Sensor signals acquired in industrial equipment contain rich information which can be analyzed to facilitate effective monitoring of equipment, early detection of system anomalies, quick diagnosis of fault root causes, and intelligent system design and control. In many mechatronic systems, multiple signals are acquired by different sensor channels (i.e., multi-channel data) which can be represented by high-order arrays (tensorial data). The multi-channel data has a high-dimensional and complex cross-correlation structure. It is crucial to develop a method that considers the interrelationships between different sensor channels. This paper proposes a new equipment monitoring approach based on uncorrelated multilinear discriminant analysis that can effectively model the multi-channel data to achieve a superior monitoring and fault diagnosis performance compared to other competing methods. The proposed method is applied directly to the high-dimensional tensorial data. Features are extracted and combined with multivariate control charts to achieve real-time fault detection of equipment. The effectiveness of the proposed method in quick detection of equipment faults is demonstrated with both the simulation and a real-world case study.
This is a preview of subscription content, access via your institution.
Buy single article
Instant access to the full article PDF.
Tax calculation will be finalised during checkout.
Hannan E (1961) The general theory of canonical correlation and its relation to functional analysis. J Aust Math Soc 2:229–242
Leurgans SE, Moyeed RA, and Silverman BW (1993) “Canonical correlation analysis when the data are curves,” Journal of the Royal Statistical Society. Series B (Methodological),725–740
Dubin JA, Müller H-G (2005) Dynamical correlation for multivariate longitudinal data. J Am Stat Assoc 100:872–881
Yang W, Müller H-G, Stadtmüller U (2011) Functional singular component analysis. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 73:303–324
Grasso M, Colosimo BM, Pacella M (2014) Profile monitoring via sensor fusion: the use of PCA methods for multi-channel data. Int J Prod Res 52(20):6110–6135. https://doi.org/10.1080/00207543.2014.916431
Di C-Z, Crainiceanu CM, Caffo BS, Punjabi NM (2009) Multilevel functional principal component analysis. Ann Appl Stat 3:458–488
Chiou J-M, Chen Y-T, Yang Y-F (2014) Multivariate functional principal component analysis: a normalization approach. Stat Sin 1571–1596
Paynabar K, Zou C, Qiu P (2016) A change-point approach for phase-I analysis in multivariate profile monitoring and diagnosis. Technometrics 58:191–204
Chiou J-M, Müller H-G (2014) Linear manifold modelling of multivariate functional data. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 76:605–626
Zhang C, Yan H, Lee S, Shi J (2018) Multiple profiles sensor-based monitoring and anomaly detection. J Qual Technol 50(4):344–362
Qiao X, James G, and Lv J (2015) “Functional graphical models,” Tech Rep, Technical report, University of Southern California
Paynabar K, Jin J, Pacella M (2013) Monitoring and diagnosis of multichannel nonlinear profile variations using uncorrelated multilinear principal component analysis. IIE Trans 45(11):1235–1247. https://doi.org/10.1080/0740817x.2013.770187
Zhu H, Strawn N, Dunson DB (2016) Bayesian graphical models for multivariate functional data. J Mach Learn Res 17:1–27
Wei Q, Huang W, Jiang W, Zhao W (2016) Real-time process monitoring using kernel distances. Int J Prod Res 54(21):6563–6578. https://doi.org/10.1080/00207543.2016.1173257
Amdouni A, Castagliola P, Taleb H, Celano G (2017) A variable sampling interval Shewhart control chart for monitoring the coefficient of variation in short production runs. Int J Prod Res 55(19):5521–5536. https://doi.org/10.1080/00207543.2017.1285076
Ye F, Zhang ZS, Xia Z, Zhou YF, Zhang H (2019) Monitoring and diagnosis of multi-channel profile data based on uncorrelated multilinear discriminant analysis. Int J Adv Manuf Technol 103(9–12):4659–4669
Paynabar K, Jin J, Agapiou J, Deeds P (2012) Robust leak tests for transmission systems using nonlinear mixed-effect models. J Qual Technol 44(3):265–278
Grasso M, Colosimo BM, Tsung F (2017) A phase I multi-modelling approach for profile monitoring of signal data. Int J Prod Res 55(15):4354–4377. https://doi.org/10.1080/00207543.2016.1251626
Lei Y, Zhang Z, Jin J (2010) Automatic tonnage monitoring for missing part detection in multi-operation forging processes. Journal of Manufacturing Science and Engineering-Transactions of the Asme 132(5). https://doi.org/10.1115/1.4002531
Bhattacharyya P, Sengupta D (2009) Estimation of tool wear based on adaptive sensor fusion of force and power in face milling. Int J Prod Res 47(3):817–833. https://doi.org/10.1080/00207540701403376
Yang W-A, Zhou Q, Tsui K-L (2016) Differential evolution-based feature selection and parameter optimisation for extreme learning machine in tool wear estimation. Int J Prod Res 54(15):4703–4721. https://doi.org/10.1080/00207543.2015.1111534
Donoho DL, Johnstone IM (1994) Ideal spatial adaptation by wavelet shrinkage. Biometrika 81(3):425–455. https://doi.org/10.1093/biomet/81.3.425
Fan Z, Cai M, Wang H (2012) An improved denoising algorithm based on wavelet transform modulus maxima for non-intrusive measurement signals. Meas Sci Technol 23(4):045007. https://doi.org/10.1088/0957-0233/23/4/045007
Guo W, Jin J, Hu SJ, Asme (2016) Profile monitoring and fault diagnosis via sensor fusion for ultrasonic welding. Proceedings of the Asme 11th International Manufacturing Science and Engineering Conference, 2016, Vol 2
This work was supported by the National Natural Science Foundation of China (NSFC) under Grant No.51775108.
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Xia, Z., Ye, F., Dai, M. et al. Real-time fault detection and process control based on multi-channel sensor data fusion. Int J Adv Manuf Technol 115, 795–806 (2021). https://doi.org/10.1007/s00170-020-06168-y
- Feature extraction
- Process monitoring and control
- Sensor fusion
- Fault detection and diagnosis
- Tensor decomposition