search query: @keyword hahmontunnistus / total: 34
results-list
reference: 9 / 34
« previous | next »
Author:Karhu, Heidi
Title:Tukin hahmontunnistaminen 3D-mittareilla ja tukkidatan hyödyntäminen sahaprosessissa
Log pattern recognizing with 3D-log scanners and the utilization of the measurement data in saw process
Publication type:Master's thesis
Publication year:2012
Pages:57 s. + liitt. 10      Language:   fin
Department/School:Puunjalostustekniikan laitos
Main subject:Puutekniikka   (Puu-28)
Supervisor:Kairi, Matti
Instructor:Haimi, Pekka ; Koskinen, Kari
OEVS:
Electronic archive copy is available via Aalto Thesis Database.
Instructions
close

Reading digital theses in the closed network of the Aalto University Harald Herlin Learning Centre

In the closed network of Learning Centre you can read digital and digitized theses not available in the open network.

The Learning Centre contact details and opening hours: https://learningcentre.aalto.fi/en/harald-herlin-learning-centre/

You can read theses on the Learning Centre customer computers, which are available on all floors.

Logging on to the customer computers

  • Aalto University staff members log on to the customer computer using the Aalto username and password.
  • Other customers log on using a shared username and password.

Opening a thesis

  • On the desktop of the customer computers, you will find an icon titled:

    Aalto Thesis Database

  • Click on the icon to search for and open the thesis you are looking for from Aaltodoc database. You can find the thesis file by clicking the link on the OEV or OEVS field.

Reading the thesis

  • You can either print the thesis or read it on the customer computer screen.
  • You cannot save the thesis file on a flash drive or email it.
  • You cannot copy text or images from the file.
  • You cannot edit the file.

Printing the thesis

  • You can print the thesis for your personal study or research use.
  • Aalto University students and staff members may print black-and-white prints on the PrintingPoint devices when using the computer with personal Aalto username and password. Color printing is possible using the printer u90203-psc3, which is located near the customer service. Color printing is subject to a charge to Aalto University students and staff members.
  • Other customers can use the printer u90203-psc3. All printing is subject to a charge to non-University members.
Location:P1 Ark Aalto  2367   | Archive
Keywords:3D-log scanner
log pattern recognizing
3D-tukkimittari
hahmontunnistus
Abstract (eng): Today in different phases of saw process it is gathered a lot of measurement data which is utilized locally.
This phenomenon is the research problem studied in this project with new technology 3D-log scanners that had two laser frames instead of one to achieve more accurate and reliable result.
The main objective of this study is the idea of 3D log pattern recognizing between log sorting and sawing.
The main purpose of the idea is to measure the logs at the log sorting and identify them from certain database by their geometrical properties before sawing.
Limab Oy supplied the log scanners for this study and the experimental study was conducted at the log sorting at Koskisen Oy.

For the experimental part of this study 500 pre-sorted spruce logs were selected.
The logs were run, first unbarked then barked, through the 3D-log scanner that was assembled to the log sorting.
The laser surfaces created the geometrical graphs from the logs, the 3D patterns that were utilized for the 3D pattern recognizing.
The 3D pattern recognizing of the logs was conducted with a simulated operating system.
The 3D graphs from unbarked and barked logs were uploaded to the operating system.
The simulated system fits the pattern of barked log to every unbarked log pattern and gives a fitting value.
The fitting value determines by length, top diameter and shape of the logs.

The 3D-log pattern recognition was calculated in different size of log group using the data from operating pattern recognizing system.
The 3D-log patter recognition was 78 % by the average of five groups of 100 logs.
The amount logs in the groups affected decreasingly to the pattern recognition.
In the group of 500 logs, the pattern recognition was 62 %.
With restricting the length parameter from +-15mm to +-10mm, the pattern recognition was increased up to 66 %.
Estimation for the growth of the annual profit was appraised according to the result of this study with an assumption if there is used x-ray and 3D-log scanner combination.
The annual profit growth could be about 2.8 million euros if the pattern recognition is 78 % and rotation of the log in sawing is fulfilled with 70 % by x-ray.
Abstract (fin): Nykypäivän sahaprosessin eri vaiheissa kerätään paljon mittausdataa, jota hyödynnetään vain paikallisesti.
Tätä ongelmaa tutkittiin tässä tutkimuksessa tukin 3D-hahmontunnistuksen kautta uuden teknologian 3D-tukkimittareilla.
Tutkimuksen tavoitteena on selvittää 3D-hahmontunnistus -idean toimivuutta tukkilajittelun ja sahaan syötön välillä.
Idean tarkoituksena on mitata tukit tukkilajittelussa ja tunnistaa ne määrätystä tietokannasta niistä mitattujen tunnuslukujen perusteella ennen sahaan syöttöä.
Tutkimusta varten Limab Oy toimitti uuden teknologian tukkimittarit, jossa on yhden sijasta kaksi laserkehää tarkemman ja luotettavamman mittaustuloksen aikaansaamiseksi.
Tutkimuksen kokeellinen osa suoritettiin Koskisen Oy:n sahan tukkilajittelussa.

Tutkimukseen valittiin 500 kuusitukkia, jotka ajettiin kuorellisina ja kuorittuina tukkilajitteluun asennetun 3D-mittarin läpi. 3D-mittarin lasertasojen mittauspisteet muodostivat tukeista geometrisen kuvan, 3D-hahmon.
Itse tukin hahmontunnistus suoritettiin simuloidulla hahmontunnistusohjelmistolla, johon tallennettiin tukkimittarin muodostamat 3D-kuvat tukeista niin kuorellisina kuin kuorettomina.
Ohjelmisto sovittaa kuoritun tukin hahmoa jokaiseen kuorelliseen hahmoon ja antaa sovituksesta yhteensopivuusarvon, joka määräytyy tukin pituus-, halkaisija- ja muotosopivuuden perusteella.
Saaduilla yhteensopivuusarvoilla laskettiin tukin 3D-hahmontunnistettavuus erikokoisissa tukkiryhmissä.

Tukkien 3D-hahmontunnistukseksi saatiin 78 % viiden 100 tukin ryhmän 3D-hahmontunnistuksen keskiarvolla.
Tukkien määrällä oli vaikutusta tukkien 3D-hahmontunnistukseen, silla 500 tukin ryhmän 3D-hahmontunnitettavuus oli 62 %.
Pituusparametrin tiukentamisella +-15mm:sta +-10mm:iin saatiin laskennallisesti 4 prosenttiyksikön parannus hahmontunnistukseen 500 tukin ryhmässä.
Tuloksien pohjalta voitiin arvioida sahan arvosaannon kasvua vuositasolla, jos käytössä olisi röntgenmittari 3D-mittarin lisäksi.
Jos 3D-hahmontunnistettavuus olisi 78 % ja tukin pyöritys toteutuu 70 % röntgentiedon mukaan, voisi arvosaannon kasvu olla vuositasolla noin 2,8 miljoonaa euroa.
ED:2013-02-26
INSSI record number: 45866
+ add basket
« previous | next »
INSSI