MIRACLE: Machine Learning for Screening Nuclear Plant Conditions

Machine Intelligence for Review and Analysis of Condition Logs and Entries (MIRACLE)
Technology No. CW-21-07
MIRACLE assists with screening condition reports submitted to the corrective action program (CAP) at nuclear power plants using machine learning models. It includes both the training of the model and applying it to records. The problem at hand is the need to improve consistency and speed up the process of condition report screening. The solution is to train a machine learning model that can provide a confidence score for predictions on whether a report is a condition adverse to quality. The results would be cost savings equivalent to a plant's reduction of several full-time staff. The software has an unfair advantage over alternatives as it performs 5% better than other solutions in the market.

This software is under copyright. To purchase a license, please use the 'Contact Us' form on this page. We will respond as promptly as possible.
  • swap_vertical_circlemode_editAuthors (4)
    Cameron Krome
    Ahmad Al Rashdan
    Jared Wadsworth
    Kellen Giraud
  • swap_vertical_circlecloud_downloadSupporting documents (0)
Questions about this technology?