Samuel Loureiro
PhD
Noise and Performance Prediction in Wind Farms Using Mobile Sensor Units
Host organisation
DTU, Department of Wind and Energy Systems
Project Description
This project aims to develop methodologies to estimate noise emissions from wind turbines and predict their performance using mobile sensor units distributed throughout a wind farm. By combining acoustic, environmental, and SCADA data with hybrid physics-informed AI models, the project aims to isolate individual turbines’ noise signatures and understand how atmospheric conditions influence noise propagation. It further investigates virtual sensing of key operational variables - such as yaw misalignment, rotor speed, and power output - to reduce dependence on physical sensors. Validated through real data provided by an industrial partner, the project will support future noise‑aware control strategies and contributes to IntelliWind’s vision of intelligent, autonomous wind‑farm operation.
​
Supervisors
Nikolay Dimitrov
Athanasios Kolios
Background
I was born in Fragoso, a small village in northern Portugal. For the past six years, I’ve lived in Porto where I completed both my Bachelor’s and Master’s degrees in Electrical and Computer Engineering, specializing in Automation. During my Master’s, I joined the DIGI2 Lab as a Research Fellow, where I developed my dissertation in the field of Predictive Maintenance. After that, I continued pursuing my passion for innovation at INEGI, an R&D institute, developing Predictive Maintenance solutions for industrial partners.
Outside of engineering, I have a keen interest in geopolitics, history, and handcrafted beer - a fantastic trio for a pleasant afternoon. I also enjoy playing sports and board games with friends.
Motivation
Witnessing Europe’s recent energy and geopolitical crisis reinforced my belief that advancing renewable energy technologies is not just a technical challenge, but a societal imperative.
This project offers a unique opportunity to contribute to that mission by improving turbine-specific noise estimation and diagnostics - key factors for increasing wind-farm efficiency and public acceptance. Its interdisciplinary focus on distributed sensing, hybrid AI models, and virtual sensing, aligns strongly with MSCA’s commitment to innovation and societal impact.
With my background in automation and predictive maintenance, I am eager to apply my knowledge to strengthen Europe’s green economy and help accelerate the transition toward a resilient, carbon-neutral energy system.
