Data-Driven Modeling and Experimental Analysis of Intelligent Air Management System in Electronic Air Control Units

Type of work:

Master thesis

Assignment:

During this thesis, the student will focus on developing a data-driven model to analyse drying in Oil Separation Cartridges of EACUs. The work includes experimental validation with a custom test bench and Vector CANoe tool, introduction of empirical correction factors, and a Python dashboard workflow for real-time monitoring, which provides a basis for future research in intelligent air management systems.

Skills:

• Python programming (pandas, asammdf, numpy, matplotlib)
• Data analysis and statistical modeling
• Simulating and monitoring data communication protocols (Vector CANoe)
• MDF file processing and time-series analysis
• Dashboard development and data visualization
• Test bench design and experimental validation
• Signal processing and pattern recognition
• Knowledge of automotive air management systems

Background:

Electronic Air Control Units (EACUs) are essential for managing air quality in commercial vehicle braking systems, but existing models do not accurately reflect real-world performance. Vector CANoe is a comprehensive software tool used for development, testing, and analysis of automotive and embedded systems.

Supervisor:

H. Bilal

Student:

Muhammad Zubair Radhan

Year:

2025