30 credits – Go fishing in Scania’s data lake and improve components’ life length prediction i Sodertalje

Scania is undergoing a transformation from being a supplier of trucks, buses and engines to a supplier of complete and sustainable transport solutions.

Background
Scania is one of the world’s leading manufacturers of trucks and buses for heavy transports, and have more than 500,000 connected vehicles. Modern vehicles contain a large number of sensors and collect an enormous amount of data. These data are stored on the vehicles’ computers and on Scania’s servers.
A key factor in the shift towards sustainable transport solutions is uptime, therefore the risk for unplanned maintenance stops must be minimized. For achieving this it is important to predict when components should be replaced.

At Materials Technology, we study properties of materials, interactions of the engine fluids with materials and try to predict how long things last in operation.
At Connected Intelligence, we have access to the whole data lake and build statistics and make use of the data for improving maintenance plans.

There are two ways of predicting life length for components. One way is to build an engineering model describing how physical processes affect the components over time. The other way is to look at how long components actually last in real world’s applications. The best way is a combination of the two, therefore we work cross-functionally to improve lifelength predictions.

Target
Correlate vehicles’ operational data with lifelength of components.
Design a methodology to create an atlas, a collection of geographical and conceptual maps, over selected components, parameters and fault codes.

Assignment
You will access a large amount of information about where the vehicles are operated, how they are used and when they run into problems. You will select relevant variables and find correlations among them. You will design a methodology to visualize these correlations and tools to predict lifelength.
You will have access to Scania’s expertise in the form of data scientists, development engineers and material experts.

Education and skills
The ideal candidate is independent and driven, enjoys understanding complex systems and explaining them in simple ways.
A suitable education background is computer science, physics, mathematics or similar. If you study any other engineering discipline and are interested in data, statistics, and machine learning, this might be the thesis work for you.

Start date: Jan/Feb 2020
Duration: 20 weeks
Number of students: 1

Contact persons and supervisors
Francesco Regali, Senior Engineer, Materials Technology, 08 553 70842,
Peter Lindskoug, Senior Engineer, Connected Intelligence, 08 553 83151,