Evaluate the utility company’s AI maturity curve to determine next steps

While many utilities acknowledge the transformational power of data, leveraging it can be another story. You could have millions of data points on everything from the condition of utility poles to hours spent in the field. But all this data does little good if you can’t synthesize it into something useful and actionable.

So how can you unlock the value of data, without spending infinite hours — and dollars?

Artificial intelligence (AI) has revolutionized everything from the devices in our hands and homes to how we drive, and now it’s even taking on the drive-thru at fast-food restaurants.

With widely distributed physical assets that can be difficult to access or examine in close detail on an individual basis, the utility industry is an optimal use case for AI. By integrating AI into your asset monitoring efforts, you can realize significant efficiency gains in both your ability to quickly locate and categorize assets and determine their condition, ultimately leading to better business decisions.

But getting started with AI can be intimidating. Before adopting any AI-based solution, it’s helpful to understand where you land on the AI maturity curve.

Getting started: viewing and validating assets

For utilities that have not embraced AI, it’s not about using AI but preparing for it. This starts with how you view and validate assets. Too many utilities still rely on outdated data collection methods. This often leads to costly re-inspections because the data is subjective and unverifiable. Plus, the data itself tends to be more traditional — checklists and form data siloed across departments, with little value on its own.

Conversely, visual data — including RGB, thermal, and LiDAR data — is hard, provable, trackable, and auditable. Whether collected by drones, helicopters, satellite, or ground crews, visual data is where many utilities begin their AI journeys.

Collecting visual data and combining it with traditional data in a centralized location provides utilities a digital system of audit. This offers many benefits, including reducing time spent on non-contributing actions like re-inspections and allowing you to bundle work that needs to be done, driving operational efficiencies.

Most critically, creating a digital system of audit sets up utilities to analyze change over time. With all your asset data in one place, you can start using the predictive capabilities of AI to compare the past with the present to predict the future.

On your way: Assessing asset conditions

Once you implement a digital system of audit to your asset data, the next stage of AI maturity is using AI to assess asset conditions. This is typically done via a three-step process that involves both humans and machines:

1. Identify and sort assets based on priority. The goal here is to discover anomalies in asset images based on priority. Doing this manually could take a person hundreds of hours. However, by stack-ranking issues based on priority and feeding this into the machine, humans can apply AI image detection technology to review a huge library of images and instantly identify the most urgent issues to address.
2. Correcting, assessing, and teaching the machine. Just because a model was created to accomplish a certain task on day one doesn’t mean it will evolve over time. As inspectors are reviewing anomalies and issuing work orders, they will be using the system to tag new conditions, alter conditions, and change severities.
3. Let the machine do its work. Training a machine learning algorithm is an evolving lifecycle of continual improvement. As inspectors change their priorities, they will retrain the machine and it will alter its outputs to adjust. Mid-stage utilities use multiple machine learning algorithms to drive efficiencies.

Operationalizing AI: making better decisions

While operationalizing AI may still feel conceptual for many, some utilities are doing it today to make better business decisions.

Automating inventory is one such area. Inventory is fairly static, so utilities strive to make sure it’s correct at all times by accounting for changes in the field. Late-stage utilities use AI to automatically update inventory systems when changes are detected.

This is particularly useful in disaster response. When a hurricane hits, AI can compare post-disaster images with pre-disaster inventory data, producing a delta report that can show response teams the best places to focus their efforts.

Plus, by connecting this technology to your work order systems, utilities can train the system to automatically create a work order for a downed pole, for example. And for negotiable items, the system can push these issues to a human to decide if corrective action is needed.

Size matters, sort of

While AI maturity often corresponds with utility size, there are exceptions. The important thing is knowing where you stand to guide your next steps.

As for whether AI software or services are best for your organization, a good rule of thumb is utilities early in their AI journey tend to get more value out of consultative AI services, while late-stage utilities tend to prefer AI software. Take this with a grain of salt, however, as what’s best for your organization always depends on your unique goals, risks, and business model.