Method to implement artificial neural network utilizing multi hidden layer process and time difference of arrival method for partial discharge acoustic emission-based localization in oil

MYPI2024007735A0Pending Publication Date: 2026-06-30UNIVERSITI PUTRA MALAYSIA
0 Cites 0 Cited by

Patent Information

Application Number
MYPI2024007735
Authority / Receiving Office
MY · MY
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-12-31
Publication Date
2026-06-30
Patent Text Reader

Abstract

The present invention applies partial discharge acoustic emission-based localization in oil using combination of Time Difference of Arrival and an optimization of Artificial Neural Network, based on multi hidden layer. Partial discharge signals are initiated using a needle-plane electrode configuration, and Time Difference of Arrival determines the distance between the partial discharge source and acoustic emission sensor. Two Time Difference of Arrival techniques, the First Peak Method and Cumulative Energy Method, are compared to assess partial discharge acoustic emission-based localization. Data from these methods was trained to using Artificial Neural Network by optimizing the configuration of number of neurons and multi hidden layer parameters.
Need to check novelty before this filing date? Find Prior Art