Inspection Overstep Early Warning Method and Early Warning System for UAV Applied to Distribution Network

Abstract

This application relates to the technical field of unmanned aerial vehicle (UAV) inspection and early warning, and specifically relates to an inspection over - boundary early warning method and an early warning system for UAVs applied to distribution networks. The method includes: obtaining the inspection path of the UAV, measuring the position of the UAV and the electromagnetic field strength at the position where it is located in real - time, and measuring the signal - to - noise ratio of the communication link at the position where the UAV is located in real - time; constructing a feature matrix at the current moment; obtaining the sensitivity of the UAV path to the electromagnetic field at the current moment; determining the degree of dispersion of the path deviation at the current moment and its adjacent moments, the first correlation between the electromagnetic field strength and the path deviation, and the second correlation between the electromagnetic field strength and the signal - to - noise ratio; determining the weighted fusion factor at the current moment; combining the weighted fusion factor with the sensitivity to obtain the electromagnetic influence coefficient at the current moment, and giving an early warning of the inspection over - boundary of the UAV. Thereby, the accuracy of UAV inspection over - boundary early warning is improved.

Description

Technical Field

[0001] This application relates to the technical field of unmanned aerial vehicle (UAV) inspection and early warning, and specifically to an inspection over - boundary early warning method and an early warning system for UAVs used in the distribution network. Background Art

[0002] The inspection over - boundary early warning technology for UAVs in the distribution network is an important breakthrough in the intelligent operation and maintenance of the power system. Its core significance lies in ensuring inspection safety, improving efficiency and reducing risks through precise boundary control. Although UAVs can break through spatial limitations, if they stray into live areas, cross safety distances or enter no - fly zones, it may cause equipment discharge, collision accidents, etc. The application of the over - boundary early warning technology can reduce the risk of human operation errors and avoid equipment damage.

[0003] In the UAV inspection near high - voltage cables, the complex sources of path deviation are caused by the coupling of strong electromagnetic fields, GPS signal errors, wind disturbances and other factors. Traditional methods are difficult to dynamically distinguish the interference of different factors due to relying on single sensors or static models. Existing technologies are limited by the single data dimension and the lack of a dynamic weight allocation mechanism for multi - source interference, and cannot effectively quantify the actual impact of electromagnetic interference in complex environments, resulting in poor adaptability in the event of sudden electromagnetic pulses or communication link fluctuations, and it is difficult to ensure the stability and safety of UAVs in strong electromagnetic environments, leading to a low accuracy of the inspection over - boundary early warning for UAVs. Summary of the Invention

[0004] In order to solve the above - mentioned technical problems, the purpose of this application is to provide an inspection over - boundary early warning method and an early warning system for UAVs used in the distribution network. The specific technical solutions adopted are as follows:

[0005] In the first aspect, an embodiment of this application provides an inspection over - boundary early warning method for UAVs used in the distribution network. The method includes the following steps:

[0006] Obtain the inspection path of the UAV, measure the position of the UAV and the electromagnetic field strength at the position in real - time, and measure the signal - to - noise ratio of the communication link at the position where the UAV is located in real - time;

[0007] Based on the inspection path and the measured position of the UAV, determine the path deviation of the UAV at each moment; use the electromagnetic field strength and the change rate of the electromagnetic field strength at the current moment and each previous moment, the path deviation and the change rate of the path deviation at the current moment and each previous moment to construct a feature matrix at the current moment;

[0008] Through the feature matrix at the current moment, with the inspection path as the target value, combined with the integrated learning algorithm, obtain the prediction deviation, mean square error, and coefficient of determination at the current moment, and obtain the sensitivity of the UAV path to the electromagnetic field at the current moment;

[0009] Determine the discreteness of the path deviation at the current moment and its adjacent moments, the first correlation between the electromagnetic field strength and the path deviation, and the second correlation between the electromagnetic field strength and the signal-to-noise ratio;

[0010] After performing fuzzy and defuzzification processing on the discreteness, the first correlation, and the second correlation respectively, output the results as the first weight, the second weight, and the third weight, and combine the path deviation, the electromagnetic field strength, and the signal-to-noise ratio at the current moment to determine the weighted fusion factor at the current moment;

[0011] Combine the weighted fusion factor and the sensitivity to obtain the electromagnetic influence coefficient at the current moment, and give an early warning for the inspection overstep of the UAV.

[0012] In one embodiment, the path deviation is the shortest distance between the measured positions of the UAV at each moment and the inspection path.

[0013] In one embodiment, the construction of the feature matrix at the current moment includes:

[0014] For the current moment and each moment before it, calculate the mean value of the electromagnetic field strength at each moment and its adjacent moments, calculate the electromagnetic field change gradient at each moment, calculate the path deviation change rate at each moment, and form column vectors of the electromagnetic field strength, the mean value, the electromagnetic field change gradient, the path deviation, and the path deviation change rate at all moments respectively to obtain the feature matrix.

[0015] In one embodiment, the determination of the sensitivity includes:

[0016] Calculate the ratio of the coefficient of determination to the mean square error at the current moment, calculate the difference between the prediction deviation and the path deviation at the current moment, and the sensitivity is positively correlated with the ratio and negatively correlated with the difference.

[0017] In one embodiment, the calculation method of the difference is:

[0018] Calculate the sum value of the path deviation at the current moment and a preset value greater than 0, calculate the ratio of the prediction deviation at the current moment to the sum value, denoted as the first ratio, and the difference is the absolute value of the difference between the first ratio and the value 1.

[0019] In one embodiment, the fuzzy processing includes:

[0020] Calculate the dispersion degree, the first correlation, and the second correlation at each moment, obtain the maximum value of the dispersion degree at the current moment and all previous moments, divide the numerical range from 0 to the maximum value into three fuzzy sets: low, medium, and high in sequence, and obtain the fuzzy set to which the dispersion degree at the current moment belongs according to the interval where the dispersion degree at the current moment is located;

[0021] For the first correlation and the second correlation at the current moment, perform fuzzy processing using the same fuzzy processing process as the dispersion degree at the current moment.

[0022] In one embodiment, the output results serve as the first weight, the second weight, and the third weight, including:

[0023] Take the output results obtained by using the centroid method for the fuzzy sets of the dispersion degree, the first correlation, and the second correlation at the current moment as the first weight, the second weight, and the third weight in sequence.

[0024] In one embodiment, the determination of the weighted fusion factor includes:

[0025] Calculate the product of the normalized value of the path deviation at the current moment and the first weight, calculate the multiplication result of the normalized value of the electromagnetic field strength at the current moment and the second weight, calculate the product of the normalized value of the signal-to-noise ratio at the current moment and the third weight, and the weighted fusion factor is the sum of the product, the multiplication result, and the product.

[0026] In one embodiment, obtaining the electromagnetic influence coefficient at the current moment and warning of the patrol overstep of the unmanned aerial vehicle includes:

[0027] The electromagnetic influence coefficient is the product of the sensitivity and the weighted fusion factor, denoted as the first product. When the normalized value of the first product is greater than a preset threshold, it is determined that the unmanned aerial vehicle has a risk of patrol overstep; otherwise, it is determined that the unmanned aerial vehicle does not have a risk of patrol overstep.

[0028] In a second aspect, an embodiment of the present application further provides a patrol overstep warning system for a distribution network unmanned aerial vehicle, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the method described in any one of the above are implemented.

[0029] The present application has at least the following beneficial effects:

[0030] This application obtains the inspection path of the drone, measures the position of the drone and the electromagnetic field intensity at the location in real time, and measures the signal-to-noise ratio of the communication link at the location where the drone is located in real time; by collecting multi-source data, the robustness of the final determination of drone inspection out-of-bounds is improved; based on the inspection path and the measured position of the drone, the path deviation of the drone at each moment is determined; using the electromagnetic field intensity and the change rate of the electromagnetic field intensity at the current moment and each previous moment, the path deviation and the change rate of the path deviation at the current moment and each previous moment, a feature matrix at the current moment is constructed; through the feature matrix at the current moment, with the inspection path as the target value, combined with the integrated learning algorithm, the prediction deviation, mean square error, and coefficient of determination at the current moment are obtained, and the sensitivity of the drone path to the electromagnetic field at the current moment is obtained; by establishing a quantitative model of the influence of electromagnetic interference on the drone flight trajectory, the sensitivity of drone path deviation recognition is improved, and the accuracy of drone inspection out-of-bounds assessment is enhanced; determine the degree of dispersion of the path deviation at the current moment and its adjacent moments, the first correlation between the electromagnetic field intensity and the path deviation, and the second correlation between the electromagnetic field intensity and the signal-to-noise ratio; after respectively performing fuzzy processing on the degree of dispersion, the first correlation, and the second correlation and then re-outputting, the output results are used as the first weight, the second weight, and the third weight. By processing uncertainty through fuzzy logic, the decision-making noise caused by environmental parameter fluctuations is solved, the noise influence is reduced, and the adaptability and reliability of feature extraction are enhanced; combining the path deviation, the electromagnetic field intensity, and the signal-to-noise ratio at the current moment, the weighted fusion factor at the current moment is determined; the weighted fusion factor reflects the influence degree of multiple factors on the drone path deviation. Combining the weighted fusion factor and the sensitivity, the electromagnetic influence coefficient at the current moment is obtained, which effectively quantifies the influence of electromagnetic interference on the drone inspection path deviation, warns of the drone inspection out-of-bounds, improves the stability and safety of the drone in a strong electromagnetic environment, and enhances the accuracy of drone inspection out-of-bounds warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0032] Figure 1 It is a flowchart of the steps of a method for warning of drone inspection out-of-bounds applied to a distribution network drone provided by an embodiment of the present application;

[0033] Figure 2 It is a flowchart for determining the electromagnetic influence coefficient. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0034] To further elaborate on the technical means and effects adopted by this application to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of the inspection over - boundary warning method and warning system for distribution network drones proposed according to this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs.

[0036] The following specifically describes the specific solutions of the inspection over - boundary warning method and warning system for distribution network drones provided by this application in combination with the accompanying drawings.

[0037] Please refer to Figure 1 , which shows the step - flow chart of the inspection over - boundary warning method for distribution network drones provided by one embodiment of this application. The method includes the following steps:

[0038] S1. Obtain the inspection path of the drone, measure the position of the drone and the electromagnetic field intensity at the position where it is located in real - time, and measure the signal - to - noise ratio of the communication link at the position where the drone is located in real - time.

[0039] In this embodiment, a high - precision GPS device is used, combined with GIS software to conduct on - site mapping of the distribution network area, obtain the accurate longitude and latitude coordinates of the boundary of the distribution network area. Inside the boundary of the distribution area, the inspection path of the drone is preset in advance. A high - precision GPS sensor and an electromagnetic field sensor are installed on the drone. The high - precision GPS sensor is used to obtain the real - time GPS longitude and latitude of the drone, and the electromagnetic field sensor is used to obtain the real - time electromagnetic field intensity at the position where the drone is located. A wireless network analyzer is installed in the drone to collect the signal - to - noise ratio of the communication link in real - time.

[0040] It should be noted that the GPS longitude and latitude, electromagnetic field intensity, and signal - to - noise ratio of the communication link of the drone collected in this embodiment are all collected synchronously. The collection frequency is set to 10Hz, and the implementer can set it according to the actual situation. This embodiment does not limit it here.

[0041] S2. Based on the inspection path and the measured position of the drone, determine the path deviation of the drone at each moment; use the electromagnetic field intensity and the change rate of the electromagnetic field intensity at the current moment and each previous moment, the path deviation and the change rate of the path deviation at the current moment and each previous moment to construct the feature matrix at the current moment.

[0042] In this embodiment, the shortest distance between the GPS longitude and latitude of the UAV at each moment and the preset inspection path of the UAV is calculated as the path deviation of the UAV at each moment. After normalizing the path deviations at the current moment and all previous moments, a deviation sequence is formed in chronological order. After normalizing the electromagnetic field intensities at the current moment and all previous moments, an electromagnetic field sequence is formed in chronological order. After normalizing the signal-to-noise ratios at the current moment and all previous moments, a signal-to-noise ratio sequence is formed in chronological order. Among them, the purpose of normalization is to eliminate the dimensionality influence between data. The normalization method in this embodiment all uses the Sigmoid function. Implementers can choose other existing feasible normalization methods by themselves, and this embodiment does not limit it here.

[0043] In the complex electromagnetic environment near high-voltage cables, the path deviation of the UAV inspection may be caused by various factors, including electromagnetic interference, GPS signal error, wind disturbance, etc. In order to accurately distinguish the influence of electromagnetic field interference and other factors on the deviation, this embodiment will establish an association model between the electromagnetic field and the path deviation through historical data. The historical data of the electromagnetic field sequence and the deviation sequence can reflect the dynamic relationship between the change of the electromagnetic field intensity and the path deviation, so as to help quantify the influence degree of electromagnetic interference on the current path deviation, thereby improving the accuracy of out-of-bounds warning and ensuring the stability and reliability of the UAV in a strong electromagnetic field environment.

[0044] This embodiment uses the deviation sequence and the electromagnetic field sequence at the current moment as the historical data for modeling. 40% of the data of the deviation sequence and the electromagnetic field sequence are used as the training set, and 60% of the data are used as the validation set. Subsequently, for the current moment, a feature matrix that can reflect the influence of the electromagnetic field on the path deviation is extracted. In this embodiment, the extracted feature matrix includes: the electromagnetic field intensity at the current moment and each previous moment, the average value of the electromagnetic field intensity at each moment and its adjacent moments, the electromagnetic field change gradient between each moment and its previous moment, the path deviation at each moment, and the path deviation change rate between each moment and its previous moment. Thus, this embodiment obtains a feature matrix of size at the current moment, where N represents the number of all moments at the current moment and before. The feature matrix is shown in Table 1 for illustration.

[0045]

[0046] In Table 1, represents the eigenvalue size of feature 5 at the acquisition moment N. Among them, the electromagnetic field intensity is denoted as feature 1, the average value of the electromagnetic field intensity is denoted as feature 2, the electromagnetic field change gradient is denoted as feature 3, the path deviation is denoted as feature 4, and the path deviation change rate is denoted as feature 5.

[0047] It should be noted that the average value of the electromagnetic field strength calculated in this embodiment is the average value of the electromagnetic field strength at the current moment and the previous adjacent 3 moments. The implementer can set the number of adjacent moments and the division ratio of the training set and the validation set according to the actual situation, and this embodiment does not limit it here.

[0048] S3. Using the feature matrix at the current moment, with the inspection path as the target value, and combining the ensemble learning algorithm, obtain the prediction deviation, mean square error, and coefficient of determination at the current moment, and obtain the sensitivity of the UAV path to the electromagnetic field at the current moment.

[0049] In this embodiment, the feature matrix at the current moment is used as the input, and the preset inspection path of the UAV is used as the target value. The number of trees is set to 100. To avoid overfitting, the maximum depth is set to 8. The random forest regression model is used to train the model through the training set to predict the path deviation. That is, for the current moment t, the prediction deviation at this moment is output, and the mean square error of this prediction is calculated through the random forest regression model. and the coefficient of determination . Among them, the random forest regression model is a well-known existing technology. The implementer can select other existing feasible regression models, such as the gradient boosting regression model, etc. The implementer can set the training parameters of the random forest regression model according to the actual situation, and this embodiment does not limit it here.

[0050] Based on the above analysis, calculate the sensitivity of the UAV path to the electromagnetic field at the current moment t , and the specific calculation formula is: ; in the formula, is the sensitivity of the UAV path to the electromagnetic field at the current moment t, is the coefficient of determination output by the random forest regression model at the current moment t, is the mean square error output by the random forest regression model at the current moment t, is the prediction deviation output by the random forest regression model at the current moment t, is the path deviation at the current moment t, is a preset value greater than 0 to avoid the denominator being 0. In this embodiment, , which can be set by the implementer according to the actual situation. This embodiment does not limit it here. e is the natural constant. Denote as the first ratio.

[0051] It should be understood that among them, the coefficient of determination reflects the prediction ability of the electromagnetic field characteristics on the current path deviation. When it is closer to 1, the electromagnetic field change can explain most of the path deviation fluctuations, indicating that electromagnetic interference is the main factor. At this time, the random forest regression model has a stronger ability to capture electromagnetic interference, indicating that the electromagnetic interference has a greater impact and the A value is larger; the mean square error Measures the prediction accuracy of the random forest regression model within a local time window, and the mean square error The larger the value, the worse the prediction ability of the random forest regression model, the lower the model confidence, and the smaller the A value; in , the numerator represents the model prediction deviation, the denominator represents the actual deviation, and when the difference between the ratio of the two and the value 1 is smaller, it indicates that the consistency between the model prediction deviation and the actual deviation is higher, the greater the impact of electromagnetic interference on the UAV path, and the larger the A value.

[0052] The sensitivity quantifies the influence intensity of the electromagnetic field at the current moment on the path deviation. The higher the value of the sensitivity, the more sensitive the deviation of the UAV's driving path at the current moment is to electromagnetic interference.

[0053] In another embodiment, the sensitivity of the UAV path to the electromagnetic field at the current moment t is calculated as: ; in the formula, is the sensitivity of the UAV path to the electromagnetic field at the current moment t, is the coefficient of determination output by the random forest regression model at the current moment t, is the mean square error output by the random forest regression model at the current moment t, is the prediction deviation output by the random forest regression model at the current moment t, is the path deviation at the current moment t, and e is the natural constant.

[0054] S4. Determine the dispersion degree of the path deviation at the current moment and its adjacent moments, the first correlation between the electromagnetic field intensity and the path deviation, and the second correlation between the electromagnetic field intensity and the signal-to-noise ratio.

[0055] During the UAV inspection process, the impact of electromagnetic interference on the path deviation is often a complex problem of multi-factor coupling. Although the interference intensity of the electromagnetic field can be preliminarily quantified through single-dimensional analysis, in actual scenarios, the path deviation may also be comprehensively affected by communication link quality, environmental noise, and the dynamic characteristics of the UAV itself. Therefore, in order to more comprehensively evaluate the overall impact of electromagnetic interference on UAV inspection, it is necessary to simultaneously consider the dynamic relationship between the electromagnetic field intensity, the change of the signal-to-noise ratio, and the path deviation, so as to improve the accuracy of interference recognition and ensure the stable operation of the UAV in a complex electromagnetic environment.

[0056] In this embodiment, a preset time window is set at each moment. A time window contains 100 moments, and the length of the time window can be set by the implementer himself. That is, in this embodiment, for any moment, 99 moments adjacent to the any moment are selected, and together with the any moment, they form the time window of the any moment.

[0057] For the current moment, calculate the degree of dispersion of the path deviations at all moments within the time window of the current moment, calculate the correlation between the electromagnetic field strengths at all moments within the time window of the current moment and the path deviation, denoted as the first correlation, and calculate the correlation between the electromagnetic field strengths at all moments within the time window of the current moment and the signal-to-noise ratio, denoted as the second correlation.

[0058] It should be noted that in this embodiment, the degree of dispersion is calculated using the variance calculation method. Implementers can choose other existing feasible calculation methods by themselves, such as standard deviation, coefficient of variation, etc. In this embodiment, the correlations are all calculated using covariance. Implementers can choose other existing feasible calculation methods by themselves, such as Pearson correlation coefficient, cosine similarity, etc.

[0059] S5. After performing fuzzy and defuzzification processing on the degree of dispersion, the first correlation, and the second correlation respectively, output the results as the first weight, the second weight, and the third weight. Combine the path deviation, the electromagnetic field strength, and the signal-to-noise ratio at the current moment to determine the weighted fusion factor at the current moment.

[0060] Obtain the degrees of dispersion at all moments before the current moment, and count the maximum value among all the degrees of dispersion. Denote the maximum value as x. Divide the degrees of dispersion at all moments before the current moment into three fuzzy sets: low, medium, and high. Among them, the value range of the low fuzzy set is [0, 0.4x], the coverage range of the medium fuzzy set is [0.3x, 0.7x], and the coverage range of the high fuzzy set is set to [0.6x, x]. For each fuzzy set, count the mode within this range. Take the left boundary, mode, and right boundary of each fuzzy set as the left vertex, peak point, and right vertex of the triangular membership function of this fuzzy set respectively. Use the triangular membership function to calculate the membership degrees of the degree of dispersion at the current moment in each fuzzy level, and realize the fuzzy mapping of the degree of dispersion at the current moment. Among them, the implementer can set the value ranges of the three fuzzy sets of low, medium, and high according to the actual situation by themselves.

[0061] For the first correlation and the second correlation at the current moment, perform fuzzy processing using the same fuzzy processing method as the degree of dispersion. Thus, the fuzzy sets of the degree of dispersion, the first correlation, and the second correlation at the current moment can be obtained respectively.

[0062] Take the output result of the fuzzy set of the degree of dispersion at the current moment using the centroid method as the first weight, take the output result of the fuzzy set of the first correlation at the current moment using the centroid method as the second weight, and take the output result of the fuzzy set of the second correlation at the current moment using the centroid method as the third weight. Among them, the centroid method is a well-known existing technology, and the specific process will not be elaborated.

[0063] It should be understood that the values of path deviation, electromagnetic field strength, and the signal-to-noise ratio may fluctuate due to sensor noise or instantaneous interference, resulting in deviations in the physical meaning represented by the calculated degree of discreteness and correlation. By fuzzifying and defuzzifying them, even if affected by interference, as long as the membership degree is within the same fuzzy set, the physical meaning and information expression represented remain consistent, reducing the influence of other factors and interference.

[0064] Based on the above analysis, the weighted fusion factor at the current moment is calculated in this embodiment, and the specific calculation method is as follows: In the formula, is the weighted fusion factor at the current moment t, is the first weight, is the path deviation at the current moment t, and Norm() is the normalization function. is the second weight, is the electromagnetic field strength at the current moment t, is the third weight, is the signal-to-noise ratio at the current moment t.

[0065] It should be understood that the weighted fusion factor is used to quantify the comprehensive influence of electromagnetic field strength and signal-to-noise ratio on path deviation within the time window at the current moment. 、 、 respectively represent the comprehensive influence contribution weights of path deviation, electromagnetic field strength, and signal-to-noise ratio, reflecting the relative importance of the influence of each factor on path deviation within the time window at the current moment. The larger its value, the greater the influence degree of the corresponding factor of the time window at the current moment on path deviation.

[0066] S6. Combining the weighted fusion factor with the sensitivity, obtain the electromagnetic influence coefficient at the current moment, and give an early warning for the out-of-bounds inspection of the UAV.

[0067] In this embodiment, the product of the weighted fusion factor at the current moment and the sensitivity is denoted as the first product, which is used as the electromagnetic influence coefficient at the current moment. The electromagnetic influence coefficient describes the overall influence of electromagnetic interference on the path deviation of UAV inspection in a complex electromagnetic environment, identifies the correlation degree of electromagnetic interference on path deviation, and distinguishes the influence of electromagnetic interference from other external factors. The higher the value of the electromagnetic influence coefficient, the worse the stability of the UAV in a strong electromagnetic environment, and the higher the risk of out-of-bounds inspection. The flow chart for determining the electromagnetic influence coefficient is as Figure 2 shown.

[0068] Based on the above analysis, in this embodiment, a patrol out-of-bounds threshold is set, denoted as the preset threshold. If the normalized value of the electromagnetic influence coefficient at the current moment is greater than the patrol out-of-bounds threshold, it is determined that the UAV has a risk of patrol out-of-bounds; otherwise, it is determined that the UAV does not have a risk of patrol out-of-bounds. In this embodiment, the patrol out-of-bounds threshold is set to 0.8, and the implementer can set it according to the actual situation, and this embodiment does not limit it here.

[0069] In this embodiment, the Sigmoid function is used to obtain the normalized value of the electromagnetic influence coefficient, and the implementer can choose other existing feasible normalization methods by himself.

[0070] Based on the same inventive concept as the above method, the embodiment of the present application also provides a patrol out-of-bounds early warning system for a distribution network UAV, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-mentioned patrol out-of-bounds early warning methods for a distribution network UAV.

[0071] It should be noted that the above sequence of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification is given. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0072] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0073] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present application shall be included in the protection scope of the present application.

Claims

1. A patrol overstep warning method for drones applied to a distribution network, characterized in that The method includes the following steps: Obtain the inspection path of the unmanned aerial vehicle (UAV), measure the position of the UAV and the electromagnetic field strength at the position in real time, and measure the signal-to-noise ratio of the communication link at the position where the UAV is located in real time; Based on the inspection path and the measured position of the UAV, determine the path deviation of the UAV at each moment; use the electromagnetic field strength and the change rate of the electromagnetic field strength at the current moment and each previous moment, the path deviation and the change rate of the path deviation at the current moment and each previous moment to construct the feature matrix at the current moment; Through the feature matrix at the current moment, with the inspection path as the target value, combined with the integrated learning algorithm, obtain the prediction deviation, mean square error, and coefficient of determination at the current moment, and obtain the sensitivity of the UAV path to the electromagnetic field at the current moment; Determine the degree of dispersion of the path deviation at the current moment and its adjacent moments, the first correlation between the electromagnetic field strength and the path deviation, and the second correlation between the electromagnetic field strength and the signal-to-noise ratio; After respectively performing fuzzy and defuzzification processing on the degree of dispersion, the first correlation, and the second correlation, output the results as the first weight, the second weight, and the third weight, and combine the path deviation, the electromagnetic field strength, and the signal-to-noise ratio at the current moment to determine the weighted fusion factor at the current moment; Combine the weighted fusion factor and the sensitivity to obtain the electromagnetic influence coefficient at the current moment, and give an early warning for the inspection overrun of the UAV.

2. The inspection overstep warning method for drones applied to the distribution network according to claim 1, characterized in that, The path deviation is the shortest distance between the measured position of the UAV at each moment and the inspection path.

3. The inspection over - boundary early - warning method for drones applied to distribution networks according to claim 1, wherein, The construction of the feature matrix at the current moment includes: For each moment from the current moment and previous moments, calculate the mean value of the electromagnetic field strength at each moment and its adjacent moments, calculate the electromagnetic field change gradient at each moment, calculate the change rate of the path deviation at each moment, and respectively form column vectors of the electromagnetic field strength, the mean value, the electromagnetic field change gradient, the path deviation, and the change rate of the path deviation at all moments to obtain the feature matrix.

4. The inspection over - boundary early warning method for UAVs applied to distribution networks according to claim 1, characterized in that, The determination of the sensitivity includes: Calculate the ratio of the coefficient of determination to the mean square error at the current moment, calculate the difference between the prediction deviation and the path deviation at the current moment, and the sensitivity is positively correlated with the ratio and negatively correlated with the difference.

5. The inspection over - boundary early - warning method for drones applied to distribution networks according to claim 4, wherein, The calculation method of the difference is: Calculate the sum value of the path deviation at the current moment and a preset value greater than 0, calculate the ratio of the prediction deviation at the current moment to the sum value, denoted as the first ratio, and the difference is the absolute value of the difference between the first ratio and the value 1.

6. The inspection over - boundary early warning method for drones applied to distribution networks according to claim 1, characterized in that, The fuzzy processing includes: Calculate the degree of dispersion, the first correlation, and the second correlation at each moment, obtain the maximum value of the degree of dispersion at the current moment and all previous moments, divide the numerical interval from 0 to the maximum value into three fuzzy sets: low, medium, and high in sequence, and obtain the fuzzy set to which the degree of dispersion at the current moment belongs according to the interval where the degree of dispersion at the current moment is located; For the first correlation and the second correlation at the current moment, perform fuzzy processing using the same fuzzy processing process as the degree of dispersion at the current moment.

7. The inspection over - boundary early - warning method for drones applied to distribution networks according to claim 6, characterized in that, The output results are used as the first weight, the second weight, and the third weight, including: The output results obtained by using the centroid method for the fuzzy sets of the discreteness degree, the first correlation, and the second correlation at the current moment are sequentially used as the first weight, the second weight, and the third weight.

8. The inspection over - boundary early - warning method for drones applied to the distribution network according to claim 1, characterized in that, The determination of the weighted fusion factor includes: Calculate the product of the normalized value of the path deviation at the current moment and the first weight, calculate the multiplication result of the normalized value of the electromagnetic field strength at the current moment and the second weight, calculate the product of the normalized value of the signal-to-noise ratio at the current moment and the third weight, and the weighted fusion factor is the sum of the product, the multiplication result, and the product.

9. The inspection over - boundary early - warning method for drones applied to distribution networks according to claim 1, wherein, Obtaining the electromagnetic influence coefficient at the current moment and warning of the inspection boundary crossing of the unmanned aerial vehicle includes: The electromagnetic influence coefficient is the product of the sensitivity and the weighted fusion factor, denoted as the first product. When the normalized value of the first product is greater than the preset threshold, it is determined that the unmanned aerial vehicle has a risk of inspection boundary crossing; otherwise, it is determined that the unmanned aerial vehicle does not have a risk of inspection boundary crossing.

10. An inspection over - boundary early warning system applied to a distribution network UAV, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-9.

Images