For this master thesis project we have been working towards modelling

the lifetime maintenance needs of a Volvo truck. Such a model

could accurately estimate problems a truck may encounter at any

given point in time. We were provided with records from workshop

visits going back over a period of 10 years. In this thesis we have

performed an exploratory data analysis involving both data mining

and machine learning techniques in order to extract the most useful

information from it. In order to separate different types of service

events from each other two different clustering techniques have been

used. Also, an operation distinction algorithm have been created to

separate maintenance operations from repair operations on the trucks.

In this thesis we have also pointed out issues in the data and given

suggestions for continues work towards building a model of a trucks

lifetime maintenance needs.