Modelling framework for artificial hybrid dynamical systems. (English) Zbl 1478.93303
Summary: Many current industry branches use hybrid approaches to solve complex application problems. Over the last decades, different tools for the simulation of such hybrid systems (e.g. Hysdel and YAMLIP) as well as the identification of hybrid systems (e.g. HIT, MLP and OAF NN) have been developed. The framework presented in this work facilitates the integration of artificial feed-forward neural networks in the modelling process of hybrid dynamical systems (HDS). Additionally, the framework provides a structured language for characterising these feed-forward networks itself. Therefore, an interdisciplinary exchange in the field of neural networks and its integration into hybrid dynamical systems is enabled. Focusing on hybrid systems with autonomous events, two different approaches, namely the artificial hybrid model and the artificial hybrid dynamics, are introduced. Challenges of the modelling process of HDS are reflected and advantages as well as disadvantages are discussed. The case study includes two common examples of HDS and analyses the simulation results and examines limitations of the modelling framework.
MSC:
| 93C30 | Control/observation systems governed by functional relations other than differential equations (such as hybrid and switching systems) |
| 93B70 | Networked control |
| 68Q45 | Formal languages and automata |
| 68T07 | Artificial neural networks and deep learning |
Keywords:
hybrid dynamical systems; neural networks; modelling benchmark; hybrid neural networks; hybrid modelling frameworkReferences:
| [1] | Christin, A.; Rosenblat, A.; Boyd, D., Courts and Predictive Algorithms, 11 (2015), datacivilrights.org, http://www.law.nyu.edu/sites/default/files/upload_documents/Angele |
| [2] | Maschewski, F.; Nosthoff, A.-V., Res Publica ex Machina: On Neocybernetic Governance and the End of Politics, 25 (2018), INC Longforms |
| [3] | Lian, J.; Liu, S.; Li, L.; Liu, X.; Zhou, Y.; Yang, F.; Yuan, L., A mixed logical dynamical-model predictive control (MLD-MPC) energy management control strategy for plug-in hybrid electric vehicles (PHEVs), Energies, 10,74 (2017) |
| [4] | Lu, W.; Zhu, P.; Ferrari, S., A hybrid-adaptive dynamic programming approach for the model-free control of nonlinear switched systems, IEEE Trans. Automat. Control, 61, 10, 3203-3208 (2016), URL http://ieeexplore.ieee.org/document/7358089/ · Zbl 1359.90146 |
| [5] | Seatzu, C.; Corona, D.; Giua, A.; Bemporad, A., Optimal control of continuous-time switched affine systems, IEEE Trans. Automat. Control, 51, 5, 726-741 (2006), URL http://ieeexplore.ieee.org/document/1632302/ · Zbl 1366.49038 |
| [6] | Choy, K.; Chow, H. K.; Tan, K.; Chan, C.-K.; Mok, E. C.; Wang, Q., Leveraging the supply chain flexibility of third party logistics - Hybrid knowledge-based system approach, Expert Syst. Appl., 35, 4, 1998-2016 (2008), URL https://linkinghub.elsevier.com/retrieve/pii/S0957417407004137 |
| [7] | Gao, G.; Liu, F.; San, H.; Wu, X.; Wang, W., Hybrid optimal kinematic parameter identification for an industrial robot based on BPNN-PSO, Complexity, 2018, 1-11 (2018), URL https://www.hindawi.com/journals/complexity/2018/4258676/ |
| [8] | Cheng, M.-Y.; Tsai, H.-C.; Sudjono, E., Evolutionary fuzzy hybrid neural network for dynamic project success assessment in construction industry, Autom. Constr., 21, 46-51 (2012), URL https://linkinghub.elsevier.com/retrieve/pii/S0926580511000951 |
| [9] | Sen, D.; Roy, A.; Bhattacharya, A.; Banerjee, D.; Bhattacharjee, C., Development of a knowledge based hybrid neural network (KBHNN) for studying the effect of diafiltration during ultrafiltration of whey, Desalination, 273, 1, 168-178 (2011), URL https://linkinghub.elsevier.com/retrieve/pii/S0011916410007538 |
| [10] | Yang, S.; Lu, M.; Xue, H., Hybrid partial least squares and neural network approach for short-term electrical load forecasting, J. Control Theory Appl., 6, 1, 93-96 (2008), URL http://link.springer.com/10.1007/s11768-008-6208-x |
| [11] | Laursen, S. O.; Webb, D.; Ramirez, W. F., Dynamic hybrid neural network model of an industrial fed-batch fermentation process to produce foreign protein, Comput. Chem. Eng., 31, 3, 163-170 (2007), URL http://linkinghub.elsevier.com/retrieve/pii/S0098135406001311 |
| [12] | Psichogios, D. C.; Ungar, L. H., A hybrid neural network-first principles approach to process modeling, AIChE J., 38, 10, 1499-1511 (1992), URL http://doi.wiley.com/10.1002/aic.690381003 |
| [13] | Gutierrez, P. A.; Hervas Martinez, C., Hybrid artificial neural networks: Models, algorithms and data, (Advances in Computational Intelligence - 11th International Work-Conference on Artificial Neural Networks, IWANN 2011, Torremolinos-Málaga, Spain, June 8-10, 2011, Proceedings, Part II (2011), Springer), pp. 177-184 |
| [14] | Wermter, S.; Sun, R., (An Overview of Hybrid Neural Systems. An Overview of Hybrid Neural Systems, Lecture Notes in Computer Science (2000), Springer) |
| [15] | Martius, G.; Lampert, C. H., Extrapolation and learning equations (2016), arXiv:1610.02995 [cs] arXiv:1610.02995. URL http://arxiv.org/abs/1610.02995 |
| [16] | Sjöberg, J.; Zhang, Q.; Ljung, L.; Benveniste, A.; Delyon, B.; Glorennec, P.-Y.; Hjalmarsson, H.; Juditsky, A., Nonlinear black-box modeling in system identification: a unified overview, Automatica, 31, 12, 1691-1724 (1995), URL https://linkinghub.elsevier.com/retrieve/pii/0005109895001208 · Zbl 0846.93018 |
| [17] | Billings, S. A.; Jamaluddin, H. B.; Chen, S., Properties of neural networks with applications to modelling non-linear dynamical systems, Internat. J. Control, 55, 1, 193-224 (1992), URL http://www.tandfonline.com/doi/abs/10.1080/00207179208934232 · Zbl 0742.93001 |
| [18] | Körner, A.; Winkler, S.; Breitenecker, F., Possibilities in state event modelling of hybrid systems, SNE Simul. Notes Eur., 28, 3, 109-111 (2018), URL https://www.sne-journal.org/10429 |
| [19] | Mehlhase, A., Konzepte für die Modellierung und Simulation Strukturvariabler Modelle, 255 (2015), Technische Universität Berlin, (Ph.D. thesis) |
| [20] | Goebel, R.; Sanfelice, R.; Teel, A., Hybrid Dynamical Systems: Modeling, Stability, and Robustness (2012), Princeton University Press: Princeton University Press Princeton, New Jersey · Zbl 1241.93002 |
| [21] | Kwiatkowski, A.; Lichtenberg, G.; Schild, A., Event prediction for switching linear systems with time varying thresholds using orthogonal functions, (Maler, O.; Pnueli, A., Hybrid Systems: Computation and Control, Vol. 2623 (2003), Springer Berlin Heidelberg), 314-327, URL http://link.springer.com/10.1007/3-540-36580-X_24 · Zbl 1032.93533 |
| [22] | Zeigler, B. P.; Praehofer, H.; Kim, T. G., Theory of Modelling and Simulation: Integrating Discrete Event and Continuous Complex Dynamic Systems (2000), Academic Press |
| [23] | T.A. Henzinger, The theory of hybrid automata, in: Proceedings of the 11th Annual IEEE Symposium on Logic in Computer Science, 1996, pp. 278-292. · Zbl 0959.68073 |
| [24] | Winkler, S.; Körner, A.; Bicher, M.; Breitenecker, F., A comparison of different modelling and simulation approaches for hybrid dynamical systems, (UKSim-AMSS 19th International Conference on Computer Modelling and Simulation (UKSim) (2017), IEEE), 97-102, URL https://ieeexplore.ieee.org/document/8359050/ |
| [25] | Körner, A., Mathematical Characterisation of State events in Hybrid Modelling (2015), Technische Universität Wien, (Ph.D. thesis) |
| [26] | Carloni, L. P.; Passerone, R.; Pinto, A.; Angiovanni-Vincentelli, A. L., Languages and tools for hybrid systems design, Found. Trends Electron. Des. Autom., 1, 1, 1-193 (2006), URL http://www.nowpublishers.com/article/Details/EDA-001 · Zbl 1107.68385 |
| [27] | Torrisi, F.; Bemporad, A., HYSDEL—A tool for generating computational hybrid models for analysis and synthesis problems, IEEE Trans. Control Syst. Technol., 12, 2, 235-249 (2004), URL http://ieeexplore.ieee.org/document/1281781/ |
| [28] | Bemporad, A.; Di Cairano, S.; Ferrari-Trecate, G.; Kvasnica, M.; Morari, M.; Paoletti, S., Tools for modeling, simulation, control, and verification of piecewise affine systems, (Lunze, J.; Lamnabhi-Lagarrigue, F., Handbook of Hybrid Systems Control (2009), Cambridge University Press), 297-324, URL https://www.cambridge.org/core/product/identifier/CBO9780511807930A020/type/book_part |
| [29] | Kvasnica, M., Efficient Software Tools for Control and Analysis of Hybrid Systems (2008), ETH Zurich: ETH Zurich ETH Zurich, Physikstrasse 3, 8092 Zurich, Switzerland, URL https://www.uiam.sk/assets/publication_info.php?id_pub=747 |
| [30] | Lofberg, J., YALMIP : a toolbox for modeling and optimization in MATLAB, (2004 IEEE International Conference on Robotics and Automation (IEEE Cat. No.04CH37508) (2004)), 284-289 |
| [31] | Ferrari-Trecate, G.; al, e., A clustering technique for the identification of piecewise affine systems, Automatica, 39, 205-217 (2003) · Zbl 1011.93508 |
| [32] | Canty, N.; O’Mahony, T.; Cychowski, M. T., An output error algorithm for piecewise affine system identification, Control Eng. Pract., 20, 4, 444-452 (2012), URL https://linkinghub.elsevier.com/retrieve/pii/S096706611100253X |
| [33] | Haykin, S., Neural Networks and Learning Machines (2009), Prentice Hall, OCLC: ocn237325326 |
| [34] | Giles, C. L.; Maxwell, T., Learning, invariance, and generalization in high-order neural networks., Appl. Opt., 26, 23, 4972-4978 (1987) |
| [35] | Shin, Y.; Ghosh, J., The pi-sigma network: an efficient higher-order neural network for pattern classification and function approximation, (IJCNN-91-Seattle International Joint Conference on Neural Networks, Vol. i (1991)), 13-18, vol.1 |
| [36] | Epitropakis, M.; Plagianakos, V.; Vrahatis, M., Hardware-friendly higher-order neural network training using distributed evolutionary algorithms, Appl. Soft Comput., 10, 2, 398-408 (2010), URL https://linkinghub.elsevier.com/retrieve/pii/S1568494609001264 |
| [37] | Sahoo, S. S.; Lampert, C. H.; Martius, G., Learning equations for extrapolation and control (2018), arXiv:1806.07259 [cs, stat]. arXiv:1806.07259. URL http://arxiv.org/abs/1806.07259 |
| [38] | Števek, J.; Szücs, A.; Kvasnica, M.; Fikar, M.; Kozák, t., Two steps piecewise affine identification of nonlinear systems, Arch. Control Sci., 22, 4, 371-388 (2012), URL http://journals.pan.pl/dlibra/publication/97660/edition/84247/content · Zbl 1270.93038 |
| [39] | Norgaard, M.; Ravn, O.; Poulsen, N. K., NNSYSID-toolbox for system identification with neural networks, Math. Comput. Model. Dyn. Syst., 8, 1, 1-20 (2002), URL http://www.tandfonline.com/doi/abs/10.1076/mcmd.8.1.1.8342 |
| [40] | Bar-Sinai, Y.; Hoyer, S.; Hickey, J.; Brenner, M. P., Learning data-driven discretizations for partial differential equations, Proc. Natl. Acad. Sci., Article 201814058 pp. (2019), URL http://www.pnas.org/lookup/doi/10.1073/pnas.1814058116 · Zbl 1431.65195 |
| [41] | Chen, R. T.Q.; Rubanova, Y.; Bettencourt, J.; Duvenaud, D., Neural ordinary differential equations (2018), arXiv:1806.07366 [cs, stat]. arXiv:1806.07366. URL http://arxiv.org/abs/1806.07366 |
| [42] | Lagaris, I. E.; Likas, A.; Fotiadis, D. I., Artificial neural networks for solving ordinary and partial differential equations, IEEE Trans. Neural Netw., 9, 5, 987-1000 (1998) |
| [43] | G. Taylor, R. Burmeister, Z. Xu, B. Singh, A. Patel, T. Goldstein, Training neural networks without gradients: A scalable ADMM approach, in: Proceedings of the 33rd International Conference on Machine Learning, 2016, p. 10. |
| [44] | Körner, A.; Breitenecker, F., State events and structural-dynamic systems: Definition of ARGESIM benchmark C21, SNE Simul. Notes Eur., 26, 2, 117-128 (2016), URL https://www.sne-journal.org/10339 |
| [45] | Shukla, D.; Paul, F. W., Computationally efficient control of nonlinear systems using orthonormal activation function based neural networks, IFAC Proc. Vol., 29, 1, 4995-5000 (1996), URL https://linkinghub.elsevier.com/retrieve/pii/S1474667017584724 |
| [46] | Števek, J.; Szucs, A.; Kvasnica, M.; Kozák, S.; Fikar, M., Smart technique for identifying hybrid systems, (2012 IEEE 10th International Symposium on Applied Machine Intelligence and Informatics (SAMI) (2012), IEEE), 383-388, URL http://ieeexplore.ieee.org/document/6208995/ |
| [47] | J. Števek, . Kozák, Matlab toolbox for PWA identification of nonlinear systems, in: Proceedings of the 18th International Conference on Process Control, Fikar, M., Kvasnica, M., 2011, pp. 111-118. |
| [48] | Kozák, S.; tevek, J., Improved piecewise linear approximation of nonlinear functions in hybrid control, IFAC Proc. Vol., 44, 1, 14982-14987 (2011), URL https://linkinghub.elsevier.com/retrieve/pii/S1474667016460374 |
| [49] | Benzaouia, A., Introduction to switched systems, (Saturated Switching Systems (2012), Springer London), 77-94 |
| [50] | Nielsen, M. A., Neural Networks and Deep Learning (2015), Determination Press, http://neuralnetworksanddeeplearning.com, last visted 20.07.2020 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
