(pagina in aggiornamento)
- 09.30 - 10.00: Digital Twin Framework for Detecting and Correcting Static Yaw Misalignment in Wind Turbines
-
Static yaw misalignment in a wind turbine occurs when the rotor plane is not oriented perpendicular to the incoming wind, often due to faulty wind sensors on the nacelle or installation errors. This misalignment leads to decrease turbine efficiency, reduced power generation, and increased mechanical stresses on turbine components.
Digital Twin (DT) modeling enables continuous, real-time evaluation of operational performance, allowing for the detection of anomalies and inefficiencies at an early stage. By integrating real-world data with high-fidelity simulations, DT models offer predictive insights that enhance decision-making, support proactive maintenance strategies, and reduce unplanned downtime.
This paper introduces an advanced DT approach for detecting and correcting static yaw misalignment in micro wind turbines, with the potential for scalability to larger turbines.
The proposed DT method models the aerodynamic behaviour of the micro wind turbine. CFD simulation information is used to analyse the airflow and power generation, enabling the identification of discrepancies between virtual and real operating performance, which indicate the presence of static yaw misalignment. Upon detecting a misalignment, the DT model can provide the necessary corrective measures to realign the turbine with the prevailing wind direction, thereby optimising its aerodynamic performance and enhancing the overall operational efficiency of the system. - 10.00 - 10.30: Predictive Maintenance System for Bridges Based on BIM and Digital Twin
-
Many bridges in Europe are approaching the end of their design service life, leading bridge maintenance to a high priority. Among the existing maintenance methods, Predictive Maintenance
(PdM) is an advanced approach utilizing monitoring data, to predict the future condition of the structure based on its current condition and reduce the chance of failure events by optimizing maintenance actions. This method can increase safety and minimize massive maintenance costs.
However, the limited knowledge level in bridge conditions (geometrical and
structural) proposes significant obstacles, making maintenance planning difficult. Additionally, integrating various information sources and dealing with large monitoring datasets (SHM data) in this method is a major challenge.
Digitalization of the bridge offers potential solutions through Building Information Modelling (BIM) technology, which facilitates the integration of available information, organized chronologically into the past (e.g. inspection results and previous maintenance), present (e.g. current geometry, mechanical properties, defects, and environmental conditions), and future (e.g. maintenance planning and predictions). This approach also allows for efficient database management. Further advancement in BIM maturity level evolves it into Digital Twin (DT) technology, allowing real-time connection between the digital model and physical structure, thus facilitating continuous monitoring and structural assessment for immediate decision-making.
This research explores the development of a digitalized PdM system for a bridge case study by utilizing data obtained from a laser scanner and drone to enhance the knowledge level of the structure and defect detection, providing an effective monitoring system for the structure (Project GIANO), data integration and management, and structural assessment using BIM technology. - 11.00 - 11.30: Studio sperimentale sul monitoraggio in real time di un processo di saldatura GMAW robotizzato attraverso indagini termografiche
-
Questo studio si propone di identificare i difetti tipici della saldatura nel processo GMAW attraverso tecniche di monitoraggio in tempo reale. Durante l'esecuzione della saldatura, i dati vengono acquisiti da una termocamera che inquadra il bagno di fusione e il cordone. Le informazioni raccolte sono state analizzate per individuare correlazioni tra i parametri monitorati e le eventuali anomalie o difetti riscontrati.
L'obiettivo è gettare le basi per lo sviluppo di sistemi di addestramento e ispezione basati su intelligenza artificiale, al fine di migliorare sia l’apprendimento dei saldatori che la qualità dei manufatti.