06-05-2013, 04:58 PM
Automation of Irrigation System Using ANN based Controller
Automation of Irrigation S.pdf (Size: 283.22 KB / Downloads: 54)
Abstract:
Irrigation systems are as old as man itself since
agriculture is the foremost occupation of civilized humanity. To
irrigate large areas of plants is an onerous job. In order to
overcome this problem many irrigation scheduling techniques
have been developed which are mainly based on monitoring the
soil, crop and weather conditions. Irrigation scheduling
engrosses when to irrigate and how much water to be applied.
Currently most of the irrigation scheduling systems and their
corresponding automated hardware are fixed rate. Variable rate
irrigation is very essential not only for the improvement of
irrigation system but also to reduce the irrigation cost and to
increase crop yield. The heart of automatic irrigation system
(fixed rate or variable rate) is its control unit: as it controls
irrigation time and water flow. Intelligent control based
irrigation is necessitated to maximize the efficiency and
production. Existing technologies varies from water balance or
check book method to sophisticated sensor-based systems
[1].Most of the irrigation systems use ON/OFF controllers.
These controllers can not give optimal results for varying time
delays and varying system parameters. This paper presents
Artificial Neural Network (ANN) based intelligent control
system for effective irrigation scheduling. The proposed
Artificial Neural Network (ANN) based controller is prototyped
using MATLAB. The input parameters like air temperature, soil
moisture, radiations and humidity are modeled. Then using
appropriate method, ecological conditions, evapotranspiration
and type of crop, the amount of water needed for irrigation is
estimated and then associated results are simulated.
Introduction
Agriculture has, throughout History, played a major role
in human societies endeavors to be self sufficient in
food[2].Irrigation is an essential component of crop
production in many areas of the world. In cotton for
example, recent studies have shown that proper timing of
irrigation is an important production factor and that
delaying irrigation can result in losses of between USD
62/ha and USD 300/ha [3]. Irrigation water use represents
a substantial opportunity for residential water savings.
Automation of irrigation system has the potential to
provide maximum water use efficiency by monitoring soil
moistures at optimum level[4].
Open loop controller:
This are also called non-feedback controllers.
This type of controller is designed on following
principles:
• It just takes input and computes output for the
system accordingly.
• It does not have any feed-back to determine
whether the desired output or goal is achieved or
not.
This is most simple form of controller in which basic
parameters and instructions are pre-defined such as:
• When to start watering/a task
• When to end watering /a task
• Time delay intervals
During execution of above set of instructions using open
loop-controller no measures are taken to check whether
right amount of water is supplied or not.
These controllers may have less cost, but they are not
very good and they do not provide optimal (or a good)
solution to irrigation problems.
Closed loop controller:
They are based on pre-defined control concept and
utilizing feedback from controlled object/system in some
manner. In this type of controller feedback of a necessary
parameter is required to check right amount of water
needed for irrigation.
Design of ANN based Irrigation Controller
Figure 1 exhibits the block diagram of Complete
Irrigation System ingrained with ANN Controller. It is
seen that control system consists of four interconnected
stages.
• Input from Sensors: In this stage different
parameters like temperature, air humidity ,soil
moisture, wind speed and radiation ,are
collected. Then these parameters are passed to
next stage as input.
• Evapotranspiration Model: This block converts
four input parameters into actual soil
moisture(details in next Section)
• Required Soil Moisture: This block provides
information about the amount of water required
for proper growth of plants.
• ANN Controller: This stage compares the
required soil moisture with actual soil moisture
and decision is made dynamically.
Conclusions and future work
This paper has described a simple approach to Irrigation
control problem using Artificial Neural Network
Controller. The proposed system is compared with
ON/OFF controller and it is shown that ON/OFF
Controller based System fails miserably because of its
limitations. On the other hand ANN based approach has
resulted in possible implementation of better and more
efficient control.