Robust identification of non-linear greenhouse model using evolutionary algorithms

Herrero, J. M.; Blasco, X.; Martínez, M.; Ramos, C.; Sanchis, Javier

doi:10.1016/j.conengprac.2007.06.001

Cited by 28 publications

(8 citation statements)

References 20 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Actually, some value and policy iterative approaches can well circumvent the deficiency, and improve the real‐time performance of the control process. Dierks has also developed an online NN‐based optimal control method to update the value function and policy at each control step . In these optimal control approaches, we need to use a critic NN to approximate the HJB equation and an action NN to learn the control signal, and in this work, we also use a NN to estimate the unmodeled dynamics of the system.…”

Section: Basic Problem Of Greenhouse Climate Optimal Controlmentioning

confidence: 99%

Nearly dynamic programming NN‐approximation–based optimal control for greenhouse climate: A simulation study

Goodman

2017

Optim Control Appl Methods

View full text Add to dashboard Cite

Summary Greenhouse production must create a suitable growth environment for its crop to improve yield while minimizing the energy used to maintain the greenhouse environment, thereby reducing production cost. To this end, this paper develops a nearly optimal control approach based on adaptive dynamic programming. In this method, 3 neural networks are used to estimate the value function and control policy and to compensate for the unmodeled dynamics of the greenhouse climate. Taking into account the greenhouse system typically being an overactuated system, the total control efforts for heat, fog, and CO2 are considered as the virtual control inputs to be generated by the optimal controller. To obtain the real control inputs, a control allocation technique is introduced to distribute the virtual control inputs to the actuators. Finally, Lyapunov stability analysis is performed to derive the update law of the neural networks to ensure the asymptotic convergence of the closed‐loop system, and simulation is carried out to illustrate the effectiveness and control performance of the proposed approach.

show abstract

Section: Basic Problem Of Greenhouse Climate Optimal Controlmentioning

confidence: 99%

Nearly dynamic programming NN‐approximation–based optimal control for greenhouse climate: A simulation study

Goodman

2017

Optim Control Appl Methods

View full text Add to dashboard Cite

show abstract

“…Com base nos resultados obtidos na otimização das não-linearidades, as rápidas respostas e o tempo computacional, os autores recomendam referidas técnicas para a aplicação em sistemas comerciais. Herrero et al (2007) apresentam um sistema de identificação de modelos não-lineares para o controle robusto das variáveis climáti-cas, dentre elas a temperatura, com base em equações de primeira ordem e na estimativa dos parâmetros (Feasible Parameter Set, FPS), aplicando otimização multimodal com um número infinito de constituintes do FPS.…”

Section: Tabelaunclassified

Controle automatizado de casas de vegetação: variáveis climáticas e fertigação

Teruel¹

2010

Rev. bras. eng. agríc. ambient.

View full text Add to dashboard Cite

Controle automatizado de casas de vegetação:Variáveis climáticas e fertigação Bárbara J. Teruel 1 RESUMO A aplicação de técnicas de automação e controle em casas de vegetação teve início nos anos 50, com o controle da temperatura através de termostatos; desde então, as mudanças tecnológicas têm abarcado todos os aspectos que compõem o sistema, do projeto estrutural até aspectos relacionados à sustentabilidade. Dentre os parâmetros que devem ser controlados, a temperatura e umidade relativa do ar, a radiação solar, a concentração de CO 2 , a ventilação e a fertigação têm tido uma evolução significativa, dos quais se apresenta uma panorâmica através da revisão do estado da arte de trabalhos publicados nessas temáticas, nos últimos anos. Na atualidade, temas relacionados com a redução do impacto ao meio ambiente e a produção eficiente e com qualidade, estão levando as casas de vegetação ao caminho da Agricultura de Precisão. Palavras-chave: temperatura, umidade relativa, concentração de CO 2 , ventilação, solução nutritivaAutomatized control in greenhouses: Climatic variables and fertigation ABSTRACTThe application of techniques of automation and control in greenhouses began in the years 50, starting with the control of temperature through thermostats. Since then, technological changes have covered all aspects that make up the system, from constructional features up to aspects of sustainability. The control of parameters sulh as, temperature and relative humidity, solar radiation, the concentration of CO 2 , ventilation and fertigation, had significant development, from which it provides a review of published works about these themes in recent years. Currently, issues related to reducing the impact to the environment and efficient production and quality, are taking the greenhouses towards Precision Agriculture.

show abstract

“…The data from dynamic systems play an important role in signal processing [1,2], adaptive filtering [3][4][5], system identification [6,7], and system control [8,9]. In order to extract the useful information from the recorded process data, the model-based optimization framework [10,11] and the data-driven framework [12,13] have been established. The data-driven procedures do not require prior knowledge of the process and have been successfully applied to process monitoring and fault diagnosis [14].…”

Section: Introductionmentioning

confidence: 99%

Convergence of the recursive identification algorithms for multivariate pseudo‐linear regressive systems

Wang

Ding

2015

Adaptive Control & Signal

View full text Add to dashboard Cite

The performance analysis of the recursive algorithms for the multivariate systems with an autoregressive moving average noise process is still open. This paper analyzes the convergence of two recursive identification algorithms, the multivariate recursive generalized extended least squares algorithm and the multivariate generalized extended stochastic gradient algorithm, for pseudo-linear multivariate systems and proves that the parameter estimation errors consistently converge to zero under persistent excitation conditions. The simulation results show that the proposed algorithms work well. 825 distillation column [29]. In the system identification area, Saadatzi et al. used two-input two-output transfer-function matrix models to describe the dynamics of the electric wheelchair on an arbitrary slope, and proposed a pre-compensator to decompose the plant's dynamics and to improve the identification accuracy [30]. Gu et al. combined the recursive least squares algorithm with the state filtering to identify the canonical state space systems [31].In practical industrial processes, the observed output data are always corrupted by various noise. Some methods assume that noise is independent identically distributed or white. However, it may be more reasonable to adopt the colored noise or the correlated noise because noise is unmeasurable [32,33]. The regressive systems involving the colored noise or correlated noise are called the pseudo-linear regressive systems. Cerutti et al. used the autoregressive moving average (ARMA) model to represent the dynamics of brain potentials [34]. Zheng et al. proposed a biased compensation based recursive least squares method for stochastic linear systems with correlated noise [35].On the convergence of the identification algorithms, early researchers always assumed that the observation noise has zero mean, finite second-order moment, and higher-order moment [36]. Some recent studies relaxed these assumptions. Liu and Ding studied the convergence properties of the recursive least squares algorithm for multivariable stochastic systems [37]; Ding and Gu studied the convergence of the auxiliary model based stochastic gradient algorithm for output-error state-delay systems [38]; Ding presented a coupled least squares algorithm for the multivariable stochastic systems and analyzed its convergence [39]. To the best of the authors' knowledge, the performance analysis for the multivariable ARMA systems has not been fully investigated. The main contributions of this paper lie in the following.By utilizing the measurable input-output data, this paper presents a multivariate generalized extended stochastic gradient (M-GESG) algorithm and a multivariate recursive generalized extended least squares (M-RGELS) algorithm for estimating the parameters of multivariate pseudo-linear regressive systems. By using the stochastic martingale theory, this paper analyzes the convergence of the M-GESG algorithm and the M-RGELS algorithm for multivariate systems with ARMA noise process.Briefly, the remainder is...

show abstract

Robust identification of non-linear greenhouse model using evolutionary algorithms

Cited by 28 publications

References 20 publications

Nearly dynamic programming NN‐approximation–based optimal control for greenhouse climate: A simulation study

Nearly dynamic programming NN‐approximation–based optimal control for greenhouse climate: A simulation study

Controle automatizado de casas de vegetação: variáveis climáticas e fertigação

Convergence of the recursive identification algorithms for multivariate pseudo‐linear regressive systems

Contact Info

Product

Resources

About