Press conference:

LATODA, a pioneer in artificial intelligence (AI) solutions, Germany’s Bundesanstalt für Materialforschung und -prüfung (BAM) and Romotioncam have completed an innovative R&D project “KI-VISIR” focussing on transforming wind turbine blade inspection and maintenance.

 

This on-going collaboration aims to enhance the efficiency of wind energy production by addressing one of the industry's most pressing challenges—rotor blade damages caused by environmental factors, particularly rain erosion.

 

The Challenge: Maximizing Wind Energy Efficiency

 

Wind turbines play a key role in achieving global climate targets. However, their efficiency depends heavily on the condition of the rotor blades, which convert wind into kinetic energy. Rotor blades are highly developed aerodynamic structures that are designed for optimum flow conditions. A key problem for their performance is erosion at the leading edge of the rotor blades. When rain or other particles hit the blades, microscopic damage can occur, leading to erosion damage over time. Such damage may cause an early transition from laminar to turbulent flow, which significantly reduces aerodynamic efficiency. The result is reduced energy production, which can amount to up to 3.7 % of annual energy production.

 

In addition, the new inspection technique can detect internal structural damages at an early stage, helping to avoid blade failures, and unintended turbine downtime. Precise, AI supported results of rotor blade inspections are also important and crucial for warranty claims. Existing methods of wind turbine inspections could be substantially improved in order to provide operators of wind parks with much better decision-making on what to maintain, repair or replace.

 

Collaborative Effort with BAM and Romotioncam

 

Thermographic inspection has become established as an effective method for the early detection of erosion damages. In this process, the temperature distribution on the surface of the rotor blades is measured using an infrared camera. Turbulence caused by surface damage changes the local temperature of the blade. These temperature differences can be visualised in thermograms. They reveal complex interactions between internal structures of rotor blades, thermal properties of material, solar radiation and wind flow, which require precise analysis to distinguish actual damage from harmless surface effects.

 

A decisive advance in inspection technology is the use of artificial intelligence (AI) for automated image evaluation. Visual and thermographic inspection from the ground allows for a quick and cost-effective analysis. However, the challenge lies in interpreting the data, especially in the case of thermographic images: Thermograms are complex and contain a wealth of information that is difficult for inexperienced observers to interpret. This is where AI comes into play.

 

By using convolutional neural networks (CNN), the captured data can be automatically analysed and damage patterns identified. These algorithms are able to detect the smallest changes in temperature distribution and precisely indicate possible damages. A major advantage of this method is the ability to carry out inspections without interrupting operations, and to identify roughness areas on blades at an early stage, which already cause efficiency losses and which may evolve in erosion damages over time.

 

Joint research project “KI-VISIR” produced reference data set

 

As part of the KI-VISIR project (artificial intelligence visual and infrared thermography), thermographic and visual inspections were carried out on a total of 30 wind turbines. The open source, free of charge comprehensive reference data set will allow researcher to compare the results of both inspection methods and improve the efficiency of AI-based image evaluation. The dataset includes over 2.200 visual images and more than 1.200 thermograms taken under various turbine operating conditions.

The reference dataset is free and can be downloaded here: https://zenodo.org/records/13771900

 

 

Ground-based AI image evaluation for No-Downtime inspections

 

Romotioncam conducted all visual inspections and at the same time harmonized image taking with thermograms. Condition monitoring of rotor blades have been revolutionized by Romotioncam which has developed a patented blade inspections method which captures high-resolution images whilst the turbine blade is in full operation. By eliminating downtime, wind turbines can operate at their full capacity, ensuring a steady supply of renewable energy and reducing the reliance on carbon-intensive alternatives.

 

Romotioncam combines No downtime inspections with advanced data analytics and monitoring technologies from LATODA. Continuous data collection allows for predictive maintenance, where potential issues are identified and addressed before they lead to significant problems. This proactive approach reduces the need for emergency repairs and the associated environmental costs, such as urgent transportation and rapid deployment of repair crews. Predictive maintenance thus ensures a more sustainable and environmentally friendly operation.

 

Reference data set promotes further research

 

The benefits of the reference-dataset for the industry and research sector are manifold. On the one hand, it enables the training and development of AI algorithms for the detection of blade damage related pattern. It also helps that AI systems can be further refined and their accuracy in damage detection can be increased. On the other hand, it offers researchers and developers the opportunity to test and validate new methods for improving wind turbine damage assessments and inspection. The dataset also demonstrates the importance of real, high-quality measurement data for training modern AI systems. The availability of this data will enable wind farm operators and maintenance companies to optimise their inspection processes and extend the service life of their turbines.

 

LATODA's AI-Driven Solution

 

LATODA has developed an advanced AI-system that sets a new standard in the industry in terms of automated detection and assessment of blade damages. By integrating training data from cutting-edge thermographic and visual imaging techniques, LATODA's solution not only detects visible damages but also uncovers potential hidden issues beneath the blade surface that would otherwise go unnoticed. The system assesses leading edge rain erosion and calculates the estimated losses in Annual  Energy Production, supporting data-driven operation and maintenance decisions that increase turbine performance and reduce repair costs.

 

AI models developed by LATODA are designed to precisely identify, localize, and categorize rain erosion damages as well as aerodynamic effects. This innovative approach significantly improves the accuracy and comprehensiveness of blade condition monitoring, surpassing the capabilities of conventional human visual inspections.

 

Benefits for the Wind Energy Industry

 

LATODA's AI solution offers wind turbine operators and inspection companies unprecedented control over their visual data. Through a user-friendly, stand-alone platform, inspection companies can quickly upload inspection images and download comprehensive AI-based analyses of blade damages and their impact on overall energy efficiency. This streamlined process not only reduces manual work involved for inspection image processing and damage detection, but also enhances decision-making, leading to increased turbine efficiency and lower maintenance costs.