Pripenjanje znane geometrije na varjenec

PIŠKUR, JOŽICA (author), Munih, Marko (mentor)

Pri robotskem varjenju s sistemom MOTOSense sledimo 4 značilnim točkam laserske linije čelnega preseka. Uporabili smo čelni presek spoja valjastega varjenca s tipom utora V. Da lahko sledimo značilnim točkam linije, moramo razpoznati geometrijo utora, ki ima trapezno obliko. Z dosedanjim načinom razpoznave značilnih točk dobimo le zgornji dve točki. Ti točki dobimo z algoritmom odvoda po osi y in iskanjem najkrajših razdalj od središčnice do vsake točke linije. Pogosto je spoj varjenca tudi predhodno točkovno zvarjen in ima nedefinirano pripravo spoja zvara, kar otežuje razpoznavo značilnih točk. Ker želimo razpoznati vse značilne točke, smo razpoznavo in analizo naredili z algoritmom odvoda po osi x in diagonalnima filtroma ter algoritmom naleganja polinomov. Pri tem smo uporabili programske knjižnice, ki so podprte za programski jezik Python. S 1. algoritmom smo iskali prelome linije v želenem delu slike in jih preverjali z diagonalnima filtroma. Z 2. algoritmom smo spreminjajoče dele linije definirali z naleganjem polinomov 1. reda. Pri razpoznavi značilnih točk je bil uspešnejši 2. algoritem, saj je zagotavljal razpoznavo točk z manjšimi absolutnimi napakami. 2. algoritem je bil natančnejši in zanesljivejši od 1. algoritma in dosedanjega načina razpoznave. Pri 1. algoritmu so bile značilne točke zamaknjene navzdol oziroma navzgor. Kljub uspešni razpoznavi bi bilo treba 2. algoritem še nadgraditi in preskusiti na širši množici slik, da bi lahko zagotovili robustnost delovanja. Možnost izpopolnitve razpoznave značilnih točk se razbere tudi iz geometrijskih preslikav in poravnav oblik.

• Language: Slovenian
• Keywords: značilne točke, strojni vid, kamera, MOTOSense, varjenje, robot
• Work type: Master's thesis/paper
• Organization: FE - Faculty of Electrical Engineering
• Year: 2018
• PID: 20.500.12556/RUL-100193
• Publication date in RUL: 14.03.2018

PIŠKUR, JOŽICA, 2018, Pripenjanje znane geometrije na varjenec [online]. Master’s thesis. [Accessed 25 March 2025]. Retrieved from: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=eng&id=100193

Secondary language

• Language: English
• Title: Attaching a known geometry to the welding parts

Abstract

Using the MOTOSense system, robotic welding is guided by 4 characteristic points on the front section of the laser line. A cross section of the joint was used with a V groove joint on a cylindrical workpiece. The geometry of the groove needs to be identified enabling guidance relative to the characteristic points, which have a trapezoidal shape. The current method of characteristic point identification yields only the upper two points. The remaining points are obtained by derivative algorithms along the y axis and searching for the shortest distance from the centre line to each point on the line. The welding joint is often tack welded in advance and has an undefined weld joint, which makes identification of the characteristic points difficult. In order to identify and analyse all characteristic points, a derivative algorithm along the x axis with a diagonal filter and a polynomial fitting algorithm was used. Software libraries supported by the Python programming language were used. The first algorithm searched for line breaks in the desired part of the image, which were then cross-referenced with a diagonal filter. The second algorithm, however, defined the changing parts of the line using first order polynomial fitting algorithms. The second algorithm returned better results as it enabled the characteristic points to be identified with smaller absolute errors. Furthermore, greater precision and reliability was observed with the second algorithm over the first algorithm as well as the current method of identification. Identified characteristic points using the first algorithm were offset above or below the desired point. Despite successful identification, the second algorithm needs to be further developed and tested on a wider set of images to ensure robust operation. There is potential for improvement in the identification of characteristic points by geometric mapping and alignment forms.

• Keywords: characteristic points, machine vision, camera, MOTOSense, welding. robot