A neural net model-based multivariable long-range predictive control strategy applied in thermal power plant control

Prasad, Girijesh; Swidenbank, E.; Hogg, B.W.

doi:10.1109/60.678982

Cited by 83 publications

(30 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Schenker and Agarwal (1995) reported long-range prediction for poorly known systems through training distinct networks. A long-range prediction strategy was proposed by Prasad et al (1998). Several neural networks for multistep prediction in time-series have recently proposed empirical models for multistep ahead prediction (Parlos et al, 2000).…”

Section: The Multistep-ahead Problemmentioning

confidence: 99%

A two‐step‐ahead recurrent neural network for stream‐flow forecasting

Chang

Chiang

2003

Hydrological Processes

View full text Add to dashboard Cite

Abstract:In many engineering problems, such as flood warning systems, accurate multistep-ahead prediction is critically important. The main purpose of this study was to derive an algorithm for two-step-ahead forecasting based on a real-time recurrent learning (RTRL) neural network that has been demonstrated as best suited for real-time application in various problems. To evaluate the properties of the developed two-step-ahead RTRL algorithm, we first compared its predictive ability with least-square estimated autoregressive moving average with exogenous inputs (ARMAX) models on several synthetic time-series. Our results demonstrate that the developed two-step-ahead RTRL network has efficient ability to learn and has comparable accuracy for time-series prediction as the refitted ARMAX models. We then investigated the two-step-ahead RTRL network by using the rainfall-runoff data of the Da-Chia River in Taiwan. The results show that the developed algorithm can be successfully applied with high accuracy for two-step-ahead real-time stream-flow forecasting.

show abstract

Section: The Multistep-ahead Problemmentioning

confidence: 99%

A two‐step‐ahead recurrent neural network for stream‐flow forecasting

Chang

Chiang

2003

Hydrological Processes

View full text Add to dashboard Cite

show abstract

“…1 ). The output of CNN is defined by 39(k + 1) = yL(k + 1) + yN(k + 1), (2) where YL( k + l ) is the output of a two-layer feed-forward neural network (FNN), which models the local hnearized dynamics of the controlled plant and the weights are trained by the BP algorithm. YN( k + 1) is the output of a local recurrent neural network (L1LNN), which approximates the nonlinear dynamics not being modeled by the linear model.…”

Section: Nonlinear System Identification Based On Neural Networkmentioning

confidence: 99%

“…Owing to its capability of approximating any nonlinear dynamic systems with arbitrary high precision, artificial neural networks (ANN) have been proposed and extensively used in identification and control of nonlinear processes [ 11 9 Over the last ten years, the multi-step predictor design based on ANN has been researched in several papers [2,3].…”

Section: Introductionmentioning

confidence: 99%

Nonlinear system PID-type multi-step predictive control

Zhang

Chen

Yuan

2004

J. Control Theory Appl.

View full text Add to dashboard Cite

A compound neural network was constructed during the process of identification and multi-step prediction. Under the PID-type long-range predictive cost function, the control signal was calculated based on gradient algorithm. The nonlinear controller's structure was similar to the conventional PID controller. The parameters of this controller were tuned by using a local recurrent neural network on-line 9 The controller has a better effect than the conventional PID controller. Simulation study shows the effectiveness and good performance.

show abstract

“…They are: 1) robust design and robust tuning of the controller [1][2][3]; 2) structure optimization of the control system [4][5][6]; and 3) utilization of fuzzy, neural and other intelligent methods [7,8].…”

Section: Introductionmentioning

confidence: 99%

Nonlinear inversion-based output tracking control of a boiler-turbine unit

Fang

Liu

Tan

2005

J. Control Theory Appl.

View full text Add to dashboard Cite

The capability to perform fast load-following has been an important issue in the power industry. An output tracking control system of a boiler-turbine unit is developed. The system is composed of stable inversion and feedback controller.The stable inversion is implemented as a feedforward controller to improve the load-following capability, and the feedback controller is utilized to guarantee the stability and robustness of the whole system. Loop-shaping Ha method is used to design the feedback controller and the final controller is reduced to a multivariable PI form. The output tracking control system takes account of the multivariable, nonlinear and coupling behavior of boiler-turbine system, and the simulation tests show that the control system works well and can be widely applied.

show abstract

A neural net model-based multivariable long-range predictive control strategy applied in thermal power plant control

Cited by 83 publications

References 7 publications

A two‐step‐ahead recurrent neural network for stream‐flow forecasting

A two‐step‐ahead recurrent neural network for stream‐flow forecasting

Nonlinear system PID-type multi-step predictive control

Nonlinear inversion-based output tracking control of a boiler-turbine unit

Contact Info

Product

Resources

About