Design and analysis of a learning-based testing system for certification of vehicle systems

In this work, a learning-based testing system is designed and evaluated in terms of its perfor-mance and feasibility of use in testing of safety-critical vehicle systems; the objective is to reduce testing time and costs. A literature study was conducted on the AMASS project, model-based testing and...

Full description

Bibliographic Details
Main Author: Markros, Adam
Format: Others
Language:English
Published: KTH, Fordonsdynamik 2019
Subjects:
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-265622
id ndltd-UPSALLA1-oai-DiVA.org-kth-265622
record_format oai_dc
spelling ndltd-UPSALLA1-oai-DiVA.org-kth-2656222019-12-20T03:39:24ZDesign and analysis of a learning-based testing system for certification of vehicle systemsengMarkros, AdamKTH, Fordonsdynamik2019Vehicle EngineeringFarkostteknikIn this work, a learning-based testing system is designed and evaluated in terms of its perfor-mance and feasibility of use in testing of safety-critical vehicle systems; the objective is to reduce testing time and costs. A literature study was conducted on the AMASS project, model-based testing and machine learning; based on which a design of the testing system was developed. The finished testing system uses a genetic algorithm for generating solutions of high fitness, which in this application implies test cases that provoke failures in a target system under test, in order for the developers to detect system defects. The target testing system is a model of Volvo’s Brake-By-Wire ABS module. It was concluded that the testing system is effective in increas-ing fitness of solutions through iteration; the performance of the machine learning algorithm is dependent on parameters such as the mutation rate and the size of the populations into which solutions are clustered. I detta arbete har ett lärningsbaserat testsystem framställts. Dess prestanda har utvärderats samt dess lämplighet att användas för testning av säkerhetskritiska fordonssystem. Syftet är att minska kostnaden samt tidsåtgången av testningsprocessen. En litteraturstudie utfördes vilken berörde AMASS-projektet, modellbaserad testning samt maskininlärning. Baserat på detta kunde det lärningsbaserade testsystemet utvecklas. Det färdiga testsystemet använder en s.k. genetisk algoritm för att generera lösningar av hög kondition, vilket benämns fitness. I denna tillämpning innebär en hög fitness ett testfall som resulterar i ett underkänt test, då syftet med testprogrammet är att utvecklaren ska upptäcka det testade systemets brister. Det testade systemet är en modell av Volvos Brake-By-Wire ABS-modul. Det konstaterades att testsystemet är effektivt i att öka lösningarnas fitness genom iteration samt att algoritmens prestanda avgörs av dess parametrar, som mutationstakt samt populationsstorlek. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-265622TRITA-SCI-GRU ; 2019:327application/pdfinfo:eu-repo/semantics/openAccess
collection NDLTD
language English
format Others
sources NDLTD
topic Vehicle Engineering
Farkostteknik
spellingShingle Vehicle Engineering
Farkostteknik
Markros, Adam
Design and analysis of a learning-based testing system for certification of vehicle systems
description In this work, a learning-based testing system is designed and evaluated in terms of its perfor-mance and feasibility of use in testing of safety-critical vehicle systems; the objective is to reduce testing time and costs. A literature study was conducted on the AMASS project, model-based testing and machine learning; based on which a design of the testing system was developed. The finished testing system uses a genetic algorithm for generating solutions of high fitness, which in this application implies test cases that provoke failures in a target system under test, in order for the developers to detect system defects. The target testing system is a model of Volvo’s Brake-By-Wire ABS module. It was concluded that the testing system is effective in increas-ing fitness of solutions through iteration; the performance of the machine learning algorithm is dependent on parameters such as the mutation rate and the size of the populations into which solutions are clustered. === I detta arbete har ett lärningsbaserat testsystem framställts. Dess prestanda har utvärderats samt dess lämplighet att användas för testning av säkerhetskritiska fordonssystem. Syftet är att minska kostnaden samt tidsåtgången av testningsprocessen. En litteraturstudie utfördes vilken berörde AMASS-projektet, modellbaserad testning samt maskininlärning. Baserat på detta kunde det lärningsbaserade testsystemet utvecklas. Det färdiga testsystemet använder en s.k. genetisk algoritm för att generera lösningar av hög kondition, vilket benämns fitness. I denna tillämpning innebär en hög fitness ett testfall som resulterar i ett underkänt test, då syftet med testprogrammet är att utvecklaren ska upptäcka det testade systemets brister. Det testade systemet är en modell av Volvos Brake-By-Wire ABS-modul. Det konstaterades att testsystemet är effektivt i att öka lösningarnas fitness genom iteration samt att algoritmens prestanda avgörs av dess parametrar, som mutationstakt samt populationsstorlek.
author Markros, Adam
author_facet Markros, Adam
author_sort Markros, Adam
title Design and analysis of a learning-based testing system for certification of vehicle systems
title_short Design and analysis of a learning-based testing system for certification of vehicle systems
title_full Design and analysis of a learning-based testing system for certification of vehicle systems
title_fullStr Design and analysis of a learning-based testing system for certification of vehicle systems
title_full_unstemmed Design and analysis of a learning-based testing system for certification of vehicle systems
title_sort design and analysis of a learning-based testing system for certification of vehicle systems
publisher KTH, Fordonsdynamik
publishDate 2019
url http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-265622
work_keys_str_mv AT markrosadam designandanalysisofalearningbasedtestingsystemforcertificationofvehiclesystems
_version_ 1719304132932665344