Use of neural networks for quick and accurate auto-tuning of PID controller

D’Emilia, Giulio; Marra, Antonio; Natale, Emanuela

doi:10.1016/j.rcim.2006.04.001

Cited by 35 publications

(11 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are varied prominent studies in self-tuning PID field. Supervisory control or self-tuning can be executed via different methods, for instance optimization based [21][22][23], fuzzy-logic mechanism [24,25], neural networks [26,27]. In this paper, for the first time in the literature and beside of mentioned self-tuning PID strategies, the self-tuning PI controller via FCM method is proposed.…”

Section: A Brief Overview Of Fuzzy Cognitive Mapsmentioning

confidence: 99%

Self-tuning PI Controllers via Fuzzy Cognitive Maps

Yeşil

Dodurka

Sakalli

et al. 2013

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Abstract. In this study, a novel self-tuning method based on fuzzy cognitive maps (FCMs) for PI controllers is proposed. The proposed FCM mechanism works in an online manner and is activated when the set-point (reference) value of the closed loop control system changes. Then, FCM tuning mechanism changes the parameters of PI controller according to systems' current and desired new reference value to improve the transient and steady state performance of the systems. The effectiveness of the proposed FCM based selftuning method is shown via simulations on a nonlinear system. The results show that the proposed self-tuning methods performances are satisfactory.

show abstract

Section: A Brief Overview Of Fuzzy Cognitive Mapsmentioning

confidence: 99%

Self-tuning PI Controllers via Fuzzy Cognitive Maps

Yeşil

Dodurka

Sakalli

et al. 2013

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

show abstract

“…It is noteworthy that earlier studies on PID control [12][13][14] and GCC [15][16][17][18][19] did not take the state-dependent noise into consideration. It is noteworthy that earlier studies on PID control [12][13][14] and GCC [15][16][17][18][19] did not take the state-dependent noise into consideration.…”

Section: Introductionmentioning

confidence: 99%

“…It is noteworthy that earlier studies on PID control [12][13][14] and GCC [15][16][17][18][19] did not take the state-dependent noise into consideration. It should be noted that the proposed concept of additive gain perturbations is significantly different from the PID control [13,14] in the sense that the stability of the overall system is guaranteed even if the additive gain perturbations exist. The new contributions of our study are as follows.…”

Section: Introductionmentioning

confidence: 99%

Guaranteed cost PID control for uncertain discrete‐time stochastic systems with additive gain perturbations

Mukaidani

2010

Asian Journal of Control

View full text Add to dashboard Cite

This paper investigates a novel design method for robust nonfragile proportional-integral-derivative (PID) control that is based on the guaranteed cost control (GCC) problem for a class of uncertain discrete-time stochastic systems with additive gain perturbations. On the basis of linear matrix inequality (LMI), a class of fixed PID controller parameters is obtained, and some sufficient conditions for the existence of the GCC are derived. Although the additive gain perturbations are included in the feedback systems, both the stability of closed-loop systems and adequate cost bound are attained. As a sequel, decentralized GCC PID for a class of discrete-time uncertain large-scale stochastic systems is also considered. Finally, the numerical results demonstrate the efficiency of the proposed controller synthesis.

show abstract

“…If the minimization of I F((J(t))1 is replaced by the calculation of c T c; , where c T = [ 0l x3 ' ll x3 ' 0lx3] , then the optimization problem (8) will be turned into the following optimization problem(9). The optimization problem (9) is depicted as follows.…”

mentioning

confidence: 99%

“…,T = [ ' I ' ' 2 , '3 1x3 denotes the dual vector of c; .Therefore, the optimization problem of the output yet)is transformed into a pair of optimization problems defined in(9) and (10). By minimizing C T c; and maximizing b T , under the conditions of A F SA c; = band A'};SA' = C , we can obtain the extremum vector ()* and the extremum output y* of the controlled system.…”

mentioning

confidence: 99%

PID controller tuning by using extremum seeking algorithm based on annealing recurrent neural network

Zuo

2010

2010 Third International Symposium on Knowledge Acquisition and Modeling

View full text Add to dashboard Cite

This paper proposes a discrete-time extremum seeking algorithm based on annealing recurrent neural network (ESA-ARNN) for auto-tuning of PID controller parameters.Firstly, the process of tuning PID controller parameters is transformed into an extremum seeking problem by introducing a cost function, such as the integral squared error (ISE). Then, in order to solve this extremum seeking problem, a discrete-time ESA-ARNN is proposed, which can realize auto-tuning for PID controller parameters. Lastly, the novel auto-tuning method is applied to tuning PID controller parameters of the process system with second-order plus dead time (SOPDT). Simulation results indicate that PID controller parameters tuned by ESA ARNN have better performance than those tuned by the eight prevalent PID tuning schemes.

show abstract

Use of neural networks for quick and accurate auto-tuning of PID controller

Cited by 35 publications

References 5 publications

Self-tuning PI Controllers via Fuzzy Cognitive Maps

Self-tuning PI Controllers via Fuzzy Cognitive Maps

Guaranteed cost PID control for uncertain discrete‐time stochastic systems with additive gain perturbations

PID controller tuning by using extremum seeking algorithm based on annealing recurrent neural network

Contact Info

Product

Resources

About