Articles
ENHANCEMENT OF THE INTELLIGENT LEAF SENSOR
Article number
421_24
Pages
231 – 240
Language
Abstract
The maintenance of a suitable humidity environment in plant propagation chambers is a prerequisite for successful root growth of plant cuttings.
This paper describes an innovative sensing method which has been developed to replace leaf sensors in plant propagation systems.
Such chambers present critical situations for control because of the high humidity levels to be maintained, which makes direct sensing methods unsuitable.
The new method is based on the fact that conditions of the microclimatic space are fully determined by the surrounding space, and implicitly relates the transfer phenomena between the two spaces through the selection of control parameters.
The measured macroclimatic variables together with the identified control parameters provide an estimate of the moisture loss and determine the rate at which humidity should be supplied in the propagation chamber.
An adaptive system guides the selection of control parameters on-line, in a process leading to optimal system performance.
The system is performance driven, conducts real experiments on the site and uses a modified descent method to maximise performance.
The performance surface was studied and a modification of the searching algorithm has improved the learning rate significantly.
This paper describes an innovative sensing method which has been developed to replace leaf sensors in plant propagation systems.
Such chambers present critical situations for control because of the high humidity levels to be maintained, which makes direct sensing methods unsuitable.
The new method is based on the fact that conditions of the microclimatic space are fully determined by the surrounding space, and implicitly relates the transfer phenomena between the two spaces through the selection of control parameters.
The measured macroclimatic variables together with the identified control parameters provide an estimate of the moisture loss and determine the rate at which humidity should be supplied in the propagation chamber.
An adaptive system guides the selection of control parameters on-line, in a process leading to optimal system performance.
The system is performance driven, conducts real experiments on the site and uses a modified descent method to maximise performance.
The performance surface was studied and a modification of the searching algorithm has improved the learning rate significantly.
Authors
N.A. Sigrimis, N. Rerras
Keywords
sensors, intelligence, mist, fog
Online Articles (31)