CN111428942A - Line icing thickness prediction method for extracting micro-terrain factors based on variable grid technology - Google Patents
Line icing thickness prediction method for extracting micro-terrain factors based on variable grid technology Download PDFInfo
- Publication number
- CN111428942A CN111428942A CN202010298173.1A CN202010298173A CN111428942A CN 111428942 A CN111428942 A CN 111428942A CN 202010298173 A CN202010298173 A CN 202010298173A CN 111428942 A CN111428942 A CN 111428942A
- Authority
- CN
- China
- Prior art keywords
- micro
- data
- icing
- terrain
- grid
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000005516 engineering process Methods 0.000 title claims abstract description 29
- 239000011248 coating agent Substances 0.000 claims abstract description 33
- 238000000576 coating method Methods 0.000 claims abstract description 33
- 238000012544 monitoring process Methods 0.000 claims abstract description 30
- 238000013528 artificial neural network Methods 0.000 claims abstract description 15
- 238000000605 extraction Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000010606 normalization Methods 0.000 claims abstract description 4
- 238000011160 research Methods 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 28
- 230000006870 function Effects 0.000 claims description 18
- 238000012821 model calculation Methods 0.000 claims description 9
- 238000011161 development Methods 0.000 claims description 6
- 230000005284 excitation Effects 0.000 claims description 6
- 238000013178 mathematical model Methods 0.000 claims description 6
- 230000003746 surface roughness Effects 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- GZPBVLUEICLBOA-UHFFFAOYSA-N 4-(dimethylamino)-3,5-dimethylphenol Chemical compound CN(C)C1=C(C)C=C(O)C=C1C GZPBVLUEICLBOA-UHFFFAOYSA-N 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000011835 investigation Methods 0.000 claims description 3
- 238000013077 scoring method Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 abstract description 7
- 230000001419 dependent effect Effects 0.000 abstract description 2
- 238000007792 addition Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a line icing thickness prediction method for extracting micro-terrain factors based on a variable grid technology, which comprises the following steps: step 1, acquiring a digital elevation model of a research area, and correcting image coordinates by using geographic information system software; step 2, collecting ice region distribution map vector files, power grid space data, ice coating monitoring terminal data and ice coating thickness, and preprocessing the data; step 3, extracting micro-terrain factor data of each monitoring terminal position by adopting a variable grid technology; step 4, calculating the average value of the maximum ice coating thickness of each ice coating monitoring terminal in the latest 5 ice periods in the step 2; step 5, carrying out normalization processing on the data in the step 3; and 6, establishing a prediction model between the micro-terrain factor and the line icing thickness by taking the data in the step 5 as independent variables and the data in the step 4 as dependent variables and adopting a neural network method, so that the problems that the extraction of the micro-terrain factor is time-consuming and the prediction of the icing thickness of the power transmission line is inaccurate are solved.
Description
Technical Field
The invention belongs to the field of risk assessment of icing disasters of power transmission lines; in particular to a line icing thickness prediction method for extracting micro-terrain factors based on a variable grid technology.
Background
The mountainous area terrain is complex and changeable, and due to the influence of micro-terrain factors on local meteorology, the icing grades of power transmission lines at different parts of the same mountain are different, and the icing of the power transmission lines in the mountainous area seriously harms the safe operation of a power system. Although a power grid company monitors the ice condition of a line by a series of means, such as an ice coating monitoring system, a manual handheld ice observation device and the like, the ice coating thickness calculation method is single, so that the ice coating condition of all micro-terrain areas cannot be represented, and the ice coating condition of the line cannot be accurately mastered because of the fact that the manual work cannot directly reach the ice coating site of the line due to special terrain. The GIS technology can accurately identify the micro-terrain factors in the adjacent area of the line, and has great significance in establishing a line icing thickness prediction model considering the micro-terrain factors. The literature, namely micro-terrain factor identification and extraction based on GIS, introduces identification of various micro-terrain factors, and micro-terrain factors are extracted by using grids with the same size, so that the method is long in time consumption; the patent: a power line icing thickness prediction method (CN103020740A) based on microclimate data inputs predicted meteorological data into an artificial neural network model to calculate corresponding icing thickness, and the method comprises the following steps: a method (CN106682771A) for predicting icing thickness of a power transmission line based on microclimate information trains a regression model with icing thickness as a dependent variable and microclimate temperature as an independent variable by using historical icing thickness data of the power transmission line and microclimate historical temperature data corresponding to the historical icing thickness, and predicts the icing thickness by using the trained model and a meteorological station to predict the meteorological temperature. The method obtains icing thickness prediction by training different models by using microclimate data, seriously depends on meteorological prediction data provided by a professional meteorological station, and has inaccurate icing thickness prediction result due to the fact that meteorological conditions change greatly and errors exist between the prediction data and actual monitoring data.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: the method for predicting the icing thickness of the line based on the variable grid technology extraction micro-terrain factor is provided, so that the problems that the micro-terrain factor extraction is time-consuming and the prediction of the icing thickness of the power transmission line is inaccurate are solved.
The technical scheme of the invention is as follows:
a line icing thickness prediction method for extracting micro-terrain factors based on a variable grid technology comprises the following steps:
step 1, acquiring a prediction area digital elevation model, and correcting the image coordinates of the prediction area digital elevation model by using geographic information system software;
step 2, acquiring vector files of ice region distribution maps in a prediction region, historical cold tide development paths, power grid space data, ice coating monitoring terminal data and ice coating thickness, preprocessing the data, and taking the corrected digital elevation model as a coordinate system to obtain the vector files of the ice region distribution maps, the power grid space data and coordinates of the ice coating monitoring terminal on the corrected digital elevation model;
step 3, extracting micro-terrain factor data of the positions of the ice-coating monitoring terminals by adopting a variable grid technology, wherein the micro-terrain factors comprise elevation, gradient, slope direction, terrain roughness and terrain relief degree, and quantizing the slope direction;
step 4, calculating the average value of the maximum ice coating thickness monitored by each ice coating monitoring terminal in the last 5 ice periods in the step 3; step 5, carrying out normalization processing on the micro terrain factor data processed in the step 3;
and 6, establishing a prediction model between the micro-terrain factor and the line icing thickness by adopting a neural network method by taking the micro-terrain factor processed in the step 5 as an input layer and the maximum icing thickness average value processed in the step 4 as an output layer.
The power grid space data acquired in the step 2 comprise 35kV and line names, pole tower longitude and latitude and line icing fault historical data, the icing monitoring terminal data comprise administrative divisions, voltage classes and longitude and latitude, the icing thickness data comprise historical data of the latest 5 icing periods, and the data preprocessing method comprises the following steps:
step 2.1, carrying out standard processing of naming and removing weight on the ice-coating monitoring terminal data;
and 2.2, checking the position information of the icing terminal by utilizing the power grid space data and field investigation.
Step 3, the grid-changing technology comprises the following steps:
step 3.1, extracting area surface files of each icing magnitude according to the vector file of the ice area distribution map of the prediction area;
step 3.2, dividing the icing magnitude of 30mm-40mm, 40mm-50mm and above into historical icing severe regions, and dividing the rest icing magnitude regions into historical icing lighter regions;
and 3.3, carrying out grid division on the digital elevation model of the prediction area by adopting a variable grid technology, dividing the historical ice-coated severe area into more than two fine grids, and dividing the historical ice-coated lighter area into more than two coarse grids.
And 3, the method for extracting the elevation, the gradient, the slope direction, the terrain roughness and the terrain relief degree comprises the following steps:
the elevation is directly obtained by a digital elevation model;
the gradient extraction adopts a three-order inverse distance square weight difference method, namely a 3 × 3 window consisting of 9 small grids, and a calculation formula of the gradient and the gradient direction of a central point e:
Aspect＝Slopen/Slopec
in the formula, Slope is the gradient, Aspect is the Slope direction, SlopecSlope in the x-axis direction, SlopenThe grid gradient is the gradient of the y axis direction, cell is the grid size of a digital elevation model, e5 is the grid gradient of the central point e in the direction close to the northwest, e1 is the grid gradient of the central point e in the direction close to the positive west, e8 is the grid gradient of the central point e in the direction close to the southwest, e7 is the grid gradient of the central point e in the direction close to the southeast, e3 is the grid gradient of the central point e in the direction close to the positive east, and e6 is the grid gradient of the central point e in the direction close to the northeast;
the surface roughness calculation method comprises the following steps:
m＝s/st
where m is the surface roughness, s is the surface area of each grid cell, stProjecting an area for each grid cell;
the surface relief degree calculation method includes:
and respectively calculating the maximum elevation value DMAX and the minimum elevation value DMIN of the digital elevation model in each fine grid and each coarse grid according to the division result of the digital elevation model variable grid technology of the research area by using a Focal function, and then calculating the difference value.
The method for quantizing the slope direction comprises the following steps:
extracting results of the slope directions into 8 directions of east, south, west, north, southeast, northeast, southwest and northwest, respectively quantitatively scoring the influence degrees of the 8 slope directions of the tower positions where the icing monitoring terminals are located on the line icing by adopting an expert percentile scoring method and combining an ice region distribution diagram, a historical cold tide development path and line icing fault historical data, and finally taking the average value of the evaluation values.
The formula for normalizing the microtopography factor data processed in the step 3 in the step 5 comprises:
in the formula, xijIn order to be a value after the processing,
as an initial value of index, xmaxj、xminjThe j index maximum value and the j index minimum value are respectively.
Step 6, the method for establishing the relation model between the micro-terrain factor and the line icing thickness by adopting the neural network method comprises the following steps: adopting three layers of BP neural network mathematical models, namely an input layer, a hidden layer and an output layer, wherein the input layer is the data of each micro-terrain factor in the step 5, and the output layer is the icing thickness value corresponding to the jth micro-terrain factor;
the hidden layer calculation expression is:
in the formula yjIs the output value, x, of the jth node of the hidden layeriInputting data for the micro-terrain factor of the ith node,
ajthreshold, ω, for the ith node of the hidden layerjiThe weighted value from the ith node of the hidden layer to the jth node of the output layer is shown, N is the number of the nodes of the hidden layer, and f (x) is an S-shaped excitation function;
the output value calculation expression of the jth node of the output layer is as follows:
in the formula ZjIs the output value of the jth node of the output layer, bjIs the jth node threshold of the output layer, yiFor the output value of the ith node of the hidden layer, ωjiThe weight value from the ith node of the hidden layer to the jth node of the output layer, M is the number of the nodes of the output layer, namely the thickness of the ice coating, and f (x) is an S-shaped excitation function;
the error function expression of the calculation result of the established three-layer BP neural network mathematical model is as follows:
wherein e is the model calculation error, the error critical value is set to be 0.001, when the model calculation error is less than the critical value, the training is stopped, and Z isjOutput layer calculation for BP model, zjAn observed value of the icing monitoring terminal is obtained;
weight function omegajiThe calculation expression is:
ωji(yp+1)＝ωji(yp)+Δωji
wherein ω isji(yp) Is the weight, ω, of the p-th sample node i to node jji(yp+1) is the weight from node i to node j for the p +1 th sample, Δ ωjiIs the weight value change quantity;
weight value change Δ ωjiThe calculation expression is:
η is learning efficiency, values are distributed between 0-1, e is model calculation error, omegajiIs a weight function.
The invention has the beneficial effects that:
in order to overcome the defect that time consumption is consumed for extracting micro-terrain factors by using grids with the same size, the micro-terrain factors are identified by using a Digital Elevation Model (DEM) and adopting a variable grid technology, namely, an ice-covered severe area is divided by adopting a fine grid, an ice-covered non-severe area is divided by adopting a coarse grid, the extraction efficiency of the micro-terrain factors of a large area is improved, and a prediction model between the micro-terrain factors and line ice is established by combining ice-covered data of an ice-covered monitoring terminal and power grid space data and adopting a neural network algorithm.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a schematic view of a 3 × 3 grid window;
the specific implementation mode is as follows:
the method for selecting the digital elevation model for predicting the regional area in the invention is a 12.5m resolution digital elevation model in Guizhou province, and the specific implementation mode is shown in FIG. 1, and the method comprises the following steps:
step 1, acquiring a prediction area digital elevation model, and correcting the image coordinates of the prediction area digital elevation model by using geographic information system software;
step 2, acquiring vector files of ice region distribution maps in a prediction region, historical cold tide development paths, power grid space data, ice coating monitoring terminal data and ice coating thickness, preprocessing the data, and taking the corrected digital elevation model as a coordinate system to obtain the vector files of the ice region distribution maps, the power grid space data and coordinates of the ice coating monitoring terminal on the corrected digital elevation model;
step 3, extracting micro-terrain factor data of the positions of the ice-coating monitoring terminals by adopting a variable grid technology, wherein the micro-terrain factors comprise elevation, gradient, slope direction, terrain roughness and terrain relief degree, and quantizing the slope direction;
step 4, calculating the average value of the maximum ice coating thickness monitored by each ice coating monitoring terminal in the last 5 ice periods in the step 3;
step 5, carrying out normalization processing on the micro terrain factor data processed in the step 3;
and 6, establishing a prediction model between the micro-terrain factor and the line icing thickness by adopting a neural network method by taking the micro-terrain factor processed in the step 5 as an input layer and the maximum icing thickness average value processed in the step 4 as an output layer.
The power grid space data acquired in the step 2 comprise 35kV and line names, pole tower longitude and latitude and line icing fault historical data, the icing monitoring terminal data comprise administrative divisions, voltage classes and longitude and latitude, the icing thickness data comprise historical data of the latest 5 icing periods, and the data preprocessing method comprises the following steps:
step 2.1, carrying out standard processing of naming and removing weight on the ice-coating monitoring terminal data;
and 2.2, checking the position information of the icing terminal by utilizing the power grid space data and field investigation.
Step 3, the grid-changing technology comprises the following steps:
step 3.1, extracting area surface files of each icing magnitude according to the vector file of the ice area distribution map of the prediction area;
step 3.2, dividing the icing magnitude of 30mm-40mm, 40mm-50mm and above into historical icing severe regions, and dividing the rest icing magnitude regions into historical icing lighter regions;
and 3.3, carrying out grid division on the digital elevation model of the prediction area by adopting a variable grid technology, dividing the historical ice-coated severe area into more than two fine grids, and dividing the historical ice-coated lighter area into more than two coarse grids.
The ice region distribution diagram of the Guizhou power grid 2018 version is selected in the embodiment;
the digital elevation model is a 12.5m resolution digital elevation model selected in Guizhou province;
the specification of the fine grid of the digital elevation model is 5m × 5 m;
the specification of the digital elevation model coarse grid is 500m × 500 m;
and 3, the method for extracting the gradient, the slope direction, the terrain roughness and the terrain relief degree comprises the following steps:
the elevation is directly obtained by a digital elevation model;
the gradient extraction adopts a three-order inverse distance square weight difference method, namely a 3 × 3 window consisting of 9 small grids, and a calculation formula of the gradient and the gradient direction of a central point e:
Aspect＝Slopen/Slopec
in the formula, Slope is the gradient, Aspect is the Slope direction, SlopecSlope in the x-axis direction, SlopenThe grid gradient is the gradient of the y axis direction, cell is the grid size of a digital elevation model, e5 is the grid gradient of the central point e in the direction close to the northwest, e1 is the grid gradient of the central point e in the direction close to the positive west, e8 is the grid gradient of the central point e in the direction close to the southwest, e7 is the grid gradient of the central point e in the direction close to the southeast, e3 is the grid gradient of the central point e in the direction close to the positive east, and e6 is the grid gradient of the central point e in the direction close to the northeast;
the surface roughness calculation method comprises the following steps:
m＝s/st
where m is the surface roughness, s is the surface area of each grid cell, stProjecting an area for each grid cell;
the surface relief degree calculation method includes:
and respectively calculating the maximum elevation value DMAX and the minimum elevation value DMIN of the digital elevation model in each fine grid and each coarse grid according to the division result of the digital elevation model variable grid technology of the research area by using a Focal function, and then calculating the difference value.
The method for quantizing the slope direction comprises the following steps:
the method mainly comprises the steps of dividing the extraction result of the slope direction into 8 directions of east, south, west, north, southeast, northeast, southwest and northwest, quantitatively scoring the influence degree of the 8 slope directions of the tower positions where the icing monitoring terminals are located on the icing of the line respectively by adopting an expert percentile scoring method and combining an ice region distribution diagram, a historical cold tide development path and historical line icing fault data, and finally taking the average value of the evaluation results.
The formula for normalizing the result factors in the step 3 in the step 5 comprises:
in the formula (I), the compound is shown in the specification,
as an initial value of index, xmaxj、xminjThe j index maximum value and the j index minimum value are respectively.
Step 6, the concrete implementation method for establishing the relation model between the micro-terrain factor and the line icing thickness by adopting the neural network method comprises the following steps: adopting three layers of BP neural network mathematical models, namely an input layer, a hidden layer and an output layer, wherein the input layer is the data of each micro-terrain factor in the step 5, and the output layer is the icing thickness value corresponding to the jth micro-terrain factor;
the hidden layer calculation expression is:
in the formula yjIs the output value, x, of the jth node of the hidden layeriFor the i-th node microtopography factor input data, ajThreshold, ω, for the ith node of the hidden layerjiThe weighted value from the ith node of the hidden layer to the jth node of the output layer is shown, N is the number of the nodes of the hidden layer, and f (x) is an S-shaped excitation function;
the output value calculation expression of the jth node of the output layer is as follows:
in the formula ZjIs the output value of the jth node of the output layer, bjIs the jth node threshold of the output layer, yiFor the output value of the ith node of the hidden layer, ωjiThe weight value from the ith node of the hidden layer to the jth node of the output layer, M is the number of the nodes of the output layer, namely the thickness of the ice coating, and f (x) is an S-shaped excitation function;
the established three-layer BP neural network mathematical model calculates the error function expression:
wherein e is the model calculation error, the error critical value is set to be 0.001, when the model calculation error is less than the critical value, the training is stopped, and Z isjOutput layer calculation for BP model, zjAn observed value of the icing monitoring terminal is obtained;
weight function omegajiThe calculation expression is:
ωji(yp+1)＝ωji(yp)+Δωji
wherein ω isji(yp) Is the weight, ω, of the p-th sample node i to node jji(yp+1) is the weight from node i to node j for the p +1 th sample, Δ ωjiIs the weight value change quantity;
weight value change Δ ωjiThe calculation expression is:
η is learning efficiency, values are distributed between 0-1, e is model calculation error, omegajiIs a weight function;
η, the larger the value, the shorter the time needed for training the BP model, but the model is not easy to converge, so in the invention, η is 0.2.
The invention discloses a line icing thickness prediction method based on variable grid technology extraction of micro-terrain factors, which is mainly based on variable grid technology extraction of micro-terrain factors and is used for solving the line icing thickness prediction problem. The above examples are merely illustrative of the technical solutions of the present invention and are not intended to be limiting, and with reference to the above examples, several additions and modifications can be made without departing from the calculation method of the present invention, and these additions and modifications should also be construed as the scope of the present invention.
Claims (8)
1. A line icing thickness prediction method for extracting micro-terrain factors based on a variable grid technology comprises the following steps:
step 1, acquiring a prediction area digital elevation model, and correcting the image coordinates of the prediction area digital elevation model by using geographic information system software;
step 2, acquiring vector files of ice region distribution maps in a prediction region, historical cold tide development paths, power grid space data, ice coating monitoring terminal data and ice coating thickness, preprocessing the data, and taking the corrected digital elevation model as a coordinate system to obtain the vector files of the ice region distribution maps, the power grid space data and coordinates of the ice coating monitoring terminal on the corrected digital elevation model;
step 3, extracting micro-terrain factor data of the positions of the ice-coating monitoring terminals by adopting a variable grid technology, wherein the micro-terrain factors comprise elevation, gradient, slope direction, terrain roughness and terrain relief degree, and quantizing the slope direction;
step 4, calculating the average value of the maximum ice coating thickness monitored by each ice coating monitoring terminal in the last 5 ice periods in the step 3;
step 5, carrying out normalization processing on the micro terrain factor data processed in the step 3;
and 6, establishing a prediction model between the micro-terrain factor and the line icing thickness by adopting a neural network method by taking the micro-terrain factor processed in the step 5 as an input layer and the maximum icing thickness average value processed in the step 4 as an output layer.
2. The line icing thickness prediction method for extracting the micro-terrain factor based on the variable mesh technology as claimed in claim 1, wherein: the power grid space data acquired in the step 2 comprise 35kV and line names, pole tower longitude and latitude and line icing fault historical data, the icing monitoring terminal data comprise administrative divisions, voltage classes and longitude and latitude, the icing thickness data comprise historical data of the latest 5 icing periods, and the data preprocessing method comprises the following steps:
step 2.1, carrying out standard processing of naming and removing weight on the ice-coating monitoring terminal data;
and 2.2, checking the position information of the icing terminal by utilizing the power grid space data and field investigation.
3. The line icing thickness prediction method for extracting the micro-terrain factor based on the variable mesh technology as claimed in claim 1, wherein: step 3, the grid-changing technology comprises the following steps:
step 3.1, extracting area surface files of each icing magnitude according to the vector file of the ice area distribution map of the prediction area;
step 3.2, dividing the icing magnitude of 30mm-40mm, 40mm-50mm and above into historical icing severe regions, and dividing the rest icing magnitude regions into historical icing lighter regions;
and 3.3, carrying out grid division on the digital elevation model of the prediction area by adopting a variable grid technology, dividing the historical ice-coated severe area into more than two fine grids, and dividing the historical ice-coated lighter area into more than two coarse grids.
4. The line icing thickness prediction method for extracting the micro-terrain factor based on the variable mesh technology as claimed in claim 3, wherein the method comprises the following steps: and 3, the method for extracting the elevation, the gradient, the slope direction, the terrain roughness and the terrain relief degree comprises the following steps:
the elevation is directly obtained by a digital elevation model;
the gradient extraction adopts a three-order inverse distance square weight difference method, namely a 3 × 3 window consisting of 9 small grids, and a calculation formula of the gradient and the gradient direction of a central point e:
Aspect＝Slopen/Slopec
in the formula, Slope is the gradient, Aspect is the Slope direction, SlopecSlope in the x-axis direction, SlopenThe gradient in the y-axis direction, Cellsize is the grid size of the digital elevation model, and e5 is the northwest direction adjacent to the center point eThe grid gradient is that e1 is the grid gradient of the central point e in the direction adjacent to the positive west, e8 is the grid gradient of the central point e in the direction adjacent to the south west, e7 is the grid gradient of the central point e in the direction adjacent to the south east, e3 is the grid gradient of the central point e in the direction adjacent to the positive east, and e6 is the grid gradient of the central point e in the direction adjacent to the north east;
the surface roughness calculation method comprises the following steps:
m＝s/st
where m is the surface roughness, s is the surface area of each grid cell, stProjecting an area for each grid cell;
the surface relief degree calculation method includes:
and respectively calculating the maximum elevation value DMAX and the minimum elevation value DMIN of the digital elevation model in each fine grid and each coarse grid according to the division result of the digital elevation model variable grid technology of the research area by using a Focal function, and then calculating the difference value.
5. The line icing thickness prediction method for extracting the micro-terrain factor based on the variable mesh technology as claimed in claim 1, wherein: the method for quantizing the slope direction comprises the following steps:
extracting results of the slope directions into 8 directions of east, south, west, north, southeast, northeast, southwest and northwest, respectively quantitatively scoring the influence degrees of the 8 slope directions of the tower positions where the icing monitoring terminals are located on the line icing by adopting an expert percentile scoring method and combining an ice region distribution diagram, a historical cold tide development path and line icing fault historical data, and finally taking the average value of the evaluation values.
6. The line icing thickness prediction method for extracting the micro-terrain factor based on the variable mesh technology as claimed in claim 1, wherein: the formula for normalizing the microtopography factor data processed in the step 3 in the step 5 comprises:
in the formula, xijIs at a positionThe value of the result of the processing is,
as an initial value of index, xmaxj、xminjThe j index maximum value and the j index minimum value are respectively.
7. The method for extracting variable grids based on the micro-terrain factors and predicting the icing thickness of the line according to claim 1, wherein the method comprises the following steps: step 6, the method for establishing the relation model between the micro-terrain factor and the line icing thickness by adopting the neural network method comprises the following steps: adopting three layers of BP neural network mathematical models, namely an input layer, a hidden layer and an output layer, wherein the input layer is the data of each micro-terrain factor in the step 5, and the output layer is the icing thickness value corresponding to the jth micro-terrain factor;
the hidden layer calculation expression is:
in the formula yjIs the output value, x, of the jth node of the hidden layeriFor the i-th node microtopography factor input data, ajThreshold, ω, for the ith node of the hidden layerjiThe weighted value from the ith node of the hidden layer to the jth node of the output layer is shown, N is the number of the nodes of the hidden layer, and f (x) is an S-shaped excitation function;
the output value calculation expression of the jth node of the output layer is as follows:
in the formula ZjIs the output value of the jth node of the output layer, bjIs the jth node threshold of the output layer, yiFor the output value of the ith node of the hidden layer, ωjiThe weight value from the ith node of the hidden layer to the jth node of the output layer, M is the number of the nodes of the output layer, namely the thickness of the ice coating, and f (x) is an S-shaped excitation function.
8. The method for extracting variable grids based on the micro-terrain factors and predicting the icing thickness of the line according to claim 7, wherein the method comprises the following steps: the error function expression of the calculation result of the established three-layer BP neural network mathematical model is as follows:
wherein e is the model calculation error, the error critical value is set to be 0.001, when the model calculation error is less than the critical value, the training is stopped, and Z isjOutput layer calculation for BP model, zjAn observed value of the icing monitoring terminal is obtained; weight function omegajiThe calculation expression is:
ωji(yp+1)＝ωji(yp)+Δωji
wherein ω isji(yp) Is the weight, ω, of the p-th sample node i to node jji(yp+1) is the weight from node i to node j for the p +1 th sample, Δ ωjiIs the weight value change quantity;
weight value change Δ ωjiThe calculation expression is:
η is learning efficiency, values are distributed between 0-1, e is model calculation error, omegajiIs a weight function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010298173.1A CN111428942B (en) | 2020-04-16 | 2020-04-16 | Line icing thickness prediction method for extracting micro-terrain factors based on variable grid technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010298173.1A CN111428942B (en) | 2020-04-16 | 2020-04-16 | Line icing thickness prediction method for extracting micro-terrain factors based on variable grid technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111428942A true CN111428942A (en) | 2020-07-17 |
| CN111428942B CN111428942B (en) | 2022-06-07 |
Family
ID=71556441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010298173.1A Active CN111428942B (en) | 2020-04-16 | 2020-04-16 | Line icing thickness prediction method for extracting micro-terrain factors based on variable grid technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111428942B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112630836A (en) * | 2020-12-11 | 2021-04-09 | 国网湖南省电力有限公司 | Monitoring and stationing method and system based on power grid micro-terrain icing threat path extension analysis |
| CN113076635A (en) * | 2021-03-26 | 2021-07-06 | 云南电网有限责任公司电力科学研究院 | Lightning activity analysis method and device based on micro-terrain environment characteristics |
| CN113779507A (en) * | 2021-09-15 | 2021-12-10 | 中国电建集团贵州电力设计研究院有限公司 | Method for establishing icing prediction model based on elevation data |
| CN113821895A (en) * | 2021-09-01 | 2021-12-21 | 南方电网科学研究院有限责任公司 | Construction method and device of power transmission line icing thickness prediction model and storage medium |
| CN114358405A (en) * | 2021-12-27 | 2022-04-15 | 中国电建集团贵州电力设计研究院有限公司 | Refined point-to-point temperature prediction method for power transmission line |
| CN114863053A (en) * | 2022-07-06 | 2022-08-05 | 中交第四航务工程勘察设计院有限公司 | Method and device for improving precision of digital elevation model |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102938021A (en) * | 2012-11-02 | 2013-02-20 | 云南大学 | Quantitative estimation and prediction method for icing load of power transmission line |
| CN104462660A (en) * | 2014-11-14 | 2015-03-25 | 贵州电力试验研究院 | Drawing method for winter icing thickness distribution of field electric transmission line |
| US20150188415A1 (en) * | 2013-12-30 | 2015-07-02 | King Abdulaziz City For Science And Technology | Photovoltaic systems with maximum power point tracking controller |
| US20150336676A1 (en) * | 2012-12-31 | 2015-11-26 | Telvent Dtn Llc | Airfoil icing controller apparatuses, methods and systems |
| CN105740558A (en) * | 2016-02-03 | 2016-07-06 | 南方电网科学研究院有限责任公司 | Power transmission line icing real-time drawing method for plateau micro-terrain |
| CN109059818A (en) * | 2018-06-27 | 2018-12-21 | 贵州电网有限责任公司 | A kind of insulator and wire icing state equivalence calculation method |
| CN110070530A (en) * | 2019-04-19 | 2019-07-30 | 山东大学 | A kind of powerline ice-covering detection method based on deep neural network |
-
2020
- 2020-04-16 CN CN202010298173.1A patent/CN111428942B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102938021A (en) * | 2012-11-02 | 2013-02-20 | 云南大学 | Quantitative estimation and prediction method for icing load of power transmission line |
| US20150336676A1 (en) * | 2012-12-31 | 2015-11-26 | Telvent Dtn Llc | Airfoil icing controller apparatuses, methods and systems |
| US20150188415A1 (en) * | 2013-12-30 | 2015-07-02 | King Abdulaziz City For Science And Technology | Photovoltaic systems with maximum power point tracking controller |
| CN104462660A (en) * | 2014-11-14 | 2015-03-25 | 贵州电力试验研究院 | Drawing method for winter icing thickness distribution of field electric transmission line |
| CN105740558A (en) * | 2016-02-03 | 2016-07-06 | 南方电网科学研究院有限责任公司 | Power transmission line icing real-time drawing method for plateau micro-terrain |
| CN109059818A (en) * | 2018-06-27 | 2018-12-21 | 贵州电网有限责任公司 | A kind of insulator and wire icing state equivalence calculation method |
| CN110070530A (en) * | 2019-04-19 | 2019-07-30 | 山东大学 | A kind of powerline ice-covering detection method based on deep neural network |
Non-Patent Citations (3)
| Title |
|---|
| XINHUI DU ET AL.: "The Study on The Prediction Method of Ice Thickness of Transmission Line Based on The Combination of GA and BP Neural Network", 《2010 INTERNATIONAL CONFERENCE ON E-PRODUCT E-SERVICE AND E-ENTERTAINMENT》 * |
| 李鹏 等: "输电线覆冰预测与融冰决策方法研究综述", 《第三十一届中国控制会议论文集D卷》 * |
| 郭晓薇 等: "广西覆冰预报与评估系统设计及应用", 《计算机测量与控制》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112630836A (en) * | 2020-12-11 | 2021-04-09 | 国网湖南省电力有限公司 | Monitoring and stationing method and system based on power grid micro-terrain icing threat path extension analysis |
| CN113076635A (en) * | 2021-03-26 | 2021-07-06 | 云南电网有限责任公司电力科学研究院 | Lightning activity analysis method and device based on micro-terrain environment characteristics |
| CN113076635B (en) * | 2021-03-26 | 2022-09-02 | 云南电网有限责任公司电力科学研究院 | Lightning activity analysis method and device based on micro-terrain environment characteristics |
| CN113821895A (en) * | 2021-09-01 | 2021-12-21 | 南方电网科学研究院有限责任公司 | Construction method and device of power transmission line icing thickness prediction model and storage medium |
| CN113821895B (en) * | 2021-09-01 | 2023-11-03 | 南方电网科学研究院有限责任公司 | Method and device for constructing power transmission line icing thickness prediction model and storage medium |
| CN113779507A (en) * | 2021-09-15 | 2021-12-10 | 中国电建集团贵州电力设计研究院有限公司 | Method for establishing icing prediction model based on elevation data |
| CN114358405A (en) * | 2021-12-27 | 2022-04-15 | 中国电建集团贵州电力设计研究院有限公司 | Refined point-to-point temperature prediction method for power transmission line |
| CN114358405B (en) * | 2021-12-27 | 2023-01-31 | 中国电建集团贵州电力设计研究院有限公司 | Refined point-to-point temperature prediction method for power transmission line |
| CN114863053A (en) * | 2022-07-06 | 2022-08-05 | 中交第四航务工程勘察设计院有限公司 | Method and device for improving precision of digital elevation model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111428942B (en) | 2022-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111428942B (en) | Line icing thickness prediction method for extracting micro-terrain factors based on variable grid technology | |
| Premalatha et al. | Analysis of different combinations of meteorological parameters in predicting the horizontal global solar radiation with ANN approach: A case study | |
| CN108227041B (en) | Horizontal visibility forecasting method based on site measured data and mode result | |
| CN110232471B (en) | Rainfall sensor network node layout optimization method and device | |
| CN110646867A (en) | Urban drainage monitoring and early warning method and system | |
| EP2884413B1 (en) | Method for predicting wind power density | |
| CN112308292A (en) | Method for drawing fire risk grade distribution map | |
| CN105760970A (en) | Method for predicting AQI | |
| CN113011455B (en) | Air quality prediction SVM model construction method | |
| CN112285807A (en) | Meteorological information prediction method and device | |
| CN115099162B (en) | Correction method for wind field under complex terrain | |
| CN114186723A (en) | Distributed photovoltaic power grid virtual prediction system based on space-time correlation | |
| CN113283155A (en) | Near-surface air temperature estimation method, system, storage medium and equipment | |
| CN115423272B (en) | Flood risk assessment method and system integrating historical flooding strength | |
| KR101264873B1 (en) | Wind power density prediction method using stepewise regression procedure | |
| CN114021830A (en) | Multi-time-range wind speed prediction method based on CNN-LSTM | |
| CN110471131B (en) | High-spatial-resolution automatic prediction method and system for refined atmospheric horizontal visibility | |
| KR101313822B1 (en) | Wind power density prediction method using neural network technique | |
| CN106772697A (en) | Sea of clouds natural landscape forecasting procedure and system | |
| CN117526274A (en) | New energy power prediction method, electronic equipment and storage medium in extreme climate | |
| CN116822185A (en) | Daily precipitation data space simulation method and system based on HASM | |
| Nizar et al. | Forecasting of temperature by using LSTM and bidirectional LSTM approach: case study in Semarang, Indonesia | |
| CN115408485B (en) | Runoff reconstruction method and system based on small sample observation of site water collection area | |
| CN116307282A (en) | Wind power prediction method and system based on mechanism model and data driving | |
| CN115496148A (en) | Method and device for evaluating large-scale hydrological situation change of river |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |