Master Thesis Automated Sensor Recalibration & Failure Classification for Intelligent Sensor Networks
Core
Develop a system to distinguish between physical hardware sensor failures and software-related drifts in industrial machinery, enabling automated software-based recalibration.
Role type
Master Thesis Researcher (Sensor Systems & Machine Learning)
Builds
Self-calibrating sensor systems for industrial machinery
Domain
Industrial automation, sensor technology, machine learning
Deliverable
production ML models | infrastructure
Required skills
Python programming, data analysis, machine learning classification, physical measurement principles, sensor technology, Git/GitHub
Preferred skills
Data science libraries (Pandas, NumPy, Scikit-learn), industrial automation knowledge
Technologies
Python, Pandas, NumPy, Scikit-learn, Git, GitHub
Responsibilities
Conduct physical measurements on a ball screw drive test bench to record healthy and failure sensor data; Analyze pre-detected datasets containing software-related sensor deviations; Determine criteria distinguishing software-correctable drift from physical hardware failure; Research and evaluate software-based recalibration techniques; Design an automated workflow for sensor recalibration and validation; Propose strategies for handling physical anomalies not solvable by software.
Seniority
Master's level research project