Modeling of the temperature distribution of a greenhouse using finite element differential neural networks

Title:

Modeling of the temperature distribution of a greenhouse using finite element differential neural networks

Creator:

Bello-Robles, Juan Carlo, Begovich, Ofelia, Ruiz-León, Javier, and Fuente-Aguilar, Rita Quetziquel

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:ecce06c0-51aa-49ce-94c1-6920c128e6f8
uuid:ecce06c0-51aa-49ce-94c1-6920c128e6f8
doi:10.14736/kyb-2018-5-1033

Subject:

differential neural networks, distributed parameter systems, and greenhouse temperature modeling

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

Most of the existing works in the literature related to greenhouse modeling treat the temperature within a greenhouse as homogeneous. However, experimental data show that there exists a temperature spatial distribution within a greenhouse, and this gradient can produce different negative effects on the crop. Thus, the modeling of this distribution will allow to study the influence of particular climate conditions on the crop and to propose new temperature control schemes that take into account the spatial distribution of the temperature. In this work, a Finite Element Differential Neural Network (FE-DNN) is proposed to model a distributed parameter system with a measurable disturbance input. The learning laws for the FE-DNN are derived by means of Lyapunov's stability analysis and a bound for the identification error is obtained. The proposed neuro identifier is then employed to model the temperature distribution of a greenhouse prototype using data measured inside the greenhouse, and showing good results.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Kybernetika | 2018 Volume:54 | Number:5

Harvested from:

CDK

Metadata only:

false