This paper aims to define the challenges and requirements necessary for the holistic management of wind turbine blades at the end of their service (EoS). Conducted within the Swedish research project Circublade, this study focuses on Sweden, although many challenges and findings are applicable to other countries. Various alternatives for managing EoS wind turbine blades exist at different levels of market maturity, but this paper specifically focuses on repurposing the blades into new products. The development of three concept designs—short-span pedestrian bridges, façade elements for building applications, and noise barriers for roads and railways—has been explored, along with aspects related to material sourcing, logistics, and implementation. For material sourcing, a digital platform containing blade data and tools to facilitate repurposing has been developed. An environmental evaluation of the different concepts highlights the significant impact of transportation on the overall environmental footprint, underscoring the necessity of a holistic approach to managing EoS blades.

We demonstrate the construction of robust counterfactual explanations for support vector machines (SVM), where the privacy mechanism that publicly releases the classifier guarantees differential privacy. Privacy preservation is essential when dealing with sensitive data, such as in applications within the health domain. In addition, providing explanations for machine learning predictions is an important requirement within so-called high risk applications, as referred to in the EU AI Act. Thus, the innovative aspects of this work correspond to studying the interaction between three desired aspects: accuracy, privacy, and explainability. The SVM classification accuracy is affected by the privacy mechanism through the introduced perturbations in the classifier weights. Consequently, we need to consider a trade-off between accuracy and privacy. In addition, counterfactual explanations, which quantify the smallest changes to selected data instances in order to change their classification, may become not credible when we have data privacy guarantees. Hence, robustness for counterfactual explanations is needed in order to create confidence about the credibility of the explanations. Our demonstrator provides an interactive environment to show the interplay between the considered aspects of accuracy, privacy, and explainability. 

The Rekovind2 project, financed by the Swedish Energy Agency, focuses on digitizing wind turbine blade streams for reuse and recycling. This is of the utmost importance to enable new, more circular technical solutions that can replace today’s non-sustainable recycling, i.e. landfill and incineration of wind turbine blades. In this report, the work carried out to map the wind turbine blades in service in Sweden is presented. The digital platform intended to make possible the re-use of blades reaching end-of-life is build around key features that will be required for re-use: blade database with all needed informations on the blade (age, damages, material, model, ...), map with blades geolocation, digital tool to help blade processing such as cutting, and information on what can be done with EoL blades.

We demonstrate the construction of robust counterfactual explanations for support vector machines (SVM), where the privacy mechanism that publicly releases the classifier guarantees differential privacy. Privacy preservation is essential when dealing with sensitive data, such as in applications within the health domain. In addition, providing explanations for machine learning predictions is an important requirement within so-called high risk applications, as referred to in the EU AI Act. Thus, the innovative aspects of this work correspond to studying the interaction between three desired aspects: accuracy, privacy, and explainability. The SVM classification accuracy is affected by the privacy mechanism through the introduced perturbations in the classifier weights. Consequently, we need to consider a trade-off between accuracy and privacy. In addition, counterfactual explanations, which quantify the smallest changes to selected data instances in order to change their classification, may become not credible when we have data privacy guarantees. Hence, robustness for counterfactual explanations is needed in order to create confidence about the credibility of the explanations. Our demonstrator provides an interactive environment to show the interplay between the considered aspects of accuracy, privacy, and explainability.

We consider counterfactual explanations for privacy-preserving support vector machines (SVM), where the privacy mechanism that publicly releases the classifier guarantees differential privacy. While privacy preservation is essential when dealing with sensitive data, there is a consequent degradation in the classification accuracy due to the introduced perturbations in the classifier weights. Therefore, counterfactual explanations need to be made robust against such perturbations in order to ensure, with high confidence, that the explanations are valid. In this work, we suitably model the uncertainties in the SVM weights and formulate the robust counterfactual explanation problem. Then, we study optimal and efficient suboptimal algorithms for its solution. Experimental results illustrate the connections between privacy levels, classifier accuracy, and the confidence levels that validate the counterfactual explanations.