Neural generalized predictive control

Soloway, Don; Haley, P.

doi:10.1109/isic.1996.556214

Cited by 98 publications

(65 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model predictive control method is based on the receding horizon technique [17]. The neural network model predicts the plant response over a specified time horizon.…”

Section: Predictive Controlmentioning

confidence: 99%

Performance Analysis of CSTR for Different Minimization Routines of NNMPC

Baweja¹,

Gupta²

2017

IJCA

View full text Add to dashboard Cite

Continues Stirred Tank Reactor (CSTR) is widely used in chemical industries and to get high productivity and quality from CSTR the control of various parameter is an important issue. Neural Network based Model Predictive Controller (NNMPC) refers to a class of control algorithms that compute a sequence of manipulated variable adjustments in order to optimize the future behaviour of a plant. In the present study NNMPC is implemented in Neural Network Toolbox of Matlab software that calculates the control input to optimize CSTR performance over a specified future time horizon using minimization routines based on five different line searches. These five conjugate gradient based line searches are namely, Golden section; Bent's; Hybrid bisection cubic; Charalambous and Backtracking line searches. Performance analysis of CSTR output response and error convergence plot indicates that the brent's line search based minimization routine gives best result as compared to other line searches and the NNMPC utilizing Brent's line search based minimization routine controls the output concentration effectively. KeywordsContinuous stirred tank reactor, Matlab, Model predictive control, neural network, System Identification.

show abstract

“…The model predictive control method is based on the receding horizon technique [17]. The neural network model predicts the plant response over a specified time horizon.…”

Section: Predictive Controlmentioning

confidence: 99%

Performance Analysis of CSTR for Different Minimization Routines of NNMPC

Baweja¹,

Gupta²

2017

IJCA

View full text Add to dashboard Cite

show abstract

“…There are different gradient-based methods for solving non-linear optimizing problems in predictive control. Newton-Rafson algorithm [16] is utilized for optimization. Gil et al [17] used gradient descent.…”

Section: Predictive Cost Function and Its Optimizationmentioning

confidence: 99%

Design of a hierarchical fuzzy model predictive controller

Fallah

Khanesar

Teshnehlab

2015

IJET

View full text Add to dashboard Cite

In order to control a nonlinear system using Nonlinear Model Predictive Control (NMPC), a nonlinear model from system is required. In this paper, a hierarchical neuro-fuzzy model is used for nonlinear identification of the plant. The use of hierarchical neuro-fuzzy systems makes it possible to overcome the curse of dimensionality. In neuro-fuzzy systems, if the input number increases, then the number of rules increases exponentially. One solution to this problem is making use of Hierarchical Fuzzy System Mamdani (HFS) in which the number of the rules increases linearly. Gradient descent and recursive least square algorithm are used simultaneously to train the parameters of the HFS. Gradient Descent Algorithm is utilized to train the parameters, which appear nonlinearly in the output of HFS, and RLS is used to train the parameters of consequent the part, which appears linearly in the output of HFS. Finally, a model predictive fuzzy controller based on a predictive cost function is proposed. Using Gradient Descent Algorithm, the parameters of the controller are optimized. The proposed controller is simulated on the control of continuous stirred tank reactor. It is shown that the proposed method can control the system with high performance.

show abstract

“…If the minimization produces either u ≤ lower or u ≥ upper then u is set to u + ε or u -ε respectively. The value of ε is set to 10 -6 [9]. Currently, there is no systematic way to determine the values for the four tuning parameters N 1 , N 2 , N u , and λ u , for a nonlinear system.…”

Section: Neural Generalized Predictive Controlmentioning

confidence: 99%

“…This problem is handled by incorporating a nominal linear model into some of the weights of the neural network while other weights are allowed to learn unmodeled or time varying dynamics of the open-loop system [9].…”

Section: Forming the Maglev Model (Fundamental Principles)mentioning

confidence: 99%

Real-time adaptive control using neural generalized predictive control

Haley

Soloway

Gold

1999

Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251)

View full text Add to dashboard Cite

The objective of this paper is to demonstrate the feasibility of a Nonlinear Generalized Predictive Control algorithm by showing real-time adaptive control on a plant with relatively fast timeconstants. Generalized Predictive Control has classically been used in process control where linear control laws were formulated for plants with relatively slow time-constants. The plant of interest for this paper is a magnetic levitation device that is nonlinear and open-loop unstable. In this application, the reference model of the plant is a neural network that has an embedded nominal linear model in the network weights. The control based on the linear model provides initial stability at the beginning of network training. In using a neural network the control laws are nonlinear and online adaptation of the model is possible to capture unmodeled or time-varying dynamics. Newton-Raphson is the minimization algorithm. Newton-Raphson requires the calculation of the Hessian, but even with this computational expense the low iteration rate make this a viable algorithm for real-time control.

show abstract

Neural generalized predictive control

Cited by 98 publications

References 13 publications

Performance Analysis of CSTR for Different Minimization Routines of NNMPC

Performance Analysis of CSTR for Different Minimization Routines of NNMPC

Design of a hierarchical fuzzy model predictive controller

Real-time adaptive control using neural generalized predictive control

Contact Info

Product

Resources

About