- Jun 22, 2021 9:18 pm GMT
Utility staff spend hours each week routinely reviewing corrective action, maintenance, and operational reports. What if we could create an artificial intelligence model that could review and understand a report that typically takes a human 10-15 minutes to read in just half a second? It would save considerable time, money and improve operations for plant staff and grid operators around the world. But building an AI solution for this task is an intricate and time-consuming process due to complex industry jargon and unique component and system names that are different from traditional word usage. The first step to begin creating an electric power industry dictionary to use with natural language processing (NLP) is to build and evaluate a smaller-scale proof of concept to evaluate its functionality for a subset of technical terms and phrases that will not be correctly interpreted by a traditional NLP tool using a standard off-the-shelf dictionary.
To drastically reduce the amount of time and effort it would require for each utility to create its own dictionary, EPRI has taken the lead on creating the key building blocks of an electric power industry dictionary by collaborating with its global network of experts. EPRI is starting with a pilot of a nuclear plant-specific dictionary, and selected a dataset from industry reports and added the word associations to an NLP dictionary, making the terms machine-readable. From there, EPRI created a template-like approach to build subject-specific NLP dictionaries that are linkable and transferable between tools and platforms. This allows the dictionary to be customizable for a specific utility and scalable across the industry.
In the future, this dictionary could be expanded to cover the entire electric power industry. Utility staff could then utilize NLP to streamline report reviews and approvals – in addition to many other tasks – significantly reducing the level of effort for reviews/approvals and improving the efficiency of staff.
Not only will this dictionary reduce costs by optimizing staff time, but it will also be capable of recommending future courses of action based on maintenance reports from utilities. Given that the dictionary is easily transferable and customizable from company to company, the industry will be able to easily share information and implement common/standard terminology as well as have the flexibility to adapt to a particular company’s components and systems.
Currently, the dictionary is operating at around 88 percent accuracy. It has already shown the capability to pro-actively detect potential leaks and spills, which in turn helps to track contamination history and make real-time predictions based on its data analysis.
To learn more about the transformative solutions generated by the convergence of artificial intelligence and the electric power industry, register for EPRI’s AI and Electric Power Summit on September 28-29, link here.
No discussions yet. Start a discussion below.
Get Published - Build a Following
The Energy Central Power Industry Network is based on one core idea - power industry professionals helping each other and advancing the industry by sharing and learning from each other.
If you have an experience or insight to share or have learned something from a conference or seminar, your peers and colleagues on Energy Central want to hear about it. It's also easy to share a link to an article you've liked or an industry resource that you think would be helpful.