Beidou-based power distribution grounding wire equipment management method

Abstract

The invention relates to the technical field of power distribution grounding wire equipment management, and discloses a Beidou-based power distribution grounding wire equipment management method, which comprises the following steps of: acquiring power data of power distribution grounding wire equipment in real time and preprocessing the power data; performing feature extraction on the preprocessed power data; constructing a distribution ground wire equipment anomaly detection model to perform anomaly detection on the power feature vector; and if an abnormality is detected, positioning the position of the current power distribution grounding wire equipment through Beidou. Iteration and filling of the missing values are carried out by combining the data feature parameter difference before and after filling of the missing values of each segment of power data, and decision judgment is carried out on whether the power feature vectors are abnormal or not by using a plurality of decision trees. And based on the information gain weights of different index nodes in the decision tree and the weight difference between the index weights of different indexes in the power feature vector, performing adaptive correction on a decision judgment result to obtain equipment anomaly identification and Beidou positioning adaptive to different power distribution grounding wire equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution grounding wire equipment management, and in particular to a power distribution grounding wire equipment management method based on Beidou. Background Art

[0002] The distribution system is an important part of the power system. The safety and stability of its operation are directly related to the overall performance of the power system. In the distribution system, the management of grounding wire equipment is crucial to ensure the safe operation of the power system. The traditional management method of grounding wire equipment mainly relies on manual inspection and recording, which is not only time-consuming and labor-intensive, but also prone to problems such as missed detection and false detection, and it is impossible to grasp the status information of grounding wire equipment in real time. Summary of the invention

[0003] In view of this, the present invention proposes a Beidou-based distribution grounding wire equipment management method, which realizes real-time monitoring and management of distribution system grounding wire equipment by integrating artificial intelligence and Beidou positioning technology, thereby improving management efficiency and equipment operation safety.

[0004] To achieve the above object, the present invention provides a Beidou-based distribution grounding wire equipment management method, comprising the following steps:

[0005] S1: collecting power data of the power distribution grounding wire equipment in real time and preprocessing it to obtain preprocessed power data, wherein filling missing data of multiple segments is an implementation method of the preprocessing;

[0006] S2: extracting features from the preprocessed power data to obtain a power feature vector, wherein the improved time series prediction is an implementation method of the feature extraction;

[0007] S3: Constructing a distribution grounding wire equipment anomaly detection model to perform anomaly detection on the power feature vector, wherein the distribution grounding wire equipment anomaly detection model takes the extracted power feature vector as input and takes the anomaly judgment result as output, wherein the improved random forest is an implementation method of the distribution grounding wire equipment anomaly detection model;

[0008] S4: If an abnormality is detected, the current distribution grounding wire equipment position is located through Beidou, among which single-point positioning is the implementation method of Beidou positioning.

[0009] As a further improvement method of the present invention:

[0010] Optionally, the real-time collection of power data of the power distribution grounding wire device in step S1 includes:

[0011] The power data of the power distribution grounding wire equipment is collected in real time, wherein the power data of the power distribution grounding wire equipment collected is in the form of:

[0012] A=(A(1),A(2),...,A(n),...,A(N))

[0013] M=(M(1),M(2),...,M(n),...,M(N))

[0014] in:

[0015] A represents the collected power data of the distribution grounding wire equipment, A(1), A(2), ..., A(n), ..., A(N) represent the power environment data of the distribution grounding wire equipment at N data collection moments, A(n) represents the power environment data of the distribution grounding wire equipment at the nth data collection moment, N represents the total number of data collection moments, where the power environment data A(n) includes the voltage value A 1 (n), current value A 2 (n), grounding resistance value A 3 (n), ambient temperature value A 4 (n) and ambient humidity value A 5 (n); In the embodiment of the present invention, the voltage value near the grounding wire is measured to ensure that the grounding system is within the normal working range; the current passing through the grounding wire is measured to monitor the load condition of the grounding system and detect possible fault current; the resistance value of the grounding system is measured, which is a key indicator to ensure the effectiveness of the grounding system;

[0016] M represents the missing value mark sequence of the power data A. If the distribution grounding wire device does not collect the power environment data at the nth data collection time, A(n) is a missing value, and the missing value mark M(n) = 0, otherwise M(n) = 1;

[0017] The missing values ​​in the power data A are filled to form the preprocessed power data a.

[0018] Optionally, filling missing values ​​in the power data A includes:

[0019] S11: The power data A is represented in a segmented manner to obtain G subsequences of the power data A, wherein the g-th subsequence of the power data A is:

[0020]

[0021] in:

[0022] A g represents the g-th subsequence of power data A, Represents subsequence A g In Power environment data;

[0023] The subsequence A g The corresponding missing value marker sequence is Mg :

[0024]

[0025] in:

[0026] Power environment data Missing value markers;

[0027] S12: Delete the missing values ​​in the subsequence to form the target subsequence, where subsequence A g The corresponding target subsequence is C g ;

[0028] S13: Construct the missing value filling objective function of power data A:

[0029]

[0030] in:

[0031] L(θ) represents the objective function value of filling missing values ​​of power data A using parameter θ, and L(·) represents the missing value filling objective function;

[0032] Represents the subsequence A after missing value filling based on parameter θ g The index value of the i-th data index, i∈[1,4], where the 1st to 4th data indexes are the sequence mean, sequence standard deviation, sequence kurtosis and sequence skewness respectively;

[0033] s i (g) represents the target subsequence C g The index value of the i-th data index;

[0034] Where the subsequence A is g The filling formula for missing value filling is: T [A g ;M g ], T represents transpose;

[0035] S14: Initialize a set of parameters θ 0 , set the current iteration number of the parameter to t, the maximum iteration number to Max, and the initial value of t to 0;

[0036] S15: Iterate the parameters, where the iteration formula is:

[0037]

[0038] in:

[0039] grad t Denotes the parameter θt The gradient of t The calculation method is: take the parameter as the variable to calculate the partial derivative of the missing value filling objective function L(θ), and use the parameter θ t Substitute the partial derivative calculation results to get the parameter θ t The gradient of

[0040] ε represents a control parameter; in the embodiment of the present invention, ε is set to 0.01;

[0041] ||·|| 2 represents the L2 norm;

[0042] α t represents the adaptive iteration weight;

[0043] exp(·) represents an exponential function with a natural constant as the base;

[0044] S16: Let t = t + 1, return to step S15, until the maximum number of iterations is reached, and use the parameters obtained in the current iteration to fill the missing values ​​of the G subsequences, and splice the subsequences after the missing values ​​are filled in order to form the preprocessed power data a = (a(1), a(2), ..., a(n), ..., a(N)), where a(n) represents the preprocessed power environment data of the distribution grounding wire equipment at the nth data collection time, and the power environment data a(n) includes the voltage value a 1 (n), current value a 2 (n), grounding resistance value a 3 (n), ambient temperature value a 4 (n) and ambient humidity value a 5 (n).

[0045] Optionally, in step S2, feature extraction is performed on the preprocessed power data, including:

[0046] The preprocessed power data a is subjected to feature extraction, wherein the improved time series prediction is the implementation method of the feature extraction, and the feature extraction process is as follows:

[0047] S21: Sequence decomposition is performed on the preprocessed power data a to obtain sequence data representing five power environment indicators, wherein the sequence data representing the jth power environment indicator is:

[0048] a j =(a j (1),a j (2),...,a j (n),...,a j (N)),j∈[1,5]

[0049] in:

[0050] a j represents the sequence number representing the jth power environment index, and the 1st to 5th power environment indexes are voltage, current, ground resistance, ambient temperature, and ambient humidity, respectively;

[0051] S22: Extracting time series information from different sequence data, where sequence data a j The time series information extraction formula is:

[0052]

[0053] in:

[0054] f j (0) indicates a sequence whose element values ​​are all 1;

[0055] f j Represents sequence data a j Timing information of

[0056] W j 1 represents the concatenated weight matrix of the jth power environment indicator, W j 2 represents the effective information extraction matrix of the j-th power environment indicator, * represents the convolution operator;

[0057] f j (n) represents sequence data a j Time series information of n power environment indicator data;

[0058] S23: Calculate the index weights of different power environment indicators, where the index weight of the j-th power environment indicator is:

[0059]

[0060] in:

[0061] w j represents the index weight of the j-th power environment index;

[0062] σ j Represents sequence data a j The standard deviation of

[0063] Sim je Represents sequence data a j with a e The Spearman correlation coefficient between , e∈[1,5];

[0064] S24: Construct power feature vector F:

[0065] F=[F 1,F 2 ,F 3 ,F 4 ,F 5 ]

[0066] F j =(w j ,f j )

[0067] in:

[0068] F j Represents the eigenvector corresponding to the j-th power environment indicator.

[0069] Optionally, in step S3, constructing a distribution grounding wire equipment abnormality detection model includes:

[0070] Constructing a distribution grounding wire equipment anomaly detection model, wherein the distribution grounding wire equipment anomaly detection model takes the extracted power feature vector as input and takes the anomaly judgment result as output, wherein the improved random forest is an implementation method of the distribution grounding wire equipment anomaly detection model;

[0071] The distribution grounding wire equipment anomaly detection model includes an input layer, a multiple decision tree decision layer and a decision result integration layer. The input layer is used to receive the power feature vector. The multiple decision tree decision layer is a random forest model obtained by combining multiple decision trees. Multiple decision trees make decisions on the power feature vector respectively to obtain the anomaly judgment result of each decision tree. The decision result integration layer is used to integrate the anomaly judgment results of multiple decision trees to obtain the anomaly detection result of the distribution grounding wire equipment.

[0072] The construction process of the distribution grounding wire equipment anomaly detection model is as follows:

[0073] Obtaining D group of power data and the abnormal judgment results corresponding to the power data to form a D group of training data sets, and performing preprocessing and feature extraction in sequence to obtain the power feature vector of the D group of power data;

[0074] Based on the information gain of five power environment indicators, a decision tree is recursively generated to construct D decision trees. The decision tree takes the power feature vector as input, filters the indicator weights, and outputs the abnormal judgment result.

[0075] Optionally, the using a distribution grounding wire equipment anomaly detection model to perform anomaly detection on the power feature vector includes:

[0076] The anomaly detection model of the power distribution grounding wire equipment is used to detect anomalies of the power feature vector, where the anomaly detection process of the power feature vector F is as follows:

[0077] S31: the input layer is used to receive the power feature vector F;

[0078] S32: Multiple decision trees in the multi-decision tree decision layer make decisions on the power feature vector F respectively to obtain the abnormality judgment result of each decision tree, wherein the abnormality judgment result of the d-th decision tree is:

[0079]

[0080]

[0081] in:

[0082] V d (F) represents the modified abnormal judgment result of the d-th decision tree;

[0083] β d (F) represents the abnormal judgment result output by the d-th decision tree, where β d (F)={0,1},β d (F) is 0, indicating that there is no abnormality, β d (F) is 1 if there is an abnormality;

[0084] λ d (F) indicates the abnormality judgment result λ d (F) is the corrected value, represents the information gain of the j-th power environment indicator in the process of building the d-th decision tree;

[0085] S33: The decision result integration layer integrates the abnormal judgment results of multiple decision trees to obtain the abnormal detection result V(F) of the distribution grounding wire equipment:

[0086]

[0087] in:

[0088] δ(·) represents the characteristic function. If V d (F) is higher than the preset threshold, then δ(V d (F)) is 1, otherwise δ(V d (F)) is 0;

[0089] If V(F) is higher than the preset detection threshold, there is an abnormality in the power distribution grounding wire equipment.

[0090] Optionally, in step S4, positioning the current power distribution grounding wire device position by using Beidou includes:

[0091] If an abnormality is detected, the current distribution grounding wire equipment position is located through Beidou, where single-point positioning is the implementation method of Beidou positioning. The positioning process of the distribution grounding wire equipment position is as follows:

[0092] S41: H satellites send satellite signals to a receiver at the location of the power distribution grounding wire device, wherein the satellite signal includes a satellite clock error and a three-dimensional coordinate of the satellite; in the embodiment of the present invention, H>4;

[0093] S42: Calculate the pseudorange from each satellite to the receiver, where the pseudorange from the hth satellite to the receiver is:

[0094]

[0095] in:

[0096] ρ h represents the pseudorange from the hth satellite to the receiver;

[0097] (x h ,y h ,z h ) represents the three-dimensional coordinates of the h-th satellite;

[0098] c represents the speed of light;

[0099] (X, Y, Z) is the three-dimensional coordinate of the receiver to be solved;

[0100] Time represents the clock error of the receiver to be solved;

[0101] Time h represents the clock error of the hth satellite;

[0102] S43: Initialize the receiver's three-dimensional coordinates (X 0 ,Y 0 ,Z 0 ) and clock error Time(0);

[0103] S44: Set the current iteration number of the receiver's three-dimensional coordinates and clock error to k, then the k-th iteration results are (X k ,Y k ,Z k ),Time(k);

[0104] S45: Based on the pseudo-range calculation formula, the iterative solution matrix R is constructed k ,J k :

[0105]

[0106] S46: Calculate the error estimation vector:

[0107]

[0108] S47: Iterate based on the error estimate vector:

[0109]

[0110] S48: Let k=k+1, and return to step S45, until the change in the three-dimensional coordinates of the receiver is lower than the preset change threshold, and the three-dimensional coordinates of the receiver at this time are used as the position of the distribution grounding wire equipment.

[0111] In order to solve the above problem, the present invention provides an electronic device, the electronic device comprising:

[0112] A memory storing at least one instruction;

[0113] Communication interface, enabling electronic equipment to communicate; and

[0114] The processor executes the instructions stored in the memory to implement the above-mentioned Beidou-based distribution grounding wire equipment management method.

[0115] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned Beidou-based distribution grounding wire equipment management method.

[0116] Compared with the prior art, the present invention proposes a Beidou-based distribution grounding wire equipment management method, which has the following advantages:

[0117] First, this scheme proposes a method for extracting power feature vectors. By collecting power data of distribution grounding wire equipment and representing it in segments, the parameters for completing missing values ​​are trained based on the difference in data feature parameters before and after missing value filling of each segment of power data, so as to achieve missing value filling of multiple segments of data. According to the time series structure characteristics of power data, the time series information of power data is iteratively obtained, and the power feature vector is calculated based on the correlation between indicators, so as to realize the extraction of feature vectors that integrate time series information and indicator correlation information.

[0118] At the same time, this scheme proposes an anomaly detection method, which constructs multiple decision trees by acquiring multiple groups of power feature vectors, and makes a decision on whether the power feature vector is abnormal. Based on the information gain weights of different indicator nodes in the decision tree and the indicator weights of different indicators in the power feature vector corresponding to the power data, the judgment results of the decision tree are adaptively corrected according to the difference between the two weights to improve the accuracy of the decision judgment. If an anomaly is detected, the satellite signal transmitted by the Beidou satellite is used to locate the current distribution grounding wire equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0119] Figure 1 A schematic flow chart of a Beidou-based power distribution grounding wire equipment management method provided in one embodiment of the present invention;

[0120] Figure 2 A schematic structural diagram of an electronic device for implementing a Beidou-based power distribution grounding wire equipment management method provided by an embodiment of the present invention.

[0121] In the figure: 1 electronic device, 10 processor, 11 memory, 12 program, 13 communication interface.

[0122] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0123] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0124] The embodiment of the present application provides a Beidou-based distribution grounding wire equipment management method. The execution subject of the Beidou-based distribution grounding wire equipment management method includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the Beidou-based distribution grounding wire equipment management method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0125] Embodiment 1:

[0126] S1: Collect power data of the distribution grounding wire equipment in real time and preprocess it to obtain preprocessed power data.

[0127] The real-time collection of power data of the power distribution grounding wire equipment in step S1 includes:

[0128] The power data of the power distribution grounding wire equipment is collected in real time, wherein the power data of the power distribution grounding wire equipment collected is in the form of:

[0129] A=(A(1),A(2),...,A(n),...,A(N))

[0130] M=(M(1),M(2),...,M(n),...,M(N))

[0131] in:

[0132] A represents the collected power data of the distribution grounding wire equipment, A(1), A(2), ..., A(n), ..., A(N) represent the power environment data of the distribution grounding wire equipment at N data collection moments, A(n) represents the power environment data of the distribution grounding wire equipment at the nth data collection moment, N represents the total number of data collection moments, where the power environment data A(n) includes the voltage value A 1 (n), current value A 2 (n), grounding resistance value A 3 (n), ambient temperature value A 4 (n) and ambient humidity value A 5 (n);

[0133] M represents the missing value mark sequence of the power data A. If the distribution grounding wire device does not collect the power environment data at the nth data collection time, A(n) is a missing value, and the missing value mark M(n) = 0, otherwise M(n) = 1;

[0134] The missing values ​​in the power data A are filled to form the preprocessed power data a.

[0135] The filling of missing values ​​in the power data A includes:

[0136] S11: The power data A is represented in a segmented manner to obtain G subsequences of the power data A, wherein the g-th subsequence of the power data A is:

[0137]

[0138] in:

[0139] A g represents the g-th subsequence of power data A, Represents subsequence A g In Power environment data;

[0140] The subsequence A g The corresponding missing value marker sequence is M g :

[0141]

[0142] in:

[0143] Power environment data Missing value markers;

[0144] S12: Delete the missing values ​​in the subsequence to form the target subsequence, where subsequence A g The corresponding target subsequence is C g ;

[0145] S13: Construct the missing value filling objective function of power data A:

[0146]

[0147] in:

[0148] L(θ) represents the objective function value of filling missing values ​​of power data A using parameter θ, and L(·) represents the missing value filling objective function;

[0149] Represents the subsequence A after missing value filling based on parameter θ g The index value of the i-th data index, i∈[1,4], where the 1st to 4th data indexes are the sequence mean, sequence standard deviation, sequence kurtosis and sequence skewness respectively;

[0150] s i (g) represents the target subsequence C g The index value of the i-th data index;

[0151] Where the subsequence A is g The filling formula for missing value filling is: T [A g ;M g ], T represents transpose;

[0152] S14: Initialize a set of parameters θ 0 , set the current iteration number of the parameter to t, the maximum iteration number to Max, and the initial value of t to 0;

[0153] S15: Iterate the parameters, where the iteration formula is:

[0154]

[0155] in:

[0156] grad t Denotes the parameter θ t The gradient of t The calculation method is: take the parameter as the variable to calculate the partial derivative of the missing value filling objective function L(θ), and use the parameter θ t Substitute the partial derivative calculation results to get the parameter θ t The gradient of

[0157] ε represents a control parameter; in the embodiment of the present invention, ε is set to 0.01;

[0158] ||·|| 2 represents the L2 norm;

[0159] α t represents the adaptive iteration weight;

[0160] exp(·) represents an exponential function with a natural constant as the base;

[0161] S16: Let t = t + 1, return to step S15, until the maximum number of iterations is reached, and use the parameters obtained in the current iteration to fill the missing values ​​of the G subsequences, and splice the subsequences after the missing values ​​are filled in order to form the preprocessed power data a = (a(1), a(2), ..., a(n), ..., a(N)), where a(n) represents the preprocessed power environment data of the distribution grounding wire equipment at the nth data collection time, and the power environment data a(n) includes the voltage value a 1 (n), current value a 2 (n), grounding resistance value a 3 (n), ambient temperature value a 4 (n) and ambient humidity value a 5 (n).

[0162] S2: Extract features from the preprocessed power data to obtain a power feature vector.

[0163] In the step S2, feature extraction is performed on the preprocessed power data, including:

[0164] The preprocessed power data a is subjected to feature extraction, wherein the improved time series prediction is the implementation method of the feature extraction, and the feature extraction process is as follows:

[0165] S21: Sequence decomposition is performed on the preprocessed power data a to obtain sequence data representing five power environment indicators, wherein the sequence data representing the jth power environment indicator is:

[0166] a j =(a j (1),a j (2),...,a j (n),...,a j (N)),j∈[1,5]

[0167] in:

[0168] a j represents the sequence number representing the jth power environment index, and the 1st to 5th power environment indexes are voltage, current, ground resistance, ambient temperature, and ambient humidity, respectively;

[0169] S22: Extracting time series information from different sequence data, where sequence data a j The time series information extraction formula is:

[0170]

[0171] in:

[0172] f j (0) indicates a sequence whose element values ​​are all 1;

[0173] f j Represents sequence data a j Timing information of

[0174] W j 1 represents the concatenated weight matrix of the jth power environment indicator, W j 2 represents the effective information extraction matrix of the j-th power environment indicator, * represents the convolution operator;

[0175] f j (n) represents sequence data a j Time series information of n power environment indicator data;

[0176] S23: Calculate the index weights of different power environment indicators, where the index weight of the j-th power environment indicator is:

[0177]

[0178] in:

[0179] w j represents the index weight of the j-th power environment index;

[0180] σ j Represents sequence data a j The standard deviation of

[0181] Sim je Represents sequence data a j with a e The Spearman correlation coefficient between , e∈[1,5];

[0182] S24: Construct power feature vector F:

[0183] F=[F 1 ,F 2 ,F 3 ,F 4 ,F 5 ]

[0184] F j =(w j ,f j )

[0185] in:

[0186] F j Represents the eigenvector corresponding to the j-th power environment indicator.

[0187] S3: Construct a distribution grounding wire equipment anomaly detection model to perform anomaly detection on the power feature vector, wherein the distribution grounding wire equipment anomaly detection model takes the extracted power feature vector as input and takes the anomaly judgment result as output.

[0188] The step S3 constructs a distribution grounding wire equipment abnormality detection model, including:

[0189] Constructing a distribution grounding wire equipment anomaly detection model, wherein the distribution grounding wire equipment anomaly detection model takes the extracted power feature vector as input and takes the anomaly judgment result as output, wherein the improved random forest is an implementation method of the distribution grounding wire equipment anomaly detection model;

[0190] The distribution grounding wire equipment anomaly detection model includes an input layer, a multiple decision tree decision layer and a decision result integration layer. The input layer is used to receive the power feature vector. The multiple decision tree decision layer is a random forest model obtained by combining multiple decision trees. Multiple decision trees make decisions on the power feature vector respectively to obtain the anomaly judgment result of each decision tree. The decision result integration layer is used to integrate the anomaly judgment results of multiple decision trees to obtain the anomaly detection result of the distribution grounding wire equipment.

[0191] The construction process of the distribution grounding wire equipment anomaly detection model is as follows:

[0192] Obtaining D group of power data and the abnormal judgment results corresponding to the power data to form a D group of training data sets, and performing preprocessing and feature extraction in sequence to obtain the power feature vector of the D group of power data;

[0193] Based on the information gain of five power environment indicators, a decision tree is recursively generated to construct D decision trees. The decision tree takes the power feature vector as input, filters the indicator weights, and outputs the abnormal judgment result.

[0194] The method of using the distribution grounding wire equipment anomaly detection model to perform anomaly detection on the power feature vector includes:

[0195] The anomaly detection model of the power distribution grounding wire equipment is used to detect anomalies of the power feature vector, where the anomaly detection process of the power feature vector F is as follows:

[0196] S31: the input layer is used to receive the power feature vector F;

[0197] S32: Multiple decision trees in the multi-decision tree decision layer make decisions on the power feature vector F respectively to obtain the abnormality judgment result of each decision tree, wherein the abnormality judgment result of the d-th decision tree is:

[0198]

[0199]

[0200] in:

[0201] V d (F) represents the modified abnormal judgment result of the d-th decision tree;

[0202] β d (F) represents the abnormal judgment result output by the d-th decision tree, where β d (F)={0,1},β d (F) is 0, indicating that there is no abnormality, β d (F) is 1 if there is an abnormality;

[0203] λ d (F) indicates the abnormality judgment result λ d (F) is the corrected value, represents the information gain of the j-th power environment indicator in the process of building the d-th decision tree;

[0204] S33: The decision result integration layer integrates the abnormal judgment results of multiple decision trees to obtain the abnormal detection result V(F) of the distribution grounding wire equipment:

[0205]

[0206] in:

[0207] δ(·) represents the characteristic function. If V d (F) is higher than the preset threshold, then δ(V d (F)) is 1, otherwise δ(V d (F)) is 0;

[0208] If V(F) is higher than the preset detection threshold, there is an abnormality in the power distribution grounding wire equipment.

[0209] S4: If an abnormality is detected, the current distribution grounding wire equipment position is located through Beidou.

[0210] In the step S4, the current power distribution grounding wire equipment position is located by using Beidou, including:

[0211] If an abnormality is detected, the current distribution grounding wire equipment position is located through Beidou, where single-point positioning is the implementation method of Beidou positioning. The positioning process of the distribution grounding wire equipment position is as follows:

[0212] S41: H satellites send satellite signals to a receiver at the location of the power distribution grounding wire device, wherein the satellite signal includes a satellite clock error and a three-dimensional coordinate of the satellite; in the embodiment of the present invention, H>4;

[0213] S42: Calculate the pseudorange from each satellite to the receiver, where the pseudorange from the hth satellite to the receiver is:

[0214]

[0215] in:

[0216] ρ h represents the pseudorange from the hth satellite to the receiver;

[0217] (x h ,y h ,z h ) represents the three-dimensional coordinates of the h-th satellite;

[0218] c represents the speed of light;

[0219] (X, Y, Z) is the three-dimensional coordinate of the receiver to be solved;

[0220] Time represents the clock error of the receiver to be solved;

[0221] Time h represents the clock error of the hth satellite;

[0222] S43: Initialize the receiver's three-dimensional coordinates (X 0 ,Y 0 ,Z 0 ) and clock error Time(0);

[0223] S44: Set the current iteration number of the receiver's three-dimensional coordinates and clock error to k, then the k-th iteration results are (X k ,Y k ,Z k ),Time(k);

[0224] S45: Based on the pseudo-range calculation formula, the iterative solution matrix R is constructed k ,J k :

[0225]

[0226] S46: Calculate the error estimation vector:

[0227]

[0228] S47: Iterate based on the error estimate vector:

[0229]

[0230] S48: Let k=k+1, and return to step S45, until the change in the three-dimensional coordinates of the receiver is lower than the preset change threshold, and the three-dimensional coordinates of the receiver at this time are used as the position of the distribution grounding wire equipment.

[0231] Embodiment 2:

[0232] like Figure 2 , is a schematic diagram of the structure of an electronic device for implementing a Beidou-based power distribution grounding wire equipment management method provided by an embodiment of the present invention.

[0233] The electronic device 1 may include a processor 10 , a memory 11 , a communication interface 13 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10 , such as a program 12 .

[0234] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a mobile hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 may be used not only to store application software and various types of data installed in the electronic device 1, such as the code of the program 12, etc., but also to temporarily store data that has been output or is to be output.

[0235] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, and executes or executes the programs or modules stored in the memory 11 (such as the program 12 for implementing the management of the power distribution grounding line equipment based on Beidou), and calls the data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0236] The communication interface 13 may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices, and to achieve connection and communication between internal components of the electronic device.

[0237] The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0238] Figure 2 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 2 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0239] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0240] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0241] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0242] The program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0243] Collect power data of power distribution grounding wire equipment in real time and pre-process it to obtain pre-processed power data;

[0244] Perform feature extraction on the preprocessed power data to obtain a power feature vector;

[0245] Construct an anomaly detection model for distribution grounding wire equipment to detect anomalies of power feature vectors;

[0246] If an abnormality is detected, the current distribution grounding wire equipment position will be located through Beidou.

[0247] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figure 1 to Figure 2 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0248] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0249] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0250] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A Beidou-based power distribution grounding wire equipment management method, characterized in that: The method comprises: S1: collect power data of distribution grounding wire equipment in real time and preprocess it to obtain preprocessed power data; S2: extracting features from the preprocessed power data to obtain a power feature vector; S3: constructing a distribution grounding wire equipment anomaly detection model to perform anomaly detection on the power feature vector, wherein the distribution grounding wire equipment anomaly detection model takes the extracted power feature vector as input and takes the anomaly judgment result as output; S4: If an abnormality is detected, the current distribution grounding wire equipment position is located through Beidou.

2. A Beidou-based distribution grounding wire equipment management method as claimed in claim 1, characterized in that: The real-time collection of power data of the power distribution grounding wire equipment in step S1 includes: Real-time collection of power data of distribution grounding wire equipment, where the collected power data of distribution grounding wire equipment is in the form of: A=(A(1),A(2),...,A(n),...,A(N)) M=(M(1),M(2),...,M(n),...,M(N)) in: A represents the collected power data of the distribution grounding wire device, A(1), A(2), ..., A(n), ..., A(N) represent the power environment data of the distribution grounding wire device at N data collection moments, A(n) represents the power environment data of the distribution grounding wire device at the nth data collection moment, N represents the total number of data collection moments, wherein the power environment data A(n) includes voltage value A1(n), current value A2(n), grounding resistance value A3(n), ambient temperature value A4(n) and ambient humidity value A5(n); M represents the missing value mark sequence of the power data A. If the distribution grounding wire device does not collect the power environment data at the nth data collection time, A(n) is a missing value, and the missing value mark M(n) = 0, otherwise M(n) = 1; The missing values ​​in the power data A are filled to form the preprocessed power data a.

3. A Beidou-based power distribution grounding wire equipment management method as described in claim 2, characterized in that: The filling of missing values ​​in the power data A includes: S11: The power data A is represented in a segmented manner to obtain G subsequences of the power data A, wherein the g-th subsequence of the power data A is: in: A g represents the g-th subsequence of power data A, Represents subsequence A g In Power environment data; The subsequence A g The corresponding missing value marker sequence is M g : in: Power environment data Missing value markers; S12: Delete the missing values ​​in the subsequence to form the target subsequence, where subsequence A g The corresponding target subsequence is C g ; S13: Construct the missing value filling objective function of power data A: in: L(θ) represents the objective function value of filling missing values ​​of power data A using parameter θ, and L(·) represents the missing value filling objective function; Represents the subsequence A after missing value filling based on parameter θ g The index value of the i-th data index, i∈[1,4], where the 1st to 4th data indexes are the sequence mean, sequence standard deviation, sequence kurtosis and sequence skewness respectively; s i (g) represents the target subsequence C g The index value of the i-th data index; Where the subsequence A is g The filling formula for missing value filling is: T [A g ;M g ], T represents transpose; S14: Initialize a set of parameters θ0, set the current iteration number of the parameters to t, the maximum iteration number to Max, and the initial value of t to 0; S15: Iterate the parameters, where the iteration formula is: in: grad t Denotes the parameter θ t The gradient of t The calculation method is: take the parameter as the variable to calculate the partial derivative of the missing value filling objective function L(θ), and use the parameter θ t Substitute the partial derivative calculation results to get the parameter θ t The gradient of ε represents the control parameter; ||·||2 represents the L2 norm; α t represents the adaptive iteration weight; exp(·) represents an exponential function with a natural constant as the base; S16: Let t=t+1, return to step S15, until the maximum number of iterations is reached, and use the parameters obtained from the current iteration to fill the missing values ​​of G subsequences, and splice the subsequences after the missing values ​​are filled in order to form preprocessed power data a=(a(1), a(2), ..., a(n), ..., a(N)), where a(n) represents the preprocessed power environment data of the distribution grounding wire equipment at the nth data collection moment, and the power environment data a(n) includes voltage value a1(n), current value a2(n), grounding resistance value a3(n), ambient temperature value a4(n) and ambient humidity value a5(n).

4. A Beidou-based power distribution grounding wire equipment management method as claimed in claim 2, characterized in that: In the step S2, feature extraction is performed on the preprocessed power data, including: The preprocessed power data a is subjected to feature extraction, and the feature extraction process is as follows: S21: Sequence decomposition is performed on the preprocessed power data a to obtain sequence data representing five power environment indicators, wherein the sequence data representing the jth power environment indicator is: a j =(a j (1),a j (2),...,a j (n),...,a j (N)),j∈[1,5] in: a j represents the sequence number representing the jth power environment index, and the 1st to 5th power environment indexes are voltage, current, ground resistance, ambient temperature, and ambient humidity, respectively; S22: Extracting time series information from different sequence data, where sequence data a j The time series information extraction formula is: in: f j (0) indicates a sequence whose element values ​​are all 1; f j Represents sequence data a j Timing information of represents the concatenated weight matrix of the jth power environment indicator, represents the effective information extraction matrix of the j-th power environment indicator, * represents the convolution operator; f j (n) represents sequence data a j Time series information of n power environment indicator data; S23: Calculate the index weights of different power environment indicators, where the index weight of the j-th power environment indicator is: in: w j represents the index weight of the j-th power environment index; σ j Represents sequence data a j The standard deviation of Sim je Represents sequence data a j with a e The Spearman correlation coefficient between , e∈[1,5]; S24: Construct power feature vector F: F=[F1,F2,F3,F4,F5] F j =(w j ,f j ) in: F j Represents the eigenvector corresponding to the j-th power environment indicator.

5. A Beidou-based distribution grounding wire equipment management method as claimed in claim 1, characterized in that: The step S3 constructs a distribution grounding wire equipment abnormality detection model, including: Constructing a power distribution grounding wire equipment anomaly detection model, wherein the power distribution grounding wire equipment anomaly detection model takes the extracted power feature vector as input and takes the anomaly judgment result as output; The distribution grounding wire equipment anomaly detection model includes an input layer, a multiple decision tree decision layer and a decision result integration layer. The input layer is used to receive the power feature vector. The multiple decision tree decision layer is a random forest model obtained by combining multiple decision trees. Multiple decision trees make decisions on the power feature vector respectively to obtain the anomaly judgment result of each decision tree. The decision result integration layer is used to integrate the anomaly judgment results of multiple decision trees to obtain the anomaly detection result of the distribution grounding wire equipment. The construction process of the distribution grounding wire equipment anomaly detection model is as follows: Obtaining D group of power data and the abnormal judgment results corresponding to the power data to form a D group of training data sets, and performing preprocessing and feature extraction in sequence to obtain the power feature vector of the D group of power data; Based on the information gain of five power environment indicators, a decision tree is recursively generated to construct D decision trees, where the decision tree takes the power feature vector as input, filters the indicator weights, and takes the abnormal judgment result as output.

6. A Beidou-based distribution grounding wire equipment management method as claimed in claim 5, characterized in that: The method of using the distribution grounding wire equipment anomaly detection model to perform anomaly detection on the power feature vector includes: The anomaly detection model of the power distribution grounding wire equipment is used to detect anomalies of the power feature vector, where the anomaly detection process of the power feature vector F is as follows: S31: the input layer is used to receive the power feature vector F; S32: Multiple decision trees in the multi-decision tree decision layer make decisions on the power feature vector F respectively to obtain the abnormality judgment result of each decision tree, wherein the abnormality judgment result of the d-th decision tree is: in: V d (F) represents the modified abnormal judgment result of the dth decision tree; β d (F) represents the abnormal judgment result output by the d-th decision tree, where β d (F)={0,1},β d (F) is 0, indicating that there is no abnormality, β d (F) is 1 if there is an abnormality; λ d (F) indicates the abnormality judgment result λ d (F) is the corrected value, represents the information gain of the j-th power environment indicator in the process of building the d-th decision tree; S33: The decision result integration layer integrates the abnormal judgment results of multiple decision trees to obtain the abnormal detection result V(F) of the distribution grounding wire equipment: in: δ(·) represents the characteristic function. If V d (F) is higher than the preset threshold, then δ(V d (F)) is 1, otherwise δ(V d (F)) is 0; If V(F) is higher than the preset detection threshold, there is an abnormality in the power distribution grounding wire equipment.

7. A Beidou-based power distribution grounding wire equipment management method as claimed in claim 6, characterized in that: In the step S4, the current power distribution grounding wire equipment position is located by using Beidou, including: If an abnormality is detected, the current power distribution grounding wire equipment position is located through Beidou, and the location positioning process of the power distribution grounding wire equipment position is as follows: S41: H satellites send satellite signals to a receiver at a location of a power distribution grounding line device, wherein the satellite signals include a satellite clock error and a three-dimensional coordinate of the satellite; S42: Calculate the pseudorange from each satellite to the receiver, where the pseudorange from the hth satellite to the receiver is: in: ρ h represents the pseudorange from the hth satellite to the receiver; (x h ,y h ,z h ) represents the three-dimensional coordinates of the h-th satellite; c represents the speed of light; (X, Y, Z) is the three-dimensional coordinate of the receiver to be solved; Time represents the clock error of the receiver to be solved; Time h represents the clock error of the hth satellite; S43: Initialize the receiver's three-dimensional coordinates (X0, Y0, Z0) and clock error Time (0); S44: Set the current iteration number of the receiver's three-dimensional coordinates and clock error to k, then the k-th iteration results are (X k ,Y k ,Z k ),Time(k); S45: Based on the pseudo-range calculation formula, the iterative solution matrix R is constructed k ,J k : S46: Calculate the error estimation vector: S47: Iterate based on the error estimate vector: S48: Let k=k+1, and return to step S45, until the change in the three-dimensional coordinates of the receiver is lower than the preset change threshold, and the three-dimensional coordinates of the receiver at this time are used as the position of the distribution grounding wire equipment.

Images