Windpower Data and Digital Innovation Forum

Move focus from a Theoretical Big Data Approach to a Clear Digital Wind Strategy

• What does the digital future hold?
• Put strategy not technology in the driving seat.
• Incorporating big and thick data.
• Leave no person behind.
• How to plan a strategy

Panel Discussion with Interactive Q&A

Digital Wind Farm Ecosystem-Trends, Challenges and Path through Machine Learning & AI

• Is digitalization the future of wind farm?
• Why is AI relevant to the wind industry?
• What is the state of wind market in terms of the adoption of AI?
• What is the role of artificial intelligence/deep learning in optimizing turbine performance?
• How can we apply machine learning & AI for cost reduction and performance improvement?
• Exploring AI’s potential for wind turbine fault detection
• Shaping tomorrow: AI and the future of wind turbines
• Understand how to optimize maintenance strategy, improve reliability and availability and increase annual energy production

Digitalization – A Practical Approach

• Why go digital
• How to approach digitalization practically (from sensor data to practical use)
• Some examples

Wind O&M in the Era of Digitalization

• The evolution of the industry
• Drastically reducing OPEX through digitizing O&M
• Fleet performance analysis strategies

How Big Data & AI Can Help to Optimise a Wind Farm Performance: A Full Overview

• Wind Farm Optimization Overview: Power Generation and Asset Maintenance & Life Cycle
• Big Data Infrastructure and Data Collection
• AI algorithms deployment: Analytics on Streaming
• Delivery and Implementation

Panel Discussion with Interactive Q&A

Picking the Patterns. Using high level Data to Assess Performance Quickly and Easily

• Why use big data?
  • Discuss the key benefits of using big data to:
    • Help spot issues that may only affect parts of the site,
    • Help maintenance teams focus their onsite work,
    • Spot issues earlier,
• I have all this data, what do I do with it?
  • Picking key data to flag issues
  • Processing this data
• What does this data tell me?
• Examples of issues spotted and how they are/could be resolved

Digital Wind Asset Performance Management

• How can you make your windfarm operation more reliable while ensuring optimal performance?
• Intelligent asset strategy- collecting and managing data and information to make the best decisions that help maximize overall asset and operational performance
• Using Big Data and machine learning to detect windfarm performance
• Data analytics and machine learning algorithms for windfarm performance monitoring
• Understanding windfarm performance requires combining traditional high-performance computing (HPC) with modern ‘big data’ techniques — neither are sufficient on their own

Data Mining and Machine Learning Models for Fault Detection and Turbine Performance

• Using machine learning techniques to predict turbine performance and fault detection
• Drivers for key turbine performance and key inflow conditions affecting turbine performance
• Predicting component failures with existing monitoring data
• Using machine learning to create turbine performance models
• Applying a machine learning algorithm to a large dataset of power performance test data
• Using an aero-elastic turbine model to predict performance

Case Studies on Application of Data Analytics to Wind Turbines

• Case studies of application of big data techniques to wind turbine data
• Prognostic failure detection
• Benchmarking across large data sets
• Diagnostics of historical performance

Performance Optimization and Monitoring for Enhanced Wind Farm Operations

• Increase wind farm performance and demonstrate improvements
• Permanently monitor the input parameter to wind farm
• Ensure maximal output - performance monitoring over lifetime
• Predictive maintenance: use cases & key enabler

Performance Monitoring Systems for the Wind Industry

• Gain an insight into monitoring processes and performances of wind fleets and how this will help improve performance
• Understand how improving performance monitoring systems could be used to maintain the high levels of safety within windfarm projects
• Take away strategies to improve performance monitoring within your plant developing quick practice you can follow and taking away other experiences from other plants

Implementing Monitoring and Diagnostics in Windfarm

• Hear about from experience of implementing monitoring and diagnostics centre in wind fleet to improve plant performance monitoring
• Understand the lessons that have been learned during this implementation, and the challenges overcome to improve the ability to detect anomalies, defer time based predictive maintenance and reduce overheads in engineering and maintenance
• Hear how the IT and Engineering teams are successfully worked together to move forward with implementing an advanced monitoring and diagnostics centre

Panel Discussion with Interactive Q&A

New Digital Intelligent Conditional Monitoring System for Windfarm

• Using machine learning to enhance the efficiency
• Reducing maintenance down-time and theoretically allowing the plant to generate an additional 1% of extra energy
• Reducing unplanned downtime, false positive alerts and operations and maintenance costs

Performance Optimization and Monitoring for Enhanced Windfarm Operations

• Increase windfarm performance and demonstrate improvements
• Permanently monitor the input parameter to windfarm
• Ensure maximal output - performance monitoring over lifetime
• Predictive maintenance: use cases & key enabler

Big Data and Advanced Analytics for Predictive Maintenance

• Data scientific on predictive maintenance
• Advanced analytics on maintenance management
• Decision making based on big data

Windfarm O&M in the Digital Era

• Digitalization: - key drivers to optimized wind operations and improved efficiency
• Moving towards digitizing wind operations excellence and analytics based on predictive models
• Leveraging the Industrial Internet of Things for maximum asset reliability
• The impact of data analytics on windfarm O&M
• Predictive tools & methodologies

Industrial AI for Windpower: A Twinning Approach

• IT and OT convergence in windpower
• Industrial AI as enabling technology for predictive maintenance
• Hybrid miodels and virtual prototyping in digital twins
• Data science and domain knowledge as cocreation for twinning

Prognostics – the “killer app” within Asset Performance Management: Approach and Benefits

• Discuss asset performance management (diagnostics + prognostics) capabilities to drive operating expenses savings and moving from reactive to proactive O&M
• Using Data Analytics Tools to Reduce Wind Turbine Failures and Operational Costs
• Preventing windfarm assets failure using predictive analytics

Applied-A.I. Measures the Effectiveness of Performance Upgrades in Real-Time

• It is expected that A.I. will revolutionise the Wind Industry, bringing deeper insights and lowering the levelised cost of energy.
• Today, industrial data is collected and stored in the hope of future value. But for now, beyond control, it is mostly used for simple reporting, condition monitoring, and analysis of previous failures.
• This year using applied A.I. at an industrial scale it has been possible to determine individual turbine performance changes automatically.
• This technology has been now used to accurately measure the effect of turbinecontrol performance upgrades across an entire offshore site, setting new benchmarks for the real-world deployment of applied machine learning and artificial intelligence.

The Evolution of Digital Twin

• Turning data into information through a centralised asset integrity management database
• Risk based / reliability centred maintenance approaches in offshore wind
• Structural Integrity Management of offshore substructures
• Use of drones and ROVs as inputs to the digital twin mode

Digital Twins for Wind Turbines: Practical Applications and Examples

• Different categories and capabilities of digital twins 
• How these are useful at various stages in a wind farm’s life 
• The value in terms of increased production or extended life 

Data and Predictive Analytics to Improve Drivetrain Availability and reduce Operational Costs

• Life cycle analytics based on SCADA data and service history
• Digital birth certificate enriching service recommendations
• CMS and automatic failure matching to reduce down time of turbines