ACL Digital

Home / CaseStudy / ML based Electrical Structure Monitoring Solution

ML based Electrical Structure Monitoring Solution

Electrical Structure Monitoring Solution for Leading US-Based Energy Company

Electrical Structure Monitoring Solution Banner

Overview

The US-based leading energy company provided electric, gas, and steam services to over 10M+ people. They wanted to develop an intelligent inspection solution for their 250K+ underground electric structures to perform asset visual inspections. ACL Digital helped the client by providing a solution that included a thermal camera for capturing installation images and the FLIR image extractor for obtaining temperature, location, and other metadata.

Download Case Study




    Challenges

    Lack of ML enabled solution based on Mask RCNN

    Absence of hotspot detection and alerting capabilities for the team

    Solutions

    • The solution consists of a thermal camera to capture installation images, FLIR Image Extractor to obtain temperature, location and other metadata, a cloud for images storage, a cloud compute instance with a GPU, ML model to detect cables, a module to make decision to raise the warning flag or send notification
    • Annotation of 25K+ images using makesense.ai tool providing polygonal annotation in PVOC annotation format
    • The images will be used to train the ML model (Mask RCNN model) that is based on ResNet 101 architecture
    • Mask is extracted based on the detection of electrical asset associated that helps to get the relevant temperature from the matrix
    • Hotspot is then detected based on the ingenious algorithm

    Outcomes

    Benefits ML based Electrical Structure Monitoring Solution
    Benefits ML based Electrical Structure Monitoring Solution
    Scroll to Top