University of Twente Student Theses

Login

Predicting failure modes of traffic control systems by classifying unstructured data of maintenance requests

Haandrikman, BEng. Robin (2020) Predicting failure modes of traffic control systems by classifying unstructured data of maintenance requests.

[img] PDF
5MB
Abstract:This graduation assignment is conducted at Dynniq, a company that helps to manage mobility flows in society through advanced technological solutions. The company sees the need to decrease their maintenance costs due to an expected decrease in revenue on maintenance contracts. The first step towards this goal is to increase the knowledge on why systems fail and what information can be extracted from the available data set on maintenance requests and solutions. This thesis proposes a method that uses problem descriptions for classifying maintenance requests based on failure behaviour of traffic control systems. Both rule-based and machine learning algorithms are used to extract valuable information from unstructured (i.e. textual) data. These algorithms use this information to predict what a possible type of failure mode might have occurred. The model has proven to be effective, although further research is required before implementation of the model in the daily workload.
Item Type:Essay (Master)
Clients:
Dynniq, Amersfoort, Netherlands
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:50 technical science in general
Programme:Industrial Engineering and Management MSc (60029)
Link to this item:https://purl.utwente.nl/essays/82712
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page