AI-Driven SCR Emission Control in SiL Environment

Scania; Stjärna; On-site; SEK 150,000 - 225,000; Full time

Job summary

Scania Nederland B.V. offers a master thesis project focusing on AI-based closed-loop SCR control in a SiL environment.

The work will use measured test data and synthetic data to develop data-driven control methods for dosing and emission control within a VTAB-based virtual powertrain. The requirement includes a background in machine learning, AI, and control engineering, with emphasis on handling large datasets and validating models in a simulated vehicle environment.

Qualifications

• Master's level education in ML/AI/control engineering/applied mathematics.
• Understanding of mathematical models and physical functions used in control systems.
• Experience handling, processing and analysing large data sets.

Responsibilities

• Literature study on SCR control, machine learning and AI-based control methods.
• Collect, structure and quality‑assure large volumes of test data.
• Select relevant control-system signals and define model inputs, outputs and constraints.
• Develop and train an AI model for SCR dosing and emission control.
• Integrate and evaluate the model in a virtual truck powertrain SiL environment.
• Compare performance with an existing reference SCR control model.
• Analyse robustness, accuracy, limitations, calibration effort and implementation potential.
• Document the methodology and present the results in a master thesis report.

Skills

Machine learning

Artificial intelligence

Control engineering

Applied mathematics

Education

Master's degree in ML/AI/Control Eng./Applied Math.

Job description

Scania Nederland B.V. offers a master thesis project focusing on AI-based closed-loop SCR control in a SiL environment.

The work will use measured test data and synthetic data to develop data-driven control methods for dosing and emission control within a VTAB-based virtual powertrain. The requirement includes a background in machine learning, AI, and control engineering, with emphasis on handling large datasets and validating models in a simulated vehicle environment.