Abstract
With the increasing complexity of modern chemical production processes, chemical operating conditions have become more and more diversified, which has improved the production efficiency of chemical companies and increased the probability of chemical production failures. With the expansion of the chemical industry’s scale of development, traditional manual diagnosis methods have been difficult to detect complex fault information. Therefore, the introduction of modern technology has become the key to chemical fault diagnosis. This paper studies chemical fault diagnosis based on machine learning, uses SVM classifier to perform chemical fault diagnosis, and then optimizes the parameters of SVM classifier through three methods of GS, GA and PSO machine learning algorithms. It is found that the diagnosis accuracy rate after GS algorithm optimization is 99.1273%, GA algorithm optimized diagnosis accuracy rate was 99.3548%, PSO algorithm optimized diagnosis accuracy rate was 99.0626%, but from the perspective of fault diagnosis running time, GS algorithm optimization running time is shorter, so GS algorithm is used to optimize SVM classification the parameters of the device more effectively improve the efficiency of diagnosis.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Liang, X., He, H., Zhang, Y.: Optimization design of micro-piles in landslide safety protection based on machine learning. Saf. Sci. 118(1), 861–867 (2019)
Han, Y., Zeng, Q., Geng, Z., et al.: Energy management and optimization modeling based on a novel fuzzy extreme learning machine: case study of complex petrochemical industries. Energy Convers. Manage. 165, 163–171 (2018)
Anna, H.R.S., Tavares, F.W., et al.: Machine learning model and optimization of a PSA unit for methane-nitrogen separation. Comput. Chem. Eng. 104, 377–391 (2017)
Zheng, L., Xiang, Y., Sheng, C.: Optimization-based improved kernel extreme learning machine for rolling bearing fault diagnosis. J. Braz. Soc. Mech. Sci. Eng. 41(11), 1–14 (2019)
Ku, J., Kamath, A., Carrington, T., Manzhos, S.: Machine learning optimization of the collocation point set for solving the Kohn-Sham equation. J. Phys. Chem. A 123(49), 10631–10642 (2019)
Wang, N., Li, H., Wu, F., et al.: Fault diagnosis of complex chemical processes using feature fusion of a convolutional network. Ind. Eng. Chem. Res. 60(5), 2232–2248 (2021)
Jiang, X., Zhao, H., Leung, H.: Fault detection and diagnosis in chemical processes using sparse principal component selection. J. Chem. Eng. Jpn. 50(1), 31–44 (2017)
Wu, H., Zhao, J.: Deep convolutional neural network model based chemical process fault diagnosis. Comput. Chem. Eng. 115, 185–197 (2018)
Yang, G., Gu, X.: Fault diagnosis of complex chemical processes based on enhanced Naive Bayesian method. IEEE Trans. Instrum. Meas. 69(7), 4649–4658 (2020)
Liang, M., Zhao, J.: Feature selection for chemical process fault diagnosis by artificial immune systems. Chin. J. Chem. Eng. 26(08), 7–12 (2018)
Wu, H., Zhao, J.: Fault detection and diagnosis based on transfer learning for multimode chemical processes. Comput. Chem. Eng. 135, 106731.1–106731.13 (2020)
Kim, C., Lee, H., Lee, W.B.: Process fault diagnosis via the integrated use of graphical lasso and Markov random fields learning & inference. Comput. Chem. Eng. 125, 460–475 (2019)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zong, H. (2022). Chemical Fault Diagnosis Modeling Optimization Based on Machine Learning. In: Tian, Y., Ma, T., Khan, M.K., Sheng, V.S., Pan, Z. (eds) Big Data and Security. ICBDS 2021. Communications in Computer and Information Science, vol 1563. Springer, Singapore. https://doi.org/10.1007/978-981-19-0852-1_57
Download citation
DOI: https://doi.org/10.1007/978-981-19-0852-1_57
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-0851-4
Online ISBN: 978-981-19-0852-1
eBook Packages: Computer ScienceComputer Science (R0)