• HDR

    Diablo Dam Digital Twin Modeling

    Whatcom County, Washington, United States

Project Summary

    • REALITY MODELING - HDR

Improving Maintenance to Prevent Dam Failures

In February 2017, heavy rainfall in northern California overwhelmed the Oroville Dam. The problem was made worse due to erosion over time causing a crater to form in the main spillway, limiting the amount of water that could be discharged. To avoid a similar near-disaster, Seattle City Light subsequently conducted major safety reviews of the six dams it operates, including the Diablo Dam. To improve inspection techniques beyond traditional methods and gain a more thorough understanding of the aging dam’s current conditions, they tasked HDR with conducting a visual survey using unmanned aerial vehicles. However, they needed a way to arrange and present that data in an intuitive, easily comprehendible fashion to improve decision-making.

Making Sense of Data with a Digital Twin

HDR determined the most effective way to manage the gathered data and put it to work for more effective inspections was to create a digital twin. A virtual replica of the dam would give the operators another reference point for understanding the state of the facility and provide a new way to maintain awareness of any changes with intuitive visualization of the data. However, the project owner wanted to go beyond an accurate reflection of real-world conditions. To meet the goals of the project, HDR needed to merge Diablo Dam’s architecture, engineering, and construction data into the digital twin, and use artificial intelligence to automatically identify cracks and spalls. HDR sought a digital twin platform that could incorporate these advanced capabilities.

Detecting Anomalies with Machine Learning

HDR determined that ContextCapture and the Bentley iTwin platform could help them develop a digital twin with all the features the project needed. They used ContextCapture to combine 82 million data points from the UAV survey with data gathered from rope surveys to create a detailed, survey-grade reality mesh of the area. The team then used the iTwin platform to create a detailed digital twin of the dam and its surroundings. By incorporating artificial intelligence, the digital twin can automatically detect cracks and spalls, as well as differentiate them from harmless shadows and discoloration. By observing changes over time, they can predict future shifts in the surroundings.

Cutting Survey Costs by 75%

Integrating all information about the state of the dam’s assets, structure, and surroundings into a digital twin has greatly improved access to and understanding of project data. HDR estimates the initial reality capture for the digital twin was just a quarter of the cost of traditional surveys. With an accuracy rate of within two centimeters, dam operators can detect much smaller anomalies and take corrective action before they grow into larger problems. Machine learning can automatically detect problems and filter out shadows and discoloration, which makes maintenance plans more efficient and effective. Dam operators plan to add more capabilities to the digital twin, such as additional hydraulic engineering, uplift analysis, and change and anomaly detection, to further improve the dam’s ongoing safety and provide additional sources of ROI.

Project Playbook: ContextCapture, ContextCapture Insights

Outcome/Facts
  • HDR estimates the initial reality capture for the digital twin was just a quarter of the cost of traditional surveys.
  • With an accuracy rate of within two centimeters, dam operators can detect much smaller anomalies and take corrective action before they grow into larger problems.
  • Dam operators plan to add more capabilities to the digital twin, such as additional hydraulic engineering, uplift analysis, and change and anomaly detection.
Quote:
  • What’s inspiring to me is that the digital twin provides more access to high-fidelity imagery and data. The dam is safer, and the ability to get data is safe and efficient.

    Carlos Femmer Associate Vice President/Data Acquisition Cross Sector Director HDR