Thesis worker - Physics-Aware Multiclass Root-Cause Classification of AC System Faults

Teknik, data och digitalt · Data, AI och analys · Dataanalys · Maskininlärning · Mjukvaruutveckling

I korthet

This thesis project focuses on developing and evaluating a physics-aware multiclass classification framework for AC system faults. The work involves analyzing refrigerant-loop faults, distinguishing between various fault types using sensor data and physics-derived features, and comparing different classification methods.

Ansvarsområden

Develop and rigorously evaluate a physics-aware multiclass classification framework for five refrigerant-loop health states.
Investigate separation of low refrigerant charge from expansion-valve underfeeding.
Investigate separation of refrigerant-side faults from abnormal compressor performance.
Analyze diagnostic accuracy, availability, and uncertainty of observer-based versus directly measured pre-expansion-valve information.
Assess the effect of TXV versus EXV hardware and its interaction with the state-information method.
Evaluate generalization to unseen hardware units and test sessions.
Calibrate class probabilities and implement an operating-domain and confidence-based inconclusive result.
Validate performance and diagnostic coverage by complete hardware unit and test session.
Define the next-stage production-validation plan.

Krav

Thesis work for 30hp
Start date: 1st of February 2027
Estimated time required: 5 months
CV, personal letter, and transcript of grades required for application.
Background check might be conducted.

Önskade kvalifikationer

Physics-Aware Multiclass Root-Cause Classification of AC System Faults knowledge
Experience with observer-based and direct-sensor methods
Understanding of TXV and EXV hardware and control dynamics
Familiarity with quantized refrigerant-property calculations
Knowledge of healthy references for discharge temperature and steady-state compressor power

Förmåner

Excellent way to get closer to Scania and build relationships for the future.
Many of today's employees began their Scania career with their degree project.

Färdigheter

Data AnalysisPhysicsMachine LearningClassification

#Physics-Aware#Multiclass Classification#AC System Faults#Thesis#Scania#TRATON#Refrigerant-loop faults#Data Quality#Machine Learning#Thermostat#Compressor#TXV#EXV#Observer-based#Direct-sensor

Om Scania Group

Scania is a world-leading provider of transport solutions committed to a better tomorrow. Our purpose is to drive the shift towards a sustainable transport system. In doing so, we are creating a world of mobility that’s better for business, society and our environment. Employing more than 50,000 people in about 100 countries, Scania’s research and development is concentrated in Sweden, while production takes place in Europe and South America.

Se alla lediga jobb hos Scania Group Läs mer om Scania Group Webbplats