| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Določanje odmerka fitofarmacevtskega sredstva z uporabo mehkega odločitvenega modela
Authors:ID Berk, Peter (Author)
ID Belšak, Aleš (Mentor) More about this mentor... New window
ID Stajnko, Denis (Comentor)
ID Hočevar, Marko (Comentor)
Files:.pdf DOK_Berk_Peter_2018.pdf (12,84 MB)
MD5: 433EB2DE19ECA662B4A1EEDE3D79CA7D
PID: 20.500.12556/dkum/1258a265-2050-4582-ae02-708b30645af6
 
Language:Slovenian
Work type:Dissertation
Typology:2.08 - Doctoral Dissertation
Organization:FS - Faculty of Mechanical Engineering
Abstract:Pri procesu nanašanja fitofarmacevtskega sredstva, pomešanega z vodo (škropilna brozga) v predpisani koncentraciji, s klasičnimi pršilniki za kemično varstvo krošenj dreves v sadovnjaku se uporabljajo standardni modeli za izražanje odmerkov fitofarmacevtskega sredstva in se pri tem ne upoštevajo karakteristične lastnosti krošenj dreves v sadovnjaku. Rezultat takšnih modelov je nekontrolirano krmiljenje količine škropilne brozge skozi posamezne šobe na krošnjo drevesa. V doktorski disertaciji predstavljamo avtonomni sistem, ki omogoča nadzorovano krmiljenje količin brozge skozi šobe na različnih segmentih krošnje drevesa. Avtonomni sistem temelji na mehkem odločitvenem modelu, v katerega smo, zaradi preciznejšega krmiljenja količin brozge, vključili informacijo o ocenjeni vrednosti listne površine. Ocenjeno vrednost listne površine na segmentih krošnje drevesa smo ovrednotili na osnovi ročnih meritev, laserskega merilnega sistema in programskega algoritma, s katerim smo omogočili tridimenzionalno rekonstrukcijo krošnje drevesa. V eksperimentu v sadovnjaku smo za ovrednotenje listne površine zajeli različne starosti in sorte jablan ('zlati delišes', 'jonagold' in 'gala'). Z uporabo regresijske metode smo ocenili zvezo med dvema odvisnima spremenljivkama (digitalno število zadetkov odbitih laserskih žarkov in digitalna prostornina krošnje drevesa) in eno neodvisno spremenljivko (listna površina, ročno izmerjena). Glede na razmerje med številom oblakov točk in listne površine smo ugotovili, da znaša maksimalna vrednost korelacijskega koeficienta 0,878. Sestavni del mehkega odločitvenega modela je predstavljal mehki logični algoritem za krmiljenje tripoložajnih elektromagnetnih ventilov v pulznoširinskem načinu, ki smo jih namestili na prototip aksialnega pršilnika. Rezultati so pokazali, da lahko z mehkim odločitvenim modelom omogočimo krmiljenje količin škropilne brozge v točno določenem območju glede na ocenjeno vrednost listne površine, zato bo ta model v bližnji prihodnosti predstavljal močno orodje pri zmanjševanju porabe fitofarmacevtskih sredstev za varstvo rastlin.
Keywords:fitofarmacevtsko sredstvo, merjenje, krmiljenje, algoritem, krošnja drevesa
Place of publishing:Maribor
Publisher:P. Berk
Year of publishing:2018
PID:20.500.12556/DKUM-70180 New window
UDC:004.942.021:632.982.1(043.3)
COBISS.SI-ID:297309696 New window
NUK URN:URN:SI:UM:DK:9PNT3CPP
Publication date in DKUM:26.07.2018
Views:2342
Downloads:174
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FS
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:16.04.2018

Secondary language

Language:English
Title:Defining plant protection product dose rate using a fuzzy decision-making model
Abstract:In the process of applying a plant protection product mixed with water (spray mixture) at the prescribed concentration with conventional sprayers for chemical protection of tree canopies in an orchard, standard models are used to express the dose rate of the plant protection product. Characteristic properties of the tree canopy in an orchard are not taken into consideration. Such models result in uncontrolled quantities of spray mixture sprayed through individual nozzles into a tree canopy. In the doctoral thesis an autonomous system is presented, which ensures a controlled quantity of spray mixture sprayed through the nozzles into different tree canopy segments. The autonomous system is based on a fuzzy decision-making model that includes information about the estimated leaf area value to ensure a more precise spray mixture control. The estimated value of the leaf area at canopy segments was evaluated using manual measurements, the laser LIDAR measuring method and a software algorithm for a three-dimensional reconstruction of the canopy. In the experiment, in an orchard, the leaf area of various ages and apple cultivars ('golden delicious', 'jonagold', 'gala') was captured for evaluation. Based on the regression approach, the relationship was assessed between two dependent variables (the digital number of hits of laser beams and the digital volume of the canopy) and an independent variable (canopy leaf area, manually measured). Based on the ratio between the number of point clouds and the leaf surface, it was established that the maximum value of the correlation coefficient was 0,878. An integral part of the fuzzy decision-making model is represented by a fuzzy logic controller for controlling three-position electromagnetic valves in the pulse width mode; the valves were installed in the axial sprayer prototype. The results showed that with the fuzzy decision-making model it was possible to control the quantity of spray mixture in the specific range depending on the estimated value of the leaf area. Consequently, this model will represent a powerful tool for reducing the quantity of spray mixture for plant protection in the near future.
Keywords:plant protection product, measurement, controlling, algorithm, tree canopy


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica