Method for contactless diagnosing power facility using artificial intelligence and signal processing technology and device using the same
The AI-powered fault diagnosis system addresses the inefficiencies of traditional methods by using a convolutional neural network to analyze ultrasonic signals, improving the speed and accuracy of power equipment fault detection.
KR102999051B1Active Publication Date: 2026-08-03CYCOM CO LTD +1
1 Cites 0 Cited by
Patent Information
- Application Number
- KR1020220052503
- Authority / Receiving Office
- KR · KR
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2022-04-28
- Publication Date
- 2026-08-03
- Estimated Expiration
- 2042-04-28
AI Technical Summary
Technical Problem
Existing power equipment diagnostic methods are time-consuming and reliant on human expertise, leading to variability in fault diagnosis accuracy.
Method used
A fault diagnosis system utilizing artificial intelligence and signal processing, specifically through a convolutional neural network-based diagnostic model, processes ultrasonic signals from power equipment to generate Mel Spectrograms, enabling accurate and efficient fault detection.
Benefits of technology
The system significantly reduces the time required for fault diagnosis and enhances accuracy by automating the process, leveraging AI to analyze ultrasonic signals for power equipment conditions.
✦ Generated by Eureka AI based on patent content.
Abstract
A non-contact method for diagnosing power facilities using artificial intelligence and signal processing technology and a device using the same are disclosed. A method for diagnosing power facilities using artificial intelligence according to one embodiment includes the steps of: acquiring an ultrasonic signal for power facilities; generating a Mel Spectrogram based on the ultrasonic signal; - the Mel Spectrogram includes time information, frequency information, and magnitude information corresponding to the ultrasonic signal and is in the form of an image -, inputting the Mel Spectrogram into a pre-trained diagnostic model; and acquiring diagnostic data for power facilities based on the diagnostic model, wherein the diagnostic model may be constructed based on a convolutional neural network algorithm.
Need to check novelty before this filing date? Find Prior Art