Fault Tracing Bot in Electric Drive Software Using Machine Learning

dc.contributor.authorJai Prakash, Soundarya
dc.contributor.authorGopinath, Hariharan
dc.contributor.departmentChalmers tekniska högskola / Institutionen för elektrotekniksv
dc.contributor.examinerEriksson, Thomas
dc.contributor.supervisorFarsi, Mohammad
dc.date.accessioned2024-03-12T12:38:56Z
dc.date.available2024-03-12T12:38:56Z
dc.date.issued2023
dc.date.submitted2023
dc.description.abstractThe Electric Drive Software Continuous Deployment (EDCD) team at Volvo Car Corporation is working towards figuring out the automation of the analysis of the build log data obtained as a result of the continuous software integration for Electronic Control Unit (ECUs) using Machine Learning. Machine Learning is expected to be used in building a fault tracing bot, whose main goal is to analyse the provided log data and find the underlying meaning or information through it with minimum or zero human interaction. As this is an ongoing process and the creation of such log data will never really end, this project could make it easier for the analysis of big projects in getting instant data. At first, we are working on the data cleaning and the preprocessing of the big unstructured log data, followed by the labeling of the data by the clustering process. Lastly, the machine learning algorithm is used to predict the classification of the newly fed data. Many different machine learning algorithms have been implied to compare and get the best accuracy predicting algorithm among them.
dc.identifier.coursecodeEENX30
dc.identifier.urihttp://hdl.handle.net/20.500.12380/307622
dc.language.isoeng
dc.setspec.uppsokTechnology
dc.subjectMachine Learning
dc.titleFault Tracing Bot in Electric Drive Software Using Machine Learning
dc.type.degreeExamensarbete för masterexamensv
dc.type.degreeMaster's Thesisen
dc.type.uppsokH
local.programmeSystems, control and mechatronics (MPSYS), MSc
Ladda ner
Original bundle
Visar 1 - 1 av 1
Hämtar...
Bild (thumbnail)
Namn:
Master_Thesis_Outline_Report final.pdf
Storlek:
3.06 MB
Format:
Adobe Portable Document Format
Beskrivning:
License bundle
Visar 1 - 1 av 1
Hämtar...
Bild (thumbnail)
Namn:
license.txt
Storlek:
2.35 KB
Format:
Item-specific license agreed upon to submission
Beskrivning: