Razvoj aplikacije za stvaranje formalnog računalnog zapisa električnih shema uz razvoj računalnog algoritma za detekciju električnih elemenata i njihovih karakteristika na slikama shema električnih krugova

master's thesis

• Title (english): The development of an application for creating a formal computer record of electrical schematics, along with the development of a computer algorithm for the recognition of electrical elements and their characteristics on images of electrical schematics
• Author: Lorena Lazar
• Mentor: Mihaela Vranić (mentor)
• Committee member: Mihaela Vranić (predsjednik povjerenstva)
• Committee member: Luka Humski (član povjerenstva)
• Committee member: Frano Škopljanac-Mačina (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-16, Croatia

Abstract

U ovom radu opisan je razvoj aplikacije za generiranje formalnog računalnog zapisa električnih shema koji se naziva netlist. Korištenjem YOLO algoritama razvijen je računalni model za detekciju električnih elemenata i njihovih karakteristika na slikama shema električnih krugova. Model je razvijen i testiran na slikama shema korištenih na kolegiju Osnove elektrotehnike na Fakultetu elektrotehnike i računarstva. Integriranjem razvijenog modela u aplikaciju omogućena je ručna prilagodba detektiranih elemenata i njihovih karakteristika. Kao rezultat, aplikacija generira formalni zapis sheme koji može služiti za izvođenje simulacija. Programsko rješenje implementirano je u programskim jezicima Python i Swift.

Abstract (english)

This paper describes the development of an application for generating a formal computer record of electrical schematics, known as a netlist. Using YOLO algorithms, a computer model was developed for the detection of electrical elements and their characteristics on images of electrical schematics. The model was developed and tested on images from the Fundamentals of Electrical Engineering course at the Faculty of Electrical Engineering and Computing. The developed model is integrated into an application that allows for manual adjustment of detected elements and their characteristics. As a result, the application generates a formal schematic representation suitable for performing simulations. The software solution is implemented in Python and Swift programming languages.

• Keywords: strojno učenje; računalni vid; detekcija; YOLO; prepoznavanje električnih krugova; električna shema; netlist; iOS
• Keywords (english): machine learning; computer vision; detection; YOLO; circuit recognition; electrical schematic; netlist; iOS
• Language: croatian
• URN:NBN: urn:nbn:hr:168:453676
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2024-10-12 21:18:13