2results about How to "Improve line selection accuracy" patented technology

The invention relates to the technical field of small-current grounding line selection, and discloses a small-current grounding line selection method and system based on a CatBoost algorithm, and the method comprises the steps: firstly, collecting the zero-sequence voltage and zero-sequence current of each line through a data collection splitter, and transmitting the collected data to a line selection host through the data collection splitter; the line selection host trained by the CatBoost algorithm selects a faulty line according to the collected data, the data collection splitter preprocesses the collected data, converts a collected analog signal into a digital signal, and transmits the digital signal to the line selection host through an optical fiber. Data of various identification methods such as amplitude comparison and phase comparison, first half wave, power direction and higher harmonic are fused together, the fused data drive a fault line selection model, fault information in multiple aspects is fully utilized, various line selection criteria are integrated and complemented and fused with one another, the fault judgment capability is improved, and the method has wider adaptability.

This invention discloses a method for fault location in distribution networks based on multi-criteria fusion and matrix topology search, relating to the field of distribution network fault detection technology. The method includes: synchronously collecting zero-sequence voltage and current at the distribution network bus and zero-sequence current information of each outgoing line; determining whether a single-phase grounding fault has occurred by calculating the magnitude of the neutral point zero-sequence voltage; constructing a steady-state line selection criterion, and simultaneously constructing a transient line selection criterion using an adaptive window S-transform, thus constructing a comprehensive line selection criterion, identifying lines with values ​​greater than a selection threshold as faulty lines; improving the features extracted from line selection to construct transient steady-state criteria for node classification, and then constructing a comprehensive node classification criterion, identifying nodes with values ​​greater than a threshold in the comprehensive criterion as faulty nodes; finally, based on the node classification results, sequentially constructing a network topology matrix, a node classification matrix, a fault path matrix, and a fault judgment matrix; and achieving accurate location of the fault section by querying the corresponding elements in the fault judgment matrix.