Prevent power outages by predicting asset failures weeks in advance
Improve services for your customers while reducing your costs with iPredict™, the world’s first artificially intelligent system for predicting failures in critical electricity distribution assets.
By showing which assets are likely to fail within the next two weeks, iPredict lets utility companies plan repairs, making it possible to manage costs and give critical infrastructure advanced notice to minimise disruption.
80
![]() accuracy in predicting equipment failures two weeks out. |
90
![]() accuracy in predicting equipment failures three days out. |
iPredict™ collects high frequency sub-cycle data and analyses it in near real-time to identify the warning signs of an imminent failure of distribution system components. That means utilities can:
By predicting imminent faults and failures, utilities can proactively schedule resources, materials and customer notifications, letting them repair or replace assets with much less disruption than emergency responses create.
iPredict makes it possible to let customers know about maintenance work in advance, which is crucial to building a trusted brand. And by telling customers how long works will take, they’ll be able to prepare, minimising the inconvenience.
As iPredict dramatically reduces the amount of emergency repairs needed, overtime and out-of-hours costs fall. And with maintenance time targeted towards at-risk assets, repairs and replacements will be more efficient.
Scheduling repairs and replacements will let utilities properly control traffic and arrange work during daylight hours to improve safety for engineers. It will also cut unexpected outages that disrupt everything from traffic lights to hospitals.
“We’ve worked with PA on numerous initiatives, from their ReliabilityOne™ program to circuit risk data modelling,” says Tom Bialek, Chief Engineer, San Diego Gas & Electric. “We were eager to co-develop this first-of-its-kind program that could benefit the entire industry by proactively predicting underground and overhead equipment failures.”
“We’re excited to be on the forefront of predicting asset failures, so we can improve the reliability of the services we deliver to our customers,” says Tom Bialek. We expect that “iPredict™ should allow us to prioritize and proactively schedule work so we can improve safety for our crews, reduce operational and maintenance costs, and minimize outage impacts on our customers.”
It’s never been more important to minimize power supply disruptions. Find out how SDG&E made its distribution network even more reliable with iPredict™, a system that uses Big Data and Machine Learning to predict faults before they happen.