Bentley Incorporated: Digital Twin helps HDR ensure safe operations at Diablo Dam

Bentley technology helps team integrate artificial intelligence and engineering data, improving maintenance and decision-making

Author: Aude Camus, Senior Solutions Marketing Manager, Reality Modeling, Bentley Systems

Seek to prevent dam disasters

In February 2017, heavy rains in Northern California overwhelmed Oroville Dam. Officials found that erosion over time caused a crater to form in the main spillway, limiting the amount of water that could be discharged and contributing to the rising water level of Lake Oroville. As a result, water flowed over the previously unused emergency spillway, causing significant soil erosion and damage to the dam. As the dam was in danger of collapsing, more than 180,000 people living downstream were evacuated as a precaution. Although the Oroville Dam ultimately remained intact, the incident alarmed dam owners and operators across the country and reinforced the need for more effective maintenance to avert potential disasters.

One such owner-operator is Seattle City Light, which conducted extensive safety reviews to avert near-disaster at six of its own facilities, including the 1936-built Diablo Dam along the Skagit River, in northwest Washington. To improve inspection techniques beyond traditional methods on Diablo and gain a deeper understanding of the current conditions of the aging dam, they wanted to establish virtual inspections that could gather more information while minimizing safety risks on the road. installation 160 feet high and reducing inspection costs. Seattle City Light commissioned HDR to conduct a survey of the dam and surrounding area with unmanned aerial vehicles. The survey was to include detailed images of the dam structure, spillways, rock abutments and concrete arch. Although HDR would collect a lot of information about the current state of the dam, they needed a way to organize and present this data in an intuitive and easily understandable way, helping operators improve decision-making and respond quickly. to changing conditions.

Combining a digital twin with machine learning

HDR determined that the most efficient way to manage the collected data and put it to work for more efficient inspections was to create a digital twin. A virtual replica of the dam would give operators another point of reference to understand the status of the installation and provide a new way to stay aware of any changes with intuitive data visualization. Ideally, the digital twin would be able to integrate data collected during traditional rope access inspections, as these manual inspections still provide key insights that UAV surveys might miss. Once developed, the digital twin would establish baseline conditions and then be updated as real-world conditions change.

However, the client wanted to go beyond a faithful reflection of the actual conditions. To achieve these goals, HDR needed to completely merge Diablo Dam’s architectural, engineering, and construction data into the digital twin. Additionally, the owner wanted to integrate artificial intelligence and machine learning into the model. With these capabilities, dam workers could perform predictive analysis and determine how assets and geotechnical conditions would change in the future, such as natural displacement and erosion of surrounding soil over time. They also wanted to automatically identify cracks and chips, allowing operators to quickly take corrective action to prevent them from developing into larger problems. With this information, owners could further improve their targeted maintenance schedule, helping to ensure safe operations. HDR was looking for a digital twin platform that could imbue its reality model with the advanced capabilities needed to ensure that Diablo Dam wouldn’t experience disaster.

Integration of all data and capabilities with Bentley apps

HDR determined that ContextCapture and the Bentley iTwin platform could help them develop a digital twin that would incorporate the analytics and machine learning capabilities needed to keep the dam safe. During a six-hour UAV flight, they collected 82 million data points covering all elements of the dam and its surroundings. Next, they used ContextCapture to combine this data with data gathered from rope surveys to create a detailed, survey-grade reality mesh of the area. In the process, the data helped engineers identify geologic features that would be difficult to access manually, which would help improve the accuracy of future assessments.

The team then used the iTwin platform to create a detailed digital twin of the dam and its surroundings. All project information, regardless of discipline, has been integrated into the federated model. Due to the open nature of the iTwin platform, HDR has integrated its preferred artificial intelligence and machine learning technology. As a result, the digital twin can automatically detect cracks and chips, as well as differentiate them from harmless shadows, discoloration and algae growth. With predictive analytics built into the digital twin, dam engineers can compare data from one year to other years. By observing changes in the environment over time, such as ground shifts, they can predict that the structure will continue to move at a similar rate over time, barring unusual seismic activity.

Take corrective action faster

Integrating all information about the condition of the dam’s assets, structure and surroundings into a digital twin has greatly improved access to and understanding of project data. Combining the digital model, which has topographic-level accuracy, with traditional on-site rope inspections gives inspectors a much more detailed look at current conditions. HDR estimates that the initial reality capture for the digital twin was only a quarter of the cost of traditional surveys. With an accuracy of less than two centimeters, dam operators can detect much smaller anomalies and take corrective action before they escalate into larger problems. Additionally, many operators can monitor current dam conditions from their offices or remote workstations, improving safety and convenience.

Now all dam stakeholders can quickly share information, providing a single source of truth and speeding decision-making. By applying artificial intelligence and machine learning, homeowners can now automatically identify areas of concrete with anomalies, then differentiate between cracks and spalls to better determine what corrective action is needed and prevent problems from escalating. At the same time, filtering out shadows and discoloration prevents unnecessary maintenance activities. Dam operators plan to add more features 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 return on investment.

Comments are closed.