Streamlining Asset Inspections with GridOS® Visual Intelligence

In past blogs we’ve covered how utilities can use GridOS Visual Intelligence to assess and address damage caused by severe storms. Today I wanted to discuss another major resiliency challenge: asset health.

“Asset health” in this context refers to the physical condition and performance of lines, transformers, fuses, switches, and poles. and the like. This is a major concern for system reliability, maintenance, and grid hardening teams around the world as they strive to minimize momentary and sustained power grid disruptions.

Many grid assets are approaching the end of their lifecycles; some are already past their estimated lifespans and are operating on borrowed time. When the time comes to replace or repair assets, utilities are faced with supply chain constraints, limited equipment inventories, resource availability, higher operational costs, and soaring customer expectations. Power Magazine recently indicated in an article that lead times for large transformers can be as long as four years, with prices skyrocketing as well due to higher costs of raw material, like copper and steel.

To navigate these challenges and get the most out of their existing assets, utilities are turning to proactive condition- and risk-based maintenance strategies that give them a better view of asset health. The goals of these methodologies are to control cost and identify and eliminate asset issues before they can outright fail and cause service interruptions to customers. This transition of maintenance strategies requires new monitoring tools and proper use of the right technology to optimize equipment usage and prioritize equipment replacements, budgets, and risk. Only then can utilities realize key KPI improvements like OpEx reductions, CapEx deferrals, and better SAIDI/SAIFI targets.

One way to accomplish all of the above is by using GE Vernova’s Visual Intelligence capabilities for asset inspection.

Visual Intelligence works by overlaying multiple sources of data like scans, photos, and other imagery against network maps. It then uses a simple color-coding system to flag any threats to resilience, while also automatically generating and dispatching detailed work orders for resolution to the relevant crews. This workflow is perhaps best known for its vegetation management use case, which identifies encroaching vegetation and/or danger trees posing a risk of an outage.

In a testament to the versatility of Visual Intelligence, its capabilities can also identify assets in need of maintenance or replacement. The application features AI-enabled capabilities that can recognize physical asset defects that may eventually impact system reliability and cause a power grid disruption. Examples of asset defects include corrosion, frayed wires, broken and flashed insulators, and broken pole tops, among others. Identified defects are flagged based on risk, prioritized, and sent to the appropriate stakeholders for tasking and mitigation. This unlocks significant gains in efficiency and accuracy over traditional field inspections.

Utilities can use Visual Intelligence to optimize their maintenance and capital expenditures by identifying defects long before they can snowball and cause a full asset failure – in other words, unlocking condition and risk-based maintenance schedules. In another sense, Visual Intelligence also verify if assets that were expected to need replacement are still in good operating condition. This enables them to extend their assets’ lifespans and defer any replacements, thus freeing up much-needed capital for other matters and controlling costs for customers.

An added benefit of using Visual Intelligence to identify asset defects is the creation of a digital asset inventory from the gathered data. With this inventory in place, auditing power assets in the field becomes much easier – and can happen at any given time.

Take a look at the below image, which shows an example of Visual Intelligence’s asset inspection capability. Specifically, it depicts two corroded transformers in one of a utility’s key network locations.

As part of the utility’s new risk-based asset maintenance schedule, Visual Intelligence identified the presence of corrosion on these transformers (outlined in red) and automatically created a work order to ensure they were promptly replaced. Had the utility still been following its traditional cycle-based maintenance plan, it likely wouldn’t have noticed the compromised transformer until its planned inspection cycle several years in the future. The corroded transformer could well have failed long before the next scheduled inspection and caused a major power grid disruption. This is just one small example of how Visual Inspection prevented a sustained outage and prolonged impact to customers. Replicated over thousands of miles of a network, the value of Visual Intelligence amplifies.

In one key success with Visual Intelligence’s asset inspection capabilities, a leading European utility faced the critical challenge of managing and maintaining over a quarter of a million kilometers of aging overhead lines. It hoped to avoid the extreme solution of burying its entire network – a solution estimated to cost tens of billions of Euros.

In addition to avoiding such heavy capital expenditures, the utility also wanted to keep costs low for customers, improve grid reliability, extend the lifespan of its existing overhead networks, and minimize environmental, customer impact of burying its electrical lines. The utility found that GE Vernova’s GridOS Visual Intelligence platform satisfied all its goals and requirements in managing and maintaining its existing line network, with the added benefit of being readily scalable.

The utility implemented Visual Intelligence as an enterprise technology tool for identifying equipment defects across its network. The Visual Intelligence rollout ensured consistent data interpretation and streamlined decision-making throughout all regions companywide – a major advantage as some regions must adhere to different mandates than others.

The utility now is at the forefront of efficient, effective, and cost-effective grid maintenance for its customers. By adopting GridOS Visual Intelligence’s advanced AI capabilities, the utility streamlined its inspection and diagnosis processes, thus helping it improve grid performance, defer infrastructure replacements, and greatly reduce both OpEx and CapEx.

To learn more about asset inspections and other Visual Intelligence use cases, check out our solution paper on the subject, “Orchestrate the Grid with Visual Precision: GridOS Visual Intelligence.”