Neural network quaternion-based controller for port-Hamiltonian system

Authors

Fawaz E. Alsaadi, Fernando E. Serrano, Larissa M. Batrancea

Abstract

In this research article, a control approach for port-Hamiltonian PH systems based in a neural network (NN) quaternion-based control strategy is presented. First, the dynamics is converted by the implementation of a Poisson bracket in order to facilitate the mathematical model in order to obtain a feasible formulation for the controller design based on quaternion NNs. In this study, two controllers for this kind of of system are presented: the first one consists in the controller design for a PH system about its equilibrium points taking into consideration the position and momentum. This mean is achieved by dividing the quaternion neural controller into scalar and vectorial parts to facilitate the controller derivation by selecting a Lyapunov functional. The second control strategy consists in designing the trajectory tracking controller, in which a reference moment is considered in order to drive this variable to the final desired position according to a reference variable; again, a Lyapunov functional is implemented to obtain the desired control law. It is important to mention that both controllers take into advantage that the energy consideration and that the representation of many physical systems could be implemented in quaternions. Besides the angular velocity, trajectory tracking of a three-phase induction motor is presented as a third numerical experiment. Two numerical experiments are presented to validate the theoretical results evinced in this study. Finally, a discussion and conclusion section is provided.

Citation

• Journal: Demonstratio Mathematica
• Year: 2024
• Volume: 57
• Issue: 1
• Pages:
• Publisher: Walter de Gruyter GmbH
• DOI: 10.1515/dema-2023-0131

BibTeX

@article{Alsaadi_2024,
  title={{Neural network quaternion-based controller for port-Hamiltonian system}},
  volume={57},
  ISSN={2391-4661},
  DOI={10.1515/dema-2023-0131},
  number={1},
  journal={Demonstratio Mathematica},
  publisher={Walter de Gruyter GmbH},
  author={Alsaadi, Fawaz E. and Serrano, Fernando E. and Batrancea, Larissa M.},
  year={2024}
}

Download the bib file

References

• Batrancea, L. M., Nichita, A., Balcı, M. A. & Akgüller, Ö. Empirical investigation on how wellbeing-related infrastructure shapes economic growth: Evidence from the European Union regions. PLOS ONE vol. 18 e0283277 (2023) – 10.1371/journal.pone.0283277
• Batrancea, L. M. The Hard Worker, the Hard Earner, the Young and the Educated: Empirical Study on Economic Growth across 11 CEE Countries. Sustainability vol. 15 15996 (2023) – 10.3390/su152215996
• Khan, A. et al. Computational and topological properties of neural networks by means of graph-theoretic parameters. Alexandria Engineering Journal vol. 66 957–977 (2023) – 10.1016/j.aej.2022.11.001
• Famelis, I., Donas, A. & Galanis, G. Comparative study of FeedForward and Radial Basis Function Neural Networks for solving an Environmental Boundary Value Problem. Results in Applied Mathematics vol. 16 100344 (2022) – 10.1016/j.rinam.2022.100344
• Chen, Y., Zhang, N. & Yang, J. A survey of recent advances on stability analysis, state estimation and synchronization control for neural networks. Neurocomputing vol. 515 26–36 (2023) – 10.1016/j.neucom.2022.10.020
• Benfenati, A. & Marta, A. A singular Riemannian geometry approach to deep neural networks II. Reconstruction of 1-D equivalence classes. Neural Networks vol. 158 344–358 (2023) – 10.1016/j.neunet.2022.11.026
• Coulibaly, S., Kamsu-Foguem, B., Kamissoko, D. & Traore, D. Deep Convolution Neural Network sharing for the multi-label images classification. Machine Learning with Applications vol. 10 100422 (2022) – 10.1016/j.mlwa.2022.100422
• Capanema, C. G. S., de Oliveira, G. S., Silva, F. A., Silva, T. R. M. B. & Loureiro, A. A. F. Combining recurrent and Graph Neural Networks to predict the next place’s category. Ad Hoc Networks vol. 138 103016 (2023) – 10.1016/j.adhoc.2022.103016
• Chen, Y., Xue, Y., Yang, X. & Zhang, X. A direct analysis method to Lagrangian global exponential stability for quaternion memristive neural networks with mixed delays. Applied Mathematics and Computation vol. 439 127633 (2023) – 10.1016/j.amc.2022.127633
• Chen, S. et al. Global Mittag–Leffler stability and synchronization of discrete-time fractional-order delayed quaternion-valued neural networks. Neurocomputing vol. 511 290–298 (2022) – 10.1016/j.neucom.2022.09.035
• Song, Q., Yang, L., Liu, Y. & Alsaadi, F. E. Stability of quaternion-valued neutral-type neural networks with leakage delay and proportional delays. Neurocomputing vol. 521 191–198 (2023) – 10.1016/j.neucom.2022.12.009
• Shang, W., Zhang, W., Chen, D. & Cao, J. New criteria of finite time synchronization of fractional-order quaternion-valued neural networks with time delay. Applied Mathematics and Computation vol. 436 127484 (2023) – 10.1016/j.amc.2022.127484
• Song, Q., Zeng, R., Zhao, Z., Liu, Y. & Alsaadi, F. E. Mean-square stability of stochastic quaternion-valued neural networks with variable coefficients and neutral delays. Neurocomputing vol. 471 130–138 (2022) – 10.1016/j.neucom.2021.11.033
• Peng, T., Lu, J., Tu, Z. & Lou, J. Finite-time stabilization of quaternion-valued neural networks with time delays: An implicit function method. Information Sciences vol. 613 747–762 (2022) – 10.1016/j.ins.2022.09.014
• Brevis, I., Muga, I. & van der Zee, K. G. Neural control of discrete weak formulations: Galerkin, least squares & minimal-residual methods with quasi-optimal weights. Computer Methods in Applied Mechanics and Engineering vol. 402 115716 (2022) – 10.1016/j.cma.2022.115716
• Alsaade, F. W., Yao, Q., Al-zahrani, M. S., Alzahrani, A. S. & Jahanshahi, H. Neural-based fixed-time attitude tracking control for space vehicle subject to constrained outputs. Advances in Space Research vol. 71 3588–3599 (2023) – 10.1016/j.asr.2022.07.081
• Jahanshahi, H., Yao, Q., Ijaz Khan, M. & Moroz, I. Unified neural output-constrained control for space manipulator using tan-type barrier Lyapunov function. Advances in Space Research vol. 71 3712–3722 (2023) – 10.1016/j.asr.2022.11.015
• Zhou, G. & Tan, D. Review of nuclear power plant control research: Neural network-based methods. Annals of Nuclear Energy vol. 181 109513 (2023) – 10.1016/j.anucene.2022.109513
• Thanh, P. N. N. & Anh, H. P. H. Advanced neural control technique for autonomous underwater vehicles using modified integral barrier Lyapunov function. Ocean Engineering vol. 266 112842 (2022) – 10.1016/j.oceaneng.2022.112842
• Zeng, D., Liu, Z., Chen, C. L. P., Zhang, Y. & Wu, Z. Decentralized adaptive neural asymptotic control of switched nonlinear interconnected systems with predefined tracking performance. Neurocomputing vol. 510 37–47 (2022) – 10.1016/j.neucom.2022.08.062
• De Vleeschauwer, F. et al. A dynamic control system for aerobic granular sludge reactors treating high COD/P wastewater, using pH and DO sensors. Journal of Water Process Engineering vol. 33 101065 (2020) – 10.1016/j.jwpe.2019.101065
• Bayili, G., Nicaise, S. & Silga, R. Rational energy decay rate for the wave equation with delay term on the dynamical control. Journal of Mathematical Analysis and Applications vol. 495 124693 (2021) – 10.1016/j.jmaa.2020.124693
• Kyriakides, A.-S., Papadopoulos, A. I., Seferlis, P. & Hassan, I. Dynamic modelling and control of single, double and triple effect absorption refrigeration cycles. Energy vol. 210 118529 (2020) – 10.1016/j.energy.2020.118529
• Shi, X., Cheng, Y., Yin, C., Huang, X. & Zhong, S. Design of adaptive backstepping dynamic surface control method with RBF neural network for uncertain nonlinear system. Neurocomputing vol. 330 490–503 (2019) – 10.1016/j.neucom.2018.11.029
• Zhou, Z., Tong, D., Chen, Q., Zhou, W. & Xu, Y. Adaptive NN control for nonlinear systems with uncertainty based on dynamic surface control. Neurocomputing vol. 421 161–172 (2021) – 10.1016/j.neucom.2020.09.026
• Feng, S., Kawano, Y., Cucuzzella, M. & Scherpen, J. M. A. Output consensus control for linear port-Hamiltonian systems. IFAC-PapersOnLine vol. 55 230–235 (2022) – 10.1016/j.ifacol.2022.11.057
• Brugnoli, A., Rashad, R. & Stramigioli, S. Dual field structure-preserving discretization of port-Hamiltonian systems using finite element exterior calculus. Journal of Computational Physics vol. 471 111601 (2022) – 10.1016/j.jcp.2022.111601
• Mora, L. A. & Morris, K. Exponential Decay Rate of port-Hamiltonian Systems with one side Boundary Damping. IFAC-PapersOnLine vol. 55 400–405 (2022) – 10.1016/j.ifacol.2022.11.086
• Tefera, D. T., Dubljevic, S. & Prasad, V. A Port Hamiltonian approach to dynamical chemical process systems network modeling and analysis. Chemical Engineering Science vol. 261 117907 (2022) – 10.1016/j.ces.2022.117907
• Jäschke, J., Skrepek, N. & Ehrhardt, M. Mixed-dimensional geometric coupling of port-Hamiltonian systems. Applied Mathematics Letters vol. 137 108508 (2023) – 10.1016/j.aml.2022.108508
• Pham, T. H., Vu, N. M. T., Prodan, I. & Lefèvre, L. A combined Control by Interconnection—Model Predictive Control design for constrained Port-Hamiltonian systems. Systems & Control Letters vol. 167 105336 (2022) – 10.1016/j.sysconle.2022.105336
• Wei, W., Yu, J., Wang, L., Hu, C. & Jiang, H. Fixed/Preassigned-time synchronization of quaternion-valued neural networks via pure power-law control. Neural Networks vol. 146 341–349 (2022) – 10.1016/j.neunet.2021.11.023
• Shu, J., Wu, B., Xiong, L., Wu, T. & Zhang, H. Stochastic stabilization of Markov jump quaternion-valued neural network using sampled-data control. Applied Mathematics and Computation vol. 400 126041 (2021) – 10.1016/j.amc.2021.126041
• Li, R. & Cao, J. Dissipativity and synchronization control of quaternion-valued fuzzy memristive neural networks: Lexicographical order method. Fuzzy Sets and Systems vol. 443 70–89 (2022) – 10.1016/j.fss.2021.10.015
• Shu, J., Wu, B. & Xiong, L. Stochastic stability criteria and event-triggered control of delayed Markovian jump quaternion-valued neural networks. Applied Mathematics and Computation vol. 420 126904 (2022) – 10.1016/j.amc.2021.126904
• Li, H.-L., Hu, C., Zhang, L., Jiang, H. & Cao, J. Complete and finite-time synchronization of fractional-order fuzzy neural networks via nonlinear feedback control. Fuzzy Sets and Systems vol. 443 50–69 (2022) – 10.1016/j.fss.2021.11.004
• Zhang, R. & Gao, L. The Brushless DC motor control system Based on neural network fuzzy PID control of power electronics technology. Optik vol. 271 169879 (2022) – 10.1016/j.ijleo.2022.169879
• Wu, Z., Jiang, B. & Gao, Q. State estimation and fuzzy sliding mode control of nonlinear Markovian jump systems via adaptive neural network. Journal of the Franklin Institute vol. 359 8974–8990 (2022) – 10.1016/j.jfranklin.2022.09.031
• Razzaghian, A. A fuzzy neural network-based fractional-order Lyapunov-based robust control strategy for exoskeleton robots: Application in upper-limb rehabilitation. Mathematics and Computers in Simulation vol. 193 567–583 (2022) – 10.1016/j.matcom.2021.10.022
• Yang, M., Sheng, Z., Yin, G. & Wang, H. A recurrent neural network based fuzzy sliding mode control for 4-DOF ROV movements. Ocean Engineering vol. 256 111509 (2022) – 10.1016/j.oceaneng.2022.111509
• Wan, J., Jiang, Q., Liao, L., Wu, S. & Wang, P. A neural-network based variable universe fuzzy control method for power and axial power distribution control of large pressurized water reactors. Annals of Nuclear Energy vol. 175 109241 (2022) – 10.1016/j.anucene.2022.109241
• Toledo, J., Wu, Y., Ramirez, H. & Gorrec, Y. L. Observer design for 1-D boundary controlled port-Hamiltonian systems with different boundary measurements. IFAC-PapersOnLine vol. 55 95–100 (2022) – 10.1016/j.ifacol.2022.10.383
• Reyes-Báez, R., van der Schaft, A. & Jayawardhana, B. Virtual contractivity-based control of fully-actuated mechanical systems in the port-Hamiltonian framework. Automatica vol. 141 110275 (2022) – 10.1016/j.automatica.2022.110275
• Ponce, C., Ramirez, H., Gorrec, Y. L. & Vargas, F. A comparative study of reduced model based boundary control design for linear port Hamiltonian systems. IFAC-PapersOnLine vol. 55 107–112 (2022) – 10.1016/j.ifacol.2022.10.385
• Ramirez, H., Gorrec, Y. L. & Maschke, B. Boundary controlled irreversible port-Hamiltonian systems. Chemical Engineering Science vol. 248 117107 (2022) – 10.1016/j.ces.2021.117107
• Maschke, B., Philipp, F., Schaller, M., Worthmann, K. & Faulwasser, T. Optimal control of thermodynamic port-Hamiltonian Systems. IFAC-PapersOnLine vol. 55 55–60 (2022) – 10.1016/j.ifacol.2022.11.028
• Brugnoli, A., Haine, G. & Matignon, D. Explicit structure-preserving discretization of port-Hamiltonian systems with mixed boundary control. IFAC-PapersOnLine vol. 55 418–423 (2022) – 10.1016/j.ifacol.2022.11.089
• Malzer, T., Ecker, L. & Schöberl, M. Energy-based Control and Observer Design for higher-order infinite-dimensional Port-Hamiltonian Systems. IFAC-PapersOnLine vol. 54 44–51 (2021) – 10.1016/j.ifacol.2021.11.053
• Malzer, T., Toledo, J., Gorrec, Y. L. & Schöberl, M. Energy-Based In-Domain Control and Observer Design for Infinite-Dimensional Port-Hamiltonian Systems. IFAC-PapersOnLine vol. 54 468–475 (2021) – 10.1016/j.ifacol.2021.06.104
• Schaller, M., Philipp, F., Faulwasser, T., Worthmann, K. & Maschke, B. Control of port-Hamiltonian systems with minimal energy supply. European Journal of Control vol. 62 33–40 (2021) – 10.1016/j.ejcon.2021.06.017
• Malzer, T., Rams, H. & Schöberl, M. On structural invariants in the energy-based in-domain control of infinite-dimensional port-Hamiltonian systems. Systems & Control Letters vol. 145 104778 (2020) – 10.1016/j.sysconle.2020.104778
• Macchelli, A., Gorrec, Y. L. & Ramirez, H. Asymptotic Stabilisation of Distributed Port-Hamiltonian Systems by Boundary Energy-Shaping Control. IFAC-PapersOnLine vol. 48 488–493 (2015) – 10.1016/j.ifacol.2015.05.143
• Haddad, W. M., Rajpurohit, T. & Jin, X. Energy-based feedback control for stochastic port-controlled Hamiltonian systems. Automatica vol. 97 134–142 (2018) – 10.1016/j.automatica.2018.07.031
• Lamoline, F. Passivity of boundary controlled and observed stochastic port-Hamiltonian systems subject to multiplicative and input noise. European Journal of Control vol. 62 41–46 (2021) – 10.1016/j.ejcon.2021.06.010
• Hamada, K., Borja, P., Fujimoto, K., Maruta, I. & Scherpen, J. M. A. On Passivity-Based High-Order Compensators for Mechanical Port-Hamiltonian Systems Without Velocity Measurements. IFAC-PapersOnLine vol. 54 287–292 (2021) – 10.1016/j.ifacol.2021.10.367
• Ramirez, H., Gorrec, Y. L., Maschke, B. & Couenne, F. Passivity Based Control of Irreversible Port Hamiltonian Systems. IFAC Proceedings Volumes vol. 46 84–89 (2013) – 10.3182/20130714-3-fr-4040.00012
• Nishida, G., Yamaguchi, K. & Sakamoto, N. Optimality of passivity-based controls for distributed port-Hamiltonian systems. IFAC Proceedings Volumes vol. 46 146–151 (2013) – 10.3182/20130904-3-fr-2041.00193
• Sakata, N., Fujimoto, K. & Maruta, I. On trajectory tracking control of simple port-Hamiltonian systems based on passivity based sliding mode control. IFAC-PapersOnLine vol. 54 38–43 (2021) – 10.1016/j.ifacol.2021.11.052
• Castaños, F. & Gromov, D. Passivity-based control of implicit port-Hamiltonian systems with holonomic constraints. Systems & Control Letters vol. 94 11–18 (2016) – 10.1016/j.sysconle.2016.04.004
• Pan, J. & Zhang, Z. Finite-time synchronization for delayed complex-valued neural networks via the exponential-type controllers of time variable. Chaos, Solitons & Fractals vol. 146 110897 (2021) – 10.1016/j.chaos.2021.110897
• Feng, J., Chai, Y. & Xu, C. A novel neural network to nonlinear complex-variable constrained nonconvex optimization. Journal of the Franklin Institute vol. 358 4435–4457 (2021) – 10.1016/j.jfranklin.2021.02.029
• Song, Q., Yu, Q., Zhao, Z., Liu, Y. & Alsaadi, F. E. Dynamics of complex-valued neural networks with variable coefficients and proportional delays. Neurocomputing vol. 275 2762–2768 (2018) – 10.1016/j.neucom.2017.11.041
• Li, W. et al. Regenerative braking control strategy for pure electric vehicles based on fuzzy neural network. Ain Shams Engineering Journal vol. 15 102430 (2024) – 10.1016/j.asej.2023.102430
• Kadak, U. & Coroianu, L. Integrating multivariate fuzzy neural networks into fuzzy inference system for enhanced decision making. Fuzzy Sets and Systems vol. 470 108668 (2023) – 10.1016/j.fss.2023.108668
• El-Nagar, A. M., El-Bardini, M. & Khater, A. A. Recurrent general type-2 fuzzy neural networks for nonlinear dynamic systems identification. ISA Transactions vol. 140 170–182 (2023) – 10.1016/j.isatra.2023.06.003
• Nguyen, S. & Turski, Ł. A. Examples of the Dirac approach to dynamics of systems with constraints. Physica A: Statistical Mechanics and its Applications vol. 290 431–444 (2001) – 10.1016/s0378-4371(00)00449-0
• Chandre, C. Incomplete Dirac reduction of constrained Hamiltonian systems. Annals of Physics vol. 361 1–13 (2015) – 10.1016/j.aop.2015.06.011
• Borja, P., Ortega, R. & Nuño, E. New results on PID passivity-based controllers for port-Hamiltonian systems. IFAC-PapersOnLine vol. 51 175–180 (2018) – 10.1016/j.ifacol.2018.06.049
• R. Krishnan, Electric Motor Drives, Modeling, Analysis and Control, Prentice Hall, New Delhi, 2006.