[go: up one dir, main page]
Skip to main content

Advertisement

Springer Nature Link
Log in

An integrated framework for diagnosing process faults with incomplete features

  • Regular Paper
  • Published:
Knowledge and Information Systems Aims and scope Submit manuscript

Abstract

Handling missing values and large-dimensional features are crucial requirements for data-driven fault diagnosis systems. However, most intelligent data-driven diagnostic systems are not able to handle missing data. The presence of high-dimensional feature sets can also further complicate the process of fault diagnosis. This paper aims to devise a missing data imputation unit along with a dimensionality reduction unit in the pre-processing module of the diagnostic system. This paper proposes a novel pooling strategy for missing data imputation (PSMI). This strategy can simplify complex patterns of missingness and incrementally update the pool. The pre-processing module receives incomplete observations, PSMI estimates missing values, and, then, the dimensionality reduction unit transforms completed observations onto a lower-dimensional feature space. These transformed observations are then fed as inputs to the fault classification module for decision making and diagnosis. This diagnostic scheme makes use of various state-of-the-art missing data imputation, dimensionality reduction and classification algorithms. This enables a comprehensive comparison and allows to find the best techniques for the sake of diagnosing faults in the Tennessee Eastman process. The obtained results show the effectiveness of the proposed pooling strategy and indicate that principal component analysis imputation and heteroscedastic discriminant analysis approaches outperform other imputation and dimensionality reduction techniques in this diagnostic application.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Altman N (1992) An introduction to kernel and nearest-neighbor nonparametric regression. Am Stat 46(3):175–185

    MathSciNet  Google Scholar 

  2. Atouni M, Verron S, Kobi A (2015) Fault detection with conditional Gaussian network. Eng Appl Artif Intell 45:473–481

    Article  Google Scholar 

  3. Batista G, Monard M (2002) A study of k-nearest neighbour as an imputation method. HIS 87:251–260

    Google Scholar 

  4. Bellman RE (1961) Adaptive control processes. Princeton University Press, Princeton

    Book  Google Scholar 

  5. Cao W, Haralick R (2009) Affine feature extraction: a generalization of the fukunaga–koontz transformation. Eng Appl Artif Intell 22(1):40–47

    Article  Google Scholar 

  6. Downs J, Vogel E (1993) A plant-wide industrial process control problem. Comput Chem Eng 17(2):245–255

    Article  Google Scholar 

  7. Farajzadeh-Zanjani M, Hallaji E, Razavi-Far R, Saif M (2021) Generative-adversarial class-imbalance learning for classifying cyber-attacks and faults—a cyber-physical power system. IEEE Trans Dependable Secure Comput. https://doi.org/10.1109/TDSC.2021.3118636

    Article  Google Scholar 

  8. Farajzadeh-Zanjani M, Hallaji E, Razavi-Far R, Saif M (2021) Generative adversarial dimensionality reduction for diagnosing faults and attacks in cyber-physical systems. Neurocomputing 440:101–110

    Article  Google Scholar 

  9. Farajzadeh-Zanjani M, Hallaji E, Razavi-Far R, Saif M, Parvania M (2021) Adversarial semi-supervised learning for diagnosing faults and attacks in power grids. IEEE Trans Smart Grid 12(4):3468–3478

    Article  Google Scholar 

  10. Farajzadeh-Zanjani M, Razavi-Far R, Saif M (2016) Efficient sampling techniques for ensemble learning and diagnosing bearing defects under class imbalanced condition. In: 2016 IEEE symposium series on computational intelligence (SSCI). pp 1–7

  11. Fisher R (1936) The use of multiple measurements in taxonomic problems. Ann Eugen 7(2):179–188

    Article  Google Scholar 

  12. Folch-Fortuny A, Arteaga F, Ferrer A (2016) Missing data imputation toolbox for MATLAB. Chemom Intell Lab Syst 154:93–100

    Article  Google Scholar 

  13. Goldberger J, Roweis S, Hinton G, Salakhutdinov R (2004) Neighbourhood components analysis. In: Advances in neural information processing systems, vol 17. MIT Press, pp 513–520

  14. Grimble M, Johnson M (2005) Advanced textbooks in control and signal processing. Springer, Berlin

    Google Scholar 

  15. Hallaji E, Razavi-Far R, Saif M (2021) DLIN: Deep ladder imputation network. IEEE Trans Cybern. https://doi.org/10.1109/TCYB.2021.3054878

    Article  Google Scholar 

  16. Hancer E, Xue B, Zhang M, Karaboga D, Akay B (2018) Pareto front feature selection based on artificial bee colony optimization. Inf Sci 422:462–479

    Article  Google Scholar 

  17. Huang G (2014) An insight into extreme learning machines: random neurons, random features and kernels. Cogn Comput 6:376–390

    Article  Google Scholar 

  18. Jing C, Gao X, Zhu X, Lang S (2014) Fault classification on Tennessee Eastman process: PCA and SVM. In: 2014 International conference on mechatronics and control (ICMC)

  19. Josse J, Husson F (2013) Handling missing values in exploratory multivariate data analysis methods. J SFdS 153(2):79–99

    MathSciNet  MATH  Google Scholar 

  20. Kasun LLC, Yang Y, Huang GB, Zhang Z (2016) Dimension reduction with extreme learning machine. IEEE Trans Image Process 25(8):3906–3918

    Article  MathSciNet  Google Scholar 

  21. Loog M, Duin R (2004) Linear dimensionality reduction via a heteroscedastic extension of LDA: the Chernoff criterion. IEEE Trans Pattern Anal Mach Intell 26(6):732–739

    Article  Google Scholar 

  22. Monsef H, Ranjbar A, Jadid S (1997) Fuzzy rule-based expert system for power system fault diagnosis. IEE Proc Gener Transm Distrib 144(2):186–192

    Article  Google Scholar 

  23. Oliveira J, Pontes VK, Sartori I, Embirucu M (2017) Fault detection and diagnosis in dynamic systems using weightless neural networks. Expert Syst Appl 84:200–219

    Article  Google Scholar 

  24. Razavi-Far R, Chakrabarti S, Saif M, Zio E (2019) An integrated imputation–prediction scheme for prognostics of battery data with missing observations. Expert Syst Appl 115:709–723

    Article  Google Scholar 

  25. Razavi-Far R, Cheng B, Saif M, Ahmadi M (2020) Similarity-learning information-fusion schemes for missing data imputation. Knowl Based Syst 187:104805

    Article  Google Scholar 

  26. Razavi-Far R, Davilu H, Palade V, Lucas C (2009) Model-based fault detection and isolation of a steam generator using neuro-fuzzy networks. Neurocomputing 72(13):2939–2951

    Article  Google Scholar 

  27. Razavi-Far R, Farajzadeh-Zanajni M, Wang B, Saif M, Chakrabarti S (2021) Imputation-based ensemble techniques for class imbalance learning. IEEE Trans Knowl Data Eng 33(5):1988–2001

    Google Scholar 

  28. Razavi-Far R, Farajzadeh-Zanjani M, Saif M (2017) An integrated class-imbalanced learning scheme for diagnosing bearing defects in induction motors. IEEE Trans Ind Inform 13(6):2758–2769

    Article  Google Scholar 

  29. Razavi-Far R, Farajzadeh-Zanjani M, Saif M, Chakrabarti S (2020) Correlation clustering imputation for diagnosing attacks and faults with missing power grid data. IEEE Trans Smart Grid 11(2):1453–1464

    Article  Google Scholar 

  30. Razavi-Far R, Kinnaert M (2012) Incremental design of a decision system for residual evaluation: a wind turbine application*. In: IFAC proceedings. 8th IFAC symposium on fault detection, supervision and safety of technical processes, vol 45(20). pp 343–348

  31. Razavi-Far R, Palade V, Zio E (2014) Optimal detection of new classes of faults by an invasive weed optimization method. In: 2014 International joint conference on neural networks (IJCNN). pp 91–98

  32. Razavi-Far R, Zio E, Palade V (2014) Efficient residuals preprocessing for diagnosing multi-class faults in a doubly fed induction generator, under missing data scenarios. Expert Syst Appl 41(14):6386–6399

    Article  Google Scholar 

  33. Scheffer J (2002) Dealing with missing data. Res Lett Inf Math Sci 3:153–160

    Google Scholar 

  34. Sharma N, Saroha K (2015) Study of dimension reduction methodologies in data mining. In: International conference on computing, communication and automation (ICCCA2015)

  35. Sim J, Kwon O, Lee K (2016) Adaptive pairing of classifier and imputation methods based on the characteristics of missing values in data sets. Expert Syst Appl 46:486–493

    Article  Google Scholar 

  36. Wang G, Li J, Sun C, Jiao J (2018) Least squares and contribution plot based approach for quality-related process monitoring. IEEE Access 6:54158–54166

    Article  Google Scholar 

  37. Yang X, Rui S, Zhang X, Xu S, Yang C, Liu PX (2019) Fault diagnosis in chemical processes based on class-incremental FDA and PCA. IEEE Access 7:18164–18171

    Article  Google Scholar 

  38. Zhang S (2012) Nearest neighbor selection for iteratively KNN imputation. J Syst Softw 85(11):2541–2552

    Article  Google Scholar 

  39. Zhang Z, Dong F (2014) Fault detection and diagnosis for missing data systems with a three time-slice dynamic Bayesian network approach. Chemom Intell Lab Syst 138:30–40

    Article  Google Scholar 

  40. Zhu J, Ge Z, Song Z (2017) Distributed parallel PCA for modeling and monitoring of large-scale plant-wide processes with big data. IEEE Trans Ind Inform 13(4):1877–1885

    Article  Google Scholar 

  41. Zhu Y, Wang Z, Gao D, Li D (2017) GMFLLM: a general manifold framework unifying three classic models for dimensionality reduction. Eng Appl Artif Intell 65:421–432

    Article  Google Scholar 

  42. Zhu Z, Song ZH (2011) A novel fault diagnosis system using pattern classification on kernel FDA subspace. Expert Syst Appl 38:6895–6905

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering and School of Computer Science, University of Windsor, Windsor, ON, N9B 3P4, Canada

    Roozbeh Razavi-Far

  2. Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, N9B 3P4, Canada

    Mehrdad Saif & Shiladitya Chakrabarti

  3. Center for Data Science, Coventry University, Coventry, CV1 5FB, UK

    Vasile Palade

Authors
  1. Roozbeh Razavi-Far
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mehrdad Saif
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Vasile Palade
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shiladitya Chakrabarti
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Roozbeh Razavi-Far.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Razavi-Far, R., Saif, M., Palade, V. et al. An integrated framework for diagnosing process faults with incomplete features. Knowl Inf Syst 64, 75–93 (2022). https://doi.org/10.1007/s10115-021-01625-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10115-021-01625-w

Keywords