Alstom is a multinational rolling stock manufacturer operating worldwide in rail transport markets, active in the fields of passenger transportation, signalling, and locomotives.
Alstom’s portfolio covers the full spectrum of solutions, ranging from trains to sub-systems and signalling to complete turnkey transport systems, e-mobility technology, and data-driven maintenance services. Combining technology and performance with empathy, Alstom continuously breaks new ground in sustainable mobility by providing integrated solutions that create substantial benefits for operators, passengers, and the environment.
Alstom currently offers 13 degree projects:
- Propulsion performance optimization by increased utilization of SiC MOSFETs:
Analyze how increasing utilization of Silicon Carbide (SiC) MOSFET Safe Operating Area (SOA) in traction converters can result in smaller traction motors and improved electric traction performance.
- Propulsion system digital twin linking test with simulation data:
Build a digital twin container to correlate actual measured test data with simulated data and improve the simulation models.
- New GUI for performance simulation tool:
Develop a new state-of-the-art Graphical User Interface for our powerful in-house performance simulation tool for electric railway traction systems.
- Test bed and methods for ML/AI battery characterisation:
Develop and design test equipment and methods to characterize state-of-health of electric railway traction batteries (part of a larger PhD project).
- Natural Language Processing (NLP) based requirements analysis:
Test NLP methods to automatically allocate requirements from customer specifications to appropriate engineering functions by labelling training data (part of a larger PhD project).
- Survey of indirect predictive maintenance methods in traction motors:
Survey and theoretically assess various methods to detect traction motor bearing wear from motor current signatures.
- Evaluation test bed for indirect predictive maintenance methods in traction motors:
Design test bed and experiments to test methods that detect traction motor bearing wear from motor current signatures.
- Real time ML parametrization of component digital twins in traction controller:
Test and evaluate one or more machine learning algorithms to parametrize control models of railway traction components, creating a digital twin in the traction controller.
- On-board edge data collection and processing device implementation:
Verify a python3 application in a Real Time Simulator environment for traction controller data processing. Develop a Smart Data Collector for IPTCom/TRDP networks.
- Investigation of increased limits for utilization of SiC MOSFETs:
Test increased utilization limits for Silicon Carbide (SiC) MOSFET Safe Operating Area (SOA) in traction converters.
- Railway equipment anomaly detection with failure biased data:
The main objective of the master’s thesis is to identify methods for anomaly detection of logs collected on deviations and errors in our train control systems and their sub-systems.
- Onboard platform performance measure:
We are working on platform that includes both hardware and software. Those platforms are part of onboard system called ETCS. We are continuously using the feedback from field to reinforce our testing. Your main responsibility will be to support the team in measuring the performance of the platform.
- Fault slip through analysis:
To analyze and measure which defects that slip through our current test activities and to the customer.