Echo State Network-Based Decentralized Control of Continuous-Time Nonlinear Large-Scale Interconnected Systems

Zhang, Huaguang; Liu, Chong; Su, Hanguang; Zhang, Kun

doi:10.1109/tsmc.2019.2958484

Cited by 66 publications

(14 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the uncertainties, such as the unknown gravitational torque imposed on the robotic manipulators, it is impractical to acquire the precise system model. With the development of the intelligent algorithms, 28‐33 the control problem of the systems with uncertainties has been well solved. In this article, we use the fuzzy logic systems (FLSs) to approximate the unknown function.…”

Section: Preliminaries and Problem Statementmentioning

confidence: 99%

Fixed‐time cooperative control for robotic manipulators with motion constraints using unified transformation function

Liu

Zhang

Wang

et al. 2021

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

This article investigates the fixed‐time consensus tracking control problem for multiagent systems composed of uncertain l‐link robotic manipulators with position and velocity constraints. Fuzzy logic systems are employed to model the uncertain dynamic of the robotic manipulators. In order to cope with the asymmetric yet time‐varying constraints, a nonlinear transformation function is introduced. With the help of the nonlinear transformation function, the original constrained manipulator systems are converted into the equivalent systems without constraint. As long as the boundedness of the state variables in the transformed systems is ensured, the constraint conditions of the original systems are not violated. Then, a fixed‐time adaptive fuzzy control scheme is developed. Under the proposed control method, the consensus tracking error can converge into a small neighborhood of origin in fixed‐time, and all the signals in the closed‐loop systems are bounded. Meanwhile, the motion constraints are not violated all the time. Specially, in view of the property of nonlinear transformation function, it is not necessary to change the control structure when the systems are subjected to no state constraint. Finally, a simulation is presented to illustrate the feasibility and effectiveness of implementing the proposed control algorithms.

show abstract

Section: Preliminaries and Problem Statementmentioning

confidence: 99%

Fixed‐time cooperative control for robotic manipulators with motion constraints using unified transformation function

Liu

Zhang

Wang

et al. 2021

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

show abstract

“…Jordanou et al [13] implemented ESNs into the practical nonlinear MPC framework developed by Plucenio et al [14] by applying the analytically computed gradient from the ESN model to the predictive model. Zhang et al [15] applied an ESN for the decentralized control problem of continuous-time nonlinear interconnected systems. They treated the interconnected terms between the subsystems as the disturbances added to the system dynamics.…”

Section: Related Workmentioning

confidence: 99%

Echo State Network Based Model Predictive Control for Active Vibration Control of Hybrid Electric Vehicle Powertrains

Ogawa

Takahashi

2021

Applied Sciences

View full text Add to dashboard Cite

Reservoir computing refers to a computational framework based on recurrent neural networks that can process time-series data. In an echo state network (ESN), which is a type of reservoir computing framework, the reservoir consists of a recursive network of artificial neurons with nonlinear activation functions. A model predictive control (MPC) technique can determine the control signals by solving the optimization problem of a system using the finite-time domain of each control period. However, real-time optimization cannot be achieved unless the optimal control problem can be solved within the next control period. To overcome this limitation, we propose a new control method based on MPC that explicitly incorporates the predicted disturbance of a time-varying trajectory using ESN to achieve the active vibration control of hybrid electric vehicle (HEV) powertrains. Once the ESN has been trained, the associated MPC explicitly satisfies the constraints over a moving horizon without further training. Instead of completing the real-time optimization within the control period, ESN predicts the future disturbance and applies it to the MPC in the future control period. Based on the predicted future disturbance, the system calculates the optimal control signals required for the future. Thus, real-time control can be realized because the optimal signals are determined before the subsequent control period occurs. The proposed method can be implemented in MPC even if the control period is too short to optimize as long as the disturbance can be reasonably measured and predicted. In this study, the simulation approach was demonstrated using the engine start condition in an HEV powertrain. The importance of this study is that the limitation of MPC relevant to real-time optimization can be relaxed by applying our proposed method.

show abstract

“…Signals and data are transmitted and exchanged through the communication network, avoiding the laying of point‐to‐point dedicated lines, and can realize resource sharing, remote operation and control, and increase the flexibility and reliability of the system. NCSs have been widely used in many critical infrastructure fields, such as networked supply chain systems, 5 unmanned marine vehicle, 6 offshore platform, 7 nonlinear large‐scale systems 8 . However, while networked control systems have many advantages, several challenging issues have also been introduced 9 .…”

Section: Introductionmentioning

confidence: 99%

Observer‐based adaptive event‐triggered PID control for networked systems under aperiodic DoS attacks

Peng

2021

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

In the present article, the observer‐based proportional integral derivative (PID) security control problem is investigated for a networked system subject to aperiodic denial‐of‐service (DoS) attacks. First, by carefully modeling cyberattacks as aperiodic DoS attacks, a suitable switching observer is constructed to solve the state reconstruction problem. Second, to improve the utilization of network resources while resisting the impact of attacks, an adaptive event‐triggered communication protocol is introduced, whose trigger parameters can be dynamically adjusted according to the set learning rules. Third, based on the above analysis, an error switching system model is established, which describes the impact of the adaptive triggered protocol and aperiodic attacks in a unified framework. Then, by employing the switched system analysis method, sufficient conditions are obtained to ensure the error switched system being asymptotically stable. Furthermore, by means of orthogonal decomposition technique, a codesign method of the observer gains, triggered parameter, and PID controller gains is given. Finally, a simulation example is provided to illustrate the efficiency and applicability of the obtained results.

show abstract

Echo State Network-Based Decentralized Control of Continuous-Time Nonlinear Large-Scale Interconnected Systems

Cited by 66 publications

References 43 publications

Fixed‐time cooperative control for robotic manipulators with motion constraints using unified transformation function

Fixed‐time cooperative control for robotic manipulators with motion constraints using unified transformation function

Echo State Network Based Model Predictive Control for Active Vibration Control of Hybrid Electric Vehicle Powertrains

Observer‐based adaptive event‐triggered PID control for networked systems under aperiodic DoS attacks

Contact Info

Product

Resources

About