A power transmission tower health state intelligent evaluation method and system

Abstract

The application discloses a kind of transmission tower health state intelligent evaluation method and system, the transmission tower is divided into zinc layer intact period and matrix corrosion period two stages to evaluate, first two stages of transmission tower health evaluation index, division health grade and corresponding expectation, entropy, super-entropy are calculated, and the membership of each secondary index is calculated, and the weight is modified by variable weight function.The comprehensive membership of each health grade is calculated based on the membership and weight of each secondary index, and then the health grade and degradation trend are determined.The application effectively solves the problem of weak degradation index covering serious fault index in fixed weight evaluation, and realizes the fine, dynamic and intelligent evaluation of transmission tower health state.

Description

Technical Field

[0001] This invention relates to the field of power equipment condition monitoring and intelligent assessment technology, specifically to a method and system for intelligent assessment of the health status of transmission towers. Background Technology

[0002] Transmission towers are one of the core pieces of equipment in power transmission systems. They bear the load and anchor the transmission lines and ground wires, and their operational health directly impacts the safe and stable operation of the power grid. Located in the field, transmission towers are frequently exposed to external factors such as wind, rain, icing, high temperatures, corrosion, strong wind vibrations, and geological subsidence, making them prone to defects such as tower tilting, component corrosion, loose bolts, main material bending, and structural fatigue damage. Failure to promptly identify and assess the health status of transmission towers can lead to major power grid accidents such as tower tilting, collapse, and line tripping, causing severe economic losses and the risk of power outages.

[0003] Currently, health status assessments of domestic power transmission towers mainly rely on manual inspections, single-sensor monitoring, and methods such as the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation. However, existing tower health assessments often use fixed weights. Fixed weights only reflect the relative importance of each indicator under ideal conditions. Once the weight values ​​are determined, they remain fixed throughout the assessment process and cannot adaptively adjust to the deterioration fluctuations of tower indicators in real-time measured data or the dynamic changes in operating status. During long-term service, power transmission towers are subject to the coupling effects of multiple factors, resulting in time-varying deterioration. Using fixed weights cannot dynamically adjust the contribution of key factors according to the degree of indicator deterioration, easily weakening the negative contribution of deteriorating indicators to the overall health status. It also results in insufficient sensitivity to abnormal indicators, making it difficult to uniformly handle the uncertainties of fuzziness and randomness in the assessment. This can easily mask local critical hidden dangers, leading to overly optimistic assessment results and the risk of misjudgment of safety. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent assessment method and system for the health status of transmission towers, aiming to overcome the technical defects of existing transmission tower health assessment methods, such as fixed weights, strong subjectivity, weak uncertainty handling capabilities, and low assessment accuracy, and to achieve dynamic, quantitative, and accurate assessment of the health status of transmission towers.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: A method for intelligently assessing the health status of power transmission towers, comprising the following steps: Multi-source data from power transmission towers are acquired and preprocessed; the multi-source data includes visible light data, infrared data, laser point cloud data, stress tilt angle sensing data, and meteorological data. The primary and secondary indicators for health assessment during the galvanized layer integrity period and the substrate corrosion period were determined separately. Based on preprocessed multi-source data, each secondary health assessment index for the zinc integrity period is calculated, and all zinc integrity period health assessment indices are converted into positive vector values. Then, the variable full cloud model is used to determine the health status of the zinc integrity period. Determine whether the substrate corrosion period has begun based on the health status of the zinc layer during its intact period; If the substrate enters the corrosion stage, calculate each health assessment index for the substrate corrosion stage, convert all health assessment indexes for the substrate corrosion stage into positive vector values, and then use the variable full cloud model to determine the health status of the substrate corrosion stage.

[0006] In the multi-source data preprocessing, the 3σ criterion is used to remove abnormal noise from the collected data. The range standardization formula is used to normalize all indicator data, unify the mapping of all indicator values, eliminate dimensional differences, and obtain a standardized indicator dataset. At the same time, the negative degradation indicators of zinc coating corrosion of iron towers are reversed and normalized, and uniformly transformed into positive vectorized evaluation values ​​in which the larger the value, the higher the integrity of the zinc coating, thus achieving a unified standard for all-dimensional evaluation indicators.

[0007] According to the above technical solution, the health assessment indicators for the integrity period of the galvanized layer include primary indicators and secondary indicators for the integrity period of the galvanized layer; The primary indicators for the integrity of the zinc layer include hydro-meteorological characteristics, structural mechanical characteristics, and zinc layer condition. The secondary indicators corresponding to the hydro-meteorological characteristics include daily rainfall, maximum wind speed, ice thickness, and ambient temperature; The secondary indicators corresponding to the structural mechanical characteristics include the structural stress stability state; The secondary indicators corresponding to the zinc layer condition include white rust coverage and coating peeling percentage.

[0008] According to the above technical solution, the health assessment indicators for the substrate corrosion period include primary indicators and secondary indicators for the substrate corrosion period; The primary indicators for the corrosion period of the substrate include hydro-meteorological characteristics, structural mechanical characteristics, geological foundation characteristics, and material deterioration characteristics; The secondary indicators corresponding to the hydro-meteorological characteristics include daily rainfall, maximum wind speed, ice thickness, and ambient temperature; The secondary indicators corresponding to the structural mechanical characteristics include stress fatigue damage state, tilt, deflection, and bolt torque; The secondary indicators corresponding to the basic geological features include settlement, soil moisture content, and permeability coefficient. The secondary indicators corresponding to the material deterioration characteristics include red rust coverage, pit depth, and cross-sectional loss rate.

[0009] Since the health assessment indicators for the two stages of transmission towers—the intact zinc coating stage and the substrate corrosion stage—are inconsistent, different indicator systems are constructed for evaluation, tailored to actual conditions. This invention constructs a multi-level indicator system covering structural status, material performance, and environmental impact, encompassing the core factors affecting the health of transmission towers, avoiding the one-sidedness of single-indicator assessments, and achieving a systematic assessment of the overall health status.

[0010] According to the above technical solution, the execution steps of the variable weight cloud model include: The health status of power transmission towers is divided into four health levels: healthy, sub-healthy, unhealthy, and dangerous. The expected value, entropy, and hyperentropy corresponding to each health level are calculated. The initial fixed weights of each secondary indicator are determined based on historical data using the entropy weight method. Based on the real-time status of the monitored secondary indicators, the initial fixed weights are dynamically adjusted using a variable weighting function to obtain the variable weights of each secondary indicator. Calculate the membership degree of each secondary indicator to each health level, using the following formula: : ; In the formula, The random entropy represents the health level k, where the random entropy is a normally distributed random number with the expected entropy and the standard deviation of the hyperentropy. For each health level, the membership degree of each secondary indicator is weighted and integrated according to the variable weight to obtain the comprehensive membership degree of the health level. The comprehensive membership degree of the health level with the largest comprehensive membership degree is selected as the health level of the tower.

[0011] If the highest membership level corresponds to the health level, the tower does not require special maintenance and should be maintained by regular periodic inspections; if it corresponds to the sub-health level, annual key inspections should be arranged and the deterioration trend should be tracked; if it corresponds to the unhealthy level, maintenance and rectification such as component corrosion prevention, bolt tightening, and foundation re-testing should be carried out within a specified period; if it corresponds to the dangerous level, the hidden danger warning should be activated immediately, and special reinforcement or tower replacement should be carried out to prevent tower collapse and line breakage accidents.

[0012] This invention combines variable weight theory to dynamically adjust weights, thereby increasing the weight of indicators as they deteriorate. This overcomes the limitations of fixed weights and accurately reflects the dynamic impact of each indicator on health status.

[0013] Based on the above technical solution, the expected health level ; The entropy of the health level ; The hyperentropy of the health level ; In the formula, This indicates the maximum score for the health level. This indicates the lower limit of the score for the health level. Represents the hyperentropy coefficient. The value range is 0.1 to 0.3.

[0014] According to the above technical solution, the variable weight function : ; In the formula, This represents the initial fixed weight of the i-th secondary indicator. express State-dependent weighting function Let represent the standardized positive vectorized value of the i-th secondary indicator; n represents the number of all secondary indicators. The initial fixed weight of the j-th secondary indicator, express State-dependent weighting function This represents the penalty intensity coefficient.

[0015] By dynamically adjusting the weights of each indicator based on its real-time degradation status using a variable weighting function, the variable weights of the indicators automatically increase when the indicators are severely degraded or the standardized values ​​are low. This strengthens the impact of fault indicators on the evaluation results, prevents minor indicators from masking major hidden dangers, and significantly improves the sensitivity of fault identification.

[0016] According to the above technical solution, the penalty intensity coefficient The determination steps include: The health status of power transmission towers is divided into four health levels: healthy, sub-healthy, unhealthy, and dangerous, and the corresponding penalty intensity coefficient ranges are determined. The penalty intensity coefficient range of the transmission tower health level at the previous moment is selected as the basic penalty intensity coefficient range at time t. The sum of the weights of all secondary indicators related to the tower's health level at the previous moment is used as the penalty weight. ; The value of the penalty intensity coefficient at time t is calculated based on the penalty weight and the penalty coefficient mapping formula. The penalty coefficient mapping formula ; In the formula, This represents the lower limit of the range of basic penalty intensity coefficients. This represents the upper limit of the range of the basic penalty intensity coefficient.

[0017] This invention introduces the sum of the weights of the secondary indicators of the tower's health level at the previous moment as the penalty weight, which can quantify the overall deterioration degree of the transmission tower in the early stage. Using this as an interpolation variable, the penalty intensity coefficient at the current moment is calculated, enabling the penalty intensity to adaptively increase or decrease with the tower's operating condition deterioration level, conforming to the variable weight mechanism that the more severe the deterioration, the stronger the penalty. Simultaneously, it relies on time-series level constraints to ensure... The values ​​are stable and continuous, without sudden jumps, avoiding the subjective bias of manually fixed coefficients and improving the objectivity and stability of health assessments.

[0018] According to the above technical solution, if the health level of the tower during the period when the galvanized layer is intact is unhealthy or dangerous, and the weighted sum of the secondary indicators of the zinc layer status index during the period when the galvanized layer is intact is greater than or equal to the weighted threshold F, then the transmission tower is considered to have entered the base corrosion period, and the health assessment index of the base corrosion period is used for health assessment.

[0019] By using both health level and weight threshold constraints, misjudgments caused by fluctuations in a single indicator can be avoided, enabling early identification and prediction of the substrate corrosion period during the intact galvanized layer stage.

[0020] This includes a technical solution: an intelligent assessment system for the health status of power transmission towers, comprising: The data acquisition module is used to acquire multi-source data from power transmission towers for preprocessing; the multi-source data includes visible light data, infrared data, laser point cloud data, stress tilt angle sensing data, and meteorological data. The assessment index determination module is used to determine the primary and secondary indicators for health assessment of the galvanized layer integrity period and the substrate corrosion period, respectively. The zinc integrity period assessment module calculates each secondary health assessment index for the zinc integrity period based on preprocessed multi-source data, converts all zinc integrity period health assessment indexes into positive vector values, and then uses a variable full cloud model to determine the health status of the zinc integrity period. The substrate corrosion period determination module determines whether the substrate corrosion period has begun based on the health status of the zinc layer during its intact period. The assessment of the substrate corrosion period involves calculating each health assessment index for the substrate corrosion period if it has entered the corrosion period, converting all health assessment indexes for the substrate corrosion period into positive vector values, and then using the variable full cloud model to determine the health status of the substrate corrosion period.

[0021] The invention includes a technical solution, an electronic device comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute a method for intelligent assessment of the health status of power transmission towers as described above.

[0022] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: This invention evaluates transmission towers in two stages: the zinc layer integrity period and the substrate corrosion period. First, it determines the health assessment indicators for the two stages, classifies health levels, calculates the corresponding expected value, entropy, and hyperentropy, and calculates the membership degree of each secondary indicator. A variable weight function is used to correct the weights. Based on the membership degree and weight of each secondary indicator, the comprehensive membership degree of each health level is calculated, thereby determining the health level and degradation trend. This invention effectively solves the problems of weak degradation indicators masking serious fault indicators and the interference of harsh operating condition monitoring data with assessment accuracy in fixed-weight assessments. It achieves refined, dynamic, and intelligent assessment of the health status of transmission towers, resulting in higher accuracy and reliability of the assessment results. It can be widely applied to the operation and maintenance, risk prediction, and status management of transmission towers of various voltage levels, providing technical support for lean operation and maintenance of power grid equipment. Attached Figure Description

[0023] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of the steps of an intelligent assessment method for the health status of power transmission towers according to the present invention; Figure 2 This is a flowchart of the execution steps of the variable power cloud model; Figure 3 This is a flowchart for determining the penalty intensity coefficient. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] Example 1: A 220kV mountain transmission line angle steel tower was used as the implementation object. Tower type: 2G1-ZB1, tower height: 42m, cross-sectional height: 30m, foundation type: slab-type cast-in-place concrete foundation. Located in a mountainous area of ​​Guangxi with heavy rainfall, strong weathering, and large topographic relief. A total of 68 sets of online monitoring and manual inspection data were collected, including indicators across all dimensions such as foundation settlement, tilt, stress, moisture content, corrosion, wind speed, and rainfall. During the implementation, phenomena such as slowly increasing foundation settlement, increased tilt rate during the rainy season, and intensified local steel corrosion were observed. The intelligent health status assessment method for transmission towers of this invention was applied to conduct a health assessment of the transmission tower. The specific steps include: S1. Through GNSS tilt monitoring, 3D laser scanning, electrochemical corrosion detection, intelligent torque detection, environmental sensors, visible light detection, infrared detection and other methods, multi-source data of power transmission towers, such as tower body tilt, tower material corrosion rate, bolt tightening rate, foundation settlement, and environmental salt spray concentration, are acquired in batches.

[0026] The acquired multi-source data underwent preprocessing, including identifying and removing outliers from gross error data caused by sensor drift, on-site interference, and manual reading errors using the Grubbs criterion and the 3σ criterion; for critical, small amounts of outlier data, neighborhood mean correction was used to avoid direct data loss leading to sample distortion. Time-series linear interpolation was used to complete missing data due to remote locations, extreme weather, or short-term equipment offline. Furthermore, differences in the dimensions and orders of magnitude of various indicators were eliminated, and a unified quantification scale was established.

[0027] S2. Determine the primary and secondary indicators for health assessment during the galvanized layer integrity period and the substrate corrosion period, respectively. Among them, the health assessment indicators for the integrity period of the galvanized coating include primary and secondary indicators for the integrity period of the galvanized coating; The primary indicators for the integrity of the zinc layer include hydro-meteorological characteristics, structural mechanical characteristics, and the state of the zinc layer. The secondary indicators corresponding to hydrometeorological characteristics include daily rainfall, maximum wind speed, ice thickness, and ambient temperature; The secondary indicators corresponding to the structural mechanical characteristics include the structural stress stability state; The secondary indicators corresponding to the zinc coating condition include white rust coverage and coating peeling percentage.

[0028] The health assessment indicators for the substrate corrosion period include primary and secondary indicators for the substrate corrosion period; The primary indicators for the corrosion period of the matrix include hydro-meteorological characteristics, structural mechanical characteristics, geological foundation characteristics, and material deterioration characteristics; The secondary indicators corresponding to hydrometeorological characteristics include daily rainfall, maximum wind speed, ice thickness, and ambient temperature; The secondary indicators corresponding to structural mechanical characteristics include stress fatigue damage state, tilt, deflection, and bolt torque; Secondary indicators corresponding to basic geological characteristics include settlement, soil moisture content, and permeability coefficient; Secondary indicators corresponding to material degradation characteristics include red rust coverage, pitting depth, and cross-sectional loss rate.

[0029] S3. Calculate each secondary health assessment index for the zinc layer integrity period based on preprocessed multi-source data, and convert all zinc layer integrity period health assessment indices into a unified positive score of [0,1]. The higher the score, the better the health status of the component and the more stable its performance.

[0030] The steps for determining the health status of the zinc layer during its intact phase using a variable full-cloud model include: S301. The health status of transmission towers is divided into four levels: healthy, sub-healthy, unhealthy, and dangerous. The expected value, entropy, and hyperentropy corresponding to each health level are calculated (Table 1). The expected value of each health level... Entropy of health level Health level hyperentropy .

[0031] Table 1 Expected, entropy, and hyperentropy of transmission tower health healthy [0.8,1] 0.9 0.033 0.0033 Sub-health [0.6,0.8) 0.7 0.033 0.0033 Unhealthy [0.3,0.6) 0.45 0.05 0.005 healthy [0,0.3) 0.15 0.05 0.005 S302. Select 12 consecutive sets of historical monitoring data from different operating periods of the transmission tower, screen valid monitoring samples, perform normalization and homogenization preprocessing on all original monitoring data of the third-level indicators, map them uniformly to the 0-1 evaluation range, eliminate the differences in the dimensions and orders of magnitude of different indicators, and construct a standardized historical evaluation matrix of the second-level indicators.

[0032] For each preprocessed secondary indicator data, calculate the indicator proportion weight of the i-th group of historical samples under the j-th secondary indicator.

[0033] Based on the sample weight matrix, the information entropy value of each secondary indicator is calculated.

[0034] The difference coefficients of each secondary indicator are calculated based on the entropy value. The difference coefficients directly reflect the distinguishing ability of the indicators. The difference coefficients of each secondary indicator are normalized to obtain the initial fixed weights of each secondary indicator.

[0035] In this embodiment, the initial fixed weights of each secondary indicator are obtained through iterative calculation using the historical data entropy weight method. For example, the white rust coverage rate is 0.093 and the ambient wind speed is 0.175. After normalization, the sum of each weight is 1.

[0036] The initial fixed weights are generated entirely based on the actual historical data of the tower's operation, which can objectively characterize the inherent impact of different secondary indicators on the health deterioration of the transmission tower.

[0037] S303. Based on the real-time status of the monitored secondary indicators, the initial fixed weights are dynamically adjusted using a variable weighting function to obtain the variable weights of each secondary indicator.

[0038] Among them, the variable weight function : ; In the formula, This represents the initial fixed weight of the i-th secondary indicator. express State-dependent weighting function Let represent the standardized positive vectorized value of the i-th secondary indicator; n represents the number of all secondary indicators. This represents the initial fixed weight of the j-th secondary indicator. express State-dependent weighting function This represents the penalty intensity coefficient.

[0039] Simultaneously, the penalty intensity coefficient The adaptive determination process includes the following steps: ① Determine the penalty intensity coefficient range for each of the four health levels of power transmission towers: healthy, sub-healthy, unhealthy, and dangerous. ② Select the penalty intensity coefficient range of the transmission tower's health level at the previous moment as the basic penalty intensity coefficient range at moment t. In this embodiment, the transmission tower's assessment result at moment t-1 is sub-healthy. According to the preset level correspondence, the basic penalty intensity coefficient range at moment t is determined to be (0.2, 0.5). This range is used as the benchmark range for correcting the penalty coefficient at the current moment.

[0040] ③ The sum of the weights of all secondary indicators of the tower's health level at the previous moment is used as the penalty weight. In this embodiment, the secondary indicators of the power transmission tower's sub-health state at time t-1 are the white rust coverage rate and the coating peeling percentage. Therefore, the penalty weight... = Weight of white rust coverage + Weight of coating peeling percentage = 0.30 + 0.25 = 0.55.

[0041] ④ Calculate the value of the penalty intensity coefficient at time t using the penalty coefficient mapping formula based on the penalty weight; Among them, the penalty coefficient mapping formula ; In the formula, This represents the lower limit of the range of basic penalty intensity coefficients. This represents the upper limit of the range of the basic penalty intensity coefficient.

[0042] The calculation in this embodiment is .

[0043] S304. Calculate the membership degree of each secondary indicator to each health level, wherein the membership degree calculation formula is as follows: : ; In the formula, The random entropy represents the health level k, where the random entropy is a normally distributed random number with the expected entropy and the standard deviation of the hyperentropy.

[0044] S305. Using the obtained variable weights as weighting coefficients, linearly weight and fuse the membership degrees of each secondary indicator corresponding to the same health level, and calculate the comprehensive membership degree of the transmission tower corresponding to the four levels of healthy, sub-healthy, unhealthy, and dangerous. Select the largest comprehensive membership degree of the health level as the tower's health level.

[0045] In this embodiment, the overall membership degree of the health level is calculated to be 0.286, the overall membership degree of the sub-health level is 0.527, the overall membership degree of the unhealthy level is 0.148, and the overall membership degree of the dangerous level is 0.039.

[0046] According to the maximum membership criterion, the maximum value of the sub-health level is 0.527, therefore the overall health status of the transmission tower is determined to be sub-healthy.

[0047] This indicates that the overall structure and foundation of the transmission tower are in good condition, but the surface galvanized anti-corrosion layer has deteriorated significantly, which is the main weak point and potential hazard. This is consistent with the actual working condition of thinning zinc layer and localized rust measured on site.

[0048] The recommended maintenance measures are to shorten the inspection cycle, carry out anti-corrosion repair treatment on rusted areas, track the deterioration trend of the zinc layer, and prevent it from further evolving into component corrosion defects.

[0049] S4. Because the current health level of the transmission tower is sub-healthy, the transmission tower has not yet entered the substrate corrosion period.

[0050] Example 2: If the transmission tower enters the substrate corrosion period, the intelligent health status assessment method of the present invention is applied to conduct a health assessment of the transmission tower. The specific steps include: L1 uses GNSS tilt monitoring, 3D laser scanning, electrochemical corrosion detection, intelligent torque detection, environmental sensors, visible light detection, and infrared detection to acquire multi-source data on power transmission towers, including tower tilt, tower material corrosion rate, bolt tightening rate, foundation settlement, and environmental salt spray concentration.

[0051] L2. Determine the health assessment indicators for the substrate corrosion period, including primary and secondary indicators for the substrate corrosion period; The primary indicators for the corrosion period of the matrix include hydro-meteorological characteristics, structural mechanical characteristics, geological foundation characteristics, and material deterioration characteristics; The secondary indicators corresponding to hydrometeorological characteristics include daily rainfall, maximum wind speed, ice thickness, and ambient temperature; The secondary indicators corresponding to structural mechanical characteristics include stress fatigue damage state, tilt, deflection, and bolt torque; Secondary indicators corresponding to basic geological characteristics include settlement, soil moisture content, and permeability coefficient; Secondary indicators corresponding to material degradation characteristics include red rust coverage, pitting depth, and cross-sectional loss rate.

[0052] L3. Calculate each secondary health assessment index for the zinc layer integrity period based on preprocessed multi-source data, and convert all the health assessment indexes for the substrate corrosion period into a unified positive score of [0,1]. The higher the score, the better the health status of the component and the more stable its performance.

[0053] The steps for determining the health status of the substrate during the corrosion period using a variable full cloud model include: L301. The health status of transmission towers is divided into four levels: healthy, sub-healthy, unhealthy, and dangerous. The expected value, entropy, and hyperentropy corresponding to each health level are calculated (Table 2). The expected value of each health level... Entropy of health level Health level hyperentropy .

[0054] Table 2 Expected, entropy, and hyperentropy of transmission tower health healthy [0.75,1.00] 0.875 0.0417 0.0042 Sub-health [0.50,0.75) 0.625 0.0417 0.0042 Unhealthy [0.25,0.50) 0.375 0.0417 0.0042 healthy [0,0.25) 0.175 0.0417 0.0042 L302. Select 12 consecutive sets of historical monitoring data from different operating periods of the transmission tower, screen valid monitoring samples, perform normalization and homogenization preprocessing on all original monitoring data of the third-level indicators, uniformly map them to the 0-1 evaluation range, eliminate the differences in the dimensions and orders of magnitude of different indicators, and construct a standardized historical evaluation matrix of the second-level indicators.

[0055] For each preprocessed secondary indicator data, calculate the indicator proportion weight of the i-th group of historical samples under the j-th secondary indicator.

[0056] Based on the sample weight matrix, the information entropy value of each secondary indicator is calculated.

[0057] The difference coefficients of each secondary indicator are calculated based on the entropy value. The difference coefficients directly reflect the distinguishing ability of the indicators. The difference coefficients of each secondary indicator are normalized to obtain the initial fixed weights of each secondary indicator.

[0058] In this embodiment, the initial fixed weights of each secondary index are obtained through iterative calculation using the entropy weight method based on historical data. For example, the tower tilt is 0.112, the main material stress is 0.105, the component deflection is 0.086, the foundation settlement is 0.128, the foundation erosion depth is 0.093, the soil moisture content is 0.102, and the ambient wind speed is 0.065. After normalization, the sum of each weight is 1.

[0059] The initial fixed weights are generated entirely based on the actual historical data of the tower's operation, which can objectively characterize the inherent impact of different secondary indicators on the health deterioration of the transmission tower.

[0060] L303. Based on the real-time status of the monitored secondary indicators, the initial fixed weights are dynamically adjusted using a variable weighting function to obtain the variable weights of each secondary indicator.

[0061] Among them, the variable weight function : ; In the formula, This represents the initial fixed weight of the i-th secondary indicator. express State-dependent weighting function Let represent the standardized positive vectorized value of the i-th secondary indicator; n represents the number of all secondary indicators. This represents the initial fixed weight of the j-th secondary indicator. express State-dependent weighting function This represents the penalty intensity coefficient.

[0062] Simultaneously, the penalty intensity coefficient The adaptive determination process includes the following steps: ① Determine the health status of transmission towers and classify them into four health levels: healthy, sub-healthy, unhealthy, and dangerous, and determine the corresponding penalty intensity coefficient ranges.

[0063] ② Select the penalty intensity coefficient range of the health level of the transmission tower at the previous moment as the basic penalty intensity coefficient range at time t.

[0064] ③ The sum of the weights of all secondary indicators of the transmission tower health level at the previous moment is used as the penalty weight. .

[0065] ④ Calculate the value of the penalty intensity coefficient at time t using the penalty coefficient mapping formula based on the penalty weight; Among them, the penalty coefficient mapping formula ; In the formula, This represents the lower limit of the range of basic penalty intensity coefficients. This represents the upper limit of the range of the basic penalty intensity coefficient.

[0066] L304. Calculate the membership degree of each secondary indicator to each health level. The membership degree calculation formula is as follows: : ; In the formula, The random entropy represents the health level k, where the random entropy is a normally distributed random number with the expected entropy and the standard deviation of the hyperentropy.

[0067] L305. The obtained variable weights are used as weighting coefficients. The membership degrees of each secondary indicator corresponding to the same health level are linearly weighted and fused to calculate the comprehensive membership degree of the transmission tower corresponding to the four levels of health, sub-health, unhealthy and dangerous.

[0068] In this embodiment, the overall membership degree of the health level is calculated to be 0.102, the overall membership degree of the sub-health level is 0.215, the overall membership degree of the unhealthy level is 0.568, and the overall membership degree of the dangerous level is 0.115.

[0069] Based on the maximum membership criterion, the maximum value of the comprehensive membership degree for the unhealthy level is 0.568, and the health level of the transmission tower during the substrate corrosion period is determined to be unhealthy.

[0070] This indicates that the galvanized protective layer of the tower has completely failed, the steel substrate is extensively corroded, the cross-sectional area of ​​the components is severely damaged, and the load-bearing capacity of the equipment has decreased significantly, posing a structural safety hazard. Therefore, it is necessary to shut down the power supply within a specified period to carry out rust removal, anti-corrosion reinforcement, and replacement of damaged components, and to increase real-time online monitoring to prevent tower collapse accidents caused by strong winds and rain.

[0071] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0072] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligently assessing the health status of power transmission towers, characterized in that, The steps include: Acquire multi-source data from power transmission towers and perform preprocessing; The primary and secondary indicators for health assessment during the galvanized layer integrity period and the substrate corrosion period were determined separately. Based on preprocessed multi-source data, each secondary health assessment index for the zinc integrity period is calculated, and all zinc integrity period health assessment indices are converted into positive vector values. Then, the variable full cloud model is used to determine the health status of the zinc integrity period. Determine whether the substrate corrosion period has begun based on the health status of the zinc layer during its intact period; If the substrate enters the corrosion stage, calculate each health assessment index for the substrate corrosion stage, convert all health assessment indexes for the substrate corrosion stage into positive vector values, and then use the variable full cloud model to determine the health status of the substrate corrosion stage.

2. The intelligent assessment method for the health status of transmission towers according to claim 1, characterized in that: The primary indicators for the health assessment of the galvanized layer during its integrity period include hydrometeorological characteristics, structural mechanical characteristics, and the condition of the zinc layer. The secondary indicators corresponding to the hydro-meteorological characteristics include daily rainfall, maximum wind speed, ice thickness, and ambient temperature; The secondary indicators corresponding to the structural mechanical characteristics include the structural stress stability state; The secondary indicators corresponding to the zinc layer condition include white rust coverage and coating peeling percentage.

3. The intelligent assessment method for the health status of transmission towers according to claim 1, characterized in that: The primary indicators for the health assessment of the substrate during the corrosion period include hydrometeorological characteristics, structural mechanical characteristics, geological foundation characteristics, and material deterioration characteristics; The secondary indicators corresponding to the hydro-meteorological characteristics include daily rainfall, maximum wind speed, ice thickness, and ambient temperature; The secondary indicators corresponding to the structural mechanical characteristics include stress fatigue damage state, tilt, deflection, and bolt torque; The secondary indicators corresponding to the basic geological features include settlement, soil moisture content, and permeability coefficient. The secondary indicators corresponding to the material deterioration characteristics include red rust coverage, pit depth, and cross-sectional loss rate.

4. The intelligent assessment method for the health status of transmission towers according to claim 3, characterized in that, The execution steps of the variable power cloud model include: The health status of power transmission towers is divided into four health levels: healthy, sub-healthy, unhealthy, and dangerous. The expected value, entropy, and hyperentropy corresponding to each health level are calculated. The initial fixed weights of each secondary indicator are determined based on historical data using the entropy weight method. Based on the real-time status of the monitored secondary indicators, the initial fixed weights are dynamically adjusted using a variable weighting function to obtain the variable weights of each secondary indicator. Calculate the membership degree of each secondary indicator to each health level, using the following formula: : ； In the formula, The random entropy represents the health level k, where the random entropy is a normally distributed random number with the expected entropy and the standard deviation of the hyperentropy. For each health level, the membership degree of each secondary indicator is weighted and integrated according to the variable weight to obtain the comprehensive membership degree of the health level. The comprehensive membership degree of the health level with the largest comprehensive membership degree is selected as the health level of the tower.

5. The intelligent assessment method for the health status of transmission towers according to claim 4, characterized in that: The expected health level ; The entropy of the health level ; The hyperentropy of the health level ; In the formula, This indicates the maximum score for the health level. This indicates the lower limit of the score for the health level. Represents the hyperentropy coefficient. The value range is 0.1 to 0.

3.

6. The intelligent assessment method for the health status of transmission towers according to claim 4, characterized in that: The weighting function : ； In the formula, This represents the initial fixed weight of the i-th secondary indicator. express State-dependent weighting function Let represent the standardized positive vectorized value of the i-th secondary indicator; n represents the number of all secondary indicators. This represents the initial fixed weight of the j-th secondary indicator. express State-dependent weighting function This represents the penalty intensity coefficient.

7. The intelligent assessment method for the health status of transmission towers according to claim 6, characterized in that: The penalty intensity coefficient The determination steps include: The health status of power transmission towers is divided into four health levels: healthy, sub-healthy, unhealthy, and dangerous, and the corresponding penalty intensity coefficient ranges are determined. The penalty intensity coefficient range of the transmission tower health level at the previous moment is selected as the basic penalty intensity coefficient range at time t. The sum of the weights of all secondary indicators related to the tower's health level at the previous moment is used as the penalty weight. ; The value of the penalty intensity coefficient at time t is calculated based on the penalty weight and the penalty coefficient mapping formula. The penalty coefficient mapping formula ; In the formula, This represents the lower limit of the range of basic penalty intensity coefficients. This represents the upper limit of the range of the basic penalty intensity coefficient.

8. The intelligent assessment method for the health status of transmission towers according to claim 1, characterized in that... If the health level of the transmission tower during the period when the galvanized layer is intact is unhealthy or dangerous, and the weighted sum of the secondary indicators of the zinc layer status index during the period when the galvanized layer is intact is greater than or equal to the weighted threshold F, then the transmission tower is considered to have entered the base corrosion period, and the health assessment index of the base corrosion period is used for health assessment.

9. An intelligent assessment system for the health status of power transmission towers, characterized in that, include: The data acquisition module is used to acquire multi-source data from power transmission towers for preprocessing; the multi-source data includes visible light data, infrared data, laser point cloud data, stress tilt angle sensing data, and meteorological data. The assessment index determination module is used to determine the primary and secondary indicators for health assessment of the galvanized layer integrity period and the substrate corrosion period, respectively. The zinc integrity period assessment module calculates each secondary health assessment index for the zinc integrity period based on preprocessed multi-source data, converts all zinc integrity period health assessment indexes into positive vector values, and then uses a variable full cloud model to determine the health status of the zinc integrity period. The substrate corrosion period determination module determines whether the substrate corrosion period has begun based on the health status of the zinc layer during its intact period. The assessment of the substrate corrosion period involves calculating each health assessment index for the substrate corrosion period if it has entered the corrosion period, converting all health assessment indexes for the substrate corrosion period into positive vector values, and then using the variable full cloud model to determine the health status of the substrate corrosion period.

10. An electronic device, characterized in that, include: One or more processors; A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the method according to any one of claims 1-8.

Images