Muhammad Zakwan | EPFL Graph Search

Muhammad Zakwan is a doctoral assistant in the Dependable Control and Decision group (DECODE) at École Polytechnique Fédérale de Lausanne (EPFL). He is also a member of the National Centre of Competence in Research (NCCR) Automation. Zakwan holds an Electrical and Electronics Engineering degree from Bilkent University(Turkey) and a Bachelor of Science in Electrical Engineering from the Pakistan Institute of Engineering and Applied Sciences (Pakistan).

Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach

Giancarlo Ferrari Trecate, Luca Furieri, Clara Lucía Galimberti, Muhammad Zakwan

Large-scale cyber-physical systems require that control policies are distributed, that is, that they only rely on local real-time measurements and communication with neighboring agents. Optimal Distributed Control (ODC) problems are, however, highly intractable even in seemingly simple cases. Recent work has thus proposed training Neural Network (NN) distributed controllers. A main challenge of NN controllers is that they are not dependable during and after training, that is, the closed-loop system may be unstable, and the training may fail due to vanishing gradients. In this paper, we address these issues for networks of nonlinear port-Hamiltonian (pH) systems, whose modeling power ranges from energy systems to non-holonomic vehicles and chemical reactions. Specifically, we embrace the compositional properties of pH systems to characterize deep Hamiltonian control policies with built-in closed-loop stability guarantees — irrespective of the interconnection topology and the chosen NN parameters. Furthermore, our setup enables leveraging recent results on well-behaved neural ODEs to prevent the phenomenon of vanishing gradients by design. Numerical experiments corroborate the dependability of the proposed architecture, while matching the performance of general neural network policies.

2022

Neural Energy Casimir Control for Port-Hamiltonian Systems

Giancarlo Ferrari Trecate, Liang Xu, Muhammad Zakwan

The energy Casimir method is an effective controller design approach to stabilize port-Hamiltonian systems at a desired equilibrium. However, its application relies on the availability of suitable Casimir and Lyapunov functions, whose computation are generally intractable. In this paper, we propose a neural network-based framework to learn these functions. We show how to achieve equilibrium assignment by adding suitable regularization terms in the training cost. We also propose a parameterization of Casimir functions for reducing the training complexity. Moreover, the distance between the equilibrium of the learned Lyapunov function and the desired equilibrium is analyzed, which indicates that for small suboptimality gaps, the distance decreases linearly with respect to the training loss. Our methods are backed up by simulations on a pendulum system.

2022

Dwell-time based stability analysis and L-2 control of LPV systems with piecewise constant parameters and delay

Saeed Ahmed, Muhammad Zakwan

Dwell-time based stability conditions for a class of LPV systems with piecewise constant parameters under time-varying delay are derived using clock-dependent Lyapunov-Krasovskii functional. Sufficient synthesis conditions for clock-dependent gain-scheduled state-feedback controllers ensuring L-2-performance are also provided. Several numerical and practical examples, to illustrate the efficacy of the results, are given. (C) 2020 Elsevier B.V. All rights reserved.

ELSEVIER2020