Internship: Anomaly Detection Smart Maintenance

We offer you an Ocean of Possibilities. Join our family.

Damen aims to become the world's most sustainable and digitally connected shipyard. The Research, Development & Innovation (RD&I) department develops and implements the technology and know-how to achieve these ambitions. We actively assist the business in creating an innovative product portfolio and provide forward-thinking guidance to improve the quality and performance of Damen's products and services.

You will be joining the Data Science team within Damen RD&I located in Gorinchem. Our department focuses on applying cutting-edge data and AI solutions to Damen's shipbuilding and maritime operations. The team includes domain experts in physics-informed machine learning, simulation acceleration, predictive maintenance, computer vision, and operational analytics. This internship is part of Smart Maintenance, a strategic project aimed at using AI to detect abnormal equipment behavior on board vessels before it leads to failure or unplanned downtime.

The role:

As an intern, you will work on our Smart Maintenance project where we have developed an anomaly detection algorithm, which aims to help engineers spot early signs of equipment problems, such as engines, pumps, propulsion and cooling systems, before they escalation into failures. Vessels generate huge amounts of sensor data during operation, and our goal is to turn that data into reliable, trustworthy signals that support maintenance decisions.

You will contribute to an existing pipeline that learns what "healthy" equipment behavior looks like and flags deviations from it. Your primary focus will be on a dedicated research topic, to be selected together with the team, that strengthens a specific part of this pipeline – from data selection to detection reliability, health trending, explainability, or deployment. There is room to shape the exact topic based on your interests and background, either before or shortly after you start.

This can be a thesis/graduate internship and could start as soon as possible, depending on your availability.

• Model transferability across vessels: exploring how an anomaly detection model trained on one vessel can be adapted to other vessels, machinery types, or operating environments – including retraining, recalibration, and drift detection strategies.
• Reliable anomaly detection: improving detection models to minimize false alarms, adapt to different operating conditions, handle transient events, and quantify prediction confidence.
• Health and degradation trending: moving beyond fault detection to identify gradual performance degradation, developing health indicators that give early warning of wear or efficiency loss.
• Explainable AI and fault diagnosis: making anomaly models explainable, identifying which sensors or components drive an alert, and supporting root-cause analysis for engineers.
• Defining "healthy" operation: identifying, selecting, and validating representative data from vessels operating under normal conditions, accounting for varying operating modes and environmental influences.

• Support the development and improvement of ML-based anomaly detection models for vessel equipment.
• Preprocess and analyze sensor/time-series data from onboard systems.
• Run experiments in Python, evaluating model performance against real and/or simulated data.
• Work closely with our Data Scientists, maintenance engineers, and vessel operations stakeholders.
• Document results and present findings to the team regularly.

• Is currently pursuing a Bachelor or Master in Data Science, Applied Mathematics, Computer Science,…