Big-data-driven Performance Analysis, Prediction and Control of Smart Factories

Principal Investigators: 

Collaborator (Guangdong University of Technology)

• Prof Qiang LIU (Director, Guangdong Province Key Lab of Computer Integrated Manufacturing; Deputy Director, State Key Lab of Precision Electronic Manufacturing Technology and Equipment)
• Dr Ding ZHANG (Assistant Professor; 2019 Hong Kong Scholars; Research Director, Office of Workshop Performance Evaluation and Control)
• Dr Jiewu LENG (Associate Professor; 2018 Hong Kong Scholars; Research Director, Office of Workshop Customized Design)

Project Period: 1 April 2020 – 31 March 2022

Data from electronics manufacturing factory have the following charcteristics: large-scale, multi-variety and high-velocity. In the industrial production, disturbance factors come frequently from both inside and outside. These dynamic and random factors challenge the factory’s performance evaluation and control. Nevertheless, rational production decisions could be crucial in reducing production cost, and improving the yield. Data-driven analysis approaches afford us a new pathway for performance deduction, prediction and further control.

This project aims to develop big data processing techniques for performance analysis, prediction and control of smart factories. and to deliver advanced computational systems to help China’s electronics manufacturing industry. It will lead to opportunities to explore future funding and collaborations in the Greater Bay Area.

The project aims to achieve the following research objectives:

1. To collect many types of manufacturing information from smart factories in Guangdong Province as well as other parts of mainland China.
2. To develop data preprocessing methods for manufacturing data filtering and imputation to improve the data quality.
3. To study statistical models, machine learning algorithms and optmization techniques for manufacturing data classification and analysis.
4. To propose strategies and implement them in software for automated and intelligent control of smart factories.

 Publications

1. A novel modeling framework for a degrading system subject to hierarchical inspection and maintenance policy
   Zhang, A., Liu, X., Wu, Z. & Xie, M., Aug 2023, In: Applied Mathematical Modelling. 120, p. 636-650
2. A global strategy based on deep learning for time‐dependent optimal reliability design
   Ling, C., Li, X., & Kuo, W. , May 2023, In: Quality and Reliability Engineering International.
3. Recognition of abnormal patterns in industrial processes with variable window size via convolutional neural networks and AdaBoost
   Maged, A. & Xie, M., Apr 2023, In: Journal of Intelligent Manufacturing. 23 p.
4. Inspection and maintenance optimization for heterogeneity units in redundant structure with Non-dominated Sorting Genetic Algorithm III
   Zhang, A., Hao, S., Xie, M., Liu, Y. & Yu, H., Apr 2023, In: ISA Transactions. 135, p. 299-308
5. Dynamic event-triggered networked predictive control for discrete-time NCSs under deception attacks
   Wu, Z., Wang, Z., Wang, Y., Xiong, J. & Xie, M., Mar 2023, In: International Journal of Robust and Nonlinear Control.
6. SEIR Model to address the impact of face masks amid COVID-19 pandemic
   Maged, A., Ahmed, A., Haridy, S., Baker, A. W. & Xie, M., Jan 2023, In: Risk Analysis. 43, 1, p. 129–143
7. Support Vector Machine-Assisted Importance Sampling for Optimal Reliability Design
   Ling, C., Lei, J. & Kuo, W., Dec 2022, In: Applied Sciences (Switzerland). 12, 24, 12750.
8. Interval estimation for nabla fractional order linear time-invariant systems
   Wei, Y., Wei, Y., Wang, Y. & Xie, M., Dec 2022, In: ISA Transactions. 131, p. 83-94
9. Performance modeling for condition-based activation of the redundant safety system subject to harmful tests
   Zhang, A., Hao, S., Li, P., Xie, M. & Liu, Y., Oct 2022, In: Reliability Engineering and System Safety. 226, 108649.
10. Digital twin enabled optimal reconfiguration of the semi-automatic electronic assembly line with frequent changeovers
    Zhang, D., Leng, J., Xie, M., Yan, H. and Liu, Q., Oct 2022, In: Robotics and Computer-Integrated Manufacturing, 77, p.102343.
11. Uncertainty utilization in fault detection using Bayesian deep learning
    Maged, A. & Xie, M., Jul 2022, In: Journal of Manufacturing Systems. 64, p. 316-329
12. An adaptive prognostics method based on a new health index via data fusion and diffusion process
    Li, P., Maged, A., Zhang, A., Xie, M., Dang, W. & Lyu, C., Apr 2022, In: Measurement. 193, 110968.
13. Model-Based Deep Transfer Learning Method to Fault Detection and Diagnosis in Nuclear Power Plants
    Yao, Y., Ge, D., Yu, J. & Xie, M., Mar 2022, In: Frontiers in Energy Research. 10, 823395.
14. WC-KNNG-PC : Watershed clustering based on k-nearest-neighbor graph and Pauta Criterion
    Xia, J., Zhang, J., Wang, Y., Han, L. and Yan, H., Jan 2022, In: Pattern Recognition, 121, p.108177.
15. A model-based reinforcement learning approach for maintenance optimization of degrading systems in a large state space
    Zhang, P., Zhu, X. & Xie, M., Nov 2021, In: Computers and Industrial Engineering. 161, 107622.
16. A matrix analytic approach for Bayesian network modeling and inference of a manufacturing system
    Zhang, D., Liu, Q., Yan, H. and Xie, M., Jul 2021, In: Journal of Manufacturing Systems, 60, pp.202-213.
17. Resilience dynamics modeling and control for a reconfigurable electronic assembly line under spatio-temporal disruptions
    Zhang, D., Xie, M., Yan, H. & Liu, Q., Jul 2021, In: Journal of Manufacturing Systems. 60, p. 852-863
18. Instance segmentation with the number of clusters incorporated in embedding learning
    Cao, J. and Yan, H., Jun 2021, In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1800-1804). IEEE.
19. Computationally predicting binding affinity in protein–ligand complexes: free energy-based simulations and machine learning-based scoring functions
    Wang, D.D., Zhu, M. and Yan, H., May 2021, In: Briefings in bioinformatics, 22(3), p.bbaa107.
20. Visualization of Protein-Drug Interactions for the Analysis of Drug Resistance in Lung Cancer
    Qureshi, R., Zhu, M. and Yan, H., May 2021, In: IEEE Journal of Biomedical and Health Informatics, 25(5), pp.1839-1848.
21. Multi-deep features fusion for high-resolution remote sensing image scene classification
    Yuan, B., Han, L., Gu, X. and Yan, H., Mar 2021, In: Neural Computing and Applications, 33, pp.2047-2063.
22. HiSCF: leveraging higher-order structures for clustering analysis in biological networks
    Hu, L., Zhang, J., Pan, X., Yan, H. and You, Z.H., Feb 2021, In: Bioinformatics, 37(4), pp.542-550.