VALIDATION
Use Cases
Discover the Power of UNDERPIN Data Space with Two Dynamic Pilots
Our two pilots serve as real-world demonstrators in dynamic asset management and predictive maintenance, spotlighting the full potential of UNDERPIN Data Space. With a focus on refineries and wind farms, these pilots highlight cross-domain data utilization, management methods, analytics, and valuable lessons learned. By exemplifying best practices, they pave the way for future implementation, fostering the expansion of Data Space mechanisms.
These initiatives validate the benefits of industrial data sharing, particularly enhancing operations for SMEs, the primary stakeholders in these sectors. Join us as we showcase innovation and drive impactful change.
Join us as we showcase innovation and drive impactful change.
USE CASE 1: REFINERIES
The primary objective of UC1 is to enhance operational efficiency, streamline maintenance processes, and optimize decision-making regarding preventive maintenance scheduling. The aim is to minimize downtime and its adverse effects on production capabilities by addressing anomalies spanning the entire production chain, not limited to individual components.
Leading example in the field of critical manufacturing:
For nearly a decade, industry-leading refinery operators like Motor Oil Hellas (MOH) have made substantial investments in digitizing their production data. This involves deploying sensors and cyber-physical systems to collect and manage a vast amount of raw data. Various sensors, including those for pressure, temperature, vibration, and axial displacement, contribute to the data stream. Current processes analyze these data streams on an hourly basis to detect abnormalities and predict the behavior of individual compressors, enabling proactive identification of potential issues.
The UC aims to collect, process, and perform quality control on data volumes exceeding 2 TB per year from a variety of sources. It seeks to establish new predictive models that leverage data sets emerging from ongoing vendor measurements and observations from operational use. Additionally, the project plans to expand the scope of predictive maintenance processes to detect anomalies associated with more complex observations. Furthermore, it will create a subset of the data that is sanitized (cleaned and anonymized) and annotated to guide the development of new algorithms and models by third-party users and providers.
USE CASE 2: WIND FARMS
Within Wind Turbine Generators (WTGs), sensitive electrical systems and critical mechanical components installed inside the nacelle and the tower are prone to failures. While electrical failures are more frequent, mechanical failures, such as those in the gearbox, bearings, shafts, yaw, and pitch systems, are costly and have a significant impact on WTG performance, leading to prolonged downtimes, high maintenance costs, and production losses.
Leading example in the field of renewable energy production
The UC aims to implement a robust predictive maintenance system for wind turbines by developing an advanced ML model capable of predicting equipment failures and identifying abnormal behavior trends. This involves collecting data from various sources, such as SCADA systems, maintenance records, and vendor measurements. The collected data undergoes thorough processing and quality control to ensure accuracy and privacy, followed by the development of machine learning models trained with historical failure data and normal operational patterns. Once deployed, the ML model will monitor wind turbine operations in real-time, continuously updating with new data to enhance prediction accuracy. The expected outcomes include reduced downtime, as the asset owner can take proactive measures to address potential failures, and an extended lifespan for the wind turbines by identifying issues before they escalate. Additionally, the asset owner will be able to evaluate the performance of maintenance contractors more effectively by tracking their responses to predicted issues and their ability to prevent equipment failures.
Another focus of the UC is on developing an automated data aggregation and processing tool designed to determine the wind turbine’s (WT) power curve based on historical data. This tool will streamline processes such as insurance claims, reducing the necessary manpower by automating data collection and analysis. Additionally, it will enable the asset owner to benchmark the actual performance of the wind turbines against expected performance metrics, providing insights to optimize overall turbine performance. The expected outcomes include increased operational efficiency, improved accuracy in performance assessments, and enhanced ability to manage and optimize wind turbine operations.
The UNDERPIN Data Space is meticulously crafted to be durable, secure, and fully compliant with EU standards. Our goal is to establish new benchmarks for performance, cost reduction, and durability in industrial applications, paving the way for innovation and excellence.