Abstract
Aiming to solve the problems of the inaccurate dimension reduction of high-dimensional data and insufficient information utilization in traditional manufacturing process monitoring methods—in which mostly only the distance information of pairwise points is used as the similarity index for the data dimension reduction—this paper proposes a data-manifold-based monitoring method that combines the distance information and angle information of pairwise points. First, the intrinsic dimension of manufacturing process data is estimated by combining multiple geometric features on the data manifold. Second, considering the angle information and distance information in the neighborhood of process data, the method to construct local features of the data manifold is given; further, a fusion method of local features and global–local features of manifold data based on the eigendimension is proposed, which constructs the data dimension-reduction mapping matrix to improve the integrity of data information extraction. Then, the data index of process monitoring is given and employed to monitor the manufacturing process. Finally, Tennessee Eastman (TE) process simulation data were used to verify the effectiveness of the proposed method. The results show that compared with other methods, the anomaly detection rate of the proposed method was increased by more than 50%, while the false alarm rate was decreased by 21.4%, which proves that the method can significantly improve the efficiency of manufacturing process anomaly monitoring.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Cai, B., Liu, Y., Fan, Q., Zhang Y., Liu, Z., Yu, S., & Ji, R. (2014). Multi-source information fusion based fault diagnosis of ground-source heat pump using Bayesian network. Applied Energy, 114(2), 1–9. https://doi.org/10.1016/j.apenergy.2013.09.043
Costa, J., & Hero, A. (2003). Manifold learning with geodesic minimal spanning trees. Eprint Arxiv Cs.
Cui, P., Wang, X., & Yang, Y. (2020). Statistics manifold learning approach and its application to non-Gaussian process monitoring. In 39th Chinese control conference (CCC) (pp. 4054–4059). https://doi.org/10.23919/CCC50068.2020.9189523
Cui, P., Wang, X., & Yang, Y. (2022). Nonparametric manifold learning approach for improved process monitoring. Canadian Journal of Chemical Engineering, 100(1), 67–89. https://doi.org/10.1002/cjce.24066
Del Castillo, E., & Zhao, X. (2020). Industrial statistics and manifold data. Quality Engineering, 32(2), 155–167.
Deng, X., & Tian, X. (2013). Nonlinear process fault pattern recognition using statistics kernel PCA similarity factor. Neurocomputing, 121(9), 298–308. https://doi.org/10.1016/j.neucom.2013.04.042
Gao, Z., Jia, M., Mao, Z., & Zhao, L. (2019). Transitional phase modeling and monitoring with respect to the effect of its neighboring phases. Chemical Engineering Research and Design, 145, 288–299. https://doi.org/10.1016/j.cherd.2019.03.023
Grassberger, P., & Procaccia, I. (1983). Characterization of strange attractors. Physical Review Letters, 50(5), 346. https://doi.org/10.1103/PhysRevLett.50.346
Gu, X., Li, Y., & Jia, J. (2015). Feature selection for transient stability assessment based on kernelized fuzzy rough sets and memetic algorithm. International Journal of Electrical Power and Energy Systems, 64, 664–670. https://doi.org/10.1016/j.ijepes.2014.07.070
He, J., Ding, L., Jiang, L., Li, Z., & Hu, Q. (2014). Intrinsic dimensionality estimation based on manifold assumption. Journal of Visual Communication and Image Representation, 25(5), 740–747. https://doi.org/10.1016/j.jvcir.2014.01.006
Himes, D., Storer, R., & Georgakis, C. (1994). Determination of the number of principal components for disturbance detection and isolation. In American control conference (Vol. 2, pp. 1279–1283). IEEE. https://doi.org/10.1109/ACC.1994.752265
Horn, J. (1965). A rationale and test for the number of factors in factor analysis. Psychometrica, 30, 73–77. https://doi.org/10.1007/BF02289447
Huang, K., Wu, Y., Long, C., Ji, H., Sun, B., Chen, X., & Yang, C. (2021). Adaptive process monitoring via online dictionary learning and its industrial application. ISA Transactions, 114, 399–412. https://doi.org/10.1016/j.isatra.2020.12.046
Ismail, M., Mostafa, N. A., & El-Assal, A. (2021). Quality monitoring in multistage manufacturing systems by using machine learning techniques. Journal of Intelligent Manufacturing. https://doi.org/10.1007/s10845-021-01792-1
Jin, M., Ren, L., Xu, Z., & Zhao, X. (2014). Reliable fault diagnosis method using ensemble fuzzy ARTMAP based on improved Bayesian belief method. Neurocomputing, 133(6), 309–316. https://doi.org/10.1016/j.neucom.2013.11.005
Lee, W. J., Mendis, G. P., Triebe, M. J., & Sutherland, J. W. (2020). Monitoring of a machining process using kernel principal component analysis and kernel density estimation. Journal of Intelligent Manufacturing, 31(5), 1175–1189. https://doi.org/10.1007/s10845-019-01504-w
Liao, Y. B., Ihab, R., Huang, Z. Y., & Scott, K. (2021). Manufacturing process monitoring using time-frequency representation and transfer learning of deep neural networks. Journal of Manufacturing Processes, 68, 231–248. https://doi.org/10.1016/j.jmapro.2021.05.046
Liu, J., Wang, J., Liu, X., Ma, T., & Tang, Z. (2021). MWRSPCA: Online fault monitoring based on moving window recursive sparse principal component analysis. Journal of Intelligent Manufacturing. https://doi.org/10.1007/s10845-020-01721-8
Luo, L. (2014). Process monitoring with global–local preserving projections. Industrial and Engineering Chemistry Research, 53(18), 7696–7705. https://doi.org/10.1021/ie4039345
Ma, Y. (2014). Study on feature extraction methods for fault detection of industrial process. South China University of Technology.
Ma, Y., Song, B., Shi, H., & Yang, Y. (2015). Fault detection via local and nonlocal embedding. Chemical Engineering Research and Design, 94, 538–548. https://doi.org/10.1016/j.cherd.2014.09.015
Qin, S. (2003). Statistical process monitoring: Basics and beyond. Journal of Chemometrics, 17(8–9), 480–502. https://doi.org/10.1002/cem.800
Qin, S., & Zheng, Y. (2013). Quality-relevant and process-relevant fault monitoring with concurrent projection to latent structures. AIChE Journal, 59(2), 496–504. https://doi.org/10.1002/aic.13959
Raginsky, M., & Lazebnik, S. (2006). Estimation of intrinsic dimensionality using high-rate vector quantization. In NIPS 2006 (Vol. 18, pp. 1105–1112).
Said, M., Abdellafou, K. B., & Taouali, O. (2020). Machine learning technique for data-driven fault detection of nonlinear processes. Journal of Intelligent Manufacturing, 31(4), 865–884. https://doi.org/10.1007/s10845-019-01483-y
Sarabi, A., Araabi, B., & Augustin, T. (2013). Information-based dissimilarity assessment in Dempster-Shafer theory. Knowledge-Based Systems, 2013(54), 114–127. https://doi.org/10.1016/j.knosys.2013.08.030
Seung, H. (2000). The manifold ways of perception. Science, 290(5500), 2268–2269.
Shu, W., & Shen, H. (2014). Incremental feature selection based on rough set in dynamic incomplete data. Pattern Recognition, 47(12), 3890–3906. https://doi.org/10.1016/j.patcog.2014.06.002
Sun, W., Zhao, R., Yan, R., Shao, S., & Chen, X. (2017). Convolutional discriminative feature learning for induction motor fault diagnosis. IEEE Transactions on Industrial Informatics, 13(3), 1350–1359. https://doi.org/10.1109/TII.2017.2672988
Sun, Y., Qin, W., Zhuang, Z., & Xu, H. (2021). An adaptive fault detection and root-cause analysis scheme for complex industrial processes using moving window KPCA and information geometric causal inference. Journal of Intelligent Manufacturing, 32, 2007–2021. https://doi.org/10.1007/s10845-021-01752-9
Sun, Yu., Zeng, Z., Long, B., Li, J., de Oliveira, J. V., & Li, C. (2019). A comparison of dimension reduction techniques for support vector machine modeling of multi-parameter manufacturing quality prediction. Journal of Intelligent Manufacturing, 30, 2245–2256. https://doi.org/10.1007/s10845-017-1388-1
Svante, W. (1978). Cross-validatory estimation of the number of components in factor and principal components models. Technometrics, 20(4), 397–405. https://doi.org/10.2307/1267639
Tong, C., Shi, X., & Lan, T. (2016). Statistical process monitoring based on orthogonal multi-manifold projections and a novel variable contribution analysis. ISA Transactions. https://doi.org/10.1016/j.isatra.2016.06.017
Vanini, Z., Khorasani, K., & Meskin, N. (2014). Fault detection and isolation of a dual spool gas turbine engine using dynamic neural networks and multiple model approach. Information Sciences, 259, 234–251. https://doi.org/10.1016/j.ins.2013.05.032
Wang, X., Liu, C., Bi, F., Bi, X., & Shao, K. (2013). Fault diagnosis of diesel engine based on adaptive wavelet packets and EEMD-fractal dimension. Mechanical Systems and Signal Processing, 41(1–2), 581–597. https://doi.org/10.1016/j.ymssp.2013.07.009
Xu, X., Ding, J., Liu, Q., & Chai, T. (2020). A novel multi-manifold joint projections model for multimode process monitoring. IEEE Transactions on Industrial Informatics. https://doi.org/10.1109/TII.2020.3036676
Yu, J. (2012). Local and global principal component analysis for process monitoring. Journal of Process Control, 22(7), 1358–1373. https://doi.org/10.1016/j.jprocont.2012.06.008
Yu, J. (2016). Process monitoring through manifold regularization-based GMM with global/local information. Journal of Process Control, 45, 84–99. https://doi.org/10.1016/j.jprocont.2016.07.006
Zhan, C., Li, S., & Yang, Y. (2019). Improved process monitoring based on global–local manifold analysis and statistical local approach for industrial process. Journal of Process Control, 75, 107–119. https://doi.org/10.1016/j.jprocont.2018.12.016
Zhang, M., Ge, Z., Song, Z., & Fu, R. (2011). Global–local structure analysis model and its application for fault detection and identification. Industrial & Engineering Chemistry Research, 50, 6837–6848. https://doi.org/10.1021/ie102564d
Zhang, M. G. (2011). Statistical process monitoring methods based on local–global structure analysis. Zhejiang University.
Acknowledgements
This research was supported by the National Science Fund of China (Grant No. 51805502) and the State Department project of China (Grant No. JCKY2017208A001). The authors gratefully acknowledge the facilities provided by the Industrial and Intelligent System Engineering Laboratory (IISEL) at the Beijing Institute of Technology.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhang, F., Zhang, J. & Ma, J. Data-manifold-based monitoring and anomaly diagnosis for manufacturing process. J Intell Manuf 34, 3159–3177 (2023). https://doi.org/10.1007/s10845-022-01978-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10845-022-01978-1