NN-adaptive predictive control for a class of discrete-time nonlinear systems with input-delay

Zhao, Jiemei

doi:10.1016/j.neucom.2015.09.059

Cited by 10 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it was used for linear systems. For an uncertain discrete-time system with input delay, the recurrent neural network was adopted to approximate the nonlinear part of the system, and a robust controller was presented to reduce approximate error and disturbance [34]. A control method based on a prediction model was put forward to resolve input time-delay.…”

Section: Introductionmentioning

confidence: 99%

“…A control method based on a prediction model was put forward to resolve input time-delay. The nonlinear part of the concerned system is hardly predicted by using the linear prediction method proposed in [34]. Similarly, disturbance was estimated by using the immersion and invariance formulation, and the formulation based the input-delay effect was reduced [35].…”

Section: Introductionmentioning

confidence: 99%

“…Its nonlinear part was differentiable, and it was linearized by using the mean value theorem. The nonlinear part was also approximated by using neural networks [34,37]. In the paper [38], the LKF was used for finite-time control of a nonlinear delay Hamiltonian system.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A pattern‐based controller for a class of production processes with input delay

Wang

Pan

2022

Asian Journal of Control

View full text Add to dashboard Cite

For the problem of stabilizing a non‐Newton mechanical system with input delay, a pattern‐based state‐feedback controller is proposed. At the beginning of the paper, pattern‐based dynamic description is introduced, and a discrete‐time state‐space model with input delay (DSMID) is obtained from the description method. Then based on the DSMID, an augmentation state‐space model without input delay is built by using the lifting technique. A stabilization method is put forward, and the relationship between stability and the feature of output‐class partition is given. At last, two simulations are carried out to demonstrate the effectiveness of the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A pattern‐based controller for a class of production processes with input delay

Wang

Pan

2022

Asian Journal of Control

View full text Add to dashboard Cite

show abstract

“…Two majority categories of MFC can be addressed as (i) data-driven controllers (DDC) (Treesatayapun 2015; Radaca and Precup 2018;Bu et al 2018) and (ii) controllers based on model or function approximations (Ntouskas et al 2018;. Nevertheless, the performance of those controllers is significantly connected with the accuracy of parameter estimations such that pseudopartial derivative (PPD) for DDC (Treesatayapun 2018;Liu and Yang 2017) and inner parameters for function approximation or model prediction (Treesatayapun 2017;Zhao 2016). Furthermore, model reparation and advance output prediction are formerly required before establishing the control law (Ziang et al 2018;Radaca and Precup 2018;Huang et al 2018).…”

Section: Introductionmentioning

confidence: 99%

Fuzzy Rules Emulated Discrete-Time Controller Based on Plant’s Input–Output Association

Treesatayapun

2019

J Control Autom Electr Syst

View full text Add to dashboard Cite

In this work, an adaptive controller is designed by an adaptive network called fuzzy rules emulated network (FREN) for a class of nonlinear discrete-time systems when the mathematical model is completely neglected. The characteristic curve between the plant's input and output is drawn by results of the experimental setup. The design parameters are determined by the characteristic curve and utilized to design the controller. The network structure of FREN controller is established by the set of human knowledge-based IF-THEN rules according to the relation between the plant's input and output. The theoretical result is provided to guarantee the convergence of tracking error of the learning algorithm. Furthermore, experimental systems with the LED current control and the robotic system are constructed to validate the performance of the proposed controller. Keywords Discrete-time systems • Adaptive control • Fuzzy neural networks • LED current control • Robotic systems • Contact force control

show abstract

“…The use of artificial intelligence has been recently used for designing MFC schemes such as artificial neural networks (ANN) (Szanto et al, 2018;Zhang et al, 2016), fuzzy logic systems (FLS) (Zhang et al, 2018;Zaki et al, 2018) and fuzzy-neural networks (FNN) (Lu et al, 2018;Solgi and Ganjefar, 2018). The approaches based on model predictions and reference models have been developed by the works in Zhao (2016), Zhao and Hu (2009) and Huang et al (2018). In fact, the model estimation accuracy has a direct effect on the control performance such that an appropriate estimation is required then the proper performance of the controller can be demanded (Lin and Wang, 2010;Spooner et al, 2001).…”

Section: Introductionmentioning

confidence: 99%

Data driven controller based on fuzzy rule adaptive network: with experimental validation

Treesatayapun

2019

COMPEL

View full text Add to dashboard Cite

Purpose The purpose of this paper is to design an online-data driven adaptive control scheme based on fuzzy rules emulated network (FREN) for a class of unknown nonlinear discrete-time systems. Design/methodology/approach By using the input-output characteristic curve of controlled plant and the set of IF-THEN rules based on human knowledge inspiration, the adaptive controller is established by an adaptive FREN. The learning algorithm is established with convergence proof of the closed-loop system and controller’s parameters are directly designed by experimental data. Findings The convergence of tracking error is verified by the theoretical results and the experimental systems. The experimental systems and comparison results show that the proposed controller and its design procedure based on input-output data can achieve superior performance. Practical implications The theoretical aspect and experimental systems with the light-emitting diode (LED) current control and the robotic system prove that the proposed controller can be designed by using only input-output data of the controlled plants when the tracking error can be affirmed the convergence. Originality/value The proposed controller has been theoretically developed and used through experimental systems by using only input-output data of the controlled plant. The novel design procedure has been proposed by using the input-output characteristic curve for both positive and negative control directions.

show abstract

NN-adaptive predictive control for a class of discrete-time nonlinear systems with input-delay

Cited by 10 publications

References 34 publications

A pattern‐based controller for a class of production processes with input delay

A pattern‐based controller for a class of production processes with input delay

Fuzzy Rules Emulated Discrete-Time Controller Based on Plant’s Input–Output Association

Data driven controller based on fuzzy rule adaptive network: with experimental validation

Contact Info

Product

Resources

About