Steel structure tower evaluation method, device, equipment, medium and program product

Abstract

The application provides a steel structure tower evaluation method, device, equipment, medium and program product, relates to the artificial intelligence technical field, and is used for improving the accuracy of the evaluation result of the steel structure tower. The specific technical scheme is: obtaining N degradation characteristic information corresponding to N detection indexes included in the first real-time detection parameter of the steel structure tower, N being a positive integer, one detection index corresponding to one degradation characteristic information; adjusting the weight corresponding to the N detection indexes based on the N degradation characteristic information; obtaining a fusion feature vector based on the adjusted weight of the N detection indexes and the N degradation characteristic information; obtaining the first health degree score corresponding to the steel structure tower based on the fusion feature vector, and the first health degree score is used for indicating the stability degree of the steel structure tower. The application is applied to the steel structure tower stability evaluation scene.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, equipment, medium, and program product for evaluating steel structure towers. Background Technology

[0002] Currently, steel structure towers (such as power transmission steel structure towers and communication single-tube towers) are key infrastructure for energy and communication networks, and their long-term stable operation is crucial to ensuring the safety of related industries.

[0003] In related technologies, to ensure the stable operation of steel structure towers, manual inspections are typically conducted every 1-3 months. However, in this method, because manual inspections are only conducted once every 1-3 months, the long inspection cycle makes it impossible to promptly capture sudden stress changes in the steel structure tower caused by strong winds, the number of load antennas, and icing. This results in low accuracy of the assessment results of the steel structure tower based on manual inspections under variable operating conditions. Summary of the Invention

[0004] This application provides a method for evaluating steel structure towers, which improves the accuracy of evaluation results for steel structure towers.

[0005] In a first aspect, embodiments of this application provide a method for evaluating steel structure towers. The method includes: acquiring N deterioration feature information corresponding to N detection indicators included in the first real-time detection parameters of the steel structure tower, where N is a positive integer and one detection indicator corresponds to one deterioration feature information; adjusting the weights corresponding to the N detection indicators based on the N deterioration feature information; obtaining a fused feature vector based on the adjusted weights of the N detection indicators and the N deterioration feature information; and obtaining a first health score corresponding to the steel structure tower based on the fused feature vector, wherein the first health score is used to indicate the stability of the steel structure tower.

[0006] The technical solution provided in this application brings at least the following beneficial effects: Since the weights corresponding to the N detection indicators can be adjusted in real time according to the changes in the current working conditions, the fused feature vector can be obtained by adjusting the data source weights, and the fused feature vector can be used as the input of the health assessment model to output a quantitative health score that conforms to the current working conditions, without the need for manual inspection, thus improving the accuracy of the assessment results of the steel structure tower.

[0007] One possible implementation involves the following first real-time detection parameters: defect data indicators, simulated load-bearing capacity data indicators, status data indicators, and historical operation and maintenance data indicators. Based on N degradation characteristic information, the weights corresponding to the N detection indicators are adjusted, including: calculating the coefficient of variation based on the degradation characteristic information corresponding to the simulated load-bearing capacity data indicators and status data indicators; determining the risk enhancement factor corresponding to the simulated load-bearing capacity data indicators and status data indicators based on the coefficient of variation; and adjusting the weights corresponding to the N detection indicators based on the risk enhancement factor.

[0008] Another possible implementation involves adjusting the weights of N detection indicators based on a risk enhancement factor. This includes: calculating the adjusted first weight for the simulation capacity data indicators based on the initial weights and the corresponding risk enhancement factor; calculating the adjusted second weight for the status data indicators based on the initial weights and the corresponding risk enhancement factor; calculating the adjusted third weight for the historical maintenance data indicators based on the sum of the initial weights, the first weight, and the second weight; and calculating the adjusted fourth weight for the defect data indicators based on the sum of the initial weights, the first weight, the second weight, and the third weight.

[0009] Another possible implementation is to obtain a fused feature vector based on the adjusted weights of N detection indicators and N degradation feature information, which includes: weighted summation of the adjusted weights of N detection indicators and N degradation feature information to obtain the fused feature vector.

[0010] Another possible implementation method, after obtaining the first health score corresponding to the steel structure tower based on the fused feature vector, further includes: when a decrease in the health score corresponding to the steel structure tower is detected, performing data analysis processing on the first real-time detection parameter to obtain the analysis result corresponding to the first real-time detection parameter; and generating a steel structure tower operation and maintenance strategy based on the location and probability of hidden dangers included in the analysis result.

[0011] Secondly, embodiments of this application provide a steel structure tower evaluation device, including: an acquisition module, an adjustment module, and a processing module. The acquisition module is used to acquire N deterioration feature information corresponding to N detection indicators included in the first real-time detection parameters of the steel structure tower, where N is a positive integer, and one detection indicator corresponds to one deterioration feature information. The adjustment module is used to adjust the weights corresponding to the N detection indicators based on the N deterioration feature information. The processing module is used to obtain a fused feature vector based on the adjusted weights of the N detection indicators and the N deterioration feature information; and based on the fused feature vector, to obtain a first health score corresponding to the steel structure tower, the first health score indicating the stability of the steel structure tower.

[0012] One possible implementation involves the following first real-time detection parameters: defect data indicators, simulated load-bearing capacity data indicators, status data indicators, and historical operation and maintenance data indicators. An adjustment module is specifically used to calculate the coefficient of variation based on the deterioration characteristic information corresponding to the simulated load-bearing capacity data indicators and status data indicators. The coefficient of variation is used to indicate the degree of structural change in the steel tower. Based on the coefficient of variation, a risk enhancement factor is determined corresponding to the simulated load-bearing capacity data indicators and status data indicators. The risk enhancement factor is used to indicate the risk level of the steel tower. Based on the risk enhancement factor, the weights corresponding to the N detection indicators are adjusted.

[0013] Another possible implementation involves the aforementioned adjustment module specifically used to calculate the adjusted first weight for the simulation capacity data indicators based on the initial weights of the simulation capacity data indicators and the corresponding risk enhancement factors; to calculate the adjusted second weight for the status data based on the initial weights of the status data and the corresponding risk enhancement factors; to calculate the adjusted third weight for the historical operation and maintenance data indicators based on the initial weights of the historical operation and maintenance data indicators and the sum of the first and second weights; and to calculate the adjusted fourth weight for the defect data indicators based on the sum of the initial weights of the defect data indicators and the first, second, and third weights.

[0014] Another possible implementation is that the above processing module is specifically used to perform a weighted summation of the adjusted weights of N detection indicators and N deterioration feature information to obtain a fused feature vector.

[0015] In another possible implementation, the above processing module is further configured to, after obtaining the first health score corresponding to the steel structure tower based on the fused feature vector, perform data analysis processing on the first real-time detection parameter when a decrease in the health score corresponding to the steel structure tower is detected, to obtain the analysis result corresponding to the first real-time detection parameter; and generate a steel structure tower operation and maintenance strategy based on the location and probability of hidden dangers included in the analysis result.

[0016] Thirdly, this application provides an electronic device comprising: a processor and a memory; the memory stores a program or instructions executable on the processor, wherein the program or instructions, when executed by the processor, implement the method of the first aspect described above.

[0017] Fourthly, this application provides a readable storage medium on which a program or instructions are stored, which, when executed by a computer, implement the method of the first aspect described above.

[0018] Fifthly, this application provides a computer program product stored in a storage medium, which, when executed by a computer, implements the method described in the first aspect.

[0019] In a sixth aspect, embodiments of this application provide a chip including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the method described in the first aspect.

[0020] The beneficial effects of the second to sixth aspects mentioned above are described in the corresponding description of the first aspect and will not be repeated here. Attached Figure Description

[0021] Figure 1 A schematic diagram of the network architecture for the application of a steel structure tower evaluation method provided in this application embodiment;

[0022] Figure 2 A flowchart illustrating a steel structure tower evaluation method provided in this application embodiment;

[0023] Figure 3 A flowchart illustrating another steel structure tower evaluation method provided in this application embodiment;

[0024] Figure 4 A flowchart illustrating another steel structure tower evaluation method provided in this application embodiment;

[0025] Figure 5 A flowchart illustrating another steel structure tower evaluation method provided in this application embodiment;

[0026] Figure 6 A flowchart illustrating another steel structure tower evaluation method provided in this application embodiment;

[0027] Figure 7 A flowchart illustrating another steel structure tower evaluation method provided in this application embodiment;

[0028] Figure 8 This is a structural schematic diagram of a steel structure tower evaluation system provided in an embodiment of this application;

[0029] Figure 9 This is a structural schematic diagram of a steel structure tower evaluation device provided in an embodiment of this application;

[0030] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0031] The following is a detailed description, with reference to the accompanying drawings, of the steel structure tower evaluation method, apparatus, equipment, media, and procedure products provided in this application.

[0032] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0033] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0034] The terms "at least one," "at least one of," etc., used in the specification and claims of this application refer to any one, any two, or a combination of two or more of the included items. For example, at least one of a, b, and c can mean: "a," "b," "c," "a and b," "a and c," "b and c," and "a, b, and c," where a, b, and c can be single or multiple. Similarly, "at least two" refers to two or more items, and its meaning is similar to that of "at least one."

[0035] In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0036] The embodiments of this application provide a method, apparatus, equipment, medium, and program product for evaluating steel structure towers, which can be applied to scenarios involving the stability evaluation of steel structure towers.

[0037] In existing technologies, steel structure towers (including power transmission steel structure towers, communication single-tube towers / guested towers, etc.) are core infrastructures for power and communication networks, and their health directly affects energy and communication security. Currently, the operation and maintenance of steel structure towers faces five major pain points:

[0038] (1) Limitations of monitoring methods: Traditional methods rely on manual inspections, which have poor real-time performance (the cycle is usually 1-3 months). They cannot capture sudden changes in stress in steel structure towers caused by strong winds, the number of load antennas, and icing in a timely manner. Furthermore, they rely on the professionalism of maintenance personnel and are prone to missing hidden dangers such as loose bolts and slack guy wires, as well as safety hazards such as personnel climbing to higher places.

[0039] (2) Insufficient data fusion: Existing solutions mostly use a single data source (such as only sensors or only drones), without integrating "real-time sensor data + drone defect data + finite element simulation data + historical operation and maintenance data", resulting in a one-sided evaluation dimension;

[0040] (3) Static weight allocation: Although some equipment health assessment schemes adopt multi-source fusion, the weights are fixed and cannot cope with changes in working conditions such as strong winds and icing, which can easily lead to assessment bias.

[0041] (4) No quantitative grading: Some solutions only alarm "abnormal / normal" without quantification of health from 0 to 100 points, which cannot guide operation and maintenance priorities.

[0042] (5) Lack of attribution analysis: It can only provide the health status result, but it is difficult to accurately locate the core causes of the decline in health status (such as weld cracks, foundation settlement, material fatigue, etc.), resulting in a lack of targeted operation and maintenance decisions;

[0043] To address the aforementioned technical issues, this application provides a method, apparatus, equipment, medium, and program product for evaluating steel structure towers. Since the weights corresponding to the N detection indicators can be adjusted in real time according to changes in the current working conditions, a fused feature vector is obtained through the adjusted data source weights. This fused feature vector is then used as the input to the health assessment model, which can output a quantitative health score that conforms to the current working conditions. Furthermore, no manual inspection is required, thus improving the accuracy of the evaluation results for steel structure towers.

[0044] The following description, in conjunction with the accompanying drawings, details the steel structure tower evaluation method, apparatus, equipment, medium, and program products provided in the embodiments of this application.

[0045] Figure 1 The network architecture for an application of a steel structure tower evaluation method provided in this application embodiment is illustrated. For example... Figure 1 As shown, the network architecture includes a steel structure tower evaluation device 101 and a terminal device 102. The steel structure tower evaluation device 101 and the terminal device 102 are interconnected.

[0046] In some embodiments, the steel structure tower evaluation device 101 may be a server, a computer, or a processor or processing unit within a server or computer. The server may be a single server or a server cluster consisting of multiple servers. It should be noted that the embodiments of this application do not limit the specific device form of the steel structure tower evaluation device 101. Figure 1 The steel structure tower evaluation device 101 is shown as an example of a single server.

[0047] In some embodiments, the terminal device may be a mobile phone, tablet computer, laptop computer, handheld computer, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, personal computer (PC), ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc., and the embodiments of this application do not specifically limit it. Figure 1 The example shown is a mobile phone, with terminal device 102 as an example.

[0048] In some embodiments, the terminal device 102 sends the first real-time detection parameters of the steel structure tower to the steel structure tower evaluation device 101. The steel structure tower evaluation device 101 obtains N deterioration feature information corresponding to N detection indicators included in the first real-time detection parameters of the steel structure tower. Based on the N deterioration feature information, the steel structure tower evaluation device 101 adjusts the weights corresponding to the N detection indicators. Based on the adjusted weights of the N detection indicators and the N deterioration feature information, a fused feature vector is obtained. Based on the fused feature vector, a first health score corresponding to the steel structure tower is obtained, which is used to indicate the stability of the steel structure tower.

[0049] It should be noted that the network architecture described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As network architectures evolve, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0050] See Figure 2 This is a flowchart illustrating a steel structure tower evaluation method provided in an embodiment of this application. Figure 2 As shown, the steel structure tower evaluation method provided in this application embodiment can be implemented by the above-mentioned steel structure tower evaluation device, specifically including the following steps 201 to 204.

[0051] Step 201: The steel structure tower evaluation device acquires N deterioration characteristic information corresponding to N detection indicators included in the first real-time detection parameters of the steel structure tower.

[0052] In some embodiments, the first real-time detection parameter includes: defect data indicators, simulation bearing capacity data indicators, status data indicators, and historical operation and maintenance data indicators. N is a positive integer, and one detection indicator corresponds to one degradation characteristic information.

[0053] In some embodiments, the aforementioned defect data indicators can be obtained by using a high-precision drone equipped with a high-definition camera and infrared sensor to perform a comprehensive scan of the steel structure tower.

[0054] For example, the aforementioned defect data indicators include defects such as corrosion, deformation, and cracks, and record parameters such as the location, size, and severity of the defects.

[0055] In some embodiments, the above-mentioned simulated load-bearing capacity data indicators are obtained by establishing a finite element model of the steel structure tower and simulating the load-bearing capacity under different environmental conditions.

[0056] For example, the above-mentioned simulation load-bearing capacity data indicators include parameters such as the number and layout of antennas, wind load, snow load, and seismic load.

[0057] In some embodiments, the aforementioned state data indicators are acquired in real time by installing acceleration sensors, strain sensors, tilt sensors, etc., at key parts of the steel structure tower.

[0058] For example, the aforementioned state data indicators include parameters such as vibration, stress, and displacement.

[0059] In some embodiments, the above-mentioned historical operation and maintenance data indicators are collected by organizing previous maintenance records, repair history, material replacement records, etc.

[0060] For example, the aforementioned historical operation and maintenance data indicators include parameters such as the number of inspections, maintenance data, and material replacement data.

[0061] For example, the frequency of collecting the above data indicators can be as follows: sensor data once per minute, drone data once per month, simulation data updated quarterly, and historical data retrieved in real time.

[0062] In some embodiments, the steel structure tower evaluation device can preprocess the above-mentioned indicators to obtain the deterioration characteristic information corresponding to each indicator.

[0063] For example, the preprocessing of the above-mentioned steel structure tower evaluation device includes: (1) outlier removal: deleting abnormal sensor data (such as sudden stress jumps); (2) converting data from different sources and in different formats into a unified format to eliminate the influence of dimensions; (3) feature extraction: extracting key features from various types of data, including extracting the "crack depth / length" feature from UAV image data, extracting the "frequency deviation value" feature from vibration data, and obtaining the bearing capacity attenuation rate from simulation data; (4) normalization processing: using the deterioration degree of multi-source data indicators as scoring items, converting data of different dimensions into deterioration degree values ​​of 0-1 (such as stress deterioration degree = measured stress / design stress, crack deterioration degree = crack length / allowable crack length).

[0064] In this way, by integrating data from four sources—sensors, drones, simulation, and history—the completeness of the assessment dimensions is improved, covering structural defects, stress state, environmental impact, and image recognition.

[0065] In some embodiments, the steel structure tower assessment device can be designed with two health update modes, automatic and manual, to adapt to the monitoring frequency requirements of daily operation and maintenance of steel structure towers. The two modes complement each other and can be flexibly switched according to the actual operation and maintenance scenario. Both modes are based on the trained random forest model to re-infer the health score, ensuring the accuracy of the updated score.

[0066] For example, the automatic update mode of the steel structure tower assessment device can be a conventional monitoring mode, which uses real-time monitoring data from sensors as the trigger source and sets a fixed trigger frequency of once a day. At the preset time node each day, the system automatically collects the latest multi-source data, and after preprocessing, weight correction, and feature fusion generation, it automatically triggers model inference to complete the update of the health score and synchronously updates the level judgment result without manual intervention.

[0067] For example, the manual update mode of the steel structure tower assessment device can be an emergency / supplementary monitoring mode, which is suitable for scenarios such as after drone inspection, after partial maintenance of the steel structure tower, and after extreme working conditions. When the system is idle and has no tasks, it supports maintenance personnel to manually trigger the health update command through the backend terminal. The system immediately collects the latest full multi-source data, re-executes the full process assessment, and quickly outputs the updated health score and level to meet the needs of emergency monitoring.

[0068] Step 202: The steel structure tower evaluation device adjusts the weights of the N detection indicators based on N deterioration characteristic information.

[0069] In some embodiments, the steel structure tower evaluation device can adjust the weights of N detection indicators according to different working conditions (such as strong winds, icing, rainstorms, earthquakes, etc.).

[0070] In some embodiments, the steel structure tower evaluation device adjusts the initial weights corresponding to N detection indicators based on N deterioration characteristic information.

[0071] In some embodiments, the steel structure tower evaluation device described above determines the initial weights based on data reliability and importance, and allocates weights through the analytic hierarchy process (expert scoring) to establish a weighted fusion model, where the sum of all weights is always 1.

[0072] For example, the initial basic weights are: status data index 0.35, defect data index 0.25, simulation carrying capacity data index 0.2, and historical operation and maintenance data index 0.2.

[0073] In some embodiments, combined with Figure 2 ,like Figure 3 As shown, step 202 above can be implemented through steps 202a to 202c.

[0074] Step 202a: The steel structure tower evaluation device calculates the coefficient of variation based on the deterioration characteristic information corresponding to the simulated bearing capacity data index and the state data index.

[0075] In some embodiments, the coefficients of variation corresponding to the above-mentioned simulation load-bearing capacity data indicators and state data indicators are used to indicate the degree of structural change of the steel structure tower in different dimensions.

[0076] For example, the formula for calculating the coefficient of variation is: Coefficient of variation (CV) = Standard deviation of data set (σ) / Mean of data set (μ). The calculation focuses on dynamic data sources that are sensitive to changes in operating conditions (simulation load capacity data, sensor monitoring data). UAV defect data is static inspection data (no fluctuation in a single inspection result, CV=0), and historical operation and maintenance data is historical statistical data (no real-time fluctuation, CV=0). CV is not calculated for these two types of static data.

[0077] Step 202b: The steel structure tower evaluation device determines the risk enhancement factors corresponding to the simulation bearing capacity data indicators and state data indicators based on the coefficient of variation.

[0078] In some embodiments, the above-mentioned simulation carrying capacity data indicators may correspond to a risk enhancement factor, and the above-mentioned state data indicators may also correspond to a risk enhancement factor. That is to say, there may be multiple risk enhancement factors.

[0079] In some embodiments, the risk enhancement factors of the aforementioned simulation load-bearing capacity data indicators and status data indicators are used to indicate the risk level of steel structure towers in different dimensions.

[0080] For example, the risk enhancement factor is a weight correction coefficient constructed by the steel structure tower assessment device based on the coefficient of variation threshold. Its function is to positively amplify the weight of risk-sensitive data sources with high CV values, while negatively reducing the weight of static / low-reference-value data sources. (For example, under high wind conditions, if the coefficient of variation of simulation data is >0.8, the weight is increased to 0.4, while the weight of historical data is reduced to 0.1.) The higher the CV value, the larger the risk enhancement factor, and the more significant the weight adjustment. The sum of the corrected weights of all data sources is always 1 (weight conservation, avoiding fusion bias). Based on industry standards for steel structure tower operation and maintenance and the actual risk level of the operating conditions, a correspondence rule between CV values ​​and the risk enhancement factor (hereinafter referred to as REF) is established (this can be fine-tuned according to region / steel structure tower type; for example, the high CV threshold can be reduced in coastal high-wind areas). REF only applies to dynamic data sources and is divided into three risk levels: low, medium, and high, corresponding to different correction magnitudes. The threshold rules for setting the CV threshold are shown in Table 1.

[0081] Table 1

[0082]

[0083] Step 202c: The steel structure tower assessment device adjusts the weights of N detection indicators based on the risk enhancement factor.

[0084] In some embodiments, the weight dynamic correction in the steel tower evaluation device follows the "weight conservation principle," and only positively boosts dynamic data sources with high CV values.

[0085] In some embodiments, combined with Figure 3 ,like Figure 4 As shown, step 202c above can be implemented through steps 202c1 to 202c4.

[0086] Step 202c1: The steel structure tower evaluation device calculates the adjusted first weight corresponding to the simulated bearing capacity data index based on the initial weight of the simulated bearing capacity data index and the risk enhancement factor corresponding to the simulated bearing capacity data index.

[0087] In some embodiments, the adjusted first weight formula corresponding to the simulated bearing capacity data index calculated by the above-mentioned steel structure tower evaluation device is as follows:

[0088] First weight = Initial weight corresponding to the simulation bearing capacity data index × REF corresponding to the simulation bearing capacity data index.

[0089] Step 202c2: The steel structure tower assessment device calculates the adjusted second weights corresponding to the state data based on the initial weights of the state data and the risk enhancement factors corresponding to the state data indicators.

[0090] In some embodiments, the adjusted second weight formula corresponding to the state data index calculated by the above-mentioned steel structure tower evaluation device is:

[0091] Second weight = Initial weight corresponding to the state data indicator × REF corresponding to the state data indicator.

[0092] Step 202c3: The steel structure tower evaluation device calculates the adjusted third weight corresponding to the historical operation and maintenance data indicators based on the initial weight, the first weight, and the second weight of the historical operation and maintenance data indicators.

[0093] In some embodiments, the weight increase values ​​of the above-mentioned steel structure tower evaluation device are all deducted from the historical operation and maintenance data (the UAV defect data is a static detection result, and its reference value for the current defects of the steel structure tower is fixed, so the weight remains unchanged to avoid ignoring actual defects due to fluctuations in operating conditions), ensuring that the total weight of all data sources after correction = 1.

[0094] For example, the formula for obtaining the third weight calculated by the steel structure tower evaluation device is as follows:

[0095] The third weight = the initial weight corresponding to the historical operation and maintenance data indicators - the sum of the weight enhancement values ​​of all dynamic data sources.

[0096] For example, the corrected weight of historical operation and maintenance data is at least ≥0.05 (to retain basic reference value and avoid complete elimination). If the increase exceeds the threshold, it is finely adjusted from the sensor data proportionally (prioritizing the correction range of simulation data). For example, under high wind conditions, the coefficient of variation of simulation data is >0.8, so REF=1.5 is taken, the weight is increased to 0.3, and the weight of historical data is reduced to 0.1.

[0097] Step 202c4: The steel structure tower evaluation device calculates the adjusted fourth weight corresponding to the defect data index based on the initial weight of the defect data index and the sum of the first weight, the second weight and the third weight.

[0098] In some embodiments, the formula for calculating the fourth weight by the above-mentioned steel structure tower evaluation device is as follows:

[0099] Fourth weight = Initial weight corresponding to defective data indicators – [Sum of weight boosts from all dynamic data sources – (Third weight – 0.05)].

[0100] In this way, the steel structure tower assessment device can adjust the data source weights according to changes in operating conditions, thereby achieving dynamic assessment of the health of the steel structure tower.

[0101] Step 203: The steel structure tower evaluation device obtains a fused feature vector based on the adjusted weights of N detection indicators and N deterioration feature information.

[0102] It should be noted that the specific implementation process of step 203 above can be found in the following embodiments, and will not be repeated here to avoid repetition.

[0103] In some embodiments, combined with Figure 2 ,like Figure 5 As shown, step 203 above can be implemented through the following step 203a1.

[0104] Step 203a1: The steel structure tower evaluation device performs a weighted summation of the adjusted weights of the N detection indicators and the N deterioration feature information to obtain a fused feature vector.

[0105] In some embodiments, the steel structure tower assessment device can generate fusion features by linearly weighting and summing the four types of normalized deterioration indices based on the corrected weights, generating a one-dimensional fusion feature vector (value range 0-1). This vector comprehensively reflects the overall deterioration degree of the steel structure tower structure in four dimensions: theoretical load-bearing capacity, real-time stress, actual defects, and historical risks, providing core input for the subsequent health assessment model. The general calculation formula is as follows:

[0106] The fused feature vector value = sensor dimension degradation × sensor data corrected weight + UAV dimension degradation × UAV data weight + simulation margin degradation × simulation data corrected weight + historical fault degradation × historical data corrected weight.

[0107] Thus, the aforementioned fused feature vector comprehensively reflects the overall deterioration degree of the steel structure tower in four dimensions: theoretical load-bearing capacity, real-time stress, actual defects, and historical risks. This provides core input for the subsequent health assessment model and improves the accuracy of the steel structure tower assessment device in evaluating steel structure towers.

[0108] Step 204: The steel structure tower evaluation device obtains the first health score corresponding to the steel structure tower based on the fused feature vector.

[0109] In some embodiments, a first health score is used to indicate the stability of the steel tower structure.

[0110] In some embodiments, the steel structure tower evaluation device can input the fused feature vector into a random forest model and output the first health score corresponding to the steel structure tower through the random forest model.

[0111] For example, the steel structure tower evaluation device inputs the fusion feature vector generated in real time by the multi-source data fusion module into the above-mentioned trained random forest model. After the model performs inference calculation, it directly outputs the current health score (0-100 points) of the steel structure tower. This score is the core quantitative basis for subsequent level determination. If the working condition is dynamically corrected (such as strong wind or icing), the model inference uses the fusion feature vector generated by the corrected weights to ensure that the inference result fits the actual working condition of the steel structure tower.

[0112] In some embodiments, the steel tower assessment device can use historical operation and maintenance full data as the training dataset, and use "fault labels" in the historical data (such as specific fault types leading to health decline events, such as loose bolts, slack guy wires, tower body cracks, foundation settlement, etc.) as supervision signals to construct and train a health assessment model using a random forest algorithm. The input of the model is a standardized fusion feature vector generated after multi-source data fusion, and the output of the model is a continuous health score of 0-100. The score is positively correlated with the health status of the steel tower: the higher the score, the better the structural health status of the steel tower; the lower the score, the more significant the structural defects / risks of the steel tower.

[0113] In some embodiments, the steel tower assessment device can also reflect the health status of the steel tower through a health level.

[0114] For example, the steel structure tower assessment device can set the correspondence between health level and score as follows: Excellent ≥ 85 points, Good 60-84 points, Warning 40-59 points, and Dangerous < 40 points. This realizes the conversion from health score to qualitative health level, making the assessment results more intuitive and adaptable to the actual decision-making needs of operation and maintenance personnel.

[0115] In this way, the steel structure tower assessment device guides the operation and maintenance priority by realizing the quantitative classification of health status, and can flexibly switch the health status update mode according to the actual operation and maintenance scenario to ensure the accuracy of the updated score.

[0116] In the steel structure tower evaluation method provided in this application, the steel structure tower evaluation device acquires N deterioration feature information corresponding to N detection indicators included in the first real-time detection parameters of the steel structure tower, where N is a positive integer, and one detection indicator corresponds to one deterioration feature information; based on the N deterioration feature information, the weights corresponding to the N detection indicators are adjusted; based on the adjusted weights of the N detection indicators and the N deterioration feature information, a fused feature vector is obtained; based on the fused feature vector, a first health score corresponding to the steel structure tower is obtained, which is used to indicate the stability of the steel structure tower. In this scheme, since the weights corresponding to the N detection indicators can be adjusted in real time according to changes in the current working conditions, the fused feature vector is obtained through the adjusted data source weights, and this fused feature vector is used as the input of the health assessment model, which can output a quantitative health score that conforms to the current working conditions, and no manual inspection is required, thus improving the accuracy of the steel structure tower evaluation results.

[0117] In some embodiments, combined with Figure 2 ,like Figure 6 As shown, after step 204 above, the steel structure tower evaluation method provided in this application embodiment may further include the following steps 301 and 302.

[0118] Step 301: When the steel structure tower evaluation device detects a decrease in the health score corresponding to the steel structure tower, it performs data analysis and processing on the first real-time detection parameter to obtain the analysis result corresponding to the first real-time detection parameter.

[0119] In some embodiments, the analysis results of the above-mentioned steel structure tower evaluation device include the location of defects and the probability of defects.

[0120] In some embodiments, the steel structure tower assessment device can take the standardized feature vector after multi-source data fusion as input, and use the SHAP (Shapley value) quantitative analysis method to calculate and classify the contribution of specific defect features (loose bolts, foundation settlement, tower body cracks, loose guy wires, etc.) of the steel structure tower with declining health / lower grade. For example, the contribution of loose bolts is 42% and foundation settlement is 31%.

[0121] In this way, specific faults and defects can be diagnosed and specific core hidden dangers can be located through attribution analysis of health status.

[0122] Step 302: Based on the analysis results, including the location and probability of potential hazards, the steel structure tower assessment device generates a steel structure tower operation and maintenance strategy.

[0123] In some embodiments, the steel structure tower assessment device can integrate data on the location and probability of potential hazards to obtain a steel structure tower operation and maintenance strategy.

[0124] For example, the above-mentioned steel structure tower operation and maintenance strategy can be a steel structure tower operation and maintenance report.

[0125] In some embodiments, the operation and maintenance strategy is to sort the potential risks from highest to lowest probability based on the above analysis results, and determine the objects that should be the focus of operation and maintenance.

[0126] In some embodiments, the steel structure tower assessment device can output a standardized attribution report containing the location of hidden dangers, related data, and operation and maintenance suggestions based on the contribution calculation. This addresses the pain point of traditional assessments that "only give results, not reasons," and enables "precise location of hidden dangers and targeted operation and maintenance." The entire process is deeply correlated with previous multi-source data, deterioration indicators, and health assessment results to ensure the accuracy and practicality of the analysis.

[0127] In this way, the steel structure tower assessment device outputs the attribution analysis results as a standardized attribution report and provides operation and maintenance suggestions to facilitate the inspection and maintenance of the steel structure tower by maintenance personnel.

[0128] The following specific examples illustrate the steel structure tower evaluation method of this application.

[0129] like Figure 7 As shown, the implementation process of the steel structure tower evaluation method provided in this application embodiment includes the following S1 to S4:

[0130] S1, the steel structure tower evaluation device performs multi-source data acquisition.

[0131] For example, the data collection includes: sensor data, such as the flange tilt angle of 0.3° and vibration frequency of 0.327Hz; drone data, such as the discovery of 3 loose bolts; simulation data, such as the stress ratio of 85% under a level 10 wind; and historical data, such as the icing disaster in 2023.

[0132] S2, the steel structure tower evaluation device performs data preprocessing.

[0133] For example, a flange tilt angle of 0.3° is converted to a corresponding deterioration degree of 0.6, a vibration frequency of 0.327Hz is converted to a corresponding deterioration degree of 0.7, the discovery of 3 loose bolts is converted to a corresponding deterioration degree of 0.5, a stress ratio of 85% under a level 10 wind is converted to a corresponding deterioration degree of 0.85, and the icing disaster in 2023 is converted to a corresponding deterioration degree of 0.3.

[0134] S3, the steel structure tower evaluation device performs weight fusion.

[0135] For example, due to the strong wind condition, the weight of the simulation data is increased to 0.4, and the fused feature vector = 0.6×0.3 +0.7×0.3 + 0.5×0.25 + 0.85×0.4 + 0.3×0.1 = 0.62.

[0136] S4. The steel structure tower assessment device performs a health assessment.

[0137] For example, the model calculated a score of 62 (grade "good", close to warning).

[0138] S5, the steel structure tower evaluation device outputs attribution results.

[0139] For example, bolt loosening contributes 42% and wind load stress 18%, so it is recommended to tighten the bolts within 3 days.

[0140] Thus, since the weights corresponding to the N detection indicators can be adjusted in real time according to changes in the current operating conditions, a fused feature vector is obtained through the adjusted data source weights. This fused feature vector is then used as input to the health assessment model, which can output a quantitative health score that conforms to the current operating conditions. Furthermore, manual inspection is unnecessary, improving the accuracy of the steel structure tower's assessment results. Simultaneously, an attribution analysis report is provided, facilitating maintenance by operations and maintenance personnel.

[0141] It should be noted that the descriptions of each step S1 to S4 in this embodiment can be found in the descriptions in the above embodiments, and will not be repeated here.

[0142] It should be noted that the above-described method embodiments, or the various possible implementations of the method embodiments, can be executed individually, or, provided there is no conflict, they can be combined with each other. The specific implementation can be determined according to actual usage requirements, and this application embodiment does not impose any restrictions on this.

[0143] Figure 8 This is a structural schematic diagram of a steel structure tower evaluation system provided in an embodiment of this application. Figure 8 As shown, the steel structure tower evaluation system 800 may include: a multi-source data acquisition module 801, a data preprocessing module 802, a dynamic weight fusion module 803, a health assessment module 804, and an attribution analysis module 805.

[0144] Among them, the multi-source data acquisition module 801 is used to collect multi-indicator data and is applied to the above steps 201 and related schemes.

[0145] The data preprocessing module 802 is used to convert data from different sources and in different formats into a unified format to obtain the corresponding degradation of each indicator, reflecting the degree of damage to the steel structure tower in different dimensions, and is applied to the above steps 201 and related schemes.

[0146] The dynamic weight fusion module 803 is used to dynamically adjust the weights corresponding to different indicators, and is applied to steps 202 and 203 and related schemes of steps 202 and 203.

[0147] The health assessment module 804 is used to output the health score and health level of the corresponding steel structure tower, which is applied to step 204 and related schemes.

[0148] The attribution analysis module 805 is used to perform attribution analysis based on the health status of the steel structure tower, and outputs a standardized attribution report containing the location of hidden dangers, related data, and operation and maintenance suggestions, which is applied to step 204 and related solutions in step 204.

[0149] It should be noted that for a detailed explanation of the steps performed by each module and their beneficial effects, please refer to the description in the above embodiments, which will not be repeated here.

[0150] As can be seen, the above mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the embodiments of this application provide corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the modules and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0151] This application embodiment can divide the steel structure tower evaluation device into functional modules according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or software functional modules. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0152] In some embodiments, this application also provides a steel structure tower evaluation device. This steel structure tower evaluation device may include one or more functional modules for implementing the steel structure tower evaluation method described in the above embodiments.

[0153] For example, Figure 9 This is a structural schematic diagram of a steel structure tower evaluation device provided in an embodiment of this application. Figure 9As shown, the steel structure tower evaluation device 900 includes: an acquisition module 901, an adjustment module 902, and a processing module 903.

[0154] The system comprises the following modules: Acquisition module 901, which acquires N deterioration feature information corresponding to N detection indicators included in the first real-time detection parameters of the steel structure tower, where N is a positive integer and one detection indicator corresponds to one deterioration feature information; Adjustment module 902, which adjusts the weights corresponding to the N detection indicators based on the N deterioration feature information; and Processing module 903, which obtains a fused feature vector based on the adjusted weights of the N detection indicators and the N deterioration feature information; and obtains a first health score for the steel structure tower based on the fused feature vector, which indicates the stability of the steel structure tower.

[0155] In the steel structure tower evaluation device provided in this application, since the weights corresponding to the N detection indicators can be adjusted in real time according to the changes in the current working conditions, a fusion feature vector is obtained through the adjusted data source weights. This fusion feature vector is then used as the input of the health assessment model, which can output a quantitative health score that conforms to the current working conditions. Furthermore, no manual inspection is required, thus improving the accuracy of the evaluation results of the steel structure tower.

[0156] In some embodiments, the first real-time detection parameter includes: defect data indicators, simulated load-bearing capacity data indicators, status data indicators, and historical operation and maintenance data indicators. The adjustment module 902 is specifically used to calculate the coefficient of variation based on the deterioration characteristic information corresponding to the simulated load-bearing capacity data indicators and status data indicators; the coefficient of variation is used to indicate the degree of structural change of the steel tower; based on the coefficient of variation, determine the risk enhancement factor corresponding to the simulated load-bearing capacity data indicators and status data indicators; the risk enhancement factor is used to indicate the risk level of the steel tower; and based on the risk enhancement factor, adjust the weights corresponding to the N detection indicators.

[0157] In other embodiments, the adjustment module 902 is specifically used to calculate the adjusted first weight corresponding to the simulation capacity data index based on the initial weight of the simulation capacity data index and the risk enhancement factor corresponding to the simulation capacity data index; to calculate the adjusted second weight corresponding to the state data based on the initial weight of the state data and the risk enhancement factor corresponding to the state data index; to calculate the adjusted third weight corresponding to the historical operation and maintenance data index based on the initial weight of the historical operation and maintenance data index and the sum of the first weight and the second weight; and to calculate the adjusted fourth weight corresponding to the defect data index based on the initial weight of the defect data index and the sum of the first weight, the second weight, and the third weight.

[0158] In some other embodiments, the processing module 903 is specifically used to perform a weighted summation of the adjusted weights of the N detection indicators and the N deterioration feature information to obtain a fused feature vector.

[0159] In some other embodiments, the processing module 903 is further configured to, after obtaining the first health score corresponding to the steel structure tower based on the fused feature vector, perform data analysis processing on the first real-time detection parameter when a decrease in the health score corresponding to the steel structure tower is detected, and obtain the analysis result corresponding to the first real-time detection parameter; and generate a steel structure tower operation and maintenance strategy based on the location and probability of hidden dangers included in the analysis result.

[0160] It should be noted that the steel structure tower evaluation device can realize all the processes implemented in the above method embodiments and achieve the same beneficial effects. To avoid repetition, it will not be described again here.

[0161] In the case where the functions of the integrated modules described above are implemented in hardware, this application provides a possible structural schematic diagram of the electronic device involved in the above embodiments. For example... Figure 10 As shown, the electronic device 90 includes: a processor 92, a communication interface 93, and a bus 94. Optionally, the electronic device 90 may also include a memory 91.

[0162] Processor 92 may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 92 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 92 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0163] Communication interface 93 is used to connect with other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0164] The memory 91 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0165] As one possible implementation, the memory 91 can exist independently of the processor 92. The memory 91 can be connected to the processor 92 via a bus 94 and is used to store instructions or program code. When the processor 92 calls and executes the instructions or program code stored in the memory 91, it can implement the steel structure tower evaluation method provided in the embodiments of this application.

[0166] In another possible implementation, memory 91 can also be integrated with processor 92.

[0167] Bus 94 can be an Extended Industry Standard Architecture (EISA) bus, etc. Bus 94 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 10 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0168] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the service calling device can be divided into different functional modules to complete all or part of the functions described above.

[0169] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described steel structure tower evaluation method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0170] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0171] This application embodiment also provides a readable storage medium storing a program or instructions that, when executed by a computer, implement the steel tower evaluation method provided in the above embodiments. It is understood that all or part of the processes in the above method embodiments can be executed by computer instructions instructing related hardware; the readable storage medium can be any of the foregoing embodiments or memory; the readable storage medium can also be an external storage device of the service invocation device, such as a pluggable hard drive, SmartMedia Card (SMC), Secure Digital (SD) card, flash card, etc., equipped on the service invocation device. Further, the readable storage medium can include both internal storage units of the service invocation device and external storage devices. The readable storage medium is used to store the computer program and other programs and data required by the service invocation device. The readable storage medium can also be used to temporarily store data that has been output or will be output.

[0172] This application also provides a computer program product, which is stored in a storage medium and, when executed by a computer, implements the steel structure tower evaluation method provided in the above embodiments.

[0173] It should be noted that, in this document, 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 a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0174] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0175] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for evaluating steel structure towers, characterized in that, include: The first real-time detection parameters of the steel structure tower include N detection indicators and N deterioration feature information corresponding to them. N is a positive integer, and one detection indicator corresponds to one deterioration feature information. Based on the N degradation feature information, adjust the weights corresponding to the N detection indicators; Based on the adjusted weights of the N detection indicators and the N degradation feature information, a fused feature vector is obtained; Based on the fused feature vector, a first health score is obtained for the steel structure tower, which is used to indicate the stability of the steel structure tower.

2. The steel structure tower evaluation method according to claim 1, characterized in that, The first real-time detection parameters include: defect data indicators, simulation bearing capacity data indicators, status data indicators, and historical operation and maintenance data indicators; adjusting the weights corresponding to the N detection indicators based on the N degradation feature information includes: Based on the degradation characteristic information corresponding to the simulated load-bearing capacity data index and the state data index, the coefficient of variation is calculated, and the coefficient of variation is used to indicate the degree of structural change of the steel structure tower. Based on the coefficient of variation, the risk enhancement factor corresponding to the simulation bearing capacity data index and the state data index is determined, and the risk enhancement factor is used to indicate the risk level of the steel structure tower. Based on the risk enhancement factor, the weights corresponding to the N detection indicators are adjusted.

3. The steel structure tower evaluation method according to claim 2, characterized in that, The adjustment of the weights corresponding to the N detection indicators based on the risk enhancement factor includes: Based on the initial weights of the simulated carrying capacity data indicators and the risk enhancement factors corresponding to the simulated carrying capacity data indicators, the adjusted first weights corresponding to the simulated carrying capacity data indicators are calculated. Based on the initial weights of the state data and the risk enhancement factors corresponding to the state data indicators, the adjusted second weights corresponding to the state data are calculated. Based on the initial weights of the historical operation and maintenance data indicators and the sum of the first weight and the second weight, the adjusted third weights corresponding to the historical operation and maintenance data indicators are calculated. Based on the initial weight of the defect data indicator and the sum of the first weight, the second weight, and the third weight, the adjusted fourth weight corresponding to the defect data indicator is calculated.

4. The steel structure tower evaluation method according to claim 1, characterized in that, The fused feature vector is obtained based on the adjusted weights of the N detection indicators and the N degradation feature information, including: The weighted sum of the N detection indicators after adjustment and the N degradation features is used to obtain the fused feature vector.

5. The method for evaluating steel structure towers according to any one of claims 1-4, characterized in that, After obtaining the first health score corresponding to the steel structure tower based on the fused feature vector, the method further includes: When a decrease in the health score corresponding to the steel structure tower is detected, data analysis and processing are performed on the first real-time detection parameter to obtain the analysis result corresponding to the first real-time detection parameter. Based on the analysis results, including the location and probability of potential hazards, a maintenance strategy for the steel structure tower is generated.

6. A steel structure tower evaluation device, characterized in that, The steel structure tower evaluation device includes: an acquisition module, an adjustment module, and a processing module; The acquisition module is used to acquire N deterioration feature information corresponding to N detection indicators included in the first real-time detection parameters of the steel structure tower, where N is a positive integer and one detection indicator corresponds to one deterioration feature information. The adjustment module is used to adjust the weights corresponding to the N detection indicators based on the N degradation feature information. The processing module is used to obtain a fused feature vector based on the adjusted weights of the N detection indicators and the N degradation feature information; and to obtain a first health score corresponding to the steel structure tower based on the fused feature vector, wherein the first health score is used to indicate the stability of the steel structure tower.

7. The steel structure tower evaluation device according to claim 6, characterized in that, The first real-time detection parameters include: defect data indicators, simulated load-bearing capacity data indicators, status data indicators, and historical operation and maintenance data indicators; the adjustment module is specifically used to calculate the coefficient of variation based on the deterioration characteristic information corresponding to the simulated load-bearing capacity data indicators and the status data indicators, the coefficient of variation being used to indicate the degree of structural change of the steel structure tower; based on the coefficient of variation, determine the risk enhancement factor corresponding to the simulated load-bearing capacity data indicators and the status data indicators, the risk enhancement factor being used to indicate the risk level of the steel structure tower; and based on the risk enhancement factor, adjust the weights corresponding to the N detection indicators.

8. The steel structure tower evaluation device according to claim 7, characterized in that, The aforementioned adjustment module is specifically used to calculate the adjusted first weight corresponding to the simulation carrying capacity data index based on the initial weight of the simulation carrying capacity data index and the risk enhancement factor corresponding to the simulation carrying capacity data index. Based on the initial weights of the state data and the risk enhancement factors corresponding to the state data indicators, the adjusted second weights corresponding to the state data are calculated. Based on the initial weights of the historical operation and maintenance data indicators and the sum of the first weight and the second weight, the adjusted third weights corresponding to the historical operation and maintenance data indicators are calculated. Based on the initial weight of the defect data indicator and the sum of the first weight, the second weight, and the third weight, the adjusted fourth weight corresponding to the defect data indicator is calculated.

9. The steel structure tower evaluation device according to claim 6, characterized in that, The aforementioned processing module is specifically used to perform a weighted summation of the adjusted weights of the N detection indicators and the N degradation feature information to obtain a fused feature vector.

10. The steel structure tower evaluation device according to any one of claims 6-9, characterized in that, The aforementioned processing module is further configured to, after obtaining the first health score corresponding to the steel structure tower based on the fused feature vector, perform data analysis processing on the first real-time detection parameter when a decrease in the health score corresponding to the steel structure tower is detected, to obtain the analysis result corresponding to the first real-time detection parameter; and generate a steel structure tower operation and maintenance strategy based on the location and probability of hidden dangers included in the analysis result.

11. An electronic device, characterized in that, It includes a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions being executed by the processor to implement the steel tower evaluation method as described in any one of claims 1-5.

12. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a computer, implement the steel tower evaluation method as described in any one of claims 1-5.

13. A computer program product, characterized in that, The computer program product is stored in a storage medium, and when executed by a computer, the computer program product implements the steel structure tower evaluation method as described in any one of claims 1-5.

Images