Anti-disaster performance evaluation method considering wind-induced fatigue effect for power transmission tower in near-fault area

Abstract

The invention relates to the technical field of power transmission tower anti-disaster evaluation, and discloses an anti-disaster performance evaluation method considering a wind-induced fatigue effect for a power transmission tower in a near-fault area. The method comprises the following steps: acquiring wind-induced fatigue data, including wind speed data, structural vibration data and fatigue damage data, of a power transmission tower in a near fault area; judging the wind-induced fatigue abnormity through the wind-induced fatigue datum line, the single-mode abnormity and secondary verification; performing feature extraction on the wind-induced fatigue data, endowing extracted features with labels with timestamps, and inputting the extracted features into an evaluation unit; the evaluation unit is provided with multi-stage evaluation transition to analyze and judge the data, and outputs an anti-disaster performance evaluation result; and the dynamic adjusting and optimizing unit receives the evaluation result, adjusts and evaluates the advancing step length in real time, and judges whether the power transmission tower structure needs to be reinforced or not. According to the method, the wind-induced fatigue dynamic process can be accurately captured, the accuracy and timeliness of anti-disaster performance evaluation are improved, and support is provided for power transmission tower maintenance.

Description

Technical Field

[0001] The present invention relates to the technical field of disaster resistance assessment of transmission towers, and in particular to a disaster resistance performance assessment method for transmission towers in near-fault areas taking into account wind-induced fatigue effects. Background Art

[0002] Due to the unique geological structure of near-fault areas, complex wind conditions often occur. Transmission towers in these environments are subjected to long-term wind loads, which can easily lead to wind-induced fatigue, causing structural damage or even collapse, posing a serious threat to the safe and stable operation of power systems. While a comprehensive technical framework exists for evaluating the disaster resistance of transmission towers, existing methods still have significant shortcomings in the unique scenario of near-fault areas.

[0003] Traditional assessment methods rely heavily on static load calculations, ignoring the dynamic nature of wind loads and the cumulative fatigue effects of long-term wind loads. In near-fault areas, wind speeds fluctuate dramatically and are accompanied by turbulence, causing continuous vibrations in transmission tower structures. This vibration causes repeated alternations in internal stresses, gradually leading to fatigue damage. Existing methods often fail to accurately capture this dynamic fatigue process, relying solely on structural parameters at a single time point for assessment, making it difficult to reflect changes in the structure's resilience over its entire service life.

[0004] The existing assessment system lacks an effective abnormality judgment mechanism. When wind-induced fatigue damage occurs in its early stages, the changes in structural parameters are often subtle, making it difficult for traditional monitoring methods to identify them. This leads to the neglect of abnormal conditions until the damage accumulates to a certain level and causes obvious failures, at which point repair measures are taken. At this point, not only does the maintenance cost increase significantly, but it may also cause serious consequences such as power supply interruptions. In addition, in the existing assessment process, there is a lack of effective linkage between data processing and assessment models. The extracted wind-induced fatigue characteristics are difficult to accurately match with real-time assessment needs. The analysis step size of the assessment unit is fixed and cannot be dynamically adjusted according to actual wind conditions and structural responses. This limits the timeliness and accuracy of the assessment results, making it difficult to meet the needs of real-time monitoring and early warning of the disaster resistance performance of transmission towers in near-fault areas. Summary of the Invention

[0005] The purpose of the present invention is to provide a disaster resistance performance evaluation method for transmission towers in near-fault areas taking into account wind-induced fatigue effects, so as to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above objectives, the present invention provides a method for evaluating the disaster resistance performance of transmission towers in near-fault areas taking into account wind-induced fatigue effects, the method comprising: Acquiring wind-induced fatigue data of transmission towers in a near-fault area, the wind-induced fatigue data including wind speed data, structural vibration data, and fatigue damage data; Determining wind-induced fatigue anomalies, including wind-induced fatigue baseline, single-mode anomaly, and secondary verification; Extract features from wind-induced fatigue data, assign the extracted wind-induced fatigue features to labels with timestamps, and input them into the evaluation unit; The evaluation unit sets a multi-level evaluation process to analyze and judge the wind-induced fatigue data and outputs the disaster resistance performance evaluation results; A dynamic tuning unit that adjusts the evaluation step size of the evaluation unit in real time receives the disaster resistance performance evaluation result and determines whether the transmission tower structure needs to be reinforced.

[0007] Preferably, the determination of wind-induced fatigue anomaly includes using a wind-induced fatigue baseline to compare the acquired wind speed data, structural vibration data, and fatigue damage data to determine whether they are within a normal threshold range of wind-induced fatigue; if the wind speed data, structural vibration data, and fatigue damage data are not within the normal threshold range of wind-induced fatigue, then triggering the determination of wind-induced fatigue anomaly; The single modal anomaly is used to map whether there is a mutation, imbalance and decoupling in the wind speed data, structural vibration data and fatigue damage data. If there is a single data anomaly in any of the wind speed data, structural vibration data and fatigue damage data, a single wind-induced fatigue anomaly data report is output and the data acquisition unit is checked for abnormality.

[0008] Preferably, the secondary verification includes time series correlation verification and spatial propagation verification, wherein the time series correlation verification is used to establish the sudden change, imbalance and decoupling of the continuous time stamp wind speed data, and the spatial propagation verification is used to obtain the sudden change, imbalance and decoupling of the structural vibration data and fatigue damage data; If the mapped data in the temporal correlation verification and spatial propagation verification are abnormal, the grid density is dynamically optimized by dividing the grid into high-resolution grids and extracting local neighborhood features.

[0009] Preferably, the feature extraction of wind-induced fatigue data includes performing dynamic fluctuation feature extraction processing on wind speed data to obtain a wind speed fluctuation feature vector, performing structural response feature analysis processing on structural vibration data to obtain a structural response feature vector, and performing cross-modal feature fusion processing on the wind speed fluctuation feature vector and the structural response feature vector to generate a fused wind-induced feature set; The cross-modal feature fusion processing includes time dimension alignment processing, mapping the wind speed fluctuation feature vector to the same time granularity as the structural response feature vector, and constructing a wind speed-structure cross-attention mechanism to calculate the cross-modal correlation matrix between the fluctuation features of each time step in the wind speed fluctuation feature vector and the response features of the corresponding time step in the structural response feature vector.

[0010] Preferably, the evaluation unit includes a wind speed evaluation and transition unit, a structural vibration evaluation and transition unit, and a fatigue damage evaluation and transition unit; The wind speed assessment and advancement unit takes the wind speed characteristics with timestamp tags as input, monitors the wind speed characteristics within consecutive timestamps in real time, obtains the difference between the wind speed characteristics at the previous moment and the wind speed characteristics at the current moment, and obtains the difference between the wind speed characteristics at the next moment and the wind speed characteristics at the current moment, and triggers an abnormal flag within the continuous time; The structural vibration assessment and advancement unit sets a structural vibration prediction model, predicts structural vibration data at the next moment through the structural vibration prediction model, and marks structural risks through mutation detection.

[0011] Preferably, the dynamic tuning unit receives the disaster resistance performance evaluation result, drives the wind speed evaluation shift unit to receive the wind speed change rate within the continuous time stamp through the wind speed change rate within the continuous time stamp, adjusts the wind speed parameter evaluation shift step, and shortens the wind speed parameter evaluation shift step if the wind speed data change rate per unit time is greater than the highest weight; The step length is adjusted by the acceleration of the structural vibration change of the continuous time stamp. If the increase in the acceleration of the structural vibration change of the time stamp from t-1 to t is greater than the acceleration of the structural vibration change of the continuous time stamp from t-2 to t-1, and the acceleration increase is greater than the minimum threshold, the step length ratio is compressed. The fatigue damage signal is obtained through the fatigue damage assessment push unit, and the step size adjustment is activated through comparison with the damage feature library. If the damage signal in the frequency band captured by the fatigue damage spectrum is crack extension and material degradation, the damage push step size of the fatigue damage assessment push unit is adjusted.

[0012] Preferably, a pre-trained evaluation network model is called to perform fatigue root cause weight distribution processing on the fused wind-induced feature set to generate an abnormal correlation score set corresponding to wind-induced fatigue, wherein the abnormal correlation score set includes the abnormal correlation distribution between fatigue damage data and each structural response feature; Based on the abnormal correlation distribution, the fatigue damage data and structural response characteristic vectors are jointly traced to generate abnormal root cause tracing results of wind-induced fatigue.

[0013] Preferably, a step boundary limit is set for receiving the adjusted damage transition step, the structural vibration compression step ratio and the adjusted wind speed assessment transition step, and an intensity level is set, wherein the intensity level includes low disturbance and medium-high disturbance; By adjusting the step size boundary, the redundant boundary buffer layer is triggered to temporarily tolerate the step size adjustment. If the step size temporarily exceeds the rated boundary, the total number of steps after actual adjustment is no greater than the maximum number of steps in the redundant boundary buffer layer. If the buffer layer stay time exceeds the threshold, it will immediately switch to the minimum safe step size.

[0014] Preferably, if the wind speed change rate, structural vibration gradient change rate, and fatigue damage spectrum characteristics after adjustment by the evaluation unit are in the stable region of the redundant boundary buffer layer, the step size of the evaluation unit evaluation shift is continuously adjusted according to the real-time data; If the total compensation amount of the evaluation unit's adjustment step size is not greater than the maximum step size of the redundant boundary buffer layer, and the buffer layer residence time is greater than a threshold, the step size freeze is triggered.

[0015] Preferably, a disaster resistance performance optimization strategy is generated based on the abnormality root cause tracing result, and the disaster resistance performance optimization strategy is fed back to the evaluation unit to trigger a parameter calibration operation; If it is determined that the transmission tower structure needs to be reinforced, the transmission tower structure connectors and foundation reinforcements are strengthened, the dampers are activated, and the balancers are triggered. The balancers move the load upward in the longitudinal and transverse directions to maintain a near-stable state, ultimately completing the reinforcement of the transmission tower structure. If the transmission tower structure does not need reinforcement, the trigger damper is activated and the balancer is triggered. The balancer moves the load upward in the longitudinal and lateral directions of the tilt to maintain a near-stable state, triggering electrical isolation of the transmission tower structure from the foundation.

[0016] Compared with the prior art, the present invention has the following beneficial effects: This disaster resistance assessment method for transmission towers in near-fault areas, taking into account wind-induced fatigue effects, first achieves multi-dimensional coverage of wind-induced fatigue-related information by comprehensively acquiring wind speed data, structural vibration data, and fatigue damage data. This overcomes the single and one-sided data collection issues of traditional assessment methods and provides a sufficient data foundation for subsequent accurate assessments. Compared to traditional assessment methods that rely solely on static parameters, this method fully incorporates dynamic wind load data and structural vibration data, more realistically reflecting the relationship between the wind field environment in near-fault areas and the structural response of transmission towers, avoiding assessment bias caused by ignoring dynamic factors.

[0017] In the wind-induced fatigue anomaly judgment link, the accuracy and reliability of anomaly identification are effectively improved by setting up a multi-level judgment mechanism consisting of a wind-induced fatigue baseline, single-modal anomaly judgment, and secondary verification. The establishment of a wind-induced fatigue baseline provides a reasonable reference for anomaly judgment. Single-modal anomaly judgment can quickly capture abnormal changes in a single parameter dimension, while secondary verification further reviews the initially identified anomalies, reducing misjudgments due to accidental factors. This multi-level anomaly judgment system solves the problem of untimely and inaccurate anomaly identification in traditional assessment methods. It can detect structural anomalies in the early stages of fatigue damage, creating conditions for subsequent timely intervention measures and avoiding further accumulation of damage that leads to more serious structural failures.

[0018] In terms of data processing and evaluation unit operation, the extracted wind-induced fatigue features are assigned tags with timestamps, so that the feature data is closely associated with the time dimension, making it easier for the evaluation unit to trace the changes in fatigue status at different time nodes and clearly present the accumulation process of fatigue damage. The multi-level evaluation transition mechanism set up by the evaluation unit can analyze and judge wind-induced fatigue data in stages and layers, rather than using the traditional fixed-mode one-time evaluation. This method can more carefully analyze the changing trends of the structure's disaster resistance performance in different time periods and improve the refinement of the evaluation results. At the same time, the introduction of the dynamic tuning unit can adjust the evaluation transition step in real time according to the disaster resistance performance evaluation results output by the evaluation unit. When the evaluation results show that the structural state is stable, the step size can be appropriately increased to improve the evaluation efficiency; when potential risks or abnormal trends are found in the structure, the step size can be reduced to enhance the sensitivity of the evaluation, achieving a dynamic balance between evaluation efficiency and accuracy, and avoiding the problem of difficulty in balancing efficiency and accuracy in traditional fixed-step evaluation.

[0019] This method uses a dynamic tuning unit to determine whether the transmission tower structure requires reinforcement based on the assessment results, forming a complete closed loop of "data collection - anomaly determination - feature extraction - assessment and analysis - reinforcement determination." This closed-loop assessment process eliminates the need for disaster resilience assessment as an isolated data analysis process, directly linking it to structural maintenance decisions. This allows for timely guidance on actual structural reinforcement based on the assessment results, avoiding the disconnect between traditional assessments and actual maintenance. This ensures targeted and timely maintenance measures, effectively extending the service life of transmission towers and safeguarding the safe and stable operation of power systems in areas near faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a working principle diagram of the disaster resistance performance assessment method for transmission towers in near-fault areas considering wind-induced fatigue effects according to the present invention; Figure 2 A flowchart of the method for refining near-abnormal judgment; Figure 3 Flowchart of the method for data feature extraction; Figure 4 Flowchart of the method for tracing the root cause of anomalies. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0022] See also Figure 1The present invention provides a method for evaluating the disaster resistance performance of transmission towers in near-fault areas considering wind-induced fatigue effects, the method comprising: Obtain wind-induced fatigue data of transmission towers in near-fault areas, which includes wind speed data, structural vibration data, and fatigue damage data; perform wind-induced fatigue anomaly judgment, which includes wind-induced fatigue baseline comparison, single-modal anomaly identification, and secondary verification operations; extract features from wind-induced fatigue data, assign timestamp labels to the extracted features, and input them into the evaluation unit; the evaluation unit analyzes and judges the data through multi-level evaluation transitions, and outputs disaster resistance performance evaluation results; the dynamic tuning unit receives the evaluation results, adjusts the evaluation transition step of the evaluation unit in real time, and determines whether the transmission tower structure needs to be reinforced.

[0023] Example 1: See Figure 2 When evaluating the disaster resistance of transmission towers near fault zones, the initial assessment of wind-induced fatigue anomalies is fundamental to the entire process. This assessment relies on a multi-level, multi-modal verification system, centered on the comprehensive review and cross-validation of three types of data: wind speed, structural vibration, and fatigue damage.

[0024] Establishing a wind-induced fatigue baseline serves as the initial threshold for determining data anomalies. This baseline is not a single numerical value, but rather a dynamically changing set of threshold ranges. These ranges are determined based on historical meteorological data for the transmission tower's location, the tower's structural design parameters, and the material's fatigue properties. For example, for wind speed data, the normal threshold range considers the region's average wind speed, the probability distribution of maximum wind speeds, and seasonal variations in wind direction. For structural vibration data, the threshold range is determined based on the tower's natural frequency, damping ratio, and expected response spectrum under design wind loads. The threshold for fatigue damage data is closely related to the material's SN curve, cumulative damage model, and stress concentration at the monitoring point. The system compares the raw data acquired in real time against these preset threshold ranges. If a data item—such as the instantaneous wind speed at a certain altitude, the vibration acceleration amplitude of a specific tower mode, or the stress cycle count at a critical node—is detected to have consistently or momentarily exceeded its corresponding normal upper and lower thresholds, the system triggers the wind-induced fatigue anomaly determination process, signaling that the data requires further evaluation.

[0025] This phase involves in-depth analysis of individual data streams for unusual patterns, primarily including mutations, imbalances, and decoupling. A mutation refers to a sudden, discontinuous jump in the data over a time series. For example, a sharp pulse in wind speed recorded by an anemometer within a very short period of time, a sharp peak in the acceleration signal collected by a structural vibration sensor, or a step-like change in the stress amplitude recorded by a fatigue damage monitoring unit. The system calculates the first-order differences (rate of change) and second-order differences (acceleration of change) of the data in real time and sets appropriate mutation thresholds to detect such events. Imbalance refers to a discrepancy between different measurement points of the same data type, or between the data and the expected theoretical relationship. For example, the values ​​measured by multiple anemometers installed at different heights on a transmission tower should normally exhibit a certain gradient distribution pattern. If the wind speed values ​​at a particular layer deviate significantly from this gradient pattern, significantly diverging from the data at adjacent layers, it is considered an imbalance. For example, under a specific wind speed, the tower's vibration response should theoretically be within a certain magnitude. If the measured vibration amplitude is significantly higher or lower than this theoretical expectation, this is also a sign of imbalance. Decoupling refers to the significant weakening or elimination of the correlation between data items that should be highly correlated. For example, under wind load, the time series of wind speed and the time series of stress in the tower's main members typically have a strong correlation. If a significant change in wind speed is detected without a corresponding change in the stress response, or vice versa, this indicates a possible decoupling between wind speed and structural response. Once any of these single-modal anomalies is identified in any data stream, the system immediately generates a single wind-induced fatigue anomaly data report, detailing the anomaly type, time of occurrence, location, and severity. Simultaneously, the system initiates a self-test to detect hardware issues such as failures, drift, or signal interruptions in the data acquisition units (such as sensors, transmission lines, and data acquisition cards) to rule out spurious anomalies caused by malfunctions in the measurement system itself.

[0026] To further improve the accuracy of anomaly detection and prevent false alarms, the system introduces a secondary verification mechanism after single-mode identification: temporal correlation verification and spatial propagation verification. Temporal correlation verification focuses on analyzing the continuity and development of anomaly patterns over time. Rather than viewing sudden changes, imbalances, or decoupling at a single data point in isolation, it contextualizes these changes within a continuous sequence of timestamps to examine whether these abnormal patterns are temporally correlated. For example, a momentary wind speed pulse may simply be a measurement disturbance. However, if the wind speed exhibits sustained, frequent sudden changes over multiple timestamps, or if the imbalance persists and gradually worsens, or if the decoupling spreads over time, the authenticity and severity of the anomaly are significantly enhanced. Spatial propagation verification examines the spread of anomalies across the structural space. For structural vibration and fatigue damage data, anomalies may not be confined to a single measurement point. For example, if a high stress anomaly occurs at one node, will this anomaly propagate along the component to adjacent nodes? Will a localized vibration anomaly excite other modes in the overall structure? Spatial propagation verification analyzes the spatiotemporal correlation patterns of sensor data anomalies at different locations to determine whether the anomaly is a localized phenomenon or a risk with global impact. This verification is achieved by constructing a topological network of all measurement points and analyzing the propagation path and speed of the anomaly along this network.

[0027] When both temporal correlation and spatial propagation verification confirm the presence of an anomaly and its temporal and spatial correlation, the system initiates high-resolution grid analysis. This grid covers the entire transmission tower structure and the surrounding wind farm space. The system dynamically adjusts the grid density based on the spatiotemporal characteristics of the anomaly signal. In areas where anomalies are strong or fluctuating, such as near nodes experiencing sudden increases in vibration amplitude or in wind farm layers with extreme wind speed gradients, the grid is automatically refined to extract more refined local neighborhood features. This extraction is achieved using a sliding window analysis technique within the refined grid. Data within the window is subjected to feature extraction to more precisely locate the anomaly source and quantify its intensity. The goal of this entire process is to transform initial anomaly alerts into precise assessments of the anomaly's nature, location, severity, and potential impact through in-depth verification and analysis, providing high-quality, highly reliable anomaly input information for subsequent assessment units.

[0028] Example 2: See Figure 3, the processing of wind speed data adopts dynamic fluctuation feature extraction. Since the wind field in the near-fault area often shows strong non-stationary and random pulsation characteristics, the simple average wind speed or maximum wind speed value is not enough to describe its dynamic load characteristics. Therefore, the system conducts an in-depth analysis of the wind speed time series collected in real time to capture its fluctuation details. For example, for a period of wind speed records under the action of continuous strong winds, the processing not only extracts its average wind speed and standard deviation, but also focuses on analyzing its turbulence intensity, gust factor, power spectrum density characteristics of pulsating wind speed, and the frequency and amplitude of wind direction changes. These parameters together constitute a multi-dimensional wind speed fluctuation feature vector, which can quantify the dynamic input energy of the wind load and its frequency distribution, thereby going beyond static indicators and more accurately describing the nature of wind excitation on the structure.

[0029] Structural vibration data is processed through structural response feature analysis. The vibration response of a transmission tower under wind loads is a complex, high-dimensional signal composed of multiple modes. The system acquires raw vibration signals from accelerometers deployed at key tower nodes (such as the tower head, crossarm connections, and tower slope change points). The analysis process first filters the signal to remove high-frequency noise and low-frequency drift. Then, modal parameter identification techniques are used to isolate the primary vibration modes of the structure, such as first-order bending, second-order bending, and torsional modes, from the response. For each identified mode, the analysis extracts its current frequency (to monitor changes in structural stiffness), damping ratio (to assess energy dissipation characteristics), and mode amplitude (to quantify vibration intensity). Furthermore, the vibration signal is analyzed for time-domain characteristics, such as peak and RMS values, as well as frequency-domain characteristics, such as the energy fraction within specific frequency bands. All these analyzed parameters are integrated into a structural response feature vector, which comprehensively characterizes the structure's dynamic state under the current wind load.

[0030] After obtaining the wind speed fluctuation eigenvectors and the structural response eigenvectors, the system performs cross-modal feature fusion to generate a fused wind-induced feature set. This fusion is not a simple data concatenation, but rather a deep integration process that emphasizes spatiotemporal correlations. First, the time dimension is aligned. Because the acquisition frequency and transmission delay of wind speed and vibration data may vary slightly, both must be mapped to a unified timestamp sequence before fusion to ensure strict temporal correspondence between wind excitation and structural response within each analysis time step. Subsequently, a wind-structure cross-attention mechanism is constructed. The core function of this mechanism is to calculate the correlation between the fluctuation characteristics of each time step in the wind speed fluctuation eigenvector (such as turbulence energy at a specific frequency) and the response characteristics of the corresponding time step in the structural response eigenvector (such as the vibration amplitude of a certain mode). Through extensive calculations, a cross-modal correlation matrix is ​​generated. This matrix quantifies the coupling strength between different wind characteristics and different structural response modes. For example, the matrix may reveal a strong positive correlation between turbulence energy in a specific frequency range and the vibration amplitude of the tower's first bending mode, while the correlation with the torsional mode response is weaker. This in-depth correlation analysis ensures that the fused feature set not only contains information about each mode, but also contains information about the mechanism of interaction between wind and structure.

[0031] These fused wind-induced features, labeled with precise timestamps, are input to the evaluation unit. This unit consists of three parallel submodules, which perform transition evaluations for wind, vibration, and damage, respectively. The wind speed evaluation transition unit takes timestamped wind speed features (from the fused feature set) as input. It works by dynamically comparing the differences in feature vectors at different moments based on a continuous time series. It not only calculates the difference between the features at the current moment and the previous moment to determine the drastic degree of change; it also estimates the possible state of the features at the next moment based on recent trends and compares it with the features of the subsequent actual input. This difference analysis within continuous timestamps can trigger the marking of persistent abnormal wind conditions, such as identifying that the wind speed fluctuation characteristics are continuously deviating from the normal pattern, even if their instantaneous values ​​do not exceed the threshold.

[0032] The structural vibration assessment transition unit is more complex, and a structural vibration prediction model is set up inside it. The model is trained based on historical long-term monitoring data and can learn the normal evolution pattern of structural response under given wind-induced characteristic inputs. The unit inputs the fusion features of the current moment into the model to predict the normal value range of the structural vibration data at the next moment. Subsequently, the actual monitored vibration data at the next moment is compared with the predicted value. If the actual value significantly exceeds the predicted range, especially if there is a sudden change in amplitude or frequency, it indicates that the structure may have unexpected behavior, such as loose connections, increased material damage, or entering the nonlinear response area. At this time, the unit will immediately mark the location as having a structural risk. This difference detection based on model prediction can more keenly capture early structural anomalies than simple threshold judgment.

[0033] The fatigue damage assessment and progression unit receives direct or indirect damage signals from sensors and similarly performs time-series analysis, focusing on changes in the damage accumulation rate. These three assessment and progression units operate in parallel, continuously and dynamically evaluating the tower's disaster resistance performance from three dimensions: wind input, structural condition, and damage results. Their output provides a multi-dimensional basis for subsequent dynamic optimization and decision-making. The entire feature extraction and assessment progression process transforms raw data into a deep understanding of the tower's condition.

[0034] Example 3: See Figure 4 The dynamic tuning unit receives the disaster resistance performance assessment results from the assessment unit. Its core function is to adjust the analysis step size of each assessment transition unit in real time according to the severity of the data change. For the wind speed assessment transition unit, the basis for tuning is the wind speed change rate within continuous time stamps. The unit continuously calculates the amplitude of the change of the wind speed characteristic vector per unit time, such as the rate of change of turbulence intensity or gust factor. If this change rate exceeds a certain set high threshold, it indicates that the wind field is in an extremely unstable state and the wind speed characteristics may evolve rapidly. At this time, the dynamic tuning unit will send an instruction to the wind speed assessment transition unit to shorten the step size of its assessment transition. This means that the system will perform a comparison of the difference between the previous and next moments of the wind speed characteristics more frequently, from possibly once a minute to once every ten seconds or less, to capture subtle mutations in the wind field with higher time resolution, and prevent the omission of key dangerous wind condition information due to too long an analysis interval.

[0035] The tuning logic for the Structural Vibration Assessment Progression Unit is more sophisticated, based on the acceleration of structural vibration changes—that is, the rate of change of vibration characteristics (such as modal amplitude or frequency). The system calculates not only the rate of change from time t-2 to time t-1, but also the rate of change from time t-1 to the current time t, and compares the difference between the two. If the rate of change in the latter interval shows a significant acceleration compared to the previous interval, and the acceleration value exceeds a minimum threshold, this indicates that the structural response may be entering a phase of rapid nonlinearity or instability. In this scenario, the dynamic tuning unit issues a command to reduce the step size of the Structural Vibration Assessment Progression Unit. This allows the structural vibration prediction model to perform predictions and comparisons at smaller step intervals, enabling it to more closely track the deterioration of the structural condition and provide earlier warnings of potential risks.

[0036] The tuning mechanism for the fatigue damage assessment progression unit is based on signal feature comparison. The unit continuously acquires and analyzes fatigue damage signals, such as waveform data from acoustic emission sensors or cumulative damage calculated based on strain history. These signals are decomposed into the frequency domain for analysis. The system maintains a damage signature library containing typical spectral signature patterns associated with various damage modes, such as microcrack initiation, stable macrocrack propagation, unstable macrocrack propagation, loosening of rivets or bolted connections, and microscopic material degradation. By comparing the real-time damage spectrum with the patterns in the signature library, the system determines that the damage progression is accelerating if the current spectrum closely matches the frequency band characteristics of a specific damage mode, such as "crack propagation" or "material degradation." This determination immediately activates the step-size adjustment mechanism, causing the dynamic tuning unit to reduce the damage progression step size of the fatigue damage assessment progression unit accordingly. This enables the system to update the damage accumulation status assessment more frequently and more sensitively monitor the rate of damage evolution.

[0037] While completing the dynamic step size adjustment, the system starts a deep diagnosis process aimed at tracing the root cause of the anomaly. This process calls a pre-trained evaluation network model. The model receives the fused wind-induced feature set generated by Example 2 as input. Its internal mechanism performs an in-depth analysis of the input features, and quantifies the correlation strength between each potential fatigue damage data point and each structural response feature in the fused feature set, that is, it performs fatigue root cause weight distribution processing. The output of this processing is an abnormal correlation score set, which is essentially a distribution matrix that clearly reveals the contribution of different structural response anomalies to the currently observed fatigue damage anomalies. For example, the scoring results may show that the current damage accumulation of the tower foot node is 80% likely to be related to the abnormal vibration amplitude of the monitored first-order bending mode of the tower body, while the direct correlation with other modes or wind speed characteristics is weak.

[0038] Based on this anomaly correlation distribution, the system performs a joint root-cause tracing process. Rather than viewing damage or vibration in isolation, this process deeply couples fatigue damage data with structural response eigenvectors in strongly correlated dimensions, tracing the anomaly's origin and propagation path in time and space. The output is a root-cause tracing result for wind-induced fatigue anomalies, which might be specifically stated as follows: "The current accelerated accumulation of fatigue damage in the main material on the southeast side of the third tower section is primarily due to persistent vortex shedding excitation near this area over the past hour. This excitation resonated with the structure's second-order vibration mode, resulting in a significant increase in the local dynamic stress amplitude." This tracing result links abstract damage data with specific physical phenomena and structural locations.

[0039] The core of the entire dynamic tuning and root cause tracing process is the closed loop of perception, analysis, and adaptation. The dynamic tuning unit determines the granularity of analysis (analysis) based on the output of the evaluation unit (perception). The step adjustment instructions and root cause tracing results it outputs, in turn, guide the evaluation unit to work more focused and efficiently (adaptation). For example, when root cause tracing points to vibration in a specific mode, the structural vibration assessment transition unit can further refine the monitoring and analysis of that mode. This process enables the system to intelligently allocate computing resources, maintaining a regular monitoring rhythm during calm times, and automatically entering a "wartime" state when a storm approaches or structural hazards arise, increasing the frequency and depth of analysis, thereby achieving efficient and accurate disaster resistance performance assessment.

[0040] The core criterion of the adaptive adjustment process can be quantified by a dynamic weight function:

[0041] in: Represents the adjusted evaluation time interval, and its value changes dynamically. Indicates the basic evaluation interval preset by the system, which is a reference constant. It is a proportional coefficient used to adjust the strength of the entire adaptive adjustment. is a sensitivity coefficient that determines how well the system responds to changing acceleration conditions. It represents the second-order derivative of the observed parameter (such as vibration amplitude or damage accumulation) with respect to time, that is, the acceleration of the change of the parameter, which directly reflects the severity of the evolution of the system state.

[0042] The meaning of this relationship is that when the acceleration of the observed parameter changes As it increases, the value of the function denominator increases, resulting in the calculated adjusted interval This means that the faster and more drastically the system state changes, the shorter the time interval between analyses by the evaluation unit, and the higher the sampling and analysis frequency, to achieve close tracking. Conversely, when the changes are stable, the intervals return to the baseline value.

[0043] Example 4: The system sets up a step size boundary limitation module, which receives the adjusted damage advancement step size, structural vibration compression step size ratio, and wind speed assessment advancement step size from the dynamic tuning unit. These adjusted step size parameters are not unlimited, but are constrained by preset boundaries. The boundary values ​​are not fixed, but are set based on historical extreme operating conditions data in the near-fault area where the transmission tower is located, taking into account factors such as maximum instantaneous wind speed, strongest earthquake motion records, and the worst fatigue damage cases. At the same time, the system defines intensity levels, which are divided according to the current degree of environmental disturbance. Low disturbance levels correspond to normal wind conditions and structural stability; medium and high disturbance levels correspond to high-risk conditions such as sustained strong winds, intensified abnormal structural vibration, or rapid accumulation of fatigue damage. Different intensity levels correspond to different step size boundary ranges. For example, under low disturbances, a wider adjustment margin is allowed for the step size, while under medium and high disturbances, the boundary is tightened, forcing the evaluation to maintain a higher frequency.

[0044] By adjusting the step size boundaries, the system triggers the redundant boundary buffer mechanism. This buffer is not a physical structure, but rather a software-level fault-tolerance logic that temporarily tolerates step size adjustments. Its core function is to allow the step size to temporarily exceed the rated boundary under certain conditions without immediately triggering a system alarm or forced reset. The operation of the buffer relies on two key criteria: whether the total number of adjusted steps exceeds the maximum capacity limit of the buffer layer, and how long the over-limit state persists within the buffer layer. For example, if a sudden increase in wind speed causes the dynamic tuning unit to significantly shorten the wind speed assessment step size, the step size value may momentarily exceed the rated boundary set for low-disturbance conditions. In this case, if the calculated total number of adjusted steps across all assessment units (which can be understood as the system processing load) does not exceed the maximum step number threshold preset by the redundant boundary buffer, the system temporarily tolerates the over-limit state and the assessment process continues at the adjusted step size, avoiding frequent switching of the assessment rhythm due to brief disturbances. However, this tolerance has limits. The system continuously monitors how long the over-limit state persists within the buffer layer. If this time exceeds a preset threshold (e.g., 5 minutes), it is considered a persistent anomaly, and the buffer layer mechanism is immediately disabled. The system will forcibly switch the step size of all assessment units to the preset minimum safety step size. The minimum safety step size is the most conservative setting for the system to ensure basic monitoring functions, ensuring that a minimum assessment capability is maintained even under the most severe operating conditions.

[0045] The system continuously monitors the status of key parameters adjusted by the evaluation unit, including the wind speed change rate, the structural vibration gradient change rate, and the fatigue damage spectrum characteristics. If these parameters are determined to be within the stable domain defined by the redundant boundary buffer layer, it indicates that the currently adjusted step size setting can effectively track changes in the system state and that the system is operating smoothly. At this point, the system will continue to fine-tune the evaluation step size through the dynamic tuning unit based on the latest data transmitted in real time to achieve adaptive tracking. The range of the stable domain is defined by stability theory methods to ensure that the system does not diverge or oscillate when operating within the domain.

[0046] The system also implements a step-size freeze mechanism. This mechanism monitors two conditions: the total number of compensations required by the evaluation units to adjust the step size (which can be understood as the total number of step-size adjustments performed by the system to maintain stability) and the buffer layer residence time. If the system calculates that the total compensation does not exceed the maximum step size limit of the redundant boundary buffer layer, but the buffer layer residence time exceeds the set time threshold, a step-size freeze is triggered. In this frozen state, the step sizes of all evaluation units are locked at their current values ​​and no longer respond to adjustment commands from the dynamic tuning unit until the system detects that key parameters (wind speed rate of change, vibration gradient rate of change, damage spectrum characteristics) have returned to the stable region for a period of time, or receives an external reset command. The freeze mechanism is intended to prevent the system from oscillating due to continuous fine-tuning near the boundary, which wastes computing resources and may distort the evaluation results. Table 1 shows the key parameters of the redundant boundary buffer layer and the system response logic in different states.

[0047] Table 1: Redundant boundary buffer layer state transition logic.

[0048]

[0049] Example 5: Based on the abnormal root cause tracing results output by Example 3, the system generates a targeted disaster resistance performance optimization strategy. This strategy is not a general solution, but is closely integrated with the specific root causes traced. For example, if the root cause tracing clearly points to the fact that the fatigue damage of a specific connection node is aggravated due to excessive dynamic stress caused by local resonance, the strategy may include measures to suppress the vibration of this modal; if the root cause is the abnormal redistribution of internal forces of the structure caused by uneven foundation settlement, the strategy may focus on foundation reinforcement. The generated strategy is fed back to the evaluation unit in real time, triggering a parameter calibration operation. This operation adjusts the threshold parameters, weight coefficients or prediction model parameters within the evaluation unit according to the specific recommendations of the strategy. For example, if the strategy recommends paying attention to the vibration of a specific mode, the structural vibration assessment transition unit will correspondingly increase the warning threshold sensitivity of the modal amplitude, or give the mode a higher weight in its prediction model. This feedback calibration enables the evaluation unit to more accurately monitor key indicators related to the strategy in subsequent work.

[0050] Based on the comprehensive output of the evaluation unit, especially the judgment of the dynamic tuning unit, the system makes the final decision on whether the transmission tower structure needs to be reinforced. If it is determined that reinforcement is necessary, the system will trigger a series of structural reinforcement operations. First, the reinforcement of the transmission tower structure connectors and foundation reinforcements will be triggered. Structural connector reinforcement targets identified weak or high-stress nodes, and may include: replacing bolts or connection plates with higher strength grades; installing additional angle steel or steel plate supports at key nodes to share the load and suppress local deformation; and locally reinforcing or wrapping rods that show signs of early damage. Foundation reinforcement reinforcement targets foundation problems that may be involved in root cause tracing, such as: pressure grouting around the foundation to improve the bearing capacity and uniformity of the foundation; adding or tensioning ground anchor cables to enhance the foundation's pull-out and anti-overturning capabilities; pouring reinforced concrete sleeves around the foundation slab to increase the foundation bottom area and stability. These reinforcement measures are intended to improve the structure's bearing capacity and fatigue resistance from the source.

[0051] Regardless of whether major structural reinforcement is required, the system triggers damper activation. Transmission tower structures are typically equipped with passive or semi-active tuned mass dampers or viscous dampers. The damper activation process is implemented through a control algorithm: the system calculates the optimal damper parameters (such as the tuning frequency and damping coefficient of the mass block) based on the currently monitored main frequency and amplitude of the structural vibration. For passive dampers, it may be necessary to remotely adjust the internal variable damping valve or mass block position; for semi-active or active dampers, real-time adjustment instructions are sent to their control system to make it output a force that is opposite to the structural vibration, thereby effectively dissipating vibration energy, suppressing structural response, and reducing the fatigue damage rate.

[0052] A balancer typically refers to a controllable counterweight system or hydraulic adjustment device installed at a specific location on the tower head or tower body. Its core function is to shift loads upward in the longitudinal and lateral directions of the tilt to maintain a near-vertical state. For example, when a transmission tower is detected to be tilting longitudinally (along the line) or transversely (perpendicular to the line) due to strong winds or uneven foundation settlement, the balancer control system activates. In the event of longitudinal tilt, the balancer may use a hydraulic jacking device to fine-tune the load at the tower head (such as the equivalent mass at the conductor attachment point) upward in the direction of tilt (i.e., in the opposite direction of tilt). In the event of lateral tilt, the balancer adjusts the position of the counterweight sliders on both sides of the tower body to shift mass upward in the direction of tilt. This active load redistribution generates a restoring moment opposing the tilt trend, effectively offsetting the tilting force and helping the structure regain or maintain a near-vertical stable state. This reduces the additional bending moment and stress concentration caused by the tilt, thereby mitigating fatigue risks. After completing the reinforcement of the structural connectors and foundation reinforcements, the balancer operation is the last step, working together with the dampers to finally complete the overall reinforcement and stabilization of the transmission tower structure.

[0053] If the system determines that the transmission tower structure does not require major structural reinforcement of the structural connectors and foundation, a different set of operations will be executed. Similarly, the system triggers damper activation, adjusting damping parameters based on real-time vibration data to suppress vibration and reduce fatigue damage. Simultaneously, the system also triggers balancer operation, which maintains the structure's near-stability through longitudinal and lateral load movement, offsetting any minor tilting trends detected and maintaining a healthy structural load-bearing state.

[0054] If major reinforcement is not required, the system triggers electrical isolation of the transmission tower structure from its foundation. This operation is intended to block any potential stray current paths through the tower and foundation. If stray currents flowing in the soil form a loop through the metal tower and foundation, they can trigger electrochemical corrosion, accelerating the corrosion of metal connectors and foundation reinforcement, thereby reducing fatigue life and load-bearing capacity. Electrical isolation is achieved physically by installing high-performance insulation materials between the tower legs and the foundation cap or at the foundation anchor bolts. These insulation materials must possess extremely high mechanical strength to withstand structural loads, as well as excellent electrical insulation properties and long-term weather resistance. Installation ensures that the insulation gaskets completely isolate the metal tower from the reinforcement mesh in the concrete foundation, completely cutting off any potential current paths. After electrical isolation is implemented, the system verifies the isolation effectiveness using a dedicated insulation resistance monitoring device to ensure the required high resistance is achieved.

[0055] Regardless of which path is executed (reinforcement required or not), the system re-enters the monitoring and evaluation loop after all triggering actions are completed. The evaluation unit, utilizing calibrated parameters, continues to receive real-time wind-induced fatigue data and executes multi-stage evaluations. The dynamic tuning unit continues to adjust the evaluation step size based on the new data stream. The system continuously monitors the effectiveness of reinforcement or optimization measures, such as observing the attenuation of vibration amplitude after damper activation, the correction of tilt trends after balancer operation, the elimination of stray currents after electrical isolation, and changes in the stress or damage accumulation rate at critical nodes.

[0056] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0057] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for evaluating the disaster resistance performance of transmission towers in near-fault areas considering wind-induced fatigue effects, characterized in that: include: Acquiring wind-induced fatigue data of transmission towers in a near-fault area, the wind-induced fatigue data including wind speed data, structural vibration data, and fatigue damage data; Determining wind-induced fatigue anomalies, including wind-induced fatigue baseline, single-mode anomaly, and secondary verification; Extract features from wind-induced fatigue data, assign the extracted wind-induced fatigue features to labels with timestamps, and input them into the evaluation unit; The evaluation unit sets a multi-level evaluation process to analyze and judge the wind-induced fatigue data and outputs the disaster resistance performance evaluation results; A dynamic tuning unit that adjusts the evaluation step size of the evaluation unit in real time receives the disaster resistance performance evaluation result and determines whether the transmission tower structure needs to be reinforced.

2. The disaster resistance performance assessment method of a transmission tower in a near-fault area considering wind-induced fatigue effects according to claim 1 is characterized in that: The determination of wind-induced fatigue anomaly includes comparing the wind-induced fatigue baseline with the acquired wind speed data, structural vibration data, and fatigue damage data to see whether they are within a normal threshold range of wind-induced fatigue. If the wind speed data, structural vibration data, and fatigue damage data are not within the normal threshold range of wind-induced fatigue, the determination of wind-induced fatigue anomaly is triggered. The single modal anomaly is used to map whether there is a mutation, imbalance and decoupling in the wind speed data, structural vibration data and fatigue damage data. If there is a single data anomaly in any of the wind speed data, structural vibration data and fatigue damage data, a single wind-induced fatigue anomaly data report is output and the data acquisition unit is checked for abnormality.

3. The disaster resistance performance assessment method of a transmission tower in a near-fault area considering wind-induced fatigue effects according to claim 2 is characterized in that: The secondary verification includes time series correlation verification and spatial propagation verification. The time series correlation verification is used to establish the sudden change, imbalance and decoupling of the continuous time stamp wind speed data. The spatial propagation verification is used to obtain the sudden change, imbalance and decoupling of the structural vibration data and fatigue damage data. If the mapped data in the temporal correlation verification and spatial propagation verification are abnormal, the grid density is dynamically optimized by dividing the grid into high-resolution grids and extracting local neighborhood features.

4. The disaster resistance performance assessment method of a transmission tower in a near-fault area considering wind-induced fatigue effects according to claim 3 is characterized in that: The feature extraction of wind-induced fatigue data includes performing dynamic fluctuation feature extraction processing on wind speed data to obtain a wind speed fluctuation feature vector, performing structural response feature analysis processing on structural vibration data to obtain a structural response feature vector, and performing cross-modal feature fusion processing on the wind speed fluctuation feature vector and the structural response feature vector to generate a fused wind-induced feature set; The cross-modal feature fusion processing includes time dimension alignment processing, mapping the wind speed fluctuation feature vector to the same time granularity as the structural response feature vector, and constructing a wind speed-structure cross-attention mechanism to calculate the cross-modal correlation matrix between the fluctuation features of each time step in the wind speed fluctuation feature vector and the response features of the corresponding time step in the structural response feature vector.

5. The disaster resistance performance assessment method of a transmission tower in a near-fault area considering wind-induced fatigue effects according to claim 4 is characterized in that: The evaluation unit includes a wind speed evaluation unit, a structural vibration evaluation unit and a fatigue damage evaluation unit; The wind speed assessment and advancement unit takes the wind speed characteristics with timestamp tags as input, monitors the wind speed characteristics within consecutive timestamps in real time, obtains the difference between the wind speed characteristics at the previous moment and the wind speed characteristics at the current moment, and obtains the difference between the wind speed characteristics at the next moment and the wind speed characteristics at the current moment, and triggers an abnormal flag within the continuous time; The structural vibration assessment and advancement unit sets a structural vibration prediction model, predicts structural vibration data at the next moment through the structural vibration prediction model, and marks structural risks through mutation detection.

6. The disaster resistance performance assessment method of a transmission tower in a near-fault area considering wind-induced fatigue effects according to claim 5, characterized in that: The dynamic tuning unit receives the disaster resistance performance evaluation result, drives the wind speed evaluation shift unit to receive the wind speed change rate within the continuous time stamp through the wind speed change rate within the continuous time stamp, and adjusts the wind speed parameter evaluation shift step. If the wind speed data change rate per unit time is greater than the highest weight, the wind speed parameter evaluation shift step is shortened; The step length is adjusted by the acceleration of the structural vibration change of the continuous time stamp. If the increase in the acceleration of the structural vibration change of the time stamp from t-1 to t is greater than the acceleration of the structural vibration change of the continuous time stamp from t-2 to t-1, and the acceleration increase is greater than the minimum threshold, the step length ratio is compressed. The fatigue damage signal is obtained through the fatigue damage assessment push unit, and the step size adjustment is activated through comparison with the damage feature library. If the damage signal in the frequency band captured by the fatigue damage spectrum is crack extension and material degradation, the damage push step size of the fatigue damage assessment push unit is adjusted.

7. The disaster resistance performance assessment method of a transmission tower in a near-fault area considering wind-induced fatigue effects according to claim 6, characterized in that: The pre-trained evaluation network model is used to perform fatigue root cause weighting on the fused wind-induced feature set to generate an abnormal correlation score set corresponding to wind-induced fatigue. The abnormal correlation score set contains the abnormal correlation distribution between fatigue damage data and various structural response features. Based on the abnormal correlation distribution, the fatigue damage data and structural response characteristic vectors are jointly traced to generate abnormal root cause tracing results of wind-induced fatigue.

8. The disaster resistance performance assessment method of a transmission tower in a near-fault area considering wind-induced fatigue effects according to claim 7, characterized in that: Setting step boundary limits for receiving the adjusted damage transition step, the structural vibration compression step ratio, and the adjusted wind speed assessment transition step, and setting intensity levels, including low disturbance and medium-high disturbance; By adjusting the step size boundary, the redundant boundary buffer layer is triggered to temporarily tolerate the step size adjustment. If the step size temporarily exceeds the rated boundary, the total number of steps after actual adjustment is no greater than the maximum number of steps in the redundant boundary buffer layer. If the buffer layer stay time exceeds the threshold, it will immediately switch to the minimum safe step size.

9. The disaster resistance performance assessment method of a transmission tower in a near-fault area considering wind-induced fatigue effects according to claim 8, characterized in that: If the wind speed change rate, structural vibration gradient change rate and fatigue damage spectrum characteristics after the evaluation unit adjustment are in the stable domain of the redundant boundary buffer layer, the step size of the evaluation unit evaluation will continue to be adjusted according to the real-time data; If the total compensation amount of the evaluation unit's adjustment step size is not greater than the maximum step size of the redundant boundary buffer layer, and the buffer layer residence time is greater than a threshold, the step size freeze is triggered.

10. The disaster resistance performance assessment method of a transmission tower in a near-fault area considering wind-induced fatigue effects according to claim 9, characterized in that: Generate a disaster resilience performance optimization strategy based on the abnormal root cause tracing results, and feed the disaster resilience performance optimization strategy back to the evaluation unit to trigger parameter calibration operations; If it is determined that the transmission tower structure needs to be reinforced, the transmission tower structure connectors and foundation reinforcements are strengthened, the dampers are activated, and the balancers are triggered. The balancers move the load upward in the longitudinal and transverse directions to maintain a near-stable state, ultimately completing the reinforcement of the transmission tower structure. If the transmission tower structure does not need reinforcement, the trigger damper is activated and the balancer is triggered. The balancer moves the load upward in the longitudinal and lateral directions of the tilt to maintain a near-stable state, triggering electrical isolation of the transmission tower structure from the foundation.

Images