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

Su, Yuanping; Xu, Lihong; Goodman, Erik D.

doi:10.1002/oca.2370

Cited by 17 publications

(14 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, the proposed PID control method was validated on Matlab platform, and was compared with the control allocation based adaptive control (CAAC) and NNapproximation-based optimal control (NNOC) proposed in our previous [31][32]. Since the simulation experiment cannot sample the real greenhouse climate, it must choose a greenhouse climate model to be regarded as the practical greenhouse.…”

Section: Validation and Resultsmentioning

confidence: 99%

“…CAAC and NNOC have many algorithm parameters that must be set correctly. Their settings can be found in [32] and [31], respectively. Single optimization is used for the control allocation in the CAAC.…”

Section: ) Settings For Caac and Nnocmentioning

confidence: 99%

“…In fact, many model-based greenhouse climate control methods usually require the accurate system model, because they are difficult to deal with the model uncertainty. Therefore, to handle the model uncertainty, we proposed several adaptive control methods for greenhouse climate in our previous work [31][32]. The experimental results indicate that these methods can achieve good control performance.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Parameter Self-Tuning PID Control for Greenhouse Climate Control Problem

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

The difficulty of the greenhouse climate control is the great uncertainties of the weather and greenhouse climate. Although many control approaches have been proposed to solve this problem, the structures of the controllers are usually complex, and the reliability of the controllers is usually not good in practice. Therefore, to improve the reliability of the controllers, this paper proposes a parameter self-tuning PID control approach (STPID). In this PID control scheme, three environmental outputs including the inside temperature, humidity and CO 2 concentration are firstly transformed into four equivalent unit outputs, and the equivalent outputs are controlled by four PID controllers respectively. Thus, each PID controller and the corresponding equivalent output construct a single closed-loop system, and the original system can be decoupled. To ensure the desired control performance, the Levenberg-Marquart (LM) algorithm is introduced to tune the PID parameters. Based on the real weather data, a simulation was performed to illustrate the effectiveness of the proposed method, and a comparison study was done to observe the performance of the proposed method. The results indicate that control performance is good.

show abstract

Section: Validation and Resultsmentioning

confidence: 99%

Section: ) Settings For Caac and Nnocmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Parameter Self-Tuning PID Control for Greenhouse Climate Control Problem

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…The advantage of greenhouse production is that the greenhouse climate can be accurately regulated to create a favourable growth environment when some control actions such as heating, fogging, CO 2 injecting are employed [1][2]. Under such situation, the yield and quality of the agricultural product can be improved greatly.…”

Section: Introduction a Abbreviations And Acronymsmentioning

confidence: 99%

Greenhouse Climate Setpoint Optimization: An Online Decision Strategy

Su¹,

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Model extension without shared coauthors is also reserved for relatively simple models, e.g. the extensions by Xu et al (2018bXu et al ( , 2019 to Van Henten (2003), the extension by Su et al (2018) to Tap (2000), and the extension of Peŕez-González et al (2018) to Hasni et al (2011).…”

Section: Inheritance Of Process-based Greenhouse Climate Modelsmentioning

confidence: 99%

Energy saving by LED lighting in greenhouses : A process-based modelling approach

Katzin¹

View full text Add to dashboard Cite

Chapter 2 investigates the discipline of process-based greenhouse modelling. The chapter shows that a considerable number of greenhouse models are being published, and sets out to understand the reasons for the existence of this multitude of models. In Section 2.2, substantial background on the concept of process-based greenhouse modelling is provided, and a general structure of these models is proposed. Subsequently, modelling studies published between 2018 and 2020 are analyzed according to this general structure. The studies are categorized according to their objectives, types of greenhouse they describe, and equipment they consider, and a model inheritance chart is presented, showing how current models are based on earlier works. Moreover, a comparison of modelling validation studies is performed. Based on this analysis, possible reasons for the abundance of greenhouse models are suggested, including a lack of model transparency and code availability, and a belief that model development is in itself a valuable research goal. The chapter ends with several recommendations for the future advancement of the discipline. These include promoting model transparency and availability of source code, and establishing shared datasets and evaluation benchmarks.Chapter 3 presents GreenLight, a process-based model for a greenhouse with a tomato crop, which describes the influence of HPS lamps and LEDs on the climate, crop, and energy use. In this chapter, GreenLight's performance is evaluated by comparing model predictions against data from two greenhouse compartments, one with HPS lamps and one with LEDs. The model is found to have a relative error in predictions of climate and energy use in the range of 1-12%. In order to promote transparency, the model is offered in an open source format at https://github.com/davkat1/GreenLight. In this way, the model is made available for inspection and extension by others.Chapter 4 uses GreenLight to predict the influence of replacing HPS lamps by LEDs in a greenhouse. A wide range of scenarios is considered, including varying climates, from subtropical China to arctic Sweden, and multiple settings for indoor temperature, lamp intensity, lighting duration, and insulation. In all scenarios, LEDs are found to reduce the energy demand for lighting by 40%, but to increase the demand for heating. This results in the total energy saving by transition to LEDs to be in the range of 10-25% for the majority of scenarios considered. An important factor influencing how much energy can be saved by a transition to LEDs is found to be the ratio between the lighting and heating demand of the greenhouse before the transition. Summary xiiiChapter 5 presents a novel concept for greenhouse climate control: heating a greenhouse by light. Considering the observation that all lamps provide heat as well as light, this chapter suggests that illuminating at high light intensities could eliminate the need to heat the greenhouse by the heating system. This approach could potentially be very efficient, as it utili...

show abstract

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

Cited by 17 publications

References 39 publications

Parameter Self-Tuning PID Control for Greenhouse Climate Control Problem

Parameter Self-Tuning PID Control for Greenhouse Climate Control Problem

Greenhouse Climate Setpoint Optimization: An Online Decision Strategy

Energy saving by LED lighting in greenhouses : A process-based modelling approach

Contact Info

Product

Resources

About