CN111126672A - A typhoon disaster prediction method for high-voltage overhead transmission lines based on classification decision tree - Google Patents
A typhoon disaster prediction method for high-voltage overhead transmission lines based on classification decision treeDownload PDFInfo
- Publication number
- CN111126672A CN111126672ACN201911211112.0ACN201911211112ACN111126672ACN 111126672 ACN111126672 ACN 111126672ACN 201911211112 ACN201911211112 ACN 201911211112ACN 111126672 ACN111126672 ACN 111126672A
- Authority
- CN
- China
- Prior art keywords
- overhead transmission
- transmission line
- voltage overhead
- typhoon
- typhoon disaster
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
Translated fromChinese
Description
Technical Field
The invention belongs to the technical field of natural disaster prediction of high-voltage transmission lines, and particularly relates to a typhoon disaster prediction method of a high-voltage overhead transmission line based on a classification decision tree.
Background
The high-voltage overhead transmission line is one of the most important infrastructures in modern society, and is used for remotely transmitting large-capacity electric energy from a power supply side to a load side. The high-voltage overhead transmission line is generally located in the field and is seriously influenced by natural disasters, wherein typhoons can damage the high-voltage overhead transmission line in a large range in a short time, and serious threats are caused to the safe and stable operation of a power grid.
By predicting typhoon disasters of the high-voltage overhead transmission line before typhoons come, the method is beneficial to the operation and maintenance department of the high-voltage overhead transmission line to carry out targeted transmission channel cleaning so as to avoid foreign matter external damage faults caused by strong winds, and can also guide the operation and maintenance department to carry out tower reinforcement in advance so as to avoid tower collapse faults, or specifically prepare emergency materials and rapidly carry out rush repair and recovery after tower collapse faults.
Whether the high-voltage overhead transmission line has typhoon disasters depends on a series of factors such as typhoon strength, typhoon landing positions, wind resistance of high-voltage overhead transmission line towers, geographical positions of the high-voltage overhead transmission line towers, trend of the high-voltage overhead transmission line and the like. In the traditional method, disaster prediction is usually performed by comparing the forecast wind speed and the design wind speed at the pole and tower of the high-voltage overhead transmission line, but the method is limited by the defect that the accuracy of a meteorological numerical forecasting system for wind speed forecast is insufficient, and the accuracy of typhoon disaster prediction is low. Typhoon disasters of high-voltage overhead transmission lines are often difficult to predict accurately, and troubles are caused to the operation and maintenance departments to carry out disaster prevention and reduction work in a targeted manner.
Disclosure of Invention
Aiming at the defect that the traditional typhoon disaster prediction method is low in accuracy, the invention provides the typhoon disaster prediction method for the high-voltage overhead transmission line based on the classification decision tree, and the classification decision tree comprehensively analyzes multiple elements to realize accurate prediction of the typhoon disaster of the high-voltage overhead transmission line, so that the disaster prevention and reduction work can be better guided.
In order to achieve the purpose, the invention adopts the following technical scheme: a high-voltage overhead transmission line typhoon disaster prediction method based on a classification decision tree comprises the following steps:
s1, selecting typhoon disaster influence factors of the high-voltage overhead transmission line;
s2, building a historical typhoon disaster fault point influence factor database of the high-voltage overhead transmission line;
s3, training a typhoon disaster prediction model by adopting a classification decision tree;
and S4, adopting a typhoon disaster prediction model and combining the target high-voltage overhead transmission line and typhoon forecast data to carry out typhoon disaster prediction.
Further, in step S1, the typhoon disaster influence factor includes a forecast wind speed at a position of the high voltage overhead transmission line tower, a design wind speed of the high voltage overhead transmission line tower, a terrain classification, a predicted landing point distance between the high voltage overhead transmission line tower and a typhoon, a voltage grade of the high voltage overhead transmission line, a forecast heading angle between a prevailing wind direction and a line of the high voltage overhead transmission line, a line corner number of the high voltage overhead transmission line, a distance between the high voltage overhead transmission line tower and a coast, an environmental corrosion grade of the high voltage overhead transmission line tower, a commissioning life of the high voltage overhead transmission line tower, an altitude of the high voltage overhead transmission line tower, and a height.
Further, in step S1, the forecasted wind speed at the tower position of the high voltage overhead transmission line is an average wind speed at a height of 10m from the ground surface; the designed wind speed of the high-voltage overhead transmission line tower refers to a wind speed value at a height of 10m from the ground; the landform classification is divided into two types of mountain land and flat land; the expected landing point distance between the tower and the typhoon of the high-voltage overhead transmission line is the linear distance between the position of the tower and the first landing point of the center of the typhoon; the voltage class of the high-voltage overhead transmission line is divided into Alternating Current (AC) 110kV, Alternating Current (AC) 220kV, Alternating Current (AC) 500kV, Alternating Current (AC) 1000kV, Direct Current (DC) 500kV, Direct Current (DC) 800kV and Direct Current (DC) 1100 kV; forecasting an included angle between the main wind direction and the direction of the high-voltage overhead transmission line to be the smaller angle of two complementary intersection angles formed by the main wind direction and the line direction; the number of the rotation angles of the high-voltage overhead transmission line refers to the rotation angles of the line path direction in front of and behind a certain base tower; the distance between the high-voltage overhead transmission line tower and the coast is the closest straight line distance between the position of the tower and the coast line; the corrosion grade of the environment where the high-voltage overhead transmission line tower is located is divided into C1, C2, C3, C4, C5 and CX from low to high; the commissioning age of the high-voltage overhead transmission line refers to the difference between the current year and the commissioning year; the altitude of the high-voltage overhead transmission line tower refers to the altitude of the position where the tower is located; the height of the high-voltage overhead transmission line tower refers to the total height of the tower.
Further, in step S2, the pointer of the typhoon disaster fault point impact factor database establishes a data record for the high-voltage overhead transmission line tower that has a typhoon disaster historically, and the database field includes all typhoon disaster impact factors instep 1, and the name, number, fault type and fault time of the line to which the historical typhoon disaster tower belongs.
Further, the fault types comprise three types of windage yaw flashover, foreign body external damage and body damage.
Furthermore, a historical typhoon disaster fault point influence factor database is built on the basis of historical typhoon disaster investigation of the high-voltage overhead transmission line, 1 data record is set for each base fault tower, the fault tower refers to the tower with the typhoon disaster, and when the typhoon disaster occurs between two base fault towers, the tower closest to the fault occurrence position is used as the fault tower; when the numerical values of the various influence factors are calculated, the actual values are used for replacing forecast values, specifically, the actual monitored wind speed is used for replacing forecast wind speed, the actual landing point of a typhoon center is used for replacing a forecast landing point, and the actual dominant wind direction of the typhoon is used for replacing forecast dominant wind direction.
Further, in step S3, the typhoon disaster prediction model training using the classification decision tree is to train a mathematical model that predicts an output parameter based on an input parameter using the historical typhoon disaster fault record as an input parameter and the typhoon disaster type as an output parameter using the classification decision tree.
Further, in step S3, a classification decision tree is adopted to conduct typhoon disaster prediction model training, historical typhoon disaster data and randomly selected data records of the same number of transmission line towers which do not have faults are utilized to conduct training on three types of typhoon disaster prediction models, the three types of typhoon disaster prediction models are respectively used for predicting wind deflection flashover risks and foreign matter external damage risks (and body damage risks), and three influence factors including terrain classification, voltage grades of the high-voltage overhead transmission line and environmental corrosion grades of the high-voltage overhead transmission line towers are subjected to one-bit effective coding before training is started.
Further, the classification decision tree method selects node sorting based on information gain, selects the influence factor with the largest information gain as a root node, and the information gain calculation formula is as follows:
gain(A)＝info(D)-infoA(D) (1)
in the formula: a is an influencing factor; d is a sample set; info (d) is the information entropy of the sample set; infoA(D) The entropy of the information of the sample set under the condition of the known influence factor A;
the information entropy calculation formula of the sample set is as follows:
in the formula: p is a radical ofiThe probability of occurrence in the sample set for the ith class; n is the total amount of samples;
suppose that the impact factor A has m possible values { A }1,A2,……,AmAnd the calculation formula of the information entropy of the sample set under the condition of the known influence factor A is as follows:
in the formula: i DiThe value of | is equal to A as the influence factor AiThe number of samples of (a); | D | is the total number of samples; info (D)i) The value of the influencing factor A is equal to AiThe entropy of the information of the sample of (1);
after the root node is selected, selecting a subsequent leaf node based on the information gain;
the classification decision tree used in the typhoon disaster prediction of the high-voltage overhead transmission line does not exceed 6 layers.
Further, in step S4, the developing of the typhoon disaster prediction by combining the target high voltage overhead transmission line and the typhoon prediction data means calculating each influence factor value of the high voltage overhead transmission line for which the typhoon disaster prediction is required, and performing the typhoon disaster prediction by using the trained typhoon disaster prediction model.
The high-voltage overhead transmission line typhoon disaster prediction method based on the classification decision tree has the beneficial effects that: the typhoon disaster prediction model is established based on a classification decision tree mode, so that the influence of the typhoon disaster on the high-voltage overhead transmission line can be accurately predicted, and the work of disaster prevention and reduction is scientifically guided.
Drawings
Fig. 1 is a flowchart of a typhoon disaster prediction method for a high-voltage overhead transmission line based on a classification decision tree according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a power transmission line transmission channel structure of a high-voltage overhead power transmission line typhoon disaster prediction method based on a classification decision tree according to an embodiment of the present invention (for calculating and forecasting a heading angle between a main wind direction and a line of a high-voltage overhead power transmission line and a rotation angle of the line of the high-voltage overhead power transmission line).
Fig. 3 is a schematic training flow diagram of a typhoon disaster prediction method for a high-voltage overhead transmission line based on a classification decision tree according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of a one-bit effective encoding result of the voltage class of the high-voltage overhead transmission line typhoon disaster prediction method based on the classification decision tree according to the first embodiment of the present invention.
Fig. 5 is a flowchart of a decision tree of the method for predicting a typhoon disaster of a high-voltage overhead transmission line based on a classification decision tree according to the first embodiment of the present invention, in which the decision tree starts to determine a state corresponding to an impact factor value layer by layer from a root node.
Detailed Description
The technical solutions of the embodiments of the present invention will be explained and explained below with reference to the drawings of the embodiments of the present invention, but the embodiments described below are only preferred embodiments of the present invention, and are not all embodiments. Other embodiments obtained by persons skilled in the art without any inventive work based on the embodiments in the embodiment belong to the protection scope of the invention.
Referring to fig. 1 to 5, a method for predicting typhoon disasters of a high-voltage overhead transmission line based on a classification decision tree according to an embodiment of the present invention includes:
s1, selecting typhoon disaster influence factors of the high-voltage overhead transmission line;
s2, building a historical typhoon disaster fault point influence factor database of the high-voltage overhead transmission line;
s3, training a typhoon disaster prediction model by adopting a classification decision tree;
and S4, adopting a typhoon disaster prediction model and combining the target high-voltage overhead transmission line and typhoon forecast data to carry out typhoon disaster prediction.
Further, in step S1, the typhoon disaster influence factor includes a forecast wind speed at a position of the high voltage overhead transmission line tower, a design wind speed of the high voltage overhead transmission line tower, a terrain classification, a predicted landing point distance between the high voltage overhead transmission line tower and a typhoon, a voltage grade of the high voltage overhead transmission line, a forecast heading angle between a prevailing wind direction and a line of the high voltage overhead transmission line, a line corner number of the high voltage overhead transmission line, a distance between the high voltage overhead transmission line tower and a coast, an environmental corrosion grade of the high voltage overhead transmission line tower, a commissioning life of the high voltage overhead transmission line tower, an altitude of the high voltage overhead transmission line tower, and a height.
Further, in step S1, the forecasted wind speed at the tower position of the high voltage overhead transmission line is an average wind speed at a height of 10m from the ground surface; the designed wind speed of the high-voltage overhead transmission line tower refers to a wind speed value at a height of 10m from the ground; the landform classification is divided into two types of mountain land and flat land; the expected landing point distance between the tower and the typhoon of the high-voltage overhead transmission line refers to the linear distance between the position of the tower and the first landing point of the center of the typhoon. The voltage class of the high-voltage overhead transmission line is divided into Alternating Current (AC) 110kV, Alternating Current (AC) 220kV, Alternating Current (AC) 500kV, Alternating Current (AC) 1000kV, Direct Current (DC) 500kV, Direct Current (DC) 800kV and Direct Current (DC) 1100 kV; forecasting an included angle between the main wind direction and the direction of the high-voltage overhead transmission line to be the smaller angle of two complementary intersection angles formed by the main wind direction and the line direction; the number of the rotation angles of the high-voltage overhead transmission line refers to the rotation angles of the line path direction in front of and behind a certain base tower; the distance between the high-voltage overhead transmission line tower and the coast is the closest straight line distance between the position of the tower and the coast line; the corrosion grade of the environment where the high-voltage overhead transmission line tower is located is divided into C1, C2, C3, C4, C5 and CX from low to high; the commissioning age of the high-voltage overhead transmission line refers to the difference between the current year and the commissioning year; the altitude of the high-voltage overhead transmission line tower refers to the altitude of the position where the tower is located; the height of the high-voltage overhead transmission line tower refers to the total height of the tower.
As shown in fig. 2, in which θ1And theta2For the angle between the main wind direction and the line trend, the main wind direction and the line trend form two complementary crossing angles, and the angle value with smaller degree is taken. In the figure theta3Is a wireThe number of road turning angles refers to the turning angles of the lines in the front and back directions of a certain base tower.
Further, in step S2, the pointer of the typhoon disaster fault point impact factor database establishes a data record for the high-voltage overhead transmission line tower that has a typhoon disaster historically, and the database field includes all typhoon disaster impact factors instep 1, and the name, number, fault type and fault time of the line to which the historical typhoon disaster tower belongs.
Further, the fault types comprise three types of windage yaw flashover, foreign body external damage and body damage.
Furthermore, a historical typhoon disaster fault point influence factor database is built on the basis of historical typhoon disaster investigation of the high-voltage overhead transmission line, 1 data record is set for each base fault tower, the fault tower refers to the tower with the typhoon disaster, and when the typhoon disaster occurs between two base fault towers, the tower closest to the fault occurrence position is used as the fault tower; when the numerical values of the various influence factors are calculated, the actual values are used for replacing forecast values, specifically, the actual monitored wind speed is used for replacing forecast wind speed, the actual landing point of a typhoon center is used for replacing a forecast landing point, and the actual dominant wind direction of the typhoon is used for replacing forecast dominant wind direction.
Further, in step S3, the typhoon disaster prediction model training using the classification decision tree is to train a mathematical model that predicts an output parameter based on an input parameter using the historical typhoon disaster fault record as an input parameter and the typhoon disaster type as an output parameter using the classification decision tree. The classification decision tree is a machine learning algorithm, and particularly relates to a classifier comprising a plurality of decision trees.
Further, in step S3, a classification decision tree is used to train a typhoon disaster prediction model, and historical typhoon disaster data and randomly selected data records of the same number of transmission line towers that have not failed are used to train three types of typhoon disaster prediction models, which are respectively used to predict the windage yaw flashover risk (typhoon disaster prediction model 1), the foreign object external damage risk (typhoon disaster prediction model 2) and the body damage risk (typhoon disaster prediction model 3) of the high-voltage overhead transmission line. Before training, three influence factors of terrain classification, voltage grade of the high-voltage overhead transmission line and corrosion grade of the environment where the high-voltage overhead transmission line tower is located are subjected to one-bit effective coding. A schematic diagram of the one-bit effective encoding result of the voltage class of the high-voltage overhead transmission line is shown in figure 4,
further, the classification decision tree method selects node sorting based on information gain, selects the influence factor with the largest information gain as a root node, and the information gain calculation formula is as follows:
gain(A)＝info(D)-infoA(D) (1)
in the formula: a is an influencing factor; d is a sample set; info (d) is the information entropy of the sample set; infoA(D) The entropy of the information of the sample set under the condition of the known influence factor A;
the information entropy calculation formula of the sample set is as follows:
in the formula: p is a radical ofiThe probability of occurrence in the sample set for the ith class; n is the total amount of samples;
suppose that the impact factor A has m possible values { A }1,A2,……,AmAnd the calculation formula of the information entropy of the sample set under the condition of the known influence factor A is as follows:
in the formula: i DiThe value of | is equal to A as the influence factor AiThe number of samples of (a); | D | is the total number of samples; info (D)i) The value of the influencing factor A is equal to AiThe entropy of the information of the sample of (1);
after the root node is selected, selecting a subsequent leaf node based on the information gain;
the classification decision tree used in the typhoon disaster prediction of the high-voltage overhead transmission line does not exceed 6 layers.
Further, in step S4, the developing of the typhoon disaster prediction by combining the target high voltage overhead transmission line and the typhoon prediction data means calculating each influence factor value of the high voltage overhead transmission line for which the typhoon disaster prediction is required, and performing the typhoon disaster prediction by using the trained typhoon disaster prediction model.
Specifically, when a typhoon comes, the predicted longitude and latitude of a landing point and the wind speed when the typhoon lands can be obtained by using typhoon path forecast data issued by a meteorological department, and in addition, the forecasted wind speed values and the main wind directions of different high-voltage overhead transmission line towers can be obtained through a numerical weather forecasting system. Based on the forecast parameters, the values of the various influence factors listed in S1 can be calculated, and then the typhoon disaster situation of the high-voltage overhead transmission line can be forecasted by using the three typhoon disaster forecasting models trained in S3.
Specifically, as shown in fig. 5, a decision tree in the typhoon disaster prediction model starts to judge the states corresponding to the impact factor values layer by layer from a root node, the states include yes and no, different states enter different next-level nodes until the process runs to the last-level node, and a final result is obtained, that is, whether three risks, namely wind deflection flashover, foreign object external damage and body damage, exist.
The method for predicting the typhoon disaster of the high-voltage overhead transmission line based on the classification decision tree has the beneficial effects that: the typhoon disaster prediction model is established based on a classification decision tree mode, so that the influence of the typhoon disaster on the high-voltage overhead transmission line can be accurately predicted, and the work of disaster prevention and reduction is scientifically guided.
While the invention has been described with reference to specific embodiments thereof, it will be understood by those skilled in the art that the invention is not limited thereto but is intended to cover various modifications and changes, including but not limited to the details shown in the drawings and described in the foregoing detailed description. Any modification which does not depart from the functional and structural principles of the invention is intended to be included within the scope of the following claims.
Claims (10)
1. A typhoon disaster prediction method for a high-voltage overhead transmission line based on a classification decision tree is characterized by comprising the following steps: the prediction method comprises the following steps:
s1, selecting typhoon disaster influence factors of the high-voltage overhead transmission line;
s2, building a historical typhoon disaster fault point influence factor database of the high-voltage overhead transmission line;
s3, training a typhoon disaster prediction model by adopting a classification decision tree;
and S4, adopting a typhoon disaster prediction model and combining the target high-voltage overhead transmission line and typhoon forecast data to carry out typhoon disaster prediction.
2. The method for predicting the typhoon disaster of the high-voltage overhead transmission line based on the classification decision tree according to the claim 1, is characterized in that: in step S1, the typhoon disaster influence factor includes a forecasted wind speed at a position of a high-voltage overhead transmission line tower, a designed wind speed of the high-voltage overhead transmission line tower, a terrain classification, a predicted landing point distance between the high-voltage overhead transmission line tower and a typhoon, a voltage class of the high-voltage overhead transmission line, a forecasted heading angle between a prevailing wind direction and a line of the high-voltage overhead transmission line, a number of corners of the line of the high-voltage overhead transmission line, a distance between the high-voltage overhead transmission line tower and a coast, an environmental corrosion class of the high-voltage overhead transmission line tower, a service life of the high-voltage overhead transmission line.
3. The method for predicting the typhoon disaster of the high-voltage overhead transmission line based on the classification decision tree according to the claim 2 is characterized in that: in the step S1, the forecasted wind speed at the position of the high-voltage overhead transmission line tower refers to the average wind speed at the height of 10m from the ground surface; the designed wind speed of the high-voltage overhead transmission line tower refers to a wind speed value at a height of 10m from the ground; the landform classification is divided into two types of mountain land and flat land; the expected landing point distance between the tower and the typhoon of the high-voltage overhead transmission line is the linear distance between the position of the tower and the first landing point of the center of the typhoon; the voltage class of the high-voltage overhead transmission line is divided into Alternating Current (AC) 110kV, Alternating Current (AC) 220kV, Alternating Current (AC) 500kV, Alternating Current (AC) 1000kV, Direct Current (DC) 500kV, Direct Current (DC) 800kV and Direct Current (DC) 1100 kV; forecasting an included angle between the main wind direction and the direction of the high-voltage overhead transmission line to be the smaller angle of two complementary intersection angles formed by the main wind direction and the line direction; the number of the rotation angles of the high-voltage overhead transmission line refers to the rotation angles of the line path direction in front of and behind a certain base tower; the distance between the high-voltage overhead transmission line tower and the coast is the closest straight line distance between the position of the tower and the coast line; the corrosion grade of the environment where the high-voltage overhead transmission line tower is located is divided into C1, C2, C3, C4, C5 and CX from low to high; the commissioning age of the high-voltage overhead transmission line refers to the difference between the current year and the commissioning year; the altitude of the high-voltage overhead transmission line tower refers to the altitude of the position where the tower is located; the height of the high-voltage overhead transmission line tower refers to the total height of the tower.
4. The method for predicting the typhoon disaster of the high-voltage overhead transmission line based on the classification decision tree according to the claim 2 is characterized in that: in step S2, the typhoon disaster fault point impact factor database pointer establishes a data record for the high-voltage overhead transmission line tower that has a typhoon disaster historically, and the database field includes all the typhoon disaster impact factors in step 1, and the name, number, fault type and fault time of the line to which the historical typhoon disaster tower belongs.
5. The method for predicting the typhoon disaster of the high-voltage overhead transmission line based on the classification decision tree according to the claim 4, is characterized in that: the failure types comprise windage yaw flashover, foreign body external damage and body damage.
6. The method for predicting the typhoon disaster of the high-voltage overhead transmission line based on the classification decision tree according to the claim 5, characterized in that: the method comprises the following steps that a historical typhoon disaster fault point influence factor database is built on the basis of historical typhoon disaster investigation of a high-voltage overhead transmission line, 1 data record is set for each base fault tower, the fault tower refers to a tower with a typhoon disaster, and when the typhoon disaster occurs between two base fault towers, the tower closest to the fault occurrence position serves as the fault tower; when the numerical values of the various influence factors are calculated, the actual values are used for replacing forecast values, specifically, the actual monitored wind speed is used for replacing forecast wind speed, the actual landing point of a typhoon center is used for replacing a forecast landing point, and the actual dominant wind direction of the typhoon is used for replacing forecast dominant wind direction.
7. The method for predicting the typhoon disaster of the high-voltage overhead transmission line based on the classification decision tree according to the claim 1, is characterized in that: in step S3, the classification decision tree is used to train a typhoon disaster prediction model, in which historical typhoon disaster fault records are used as input parameters, typhoon disaster types are used as output parameters, and a mathematical model for predicting the output parameters based on the input parameters is trained by using the classification decision tree.
8. The method for predicting the typhoon disaster of the high-voltage overhead transmission line based on the classification decision tree according to the claim 7, is characterized in that: in the step S3, a classification decision tree is adopted to train a typhoon disaster prediction model, historical typhoon disaster data and randomly selected data records of the same number of transmission line towers which do not have faults are utilized to train three types of typhoon disaster prediction models which are respectively used for predicting windage yaw flashover risks and foreign matter external damage risks (and body damage risks) of the high-voltage overhead transmission line, and before training, three influence factors of terrain classification, voltage grade of the high-voltage overhead transmission line and environmental corrosion grade of the high-voltage overhead transmission line tower are subjected to one-bit effective coding.
9. The method for predicting the typhoon disaster of the high-voltage overhead transmission line based on the classification decision tree according to the claim 7, is characterized in that: the classification decision tree method selects node sorting based on information gain, selects the influence factor with the largest information gain as a root node, and the calculation formula of the information gain is as follows:
gain(A)＝info(D)-infoA(D) (1)
in the formula: a is an influencing factor; d is a sample set; info (d) is the information entropy of the sample set; infoA(D) For the known influence factor A caseThe information entropy of the sample set of;
the information entropy calculation formula of the sample set is as follows:
in the formula: p is a radical ofiThe probability of occurrence in the sample set for the ith class; n is the total amount of samples;
suppose that the impact factor A has m possible values { A }1,A2,……,AmAnd the calculation formula of the information entropy of the sample set under the condition of the known influence factor A is as follows:
in the formula: i DiThe value of | is equal to A as the influence factor AiThe number of samples of (a); | D | is the total number of samples; info (D)i) The value of the influencing factor A is equal to AiThe entropy of the information of the sample of (1);
after the root node is selected, selecting a subsequent leaf node based on the information gain;
the classification decision tree used in the typhoon disaster prediction of the high-voltage overhead transmission line does not exceed 6 layers.
10. The method for predicting the typhoon disaster of the high-voltage overhead transmission line based on the classification decision tree according to the claim 1, is characterized in that: in step S4, the typhoon disaster prediction performed by combining the target high-voltage overhead transmission line and the typhoon prediction data means that each influence factor value of the high-voltage overhead transmission line for which the typhoon disaster prediction is required is calculated, and the typhoon disaster prediction is performed by using the trained typhoon disaster prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911211112.0ACN111126672A (en) | 2019-12-02 | 2019-12-02 | A typhoon disaster prediction method for high-voltage overhead transmission lines based on classification decision tree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911211112.0ACN111126672A (en) | 2019-12-02 | 2019-12-02 | A typhoon disaster prediction method for high-voltage overhead transmission lines based on classification decision tree |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111126672Atrue CN111126672A (en) | 2020-05-08 |
Family
ID=70496535
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911211112.0APendingCN111126672A (en) | 2019-12-02 | 2019-12-02 | A typhoon disaster prediction method for high-voltage overhead transmission lines based on classification decision tree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111126672A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951550A (en)* | 2020-08-06 | 2020-11-17 | 华南理工大学 | Traffic safety risk monitoring method, device, storage medium and computer equipment |
| CN112529067A (en)* | 2020-12-04 | 2021-03-19 | 国网电力科学研究院武汉南瑞有限责任公司 | Power transmission line ice wind disaster fault type evaluation method based on naive Bayes |
| CN112861973A (en)* | 2021-02-08 | 2021-05-28 | 汕头大学 | Communication tower fault diagnosis method based on decision tree |
| CN113191585A (en)* | 2021-03-23 | 2021-07-30 | 广东电网有限责任公司东莞供电局 | Typhoon disaster risk assessment method for power transmission line |
| CN115115163A (en)* | 2021-12-15 | 2022-09-27 | 昆明能讯科技有限责任公司 | Evaluation method and storage medium of transmission line tower failure risk degree under typhoon transit |
| CN118333226A (en)* | 2024-05-06 | 2024-07-12 | 国网福建省电力有限公司 | A method for disaster damage assessment of power transmission and distribution line equipment based on decision tree |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096110A (en)* | 2016-06-03 | 2016-11-09 | 国网电力科学研究院武汉南瑞有限责任公司 | Flashover of power transmission circuit caused by windage yaw method for early warning based on numerical weather forecast |
| CN107886194A (en)* | 2017-10-31 | 2018-04-06 | 广东电网有限责任公司惠州供电局 | Foreign matter hanging wire probability of malfunction computational methods under a kind of strong wind disaster |
| CN108564263A (en)* | 2018-04-02 | 2018-09-21 | 国网安徽省电力有限公司电力科学研究院 | One kind is for the disaster-stricken prediction technique of electric power line pole tower under squall line environment |
| CN109359882A (en)* | 2018-10-29 | 2019-02-19 | 武汉理工大学 | A risk assessment method for transmission line tripping under typhoon disaster |
| CN109522599A (en)* | 2018-10-16 | 2019-03-26 | 国电南瑞科技股份有限公司 | Transmission line of electricity catastrophic failure method for early warning caused by a kind of typhoon |
| CN109522957A (en)* | 2018-11-16 | 2019-03-26 | 上海海事大学 | The method of harbour gantry crane machine work status fault classification based on decision Tree algorithms |
| CN110097223A (en)* | 2019-04-30 | 2019-08-06 | 武汉理工大学 | Early warning method for damage of power transmission line under typhoon disaster |
- 2019
- 2019-12-02CNCN201911211112.0Apatent/CN111126672A/enactivePending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096110A (en)* | 2016-06-03 | 2016-11-09 | 国网电力科学研究院武汉南瑞有限责任公司 | Flashover of power transmission circuit caused by windage yaw method for early warning based on numerical weather forecast |
| CN107886194A (en)* | 2017-10-31 | 2018-04-06 | 广东电网有限责任公司惠州供电局 | Foreign matter hanging wire probability of malfunction computational methods under a kind of strong wind disaster |
| CN108564263A (en)* | 2018-04-02 | 2018-09-21 | 国网安徽省电力有限公司电力科学研究院 | One kind is for the disaster-stricken prediction technique of electric power line pole tower under squall line environment |
| CN109522599A (en)* | 2018-10-16 | 2019-03-26 | 国电南瑞科技股份有限公司 | Transmission line of electricity catastrophic failure method for early warning caused by a kind of typhoon |
| CN109359882A (en)* | 2018-10-29 | 2019-02-19 | 武汉理工大学 | A risk assessment method for transmission line tripping under typhoon disaster |
| CN109522957A (en)* | 2018-11-16 | 2019-03-26 | 上海海事大学 | The method of harbour gantry crane machine work status fault classification based on decision Tree algorithms |
| CN110097223A (en)* | 2019-04-30 | 2019-08-06 | 武汉理工大学 | Early warning method for damage of power transmission line under typhoon disaster |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951550A (en)* | 2020-08-06 | 2020-11-17 | 华南理工大学 | Traffic safety risk monitoring method, device, storage medium and computer equipment |
| CN111951550B (en)* | 2020-08-06 | 2021-10-29 | 华南理工大学 | Traffic safety risk monitoring method, device, storage medium and computer equipment |
| CN112529067A (en)* | 2020-12-04 | 2021-03-19 | 国网电力科学研究院武汉南瑞有限责任公司 | Power transmission line ice wind disaster fault type evaluation method based on naive Bayes |
| CN112861973A (en)* | 2021-02-08 | 2021-05-28 | 汕头大学 | Communication tower fault diagnosis method based on decision tree |
| CN113191585A (en)* | 2021-03-23 | 2021-07-30 | 广东电网有限责任公司东莞供电局 | Typhoon disaster risk assessment method for power transmission line |
| CN115115163A (en)* | 2021-12-15 | 2022-09-27 | 昆明能讯科技有限责任公司 | Evaluation method and storage medium of transmission line tower failure risk degree under typhoon transit |
| CN118333226A (en)* | 2024-05-06 | 2024-07-12 | 国网福建省电力有限公司 | A method for disaster damage assessment of power transmission and distribution line equipment based on decision tree |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111126672A (en) | A typhoon disaster prediction method for high-voltage overhead transmission lines based on classification decision tree | |
| CN104239970B (en) | A kind of conductor galloping method for prewarning risk based on Adaboost | |
| CN107292478B (en) | Method for acquiring influence situation of disaster on power distribution network | |
| CN111275216B (en) | Hierarchical collaborative optimization inspection method for high-voltage transmission full-line | |
| CN105427019B (en) | A kind of geographical meteorological related transmission line of electricity risk difference evaluation method | |
| CN107230015A (en) | A kind of power distribution network toughness appraisal procedure based on system information entropy | |
| CN110866693B (en) | A GIS model-based ice-covering risk assessment method for overhead transmission lines | |
| CN112116160B (en) | Important power transmission channel disaster monitoring method based on improved cellular automaton of optimized neural network | |
| CN103678865B (en) | A kind of sleet causes the probability of malfunction online evaluation method of transmission line malfunction | |
| CN111612315A (en) | A new type of early warning method for catastrophic high winds in power grids | |
| CN112668821B (en) | Distribution line risk analysis method based on wind-sand region insulator fault probability | |
| CN109522599A (en) | Transmission line of electricity catastrophic failure method for early warning caused by a kind of typhoon | |
| CN105426671B (en) | The reliability evaluating method of overhead distribution under a kind of Thunderstorm Weather | |
| CN110378549B (en) | A method for evaluating the bird damage level of transmission towers based on FAHP-entropy weight method | |
| CN102508046A (en) | Real-time lightning stroke prewarning method and device for outdoor electric equipment | |
| CN115115163A (en) | Evaluation method and storage medium of transmission line tower failure risk degree under typhoon transit | |
| CN117436351B (en) | Power grid equipment fault prediction method and system based on knowledge graph under complex weather conditions | |
| CN106327071A (en) | Power line communication risk analysis method and power line communication risk analysis system | |
| CN111680862A (en) | Risk early warning method of multi-source data fusion in distribution network based on spatiotemporal grid association | |
| CN106055889A (en) | A Method for Evaluating the State of Overhead Transmission Lines | |
| Wu et al. | Extension of power system early-warning defense schemes by integrating typhoon information | |
| CN113609752A (en) | Distribution transformer loss evaluation system and method for southwest vortex | |
| CN105203926B (en) | A kind of method for improving super high voltage direct current electricity transmission line fault location accuracy | |
| CN112257329A (en) | Method for judging influence of typhoon on line | |
| CN111092430A (en) | An optimal allocation method of emergency resources suitable for power system restoration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20200508 |