Skip to main content

Prof. Kang Li
Professor
Profile
Photo of Kang Li  
Phone: +44 (0)28 9097 4663
E-mail: k dot li at ee dot qub dot ac dot uk
Recent Publications

 

Biography

 

Biography
 
Education
  • PGCert in Higher Education Teaching, Queen’s University Belfast, (2000)
  • PhD in Control Theory and Applications, recipient of university scholarships and prizes, Shanghai Jiaotong University (1995)
  • MSc in Control Theory and Applications, distinction, Harbin Institute of Technology (1992)
  • BSc in Industrial Automation, award of university role model students, Xiang Tan University (1989)
Memberships
  • Senior Member IEEE
  • Fellow High Education Academy
 
Appointments

  • Professor of Intelligent Systems and Control (2011), Reader (2009), Senior Lecturer (2007), Lecturer (2002), School of Electronics, Electrical Engineering & Computer Science, Queen's University Belfast.
  • Research fellow, School of Mechanical & Manufacturing Engineering, Queen's University Belfast (1998- 2002)
  • Senior research fellow, Lab for Measurement and Control, Delft University of Technology (1997-1998)
  • Postdoctoral research fellow, then associate professorship. Department of Automation, Shanghai Jiaotong University (1995-1996)
Administrations
  • School Internationalization Champion
  • University Head of China Initiatives

Research Interests

Prof Li’s research interests cover nonlinear system modelling, identification and control, and bio-inspired computational intelligence, with recent applications to power systems and polymer extrusion. He is particularly interested in the development of a generation of low-cost intelligent energy saving technologies for decarbonizing the whole energy systems, from conventional thermal power plants, integration of renewable energies, to end user energy efficiency in industries and integration of electric vehicles to the grid. He is also interested in bioinformatics and systems biology with applications on food safety and healthcare. Professor Li has published over 200 papers in his field, and has been invited to give over 30 research seminars worldwide.

Honours & Awards

  • Highly commended paper, International Journal of Systems Science. ‘Model selection approaches for non-linear system identification: a review’’, 2010, co-authored with Xia Hong, R.J. Mitchell, S. Chen, C. J. Harris and George Irwin.
  • Best oral presentation award. 2013 International Conference on Intelligent Robotics and Applications (ICIRA 2013, Sept 25-28, 2013) presented the award to Zhixuan Wei, Weidong Chen, Jingchuan Wang, Huiyu Wang and Kang Li for the paper entitled 'Semantic Mapping for Safe and Comfortable Navigation of a Brain-Controlled Wheelchair'.
  • Best paper award. 2010 International Conference on Sustainable Energy and Built Environment. ‘Identification of Chiller Model in HVAC System Using Fuzzy Inference Rules with Zadeh’s Implication Operator’, co-authored with Yukui Zhang, Shiji Song, and Cheng Wu.
  • Young Author Best Paper Award. 2011 International Conference on Modelling, Identification and Control (ICMIC 2011). “Modeling of Melt Pressure Development in Polymer Extrusion: Effects of Process Settings and Screw Geometry”, co-authored with Chamil Abeykoon, Peter J. Martin and Adrian L. Kelly, 2011.
  • Third prize. 2012 China (International) Transducer & Sensor Innovation Contest presented the award on project ‘Soft sensor technology for measuring the melt viscosity of polymer extrusion’, to the team led by Kang Li.
  • Visiting Professor awarded by Harbin Institute of Technology, China, 2011; Ningbo Institute of Technology, Zhejiang University, China, 2010; Shanghai University, China, 2007; Polytechnic University of Bari, Taranto, Italy, 2006. 
  • Senior visiting scholar, Tsinghua University, China, 2010.
  • Visiting scholar, University of Iowa, USA, 2007, New Jersey Institute of Technology, Newark, USA, 2007, National University of Singapore, 2006.

Professional Activity
Editorial Board
  • Associate Editor, Editorial Board, Transactions of the Institute of Measurement & Control (Sage), 2005-present
  • Member, Editorial Board, Neurocomputing (Elsevier), 2005-present; Cognitive Computation (Springer, NY, USA), 2009- present ; Int. J. of Modelling, Identification and Control (inderscience), 2007-present.
  • Guest Editor, two special issues, Neurocomputing, 2007, 2010; one special issue, IFAC Journal of Mechatroncis, 2010; One special issue, Neural Computing and Applications, 2010; four special issues, Transactions of the Institute of Measurement and Control, 2006, 2007, 2010; one special issue, Applied Mathematics and Computation, 2007; two special issues, International Journal of Modelling, Identification and Control, 2008; Mathematical Problems in Engineering, 2013.
  • Volume Editor/Co-editor, 12 volumes of Springer's Lecture Notes series, including Lecture Notes in Computer Science (LNCS) (4 volumes), Lecture Notes in Artificial Intelligence (LNAI) (1 volumes), Lecture notes in Bioinformatics (LNBI) (3 volumes), and Lecture Notes in Control and Information Sciences (LNCIS) (2 volumes), 2006, 2007, 2010.
Committee of International Conferences Invited seminars – over 30 invited seminars and speeches worldwide

PhD students
Patrick Connaly (graduated in 2006); Barbara Pizzileo (graduated in 2009); Dajun Du (exchange, graduated in 2011); Xiao-Lei Xia (Celina, graduated in 2009); Padraig Gormley (graduated in 2010); Li Pan (2009-2010, graduated in 2010);. Jing Deng (graduated in 2011); Yapa Abeykoon ( graduated in 2011); Aolei Yang (Bert, 2009-2012); Wanqing Zhao (Horace, 2009-2012); Jingjing Zhang (Clare, 2009-2012); Hui Cai (2009-2012); Da Lu (Exchange student from Zhejiang University, 2010); Weihua Deng (exchange student from Shanghai University, 2010- 2011, graduated in 2012); Xiaoqing Tang (Emma, 2010-2013); Long Zhang (Will, 2010-2013);  Juan Yan (Joanna, 2011-2014); Yuanjun Guo (Anna, 2011-2014); Xiaodong Zhao (Leo, 2011-2014); Ziqi Yang (Wallace, 2011-2014); Lijun Xu (Michelle, Exchange from Shanghai Jiaotong, 2011-2012, graduated in 2013); Jianxing Li (exchange from Zhejiang University, 2012-2013); Yongling Wu (exchange from Shanghai Jiaotong University, 2012- 2014); Sable Campbell (2012-2013); Jeong Park (2013-2018); Paraic Higgins ( 2013-2015); Zhebing Sun (2013-2014). .

Postdoctoral researcher
Dr Jing Deng (EPSRC, 2011 -2013; POC 2013; EPSRC 2013-2016); Dr Songyan Wang (EPSRC 2013-2016); Dr Dajun Du (RCUK, 2011-2012); Mr Peter Henon (KTP associate, 2012-2014); Dr Qun Niu (RCUK, 2009 -2011); Dr Xueqing Liu (EPSRC, 2009-2011); Dr Patrick Connally (EPSRC, 2007); Dr Jian-Xun Peng (EPSRC, 2004-2007); Dr James J Govindhasamy (KTP, 2005-2007).

Funded Projects
  1. 2013-2016, EPSRC (EP/L001063/1), “Intelligent Grid Interfaced Vehicle Eco-charging (iGIVE)’, one of four jointly funded by EPSRC-NSFC, totalling over £1 Million, as PI.
  2. 2013-2015, Proof of Concept (PoC) project, “Integrating energy efficiency monitoring, control and optimization for plastics industry”. Invest Northern Ireland and European Regional Development Fund, as PI.
  3. 2012-2014, Knowledge Transfer Partnerships, Technology Strategy Board, ‘To embed in-house electronic software and hardware capability’, as the PI.
  4. 2011, Distinguished Visiting Fellow, “Advanced process control techniques for sustainable development for energy intensive processes,” Royal Academy of Engineering, as PI.
  5. 2009- 2012, from EPSRC/RCUK (EP/G042594/1), “UK-China Bridge in Sustainable Energy and Built Environment (UC-SEBE)”, as CI and topic leader (total funding £2.3 million), together with George Irwin (PI), Haifeng Wang, Muhammad Basheer, Yun Bai and Tim Littler.  
  6. 2008-2011, EPSRC (EP/F021070/1), “An integrated system of inferential measurement and control of polymer extrusion for self-tuning optimisation and response to disturbances”, as PI, together with Marion McAfee, and Peter Martin.
  7. 2010-2013, EPSRC (EP/G059489/1), “Thermal Management in Polymer Processing”, as CI, together with Eileen Harkin-Jones, and Mark Price.
  8. 2010, British Council, Prime Minister Initiative (PMI2), “International mobility of UK students’, K Li*, as PI.
  9. 2009, Distinguished Visiting Research Fellow, “Computational intelligence in control for sustainable development,” Royal Academy of Engineering, as PI.
  10. 2007- 2010, EPSRC (Engineering and Physical Sciences Research Council), Q Zhong*, A Zolotas, K Li, D Coca, and S Evangelou, “New-ACE: A Network for New Academics in Control Engineering”, as Collaborator and Core member.
  11. 2008-2011, Shanghai Municipal Science and Technology Commission, M Fei, G. Irwin and K Li, “Research on optimization and networked control of large-scale fossil-fuel power generation plants for energy efficiency”, as CI.
  12. 2004 – 2007, EPSRC (Engineering and Physical Sciences Research Council), K Li*, “Eng-genes - a new genetic modelling approach for real-time operation and control of engineering systems”, Project highlighted in EPSRC Newsline, issue 29, page 4, 2004, as PI.
  13. 2005-2006, EPSRC (Engineering and Physical Sciences Research Council), P Crossley*, G Irwin, K Li, T Littler, “INTERACT: Establishing New Research Links with Chinese Universities and Chinese Academy of Science”, as CI.
  14. 2005-2007, KTP project, Knowledge Transfer Partnership, “To optimise the control of substrate grinding and polishing processes and improve process capability, which achieves the stringent requirements of future high density disk production”, with Seagate Technology Media (Ireland), as CI.
Over 40 projects including funded PhD studentships and funding from other resources, totalling over £4.5 million 
 
Research summary

One of the main research themes is on the subset selection in the following regression modelling problem. Suppose variable y can be represented by (1): y=f(g_1, g_2,…, g_m)+e, where function f represents a model structure to combine a set of low dimensional functions g_i, i=1,…,m, and e is the modelling residual. If f is a linear-in-the-parameter structure, and a large number of g_i may be possibly included into the model, then the aim is to select a much smaller set of g_i to approximate y, given a criterion or a set of criteria. This is a subset selection problem, and a fast forward selection algorithm (FRA) was proposed in [1], which works directly on the sum squared errors by introducing a recursive residual matrix, in contrast to the popular Orthogonal Least Squares (OLS) method which applies orthogonalization directly on the regressors. This allows faster and more stable forward regressor selection. This framework further enables a fast two stage procedure which in the second stage removes or replaces redundant regressors obtained in the first stage of the forward subset selection [2]. The mathematical framework of the two stage approach was then extended to the OLS, resulting in a more efficient two-stage OLS method. The results are further extended to the cases when g_i has tunable parameters in it, such as RBF networks, Single Layer Forward Neural Networks [3][4]. The basic methods have also been extended to more advanced topics for the construction of compact neural networks and fuzzy neural networks, as well as to the training of least squares support vector machines, and nonlinear principal component analysis (use neural networks to model the principal curves), etc [5]-[10]. These methods have been applied to system modelling and identification, system monitoring and fault diagnosis, and nonlinear control. External collaborations in the identification area (non-parametric modelling, Wiener-Hammerstein model, etc) are mainly with Prof Erwei Bai from Univ. Iowa [11,12], and a survey paper on nonlinear system identification with Dr Hong Xia, Prof Sheng Chen, Dr Richard Mitchell, Prof Chris Harris and Prof George Irwin has been highly commended by the International Journal of Systems Science [13]. Recent interest is on the development of machine learning algorithms for dealing with curse of dimensionality problem, imbalanced data and fusion of heterogeneous temporal spatial data, in collaboration with international colleagues [14]. 
Another research interest in system identification is on the eng-genes modelling framework, which in (1) the low dimensional functions g_i are selected among a group of salient fundamental functions (engineering genes) in the first principle laws governing the underlying physics for the systems under study, while f in (1) uses a combination of simple operations on the genes to produce transparent/interpretable model of the original complex systems. To produce such an eng-genes model for a complex system, bio-inspired heuristic optimization algorithms have also been investigated. The eng-genes idea has been applied to the modelling of both engineering systems as well as biological systems [15]-[18].
On the application side, the recent major interest is on the development of advanced control technologies for decarbonizing the whole energy system. 1) modelling, control and optimization of polymer processing (extrusion, stretch blow moulding), including software sensor approach for real-time estimation of melt viscosity; fault diagnosis, optimization and control of polymer processes, in collaboration with colleagues from polymer processing centres at Queen’s University Belfast and the University of Bradford [20]-[23]. In particular, Prof Li is currently leading a proof of concept project funded by Invest Northern Ireland and European Regional Development Fund, developing a new generation of low cost non-invasive intelligent energy and health monitoring system as well as intelligent control and optimization platform for energy saving, primarily for plastics industry, and with the aim to extend to other major energy intensive industries. 2) Conventional power generation plants, especially modelling and control of NOx emissions from thermal power plants [24]. 3) Integration of renewable energies, economic load dispatch considering wind penetration, control of multi-terminal HVDC systems for integrating large scale offshore wind farms, wide area power system monitoring and fault detection, and integration of electric vehicles to the grid, etc. [25[26]. Other application interests are Systems biology, bioinformatics, and food safety [27], etc.
One of the recent highlights in international  research collaboration initiated by Prof Li and colleagues has been through the RCUK funded UK-China Science Bridge project, which has enabled the strategic alliance with over 14 leading Chinese universities, institutions and companies, as well as their associated research groups in China, including Tsinghua, Zhejiang, Shanghai Jiaotong, and Shanghai Universities, etc., carrying out research and knowledge transfer activities on the sustainable energy and built environment technologies. Another recent major initiative is the development of intelligent grid interfaced eco-charging system (iGIVE) for seamless integration of electric vehicles, one of four jointly funded by EPSRC and NSFC, in collaboration with Cranfield University, Harbin Institute of Technology and China State Grid EPRI.

For full details, please refer to the group website.

References:

[1]  K. Li, J. Peng, G. Irwin, “A fast nonlinear model identification method”, IEEE Transactions on Automatic Control, Vol. 50, No. 8, 1211-1216, 2005. (For the matlab code, please contact Prof Kang Li)
[2] K. Li, J. Peng, E-W Bai. “A two-stage algorithm for identification of nonlinear dynamic systems”. Automatica, Vol. 42, No 7, pp. 1189-1197, 2006. (For the matlab code, please contact Prof Kang Li)
[3] J. Peng, K. Li, D.S. Huang. “A Hybrid forward Algorithm for RBF neural Network construction”.  IEEE Transactions on Neural Networks, Vol 17, No. 6, pp 1439-1451, 2006.
[4] K. Li, J. Peng, E-W Bai. “Two-stage mixed discrete-continuous identification of Radial Basis Function (RBF) neural models for nonlinear systems”.  IEEE Transactions on Circuits & Systems, Vol 56, No. 3, 630-643, March 2009.
[5] J. Peng, K. Li, G. W. Irwin. “A new Jacobian matrix for optimal learning of single-layer neural nets”.  IEEE Transactions on Neural Networks, Vol. 19, No.1, 119-129, 2008.
[6] J. Deng, K. Li, G. W. Irwin, “Locally regularised two-stage learning algorithm for RBF network centre selection”, International Journal of Systems Science , Vol.43, No. 6, pages 1157-1170, 2012.
[7] W. Zhao, K. Li, and G. Irwin, “A New Gradient Descent Approach for Local Learning of Fuzzy Neural Models”, IEEE Transactions on Fuzzy Systems, 2012, (DOI:10.1109/TFUZZ.2012.2200900).
[8] B. Pizzileo, K. Li, G. Irwin and W. Zhao, ‘Improved structure optimization for fuzzy-neural networks’, IEEE Transactions on Fuzzy Systems, 2012 (DOI: 10.1109/TFUZZ.2012.2193587).
[9] X. Liu, K. Li, M. McAfee, G. Irwin, “Improved Nonlinear PCA for Process Monitoring Using Support Vector Data Description”, Journal of Process Control, Vol. 21, No. 9, 2011, Pages 1306-1317.
[10] L. Zhang, K. Li, E-W Bai, ‘A New Extension of Newton Algorithm for Radial Basis Function (RBF) Networks Modelling’, IEEE Transactions on Automatic Control, 2013, Vol. 58 , No. 11, pp. 2929 - 2933
[11] E-W Bai, K. Li. “Convergence of the Iterative Algorithm for a General Hammerstein System Identification”, Automatica, Vol. 46, No.11, November 2010, pp 1891-1896.
[12] E-W Bai, K. Li, W. Zhao, W. Xu, ‘Kernel Based Approaches to Local Nonlinear Non-parametric Variable Selection’, Automatica, 2013,DOI:10.1016/j.automatica.2013.10.010.
[13]  X. Hong, R.J. Mitchell, S. Chen, C. J. Harris, K. Li, G. W. Irwin. “Model selection approaches for non-linear system identification: a review”. International Journal of Systems Science, Vol. 39, No. 10, 925–946, October 2008.
[14] Haibo He, Sheng Chen, K Li, Xin Xu. “Incremental Learning from Stream Data”. IEEE Transactions on Neural Networks, 2011, Vol 22, No. 12, pp. 1901-1914.
[15]    P. Gormley, K. Li, Olaf Wolkenhauer, G. W. Irwin, D. Du, “Reverse engineering of biochemical reaction networks using co-evolution with eng-genes”, Cognitive Computation, 2012,  DOI: 10.1007/s12559-012-9159-y.
[16] P. Connally, K. Li, G. W. Irwin. “Integrated Structure Selection and Parameter Optimisation for Eng-genes Neural Models”, Neurocomputing, Vol 71, No 13-15, 2964-2977, 2008.
[17]    K. Li, “Eng-genes: A new genetic modelling approach for nonlinear dynamic systems”, Proceedings of the 16th IFAC World Congress, Prague, July 4-8, 2005.
[18]      K. Li, J. Peng, “System Oriented Neural Networks – Problem Formulation, Methodology, and Application”, International Journal of Pattern Recognition and Artificial Intelligence, Vol. 20, No. 2, 2006, 143-158.
[19] J. Peng, K. Li, S. Thompson, P. A. Wieringa. “Distribution-based Adaptive Bounding Genetic Algorithm for Continuous Optimisation Problems”. Applied Mathematics and Computation, Vol 185: 1063–1077, 2007.
[20] X. Liu, K. Li, M. McAfee, “Dynamic grey-box modeling for online monitoring of extrusion viscosity”. Polymer Engineering & Science, Vol 52, No 6, pp 1332-1341, June 2012.
[21] Xueqin Liu, K. Li, Marion McAfee, Jing Deng, “Application of Nonlinear PCA for Fault Detection in Polymer Extrusion Processes”, Neural Computing and Applications,  2011, doi 10.1007/s00521-011-0581-y.
[22] C. Abeykoona, K Li, M. McAfee, P. J. Martin, Q. Niu, A. L. Kelly, J. Deng, “A new model based approach for the prediction and optimisation of thermal homogeneity in single screw extrusion”, Control Engineering Practice, Vol 19, No 8, 2011, pp 862-874.
[23] J. Deng, K. Li, E. Harkin-Jones, M. Price, N. Karnachi, A. Kelly, J. Vera-Sorroche, P. Coates, E. Brown, M. Fei, “Energy monitoring and quality control of a single screw extruder”, Applied Energy, Vol. 113, Pages 1775–1785, January 2014.
[24] K. Li, S. Thompson, J. Peng, “Modelling and prediction of NOx emission in a coal-fired power generation plant", Control Engineering Practice, Vol. 12, 707-723, 2004.
[25] X. Tang, B. Fox and K. Li, “Reserve from wind power potential in system economic loading”, IET Renewable Power Generation, 2013, accepted.
[26] Q. Niu, H. Zhang, K. Li, G. W. Irwin, ‘An Efficient Harmony Search with New Pitch Adjustment for Dynamic Economic Dispatch’, Energy, 2013, accepted.
[27] R. T. Cunningham, M. H. Mooney, X.L. Xia, S. Crooks, D. Matthews, M. O. Keeffe, K. Li and C. T. Elliott. “Feasibility of a Clinical Chemical Analysis Approach to Predict Misuse of Growth Promoting Hormones in Cattle”. Analytic Chemistry, 2009, 81 (3), pp 977–983.