Mountain forest fire early warning method applied to power transmission line

A technology for transmission lines and fire early warning, applied in data processing applications, instruments, information technology support systems, etc., to achieve the effect of enhancing mountain fire protection, weakening adverse effects, and improving generalization capabilities

Pending Publication Date: 2021-12-07
STATE GRID HUNAN ELECTRIC POWER +2
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing forest fire risk assessment relies more on the experience of on-site operation and maintenance experts, which inevitably has the influence of subjective factors

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Mountain forest fire early warning method applied to power transmission line
  • Mountain forest fire early warning method applied to power transmission line
  • Mountain forest fire early warning method applied to power transmission line

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Such as figure 1 It is a schematic flow chart of the method of the present invention: the forest fire early warning method applied to power transmission lines provided by the present invention comprises the following steps:

[0044] S1. Obtain the historical forest fire sample library, and perform feature screening to obtain the final historical forest fire sample library;

[0045] S2. Divide all samples in the final historical wildfire sample library into training set and test set, and calculate the sample imbalance ratio;

[0046] S3. Construct the overall objective function of the fire risk assessment model;

[0047] S4. Construct the first decision tree, and calculate the split gain of each historical weather feature and vegetation feature as an alternative split node;

[0048] S5. After determining the first tree structure, calculate the weight of each leaf node;

[0049] S6. On the basis of the first tree, build the second, third, ..., k-th trees one by one, an...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a mountain forest fire early warning method applied to a power transmission line. The method comprises the following steps: obtaining a historical mountain forest fire sample library, carrying out the feature screening, and obtaining a final historical mountain fire sample library; dividing all samples in the final historical forest fire sample library into a training set and a test set, and calculating a sample imbalance ratio; constructing a total objective function of the fire risk assessment model; constructing a first decision tree; after a first tree structure is determined, calculating the weight of each leaf node; on the basis of the first tree, constructing a plurality of trees one by one, and performing training; obtaining a final model of mountain forest fire risk assessment according to the plurality of trained decision trees; and predicating the mountain forest fire risk in real time. The vegetation types in a line channel are described by using a multi-dimensional binary array, and character feature information is converted into numerical features; and the feature complexity of the sample library is reduced. The accuracy and efficiency of evaluating the mountain forest fire risk are improved.

Description

technical field [0001] The invention belongs to the field of forest fire prevention for high-voltage transmission lines, and in particular relates to a forest fire early warning method applied to transmission lines. Background technique [0002] my country's transmission lines usually have long transmission distances and complex terrains. Various natural and human factors pose threats to the safe operation of transmission lines, among which forest fires are one of the most common threats. Once the fire spreads to the vicinity of the transmission line, it will reduce the insulation level of the transmission line and cause problems such as tripping of the transmission line. At present, the work on the prevention and control of wildfires on transmission lines can be mainly divided into the following two aspects: real-time monitoring of wildfires and risk assessment of wildfires. In terms of real-time monitoring of mountain fires, video surveillance, weather radar, satellite re...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06Q10/06G06Q50/06
CPCG06Q10/0635G06Q10/067G06Q50/06Y04S10/50
Inventor 罗昊杨琪秦泽彭沙沙乔明明王振宇陈华一
Owner STATE GRID HUNAN ELECTRIC POWER
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products