Machine Learning on Quality Test Processes
About this opportunity
Mobile networks are used all over the world and is the corner stone for the networked society, where everything shall be connected. Microwave and MINI-LINK are vital products into this communication network. They combine RAN network with the backhaul network, and can be seen in mobile masts, up on the roof tops, or on housing walls.
Our unit is responsible for supply product quality and supply test development of Ericsson´s MINI-LINK product portfolio.
Do you want to take the opportunity to shape the Microwave future of technology with us?
What you will do
This thesis strives to apply Machine Learning on data sets coming from a Temperature Quality Test (TQT) which is performed to ensure and understand product performance over time in both product development and volume production phases. The expected outcomes of the thesis are:
- Understand the different datasets coming from the TQT concept
- Apply Machine Learning methods to explore the TQT concept
- Select relevant Machine Learning methods for predictive modelling
- Explore the possibilities for deep learning
- Explore significant external factors that can influence the results
- Recommend future areas to focus on when it comes to Machine learning/Deep Learning implementation on existing test flows
- Visualize test results trends in a way which makes us aware of future expected results
A major part of the work can be done remotely using teams as a collaborative tool, with some periods needing more face to face and direct interaction at Ericssons facilities in Borås.
The thesis will be concluded with a presentation of the results for the Ericsson R&D and Supply team.
You will bring
This project aims at M.Sc students in Mathematics, Statistics and Machine Learning. Knowledge about GIT/GITLab and programming experience is a must.