CN117933097A - Intelligent measuring method for magnetic field strength of overhead transmission line - Google Patents
Intelligent measuring method for magnetic field strength of overhead transmission line Download PDFInfo
- Publication number
- CN117933097A CN117933097A CN202410322975.XA CN202410322975A CN117933097A CN 117933097 A CN117933097 A CN 117933097A CN 202410322975 A CN202410322975 A CN 202410322975A CN 117933097 A CN117933097 A CN 117933097A
- Authority
- CN
- China
- Prior art keywords
- magnetic field
- field intensity
- axis
- measurement
- value
- 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
- 238000000034 method Methods 0.000 title claims abstract description 66
- 230000005540 biological transmission Effects 0.000 title claims abstract description 46
- 238000005259 measurement Methods 0.000 claims abstract description 76
- 238000013528 artificial neural network Methods 0.000 claims abstract description 34
- 238000004088 simulation Methods 0.000 claims abstract description 12
- 239000011159 matrix material Substances 0.000 claims description 45
- 238000004364 calculation method Methods 0.000 claims description 11
- 210000002569 neuron Anatomy 0.000 claims description 10
- 230000006698 induction Effects 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 6
- 230000017105 transposition Effects 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 4
- 239000004020 conductor Substances 0.000 claims description 3
- 230000005415 magnetization Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000000691 measurement method Methods 0.000 claims 8
- 238000001514 detection method Methods 0.000 description 5
- 230000005672 electromagnetic field Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R33/00—Arrangements or instruments for measuring magnetic variables
- G01R33/02—Measuring direction or magnitude of magnetic fields or magnetic flux
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an intelligent measuring method for the magnetic field strength of an overhead transmission line, which comprises the following steps: constructing a three-dimensional model of the power transmission line, calculating to obtain a magnetic field intensity soft measurement value and a magnetic field intensity hard measurement value of a point position in a plane of the three-dimensional model of the power transmission line, and correcting and compensating the magnetic field intensity hard measurement value; constructing a BP neural network, and calculating to obtain a magnetic field strength predicted value of each point location by using the BP neural network; comparing the predicted value of the magnetic field intensity, the soft measured value of the magnetic field intensity, the hard measured value of the magnetic field intensity and the simulation result of each point with the true value of the magnetic field intensity of each point, and feeding back the values in the forward and reverse directions until the error between the predicted value of the magnetic field intensity of each point and the true value is not larger than a preset value; the invention can replace manual work to measure the magnetic field intensity of the overhead transmission line, and effectively solves the problems of time consumption, labor consumption, danger and high cost of manual measurement in overhead operation.
Description
Technical Field
The invention relates to the technical field of ultra-high voltage transmission and transformation line detection, in particular to an intelligent measuring method for the magnetic field strength of an overhead transmission line.
Background
Electromagnetic fields are an invisible abstract substance, and the concept in the mind of the general public is relatively deficient, which results in some degree of overspray or inattention of people to the electromagnetic fields. With the large-scale construction of ac overhead transmission lines, the transmission lines are routed through densely populated areas. In addition, the voltage level of the transmission line is high, the transmission capacity is large, and particularly, the electromagnetic field environment problem caused in the surrounding space of the ultra-high voltage transmission line is more and more concerned. Induced charges, transient electric shock and other phenomena caused by high electric fields of the power transmission line are easy to cause worry of nearby residents. Therefore, the magnetic field intensity of the overhead transmission line needs to be measured, and whether the transmission line fails or not is monitored by measuring the magnetic field intensity. At present, the magnetic field strength of the overhead transmission line is manually measured, and the problems of time consumption, labor consumption, danger, high cost and the like of manual measurement in overhead operation exist.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an intelligent measuring method for the magnetic field strength of an overhead transmission line, which aims to quickly and accurately measure the magnetic field strength in the transmission line.
In order to achieve the above purpose, the present invention provides the following technical solutions: an intelligent measuring method for the magnetic field strength of an overhead transmission line comprises the following steps:
Step S1: leading a tower model, a wire and the bearing current of the wire in the unmanned aerial vehicle model and the overhead transmission line and input voltages at two ends of the wire into finite element simulation software to construct a three-dimensional model of the transmission line, and carrying out simulation calculation on a plurality of evenly distributed points in any plane of the three-dimensional model of the transmission line, which passes through the central position of the tower model, by using the finite element simulation software to obtain geometric space coordinates of each point and magnetic field intensity soft measurement values corresponding to each point;
Step S2: constructing a point cloud model of a three-dimensional model of the power transmission line, planning each point, measuring each point one by one according to a planning route by using an unmanned aerial vehicle carrying a triaxial magnetometer to obtain a magnetic field intensity hard measured value corresponding to each point, and correcting and compensating the magnetic field intensity hard measured value;
Step S3: constructing a BP neural network, wherein the BP neural network consists of an input layer, an hidden layer and an output layer, geometrical space coordinates, a magnetic field intensity soft measurement value and a magnetic field intensity hard measurement value of each point position are used as inputs to be imported into the input layer of the BP neural network, meanwhile, hidden layer conditions of the BP neural network are input, and the BP neural network is used for calculating to obtain a magnetic field intensity predicted value of each point position; wherein the hidden layer condition comprises triaxial magnetometer measurement noise and environmental impact factors;
Step S4: comparing the predicted value of the magnetic field intensity, the soft measured value of the magnetic field intensity, the hard measured value of the magnetic field intensity and the simulation result of each point position with the true value of the magnetic field intensity of each point position, feeding back the values in the forward direction and the reverse direction, calculating the error and the error gradient of the hidden layer according to the variable control of a plurality of input layers and the hidden layer of the BP neural network and carrying out reverse propagation for a plurality of times, and reducing the error of the predicted value of the magnetic field intensity; calculating the output of neurons of an implicit layer and an output layer by determining the node number, the learning rate, the training times and the convergence error of each layer of the BP neural network; and calculating hidden layer errors and error gradients by correcting the connection weights and thresholds of hidden layer neurons and output layer neurons in the BP neural network until the errors of the magnetic field strength predicted values and the true values of all the points are not larger than a preset value.
Further, in step S1, a plane passing through the central position of the tower model is perpendicular to the horizontal direction of the wire, and 200 evenly distributed points in the plane passing through the central position of the tower model are preferentially selected for simulation calculation, so as to obtain a magnetic field intensity soft measurement value of each selected point.
Further, the specific process of correcting and compensating the hard magnetic field strength measurement value in step S2 is as follows:
Constructing a three-axis magnetometer carrying flying and patrolling measuring model of the unmanned aerial vehicle, and obtaining a three-axis magnetometer carrying flying and patrolling measuring calibration model of the unmanned aerial vehicle according to the three-axis magnetometer carrying flying and patrolling measuring model of the unmanned aerial vehicle; in the area that the total magnetic field intensity of the selected point location is a fixed value, the actual measurement quantity of the magnetic field intensity of the carried triaxial magnetometer on the x axis, the y axis and the z axis of the selected point location is changed, but the total quantity is a fixed value: when the unmanned aerial vehicle changes the gesture in the area with the total magnetic field intensity of the selected point position being a fixed value, the track of an ideal measurement vector H l carried by the unmanned aerial vehicle is kept on a certain ellipsoidal curved surface r 1, and the track is influenced by measurement errors, and the unmanned aerial vehicle carries an actual measurement vector of the triaxial magnetometer The track of the three-axis magnetometer is kept on a certain ellipsoidal surface r 2, and the actual measurement vector of each parameter of the ellipsoidal surface r 2 to the unmanned plane carrying the three-axis magnetometer is calculatedCorrecting; acquiring a measured value of the unmanned aerial vehicle carrying the triaxial magnetometer when the posture of the unmanned aerial vehicle is changed in a region with the total amount of the point-taking magnetic fields as a fixed valueSolving the ellipsoidal curved surface parameters by adopting a minimized arithmetic distance square sum to obtain the ellipsoidal curved surface parametersIs the minimum of (2); the Lagrangian method is adopted to carry out the parameter on the ellipsoidal curved surfaceSolving the minimum value of (2); according to the obtained minimum value of the ellipsoidal curved surface parameter, obtaining a matrix of the minimum value and zero offset; and decomposing the induction matrix A, finding a matrix meeting the conditions, substituting the finally obtained ellipsoidal curved surface parameters into a calibration model of the unmanned aerial vehicle carrying the triaxial magnetometer for flight patrol measurement, and realizing the total amount correction of the unmanned aerial vehicle.
Further, the unmanned aerial vehicle carries the triaxial magnetometer to fly and patrol and measure the model and express as:
（1）；
In the method, in the process of the invention, The magnetic field intensity of the triaxial magnetometer carried by the unmanned aerial vehicle on the selected point location is measured, wherein,The magnetic field intensity of the triaxial magnetometer carried by the unmanned aerial vehicle on the x axis of the selected point location is measured,The magnetic field intensity of the triaxial magnetometer carried by the unmanned aerial vehicle on the y axis of the selected point location is measured,Carrying real measurement of the magnetic field intensity of the triaxial magnetometer on the z axis of the selected point location for the unmanned aerial vehicle; Is a scale factor error matrix; Is a triaxial non-orthogonal matrix; Is a true measure of the magnetic field strength at the selected point, where, For the field strength of the x-axis of the selected spot,For the true magnitude of the magnetic field strength of the y-axis of the selected spot,The magnetic field intensity of the z-axis of the selected point location is the true quantity; is the zero bias error of the magnetic field intensity of the triaxial magnetometer at the selected point location, wherein, The magnetic field intensity zero bias error of the triaxial magnetometer on the x axis of the selected point location,The magnetic field intensity zero bias error of the triaxial magnetometer on the y axis of the selected point location,Zero bias error of magnetic field intensity of the triaxial magnetometer on the z axis of the selected point location; Measuring noise of the triaxial magnetometer; Representing a transpose of the matrix; Representing magnetization;
The unmanned aerial vehicle carries triaxial magnetometer to fly and patrols and measures calibration model and represents as:
（2）。
Further, the ellipsoidal curved surface r 2 is expressed as:
（3）；
In the method, in the process of the invention, The magnetic field intensity of the selected point location is the magnitude; a transposed matrix of the true value H of the magnetic field intensity of the selected point location; real-time measurement of magnetic field strength of three-axis magnetometer carried by unmanned aerial vehicle on x-axis, y-axis and z-axis of selected point position Is a transposed matrix of (a); Is an induction matrix; the zero offset error of the triaxial magnetometer is transposed; representing an estimate of the triaxial magnetometer measurement noise; wherein:
（4）；
In the method, in the process of the invention, The transposition of the measurement noise of the triaxial magnetometer;
Expanding equation (3) into a quadric equation in three-dimensional space, expressed as:
（5）；
In the method, in the process of the invention, An ellipsoidal quadric surface equation in a three-dimensional space; is an ellipsoidal curved surface parameter; wherein, All are algebraic.
Further, parameters of ellipsoidal curved surfacesThe minimum value of (2) is expressed as:
（6）；
（7）；
In the method, in the process of the invention, Scalar values representing the ellipsoid surface parameter differences; a diagonal matrix representing ellipsoidal surface parameters; representing the transposition of an ellipsoidal curved surface parameter matrix; A transpose of the diagonal matrix representing ellipsoidal surface parameters; representing the partial derivative of the nth hard measurement on the x-axis; representing the product of the partial derivatives of the nth hard measurement on the x-axis; representing the product of the partial derivatives of the nth hard measurement on the y-axis;
From parameters of ellipsoidal curved surfaces The quadric surface is an ellipsoidal surface, and the induction matrix A is positive or negative, so that:
（8）；
Equation (7) is constrained by an equation and represented by a matrix:
（9）；
Wherein:
（10）。
further, the Lagrangian method is adopted to carry out the curve surface parameter of the ellipsoid Solving for the minimum of (2):
（11）；
In the method, in the process of the invention, Is Lagrangian method; Representing a lagrangian multiplier;
The bias guide of formula (11) is 0:
（12）；
And according to the obtained minimum value of the ellipsoidal curved surface parameter, obtaining a matrix of the minimum value and zero offset, wherein:
（13）；
（14）。
Further, decomposing the sensing matrix A to find out the meeting condition Substituting the finally obtained ellipsoidal curved surface parameters (M, b) into the formula (2) to realize the total correction of the unmanned aerial vehicle.
Further, the input layer contains the following six values: x1, x2, x3, x4, x5, x6; wherein x1, x2 and x3 respectively correspond to the longitude, latitude and altitude of the obtained 200 points, x4 is a magnetic field intensity soft measurement value, x5 is a magnetic field intensity hard measurement value, and x6 is the current-carrying capacity of the overhead line conductor.
Compared with the prior art, the invention has the following beneficial effects: the invention compares the predicted value of the magnetic field intensity of the point location, the soft measured value of the magnetic field intensity and the corrected hard measured value of the magnetic field intensity with the true value and feeds back the predicted value, the soft measured value of the magnetic field intensity and the corrected hard measured value of the magnetic field intensity to the true value, and the BP neural network continuously learns to reduce the error between the predicted value and the true value; the invention can replace manual work to measure the magnetic field intensity of the overhead transmission line, and effectively solves the problems of time consumption, labor consumption, danger and high cost of manual measurement in overhead operation; after a large amount of data is accumulated, the accuracy of magnetic field intensity measurement can be further improved through a BP neural network method.
Drawings
FIG. 1 is a step diagram of the present invention.
Fig. 2 is a schematic diagram of the algorithm of the BP neural network of the present invention.
Detailed Description
As shown in fig. 1, the present invention provides the following technical solutions: an intelligent measuring method for the magnetic field strength of an overhead transmission line comprises the following steps:
Step S1: leading a tower model, a wire and the bearing current of the wire in the unmanned aerial vehicle model and the overhead transmission line and input voltages at two ends of the wire into finite element simulation software to construct a three-dimensional model of the transmission line, and carrying out simulation calculation on a plurality of evenly distributed points in any plane of the three-dimensional model of the transmission line, which passes through the central position of the tower model, by using the finite element simulation software to obtain geometric space coordinates of each point and magnetic field intensity soft measurement values corresponding to each point;
the plane passing through the central position of the tower model is vertical to the horizontal direction of the lead, and 200 evenly distributed points in the plane passing through the central position of the tower model are preferentially selected for simulation calculation, so that a magnetic field intensity software simulation measured value (a detected magnetic field intensity soft measured value) of each selected point is obtained.
Step S2: constructing a point cloud model of a three-dimensional model of the power transmission line, planning each point, measuring each point one by one according to a planning route by using an unmanned aerial vehicle carrying a triaxial magnetometer to obtain a magnetic field intensity hard measured value corresponding to each point, and correcting and compensating the magnetic field intensity hard measured value;
Because the unmanned plane has the problem of insufficient posture in the process of measuring the positions one by one, the problem of singularity of measured data is easy to cause, and the problem needs to be solved from the angle of an algorithm, the correction and compensation calculation are carried out on the hard measured value, and the specific steps of calculation are as follows:
Constructing a flight patrol measuring model of the unmanned aerial vehicle carrying the triaxial magnetometer:
（1）；
In the method, in the process of the invention, The magnetic field intensity of the triaxial magnetometer carried by the unmanned aerial vehicle on the selected point location is measured, wherein,The magnetic field intensity of the triaxial magnetometer carried by the unmanned aerial vehicle on the x axis of the selected point location is measured,The magnetic field intensity of the triaxial magnetometer carried by the unmanned aerial vehicle on the y axis of the selected point location is measured,Carrying real measurement of the magnetic field intensity of the triaxial magnetometer on the z axis of the selected point location for the unmanned aerial vehicle; Is a scale factor error matrix; Is a triaxial non-orthogonal matrix; Is a true measure of the magnetic field strength at the selected point, where, For the field strength of the x-axis of the selected spot,For the true magnitude of the magnetic field strength of the y-axis of the selected spot,The magnetic field intensity of the z-axis of the selected point location is the true quantity; is the zero bias error of the magnetic field intensity of the triaxial magnetometer at the selected point location, wherein, The magnetic field intensity zero bias error of the triaxial magnetometer on the x axis of the selected point location,The magnetic field intensity zero bias error of the triaxial magnetometer on the y axis of the selected point location,Zero bias error of magnetic field intensity of the triaxial magnetometer on the z axis of the selected point location; Measuring noise of the triaxial magnetometer; Representing a transpose of the matrix; Representing magnetization;
Obtaining a flight patrol measurement calibration model of the unmanned aerial vehicle carrying the triaxial magnetometer by the aid of the unmanned aerial vehicle (1):
（2）；
In the area that the total magnetic field intensity of the selected point position is a fixed value, the actual measurement quantity of the magnetic field intensity of the carried triaxial magnetometer on the x axis, the y axis and the z axis of the selected point position is changed, but the total quantity is a fixed value: when the unmanned aerial vehicle changes the gesture in the area with the total magnetic field intensity of the selected point position being a fixed value, the track of an ideal measurement vector H l carried by the unmanned aerial vehicle is kept on a certain ellipsoidal curved surface r 1, and the track is influenced by measurement errors, and the unmanned aerial vehicle carries an actual measurement vector of the triaxial magnetometer The track of the three-axis magnetometer is kept on a certain ellipsoidal surface r 2, and the actual measurement vector of each parameter of the ellipsoidal surface r 2 to the unmanned plane carrying the three-axis magnetometer is calculatedAnd correcting, wherein the ellipsoidal curved surface r 2 is expressed as:
（3）；
In the method, in the process of the invention, The magnetic field intensity of the selected point location is the magnitude; a transposed matrix of the true value H of the magnetic field intensity of the selected point location; real-time measurement of magnetic field strength of three-axis magnetometer carried by unmanned aerial vehicle on x-axis, y-axis and z-axis of selected point position Is a transposed matrix of (a); Is an induction matrix; the zero offset error of the triaxial magnetometer is transposed; representing an estimate of the triaxial magnetometer measurement noise; wherein:
（4）；
In the method, in the process of the invention, The transposition of the measurement noise of the triaxial magnetometer;
since the ellipsoidal surface is a quadric surface, equation (3) can be developed into a quadric equation in three-dimensional space, expressed as:
）（5）；
In the method, in the process of the invention, A quadric surface equation of a three-dimensional space ellipsoid; is an ellipsoidal curved surface parameter; wherein, All are algebraic.
Acquiring a measured value of the unmanned aerial vehicle carrying the triaxial magnetometer when the posture of the unmanned aerial vehicle is changed in a region with the total amount of the point-taking magnetic fields as a fixed valueThe problem of solving the ellipsoidal curved surface parameters can be converted into the problem of minimizing the sum of squares of arithmetic distances, namely solving and obtaining the ellipsoidal curved surface parametersIs the minimum of (2);
（6）；
（7）；
In the method, in the process of the invention, Scalar values representing the ellipsoid surface parameter differences; a diagonal matrix representing ellipsoidal surface parameters; representing the transposition of an ellipsoidal curved surface parameter matrix; A transpose of the diagonal matrix representing ellipsoidal surface parameters; representing the partial derivative of the nth hard measurement on the x-axis; representing the product of the partial derivatives of the nth hard measurement on the x-axis; representing the product of the partial derivatives of the nth hard measurement on the y-axis;
to ensure that the parameters of the ellipsoidal curved surface The quadric surface is an ellipsoidal surface, and the induction matrix A is required to be positive or negative, so that:
（8）；
the minimum problem under the inequality constraint is difficult to solve, so equation (7) is converted into the equality constraint and expressed by a matrix:
（9）；
Wherein:
（10）；
Using Lagrangian method to calculate parameters of ellipsoidal curved surface Solving for the minimum of (2):
（11）；
In the method, in the process of the invention, Is Lagrangian method; Representing a lagrangian multiplier;
The bias guide of formula (11) is 0:
（12）；
After the minimum value of the ellipsoidal curved surface parameter is obtained, the matrix and the zero offset of the minimum value can be obtained, wherein:
（13）；
（14）；
decomposing the matrix A to find a meeting condition Substituting the finally obtained ellipsoidal curved surface parameters (M, b) into the formula (2) to realize the total correction of the unmanned aerial vehicle.
Step S3: constructing a BP neural network, wherein the BP neural network consists of an input layer, an hidden layer and an output layer, geometrical space coordinates, a magnetic field intensity soft measurement value and a magnetic field intensity hard measurement value of each point position are used as inputs to be imported into the input layer of the BP neural network, meanwhile, hidden layer conditions of the BP neural network are input, and the BP neural network is used for calculating to obtain a magnetic field intensity predicted value of each point position; wherein the hidden layer condition comprises triaxial magnetometer measurement noise and environmental impact factors.
Step S4: comparing the predicted value of the magnetic field intensity, the soft measured value of the magnetic field intensity, the hard measured value of the magnetic field intensity and the simulation result of each point position with the true value of the magnetic field intensity of each point position, feeding back the values in the forward direction and the reverse direction, calculating the error and the error gradient of the hidden layer according to the variable control of a plurality of input layers and the hidden layer of the BP neural network and carrying out reverse propagation for a plurality of times, and reducing the error of the predicted value of the magnetic field intensity; calculating the output of neurons of an implicit layer and an output layer by determining the node number, the learning rate, the training times and the convergence error of each layer of the BP neural network; and calculating hidden layer errors and error gradients by correcting the connection weights and thresholds of hidden layer neurons and output layer neurons in the BP neural network until the errors of the magnetic field intensity predicted values and the true values of all the points are not more than 8%.
In the embodiment, the BP neural network is utilized for prediction, and has higher capability of predicting nonlinear related problems due to the characteristics of simplicity in operation, high self-learning and self-adaption. The BP neural network is composed of an input layer, an implicit layer and an output layer, wherein the input layer comprises the following six values: x1, x2, x3, x4, x5, x6; wherein x1, x2 and x3 respectively correspond to the longitude, latitude and altitude of the obtained 200 points, x4 is a simulation result of finite element simulation software, namely a magnetic field intensity soft measurement value, x5 is a measurement value of an intelligent detection device carried by the unmanned aerial vehicle, namely a magnetic field intensity hard measurement value, and x6 is the current-carrying capacity of an overhead line conductor; the implicit layer error and the error gradient are calculated, the weight and the threshold value are modified to be relearned, and the output value result can be more accurate through iterative operation; the threshold value mainly comprises errors of geometric space positioning of the unmanned aerial vehicle, errors of a model during simulation calculation and errors of an intelligent detection device carried by the unmanned aerial vehicle due to environmental factors such as temperature, humidity and other charged body influences, and the like, and a prediction result is close to a true value as much as possible through multi-point calculation and neuron learning until the errors of the prediction result and the true value are smaller than 7%.
As shown in fig. 2, the calculation process of the BP neural network is as follows: six inputs [ x1, x2, x3, x4, x5, x6], 2 weights [ w11, w12], 2 offsets [ w21, w22], so that six objects are visible in the input layer, two hidden layers are visible in the input layer, wherein the meanings of w11 and w12 are respectively a measurement error calibration value 1 and a measurement error calibration value 2, and the meanings of w21 and w22 are respectively a magnetic interference compensation 1 and a magnetic interference compensation 2; h11, H12, H21, H22 represent the 1 st factor in hidden layer 1, the 2 nd factor in hidden layer 1, the 1 st factor in hidden layer 2, the 2 nd factor in hidden layer 2, respectively; y represents the output result. In BP neural networks, error back propagation is based on Delta learning rules.
The main purpose of the back propagation of errors and the BP neural network is to correct the weight so that the error value reaches the minimum; delta learning rules are a general learning rule that exploits gradient descent, thereby improving accuracy.
Selecting a plane with the height of 0 as an example, measuring the magnetic field intensity of 200 evenly distributed points on the plane by adopting finite element simulation software, and listing the magnetic field intensity of 30 points, wherein the result is shown in table 1:
Table 1 magnetic field strength soft measurements
The magnetic field intensity of the selected 200 evenly distributed points is measured one by adopting an intelligent detection device carried by the unmanned aerial vehicle; the magnetic field strength values of 30 points are listed, and the results are shown in table 2:
Table 2 hard measurement of magnetic field strength
In tables 1 and 2, X is the horizontal distance from the origin (0, 0) on the central axis of the tower in the overhead transmission line, and Z is the height from the origin (0, 0) on the central axis of the tower in the overhead transmission line;
The error between the true values for each point by comparing the soft and hard measurements of the magnetic field is no more than 8%. Therefore, the intelligent detection method for the magnetic field strength of the overhead transmission line is effective.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. The intelligent measuring method for the magnetic field strength of the overhead transmission line is characterized by comprising the following steps of:
Step S1: leading a tower model, a wire and the bearing current of the wire in the unmanned aerial vehicle model and the overhead transmission line and input voltages at two ends of the wire into finite element simulation software to construct a three-dimensional model of the transmission line, and carrying out simulation calculation on a plurality of evenly distributed points in any plane of the three-dimensional model of the transmission line, which passes through the central position of the tower model, by using the finite element simulation software to obtain geometric space coordinates of each point and magnetic field intensity soft measurement values corresponding to each point;
Step S2: constructing a point cloud model of a three-dimensional model of the power transmission line, planning each point, measuring each point one by one according to a planning route by using an unmanned aerial vehicle carrying a triaxial magnetometer to obtain a magnetic field intensity hard measured value corresponding to each point, and correcting and compensating the magnetic field intensity hard measured value;
Step S3: constructing a BP neural network, wherein the BP neural network consists of an input layer, an hidden layer and an output layer, geometrical space coordinates, a magnetic field intensity soft measurement value and a magnetic field intensity hard measurement value of each point position are used as inputs to be imported into the input layer of the BP neural network, meanwhile, hidden layer conditions of the BP neural network are input, and the BP neural network is used for calculating to obtain a magnetic field intensity predicted value of each point position; wherein the hidden layer condition comprises triaxial magnetometer measurement noise and environmental impact factors;
Step S4: comparing the predicted value of the magnetic field intensity, the soft measured value of the magnetic field intensity, the hard measured value of the magnetic field intensity and the simulation result of each point position with the true value of the magnetic field intensity of each point position, feeding back the values in the forward direction and the reverse direction, calculating the error and the error gradient of the hidden layer according to the variable control of a plurality of input layers and the hidden layer of the BP neural network and carrying out reverse propagation for a plurality of times, and reducing the error of the predicted value of the magnetic field intensity; calculating the output of neurons of an implicit layer and an output layer by determining the node number, the learning rate, the training times and the convergence error of each layer of the BP neural network; and calculating hidden layer errors and error gradients by correcting the connection weights and thresholds of hidden layer neurons and output layer neurons in the BP neural network until the errors of the magnetic field strength predicted values and the true values of all the points are not larger than a preset value.
2. The intelligent measurement method for the magnetic field strength of the overhead transmission line according to claim 1, wherein the method comprises the following steps: in step S1, a plane passing through the central position of the tower model is vertical to the horizontal direction of the lead, and 200 evenly distributed points in the plane passing through the central position of the tower model are preferentially selected for simulation calculation, so that a magnetic field intensity soft measurement value of each selected point is obtained.
3. The intelligent measurement method for the magnetic field strength of the overhead transmission line according to claim 2, wherein the method comprises the following steps: the specific process of correcting and compensating the magnetic field intensity hard measured value in the step S2 is as follows:
Constructing a three-axis magnetometer carrying flying and patrolling measuring model of the unmanned aerial vehicle, and obtaining a three-axis magnetometer carrying flying and patrolling measuring calibration model of the unmanned aerial vehicle according to the three-axis magnetometer carrying flying and patrolling measuring model of the unmanned aerial vehicle; in the area that the total magnetic field intensity of the selected point location is a fixed value, the actual measurement quantity of the magnetic field intensity of the carried triaxial magnetometer on the x axis, the y axis and the z axis of the selected point location is changed, but the total quantity is a fixed value: when the unmanned aerial vehicle changes the gesture in the area with the total magnetic field intensity of the selected point position being a fixed value, the track of an ideal measurement vector H l carried by the unmanned aerial vehicle is kept on a certain ellipsoidal curved surface r 1, and the track is influenced by measurement errors, and the unmanned aerial vehicle carries an actual measurement vector of the triaxial magnetometer The track of the three-axis magnetometer is kept on a certain ellipsoidal surface r 2, and each parameter of the ellipsoidal surface r 2 is calculated to carry the actual measurement vector/>, of the three-axis magnetometer, of the unmanned planeCorrecting; obtaining measured value/>, when the unmanned plane carries the triaxial magnetometer and changes the gesture in the area with the total amount of the point location magnetic fields as a fixed valueSolving the ellipsoidal curved surface parameters by adopting a minimized arithmetic distance square sum to obtain ellipsoidal curved surface parameters/>Is the minimum of (2); lagrangian method is adopted to carry out the method of parameter/>, of ellipsoidal curved surfaceSolving the minimum value of (2); according to the obtained minimum value of the ellipsoidal curved surface parameter, obtaining a matrix of the minimum value and zero offset; and decomposing the induction matrix A, finding a matrix meeting the conditions, substituting the finally obtained ellipsoidal curved surface parameters into a calibration model of the unmanned aerial vehicle carrying the triaxial magnetometer for flight patrol measurement, and realizing the total amount correction of the unmanned aerial vehicle.
4. The intelligent measurement method for the magnetic field strength of the overhead transmission line according to claim 3, wherein the method comprises the following steps: the unmanned aerial vehicle carrying the triaxial magnetometer flies to patrol and measures the model and expresses as:
（1）；
In the method, in the process of the invention, Carrying real measurement of magnetic field intensity of triaxial magnetometer on selected point location for unmanned aerial vehicle, wherein/>Real measurement of magnetic field strength on x-axis of selected point location for carrying triaxial magnetometer for unmanned aerial vehicle,/>Real measurement of magnetic field strength on y-axis of selected point location for carrying triaxial magnetometer for unmanned aerial vehicle,/>Carrying real measurement of the magnetic field intensity of the triaxial magnetometer on the z axis of the selected point location for the unmanned aerial vehicle; /(I)Is a scale factor error matrix; /(I)Is a triaxial non-orthogonal matrix; /(I)Is the true magnitude of the magnetic field strength at the selected point, where/>For the true magnitude of the magnetic field strength of the x-axis of the selected spot,/>For the true magnitude of the magnetic field strength of the y-axis of the selected spot,/>The magnetic field intensity of the z-axis of the selected point location is the true quantity; /(I)Zero bias error of magnetic field intensity of triaxial magnetometer at selected point location, wherein/>Zero bias error of magnetic field intensity of triaxial magnetometer on x-axis of selected point location,/>Zero bias error of magnetic field intensity of triaxial magnetometer on y axis of selected point location,/>Zero bias error of magnetic field intensity of the triaxial magnetometer on the z axis of the selected point location; /(I)Measuring noise of the triaxial magnetometer; /(I)Representing a transpose of the matrix; /(I)Representing magnetization;
The unmanned aerial vehicle carries triaxial magnetometer to fly and patrols and measures calibration model and represents as:
（2）。
5. the intelligent measurement method for the magnetic field strength of the overhead transmission line according to claim 4, wherein the method comprises the following steps: the ellipsoidal curved surface r 2 is expressed as:
（3）；
In the method, in the process of the invention, The magnetic field intensity of the selected point location is the magnitude; /(I)A transposed matrix of the true value H of the magnetic field intensity of the selected point location; /(I)Real measurement/>, of magnetic field intensity of three-axis magnetometer carried by unmanned aerial vehicle on selected point positions x-axis, y-axis and z-axisIs a transposed matrix of (a); /(I)Is an induction matrix; /(I)The zero offset error of the triaxial magnetometer is transposed; /(I)Representing an estimate of the triaxial magnetometer measurement noise; wherein:
（4）；
In the method, in the process of the invention, The transposition of the measurement noise of the triaxial magnetometer;
Expanding equation (3) into a quadric equation in three-dimensional space, expressed as:
（5）；
In the method, in the process of the invention, An ellipsoidal quadric surface equation in a three-dimensional space; is an ellipsoidal curved surface parameter; wherein, All are algebraic.
6. The intelligent measurement method for the magnetic field strength of the overhead transmission line according to claim 5, wherein the method comprises the following steps: ellipsoid surface parametersThe minimum value of (2) is expressed as:
（6）；
（7）；
In the method, in the process of the invention, Scalar values representing the ellipsoid surface parameter differences; /(I)A diagonal matrix representing ellipsoidal surface parameters; /(I)Representing the transposition of an ellipsoidal curved surface parameter matrix; /(I)A transpose of the diagonal matrix representing ellipsoidal surface parameters; /(I)Representing the partial derivative of the nth hard measurement on the x-axis; /(I)Representing the product of the partial derivatives of the nth hard measurement on the x-axis; /(I)Representing the product of the partial derivatives of the nth hard measurement on the y-axis;
From parameters of ellipsoidal curved surfaces The quadric surface is an ellipsoidal surface, and the induction matrix A is positive or negative, so that:
（8）；
Equation (7) is constrained by an equation and represented by a matrix:
（9）；
Wherein:
（10）。
7. The intelligent measurement method for the magnetic field strength of the overhead transmission line according to claim 6, wherein the method comprises the following steps: the Lagrangian method is adopted to carry out the parameter on the ellipsoidal curved surface Solving for the minimum of (2):
（11）；
In the method, in the process of the invention, Is Lagrangian method; /(I)Representing a lagrangian multiplier;
The bias guide of formula (11) is 0:
（12）；
And according to the obtained minimum value of the ellipsoidal curved surface parameter, obtaining a matrix of the minimum value and zero offset, wherein:
（13）；
（14）。
8. The intelligent measurement method for the magnetic field strength of the overhead transmission line according to claim 7, wherein the method comprises the following steps: decomposing the induction matrix A to find out the meeting condition Substituting the finally obtained ellipsoidal curved surface parameters (M, b) into the formula (2) to realize the total correction of the unmanned aerial vehicle.
9. The intelligent measurement method for the magnetic field strength of the overhead transmission line according to claim 8, wherein the method comprises the following steps: the input layer contains the following six values: x1, x2, x3, x4, x5, x6; wherein x1, x2 and x3 respectively correspond to the longitude, latitude and altitude of the obtained 200 points, x4 is a magnetic field intensity soft measurement value, x5 is a magnetic field intensity hard measurement value, and x6 is the current-carrying capacity of the overhead line conductor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410322975.XA CN117933097A (en) | 2024-03-21 | 2024-03-21 | Intelligent measuring method for magnetic field strength of overhead transmission line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410322975.XA CN117933097A (en) | 2024-03-21 | 2024-03-21 | Intelligent measuring method for magnetic field strength of overhead transmission line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117933097A true CN117933097A (en) | 2024-04-26 |
Family
ID=90752176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410322975.XA Pending CN117933097A (en) | 2024-03-21 | 2024-03-21 | Intelligent measuring method for magnetic field strength of overhead transmission line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117933097A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105676302A (en) * | 2015-11-12 | 2016-06-15 | 东南大学 | Magnetometer random noise error compensation method based on improved least square method |
| CN205750554U (en) * | 2016-06-07 | 2016-11-30 | 三峡大学 | A kind of electromagnetic field positioner of overhead transmission line line walking unmanned plane |
| CN107894241A (en) * | 2017-12-07 | 2018-04-10 | 智灵飞（北京）科技有限公司 | A kind of unmanned plane magnetic sensor calibration method, unmanned plane based on ellipsoid fitting |
| CN109541704A (en) * | 2018-12-05 | 2019-03-29 | 加泰科(深圳)科技有限公司 | Three axis fluxgate magnetic airborne survey systems of one kind and correction compensation method |
| CN110488096A (en) * | 2019-06-17 | 2019-11-22 | 中国南方电网有限责任公司超高压输电公司天生桥局 | A kind of electromagnetic field intensity measurement UAV system and measurement method |
| CN115507849A (en) * | 2022-11-22 | 2022-12-23 | 北京理工大学前沿技术研究院 | Magnetic sensor correction method and system based on INS/GNSS combined navigation assistance |
| CN115856744A (en) * | 2022-11-09 | 2023-03-28 | 电子科技大学 | Correction method for linear misalignment error of triaxial fluxgate sensor array |
| CN116256568A (en) * | 2023-03-31 | 2023-06-13 | 中国南方电网有限责任公司超高压输电公司南宁局 | Intelligent measurement method and device for electric field strength of overhead transmission line |
-
2024
- 2024-03-21 CN CN202410322975.XA patent/CN117933097A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105676302A (en) * | 2015-11-12 | 2016-06-15 | 东南大学 | Magnetometer random noise error compensation method based on improved least square method |
| CN205750554U (en) * | 2016-06-07 | 2016-11-30 | 三峡大学 | A kind of electromagnetic field positioner of overhead transmission line line walking unmanned plane |
| CN107894241A (en) * | 2017-12-07 | 2018-04-10 | 智灵飞（北京）科技有限公司 | A kind of unmanned plane magnetic sensor calibration method, unmanned plane based on ellipsoid fitting |
| CN109541704A (en) * | 2018-12-05 | 2019-03-29 | 加泰科(深圳)科技有限公司 | Three axis fluxgate magnetic airborne survey systems of one kind and correction compensation method |
| CN110488096A (en) * | 2019-06-17 | 2019-11-22 | 中国南方电网有限责任公司超高压输电公司天生桥局 | A kind of electromagnetic field intensity measurement UAV system and measurement method |
| CN115856744A (en) * | 2022-11-09 | 2023-03-28 | 电子科技大学 | Correction method for linear misalignment error of triaxial fluxgate sensor array |
| CN115507849A (en) * | 2022-11-22 | 2022-12-23 | 北京理工大学前沿技术研究院 | Magnetic sensor correction method and system based on INS/GNSS combined navigation assistance |
| CN116256568A (en) * | 2023-03-31 | 2023-06-13 | 中国南方电网有限责任公司超高压输电公司南宁局 | Intelligent measurement method and device for electric field strength of overhead transmission line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107515621B (en) | Line patrol unmanned aerial vehicle flight trajectory control method based on power transmission line electromagnetic sensing | |
| Lv et al. | WSN localization technology based on hybrid GA-PSO-BP algorithm for indoor three-dimensional space | |
| CN114460654B (en) | Semi-aviation transient electromagnetic data inversion method and device based on L1L2 mixed norm | |
| KR101651893B1 (en) | Method of synthesizing axial power distribution of reactor core using neural network and the In-Core Monitoring System(ICOMS) using the same | |
| CN109725360A (en) | One-point positioning method based on magnetic gradient tensor invariant | |
| Ge et al. | Aeromagnetic compensation algorithm robust to outliers of magnetic sensor based on Huber loss method | |
| CN108318854B (en) | Positioning method, positioning device, electronic equipment and readable storage medium | |
| CN111912295A (en) | Trajectory drop point prediction system | |
| CN113609749A (en) | Current calculation method based on magnetic field signal and suitable for multiple scenes | |
| CN113640712B (en) | Prediction method for vertical component of vertical induction magnetic field of ship | |
| Jiang et al. | Scalar calibration of aeromagnetic data using BPANN and LS algorithms based on fixed-wing UAV platform | |
| CN116256568A (en) | Intelligent measurement method and device for electric field strength of overhead transmission line | |
| CN117933097A (en) | Intelligent measuring method for magnetic field strength of overhead transmission line | |
| CN108061922B (en) | A kind of distribution magnetic anomaly detection system dynamic magnetic compensation method | |
| CN110398702B (en) | Real-time online magnetic calibration method based on multi-sensor fusion | |
| CN115979245B (en) | Magnetic induction network positioning method based on self-calibration estimation | |
| CN111609850B (en) | Positioning compensation method for rope suspension type robot | |
| CN116299735A (en) | Interference magnetic field compensation method of geomagnetic vector measurement system based on BP neural network | |
| CN111756026B (en) | Transformer direct-current magnetic bias suppression method based on multiple soil models | |
| Luo et al. | An indoor autonomous guided vehicle based on electromagnetic tracking and positioning ibeacon | |
| AU2011204519B2 (en) | Improved method for determining the magnetisation of the hull of a ship, and associated device | |
| Huang et al. | Magnetometer error compensation algorithm based on improved particle swarm optimization algorithm | |
| Chen | Research on improving positioning accuracy of sensor networks | |
| Xiaojing et al. | Two-dimensional Photoelectric Compensation based on BP Neural Network | |
| CN110824569B (en) | Aeromagnetic compensation method based on differential evolution optimization algorithm |
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 |