Power tower health state comprehensive evaluation method and system based on multi-source data fusion

Abstract

The application provides a power tower health state comprehensive evaluation method and system based on multi-source data fusion, and belongs to the technical field of power equipment evaluation. The application obtains the grounding resistance measurement record, the current waveform record and the soil humidity coefficient of a target tower, corrects the resistance value to obtain a resistance evolution sequence, time-integrates the instantaneous current of the current waveform to obtain an energy impact sequence, and correlates and maps the two sequences to obtain an impedance evolution trajectory. Then, the application calculates the similarity through gray correlation analysis and quantifies the contribution strength of the energy impact to the resistance rising trend to obtain a first weight matrix. Then, the application adjusts the weight matrix by using a penalty factor determined based on the initial design parameters and the operation life to obtain a second weight matrix. Finally, the application obtains a health evaluation score by weighted fusion of the two sequences based on the matrix and determines the target health state by comparing the health threshold interval. The application can realize quantitative evaluation of the tower grounding system.

Description

Technical Field

[0001] This application belongs to the technical field of power equipment assessment, and in particular relates to a comprehensive assessment method and system for the health status of power transmission towers based on multi-source data fusion. Background Technology

[0002] The grounding system of power transmission towers is a key component in ensuring the safe operation of transmission lines, and its health status affects the lightning protection and fault current discharge capabilities of power grid equipment. With the increasing abundance of power system monitoring data, conducting health assessments of power tower grounding systems using multi-source data fusion technology is of great significance for improving the accuracy of condition-based maintenance of transmission lines and reducing operation and maintenance costs.

[0003] Currently, the health assessment methods for power transmission towers mainly rely on a combination of regular grounding resistance measurement and manual inspection. Some technical solutions use online monitoring devices to collect grounding resistance values ​​in real time and make simple corrections based on environmental temperature and humidity data to determine whether the grounding system exceeds the standard. Other solutions use fault recording data to count the number of short circuits, but only use the short circuit frequency as an independent indicator for evaluation, without deeply analyzing the cumulative impact of short circuit current on the performance degradation of the grounding body.

[0004] However, existing methods generally have the following shortcomings in the assessment process: First, they fail to effectively establish the causal relationship between short-circuit current impact and grounding resistance evolution, resulting in the inability to quantify the contribution of electrical stress to the aging of the grounding system; second, the assessment weights are fixed and cannot adaptively adjust the evaluation focus when grounding performance changes abruptly, affecting the sensitivity of risk identification; and third, the correction for environmental factors is limited to simple coefficient conversion, without considering the impact of long-term corrosion and other cumulative effects on the measurement data. Summary of the Invention

[0005] The purpose of this application is to provide a comprehensive assessment method and system for the health status of power transmission towers based on multi-source data fusion, in order to solve the problems of insufficient accuracy in the health assessment of grounding systems and lack of ability to sensitively capture abrupt changes in the existing technology.

[0006] To address the aforementioned technical problems, in a first aspect, this application provides a comprehensive assessment method for the health status of power transmission towers based on multi-source data fusion, comprising: Acquire grounding resistance measurement records, short-circuit current waveform records, and soil moisture coefficient of the target tower within a preset time period; The resistance value in the grounding resistance measurement record is corrected using the soil moisture coefficient to obtain the resistance evolution sequence, and the energy impact sequence is obtained by time integration of the short-circuit current waveform record. By mapping the resistance evolution sequence and the energy impact sequence along the time axis, the impedance evolution trajectory is obtained. The similarity between the standardized resistance value and the energy impact value in the impedance evolution trajectory is calculated by gray-scale correlation analysis, and the contribution of the energy impact value to the resistance increase trend is quantified by the similarity measure to obtain the first weight matrix. When the rate of change of the resistance evolution sequence is greater than a preset safety threshold, the weights of the corresponding time nodes in the first weight matrix are adjusted using a penalty factor determined based on the initial design parameters and operating years of the target tower, to obtain a second weight matrix. The resistance evolution sequence and the energy impact sequence are weighted and fused based on the second weight matrix to obtain a health assessment score, which is then compared with a preset health threshold range to determine the target health status.

[0007] Optionally, the resistance values ​​measured at each recording time point in the grounding resistance measurement record are corrected using the soil moisture coefficient to obtain a resistance evolution sequence. The instantaneous current of the current waveform at each recording time point in the current waveform record is then integrated over time to obtain an energy impulse sequence, including: Based on the time point of each measurement record in the grounding resistance measurement record, determine the target humidity coefficient corresponding to each measurement record in the soil moisture coefficient; The ratio of the resistance value of each measurement record to the corresponding target humidity coefficient is calculated to obtain the standardized resistance value. The standardized resistance values ​​of each measurement record are then arranged in chronological order to obtain the resistance evolution sequence. Extract the instantaneous current amplitude at each sampling point and the time interval between adjacent sampling points from the current waveform records. The single-point impact energy is obtained by multiplying the square of the instantaneous current amplitude at each sampling point by the corresponding time interval. The single-point impact energy of each sampling point is accumulated to obtain the energy impact value at each waveform recording time point. The energy impact values ​​of each waveform recording are arranged in chronological order to obtain the energy impact sequence.

[0008] Optionally, after correcting the resistance values ​​measured at each recording time point in the grounding resistance measurement record using the soil moisture coefficient to obtain the resistance evolution sequence, the method further includes: Based on the service life of the target tower and the soil corrosion level of the area where the target tower is located, the corresponding corrosion rate is determined in a preset corrosion rate table, and the product of the corrosion rate and the service life is calculated to obtain the corrosion compensation value. The standardized resistance value of each measurement record in the resistance evolution sequence is differiated from the corrosion compensation value to correct the resistance evolution sequence.

[0009] Optionally, the step of mapping the resistance evolution sequence and the energy impact sequence along the time axis to obtain the impedance evolution trajectory includes: The time difference between each measurement record time point in the resistance evolution sequence and each waveform record time point in the energy impact sequence is statistically analyzed. The standardized resistance value in the resistance evolution sequence and the energy impact value in the energy impact sequence with the time difference less than a preset time window are identified as paired data at the same time point. Based on the pairing data, a first time point is determined in the energy impact sequence that does not correspond to the measurement record in the resistance evolution sequence, and the first time point is filled with the average of the standardized resistance values ​​of the two time points closest to the first time point in the resistance evolution sequence. Based on the pairing data, a second time point is determined in the resistance evolution sequence that does not correspond to the waveform record in the energy impact sequence. The second time point is then filled with the average of the energy impact values ​​of the two time points closest to the second time point in the energy impact sequence. The impedance evolution trajectory is obtained by arranging the standardized resistance value and energy impact value at each time point in the filled resistance evolution sequence and the filled energy impact sequence in chronological order.

[0010] Secondly, this application provides a comprehensive health status assessment system for power transmission towers based on multi-source data fusion, including: The acquisition module is used to acquire the grounding resistance measurement record, short-circuit current waveform record and soil moisture coefficient of the target tower within a preset time period; The correction module is used to correct the resistance value in the grounding resistance measurement record using the soil moisture coefficient to obtain the resistance evolution sequence, and to perform time integration on the short-circuit current waveform record to obtain the energy impact sequence. The mapping module is used to map the resistance evolution sequence and the energy impact sequence along the time axis to obtain the impedance evolution trajectory. The calculation module is used to calculate the similarity between the standardized resistance value and the energy impact value in the impedance evolution trajectory through gray-scale correlation analysis, and to use the similarity measure to quantify the contribution of the energy impact value to the resistance increase trend, thereby obtaining the first weight matrix. The adjustment module is used to adjust the weights of the corresponding time nodes in the first weight matrix by using a penalty factor determined based on the initial design parameters and operating years of the target tower when the rate of change of the resistance evolution sequence is greater than a preset safety threshold, so as to obtain a second weight matrix. The fusion module is used to perform weighted fusion of the resistance evolution sequence and the energy impact sequence based on the second weight matrix to obtain a health assessment score, and compare it with a preset health threshold range to determine the target health status.

[0011] Thirdly, this application provides an electronic device, comprising: Memory, used to store computer programs; A processor is used to execute computer programs to implement the steps of the comprehensive assessment method for the health status of power transmission towers based on multi-source data fusion as described in the first aspect above.

[0012] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps of the comprehensive assessment method for the health status of power transmission towers based on multi-source data fusion as described in the first aspect above.

[0013] The comprehensive health status assessment method for power transmission towers based on multi-source data fusion provided in this application has the following beneficial effects: This application achieves data acquisition without the need for additional sensors by utilizing existing production management data and fault recording data from the power system. It then eliminates the interference of seasonal fluctuations in soil moisture on resistance measurements and converts short-circuit current into an energy index characterizing electrothermal stress, ensuring comparability of data of different natures. Next, it aligns and correlates the resistance evolution process with energy impact events over time to establish a temporal correspondence between the two. Furthermore, it quantifies the causal contribution of energy impacts to resistance increases, providing a weighting basis for subsequent differentiated assessments. Subsequently, when grounding performance exhibits rapid deterioration or high correlation strength, the assessment weight of the corresponding time point is automatically increased, enhancing the sensitivity to anomaly identification. Finally, by integrating information from both resistance evolution and energy impact dimensions, a quantified health assessment score is obtained, thus avoiding misjudgments caused by fluctuations in a single indicator.

[0014] Furthermore, this application calculates the absolute range of the difference between resistance and energy values ​​at each time point, then uses the resolution coefficient to construct the numerator and denominator values ​​and calculates the ratio to obtain the correlation coefficient. Next, it calculates the arithmetic mean of all correlation coefficients to obtain the overall similarity. Then, it identifies target time points where resistance shows an increasing trend, and multiplies the similarity by the correlation coefficient at that time point as its weight. For non-target time points, a baseline weight is multiplied by the correlation coefficient, and finally, all weights are arranged in chronological order to form the first weight matrix. This method achieves precise quantification of the contribution of energy shocks to increased resistance, highlighting the assessment weight of critical periods of resistance degradation, ensuring that all time points participate in subsequent fusion calculations, and avoiding information loss. This lays a data foundation for dynamic weight adjustment and comprehensive health assessment. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart illustrating a comprehensive assessment method for the health status of power transmission towers based on multi-source data fusion, provided for an embodiment of this application; Figure 2 A flowchart illustrating a method for generating impedance evolution trajectories provided in an embodiment of this application; Figure 3 A flowchart illustrating a method for generating a target health status, provided in an embodiment of this application; Figure 4 A schematic diagram of the structure of a comprehensive health status assessment system for power transmission towers based on multi-source data fusion, provided in an embodiment of this application; Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in one embodiment of this application. Detailed Implementation

[0017] Health assessment of power tower grounding systems currently relies mainly on periodic manual measurement of grounding resistance, comparing single measurements with safety thresholds. This method has significant limitations: grounding resistance measurements fluctuate with soil moisture and seasonal changes, and single measurements are insufficient to reflect the true state; towers are subjected to multiple short-circuit current surges during long-term operation, and existing methods have failed to establish a correlation between current surges and grounding performance degradation; furthermore, fixed-weight assessment methods cannot automatically increase the assessment weight of key indicators when grounding performance deteriorates rapidly, leading to a lag in abnormal state identification.

[0018] To address this, this application proposes a comprehensive health status assessment method for power transmission towers based on multi-source data fusion. This method utilizes existing resistance measurement records and fault waveform data. It eliminates environmental interference through soil moisture coefficient correction to obtain a resistance evolution sequence, integrates the short-circuit current waveform to obtain an energy impact sequence, and then uses grayscale correlation analysis to quantify the contribution of energy impacts to resistance increases, resulting in a first weight matrix. When the resistance change rate exceeds a safety threshold, a penalty factor is introduced to dynamically adjust the weights, resulting in a second weight matrix. Finally, a weighted fusion is performed to output a health assessment score, thus solving the problems of inaccurate assessment results and delayed abnormal state identification in existing methods.

[0019] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some embodiments of the present application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] To address the problems in the prior art, this application provides a method and system for comprehensive health status assessment of power transmission towers based on multi-source data fusion. The method for comprehensive health status assessment of power transmission towers based on multi-source data fusion, as provided in this application, will be described below.

[0021] Figure 1 This illustration shows a flowchart of a comprehensive health status assessment method for power transmission towers based on multi-source data fusion, provided in one embodiment of this application. Figure 1 As shown.

[0022] S101. Obtain the grounding resistance measurement record, short-circuit current waveform record and soil moisture coefficient of the target tower within a preset time period. In this sub-step, the grounding resistance measurement record refers to the historical data set formed by periodically measuring the power frequency grounding resistance of the target tower's grounding device. This data may include the measurement time point, the corresponding resistance measurement value, and environmental information during the measurement. The current waveform record refers to the waveform data of current changes over time, automatically collected and stored by the fault recording device when a short-circuit fault occurs on the transmission line where the target tower is located. This data may include the time of the short circuit, the current sampling sequence, and the corresponding sampling time interval.

[0023] Soil moisture coefficient refers to a series of correction coefficients reflecting the monthly variation of soil moisture content in the area where the target tower is located. It can be a coefficient table divided by month, used to eliminate the influence of soil moisture differences in different measurement seasons on the grounding resistance measurement value. The preset time period refers to the historical time range covered by the health status assessment of the target tower, which can be a continuous period of several years to more than ten years. The length of the time period affects the amount of data in the subsequent series and the reliability of the assessment results.

[0024] In this embodiment, grounding resistance measurement records of the target tower within a preset time period are retrieved from the power production management system. These records contain multiple measurement records, each corresponding to a measurement time point and the resistance measurement value at that time point. Since grounding resistance is typically measured according to fixed cycles such as spring and autumn inspections, the time point distribution of each measurement record in the grounding resistance measurement record is relatively sparse. For example, a certain tower may have n measurement records within the preset time period, denoted as: ,in, This represents the time point of the i-th measurement. This indicates the corresponding resistance measurement value.

[0025] Retrieve current waveform records corresponding to the line where the target tower is located within the same preset time period from the dispatch automation system or fault recording device. Each current waveform record corresponds to a short-circuit fault event, and includes the occurrence time of the fault and the current sampling sequence. Assume that the occurrence time of the j-th short-circuit fault is... Its current sampling sequence is denoted as: ,in, This indicates the k-th sampling time. The corresponding instantaneous current amplitude m represents the total number of sampling points for the fault waveform. The preset time period can be determined based on the tower commissioning time and the completeness of the maintenance records. It usually covers all historical data of the tower from commissioning to the evaluation time to ensure that the subsequently generated resistance evolution sequence and energy impact sequence have a sufficient time span.

[0026] The measured soil resistivity values ​​ρk for each month were retrieved from the geological monitoring database of the area where the target tower is located. Using the soil resistivity ρ1 in January of each year as a benchmark, the soil moisture coefficient sk = ρ1 / ρk for each month was calculated and compiled into a coefficient table by month, denoted as follows: ,in, This represents the k-th month. This represents the humidity correction factor for the corresponding month. This soil moisture coefficient is a dimensionless ratio, and its physical meaning is: based on the resistivity of the driest month of the year (January), it measures the relative degree to which the soil resistivity decreases due to increased humidity in other months. The larger the coefficient, the greater the soil moisture in that month.

[0027] This application provides a complete foundation for evaluation by acquiring existing multi-source data at low cost and without the need for additional sensors.

[0028] S102. The resistance value in the grounding resistance measurement record is corrected using the soil moisture coefficient to obtain the resistance evolution sequence, and the short-circuit current waveform record is integrated over time to obtain the energy impact sequence. In one specific implementation, step S102 includes: Step 1021: Based on the time point of each measurement record in the grounding resistance measurement record, determine the target humidity coefficient corresponding to each measurement record in the soil moisture coefficient; In this sub-step, the target humidity coefficient refers to the humidity correction coefficient corresponding to the month of a certain measurement record time point from the soil humidity coefficient. It is used to characterize the degree of influence of the soil humidity state of the season at the measurement time point on the grounding resistance measurement value.

[0029] In this embodiment of the application, for each measurement record in the grounding resistance measurement record, the month information corresponding to its time point is extracted, and the coefficient consistent with that month is found in the soil moisture coefficient table, and this coefficient is determined as the target moisture coefficient of the measurement record; assuming the time point of the i-th measurement record The month in question is The corresponding target humidity coefficient satisfy: ,in, This indicates the mapping relationship for finding the corresponding coefficient by month from the soil moisture coefficient table. For example, if a measurement record is for March, then the target moisture coefficient for March will be found in the soil moisture coefficient table. The target humidity coefficient is used as the measurement record.

[0030] Step 1022: Calculate the ratio of the resistance value of each measurement record to the corresponding target humidity coefficient to obtain the standardized resistance value, and arrange the standardized resistance values ​​of each measurement record in chronological order to obtain the resistance evolution sequence; In this sub-step, the standardized resistance value is used to eliminate the interference of seasonal fluctuations in soil moisture on the resistance measurement value, so as to make the measurement values ​​in different seasons comparable. The resistance evolution sequence reflects the true change trend of the target tower grounding resistance after eliminating seasonal interference.

[0031] In this embodiment of the application, for each measurement record, its resistance measurement value is... Divide by the corresponding target humidity coefficient The standardized resistance value of the measurement record is obtained. Its calculation formula is Then, the standardized resistance values ​​of all the measurement records are arranged in chronological order to obtain the resistance evolution sequence. ,in, For the time point of the i-th measurement record, Here, n represents the corresponding standardized resistance value, and n is the total number of measurement records. For example, the resistance measurement value of a certain iron tower in March is... The corresponding target humidity coefficient for March is The standardized resistance value of this measurement record is... It reflects the true grounding resistance level after excluding the influence of soil moisture.

[0032] Step 1023: Extract the instantaneous current amplitude and the time interval between adjacent sampling points from the current waveform of each waveform record from the short-circuit current waveform record; In this sub-step, the instantaneous current amplitude refers to the instantaneous current value at a certain sampling point in the current waveform record, reflecting the actual magnitude of the short-circuit current at that sampling moment. The time interval refers to the time length between two adjacent sampling points in the current waveform record, determined by the sampling frequency, and is used as the time weight in subsequent calculations of single-point impact energy.

[0033] In this embodiment of the application, for each waveform record in the current waveform record, the instantaneous current amplitude at each sampling point in the current waveform and the time interval between adjacent sampling points are read point by point. It is assumed that the j-th waveform record has a total of There are 3 sampling points, and the instantaneous current amplitude at the k-th sampling point is 1. The time interval between the k-th sampling point and the (k+1)-th sampling point is The extraction result can be represented as , where the time interval The sampling frequency f of the fault recording device determines that it satisfies Furthermore, the time interval between each sampling point in the same waveform record is usually equal.

[0034] Step 1024: Calculate the product of the square of the instantaneous current amplitude at each sampling point and the corresponding time interval to obtain the single-point impact energy. Accumulate the single-point impact energy at each sampling point to obtain the energy impact value at each waveform recording time point. Arrange the energy impact values ​​of each waveform recording in chronological order to obtain the energy impact sequence.

[0035] In this sub-step, the single-point impact energy is used to characterize the instantaneous electrothermal stress generated by the short-circuit current on the grounding electrode at that sampling point. The energy impact value is used to characterize the total electrothermal stress caused by the short-circuit fault on the grounding electrode. The energy impact sequence is used to reflect the change in electrothermal stress borne by the target tower grounding electrode over time during each short-circuit fault.

[0036] In this embodiment of the application, the single-point impact energy is calculated for the k-th sampling point in the j-th waveform record. Then, the single-point impact energy of all sampling points in the j-th waveform record is accumulated to obtain the energy impact value corresponding to that waveform record. Then, the energy impact values ​​of all waveform records are arranged in chronological order of their occurrence to obtain the energy impact sequence: ,in, Let j be the time when the short-circuit fault occurs. Here, p represents the corresponding energy impact value, and p is the total number of waveform records. For example, the current waveform of a short-circuit fault includes... There are 10 sampling points, and the instantaneous current amplitude sequence of each sampling point is as follows: The time intervals are all The energy impact value of this fault is... .

[0037] After correcting the resistance values ​​measured at each time point in the grounding resistance measurement record using the soil moisture coefficient to obtain the resistance evolution sequence, S102 also includes: Step 1025: Based on the service life of the target tower and the soil corrosion level of the area where the target tower is located, determine the corresponding corrosion rate in the preset corrosion rate table, and calculate the product of the corrosion rate and the service life to obtain the corrosion compensation value. In this sub-step, the soil corrosion level refers to a classification standard that divides the corrosion intensity of the soil on the metal grounding electrode into several levels based on the chemical composition, conductivity, and pH value of the soil in the area where the target tower is located. These levels can be categorized as strong corrosion, moderate corrosion, weak corrosion, etc. The corrosion rate refers to the annual increase in grounding resistance due to corrosion of the grounding electrode material under specific soil corrosion levels and operating years, which is obtained from a preset corrosion rate table.

[0038] The corrosion compensation value is used to quantify the increase in resistance of the grounding electrode due to corrosion accumulation throughout its entire operating cycle. The preset corrosion rate table can be obtained by statistical analysis of long-term measured data of tower grounding electrodes under different soil corrosion levels, or it can be constructed by referring to the corrosion rate reference values ​​in relevant industry standards. The table stores the corrosion rate values ​​corresponding to the soil corrosion level and the operating year range.

[0039] In this embodiment, the service life Y of the target tower and the soil corrosion level L of the area are obtained. The corresponding corrosion rate v is looked up in a preset corrosion rate table using L and Y as indexes. After determining the corrosion rate, the corrosion compensation value is calculated. The structure of its corrosion rate table is shown in Table 1: Table 1: Structure of the Corrosion Rate Table

[0040] Step 1026: Difference the standardized resistance value and the corrosion compensation value of each measurement record in the resistance evolution sequence to correct the resistance evolution sequence.

[0041] In the embodiments of this application, the resistance evolution sequence Standardized resistance value for each measurement record Subtract corrosion compensation value The corrected standardized resistance value is obtained. Then, all the corrected standardized resistance values ​​are rearranged in their original chronological order, and the corrected values ​​are used to replace the corresponding standardized resistance values ​​in the original resistance evolution sequence, resulting in the corrected resistance evolution sequence. The corrected resistance evolution sequence eliminates two types of interference: seasonal fluctuations in soil moisture and cumulative corrosion of the grounding electrode. It more accurately reflects the changes in grounding performance caused by electrothermal stress, providing a more reliable data basis for the subsequent generation of impedance evolution trajectories.

[0042] For example, the service life of a certain iron tower is In [year], the soil corrosion level was classified as moderate corrosion. From the table, the corrosion rate was [value]. The corrosion compensation value is then The standardized resistance value of the tower, as measured in March, was... Revised to .

[0043] This application improves data accuracy by eliminating humidity and corrosion interference and quantifying electrothermal stress to generate comparable sequences.

[0044] S103. Map the resistance evolution sequence and the energy impact sequence along the time axis to obtain the impedance evolution trajectory; In one specific implementation, such as Figure 2 As shown, step S103 includes: Step 1031: Calculate the time difference between the time point of each measurement record in the resistance evolution sequence and the time point of each waveform record in the energy impact sequence, and determine the standardized resistance value in the resistance evolution sequence and the energy impact value in the energy impact sequence with the time difference less than a preset time window as paired data at the same time point. In this sub-step, the time difference refers to the time interval between a measurement record time point in the resistance evolution sequence and a waveform record time point in the energy impact sequence. It is used to determine whether the data points in the two sequences are sufficiently close in time to be considered the same time node. The preset time window refers to the maximum allowable time difference threshold for determining whether two time points can be paired. It can be obtained based on statistical analysis of the tower grounding resistance measurement cycle and the frequency of short-circuit faults. It is usually set to cover a reasonable time range for short-circuit faults between two adjacent measurement records. In this embodiment, the preset time is preferably 1.5 times the target tower grounding resistance measurement cycle.

[0045] Paired data refers to the combination of standardized resistance value of a measurement record in a resistance evolution sequence and energy impact value of a waveform record in an energy impact sequence, formed at the same time node under the condition that the time difference is less than a preset time window. It can include the time identifier, standardized resistance value and energy impact value of that time node.

[0046] In the embodiments of this application, the time points of each measurement record in the resistance evolution sequence are... The time points recorded for each waveform in the energy impact sequence Calculate the time difference between the two. Then With preset time window If a comparison is made, Then the standardized resistance value of the measurement record The energy impact value recorded by this waveform Paired data that are identified as being at the same time point are denoted as: .

[0047] Step 1032: Based on the pairing data, determine a first time point in the energy impact sequence that does not correspond to the measurement record in the resistance evolution sequence, and fill the first time point with the average of the standardized resistance values ​​of the two time points closest to the first time point in the resistance evolution sequence. In this sub-step, the first time point refers to the time point in which a waveform record exists in the energy impact sequence but fails to form a pair with any measurement record in the resistance evolution sequence in the paired dataset. This time point lacks a corresponding standardized resistance value and needs to be filled by interpolation.

[0048] In this embodiment of the application, based on the paired dataset, the time points of each waveform record are examined one by one in the energy impact sequence, and the first time point that did not participate in the pairing is determined, denoted as... Then search for the relationship in the resistance evolution sequence. The two closest measurement recording time points are denoted as . and That is, satisfying Then, the mean of the standardized resistance values ​​corresponding to these two time points is calculated and used as the filled standardized resistance value for the first time point. ,in, and They are time points respectively and The corresponding standardized resistance value is used to fill all the first time points. After the filling is completed, each time point in the energy impact sequence has a corresponding standardized resistance value.

[0049] Step 1033: Based on the pairing data, determine a second time point in the resistance evolution sequence that does not correspond to the waveform record in the energy impact sequence, and fill the second time point with the average of the energy impact values ​​of the two time points closest to the second time point in the energy impact sequence. In this sub-step, the second time point refers to the time point in which a measurement record exists in the resistance evolution sequence but fails to form a pair with any waveform record in the energy impact sequence in the paired dataset. This time point lacks a corresponding energy impact value and needs to be filled by interpolation.

[0050] In this embodiment, based on the paired dataset, each measurement record time point is examined sequentially in the resistance evolution sequence, and a second time point that did not participate in the pairing is determined, denoted as... Then search for related energy shock sequences. The two waveforms with the closest time intervals are recorded at the following time points, denoted as . and That is, satisfying Then, calculate the average of the energy impact values ​​corresponding to these two time points, and use this average as the filling energy impact value for the second time point. ,in, and They are time points respectively and The corresponding energy impact value, after filling all the second time points, means that each time point in the filled resistance evolution sequence has a corresponding energy impact value.

[0051] Step 1034: Arrange the standardized resistance value and energy impact value at each time point in the filled resistance evolution sequence and the filled energy impact sequence in chronological order to obtain the impedance evolution trajectory.

[0052] In this sub-step, the impedance evolution trajectory refers to the two-dimensional time series data set formed by arranging the standardized resistance values ​​and energy impact values ​​at each time point in the filled resistance evolution sequence and the filled energy impact sequence in chronological order. It can include the time marker, standardized resistance value and energy impact value of each time point, which are used to calculate the similarity between the two in the subsequent gray-scale correlation analysis.

[0053] In this embodiment, all time points in the filled resistance evolution sequence and the filled energy impact sequence are merged to form a unified time axis, which is then arranged in chronological order to obtain a sequence containing... An ordered set of n time points, where... The total number of time points after deduplication and merging the two sequences; then, for each time point on the time axis... Extract the corresponding standardized resistance value and energy impact value The two are combined to form binary data at that time point, and then all time points are arranged in chronological order to obtain the impedance evolution trajectory. ,in, For the first At a certain point in time, For the corresponding standardized resistance value, This corresponds to the energy impact value. This represents the total number of time points.

[0054] This application ensures complete temporal correspondence by associating timelines and filling missing data, and constructing a unified evolutionary trajectory.

[0055] S104. Calculate the similarity between the standardized resistance value and the energy impact value in the impedance evolution trajectory through gray-scale correlation analysis, and use the similarity measure to quantify the contribution of the energy impact value to the resistance increase trend to obtain the first weight matrix. In one specific implementation, step S104 includes: Step 1041: Calculate the absolute value of the difference between the standardized resistance value and the energy impact value at each time point in the impedance evolution trajectory, and obtain the minimum absolute difference and the maximum absolute difference; In this sub-step, the absolute difference refers to the absolute value of the difference between the standardized resistance value and the energy surge value at a certain time point in the impedance evolution trajectory. Since the two values ​​have different dimensions, the standardized resistance value sequence and the energy surge value sequence need to be normalized separately before calculation to make them dimensionless. The minimum absolute difference refers to the minimum of the absolute differences among all time points in the impedance evolution trajectory, and the maximum absolute difference refers to the maximum of the absolute differences among all time points. Both are used together in the subsequent normalization calculation of the correlation coefficient.

[0056] In the embodiments of this application, the impedance evolution trajectory The normalized resistance value sequence and energy impact value sequence in the data are normalized to obtain the normalized resistance value. and normalized energy impact value : Both are dimensionless, among which, and These are the minimum and maximum values ​​of the standardized resistance value sequence, respectively. and These are the minimum and maximum values ​​of the energy impact value sequence, respectively; Then, for each time point in the impedance evolution trajectory... Calculate the absolute value of the normalized difference. Then iterate through all At each time point, the set of absolute values ​​of the differences is obtained. And determine the minimum absolute difference from it. and maximum absolute difference .

[0057] Step 1042: Multiply the preset resolution coefficient and the maximum absolute difference, and add the product to the minimum absolute difference to obtain the numerator value. Multiply the maximum absolute difference and the preset resolution coefficient, and add the product to each absolute difference to obtain the denominator value. Calculate the ratio of the numerator value to the denominator value to obtain the correlation coefficient at each time point. In this sub-step, the resolution coefficient refers to a preset parameter used in gray-scale correlation analysis to adjust the resolution capability of the correlation coefficient. Its value ranges from [0,1] and can be set according to the required analysis accuracy. It is usually set to 0.5, a value that has been widely verified in engineering practice to achieve a balance between the resolution and stability of the correlation coefficient. The correlation coefficient is a dimensionless quantitative index that measures the geometric similarity between the standardized resistance value and the energy impact value at a certain time point based on the gray-scale correlation analysis method. Its value ranges from (0,1), and the larger the value, the more consistent the trends of the two at that time point.

[0058] In the embodiments of this application, using , and at each time point Combined with resolution coefficient For each time point Calculate the correlation coefficient Its molecular value is The denominator value is The correlation coefficient at each time point is: It should be noted that all terms in the above equation are dimensionless, and the dimensions on both sides of the equals sign are consistent; subsequently, all terms in the impedance evolution trajectory are considered. The correlation coefficient sequence is obtained by calculating each time point individually. .

[0059] Step 1043: Calculate the arithmetic mean of the correlation coefficients at all time points to obtain the similarity between the standardized resistance value and the energy impact value; In this sub-step, similarity refers to the overall index obtained by arithmetically averaging the correlation coefficients of all time points in the impedance evolution trajectory. It is dimensionless and its value ranges from (0,1). It is used to measure the consistency of the changing trends of the standardized resistance value sequence and the energy impact value sequence in the time dimension. The larger the value, the stronger the overall correlation between the energy impact and the resistance change.

[0060] In this embodiment of the application, the correlation coefficient sequence All The similarity is obtained by arithmetically averaging the correlation coefficients at each time point. Among them, similarity This reflects the overall correlation between energy surges and changes in standardized resistance over the entire preset time period, and The larger the value, the more significant the impact of each short-circuit current surge on the increasing trend of grounding resistance.

[0061] Step 1044: Determine the time point of the next measurement record in the adjacent measurement records of the resistance evolution sequence in which the standardized resistance value shows an increasing trend as the target time point, calculate the product of the similarity and the correlation coefficient of the target time point, and obtain the weight of the target time point; In this sub-step, the target time point refers to the time point corresponding to the next measurement record when the standardized resistance values ​​of two adjacent measurement records in the resistance evolution sequence show an increasing change. It is used to identify the time node when the grounding resistance increases and is the key analytical object for quantifying the contribution intensity of energy impact to the resistance increase.

[0062] In this embodiment, all adjacent measurement records in the resistance evolution sequence are traversed, and the normalized resistance values ​​of two adjacent measurement records are compared. If the normalized resistance value of the later measurement record is... Greater than the standardized resistance value of the previous measurement record Then the time point of the next measurement record will be... Once the target time point is identified, all target time points that meet the criteria are collected to form a target time point set. ,in, The total number of target time points; then for each target time point In the correlation coefficient sequence Search for the correlation coefficient at the corresponding time point. And calculate similarity The product of this correlation coefficient yields the weight at the target time point. .

[0063] Step 1045: Calculate the product of the preset benchmark weight and the correlation coefficient of the non-target time point to obtain the weight of the non-target time point. Arrange all the weights in chronological order to obtain the first weight matrix. The non-target time point is the remaining time point in the impedance evolution trajectory other than the target time point.

[0064] In this sub-step, non-target time points refer to the remaining time points in the impedance evolution trajectory other than the target time points, namely, the measurement and recording time points where the standardized resistance value does not increase in the resistance evolution sequence, and all waveform recording time points in the energy impact sequence.

[0065] The benchmark weight refers to the preset basic coefficient assigned to the weight calculation of non-target time points. It is dimensionless and its value range is (0,1). It can be set according to the reference degree of non-target time points to the overall evaluation. It is usually taken as a fixed value less than the similarity to ensure that the weight of the target time point is higher than that of the non-target time point, thereby highlighting the importance of the resistance increase period in the comprehensive evaluation.

[0066] In the embodiments of this application, in the entire impedance evolution trajectory Among the time points, those that do not belong to the target time point set The time points are determined as non-target time points, thus forming a set of non-target time points. Then, for each non-target time point, in the correlation coefficient sequence Find the corresponding correlation coefficient in the middle. And calculate the benchmark weights. The product of this correlation coefficient yields the weight for the non-target time point. Among them, the benchmark weight The weights are preset constants, dimensionless; then the weights of all target time points are... and the weights of all non-target time points The first weight matrix is ​​obtained by merging and arranging the corresponding time points in chronological order on the time axis. The weights at each time point The calculation is based on whether the time point is the target time point and is obtained from the formula in step 1044 and this step.

[0067] This application quantifies the contribution of shock to resistance increase through grayscale correlation and dynamically assigns weights, which can highlight key degradation periods.

[0068] S105. When the rate of change of the resistance evolution sequence is greater than the preset safety threshold, the weights of the corresponding time nodes in the first weight matrix are adjusted using the penalty factor determined based on the initial design parameters and operating years of the target tower, to obtain the second weight matrix. In one specific implementation, step S105 includes: Step 1051: Calculate the ratio of the difference between the standardized resistance values ​​of adjacent measurement records in the resistance evolution sequence to the corresponding time interval to obtain the resistance change rate at each measurement record time point. Determine the time points of measurement records where the resistance change rate is greater than a preset safety threshold and the time points in the first weight matrix where the weight is greater than the preset weight threshold as risk time nodes. In this sub-step, the resistance change rate is used to measure the rate of change of grounding resistance per unit time, reflecting the degree of degradation of grounding performance. The preset safety threshold refers to the upper limit of the resistance change rate used to determine whether the rate of degradation of grounding resistance exceeds the safe range. The preset safety threshold is determined as follows: The resistance change rate at all adjacent measurement recording time points in the resistance evolution sequence is taken, and its average value μ is calculated. λ and standard deviation σ λ , with μ λ +2σ λ As a preset security threshold λ th The preset safety threshold is dynamically determined based on the statistical characteristics of the resistance evolution sequence itself. Exceeding this threshold indicates that the resistance change rate at the corresponding time point deviates significantly from the normal fluctuation range, and there is a risk of rapid deterioration in grounding performance.

[0069] The preset weight threshold refers to the upper limit of the weights used to determine whether the contribution of energy shock to the increase in resistance is significant at a certain time point. It can be set based on the statistical distribution characteristics of the weights in the first weight matrix, usually taking the mean of the weight sequence plus one standard deviation as a reference. Exceeding this threshold indicates that the time point has been subjected to significant electrical stress shock. A risk time point is a time point that meets either of the following conditions: a measurement recording time point where the resistance change rate is greater than the preset safety threshold, or a time point where the weights in the first weight matrix are greater than the preset weight threshold. It is used to identify critical time points where grounding performance exhibits rapid degradation or high correlation strength.

[0070] In this embodiment of the application, the resistance evolution sequence of the first... The and the first For each of the adjacent measurement records, calculate the ratio of the difference in standardized resistance values ​​to the corresponding time interval to obtain the result. Rate of resistance change at each measurement and recording time point ,in, and The first and the The standardized resistance values ​​of each measurement record The time interval between two measurement recording points; Then, the rate of change of resistance at each measurement time point was recorded. With preset security threshold A comparison will satisfy The measurement and recording time points are marked as the first type of candidate risk time nodes; simultaneously, in the first weight matrix In the middle, the weights Greater than the preset weight threshold The time points are marked as the second type of candidate risk time nodes, and then the two types of candidate risk time nodes are merged and deduplicated to obtain the risk time nodes.

[0071] Step 1052: Calculate the ratio of the standardized resistance value at the risk time node to the grounding resistance design value in the initial design parameters of the target tower to obtain the resistance deviation coefficient. Use the ratio of the actual operating years of the target tower to the preset years as the years coefficient, and use the product of the resistance deviation coefficient and the years coefficient as the penalty factor. In this sub-step, the grounding resistance design value refers to the rated grounding resistance value specified in the design phase of the target tower. It originates from the initial design parameters of the tower and reflects the resistance standard that the tower grounding system should meet when it is newly built and put into operation. The resistance deviation coefficient is the ratio of the standardized resistance value at the risk time node to the grounding resistance design value. It is used to characterize the degree of deviation of the grounding resistance from the design reference at that risk time node. The larger the value, the more severe the deterioration of the grounding performance.

[0072] The preset service life refers to the reference service life used to characterize the design life of a transmission tower. It is determined based on the design specifications and operation and maintenance experience of power transmission line towers, and is usually based on the expected service life specified in the tower design documents. The service life coefficient is the ratio of the actual service life of the target tower to the preset service life, used to characterize the cumulative aging degree of the tower. The closer the actual service life is to or exceeds the preset service life, the larger the service life coefficient, indicating a higher degree of tower aging.

[0073] The penalty factor is a comprehensive adjustment coefficient composed of the product of the resistance deviation coefficient and the age coefficient. It reflects both the degree of deterioration of the grounding resistance and the aging of the tower. It is used to amplify and adjust the weight of risk time nodes. The larger the value, the stronger the penalty.

[0074] In this embodiment of the application, the risk time node set Each risk time point Find the corresponding standardized resistance value from the resistance evolution sequence. Obtain the grounding resistance design value from the initial design parameters of the target tower. And calculate the resistance deviation coefficient. ,in, and All units are The dimensions on both sides of the equals sign are consistent; then, the actual service life of the target tower is obtained. and the preset value of the number of years And calculate the lifespan coefficient. Then adjust the resistance deviation coefficient With age coefficient Multiply to obtain the penalty factor corresponding to the risk time point. .

[0075] Step 1053: Normalize the product of the risk time node weights and the penalty factor in the first weight matrix, and replace the weights of the risk time nodes in the first weight matrix to obtain the second weight matrix.

[0076] In this embodiment of the application, the risk time node set Each risk time point From the first weight matrix Extract the corresponding weight from and the penalty factor of that node. Multiply to obtain the unadjusted amplification weights. Then collect the amplified weights of all risk time points. The adjusted weights are then normalized to obtain the normalized adjustment weights. ,in, To determine the total number of risk time points, normalization ensures that the sum of the adjusted weights for all risk time points is 1. Normalization is achieved by dividing the adjusted weight of each time point by the sum of the adjusted weights of all time points. The purpose of this normalization is to rescale the entire weight matrix to a standard distribution where the sum is 1 after amplifying the weights of risk time points through a penalty factor. This ensures that the resistance weights and energy weights are on the same order of magnitude in subsequent weighted fusion calculations, while maintaining the amplified weight advantage of risk time points relative to non-risk time points.

[0077] Next, the first weight matrix The original weights at medium-risk time points are replaced with the corresponding normalized adjusted weights. The weights of non-risk time points remain unchanged, and the weights of all time points are rearranged in chronological order to obtain the second weight matrix. Among them, non-risk time nodes The weights satisfy That is, keep the original weights in the first weight matrix unchanged.

[0078] This application enhances the sensitivity to identifying abrupt changes in resistance by introducing a penalty factor to dynamically adjust the weights.

[0079] S106. The resistance evolution sequence and the energy impact sequence are weighted and fused based on the second weight matrix to obtain a health assessment score, and the score is compared with a preset health threshold range to determine the target health status.

[0080] In one specific implementation, such as Figure 3 As shown, step S106 includes: Step 1061: Normalize the standardized resistance value of each measurement record in the resistance evolution sequence to obtain a normalized resistance value; normalize the energy impact value of each waveform record in the energy impact sequence to obtain a normalized energy impact value. In this embodiment of the application, the normalized resistance value is obtained in the same step 1041. and normalized energy impact value : Both are dimensionless, among which, and These are the minimum and maximum values ​​of the standardized resistance value sequence, respectively. and These are the minimum and maximum values ​​of the energy impact value sequence, respectively.

[0081] Step 1062: The product of the normalized resistance value and the weight of the corresponding time point in the second weight matrix is ​​used as the resistance weight value at the corresponding time point, and the product of the normalized energy impact value and the weight of the corresponding time point in the second weight matrix is ​​used as the energy weight value at the corresponding time point. In the embodiments of this application, for each time point in the impedance evolution trajectory From the second weight matrix Extract the corresponding weight from Then, combined with the normalized resistance value at that time point and normalized energy impact value Calculate the resistance weighting values ​​respectively. and energy weighting It should be noted that, after the correlation mapping and filling in step S103, the time points of the resistance evolution sequence and the energy impact sequence have been unified to the time axis of the impedance evolution trajectory. Therefore, each time point... Each corresponds to a unique normalized resistance value, a normalized energy impact value, and a second weight matrix weight.

[0082] Step 1063: Sum the resistance weights at all time points to obtain a resistance weighted sum, sum the energy weights at all time points to obtain an energy weighted sum, and sum all the weights in the second weight matrix to obtain a total weight sum; In this embodiment of the application, for all The resistance weighted values ​​at each time point are accumulated to obtain the resistance weighted sum. Then for all The energy weighted values ​​at each time point are summed to obtain the energy weighted sum. Then, for the second weight matrix All The weights at each time point are summed to obtain the total weight. .

[0083] Step 1064: Calculate the ratio of the sum of the resistance weighted sum and the energy weighted sum to the total weighted sum to obtain the health assessment score; In this sub-step, the health assessment score comprehensively reflects the overall health status of the target tower grounding system within a preset time period. The higher the value, the higher the degree of resistance degradation and cumulative electrothermal stress of the grounding system, and the worse the health status.

[0084] In the embodiments of this application, the resistance weighted sum is... With energy weighted sum After adding them together, divide by the sum of the weights. Receive a health assessment score because, and All are dimensionless normalized values ​​and take values ​​in the range of Inside, The health assessment score is a dimensionless weighted score. The dimensions on both sides of the equal sign are the same.

[0085] Step 1065: By comparing the health assessment score with multiple preset health threshold intervals, the target health status of the target tower is determined.

[0086] In this sub-step, the health threshold range refers to dividing the range of health assessment scores into several continuous sub-ranges, with each sub-range corresponding to a preset grading standard for a target health state. This can include levels such as safety, monitoring, early warning, and governance. Each level corresponds to a numerical range, with higher health assessment scores indicating a worse health state. The threshold range can be determined based on the power industry's transmission tower operation and maintenance regulations and the statistical distribution of historical assessment data, combined with the safety operation requirements of the tower grounding system to define the score boundaries for each level.

[0087] In this embodiment of the application, the health assessment score is... It is compared sequentially with the boundary values ​​of multiple preset health threshold intervals to determine The health status corresponding to the range into which the threshold falls is defined as the target health status. The correspondence between the health threshold range and the target health status is shown in Table 2. For each level's boundary threshold: Table 2: Correspondence between health threshold ranges and target health states

[0088] This application obtains a health score through weighted fusion and then compares it with a threshold range to determine the status, which can avoid misjudgment by a single indicator.

[0089] Figure 4This application provides a schematic diagram of a specific implementation of a comprehensive health status assessment system for power transmission towers based on multi-source data fusion, as illustrated in the embodiments of this application. Figure 4 The system may include: The acquisition module 41 is used to acquire the grounding resistance measurement record, short-circuit current waveform record and soil moisture coefficient of the target tower within a preset time period; The correction module 42 is used to correct the resistance value in the grounding resistance measurement record using the soil moisture coefficient to obtain the resistance evolution sequence, and to perform time integration on the short-circuit current waveform record to obtain the energy impact sequence. Mapping module 43 is used to map the resistance evolution sequence and the energy impact sequence along the time axis to obtain the impedance evolution trajectory; The calculation module 44 is used to calculate the similarity between the standardized resistance value and the energy impact value in the impedance evolution trajectory through gray-scale correlation analysis, and to use the similarity measure to quantify the contribution of the energy impact value to the resistance increase trend, thereby obtaining the first weight matrix. The adjustment module 45 is used to adjust the weights of the corresponding time nodes in the first weight matrix by using a penalty factor determined based on the initial design parameters and operating years of the target tower when the rate of change of the resistance evolution sequence is greater than a preset safety threshold, so as to obtain a second weight matrix. The fusion module 46 is used to perform weighted fusion of the resistance evolution sequence and the energy impact sequence based on the second weight matrix to obtain a health assessment score, and compare it with a preset health threshold range to determine the target health status.

[0090] The comprehensive health status assessment system for power transmission towers based on multi-source data fusion in this application is used to implement the aforementioned comprehensive health status assessment method for power transmission towers based on multi-source data fusion. Therefore, the specific implementation of the comprehensive health status assessment system for power transmission towers based on multi-source data fusion can be found in the embodiment section of the comprehensive health status assessment method for power transmission towers based on multi-source data fusion described above. The specific implementation can be referred to the description of the corresponding embodiments, which will not be repeated here.

[0091] Figure 5 A schematic diagram of the hardware structure of an electronic device provided in one embodiment of this application is shown.

[0092] The electronic device may include a processor 510 and a memory 520 storing computer program instructions.

[0093] Specifically, the processor 510 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0094] Memory 520 may include mass storage for data or instructions. For example, and not limitingly, memory 520 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 520 may include removable or non-removable (or fixed) media. Where appropriate, memory 520 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 520 is non-volatile solid-state memory.

[0095] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to the first aspect of this disclosure.

[0096] The processor 510 reads and executes computer program instructions stored in the memory 520 to implement any of the comprehensive assessment methods for the health status of power transmission towers based on multi-source data fusion in the above embodiments.

[0097] In one example, the electronic device may also include a communication interface 530 and a bus 540. Wherein, such as Figure 5 As shown, the processor 510, memory 520, and communication interface 530 are connected through bus 540 and complete communication with each other.

[0098] The communication interface 530 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0099] Bus 540 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 540 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0100] The electronic device can execute the comprehensive health status assessment method for power towers based on multi-source data fusion in the embodiments of this application, thereby realizing the comprehensive health status assessment method for power towers based on multi-source data fusion described in conjunction with the accompanying drawings.

[0101] Furthermore, in conjunction with the comprehensive health status assessment method for power transmission towers based on multi-source data fusion in the above embodiments, this application embodiment can provide a computer-readable storage medium for implementation. This computer-readable storage medium stores computer program instructions; when executed by a processor, these computer program instructions implement any of the comprehensive health status assessment methods for power transmission towers based on multi-source data fusion in the above embodiments.

[0102] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0103] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0104] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

Claims

1. A power tower health state comprehensive evaluation method based on multi-source data fusion, characterized in that, include: Acquire grounding resistance measurement records, short-circuit current waveform records, and soil moisture coefficient of the target tower within a preset time period; The resistance value in the grounding resistance measurement record is corrected using the soil moisture coefficient to obtain the resistance evolution sequence, and the energy impact sequence is obtained by time integration of the short-circuit current waveform record. By mapping the resistance evolution sequence and the energy impact sequence along the time axis, the impedance evolution trajectory is obtained. The similarity between the standardized resistance value and the energy impact value in the impedance evolution trajectory is calculated by gray-scale correlation analysis, and the contribution of the energy impact value to the resistance increase trend is quantified by the similarity measure to obtain the first weight matrix. When the rate of change of the resistance evolution sequence is greater than a preset safety threshold, the weights of the corresponding time nodes in the first weight matrix are adjusted using a penalty factor determined based on the initial design parameters and operating years of the target tower, to obtain a second weight matrix. The resistance evolution sequence and the energy impact sequence are weighted and fused based on the second weight matrix to obtain a health assessment score, which is then compared with a preset health threshold range to determine the target health status.

2. The power tower health state comprehensive evaluation method based on multi-source data fusion according to claim 1, characterized in that, The resistance values ​​in the grounding resistance measurement records are corrected using the soil moisture coefficient to obtain a resistance evolution sequence. Furthermore, the short-circuit current waveform records are integrated over time to obtain an energy impact sequence, including: Based on the time point of each measurement record in the grounding resistance measurement record, determine the target humidity coefficient corresponding to each measurement record in the soil moisture coefficient; Calculate the ratio of the resistance value of each measurement record to the corresponding target humidity coefficient to obtain the standardized resistance value, and arrange the standardized resistance values ​​of each measurement record in chronological order to obtain the resistance evolution sequence; Extract the instantaneous current amplitude at each sampling point and the time interval between adjacent sampling points from the current waveform of each waveform record; The single-point impact energy is obtained by multiplying the square of the instantaneous current amplitude at each sampling point by the corresponding time interval. The single-point impact energy at each sampling point is accumulated to obtain the energy impact value at each waveform recording time point. The energy impact values ​​of each waveform recording are arranged in chronological order to obtain the energy impact sequence.

3. The method according to claim 2, wherein, After correcting the resistance values ​​measured at each recording time point in the grounding resistance measurement record using the soil moisture coefficient to obtain the resistance evolution sequence, the method further includes: Based on the service life of the target tower and the soil corrosion level of the area where the target tower is located, the corresponding corrosion rate is determined in a preset corrosion rate table, and the product of the corrosion rate and the service life is calculated to obtain the corrosion compensation value. The standardized resistance value of each measurement record in the resistance evolution sequence is differiated from the corrosion compensation value to correct the resistance evolution sequence.

4. The power tower health state comprehensive evaluation method based on multi-source data fusion according to claim 1, characterized in that, By mapping the resistance evolution sequence and the energy impact sequence along the time axis, the impedance evolution trajectory is obtained, including: The time difference between each measurement record time point in the resistance evolution sequence and each waveform record time point in the energy impact sequence is statistically analyzed. The standardized resistance value in the resistance evolution sequence and the energy impact value in the energy impact sequence with the time difference less than a preset time window are identified as paired data at the same time point. Based on the pairing data, a first time point is determined in the energy impact sequence that does not correspond to the measurement record in the resistance evolution sequence, and the first time point is filled with the average of the standardized resistance values ​​of the two time points closest to the first time point in the resistance evolution sequence. Based on the pairing data, a second time point is determined in the resistance evolution sequence that does not correspond to the waveform record in the energy impact sequence. The second time point is then filled with the average of the energy impact values ​​of the two time points closest to the second time point in the energy impact sequence. The impedance evolution trajectory is obtained by arranging the standardized resistance value and energy impact value at each time point in the filled resistance evolution sequence and the filled energy impact sequence in chronological order.

5. The power tower health state comprehensive evaluation method based on multi-source data fusion according to claim 1, characterized in that, The similarity between the standardized resistance value and the energy surge value in the impedance evolution trajectory is calculated by gray-level correlation analysis, and the contribution of the energy surge value to the resistance increase trend is quantified using the similarity measure to obtain the first weight matrix, which includes: Calculate the absolute value of the difference between the standardized resistance value and the energy impact value at each time point in the impedance evolution trajectory to obtain the minimum absolute difference and the maximum absolute difference; The numerator value is obtained by multiplying the preset resolution coefficient and the maximum absolute difference, and then adding the product with the minimum absolute difference. The denominator value is obtained by multiplying the maximum absolute difference and the preset resolution coefficient, and then summing the product with each absolute difference. The ratio of the numerator value to the denominator value is calculated to obtain the correlation coefficient at each time point. The arithmetic mean of the correlation coefficients at all time points is used to obtain the similarity between the standardized resistance value and the energy impact value. The time point of the next measurement record in the adjacent measurement records of the resistance evolution sequence in which the standardized resistance value shows an increasing trend is determined as the target time point. The product of the similarity and the correlation coefficient of the target time point is calculated to obtain the weight of the target time point. The product of the preset baseline weight and the correlation coefficient of the non-target time point is calculated to obtain the weight of the non-target time point. All the weights are arranged in chronological order to obtain the first weight matrix. The non-target time point is the remaining time point in the impedance evolution trajectory other than the target time point.

6. The power tower health state comprehensive evaluation method based on multi-source data fusion according to claim 5, characterized in that, When the rate of change of the resistance evolution sequence exceeds a preset safety threshold, the weights of the corresponding time nodes in the first weight matrix are adjusted using a penalty factor determined based on the initial design parameters and service life of the target tower, resulting in a second weight matrix, including: The ratio of the difference in standardized resistance values ​​between adjacent measurement records in the resistance evolution sequence to the corresponding time interval is calculated to obtain the resistance change rate at each measurement record time point. The time points of measurement records where the resistance change rate is greater than a preset safety threshold and the time points in the first weight matrix where the weight is greater than the preset weight threshold are determined as risk time nodes. The ratio of the standardized resistance value at the risk time node to the grounding resistance design value in the initial design parameters of the target tower is calculated to obtain the resistance deviation coefficient. The ratio of the actual operating years of the target tower to the preset years is used as the years coefficient, and the product of the resistance deviation coefficient and the years coefficient is used as the penalty factor. By normalizing the product of the risk time node weights and the penalty factor in the first weight matrix, and replacing the weights of the risk time nodes in the first weight matrix, a second weight matrix is ​​obtained.

7. The power tower health state comprehensive evaluation method based on multi-source data fusion according to claim 1, characterized in that, The resistance evolution sequence and the energy impact sequence are weighted and fused based on the second weight matrix to obtain a health assessment score, which is then compared with a preset health threshold range to determine the target health status, including: The standardized resistance value of each measurement record in the resistance evolution sequence is normalized to obtain a normalized resistance value. The energy impact value of each waveform record in the energy impact sequence is normalized to obtain a normalized energy impact value. The product of the normalized resistance value and the weight of the corresponding time point in the second weight matrix is ​​used as the resistance weight value at the corresponding time point, and the product of the normalized energy impact value and the weight of the corresponding time point in the second weight matrix is ​​used as the energy weight value at the corresponding time point. The resistance weighted sum is obtained by summing the resistance weighted values ​​at all time points, the energy weighted sum is obtained by summing the energy weighted values ​​at all time points, and the total weight is obtained by summing all the weights in the second weight matrix. The ratio of the sum of the resistance weighted sum and the energy weighted sum to the total weighted sum is calculated to obtain the health assessment score; The target health status of the target tower is determined by comparing the health assessment score with multiple preset health threshold intervals.

8. A power tower health state comprehensive evaluation system based on multi-source data fusion, characterized in that, include: The acquisition module is used to acquire the grounding resistance measurement record, short-circuit current waveform record and soil moisture coefficient of the target tower within a preset time period; The correction module is used to correct the resistance value in the grounding resistance measurement record using the soil moisture coefficient to obtain the resistance evolution sequence, and to perform time integration on the short-circuit current waveform record to obtain the energy impact sequence. The mapping module is used to map the resistance evolution sequence and the energy impact sequence along the time axis to obtain the impedance evolution trajectory. The calculation module is used to calculate the similarity between the standardized resistance value and the energy impact value in the impedance evolution trajectory through gray-scale correlation analysis, and to use the similarity measure to quantify the contribution of the energy impact value to the resistance increase trend, thereby obtaining the first weight matrix. The adjustment module is used to adjust the weights of the corresponding time nodes in the first weight matrix by using a penalty factor determined based on the initial design parameters and operating years of the target tower when the rate of change of the resistance evolution sequence is greater than a preset safety threshold, so as to obtain a second weight matrix. The fusion module is used to perform weighted fusion of the resistance evolution sequence and the energy impact sequence based on the second weight matrix to obtain a health assessment score, and compare it with a preset health threshold range to determine the target health status.

9. An electronic device, comprising: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the comprehensive assessment method for the health status of power transmission towers based on multi-source data fusion as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, enables the implementation of the comprehensive assessment method for the health status of power transmission towers based on multi-source data fusion as described in any one of claims 1 to 7.

Images