Photovoltaic arc detection method and system based on neural network

By combining the hybrid architecture of CNN and Transformer models, the sensitivity and accuracy of fault arc detection in photovoltaic systems are solved, efficient and stable arc fault detection is achieved, and the safety and stability of photovoltaic systems are improved.

CN120372212APending Publication Date: 2025-07-25SUZHOU HYPONTECH CO LTD
0 Cites 3 Cited by

Patent Information

Application Number
CN202510476564.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-04-16
Publication Date
2025-07-25

AI Technical Summary

Technical Problem

The sensitivity and accuracy of fault arc detection methods in existing photovoltaic systems are insufficient in complex environments, and traditional methods are prone to false alarms or missed reports. The accuracy and generalization capabilities of software-based intelligent methods are limited when facing changing environments. Convolutional neural networks and recurrent neural networks have gradient disappearance or explosion problems when processing long sequence data.

Method used

Using a hybrid architecture combining CNN and Transformer models, by constructing data sets, data preprocessing, model training and arc detection, using CNN to extract voltage timing data features, Transformer performs feature fusion, builds an arc detection model, and detects the occurrence of arcs in photovoltaic systems in real time.

Benefits of technology

It greatly improves the accuracy of arc fault detection in photovoltaic systems, improves the safety and stability of the system, and can accurately capture the key characteristics of arc faults from complex electrical signals, achieving more efficient and stable detection.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a photovoltaic arc detection method and system based on a neural network. The method comprises the following steps: generating a data set; preprocessing the data set to obtain a training data set; a hybrid architecture detection model combining a CNN model and a Transform model is constructed, the CNN model processes the voltage time sequence data to extract feature information, the Transform model fuses the feature information at each moment to extract fused feature information, and a predicted value is calculated to adjust parameters of the hybrid architecture detection model to obtain an arc detection model; sampling voltage time sequence data of the photovoltaic system are collected and imported into the arc detection model, and the arc detection model detects whether an arc occurs or not and outputs detection information. According to the method, the accuracy of arc fault detection in the photovoltaic system is greatly improved by fusing the convolutional neural network CNN and the Transform technology, and the safety and stability of operation of the photovoltaic system are improved. The key features of the arc fault can be accurately captured from the complex electric signal, so that the detection is more efficient and stable.
Need to check novelty before this filing date? Find Prior Art