Ground Fault Directionality Detection Using Current-Only Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ground fault directionality detection methods in small current grounding systems require voltage information, are cumbersome, and have low reliability, making them inefficient and inaccurate.
Innovation Solution
A neural network-based method that uses only current information to detect the directionality of ground faults, employing a convolutional neural network to classify upstream and downstream faults without the need for voltage data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If voltage information is used in ground fault directionality detection, then detection accuracy can be improved, but device complexity and cost increase due to requiring additional sensors
Solution Approach 1:
The patent extracts and eliminates the requirement for voltage information from the ground fault detection system, achieving accurate directionality detection using only current information. This removes the need for voltage sensors and reduces system complexity while maintaining detection accuracy through intelligent signal processing of available current data
Solution Approach 2:
The patent makes the current sensor perform multiple functions: it not only detects fault current magnitude but also determines fault directionality through advanced signal processing. This multi-functional approach eliminates the need for separate voltage sensors, reducing device complexity while maintaining detection capabilities
2Reliability
If traditional ground fault detection methods are used, then comprehensive fault information can be obtained, but the detection process becomes cumbersome and less efficient
Solution Approach 1:
The patent replaces complex mechanical and computational processing systems with an intelligent neural network-based detection system. The neural network automatically processes current signals to determine fault directionality, eliminating cumbersome manual or algorithmic processing steps while maintaining high reliability through learned patterns from training data
3Measurement precision
If additional sensors and resistors are deployed for ground fault detection, then detection capability is enhanced, but system cost and complexity increase
Solution Approach 1:
The patent enables existing current sensors to perform multiple functions including fault detection, directionality determination, and system monitoring. This multi-functional approach eliminates the need for additional voltage sensors and resistors, reducing component quantity while enhancing detection capability through intelligent signal processing
Solution Approach 2:
The patent enables the existing current sensing system to serve itself by using the same current information for both magnitude detection and directionality determination. The neural network processes the current signal to extract multiple pieces of information, making the system self-sufficient without requiring additional components
Data Source
AI summary
A ground fault directionality detection method, a ground fault directionality detection device and a computer-readable storage medium for a small current grounding system are disclosed. The ground fault directionality detection method comprises sampling at least a part of a current signal to obtain a numerical matrix; providing the numerical matrix as an input to a ground fault directionality detection neural network; calculating a label vector corresponding to the numerical matrix by the ground fault directionality detection neural network, wherein the label vector indicates whether the current signal is an upstream fault current signal or a downstream fault current signal; receiving a ground fault confirmation signal by the ground fault directionality detection neural network; and outputting the label vector by the ground fault directionality detection neural network when the ground fault confirmation signal indicates that the current signal is a ground fault current signal.