Artificial Intelligence Monitors Critical Infrastructure

Minimising threats to energy and utilities plants is essential to ensure the smooth running of the critical infrastructure that powers our lives. Traditional detection techniques are inefficient when dealing with huge amounts of data because their analysis processes are complex and time-consuming.

Critical infrastructure, including electricity, oil, gas, and water supply systems, as well as transportation hubs, are under constant threat of cyber attack by threat actors. Some of these attacks are motivated by nations states to diminish opponents for strategic reasons. Others are launched for ransom, as in the case of the recent cyber attack on the Colonial Pipeline. 

Today, technology based on Artificial Intelligence (AI) and computer vision is helping monitor critical infrastructure. 

These tools support the analysis and storage of data in intrusion detection systems, as well as reduce processing and training time and AI and video surveillance is being being increasingly adopted to monitor critical national infrastructure facilities.

FirstEnergy Corp is a US electric utility based in Ohio that has recently  completed a pilot program demonstrating how computer vision can be deployed to analyse thousands of utility pole infrastructure images. The company worked together with Noteworthy AI to instal smart cameras in its utility truck fleet, with software powered by edge AI chips by Nvidia. The platform provides geolocation for each pole in the widespread utility pole network before visually picking out the presence of components like insulators and current transformers. The computer vision software can then gauge whether it is physically damaged.

According to Nvidia, manual maintenance workers inspect a fraction of the 185 million utility poles in the US in a single year. It would take an entire decade for them to inspect all of them. In a pilot test, the AI technology collected more than 5,000 high-resolution images of its poles within 30 days, which expanded its database by more than fivefold. 

Superior image quality is also anticipated to help avoid wasted visits by engineers to locations where the actual line conditions differ from initial expectations.

Since completing the initial test, FirstEnergy focused on streetlights joined the program along with a unit that tracks vegetation growth around the company’s power infrastructure. The smart camera module attaches to the truck with magnets or suction cups and links to a smaller unit inside the truck’s cab that processes the images.

The integration of AI methods into the cyber security domain can increase the accuracy in the detection of true positive instances reducing the load of incidents the security managers receive, allowing them to focus on strategic aspects of cyber security. 

The next steps to be taken to create the new generation cyber security for critical infrastructure include training the AI algorithms right data, testing the algorithms for bias, and ensuring the robustness of the system.

Calipsa:       IoT World Today:      ResearchGate:      I-HLS:      GlobeNewswire:      SPEAR Project: 

You Might Also Read: 

Cyber Security Standards For Critical Infrastructure: