Skip to main content

Advertisement

SpringerLink
Log in

Energy inefficiency diagnosis in industrial process through one-class machine learning techniques

  • Published:
Journal of Intelligent Manufacturing Aims and scope Submit manuscript

Abstract

In the era of Industry 4.0, the ease of access to precise measurements in real-time and the existence of machine-learning (ML) techniques will play a vital role in building practical tools to isolate inefficiencies in energy-intensive processes. This paper aims at developing an abnormal event diagnosis (AED) tool based on ML techniques for monitoring the operation of industrial processes. This tool makes it easier for operators to accomplish their tasks and to make quick and accurate decisions to ensure highly efficient processes. One of the most popular ML techniques for AED is the multivariate statistical control (MSC) method; it only requires the dataset of the normal operating conditions (NOC) to detect and identify the variables that contribute to abnormal events (AEs). Despite the popularity of MSC, it is challenging to select the appropriate method for detecting and isolating all possible abnormalities a complex industrial process can experience. To address this limitation and improve efficiency, we have developed a generic methodology that integrates different ML techniques into a unified multiagent based approach, the selected ML techniques are supposed to be built using only the normal operating condition. For the sake of demonstration, we chose a combination of two ML methods: principal component analysis and k-nearest neighbors (k-NN). The k-NN was integrated into the proposed multiagent to take into account the nonlinearity and multimodality that frequently occur in industrial processes. In addition, we modified a k-NN method proposed in the literature to reduce computation time during real-time detection and isolation. Finally, the proposed methodology was successfully validated to monitor the energy efficiency of a reboiler located in a thermomechanical pulp mill.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

Abbreviations

ML:

Machine learning

AED:

Abnormal event diagnosis

MSC:

Multivariate statistical control

AE:

Abnormal event

PCA:

Principal component analysis

k-NN:

K-nearest neighbors

NOC:

Normal operating condition

CAM:

Contribution analysis method

AEDI:

Abnormal event detection and isolation

OCML:

One-class machine learning

UCL:

Upper control limit

AEDe:

Abnormal event detection

KDE:

Kernel density estimation

AEI:

Abnormal event isolation

VckNN:

Variable contribution by k-NN

SPE:

Squared prediction error

MkNN:

Modified kNN

References

  • Alauddin, M., Khan, F., Imtiaz, S., & Ahmed, S. (2018). A bibliometric review and analysis of data-driven fault detection and diagnosis methods for process systems. Industrial & Engineering Chemistry Research, 57(32), 10719–10735.

    Article  Google Scholar 

  • Alcala, C. F., & Qin, S. J. (2009). Unified analysis of diagnosis methods for process monitoring. In Proceedings of the 7th IFAC Symposium on fault detection, supervision and safety of technical processes Barcelona.

  • Alcala, C. F., & Qin, S. J. (2011). Analysis and generalization of fault diagnosis methods for process monitoring. Journal of Process Control, 21(3), 322–330.

    Article  Google Scholar 

  • Cecati, C. (2015). A survey of fault diagnosis and fault-tolerant techniques—Part II: Fault diagnosis with knowledge-based and hybrid/active approaches.

  • den Kerkhof, P., Vanlaer, J., Gins, G., & Van Impe, J. F. M. (2013). Analysis of smearing-out in contribution plot based fault isolation for statistical process control. Chemical Engineering Science, 104, 285–293.

    Article  Google Scholar 

  • Diana, G., & Tommasi, C. (2002). Cross-validation methods in principal component analysis: a comparison. Statistical Methods and Applications, pp. 71–82.

  • Durocher, D. B., & Higginson, M. (2017). Successful technology upgrade reduces thermo-mechanical pulp mill energy footprint. In 2017 Annual pulp, paper and forest industries technical conference (PPFIC), 2017 (pp. 1–9).

  • Fan, J., & Wang, Y. (2014). Fault detection and diagnosis of non-linear non-Gaussian dynamic processes using kernel dynamic independent component analysis. Information Sciences, 259, 369–379.

    Article  Google Scholar 

  • Gajjar, S., & Palazoglu, A. (2016). A data-driven multidimensional visualization technique for process fault detection and diagnosis. Chemometrics and Intelligent Laboratory Systems, 154, 122–136.

    Article  Google Scholar 

  • Ge, Z., & Song, Z. (2012). Multivariate statistical process control: Process monitoring methods and applications. Springer.

  • Grbovic, M., Li, W., Subrahmanya, N. A., Usadi, A. K., & Vucetic, S. (2013). Cold start approach for data-driven fault detection. IEEE Transactions on Industrial Informatics, 9(4), 2264–2273.

    Article  Google Scholar 

  • Gu, X. (2018). Self-organising transparent learning system. . Lancaster University.

    Google Scholar 

  • He, Q., & Wang, J. (2007). Fault detection using the k-nearest neighbor rule for semiconductor manufacturing processes. IEEE Transactions on Semiconductor Manufacturing, 20(4), 345–354.

    Article  Google Scholar 

  • Jaffel, I., Taouali, O., Harkat, M. F., & Messaoud, H. (2017). Kernel principal component analysis with reduced complexity for nonlinear dynamic process monitoring. The International Journal of Advanced Manufacturing Technology, 88(9–12), 3265–3279.

    Article  Google Scholar 

  • Li, G., Alcala, C. F., Qin, S. J., & Zhou, D. (2010). Generalized reconstruction-based contributions for output-relevant fault diagnosis with application to the Tennessee Eastman process. IEEE Transactions on Control Systems Technology, 19(5), 1114–1127.

    Article  Google Scholar 

  • Li, G., Qin, S. J., & Chai, T. (2014). Multi-directional reconstruction based contributions for root-cause diagnosis of dynamic processes. In Proceedings of the American control conference (pp. 3500–3505).

  • Li, G., Qin, S. J., & Yuan, T. (2016). Data-driven root cause diagnosis of faults in process industries. Chemometrics and Intelligent Laboratory Systems, 159, 1–11.

    Article  Google Scholar 

  • Liu, J. (2012). Fault diagnosis using contribution plots without smearing effect on non-faulty variables. Journal of Process Control, 22(9), 1609–1623.

    Article  Google Scholar 

  • Lu, C.-J. (2012). An independent component analysis-based disturbance separation scheme for statistical process monitoring. Journal of Intelligent Manufacturing, 23(3), 561–573.

    Article  Google Scholar 

  • Luo, J., Huang, J., & Li, H. (2020). A case study of conditional deep convolutional generative adversarial networks in machine fault diagnosis. Journal of Intelligent Manufacturing, pp. 1–19.

  • Mahadevan, S., & Shah, S. L. (2009). Plant wide fault identification using one-class support vector machines. IFAC Proceedings Volumes, 42(8), 1013–1018.

    Article  Google Scholar 

  • Ming, J., Zhao, J. (2017). Review on chemical process fault detection and diagnosis. In 2017 6th international symposium on advanced control of industrial processes (AdCONIP), 2017 (pp. 457–462).

  • O’Rielly, K., & Jeswiet, J. (2014). Strategies to improve industrial energy efficiency. Procedia Cirp, 15, 325–330.

    Article  Google Scholar 

  • Odiowei, P.-E.P., & Cao, Y. (2009). Nonlinear dynamic process monitoring using canonical variate analysis and kernel density estimations. IEEE Transactions on Industrial Informatics, 6(1), 36–45.

    Article  Google Scholar 

  • Peng, L., Zeng, X., Wang, Y., & Hong, G.-B. (2015). Analysis of energy efficiency and carbon dioxide reduction in the Chinese pulp and paper industry. Energy Policy, 80, 65–75.

    Article  Google Scholar 

  • Qin, S. J. (2014). Process data analytics in the era of big data. American Institute of Chemical Engineers Journal, pp. 1–15.

  • Ragab, A., El-Koujok, M., Poulin, B., Amazouz, M., & Yacout, S. (2018a). Fault diagnosis in industrial chemical processes using interpretable patterns based on logical analysis of data. Expert Systems with Applications, 95, 368–383.

    Article  Google Scholar 

  • Ragab, A., El-Koujok, M., Poulin, B., Amazouz, M., & Yacout, S. (2018b). Fault diagnosis in industrial chemical processes using interpretable patterns based on logical analysis of data authors. Expert Systems With Applications, 95, 368–383.

    Article  Google Scholar 

  • Rongyu, L., & Gang, R. (2006). Fault isolation by partial dynamic principal component analysis in dynamic process. Chinese Journal of Chemical Engineering, 14(4), 486–493.

    Article  Google Scholar 

  • Said, M., ben Abdellafou, K., & Taouali, O. (2019). Machine learning technique for data-driven fault detection of nonlinear processes. Journal of Intelligent Manufacturing (pp. 1–20).

  • Samuel, R. T., & Cao, Y. (2014).Fault detection in a multivariate process based on kernel PCA and kernel density estimation. In 2014 20th international conference on automation and computing, 2014 (pp. 146–151).

  • Samuel, R. T., & Cao, Y. (2015). Kernel canonical variate analysis for nonlinear dynamic process monitoring. In 9th international symposium on advanced control of chemical processes, vol. 48, no. 8 (pp. 605–610).

  • Samuel, R. T., & Cao, Y. (2016). Nonlinear process fault detection and identification using kernel PCA and kernel density estimation. Systems Science & Control Engineering, 4(1), 165–174.

    Article  Google Scholar 

  • Tao, H., Wang, P., Chen, Y., Stojanovic, V., & Yang, H. (2020). An unsupervised fault diagnosis method for rolling bearing using STFT and generative neural networks. Journal of the Franklin Institute.

  • van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-SNE. Journal of Machine Learning Research, 9, 2579–2605.

    Google Scholar 

  • Venkatasubramanian, V. (2003). Abnormal events management in complex process plants: Challenges and opportunities in intelligent supervisory control. In Proceedings FOCAPO, 2003 (p. 117ff).

  • Venkatasubramanian, V., Rengaswamy, R., & Kavuri, S. N. (2003b). A review of process fault detection and diagnosis: Part II: Qualitative models and search strategies. Computers & Chemical Engineering, 27(3), 313–326.

    Article  Google Scholar 

  • Venkatasubramanian, V., Rengaswamy, R., Kavuri, S. N., & Yin, K. (2003a). A review of process fault detection and diagnosis: Part III: Process history based methods. Computers & Chemical Engineering, 27(3), 327–346.

    Article  Google Scholar 

  • Wang, G., Zhang, F., Cheng, B., & Fang, F. (2020). DAMER: A novel diagnosis aggregation method with evidential reasoning rule for bearing fault diagnosis. Journal of Intelligent Manufacturing, pp. 1–20.

  • Wu, X. et al. (2008). Top 10 algorithms in data mining, vol. 14, no. 1.

  • Yang, J., Sun, Z., & Chen, Y. (2016). Fault detection using the clustering-kNN rule for gas sensor arrays. Sensors, 16(12), 2069.

    Article  Google Scholar 

  • Yin, S., Ding, S. X., Xie, X., & Luo, H. (2014). A review on basic data-driven approaches for industrial process monitoring. IEEE Transactions on Industrial Electronics, 61(11), 6418–6428.

    Article  Google Scholar 

  • Zhao, X., & Xue, Y. (2014). Output-relevant fault detection and identification of chemical process based on hybrid kernel T-PLS. Canadian Journal of Chemical Engineering, 92(10), 1822–1828.

    Article  Google Scholar 

  • Zhou, L., Chen, J., Song, Z., & Ge, Z. (2015). Semi-supervised PLVR models for process monitoring with unequal sample sizes of process variables and quality variables. Journal of Process Control, 26, 1–16.

    Article  Google Scholar 

  • Zhou, Z., Wen, C., & Yang, C. (2016). Fault isolation based on k-nearest neighbor rule for industrial processes. IEEE Transactions on Industrial Electronics, 63(4), 2578–2586.

    Google Scholar 

Download references

Acknowledgements

The authors wish to thank the Program of Energy Research and Development (PERD) of Natural Resources Canada for its financial support.

Author information

Authors and Affiliations

  1. CanmetENERGY-Natural Resources Canada, 1615 Boulevard Lionel-Boulet, Varennes, QC, J3X 1P7, Canada

    Mohamed El Koujok, Hakim Ghezzaz & Mouloud Amazouz

Authors
  1. Mohamed El Koujok
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hakim Ghezzaz
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mouloud Amazouz
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mohamed El Koujok.

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

El Koujok, M., Ghezzaz, H. & Amazouz, M. Energy inefficiency diagnosis in industrial process through one-class machine learning techniques. J Intell Manuf 32, 2043–2060 (2021). https://doi.org/10.1007/s10845-021-01762-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10845-021-01762-7

Keywords

Search

Navigation