In recent years more data is logged from the electronic control units on-board in commercial vehicles. Typically, the data is transferred from the vehicle at the workshop to a centralized storage for future analysis. This vast amount of data is used for debugging, as a knowledgebase for the design engineer and as a tool for service planning.
Manual analysis of this data is often time consuming, due to the rich amount of information contained. However, there is an opportunity to automatically assist in the process based on knowledge discovery techniques, even directly when the trucks data is first offloaded at the workshop. One typical example of how this technique could be helpful is when two groups of trucks behave differently, e.g. one well-functioning group and one faulty group, when the two groups have the same specification. The desired information is the specific difference in the logged data, e.g. what particular sensors or signals are different.
An evaluation cycle is proposed and applied to extract knowledge from three different large real-world data-sets measured on Volvo long haulage trucks. Information in the logged data that describes the vehicle’s operating environment, allows the detection of trucks that are operated differently from their intended use. Experiments to find such vehicles were conducted and recommendations for an automated application are given.
