A Cable Anti-External Damage Method and System Based on Non-Uniform FDM-NLFM

Abstract

The present invention relates to a method and system for preventing external damage to cables based on non-uniform FDM-NLFM, which relates to the field of data processing and includes: by optimizing the fitness function, the number of population updates, and the update influence adjustment factor, comprehensively considering the influence of power attenuation and phase distortion on signal propagation, significantly improving the adaptability of the signal in different soil environments, and ensuring that the signal can stably propagate in a complex underground environment; optimizing the non-uniform FDM-NLFM signal parameters, so that the signal can better resist the influence brought by changes in soil characteristics during propagation. Select the signal parameters with the smallest fitness value to ensure that the signal has the smallest attenuation and distortion during propagation; by continuously adjusting the signal parameters to gradually approach the optimal solution, through multiple rounds of optimization, the finally obtained signal parameters can maintain stable propagation characteristics in different soil zones, solving the technical problem of low accuracy during signal propagation.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a cable anti-external damage method and system based on non-uniform FDM-NLFM. Background Art

[0002] As an important carrier for power transmission, the safe operation of cables is of crucial importance. During the cable laying process, especially underground laying, cables are prone to external damage, such as construction excavation, natural disasters, etc. To ensure the safe operation of cables, traditional cable anti-external damage methods mainly rely on monitoring the cable status and analyzing the cable status by detecting the reflected signal of the injected signal.

[0003] Traditional cable anti-external damage methods have certain limitations. Since the soil environment where the underground cables are laid is complex and diverse, and there are significant differences in soil characteristics in different regions, this difference will cause the signal to be affected to varying degrees during propagation, thereby affecting the accuracy of the detection results. Traditional methods often ignore this regional difference, resulting in a low adaptability of the injected signal to the actual scenario and making it difficult to accurately reflect the true state of the cable. Summary of the Invention

[0004] In view of the technical problem that in the prior art, by detecting the injected non-uniform FDM-NLFM composite signal and then analyzing the cable status according to the reflected signal, since the signal emitted by the underground cable is affected by regional differences, there are problems that the reflected signal is affected and the cable status cannot be accurately analyzed, the present invention provides a cable anti-external damage method and system based on non-uniform FDM-NLFM to solve this problem.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] In a first aspect, a cable anti-external damage method based on non-uniform FDM-NLFM includes:

[0007] Receiving the soil detection information of the cable laying area, partitioning the laying soil, and sorting starting from the signal injection point in combination with the detection direction to obtain a soil partition sequence;

[0008] Traversing the soil partition sequence to perform the mode statistics of the historical sample soil conductivity to obtain a soil conductivity sequence;

[0009] Traversing the soil partition result to perform the mode statistics of the historical sample dielectric constant to obtain a soil dielectric constant sequence;

[0010] Randomly generating a number of non-uniform FDM-NLFM signal parameters, and performing signal propagation simulation in combination with the soil conductivity sequence and the soil dielectric constant sequence to obtain a number of power attenuation coefficients and a number of phase distortion coefficients;

[0011] Based on the plurality of power attenuation coefficients and the plurality of phase distortion coefficients, perform optimization on the plurality of non-uniform FDM-NLFM signal parameters to obtain target non-uniform FDM-NLFM signal parameters for cable external damage detection.

[0012] In a second aspect, the present invention provides a cable external damage prevention system based on non-uniform FDM-NLFM, including:

[0013] A soil zoning sequence module, configured to receive soil detection information of a cable laying area, zone the laying soil, and sort it starting from the signal injection point in combination with the detection direction to obtain a soil zoning sequence;

[0014] A soil conductivity sequence module, configured to traverse the soil zoning sequence to perform mode statistics of historical sample soil conductivity to obtain a soil conductivity sequence;

[0015] A soil dielectric constant sequence module, configured to traverse the soil zoning result to perform mode statistics of historical sample dielectric constants to obtain a soil dielectric constant sequence;

[0016] A power attenuation and phase distortion coefficient module, configured to randomly generate a plurality of non-uniform FDM-NLFM signal parameters, perform signal propagation simulation in combination with the soil conductivity sequence and the soil dielectric constant sequence to obtain a plurality of power attenuation coefficients and a plurality of phase distortion coefficients;

[0017] A cable external damage detection module, configured to perform optimization on the plurality of non-uniform FDM-NLFM signal parameters according to the plurality of power attenuation coefficients and the plurality of phase distortion coefficients to obtain target non-uniform FDM-NLFM signal parameters for cable external damage detection.

[0018] The beneficial effects of the present invention are as follows: Compared with the traditional method of detecting the injected non-uniform FDM-NLFM composite signal and then analyzing the cable status based on the reflected signal, this method is greatly affected by regional differences. By introducing an optimization fitness function, the present invention can comprehensively consider the effects of power attenuation and phase distortion on signal propagation. The fitness function not only considers the power attenuation coefficient and the phase distortion coefficient, but also introduces the population update times and the update influence adjustment factor, making the optimization process of signal parameters more dynamic and adaptable. This optimization method that comprehensively considers various factors significantly improves the adaptability of the signal in different soil environments, ensuring that the signal can propagate stably in complex underground environments; further, by optimizing the non-uniform FDM-NLFM signal parameters, the present invention enables the signal to better resist the influence brought by changes in soil characteristics during the propagation process. By selecting the signal parameters with the smallest fitness value, it is possible to ensure that the signal has the smallest attenuation and distortion during propagation, thereby improving the accuracy of detection results; furthermore, through guided mutation and cyclic optimization, the present invention can continuously adjust the signal parameters to gradually approach the optimal solution. Through multiple cycles of optimization, the finally obtained signal parameters can maintain stable propagation characteristics in different soil partitions, reducing the uncertainty during signal propagation, thereby achieving the technical effects of improving efficiency and taking into account the implementation cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 FIG. is a schematic flow chart of a cable anti-external damage method based on non-uniform FDM-NLFM provided by the present invention;

[0020] Figure 2 FIG. is a schematic structural diagram of a cable anti-external damage system based on non-uniform FDM-NLFM provided by the present invention.

[0021] Reference numerals: soil partition sequence module 11, soil conductivity sequence module 12, soil dielectric constant sequence module 13, power attenuation and phase distortion coefficient module 14, cable anti-external damage detection module 15. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0023] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0024] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without the use of these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0025] Embodiment 1:

[0026] As Figure 1 shown, an embodiment of the present invention provides a method for preventing external damage to cables based on non-uniform FDM-NLFM. The execution steps include:

[0027] S10: Receive the soil detection information of the cable laying area, partition the laying soil, and sort it starting from the signal injection point in combination with the detection direction to obtain a soil partition sequence;

[0028] Specifically, the soil detection information includes soil composition information, soil temperature information, and soil humidity information, which are obtained through sensors or on-site detection and are used to reflect the physical and chemical properties of the soil in the cable laying area.

[0029] Furthermore, multi-level hierarchical clustering analysis is a data mining method that gradually clusters similar samples by calculating the similarity or distance between samples. Multi-level hierarchical clustering analysis refers to clustering at multiple levels, first performing rough clustering and then more detailed clustering within each rough cluster. The soil partition set is a set of several soil partitions obtained through clustering analysis, and the soil properties (composition, temperature and humidity) within each partition are relatively consistent. Soil partition sequence: The sequence obtained by sorting the soil partition set starting from the signal injection point in combination with the detection direction, which is used for subsequent signal propagation simulation and optimization.

[0030] Details are as follows:

[0031] Further, according to the soil detection information of the receiving cable laying area, the laying soil is partitioned, and sorted starting from the signal injection point in combination with the detection direction to obtain a soil partition sequence. Performing step S10 includes:

[0032] S11: The soil detection information includes soil composition information, soil temperature information, and soil humidity information;

[0033] Exemplarily, assume that the cable laying area is a square area of 100 meters × 100 meters, the signal injection point is located at the lower left corner of the area (coordinates (0, 0)), and the detection direction is from left to right and from bottom to top. The soil detection information is collected through a sensor network, including soil composition (content percentage of component A), soil temperature (°C), and soil humidity (%RH).

[0034] Receive the soil detection information of the cable laying area. Within the cable laying area, collect the soil detection information through a sensor network. Assume that the sensors are distributed at the following points, and the collected data is shown in the following table:

[0035]

[0036] S12: Configure a soil composition deviation threshold, a soil temperature deviation threshold, and a soil humidity deviation threshold;

[0037] Further, configure a soil composition deviation threshold, a soil temperature deviation threshold, and a soil humidity deviation threshold. Performing step S12 includes:

[0038] S121: Extract the attributes to be analyzed from the soil composition information, soil temperature information, and soil humidity information;

[0039] S122: With the attribute to be analyzed as the only variable, set the non-attribute-to-be-analyzed set as a fixed quantity, and with conductivity and permittivity as following variables, collect the set of recorded values of the attribute to be analyzed, the set of recorded values of conductivity, and the set of recorded values of permittivity;

[0040] S123: Perform pairwise fluctuation calculations on the set of recorded values of the attribute to be analyzed, the set of recorded values of conductivity, and the set of recorded values of permittivity to obtain a set of deviations of the recorded values of the attribute to be analyzed, a set of deviations of the recorded values of conductivity, and a set of deviations of the recorded values of permittivity;

[0041] S124: Based on the set of recorded value deviations of conductivity, screen out from the set of recorded value deviations of the attribute to be analyzed a first selected set of recorded value deviations of the attribute to be analyzed where the recorded value deviation of conductivity is greater than or equal to the conductivity deviation threshold;

[0042] S125: Based on the set of dielectric constant recorded value deviations, screen from the set of recorded value deviations of the attribute to be analyzed a first selected set of recorded value deviations of the attribute to be analyzed where the dielectric constant recorded value deviation is greater than or equal to the dielectric constant deviation threshold.

[0043] S126: After performing outlier deletion on the first selected set of recorded value deviations of the attribute to be analyzed and the first selected set of recorded value deviations of the attribute to be analyzed respectively, extract the minimum value of the first remaining recorded value deviation of the attribute to be analyzed and the second remaining recorded value deviation of the attribute to be analyzed, set it as the deviation threshold of the attribute to be analyzed, and add it to the soil component deviation threshold, the soil temperature deviation threshold, and the soil humidity deviation threshold.

[0044] Exemplarily, extract the attribute to be analyzed from the collected soil detection information. Suppose we select soil component (content percentage of component A), soil temperature (°C), and soil humidity (%RH) as the attributes to be analyzed, and collect the corresponding conductivity and dielectric constant as follow-up variables at the same time. The collected data is shown in the following table:

[0045]

[0046] Taking the attribute to be analyzed as the only variable, fixing the non-attributes to be analyzed, collecting the set of recorded values. Taking the soil component as the attribute to be analyzed, setting the soil temperature and humidity as fixed quantities (for example, the soil temperature is 20 °C and the soil humidity is 60%RH), and collecting the corresponding set of recorded values of soil component, conductivity, and dielectric constant. The sorted data is shown in the following table:

[0047]

[0048] Perform pairwise fluctuation calculations to obtain the set of deviations. Fluctuation calculation:

[0049] Calculate the pairwise fluctuation deviations of soil component, conductivity, and dielectric constant. For example, calculate the deviation between point 1 and point 3 as follows:

[0050] Soil component deviation: |31 - 30| = 1%; Conductivity deviation: |11 - 10| = 1 mS / m; Dielectric constant deviation: |5.2 - 5| = 0.2.

[0051] Calculate the deviations between all points to obtain the following set of deviations: Soil component deviation set: {1%, 1%, 0%}; Conductivity deviation set: {1 mS / m, 1 mS / m, 0 mS / m}; Dielectric constant deviation set: {0.2, 0.2, 0.0}.

[0052] Screen the recorded values with a screening deviation greater than or equal to the threshold. Assume that the threshold for conductivity deviation is 1 mS / m and the threshold for dielectric constant deviation is 0.2. Screen the recorded values with conductivity and dielectric constant deviations greater than or equal to the threshold:

[0053] Set of recorded values with conductivity recorded value deviation greater than or equal to 1 mS / m: {1 mS / m, 1 mS / m};

[0054] Set of recorded values with dielectric constant recorded value deviation greater than or equal to 0.2: {0.2, 0.2};

[0055] Corresponding set of soil component recorded value deviations: Selected set of first attribute to be analyzed recorded value deviations: {1%, 1%}.

[0056] Delete outliers and extract the minimum value as the deviation threshold. Perform outlier deletion on the screened set of recorded values. Assume there are no outliers and directly extract the minimum value as the deviation threshold:

[0057] Soil component deviation threshold: 1%; Soil temperature deviation threshold: 2°C (assumed to be preset); Soil humidity deviation threshold: 2%RH (assumed to be preset).

[0058] Automatically configure the deviation threshold. To achieve automatic configuration of the deviation threshold, the following methods can be used:

[0059] Data fitting and regression analysis: Use a multiple linear regression model to analyze the relationships between soil components, temperature, humidity, conductivity, and dielectric constant. According to the research in the literature, factors such as soil moisture content, soil bulk density, soil temperature, and soil salt content have significant effects on soil dielectric properties. Similar regression models can be established to determine the influence degrees of various factors on conductivity and dielectric constant.

[0060] Threshold determination based on fluctuation analysis: Determine the influence of the minimum deviation value of each attribute on conductivity and dielectric constant through fluctuation calculation. For example, according to the research in the literature, the changes in soil conductivity and dielectric constant are closely related to the changes in soil components, humidity, and temperature. A fluctuation range can be set, and when the attribute deviation exceeds this range, the changes in conductivity or dielectric constant are significant.

[0061] Automated threshold calculation: Calculate the minimum deviation threshold of each attribute based on the results of fluctuation analysis. For example, if the minimum deviation of soil components is 1% when the conductivity change is significant, then set the soil component deviation threshold to 1%. Similarly, set the corresponding deviation thresholds according to the fluctuation analysis results of soil temperature and humidity.

[0062] Through the above steps, we obtained the following deviation thresholds: soil composition deviation threshold: 1%; soil temperature deviation threshold: 2°C; soil humidity deviation threshold: 2%RH.

[0063] Through the above embodiments, it is possible to achieve automatic configuration of the deviation thresholds of soil composition, temperature, and humidity. The setting of these thresholds is based on the actually collected data, and through fluctuation calculation and screening, their rationality and effectiveness are ensured. The finally obtained deviation thresholds will provide a scientific basis for soil zoning, thereby improving the accuracy and reliability of cable external damage detection.

[0064] S13: According to the soil composition deviation threshold, the soil temperature deviation threshold, and the soil humidity deviation threshold of the soil, combined with the soil composition information, the soil temperature information, and the soil humidity information, perform multi-level hierarchical clustering analysis to obtain a set of soil zones, where the soil composition, soil temperature, and humidity of any one zone are consistent.

[0065] Further, perform multi-level hierarchical clustering analysis according to the thresholds obtained from the above embodiments, as follows:

[0066] Calculate the similarity between points:

[0067] Use the Euclidean distance or other similarity measurement methods to calculate the similarity between each pair of points. The similarity calculation formula is:

[0068]

[0069] where x, y, and z respectively represent the normalized values of soil composition, temperature, and humidity, and D1 represents the distance.

[0070] Initialize clustering: Initialize each point as a separate cluster.

[0071] Merge the most similar clusters: In each step, find the two most similar clusters and merge them until all points are merged into one cluster.

[0072] Apply the deviation threshold: During the merging process, check whether the merged cluster meets the deviation threshold. If the deviation of the points within a certain cluster in a certain attribute exceeds the threshold, stop merging that cluster.

[0073] Exemplarily, according to the thresholds obtained from the above embodiments: soil composition deviation threshold: 1%; soil temperature deviation threshold: 2°C; soil humidity deviation threshold: 2%RH, perform multi-level hierarchical clustering analysis, as follows:

[0074] Calculate the distance between points:

[0075] For example, the distance between point 1 and point 2 is calculated as follows:

[0076]

[0077] Initialize clustering, with each point as a separate cluster:

[0078] Cluster 1: {1}; Cluster 2: {2}; Cluster 3: {3}; Cluster 4: {4}; Cluster 5: {5}; Cluster 6: {6}; Cluster 7: {7}; Cluster 8: {8}; Cluster 9: {9}.

[0079] Merge the most similar clusters:

[0080] Find the two closest clusters and merge them. For example, the distance between point 1 and point 3 is:

[0081]

[0082] Merge Cluster 1 and Cluster 3: Cluster 1: {1, 3}, and continue to merge other clusters until all points are merged into one cluster.

[0083] Apply the deviation threshold to check whether the deviation of the point attributes within each cluster exceeds the threshold. For example, check point 1 and point 3 in Cluster 1:

[0084] Soil composition deviation: |31 - 30| = 1% (less than the threshold of 1%); Soil temperature deviation: |20 - 20| = 0°C (less than the threshold of 2°C); Soil humidity deviation: |61 - 60| = 1%RH (less than the threshold of 2%RH).

[0085] Since all deviations are less than the threshold, Cluster 1 can continue to merge other points.

[0086] After multi-level hierarchical clustering analysis, the following partition sets are finally obtained:

[0087] Partition 1: Contains point 1, point 3, point 8; Partition 2: Contains point 2, point 6, point 9; Partition 3: Contains point 4, point 5, point 7.

[0088] S14: Sort the soil partition set starting from the signal injection point in combination with the detection direction to obtain a soil partition sequence.

[0089] Exemplarily, in order to more accurately describe the soil characteristics of each partition, the average soil composition, temperature, and humidity within each partition will be calculated based on the data point coordinates and soil characteristics collected in the above embodiments. The calculation formula is the average value of the corresponding soil composition data within each partition. The following are the soil composition calculation results for each partition:

[0090] Partition 1: Contains point 1, point 3, point 8.

[0091] Average soil composition: (30 + 31 + 30) / 3 = 30.33%; average soil temperature: (20 + 20 + 20) / 3 = 20°C; average soil humidity: (60 + 61 + 60) / 3 = 60.33%RH.

[0092] Similarly, for Zone 2: it includes Point 2, Point 6, and Point 9.

[0093] Average soil composition: 32%; average soil temperature: 21.33°C; average soil humidity: 62%RH.

[0094] Zone 3: it includes Point 4, Point 5, and Point 7.

[0095] Average soil composition: 31.33%; average soil temperature: 22°C; average soil humidity: 62.67%RH.

[0096] According to the above-refined soil characteristics, assign a number to each zone to more clearly represent the soil characteristics of each zone, as follows:

[0097] According to the signal injection point (0, 0) and the detection direction (from left to right, from bottom to top), sort the zones. The sorted zone sequence is: Zone 1, Zone 3, Zone 2.

[0098] The sorted zone results are shown in the following table:

[0099]

[0100] The soil zone sequence obtained in the above manner can accurately reflect the differences in soil characteristics at different positions in the cable laying area, providing a zoning model that highly matches the actual scenario for subsequent signal propagation simulation, thereby improving the accuracy and reliability of signal propagation simulation.

[0101] S20: Traverse the soil zone sequence to perform the mode statistics of the historical sample soil conductivity, and obtain the soil conductivity sequence.

[0102] Further, according to traversing the soil zone sequence to perform the mode statistics of the historical sample soil conductivity and obtaining the soil conductivity sequence, the execution of step S20 includes:

[0103] S21: According to the soil zone sequence, extract the first soil zone, where the first soil zone has a soil composition identifier, a soil temperature identifier, and a soil humidity identifier;

[0104] S22: According to the soil composition identifier, the soil temperature identifier, and the soil humidity identifier, construct the first index constraint rule;

[0105] S23: Retrieve the first set of detected soil conductivity values for the first set of historical samples that meet the first index constraint rule, where the first set of historical samples has a set of soil composition labels, a set of soil temperature labels, and a set of soil humidity labels;

[0106] S24: Construct a second set of index constraint rules based on the set of soil composition labels, the set of soil temperature labels, and the set of soil humidity labels, and respectively retrieve multiple sets of second detected soil conductivity values for multiple sets of second historical samples that meet the second set of index constraint rules;

[0107] S25: Perform mode aggregation on the first set of detected soil conductivity values and the multiple sets of second detected soil conductivity values to obtain the first partition soil conductivity, and add it to the soil conductivity sequence.

[0108] Exemplarily, according to the set of soil partitions obtained by the multi-level hierarchical clustering analysis in the above embodiment, and which has been sorted according to the signal injection point and the detection direction, process each partition in turn according to the sorted soil partition sequence:

[0109] Process partition 1 and extract the first soil partition:

[0110] Partition 1: Contains point 1, point 3, and point 8; soil composition identifier: 30.33%; soil temperature identifier: 20°C; soil humidity identifier: 60.33%RH.

[0111] Construct the first index constraint rule: Soil composition identifier: 30.33%; soil temperature identifier: 20°C; soil humidity identifier: 60.33%RH.

[0112] Retrieve the first set of detected soil conductivity values for the first set of historical samples: Retrieve the set of historical samples and find the historical samples that meet the above index constraint rule.

[0113] Suppose the set of historical samples is as follows: Sample 1: Soil composition 30%, temperature 20°C, humidity 60%RH, conductivity 10 mS / m; Sample 2: Soil composition 31%, temperature 20°C, humidity 61%RH, conductivity 11 mS / m; Sample 3: Soil composition 30%, temperature 20°C, humidity 60%RH, conductivity 10 mS / m.

[0114] The first set of detected soil conductivity values: {10, 11, 10}.

[0115] Construct the second set of index constraint rules: Construct the second set of index constraint rules based on the set of soil composition labels, the set of soil temperature labels, and the set of soil humidity labels.

[0116] Suppose the second index constraint rule set is as follows: Rule 1: soil composition 30%, temperature 20°C, humidity 60%RH; Rule 2: soil composition 31%, temperature 20°C, humidity 61%RH.

[0117] Retrieve multiple sets of second soil conductivity detection values for multiple sets of second historical samples:

[0118] Retrieve historical samples that meet Rule 1: Sample 4: soil composition 30%, temperature 20°C, humidity 60%RH, conductivity 10 mS / m; Sample 5: soil composition 30%, temperature 20°C, humidity 60%RH, conductivity 10 mS / m.

[0119] Second soil conductivity detection value set 1: {10, 10}.

[0120] Retrieve historical samples that meet Rule 2: Sample 6: soil composition 31%, temperature 20°C, humidity 61%RH, conductivity 11 mS / m; Sample 7: soil composition 31%, temperature 20°C, humidity 61%RH, conductivity 11 mS / m.

[0121] Second soil conductivity detection value set 2: {11, 11}.

[0122] Perform mode aggregation to combine the first soil conductivity detection value set and multiple sets of second soil conductivity detection values:

[0123] Combined conductivity set: {10, 11, 10, 10, 10, 11, 11}; Calculate the mode: The mode is 10 mS / m (appears most frequently).

[0124] Add to the soil conductivity sequence: First partition soil conductivity: 10 mS / m; Soil conductivity sequence:

[10] .

[0125] Repeat the above steps to process partition 2:

[0126] Partition 2: Contains point 2, point 6, point 9; Soil composition identifier: 32%; Soil temperature identifier: 21.33°C; Soil humidity identifier: 62%RH.

[0127] Suppose the historical sample set is as follows: Sample 8: soil composition 32%, temperature 21°C, humidity 62%RH, conductivity 12 mS / m; Sample 9: soil composition 32%, temperature 22°C, humidity 62%RH, conductivity 12 mS / m; Sample 10: soil composition 32%, temperature 21°C, humidity 62%RH, conductivity 12 mS / m.

[0128] After mode aggregation, the soil conductivity of partition 2 is 12 mS / m; Soil conductivity sequence: [10, 12].

[0129] Repeat the above steps to process partition 3:

[0130] Partition 3: contains point 4, point 5, and point 7; Soil component identification: 31.33%; Soil temperature identification: 22°C; Soil humidity identification: 62.67%RH.

[0131] Suppose the historical sample set is as follows: Sample 11: Soil component 31%, temperature 22°C, humidity 63%RH, conductivity 11 mS / m; Sample 12: Soil component 33%, temperature 23°C, humidity 64%RH, conductivity 13 mS / m; Sample 13: Soil component 31%, temperature 21°C, humidity 61%RH, conductivity 11 mS / m.

[0132] After mode aggregation, the soil conductivity of partition 3 is 11 mS / m; Soil conductivity sequence: [10, 12, 11].

[0133] Through the above steps, the soil partition sequence is successfully traversed, and the mode statistics of the historical sample soil conductivity are carried out, and finally the soil conductivity sequence is obtained. The results are shown in the following table:

[0134]

[0135] S30: Traverse the soil partition results to perform mode statistics on the historical sample dielectric constant to obtain the soil dielectric constant sequence;

[0136] Furthermore, the method of traversing the soil partition results to perform mode statistics on the historical sample dielectric constant to obtain the soil dielectric constant sequence executes step S20, and the results are shown in the following table:

[0137]

[0138] Through the above steps, the soil partition sequence is traversed, and the mode statistics of the historical sample soil conductivity are carried out to obtain the soil conductivity sequence. This method can ensure that the soil conductivity and dielectric constant of each partition are representative, providing more accurate basic data for subsequent signal propagation simulation and cable anti-external break detection.

[0139] S40: Randomly generate several non-uniform FDM-NLFM signal parameters, and perform signal propagation simulation by combining the soil conductivity sequence and the soil dielectric constant sequence to obtain several power attenuation coefficients and several phase distortion coefficients;

[0140] Further, several non-uniform FDM-NLFM signal parameters are randomly generated, and signal propagation simulation is performed by combining the soil conductivity sequence and the soil dielectric constant sequence to obtain several power attenuation coefficients and several phase distortion coefficients. Performing step S40 includes:

[0141] S41: Any one of the several non-uniform FDM-NLFM signal parameters includes an FDM frequency band parameter set, an FDM propagation frequency parameter, an FDM propagation power set, an NLFM propagation frequency curve, and an NLFM propagation power parameter;

[0142] Specifically, the FDM (Frequency Division Multiplexing) frequency band parameter set refers to the frequency ranges of each sub-carrier in the frequency division multiplexing signal, and these frequency ranges determine the distribution of the signal in the frequency domain; the FDM propagation frequency parameter refers to the center frequency of each sub-carrier in the frequency division multiplexing signal, and these center frequencies are used to define the frequency position of the signal; the FDM propagation power set refers to the propagation power of each sub-carrier in the frequency division multiplexing signal, and these power values determine the energy distribution of the signal at different frequencies; the NLFM (Non-Linear Frequency Modulation) propagation frequency curve refers to the curve of the frequency of the non-linear frequency modulation signal changing with time, and this curve defines the frequency modulation characteristics of the signal; the NLFM propagation power parameter refers to the propagation power of the non-linear frequency modulation signal, and this parameter determines the overall energy level of the signal.

[0143] S42: According to the FDM frequency band parameter set, the FDM propagation frequency parameter, the FDM propagation power set, the NLFM propagation frequency curve, and the NLFM propagation power parameter, combined with the soil conductivity sequence and the soil dielectric constant sequence, perform unit-distance signal propagation simulation to obtain a unit-distance power attenuation rate sequence and a unit-distance phase distortion rate sequence;

[0144] Further, according to the FDM frequency band parameter set, the FDM propagation frequency parameter, the FDM propagation power set, the NLFM propagation frequency curve, and the NLFM propagation power parameter, combined with the soil conductivity sequence and the soil dielectric constant sequence, perform unit-distance signal propagation simulation to obtain a unit-distance power attenuation rate sequence and a unit-distance phase distortion rate sequence. Performing step S42 includes:

[0145] S421: Configure the FDM frequency band parameter set record data, FDM propagation frequency parameter record data, FDM propagation power set record data, NLFM propagation frequency curve record data, NLFM propagation power parameter record data, unit distance power attenuation rate identification data, and unit distance phase distortion rate identification data;

[0146] S422: Using the unit distance power attenuation rate identification data as supervision, and using the FDM frequency band parameter set record data, FDM propagation frequency parameter record data, FDM propagation power set record data, NLFM propagation frequency curve record data, and NLFM propagation power parameter record data as inputs, train the first BP neural network to obtain a unit distance power attenuation rate simulation channel.

[0147] Specifically, the BP neural network training model is a multi-layer feedforward neural network, which is trained through the backpropagation algorithm. The steps are as follows:

[0148] Initialize the network structure and determine the network structure.

[0149] Number of input layer nodes: determined according to the number of features of the input data; Number of hidden layer nodes: select an appropriate number of nodes according to the problem complexity; Number of output layer nodes: determined according to the number of features of the output data.

[0150] Initialize the weights and biases. Weights: usually randomly initialized to small non-zero values to avoid all neurons having the same output; Biases: usually initialized to 0 or small non-zero values.

[0151] Forward propagation, input data: Pass the input data X to the input layer; Calculate the output of the hidden layer: For each hidden layer node j, calculate its input zj: .

[0152] Apply the activation function σ (such as Sigmoid, ReLU, etc.): .

[0153] Calculate the output of the output layer: For each output layer node k, calculate its input zk: , and apply the activation function σ (such as Sigmoid, ReLU, etc.): .

[0154] Calculate the loss function. Commonly used loss functions include mean squared error MSE and cross-entropy loss Cross-Entropy.

[0155] Mean squared error:

[0156] Cross-entropy loss:

[0157] The output of the forward propagation is compared with the true value y to calculate the loss value, where N represents the training samples.

[0158] Backpropagation is performed, and then when the loss value is greater than the loss threshold, the weights of the model parameters are adjusted;

[0159] Iterative training: Repeat the processes of forward propagation, loss calculation, backpropagation, and weight update until the loss value converges or converges when reaching the preset number of iterations, to obtain the simulated channel of the power attenuation rate per unit distance.

[0160] Through the above model training, the BP neural network can learn the complex relationship between the input data and the output data, so as to accurately predict the signal propagation characteristics. This method performs excellently in dealing with complex non-linear problems and is applicable to signal propagation simulation in cable anti-external damage detection.

[0161] S423: Using the data of the per-unit-distance phase distortion rate identification as supervision, and using the data recorded by the FDM frequency band parameter set, the FDM propagation frequency parameter data, the FDM propagation power set data, the NLFM propagation frequency curve data, and the NLFM propagation power parameter data as inputs, train the second BP neural network to obtain the simulated channel of the per-unit-distance phase distortion rate;

[0162] S424: Merge the input layers of the simulated channel of the per-unit-distance power attenuation rate and the simulated channel of the per-unit-distance phase distortion rate to generate a per-unit-distance signal propagation simulation function, perform per-unit-distance signal propagation simulation, and obtain a per-unit-distance power attenuation rate sequence and a per-unit-distance phase distortion rate sequence.

[0163] Exemplarily, use the previously obtained soil conductivity sequence and soil dielectric constant sequence:

[0164] Soil conductivity sequence: [10, 12, 11] mS / m; Soil dielectric constant sequence: [5.0, 5.5, 5.3].

[0165] Configure the signal parameter recording data, and randomly generate a number of non-uniform FDM-NLFM signal parameters, each parameter including:

[0166] FDM frequency band parameter set; FDM propagation frequency parameter; FDM propagation power set; NLFM propagation frequency curve; NLFM propagation power parameter.

[0167] Suppose 3 groups of non-uniform FDM-NLFM signal parameters are randomly generated, specifically as follows:

[0168]

[0169] Configure the following data for BP neural network training:

[0170] Data set records of FDM frequency band parameters; Data records of FDM propagation frequency parameters; Data set records of FDM propagation power; NLFM propagation frequency curve records; Data records of NLFM propagation power parameters; Identification data of power attenuation rate per unit distance; Identification data of phase distortion rate per unit distance. Assume the historical data is as shown in the following table:

[0171]

[0172] Train the first BP neural network (power attenuation rate), input data: Data set of FDM frequency band parameters; FDM propagation frequency parameters; Data set of FDM propagation power; NLFM propagation frequency curve; NLFM propagation power parameters.

[0173] Output data: Power attenuation rate per unit distance; Training process: Use historical data to train the first BP neural network to predict the power attenuation rate per unit distance.

[0174] Train the second BP neural network (power attenuation rate), input data: Data set of FDM frequency band parameters; FDM propagation frequency parameters; Data set of FDM propagation power; NLFM propagation frequency curve; NLFM propagation power parameters.

[0175] Output data: Power attenuation rate per unit distance; Training process: Use historical data to train the second BP neural network to predict the power attenuation rate per unit distance.

[0176] Generate a simulation function for signal propagation per unit distance, merge the input layer: Merge the input layers of the first BP neural network and the second BP neural network to generate a simulation function for signal propagation per unit distance.

[0177] Conduct a simulation of signal propagation per unit distance: Use the generated simulation function, combined with the soil conductivity sequence and the soil dielectric constant sequence, to conduct a simulation of signal propagation per unit distance to obtain the power attenuation rate sequence per unit distance and the phase distortion rate sequence per unit distance.

[0178] Assume the simulation results are as shown in the following table:

[0179]

[0180] Through the above steps, a simulation of signal propagation per unit distance is carried out using the BP neural network, and the power attenuation rate sequence per unit distance and the phase distortion rate sequence per unit distance are obtained. This method can effectively consider the complex relationship between soil characteristics and signal parameters, providing more accurate basic data for subsequent signal propagation simulation and cable anti-external damage detection.

[0181] S43: obtaining a propagation distance sequence according to the soil partition sequence, and accumulating and calculating the unit distance power attenuation rate sequence and the unit distance phase distortion rate sequence respectively to obtain a first power attenuation coefficient and a first phase distortion coefficient;

[0182] Furthermore, according to the soil partition sequence, a propagation distance sequence is obtained, and the unit distance power attenuation rate sequence and the unit distance phase distortion rate sequence are accumulated and calculated respectively to obtain a first power attenuation coefficient and a first phase distortion coefficient.

[0183] For example, partition 1 accumulates the calculation results:

[0184] The first power attenuation coefficient: 0.1×10+0.2×20+0.15×15=1+4+2.25=7.25 dB; the first phase distortion coefficient: 0.01×10+0.02×20+0.015×15=0.1+0.4+0.225=0.725 rad.

[0185] Cumulative calculation results for partition 2:

[0186] The first power attenuation coefficient: 0.12×10+0.22×20+0.17×15=1.2+4.4+2.55=8.15 dB; the first phase distortion coefficient: 0.012×10+0.022×20+0.017×15=0.12+0.44+0.255=0.815 rad.

[0187] Cumulative calculation results of partition 3:

[0188] The first power attenuation coefficient: 0.11×10+0.21×20+0.16×15=1.1+4.2+2.4=7.7 dB; the first phase distortion coefficient: 0.011×10+0.021×20+0.016×15=0.11+0.42+0.24=0.77 rad.

[0189] Sum up the first power attenuation coefficient and the first phase distortion coefficient of all signal parameters:

[0190]

[0191] S44: Add the first power attenuation coefficient into the plurality of power attenuation coefficients, and add the first phase distortion coefficient into the plurality of phase distortion coefficients.

[0192] Furthermore, a power attenuation coefficient set is added: AttenuationCoefficients=[]; a phase distortion coefficient set is added: PhaseDistortionCoefficients=[].

[0193] Add the first power attenuation coefficient and the first phase distortion coefficient of each partition to the corresponding sets respectively.

[0194] Add the coefficients of partition 1. Power attenuation coefficient set: AttenuationCoefficients = [7.25]; Phase distortion coefficient set: PhaseDistortionCoefficients = [0.725].

[0195] Add the coefficients of partition 2. Power attenuation coefficient set: AttenuationCoefficients = [7.25, 8.15]; Phase distortion coefficient set: PhaseDistortionCoefficients = [0.725, 0.815].

[0196] Add the coefficients of partition 3. Power attenuation coefficient set: AttenuationCoefficients = [7.25, 8.15, 7.7]; Phase distortion coefficient set: PhaseDistortionCoefficients = [0.725, 0.815, 0.77].

[0197] Specifically, through the above steps, the first power attenuation coefficient and the first phase distortion coefficient of each partition are added to the corresponding sets respectively. These sets summarize the signal propagation characteristics of all partitions, providing comprehensive data support for subsequent signal optimization and cable external break detection.

[0198] S50: Based on the several power attenuation coefficients and the several phase distortion coefficients, perform optimization on the several non-uniform FDM-NLFM signal parameters to obtain target non-uniform FDM-NLFM signal parameters for cable external break detection;

[0199] Furthermore, according to performing optimization on the several non-uniform FDM-NLFM signal parameters based on the several power attenuation coefficients and the several phase distortion coefficients to obtain target non-uniform FDM-NLFM signal parameters for cable external break detection, the implementation of step S50 includes:

[0200] S51: Construct an optimization fitness function:

[0201] , where represents the fitness value, and represent the weight parameters, represents the predicted power attenuation coefficient, represents the predicted phase distortion coefficient, represents the number of population update times, Characterize the update impact regulator, >0, where e represents the natural constant, Characterize the power attenuation coefficient, Characterize the phase distortion coefficient threshold;

[0202] S52: According to the optimization fitness function, based on the plurality of power attenuation coefficients and the plurality of phase distortion coefficients, obtain a plurality of fitness evaluation values for the plurality of non-uniform FDM-NLFM signal parameters;

[0203] S53: Based on the plurality of fitness evaluation values from smallest to largest, select the top three non-uniform FDM-NLFM signal parameters from the plurality of non-uniform FDM-NLFM signal parameters;

[0204] S54: Calculate the mean value of the quantization signal parameters of the top three non-uniform FDM-NLFM signal parameters, and take the union of the type signal parameters to obtain the target signal parameters;

[0205] S55: Using the target signal parameters as the guiding target, perform guiding mutation on the plurality of non-uniform FDM-NLFM signal parameters to obtain updated non-uniform FDM-NLFM signal parameters and execute a loop, where the mutation rules are reduction mutation of the quantization parameter distance and crossover mutation of the type parameters;

[0206] S56: Until non-uniform FDM-NLFM signal parameters with a fitness value less than or equal to the convergence threshold are obtained, and set them as the target non-uniform FDM-NLFM signal parameters.

[0207] In the embodiments of the present application, preferably, use the optimization fitness function to obtain the fitness evaluation value. The fitness function evaluation value increases as the power attenuation coefficient and the phase distortion coefficient increase, and decreases as the power attenuation coefficient and the phase distortion coefficient are continuously iterated. The closer it is to the preferred value, the smaller the fitness value, indicating that the attenuation and distortion of the signal parameters during propagation are smaller, and the higher the signal quality. In order to test convergence, a convergence value is set, and this convergence value is set according to actual use. The specific steps are as follows:

[0208] Select the first three non-uniform FDM-NLFM signal parameters as the preferred parameters, which are more likely to guide inferior parameters. For the selected first three non-uniform FDM-NLFM signal parameters, further processing is performed to obtain the target signal parameters: calculate the mean value of the quantization signal parameters (such as the propagation power set) to obtain a comprehensive quantization parameter value; take the union of the type signal parameters (such as the frequency band parameter set) to obtain a comprehensive type parameter set.

[0209] Further, using the target signal parameters as the guiding target, perform guided mutation on all non-uniform FDM-NLFM signal parameters:

[0210] Quantization parameter distance reduction mutation: Adjust the quantization parameters to make them closer to the quantization parameters of the target signal parameters, reducing the distance from the target parameters; Type parameter crossover mutation: Through crossover operations, combine the type parameters of the target signal parameters with the type parameters of other signal parameters to generate a new set of type parameters.

[0211] Furthermore, repeat the above process for multiple cycles of optimization until non-uniform FDM-NLFM signal parameters with a fitness value less than or equal to the convergence threshold are obtained. This convergence threshold is a preset value used to determine whether the optimization process has reached a satisfactory level. Once the fitness value of a certain signal parameter reaches or is below this threshold, the parameter is considered the target non-uniform FDM-NLFM signal parameter.

[0212] Through the above optimization process, the signal parameters most suitable for cable external break detection are found from multiple non-uniform FDM-NLFM signal parameters. This method comprehensively considers the attenuation and distortion of the signal during propagation. Through dynamic adjustment and optimization, it ensures the optimality of the signal parameters, thereby improving the accuracy and reliability of cable external break detection.

[0213] A cable external break prevention method based on non-uniform FDM-NLFM provided by an embodiment of the present invention has at least the following technical effects:

[0214] By introducing an optimization fitness function, the present invention can comprehensively consider the effects of power attenuation and phase distortion on signal propagation. The fitness function not only considers the power attenuation coefficient and phase distortion coefficient, but also introduces the population update times and update influence adjustment factors, making the optimization process of signal parameters more dynamic and adaptable. This optimization method that comprehensively considers multiple factors significantly improves the adaptability of the signal in different soil environments, ensuring that the signal can propagate stably in a complex underground environment; Further, by optimizing the non-uniform FDM-NLFM signal parameters, the present invention enables the signal to better resist the influence brought by changes in soil characteristics during propagation. By selecting the signal parameters with the smallest fitness value, it can ensure that the signal has the smallest attenuation and distortion during propagation, thereby improving the accuracy of the detection results; Furthermore, through guided mutation and cyclic optimization, the present invention can continuously adjust the signal parameters to gradually approach the optimal solution. Through multiple cycles of optimization, the finally obtained signal parameters can maintain stable propagation characteristics in different soil zones, reducing the uncertainty during signal propagation, thereby achieving the technical effects of improving efficiency and taking into account the implementation cost.

[0215] Embodiment 2, as Figure 2As shown, based on the same inventive concept as the cable anti-external damage method based on non-uniform FDM-NLFM provided in Embodiment 1, an embodiment of the present invention further provides a cable anti-external damage system based on non-uniform FDM-NLFM, including:

[0216] A soil zoning sequence module 11, configured to receive soil detection information of a cable laying area, zone the laying soil, and sort it starting from a signal injection point in combination with a detection direction to obtain a soil zoning sequence;

[0217] A soil conductivity sequence module 12, configured to traverse the soil zoning sequence to perform a mode statistics of historical sample soil conductivity to obtain a soil conductivity sequence;

[0218] A soil dielectric constant sequence module 13, configured to traverse the soil zoning result to perform a mode statistics of historical sample dielectric constants to obtain a soil dielectric constant sequence;

[0219] A power attenuation and phase distortion coefficient module 14, configured to randomly generate a plurality of non-uniform FDM-NLFM signal parameters, perform signal propagation simulation in combination with the soil conductivity sequence and the soil dielectric constant sequence to obtain a plurality of power attenuation coefficients and a plurality of phase distortion coefficients;

[0220] A cable anti-external damage detection module 15, configured to perform optimization on the plurality of non-uniform FDM-NLFM signal parameters according to the plurality of power attenuation coefficients and the plurality of phase distortion coefficients to obtain target non-uniform FDM-NLFM signal parameters for cable anti-external damage detection.

[0221] Further, the steps executed by the soil zoning sequence module 11 include:

[0222] The soil detection information includes soil composition information, soil temperature information, and soil humidity information;

[0223] Configure a soil composition deviation threshold, a soil temperature deviation threshold, and a soil humidity deviation threshold;

[0224] According to the soil composition deviation threshold, the soil temperature deviation threshold, and the soil humidity deviation threshold, perform multi-level hierarchical clustering analysis in combination with the soil composition information, the soil temperature information, and the soil humidity information to obtain a soil zoning set, where the soil composition, soil temperature, and humidity of any one zone are consistent;

[0225] Sort the soil zoning set starting from the signal injection point in combination with the detection direction to obtain a soil zoning sequence.

[0226] Further, the steps executed by the soil zoning sequence module 11 further include:

[0227] Extract the attributes to be analyzed from the soil composition information, soil temperature information, and soil humidity information;

[0228] Taking the attribute to be analyzed as the only variable, setting the non-attributes-to-be-analyzed set as a fixed quantity, and taking the conductivity and dielectric constant as following variables, collect the set of recorded values of the attribute to be analyzed, the set of recorded values of conductivity, and the set of recorded values of dielectric constant;

[0229] Perform pairwise fluctuation calculations on the set of recorded values of the attribute to be analyzed, the set of recorded values of conductivity, and the set of recorded values of dielectric constant to obtain the set of deviations of the recorded values of the attribute to be analyzed, the set of deviations of the recorded values of conductivity, and the set of deviations of the recorded values of dielectric constant;

[0230] Based on the set of deviations of the recorded values of conductivity, screen from the set of deviations of the recorded values of the attribute to be analyzed the first selected set of deviations of the recorded values of the attribute to be analyzed where the deviation of the recorded value of conductivity is greater than or equal to the conductivity deviation threshold;

[0231] Based on the set of deviations of the recorded values of dielectric constant, screen from the set of deviations of the recorded values of the attribute to be analyzed the first selected set of deviations of the recorded values of the attribute to be analyzed where the deviation of the recorded value of dielectric constant is greater than or equal to the dielectric constant deviation threshold;

[0232] After performing outlier deletion on the first selected set of deviations of the recorded values of the attribute to be analyzed and the first selected set of deviations of the recorded values of the attribute to be analyzed respectively, extract the minimum value of the first retained deviation of the recorded values of the attribute to be analyzed and the second retained deviation of the recorded values of the attribute to be analyzed, set it as the deviation threshold of the attribute to be analyzed, and add it to the deviation threshold of soil composition, the deviation threshold of soil temperature, and the deviation threshold of soil humidity.

[0233] Further, the steps executed by the soil conductivity sequence module 12 include:

[0234] According to the soil partition sequence, extract the first soil partition, where the first soil partition has a soil composition identifier, a soil temperature identifier, and a soil humidity identifier;

[0235] Construct the first index constraint rule according to the soil composition identifier, the soil temperature identifier, and the soil humidity identifier;

[0236] Retrieve the first set of detected soil conductivity values of the first historical sample set that satisfies the first index constraint rule, where the first historical sample set has a set of soil composition labels, a set of soil temperature labels, and a set of soil humidity labels;

[0237] Construct a second index constraint rule set according to the soil composition label set, the soil temperature label set, and the soil moisture label set, and respectively retrieve multiple groups of second soil conductivity detection values of multiple groups of second historical samples that meet the second index constraint rule set;

[0238] Perform mode aggregation on the first soil conductivity detection value set and the multiple groups of second soil conductivity detection values to obtain the first partition soil conductivity, and add it to the soil conductivity sequence.

[0239] Furthermore, the execution steps of the soil dielectric constant sequence module 13 are the same as those of the soil conductivity sequence module 12.

[0240] Furthermore, the execution steps of the power attenuation and phase distortion coefficient module 14 include:

[0241] Any one of the several non-uniform FDM-NLFM signal parameters includes an FDM frequency band parameter set, an FDM propagation frequency parameter, an FDM propagation power set, an NLFM propagation frequency curve, and an NLFM propagation power parameter;

[0242] According to the FDM frequency band parameter set, the FDM propagation frequency parameter, the FDM propagation power set, the NLFM propagation frequency curve, and the NLFM propagation power parameter, combine the soil conductivity sequence and the soil dielectric constant sequence to perform unit distance signal propagation simulation, and obtain a unit distance power attenuation rate sequence and a unit distance phase distortion rate sequence;

[0243] According to the soil partition sequence, obtain a propagation distance sequence, and respectively perform cumulative calculations on the unit distance power attenuation rate sequence and the unit distance phase distortion rate sequence to obtain a first power attenuation coefficient and a first phase distortion coefficient;

[0244] Add the first power attenuation coefficient to the several power attenuation coefficients, and add the first phase distortion coefficient to the several phase distortion coefficients.

[0245] Furthermore, the execution steps of the power attenuation and phase distortion coefficient module 14 further include:

[0246] Configure the FDM frequency band parameter set record data, the FDM propagation frequency parameter record data, the FDM propagation power set record data, the NLFM propagation frequency curve record data, the NLFM propagation power parameter record data, the unit distance power attenuation rate identification data, and the unit distance phase distortion rate identification data;

[0247] Taking the data marked by the power attenuation rate per unit distance as supervision, and using the data recorded by the FDM frequency band parameter set, the FDM propagation frequency parameter record data, the FDM propagation power set record data, the NLFM propagation frequency curve record data, and the NLFM propagation power parameter record data as inputs, train the first BP neural network to obtain a power attenuation rate per unit distance simulation channel;

[0248] Taking the data marked by the phase distortion rate per unit distance as supervision, and using the data recorded by the FDM frequency band parameter set, the FDM propagation frequency parameter record data, the FDM propagation power set record data, the NLFM propagation frequency curve record data, and the NLFM propagation power parameter record data as inputs, train the second BP neural network to obtain a phase distortion rate per unit distance simulation channel;

[0249] Merge the input layers of the power attenuation rate per unit distance simulation channel and the phase distortion rate per unit distance simulation channel to generate a unit distance signal propagation simulation function, perform unit distance signal propagation simulation, and obtain a power attenuation rate sequence per unit distance and a phase distortion rate sequence per unit distance.

[0250] Further, the steps executed by the cable anti-external damage detection module 15 include:

[0251] Construct an optimization fitness function:

[0252] ,

[0253] Among them, represents the fitness value, and represents the weight parameter, represents the power prediction attenuation coefficient, represents the phase prediction distortion coefficient, represents the population update times, represents the update influence adjustment factor, >0, e represents the natural constant, represents the power attenuation coefficient, represents the phase distortion coefficient threshold;

[0254] According to the optimization fitness function, based on the several power attenuation coefficients and the several phase distortion coefficients, obtain several fitness evaluation values for the several non-uniform FDM-NLFM signal parameters;

[0255] Based on the several fitness evaluation values from small to large, select the top three non-uniform FDM-NLFM signal parameters from the several non-uniform FDM-NLFM signal parameters;

[0256] Calculate the mean of the quantized signal parameters of the first three non-uniform FDM-NLFM signal parameters, find the union of the type signal parameters, and obtain the target signal parameters;

[0257] Using the target signal parameters as the guiding target, perform guiding mutation on the several non-uniform FDM-NLFM signal parameters to obtain updated non-uniform FDM-NLFM signal parameters and execute a loop, where the mutation rules are reduction mutation of quantization parameter distance and crossover mutation of type parameters;

[0258] Until non-uniform FDM-NLFM signal parameters with a fitness value less than or equal to the convergence threshold are obtained, which are set as the target non-uniform FDM-NLFM signal parameters.

[0259] It should be noted that in the above embodiments, each embodiment description has its own focus. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0260] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0261] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0262] These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including instruction means, and the instruction means implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0263] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, causing a series of operational steps to be performed on the computer or other programmable apparatus to generate a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one process or a plurality of processes and / or blocks Figure 1 one process or a plurality of processes and / or blocks Figure 1 or steps for implementing the functions specified in one block or a plurality of blocks.

[0264] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made to these embodiments by those skilled in the art once they learn of the basic inventive concept.

[0265] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A cable anti-external damage method based on non-uniform FDM-NLFM, characterized in that, Including: Receiving soil detection information of the cable laying area, partitioning the laying soil, and sorting starting from the signal injection point in combination with the detection direction to obtain a soil partition sequence; Traversing the soil partition sequence to perform mode statistics of the historical sample soil conductivity to obtain a soil conductivity sequence; Traversing the soil partition sequence to perform mode statistics of the historical sample dielectric constant to obtain a soil dielectric constant sequence; Randomly generating several non-uniform FDM-NLFM signal parameters, and performing signal propagation simulation in combination with the soil conductivity sequence and the soil dielectric constant sequence to obtain several power attenuation coefficients and several phase distortion coefficients; Based on the several power attenuation coefficients and the several phase distortion coefficients, optimizing the several non-uniform FDM-NLFM signal parameters to obtain target non-uniform FDM-NLFM signal parameters for cable external damage prevention detection.

2. The method according to claim 1, characterized in that Receiving soil detection information of the cable laying area, partitioning the laying soil, and sorting starting from the signal injection point in combination with the detection direction to obtain a soil partition sequence, including: The soil detection information includes soil composition information, soil temperature information, and soil humidity information; Configuring a soil composition deviation threshold, a soil temperature deviation threshold, and a soil humidity deviation threshold; According to the soil composition deviation threshold, the soil temperature deviation threshold, and the soil humidity deviation threshold, performing multi-level hierarchical clustering analysis in combination with the soil composition information, the soil temperature information, and the soil humidity information to obtain a soil partition set, where the soil composition, soil temperature, and humidity of any one partition are consistent; Sorting the soil partition set starting from the signal injection point in combination with the detection direction to obtain a soil partition sequence.

3. The method according to claim 2, wherein Configuring a soil composition deviation threshold, a soil temperature deviation threshold, and a soil humidity deviation threshold, including: Extracting attributes to be analyzed from the soil composition information, soil temperature information, and soil humidity information; Taking the attribute to be analyzed as the only variable, setting the non-attribute set to be analyzed as a fixed quantity, and taking conductivity and dielectric constant as following variables to collect a set of recorded values of the attribute to be analyzed, a set of recorded values of conductivity, and a set of recorded values of dielectric constant; Performing pairwise fluctuation calculations on the set of recorded values of the attribute to be analyzed, the set of recorded values of conductivity, and the set of recorded values of dielectric constant to obtain a set of recorded value deviations of the attribute to be analyzed, a set of recorded value deviations of conductivity, and a set of recorded value deviations of dielectric constant; Based on the set of recorded value deviations of conductivity, screening from the set of recorded value deviations of the attribute to be analyzed a first selected set of recorded value deviations of the attribute to be analyzed where the recorded value deviation of conductivity is greater than or equal to the conductivity deviation threshold; Based on the set of recorded value deviations of dielectric constant, screening from the set of recorded value deviations of the attribute to be analyzed a second selected set of recorded value deviations of the attribute to be analyzed where the recorded value deviation of dielectric constant is greater than or equal to the dielectric constant deviation threshold; After performing outlier deletion on the selected set of deviation values of the first attribute to be analyzed and the selected set of deviation values of the second attribute to be analyzed respectively, extract the minimum value of the remaining deviation values of the first attribute to be analyzed and the remaining deviation values of the second attribute to be analyzed, and set it as the deviation threshold of the attribute to be analyzed, and add it to the soil composition deviation threshold, the soil temperature deviation threshold, and the soil humidity deviation threshold.

4. The method according to claim 1, wherein Traverse the soil partition sequence to perform the mode statistics of the historical sample soil conductivity, and obtain the soil conductivity sequence, including: According to the soil partition sequence, extract the first soil partition, where the first soil partition has a soil composition identifier, a soil temperature identifier, and a soil humidity identifier; Construct a first index constraint rule according to the soil composition identifier, the soil temperature identifier, and the soil humidity identifier; Retrieve the set of first soil conductivity detection values of the first historical sample set that satisfies the first index constraint rule, where the first historical sample set has a soil composition label set, a soil temperature label set, and a soil humidity label set; Construct a set of second index constraint rules according to the soil composition label set, the soil temperature label set, and the soil humidity label set, and retrieve the sets of second soil conductivity detection values of multiple groups of second historical samples that satisfy the set of second index constraint rules respectively; Perform mode aggregation on the set of first soil conductivity detection values and the sets of second soil conductivity detection values of multiple groups to obtain the soil conductivity of the first partition, and add it to the soil conductivity sequence.

5. The method according to claim 1, wherein Randomly generate a number of non-uniform FDM-NLFM signal parameters, and perform signal propagation simulation by combining the soil conductivity sequence and the soil dielectric constant sequence to obtain a number of power attenuation coefficients and a number of phase distortion coefficients, including: Any one of the number of non-uniform FDM-NLFM signal parameters includes an FDM frequency band parameter set, an FDM propagation frequency parameter, an FDM propagation power set, an NLFM propagation frequency curve, and an NLFM propagation power parameter; According to the FDM frequency band parameter set, the FDM propagation frequency parameter, the FDM propagation power set, the NLFM propagation frequency curve, and the NLFM propagation power parameter, perform unit-distance signal propagation simulation by combining the soil conductivity sequence and the soil dielectric constant sequence to obtain a unit-distance power attenuation rate sequence and a unit-distance phase distortion rate sequence; According to the soil partition sequence, obtain a propagation distance sequence, and perform cumulative calculation on the unit-distance power attenuation rate sequence and the unit-distance phase distortion rate sequence respectively to obtain a first power attenuation coefficient and a first phase distortion coefficient; Add the first power attenuation coefficient to the number of power attenuation coefficients, and add the first phase distortion coefficient to the number of phase distortion coefficients.

6. The method according to claim 5, wherein According to the set of FDM frequency band parameters, the FDM propagation frequency parameter, the set of FDM propagation powers, the NLFM propagation frequency curve, and the NLFM propagation power parameter, combining the soil conductivity sequence and the soil dielectric constant sequence to perform unit-distance signal propagation simulation, obtaining a unit-distance power attenuation rate sequence and a unit-distance phase distortion rate sequence, including: Configuring the recorded data of the set of FDM frequency band parameters, the recorded data of the FDM propagation frequency parameter, the recorded data of the set of FDM propagation powers, the recorded data of the NLFM propagation frequency curve, the recorded data of the NLFM propagation power parameter, the unit-distance power attenuation rate identification data, and the unit-distance phase distortion rate identification data; Using the unit-distance power attenuation rate identification data as supervision, and using the recorded data of the set of FDM frequency band parameters, the recorded data of the FDM propagation frequency parameter, the recorded data of the set of FDM propagation powers, the recorded data of the NLFM propagation frequency curve, and the recorded data of the NLFM propagation power parameter as inputs to train the first BP neural network to obtain a unit-distance power attenuation rate simulation channel; Using the unit-distance phase distortion rate identification data as supervision, and using the recorded data of the set of FDM frequency band parameters, the recorded data of the FDM propagation frequency parameter, the recorded data of the set of FDM propagation powers, the recorded data of the NLFM propagation frequency curve, and the recorded data of the NLFM propagation power parameter as inputs to train the second BP neural network to obtain a unit-distance phase distortion rate simulation channel; Combining the input layers of the unit-distance power attenuation rate simulation channel and the unit-distance phase distortion rate simulation channel to generate a unit-distance signal propagation simulation function, performing unit-distance signal propagation simulation, and obtaining a unit-distance power attenuation rate sequence and a unit-distance phase distortion rate sequence.

7. The method according to claim 1, wherein Based on the several power attenuation coefficients and the several phase distortion coefficients, performing optimization on the several non-uniform FDM-NLFM signal parameters to obtain target non-uniform FDM-NLFM signal parameters for cable external damage detection, including: Constructing an optimization fitness function: ， Among them, represents the fitness value, and represents the weight parameter, represents the power prediction attenuation coefficient, represents the phase prediction distortion coefficient, represents the population update times, represents the update influence regulation factor, > 0, e represents the natural constant, represents the power attenuation coefficient, represents the phase distortion coefficient threshold; According to the optimization fitness function, based on the several power attenuation coefficients and the several phase distortion coefficients, for the several non-uniform FDM-NLFM signal parameters, obtaining several fitness evaluation values; Based on the several fitness evaluation values from small to large, sorting the top three non-uniform FDM-NLFM signal parameters from the several non-uniform FDM-NLFM signal parameters; Calculating the mean value of the quantization signal parameters of the top three non-uniform FDM-NLFM signal parameters, and taking the union of the type signal parameters to obtain target signal parameters; Using the target signal parameters as a guiding target, performing guided mutation on the several non-uniform FDM-NLFM signal parameters to obtain updated non-uniform FDM-NLFM signal parameters to execute a loop, where the mutation rules are quantization parameter distance reduction mutation and type parameter crossover mutation; Until the non-uniform FDM-NLFM signal parameters with a fitness value less than or equal to the convergence threshold are obtained, and set as the target non-uniform FDM-NLFM signal parameters.

8. A cable anti-external damage system based on non-uniform FDM-NLFM, characterized in that, Including: A soil zoning sequence module, configured to receive soil detection information of a cable laying area, zone the laying soil, and sort it starting from the signal injection point in combination with the detection direction to obtain a soil zoning sequence; A soil conductivity sequence module, configured to traverse the soil zoning sequence to perform a mode statistics of the historical sample soil conductivity to obtain a soil conductivity sequence; A soil dielectric constant sequence module, configured to traverse the soil zoning sequence to perform a mode statistics of the historical sample dielectric constant to obtain a soil dielectric constant sequence; A power attenuation and phase distortion coefficient module, configured to randomly generate a plurality of non-uniform FDM-NLFM signal parameters, perform signal propagation simulation in combination with the soil conductivity sequence and the soil dielectric constant sequence to obtain a plurality of power attenuation coefficients and a plurality of phase distortion coefficients; A cable anti-external damage detection module, configured to perform optimization on the plurality of non-uniform FDM-NLFM signal parameters according to the plurality of power attenuation coefficients and the plurality of phase distortion coefficients, and obtain the target non-uniform FDM-NLFM signal parameters for cable anti-external damage detection.

Images