Software Lifecycle Management Unsupervised Anomaly Detection

Abstract

The purpose of this thesis is to evaluate if unsupervised anomaly detection, the task of nding anomalies in unlabelled data, can be used as a supportive tool for software life cycle management in nding errors which are tedious to detect manually. The goal is to apply the techniques of unsupervised machine learning on data-sets that are collected and analysed from a miniature-scaled research vehicle system that resembles the operation of a real automotive vehicles electrical architecture. Using a stacked autoencoder implemented with TensorFlow, the nal application is able to detect anomalies within the collected data-sets from the research vehicle. This proves the concept of utilising machine learning for error detection as a viable method. Finally concluding whether the techniques of unsupervised anomaly detection is applicable on a larger scale for real automotive vehicles.