magistrsko delo
Kristijan Medved (Author), Marjan Golob (Mentor)

Abstract

V procesu izdelave magistrskega dela smo sprogramirali zvezni genetski algoritem, ki smo ga uporabili za optimizacijo parametrov PID regulatorja. Za preizkus delovanja algoritma smo replicirali industrijski proces regulacije izhodnega tlaka dveh zaporedno vezanih tlačnih posod in nelinearnega člena. V ta namen smo izdelali sistem vodenja s programom TIA Portal, za oddaljen dostop do procesa pa smo uporabili program KEPServerEX. Procesne odzive smo zajeli pred in po optimizaciji ter ugotovili, da je s predstavljenim optimizacijskim algoritmom mogoče optimizirati parametre PID regulatorja, ne da bi prekinili delovanje procesa.

Keywords

genetski algoritem;optimizacija;digitalni dvojček;PID regulator;magistrske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: [K. Medved]
UDC: 681.515.8:004.8(043.2)
COBISS: 116058115 Link will open in a new window
Views: 94
Downloads: 30
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Controler parameters optimization with genetic algorithm
Secondary abstract: In the process of creating the master's thesis, we programmed a continues genetic algorithm, which we used to optimize the parameters of the PID controller. To test the operation of the algorithm, we replicated the industrial process of regulating the outlet pressure of two series-connected pressure vessels and a nonlinear component. For this purpose, we created a management system with the TIA Portal program, and we used the KEPServerEX program for remote access to the process. Process responses were captured before and after optimization and it was found that with the presented optimization algorithm it is possible to optimize the parameters of the PID controller without interrupting the operation of the process.
Secondary keywords: genetic algorithm;optimization;digital twin;PID controller;
Type (COBISS): Master's thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Elektrotehnika
Pages: 1 spletni vir (1 datoteka PDF (XXI, 76 f.))
ID: 15759038