Low-voltage user side series arc detection method and device based on artificial intelligence

• Main Authors: HAN LINGXIA, WANG YAMING, CHU HAIBING, LI CONG, CUI SHAOHUA
• Format: Patent
• Language: Chinese; English
• Published: 28.05.2024
• Subjects: MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PHYSICS; TESTING

The invention discloses a low-voltage user side series arc detection method and device based on artificial intelligence, and the method comprises the steps: constructing a series arc hidden danger early warning model for carrying out the early warning before a fault, and predicting a fault arc hidden danger probability value of a next period according to the electrical signal data at a current moment and a development trend, when the preset early warning threshold value is exceeded, it is judged that a potential fault exists, field personnel are notified to carry out detection and verification, and meanwhile early warning information is visually displayed; and constructing a multi-scene low-voltage series arc identification model to carry out post-fault identification, carrying out arc related feature extraction based on electrical signal data monitored in real time, inputting the trained multi-scene low-voltage series arc identification model, and further judging the type and state of the arc. Through the me