from PHM Data Challenge Competitions held between 2018 and 2023 by PHM Society and IEEE Reliability Society and summarizes a unified ML framework. This review systematically categorizes and scrutinizes the problems, challenges, methodologies, and advancements demonstrated in these competitions, highlighting the evolving role of both conventional machine learning and deep learning in tackling complex industrial tasks related to detection, diagnosis, assessment, and prognosis. Moreover, this paper delves into the common challenges in PHM data challenge competitions by emphasizing data-related and model-related issues and evaluating the limitations of these competitions. The potential solutions to address these challenges are also summarized. Finally, we identify key themes and potential directions for future research, providing opportunities and prospects for next-generation ML-PHM development in PHM domain.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (82)
  1. Expert-informed hierarchical diagnostics of multiple fault modes of a spacecraft propulsion system. In PHM Society Asia-Pacific Conference, volume 4, 2023.
  2. Rule-based diagnostics of a production line. In PHM Society European Conference, volume 6, pages 10–10, 2021.
  3. An extreme gradient boosting aided fault diagnosis approach: A case study of fuse test bench. IEEE Transactions on Artificial Intelligence, 2022.
  4. Ensemble of lstm networks for fault detection, classification, and root cause identification in quality control line. In PHM Society European Conference, volume 6, pages 6–6, 2021.
  5. 2023 ieee international conference on prognostics and health management (icphm).
  6. A data-driven approach for rul prediction of an experimental filtration system. In PHM Society European Conference, volume 5, 2020.
  7. D. J. Berndt and J. Clifford. Using dynamic time warping to find patterns in time series. In Proceedings of the 3rd international conference on knowledge discovery and data mining, pages 359–370, 1994.
  8. Phm society data challenge 2021, 2021.
  9. To trust or not: Towards efficient uncertainty quantification for stochastic shapley explanations. In PHM Society Asia-Pacific Conference, volume 4, 2023.
  10. Fault prognosis of turbofan engines: Eventual failure prediction and remaining useful life estimation. arXiv preprint arXiv:2303.12982, 2023.
  11. Shapley-based explainable ai for clustering applications in fault diagnosis and prognosis. arXiv preprint arXiv:2303.14581, 2023.
  12. Divide, propagate and conquer: Splitting a complex diagnosis problem for early detection of faults in a manufacturing production line. In PHM Society European Conference, volume 6, pages 9–9, 2021.
  13. Rocket: exceptionally fast and accurate time series classification using random convolutional kernels. Data Mining and Knowledge Discovery, 34(5):1454–1495, 2020.
  14. Inception based deep convolutional neural network for remaining useful life estimation of turbofan engines. In Annual Conference of the PHM Society, volume 13, 2021.
  15. Evaluating image classification deep convolutional neural network architectures for remaining useful life estimation of turbofan engines. International Journal of Prognostics and Health Management, 13(2), 2022.
  16. Icphm’23 benchmark vibration dataset applicable in machine learning for systems’ health monitoring. In In proceeding of IEEE Conference on Prognostics and Health Management (ICPHM), 2023.
  17. Neural turing machines for the remaining useful life estimation problem. Computers in Industry, 143:103762, 2022.
  18. A hierarchical xgboost early detection method for quality and productivity improvement of electronics manufacturing systems. In 7th European Conference of the Prognostics and Health Management Society 2022, 2022.
  19. A. He and X. Jin. Failure detection and remaining life estimation for ion mill etching process through deep-learning based multimodal data fusion. Journal of Manufacturing Science and Engineering, 141(10):101008, 2019.
  20. Temporal convolution-based long-short term memory network with attention mechanism for remaining useful life prediction. IEEE Transactions on Semiconductor Manufacturing, 35(2):220–228, 2022.
  21. Review of data-driven prognostics and health management techniques: lessions learned from phm data challenge competitions. Machine Failure Prevention Technology, 2017:1–17, 2017.
  22. Remaining useful life estimation for systems with abrupt failures. In Annual conference of the PHM society. September, pages 24–27, 2018.
  23. Tool wear monitoring with vibration signals based on short-time fourier transform and deep convolutional neural network in milling. Mathematical Problems in Engineering, 2021:1–14, 2021.
  24. Fault detection and classification for robotic test-bench. In PHM Society European Conference, volume 6, pages 7–7, 2021.
  25. K. İnce and Y. Genc. Joint autoencoder-regressor deep neural network for remaining useful life prediction. Engineering Science and Technology, an International Journal, 41:101409, 2023.
  26. Remaining useful life prediction for experimental filtration system: A data challenge. In PHM Society European Conference, volume 5, 2020.
  27. A dataset for fault classification in rock drills, a fast oscillating hydraulic system. In Annual Conference of the PHM Society, volume 14, 2022.
  28. Neural network and particle filtering: a hybrid framework for crack propagation prediction. arXiv preprint arXiv:2004.13556, 2020.
  29. Anomaly detection in spacecraft propulsion system using time series classification based on k-nn. In PHM Society Asia-Pacific Conference, volume 4, 2023.
  30. Challenges and opportunities of system-level prognostics. Sensors, 21(22):7655, 2021.
  31. Domain adaptation based fault diagnosis under variable operating conditions of a rock drill. International Journal of Prognostics and Health Management, 14(2), 2023.
  32. A hybrid approach of data-driven and physics-based methods for estimation and prediction of fatigue crack growth. International Journal of Prognostics and Health Management, 11(1), 2020.
  33. M. Kreuzer and W. Kellermann. 1-d residual convolutional neural network coupled with data augmentation and regularization for the icphm 2023 data challenge. In 2023 IEEE International Conference on Prognostics and Health Management (ICPHM), pages 186–191. IEEE, 2023.
  34. Industry 4.0. Business & information systems engineering, 6:239–242, 2014.
  35. A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manufacturing letters, 3:18–23, 2015.
  36. J. Lee et al. Industrial ai. Applications with sustainable performance, 2020.
  37. Stream-of-quality methodology for industrial internet-based manufacturing system. Manufacturing Letters, 34:58–61, 2022.
  38. J. Lee and H. Su. A unified industrial large knowledge model framework in smart manufacturing. arXiv preprint arXiv:2312.14428, 2023.
  39. Data-driven health condition and rul prognosis for liquid filtration systems. Journal of Mechanical Science and Technology, 35:1597–1607, 2021.
  40. Hybrid approach of xgboost and rule-based model for fault detection and severity estimation in spacecraft propulsion system. In PHM Society Asia-Pacific Conference, volume 4, 2023.
  41. An ensemble of convolution-based methods for fault detection using vibration signals. arXiv preprint arXiv:2305.05532, 2023.
  42. Chatgpt-like large-scale foundation models for prognostics and health management: A survey and roadmaps. arXiv preprint arXiv:2305.06472, 2023.
  43. Hydraulic rock drill fault classification using x- vectors. Mathematics, 11(7):1724, 2023.
  44. Two-stage transfer learning for fault prognosis of ion mill etching process. IEEE Transactions on Semiconductor Manufacturing, 34(2):185–193, 2021.
  45. R. Łomowski and S. Hummel. A method to estimate the remaining useful life of a filter using a hybrid approach based on kernel regression and simple statistics. In PHM Society European Conference, volume 5, 2020.
  46. Predictive maintenance in the industry: A comparative study on deep learning-based remaining useful life estimation. In 2023 IEEE 21st International Conference on Industrial Informatics (INDIN), pages 1–9. IEEE, 2023.
  47. A. Lövberg. Remaining useful life prediction of aircraft engines with variable length input sequences. In Annual Conference of the PHM Society, volume 13, 2021.
  48. A unified approach to interpreting model predictions. Advances in neural information processing systems, 30, 2017.
  49. T. Minami and J. Lee. Phm for spacecraft propulsion systems: Similarity-based model and physics-inspired features. In PHM Society Asia-Pacific Conference, volume 4, 2023.
  50. Novel ensemble domain adaptation methodology for enhanced multi-class fault diagnosis of highly-connected fleet of assets. In PHM Society Asia-Pacific Conference, volume 4, 2023.
  51. Application of machine learning for anomaly detection in printed circuit boards imbalance date set. In 2023 IEEE International Conference on Prognostics and Health Management (ICPHM), pages 128–133. IEEE, 2023.
  52. C. Molnar. Interpretable machine learning. Lulu. com, 2020.
  53. A hybrid approach combining data-driven and signal-processing-based methods for fault diagnosis of a hydraulic rock drill. International Journal of Prognostics and Health Management, 14(1), 2023.
  54. Industrial artificial intelligence in industry 4.0-systematic review, challenges and outlook. IEEE Access, 8:220121–220139, 2020.
  55. Explainable machinery faults prediction using ensemble tree classifiers: Bagging or boosting? In Annual Conference of the PHM Society, volume 13, 2021.
  56. Structure fatigue crack length estimation and prediction using ultrasonic wave data based on ensemble linear regression and paris’s law. International Journal of Prognostics and Health Management, 11(2), 2020.
  57. B. Rezaeianjouybari and Y. Shang. Deep learning for prognostics and health management: State of the art, challenges, and opportunities. Measurement, 163:107929, 2020.
  58. ” why should i trust you?” explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135–1144, 2016.
  59. Application of machine learning methods to predict the quality of electric circuit boards of a production line. In PHM Society European Conference, volume 7, pages 550–555, 2022.
  60. Gear fault diagnosis based on short-time fourier transform and deep residual network under multiple operation conditions. In 2023 IEEE International Conference on Prognostics and Health Management (ICPHM), pages 166–171. IEEE, 2023.
  61. Concurrent estimation of remaining useful life for multiple faults in an ion etch mill: a data-driven approach. In Annual conference of the PHM society, volume 10, 2018.
  62. Industrial internet of things: Challenges, opportunities, and directions. IEEE transactions on industrial informatics, 14(11):4724–4734, 2018.
  63. X-vectors: Robust dnn embeddings for speaker recognition. In 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pages 5329–5333. IEEE, 2018.
  64. A comprehensive approach for gearbox fault detection and diagnosis using sequential neural networks. In 2023 IEEE International Conference on Prognostics and Health Management (ICPHM), pages 180–185. IEEE, 2023.
  65. A stacked deep convolutional neural network to predict the remaining useful life of a turbofan engine. arXiv preprint arXiv:2111.12689, 2021.
  66. On the soundness of xai in prognostics and health management (phm). Information, 14(5):256, 2023.
  67. Multi-modal machine learning for vehicle rating predictions using image, text, and parametric data. arXiv preprint arXiv:2305.15218, 2023.
  68. A novel methodology for health assessment in printed circuit boards. In PHM Society European Conference, volume 7, pages 556–562, 2022.
  69. A novel technique for multiple failure modes classification based on deep forest algorithm. Journal of Intelligent Manufacturing, pages 1–15, 2023.
  70. Prediction of production line status for printed circuit boards. In PHM Society European Conference, volume 7, pages 563–570, 2022.
  71. High-performance fault classification based on feature importance ranking-xgboost approach with feature selection of redundant sensor data. Current Chinese Science, 2(3):243–251, 2022.
  72. A novel transfer ensemble learning framework for remaining useful life prediction under multiple working conditions. IEEE Transactions on Instrumentation and Measurement, 2023.
  73. Dataset generation based on 1d-cae modeling for fault diagnostics in a spacecraft propulsion system. In PHM Society Asia-Pacific Conference, 2023.
  74. Big data opportunities: System health monitoring and management. IEEE Access, 7:68853–68867, 2019.
  75. A deep learning first approach to remaining useful lifetime prediction of filtration system with improved response to changing operational parameters using parameterized fully-connected layer. In PHM Society European Conference, volume 6, pages 9–9, 2021.
  76. Empower large language model to perform better on industrial domain-specific question answering. arXiv preprint arXiv:2305.11541, 2023.
  77. Remaining useful life prediction for ion etching machine cooling system using deep recurrent neural network-based approaches. Control Engineering Practice, 109:104748, 2021.
  78. Fatigue crack length estimation and prediction using trans-fitting with support vector regression. International Journal of Prognostics and Health Management, 11(1), 2020.
  79. Deep learning-based remaining useful life prediction method with transformer module and random forest. Mathematics, 10(16):2921, 2022.
  80. A survey of large language models. arXiv preprint arXiv:2303.18223, 2023.
  81. Cross-modal knowledge distillation for fault detection under multiple failure modes. In 2021 China Automation Congress (CAC), pages 7714–7719. IEEE, 2021.
  82. E. Zio. Prognostics and health management (phm): Where are we and where do we (need to) go in theory and practice. Reliability Engineering & System Safety, 218:108119, 2022.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now