Extraction of Failure Graphs from Structured and Unstructured Data

Author

Schierle, Martin ; Trabold, Daniel

Author_Institution

R&D, Daimler AG, Ulm

fYear

2008

fDate

11-13 Dec. 2008

Firstpage

324

Lastpage

330

Abstract

Quality analysis in the automotive domain is up to now mainly focused on structured data obtained from repair visits, using for example association rules or decision trees on model families, model years and damage codes. This work will outline a way to extract failure graphs from textual repair orders using taxonomy based concept recognition, significant co-occurrences and graph clustering methods. We will furthermore combine unstructured data with structured data and demonstrate the benefits of this method for root cause analysis in the automotive domain.

Keywords

automobile industry; data mining; decision trees; failure analysis; maintenance engineering; pattern clustering; association rule; automotive quality analysis; co-occurrence method; damage code; decision tree; failure graph extraction; graph clustering method; model family; model year; root cause analysis; structured data; taxonomy based concept recognition; textual repair order; unstructured data; Association rules; Automotive engineering; Clustering algorithms; Data analysis; Data mining; Decision trees; Failure analysis; Machine learning; Research and development; Taxonomy; Automotive Quality Analysis; Cooccurrence Graphs; Failure Graphs; Graph Clustering; Small World Graphs; Text Mining;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Applications, 2008. ICMLA '08. Seventh International Conference on

Conference_Location

San Diego, CA

Print_ISBN

978-0-7695-3495-4

Type

conf

DOI

10.1109/ICMLA.2008.76

Filename

4724993