Learning techniques for improving control systems performance using model-free approaches (LTIPerforM), 83114 EUR, national research grant Young Teams (TE), financed by the Executive Agency for Higher Education, Research, Development and Innovation Funding - UEFISCDI), 2015-2017, project code: PNII-RU-TE-2014-4-0207
The team:
Abstract:
- The main objective of this proposal is to develop the necessary tools, algorithms and theoretical framework in order to induce the learning-predictive behavior for control systems using model-free control approaches. The control loops at the lower hierarchical level will be first designed and tuned using model-free techniques such as Iterative Feedback Tuning, Virtual Reference Feedback Tuning, Model Free Adaptive Control. With the fixed designed control loops, the typical reference input-controlled output behavior specific to stable closed-loop control systems will be next improved using a model-free Iterative Learning Control approach to optimize the reference inputs in a trajectory tracking problem framework. Several reference input-controlled output behaviors are memorized as primitive tasks inside a library of primitives. The primitives are used in predicting the optimal behavior of the control system when a new complex task is to be executed. A planning mechanism similar to a brain will be built in order to achieve this task. The developed mechanism operates at the higher hierarchical level with respect to that of the basic control tasks (reference tracking and disturbance rejection). This will be done using the Linear Time Invariant framework and will be developed for both Single Input-Single Output and Multi Input-Multi Output systems. This approach will then be experimentally validated on various linear and nonlinear laboratory control systems.
Estimated results:
- The publication of papers in high impact leading journals, minimum 3 papers.
- The participation and presentation of papers at leading international academic conferences.
- Minimum 4 papers in conference proceedings / journals / book chapters.
Research reports:
Overall results (2015-2017):
- 7 papers published in Thomson Reuters Web of Science journals with impact factors, cumulated impact factor from publication year according to the Journal Citation Reports = 20.766, 14 papers published in conference proceedings (to be) indexed in international databases (ISI, IEEE Xplore, INSPEC, Scopus, DBLP), 1 book chapter published in a Springer-Verlag volumes.
Results in 2017:
- 3 papers published in Thomson Reuters Web of Science journals with impact factors, cumulated impact factor according to 2017 Journal Citation Reports = 13.950, 6 papers published in conference proceedings (to be) indexed in international databases (ISI, IEEE Xplore, INSPEC, Scopus, DBLP).
- Radac M.-B., Precup R.-E., Data-Driven Model-Free Slip Control of Anti-lock Braking Systems Using Reinforcement Q-Learning, Neurocomputing, vol. pp, no. 1, pp. 1-13, 2017, 2017 impact factor (IF) = 3.317 (www.sciencedirect.com).
- R.-E. Precup, M.-B. Radac, R.-C. Roman, and E. M. Petriu, Model-free sliding mode control of nonlinear systems: Algorithms and experiments, Information Sciences, vol. 381, no. 3, pp. 176-192, 2017, impact factor (IF) = 4.832. (www.sciencedirect.com).
- R.-E. Precup, R.-C. David, and E. M. Petriu, Grey Wolf Optimizer algorithm-based tuning of fuzzy control systems with reduced parametric sensitivity, IEEE Transactions on Industrial Electronics, vol. 64, no. 1, pp. 527-534, 2017, impact factor (IF) = 7.168. (www.ieeexplore.ieee.org).
- C. Pozna and R.-E. Precup, On a translated frame-based approach to geometric modeling of robots, Robotics and Autonomous Systems, vol. 91, pp. 49-58, May 2017, impact factor (IF) = 1.950, (www.sciencedirect.com).
- D.-A. Dutescu, M.-B. Radac and R.-E. Precup, Model Predictive Control of a Nonlinear Laboratory Twin Rotor Aero-dynamical System, Proceedings of 15th IEEE International Symposium on Applied Machine Intelligence and Informatics (SAMI 2017), Herl'any, Slovakia, pp. 37-42, 2017, (ieeexplore.ieee.org).
- M.-B. Radac, R.-E. Precup, and R.-C. Roman, Anti-lock Braking Systems Data-Driven Control Using Q-Learning, Proceedings of the 2017 IEEE International Symposium on Industrial Electronics (ISIE 2017), Edinborough, UK, pp. 418-423, 2017, ( ieeexplore.ieee.org).
- M.-B. Radac, R.-E. Precup, and R.-C. Roman, Multi Input-Multi Output Tank System Data-Driven Model Reference Control, Proceedings of the 13th IEEE International Conference on Control & Automation (ICCA 2017), Ohrid, Macedonia, pp. 1078-1083, 2017 ( ieeexplore.ieee.org).
- R.-C. Roman, R.-E. Precup, and M.-B. Radac, Model-Free Fuzzy Control of Twin Rotor Aerodynamic Systems, Proceedings of the 25th Mediterranean Conference on Control and Automation (MED 2017), Valletta, Malta, pp. 559-564, 2017 (ieeexplore.ieee.org).
- R-.C. Roman, R.-E. Precup, M.-B. Radac and E. M. Petriu, Takagi-Sugeno Fuzzy Controller Structures for Twin Rotor Aerodynamic Systems, Proceedings of the 2017 IEEE International Conference on Fuzzy Systems (FUZZIEEE 2017), Napoli, Italy, pp. 1-6, 2017, (ieeexplore.ieee.org).
- A.-I. Szedlak-Stinean, R.-E. Precup, and E. M. Petriu, Fuzzy and 2-DOF Controllers for Processes with a Discontinuously Variable Parameter, Proceedings of 14th International Conference on Informatics in Control, Automation and Robotics (ICINCO 2017), Madrid, Spania, pp. 431-438, 2017 (www.scitepress.org).
Results in 2015-2016:
- 4 papers published in Thomson Reuters Web of Science journals with impact factors, cumulated impact factor according to 2016 Journal Citation Reports = 6.816, 8 papers published in conference proceedings (to be) indexed in international databases (ISI, IEEE Xplore, INSPEC, Scopus, DBLP), 1 book chapter published in a Springer-Verlag volume.
- Radac M.-B., Precup R.-E., Roman R.-C., Model-Free control performance improvement using virtual reference feedback tuning and reinforcement Q-learning, International Journal of Systems Science (Taylor & Francis), vol. pp, no. 1, pp. 1-13, 2016, 2016 impact factor (IF) = 1.947, relative influence score = 0.87 (www.tandfonline.com).
- Radac M.-B., Precup R.-E., Three-level hierarchical model-free learning approach to trajectory tracking control, Engineering Applications of Artificial Intelligence (Elsevier), vol. 55, pp. 103-118, 2016, 2016 impact factor (IF) = 2.368, relative influence score = 2.116 (www.sciencedirect.com).
- Roman R.-C., Radac M.-B., Precup R.-E., Multi-input-multi-output system experimental validation of model-free control and virtual reference feedback tuning techniques, IET Control Theory and Applications, vol. 10, no. 12, pp.1395-1403, 2016, 2016 impact factor (IF)= 1.957, relative influence score = 1.856, (http:// digital-library.theiet.org).
- Roman R.-C., Radac M.-B., Precup R.-E., Petriu E. M., Data-driven Model-Free Adaptive Control Tuned by Virtual Reference Feedback Tuning, Acta Polytechnica Hungarica, vol. 13, no. 1, pp. 83-96, 2016, 2016 impact factor (IF) = 0.544, relative influence score = 0.313 (www.uni-obuda.hu/journal/).
- Roman R.-C., Radac M.-B., Precup R.-E., Petriu E. M., Virtual Reference Feedback Tuning of MIMO Data-Driven Model-Free Adaptive Control Algorithms, in: Technological Innovation for Cyber-Physical Systems, L. M. Camarinha-Matos, A. J. Falcao, N. Vafaei and S. Najdi, Eds., IFIP Advances in Information and Communication Technology, vol. 470 (Springer International Publishing), pp. 253-260, 2016, indexed in Scopus, DBLP (link.springer.com).
- Radac M.-B., Precup R.-E., Improving Model Reference Control Performance Using Model-Free VRFT and Q-Learning, Proceedings of 2016 20th International Conference on System Theory, Control and Computing (ICSTCC 2016), Sinaia, Romania, pp. 7-13, 2016, to be indexed in IEEE Xplore, INSPEC ( ieeexplore.ieee.org).
- Radac M.-B., Precup R.-E., Hierarchical Data-Driven Model-Free Iterative Learning Control Using Primitives, Proceedings of 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2016), Budapest, Hungary, pp. 2785-2790, 2016, to be indexed in IEEE Xplore, INSPEC ( ieeexplore.ieee.org).
- Roman R.-C., Radac M.-B., Precup R.-E., Mixed MFC-VRFT Approach for a Multivariable Aerodynamic System Position Control, Proceedings of 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2016), Budapest, Hungary, pp. 2615-2620, 2016, to be indexed in IEEE Xplore, INSPEC ( ieeexplore.ieee.org).
- Radac M.-B., Precup R.-E., Roman R.-C., Data-Driven Virtual Reference Feedback Tuning and Reinforcement Q-learning for Model-Free Position Control of an Aerodynamic System, Proceedings of 24th Mediterranean Conference on Control and Automation MED'2016, Athens, Greece, pp. 1126-1132, 2016, (ieeexplore.ieee.org).
- Precup R.-E., David R.-C., Petriu E. M., Szedlak-Stinean A.-I., Bojan-Dragos C.-A., Grey Wolf Optimizer-Based Approach to the Tuning of PI-Fuzzy Controllers with a Reduced Process Parametric Sensitivity, Proceedings of 4th IFAC International Conference on Intelligent Control and Automation Sciences ICONS 2016, Reims, France, 2016, IFAC-PapersOnLine, vol. 48, no. 5, pp. 55-60, 2016, (www.sciencedirect.com).
- Bojan-Dragos C.-A., Precup R.-E., Preitl S., Szedlak-Stinean A.-I., Petriu E. M., Particle Swarm Optimization of Fuzzy Models for Electromagnetic Actuated Clutch Systems, Proceedings of 18th Mediterranean Electromechanical Conference MELECON 2016, Limassol, Cyprus, pp. 1-6, 2016, indexed in IEEE Xplore, INSPEC (ieeexplore.ieee.org).
- Hedrea E.-L., Radac M.-B., Precup R.-E., Virtual Reference Feedback Tuning for Position Control of a Twin Rotor Aerodynamic System, Proceedings of 11th IEEE International Symposium on Applied Computational Intelligence and Informatics SACI 2016, Timisoara, Romania, pp. 57-62, 2016, indexed in IEEE Xplore, INSPEC (ieeexplore.ieee.org).
- Precup R.-E., David R.-C., Petriu E. M., Radac M.-B., Voisan E.-I., Experiment-Based Comparison of Nature-Inspired Algorithms for Optimal Tuning of PI-Fuzzy Controlled Nonlinear DC Servo Systems, Proceedings of 2016 International Symposium on Power Electronics, Electrical Drives, Automation and Motion SPEEDAM 2016, Capri, Italy, pp. 1263-1268, 2016, indexed in IEEE Xplore, INSPEC (ieeexplore.ieee.org).
Home