CCDNN: A Novel Deep Learning Architecture for Multi-Source Data Fusion

Zhiwen Chen; Siwen Mo; Haobin Ke; Steven X. Ding; Zhaohui Jiang; Chunhua Yang; Weihua Gui

doi:10.1109/JAS.2025.125411

IEEE/CAA Journal of Automatica Sinica

JCR Impact Factor: 19.2, Top 1 (SCI Q1)

CiteScore: 28.2, Top 1% (Q1)
Google Scholar h5-index: 95， TOP 5

Turn off MathJax

Article Contents

Article Navigation > IEEE/CAA Journal of Automatica Sinica > 2026 > In Press, Accepted Manuscript

Z. Chen, S. Mo, H. Ke, S. Ding, Z. Jiang, C. Yang, and W. Gui, “CCDNN: A novel deep learning architecture for multi-source data fusion,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 3, pp. 1–13, Mar. 2026. doi: 10.1109/JAS.2025.125411

Citation:

Z. Chen, S. Mo, H. Ke, S. Ding, Z. Jiang, C. Yang, and W. Gui, “CCDNN: A novel deep learning architecture for multi-source data fusion,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 3, pp. 1–13, Mar. 2026. doi: 10.1109/JAS.2025.125411

Citation:

PDF( 0 KB)

CCDNN: A Novel Deep Learning Architecture for Multi-Source Data Fusion

doi: 10.1109/JAS.2025.125411

Funds: This work was supported in part by National Natural Science Foundation of China (62173349), the Science and Technology Innovation Program of Hunan Province (2022RC1090), Natural Science Foundation of Hunan Province (2022JJ20076)

More Information

Author Bio:
Zhiwen Chen (Member, IEEE) received the B.S. degree in electronic information science and technology and the M.S. degree in electronic information and technology from Central South University, China, in 2008 and 2012, respectively, the Ph.D. degree in electrical engineering and information technology from the University of Duisburg-Essen, Germany, in 2016. He is currently a Professor at Central South University. His research interests are model-based and data-driven fault diagnosis and health monitoring, data analytics

Siwen Mo (Student Member, IEEE) received the B.S. degree from the University of Science and Technology Beijing in 2022. Currently, he is a master student degree at the School of Automation, Central South University, under the supervision of Professor Zhiwen Chen. His research interests include fault diagnosis, knowledge graph, and machine learning

Haobin Ke (Student Member, IEEE) received the M.S. degree in control science and engineering from Central South University in 2024. He is currently a Ph.D. degree candidate with the Department of Electrical and Electronic Engineering, Hong Kong Polytechnic University HangKong, China. His research interest include data privacy, graph learning, and machine learning

Steven X. Ding received the Ph.D. degree in electrical engineering from the Gerhard-Mercator University of Duisburg, Germany, in 1992. From 1992 to 1994, he was a Research and Development Engineer at Rheinmetall GmbH, Germany. From 1995 to 2001, he was a Professor of control engineering at the University of Applied Science Lausitz, Germany, where he was the Vice President from 1998 to 2000. He is currently a Full Professor of control engineering and the Head of the Institute for Automatic Control and Complex Systems (AKS), University of Duisburg-Essen, Germany.His research interests are model-based and data-driven fault diagnosis, fault-tolerant systems, real-time control, and their application in industry with a focus on automotive systems and chemical processes

Zhaohui Jiang received the M.E. degree in automatic control engineering and the Ph.D. degree in control science and engineering from Central South University, in 2006 and 2011, respectively. He is currently a Professor at Central South University. His research interests include detection technology and automatic equipment, image processing, industrial virtual reality, modeling, and optimal control of complex industrial processes

Chunhua Yang (Fellow, IEEE) received the M.E. degree in automatic control engineering and the Ph.D. degree in control science and engineering from Central South University, in 1988 and 2002, respectively. She was a Visiting Professor with the Department of Electrical Engineering, Katholieke Universiteit Leuven, Belgium, from 1999 to 2001. She is currently a Full Professor with the School of Automation, Central South University. Her current research interests include model-based and data-driven fault diagnosis, modeling and optimal control of complex industrial processes, intelligent control systems, and fault-tolerant control of real-time systems

Weihua Gui received the B.E. degree in electrical engineering and the M.E. degree in automatic control engineering from Central South University, in 1976 and 1981, respectively. From 1986 to 1988, he was a Visiting Scholar with the University of Duisburg-Essen, Germany. Since 1991, he has been a Full Professor with Central South University. His research interests include modeling and optimal control of complex industrial processes, distributed robust control, and fault diagnoses
Corresponding author: Zhiwen Chen, e-mail: zhiwen.chen@csu.edu.cn
¹ https://github.com/CSU-IILab
Received Date: 2025-01-23
Revised Date: 2025-03-01
Accepted Date: 2025-03-05

Available Online: 2026-02-12

Abstract

Abstract

With the rapid development of Industrial 4.0 and Industrial Internet of Things, the data collection with multi-source has significantly improved. How to effectively fuse these data for various engineering applications is still an open and challenge issue. To this end, we propose the canonical correlation guided deep neural network (CCDNN), a novel deep learning architecture, to learn a correlated representation for multi-source data fusion. Unlike the linear canonical correlation analysis (CCA), kernel CCA and deep CCA, in the proposed method, the optimization formulation is not restricted to maximize correlation, instead we make canonical correlation as a constraint, which preserves the correlated representation learning ability and focuses more on the engineering tasks endowed by optimization formulation, such as reconstruction, classification and prediction. Furthermore, to reduce the redundancy induced by correlation, a redundancy filter is designed. We illustrate its data fusion ability via correlated representation learning and superior performance on various engineering tasks. In experiments on MNIST dataset, the results show that CCDNN has better reconstruction performance in terms of mean squared error and mean absolute error than DCCA and DCCAE. Also, we present the application of the proposed network to industrial fault diagnosis and remaining useful life cases for the classification and prediction tasks accordingly. The proposed method demonstrates approving performance in both tasks when compared to existing methods. Extension of CCDNN to much more deeper with the aid of residual connection is also presented in appendix.
- Canonical correlation analysis (CCA),
- correlated representation learning,
- deep learning,
- fault diagnosis,
- multi-source data fusion,
- remaining useful life

FullText(HTML)

¹ https://github.com/CSU-IILab

References(43)

References

[1]	H. Hotelling, “Relations between two sets of variates,” Biometrika, vol. 28, no. 3–4, pp. 321–377, 1936. doi: 10.1093/biomet/28.3-4.321
[2]	T. Anderson, An Introduction to Multivariate Statistical Analysis, 2nd ed. New York, USA: John Wiley and Sons, LTD, 1984.
[3]	C. NM, A. T, L. YO, and C. VD, “Canonical correlation analysis for data fusion and group inferences: Examining applications of medical imaging data,” IEEE Signal Process Mag, vol. 27, no. 4, pp. 39–50, 2010. doi: 10.1109/MSP.2010.936725
[4]	Y. Bengio, A. Courville, and P. Vincent, “Representation learning: A review and new perspectives,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 35, no. 8, pp. 1798–1828, 2013. doi: 10.1109/TPAMI.2013.50
[5]	L. A. Passos, J. P. Papa, J. Del Ser, A. Hussain, and A. Adeel, “Multimodal audio-visual information fusion using canonical-correlated graph neural network for energy-efficient speech enhancement,” Information Fusion, vol. 90, pp. 1–11, 2023. doi: 10.1016/j.inffus.2022.09.006
[6]	B. Scholkopf and A. J. Smola, Learning With Kernels Cambridge, USA. MIT Press, 2002.
[7]	S. Akaho, “A kernel method for canonical correlation analysis,” arXiv preprint arXiv cs/0609071, 2006.
[8]	K. Fukumizu, F. R. Bach, and A. Gretton, “Statistical consistency of kernel canonical correlation analysis,” J. Machine Learning Research, vol. 8, pp. 361–383, 2007.
[9]	X. Li, S. Yu, Y. Lei, N. Li, and B. Yang, “Dynamic vision-based machinery fault diagnosis with cross-modality feature alignment,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 10, pp. 2068–2081, 2024. doi: 10.1109/JAS.2024.124470
[10]	J. Zhang, L. Pan, Q.-L. Han, C. Chen, S. Wen, and Y. Xiang, “Deep learning based attack detection for cyber-physical system cybersecurity: A survey,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 3, pp. 377–391, 2021.
[11]	A. J. Moshayedi, A. S. Khan, S. Yang, and S. M. Zanjani, “Personal image classifier based handy pipe defect recognizer (HPD): Design and test,” in Proc. 7th Int. Conf. Intelligent Computing and Signal Processing, 2022, pp. 1721–1728.
[12]	Z. Li, S. Li, and X. Luo, “An overview of calibration technology of industrial robots,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 1, pp. 23–36, 2021. doi: 10.1109/JAS.2020.1003381
[13]	G. Andrew, R. Arora, J. Bilmes, and K. Livescu, “Deep canonical correlation analysis,” in Proc. 30th Int. Conf. Machine Learning, 2013, vol. 28, no. 3. pp. 1247–1255.
[14]	H. Asoh and O. Takechi, “An approximation of nonlinear canonical correlation analysis by multilayer perceptrons,” in Proc. Int. Conf. Artificial Neural Networks, 1994, pp. 713–716.
[15]	X. Yuan, W. Xu, Y. Wang, C. Yang, and W. Gui, “A deep residual pls for data-driven quality prediction modeling in industrial process,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 8, pp. 1777–1785, 2024. doi: 10.1109/JAS.2024.124578
[16]	A. J. Moshayedi, A. S. Khan, M. Davari, T. Mokhtari, and M. E. Andani, “Micro robot as the feature of robotic in healthcare approach from design to application: The state of art and challenges,” EAI Endorsed Trans. AI and Robotics, vol. 3, 2024.
[17]	Z. Li, S. Li, A. Francis, and X. Luo, “A novel calibration system for robot arm via an open dataset and a learning perspective,” IEEE Trans. Circuits and Systems II: Express Briefs, vol. 69, no. 12, pp. 5169–5173, 2022.
[18]	G. Xu, A. S. Khan, A. J. Moshayedi, X. Zhang, and Y. Shuxin, “The object detection, perspective and obstacles in robotic: A review,” EAI Endorsed Trans. AI and Robotics, vol. 1, p. 1, 2022.
[19]	A. G. Barnston and C. F. Ropelewski, “Prediction of ENSO episodes using canonical correlation analysis,” J. Climate, vol. 5, p. 11, 1992.
[20]	L. Sun, S. Ji, S. Yu, and J. Ye, “On the equivalence between canonical correlation analysis and orthonormalized partial least squares,” in Proc. 21st Int. Joint Conf. Artificial Intelligence, Pasadena, USA, Jul. 2009, pp. 1230–1235.
[21]	D. R. Hardoon, S. Szedmak, and J. Shawe-Taylor, “Canonical correlation analysis: An overview with application to learning methods,” Neural Computation, vol. 16, no. 12, pp. 2639–2664, 12, 2004. doi: 10.1162/0899766042321814
[22]	B. Juricek, D. Seborg, and W. Larimore, “Fault detection using canonical variate analysis,” Industrial & Engineering Chemistry Research, vol. 43, no. 2, pp. 458–474, Jan. 2004.
[23]	S. X. Ding, Data-Driven Design of Fault Diagnosis and Fault-tolerant Control Systems. Lonson UK: Springer-Verlag, 2014.
[24]	Z. W. Chen, S. X. Ding, K. Zhang, Z. B. Li, and Z. K. Hu, “Canonical correlation analysis-based fault detection methods with application to alumina evaporation process,” Control Engineering Practice, vol. 46, pp. 51–58, 2016. doi: 10.1016/j.conengprac.2015.10.006
[25]	Q. Jiang and X. Yan, “Learning deep correlated representations for nonlinear process monitoring,” IEEE Trans. Industrial Informatics, vol. 15, no. 12, pp. 6200–6209, 2019. doi: 10.1109/TII.2018.2886048
[26]	H. Chen, Z. Chen, Z. Chai, B. Jiang, and B. Huang, “A single-side neural network-aided canonical correlation analysis with applications to fault diagnosis,” IEEE Trans. Cybern., vol. 52, no. 9, pp. 9454–9466, 2022. doi: 10.1109/TCYB.2021.3060766
[27]	A. Er, D. Y. Ding, B. Er, M. Uzun, M. Cakmak, C. Sadee, G. Durhan, M. N. Ozmen, M. D. Tanriover, A. Topeli, S. Y. Aydin, R. Tibshirani, S. Unal, and O. Gevaert, “Multimodal data fusion using sparse canonical correlation analysis and cooperative learning: A covid-19 cohort study,” NPJ Digit Med, vol. 7, no. 1, p. 117, 2024. doi: 10.1038/s41746-024-01128-2
[28]	V. Uurtio, J. a. M. Monteiro, J. Kandola, J. Shawe-Taylor, D. Fernandez-Reyes, and J. Rousu, “A tutorial on canonical correlation methods,” ACM Comput. Surv., vol. 50, p. 6, Nov. 2017.
[29]	F. R. Bach and M. I. Jordan, “Kernel independent component analysis,” J. Mach. Learn. Res., vol. 3, pp. 1–48, 2003.
[30]	M. J. Healy, “A rotation method for computing canonical correlations,” Mathematics of Computation, vol. 11, pp. 83–86, 1957. doi: 10.1090/S0025-5718-1957-0085600-6
[31]	Z. Li, S. Li, O. O. Bamasag, A. Alhothali, and X. Luo, “Diversified regularization enhanced training for effective manipulator calibration,” IEEE Trans. Neural Networks and Learning Systems, vol. 34, no. 11, pp. 8778–8790, 2022.
[32]	W. Wang, R. Arora, K. Livescu, and J. Bilmes, “On deep multiview representation learning,” in Proc. Int. Conf. Machine Learning, 2015, pp. 1083–1092.
[33]	X. Li, Y. Xu, N. Li, B. Yang, and Y. Lei, “Remaining useful life prediction with partial sensor malfunctions using deep adversarial networks,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 1, pp. 121–134, 2023. doi: 10.1109/JAS.2022.105935
[34]	X. Jiang, X. Kong, and Z. Ge, “Augmented industrial data-driven modeling under the curse of dimensionality,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 6, pp. 1445–1461, 2023. doi: 10.1109/JAS.2023.123396
[35]	Z. W. Chen, S. X. Ding, T. Peng, C. H. Yang, and W. H. Gui, “Fault detection for non-gaussian processes using generalized canonical correlation analysis and randomized algorithms,” IEEE Trans. Industrial Electronics, vol. 65, no. 2, pp. 1559–1567, 2018. doi: 10.1109/TIE.2017.2733501
[36]	S. Akaho, “A kernel method for canonical correlation analysis,” 2007.
[37]	C. Dong, C. C. Loy, K. He, and X. Tang, “Image super-resolution using deep convolutional networks,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 38, no. 2, pp. 295–307, 2016. doi: 10.1109/TPAMI.2015.2439281
[38]	Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proc. IEEE, vol. 86, no. 11, pp. 2278–2324, 1998. doi: 10.1109/5.726791
[39]	I. Tolstikhin, O. Bousquet, S. Gelly, and B. Schoelkopf, “Wasserstein auto-encoders,” arXiv preprint arXiv: 1711.01558, 2017.
[40]	Z. Chen, K. Liang, S. X. Ding, C. Yang, T. Peng, and X. Yuan, “A comparative study of deep neural network-aided canonical correlation analysis-based process monitoring and fault detection methods,” IEEETrans. Neural Networks and Learning Systems, vol. 33, no. 11, pp. 6158–6172, 2021.
[41]	S. Shao, S. McAleer, R. Yan, and P. Baldi, “Highly accurate machine fault diagnosis using deep transfer learning,” IEEE Trans. Industrial Informatics, vol. 15, no. 4, pp. 2446–2455, 2019. doi: 10.1109/TII.2018.2864759
[42]	A. Saxena, K. Goebel, D. Simon, and N. Eklund, “Damage propagation modeling for aircraft engine run-to-failure simulation,” in Proc. 1st Int. Conf. Prognostics and Health Management, Oct. 2008.
[43]	K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2016, pp. 770–778.

Supplements(0)

Cited By

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Figures(13) / Tables(4)

Get Citation

PDF

XML

Article Metrics

Article views (22) PDF downloads(0)

CCDNN: A Novel Deep Learning Architecture for Multi-Source Data Fusion

doi: 10.1109/JAS.2025.125411

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Export File

Citation

Format

Content