Dynamic monitoring method and system for settlement and inclination of tower drum of wind generating set

Abstract

The invention discloses a dynamic monitoring method and system for settlement and inclination of a tower drum of a wind generating set, and relates to the technical field of safety monitoring of wind power generation infrastructure, the method comprises the following steps: synchronously collecting inclination data and positioning data of each monitoring point, and carrying out space-time alignment to obtain a fusion data set; decoupling the dynamic elastic response of the tower drum and the steady-state deformation of the foundation from the fused data through frequency domain analysis, and further calculating the overall inclination rate, the settlement amount and the non-uniform settlement rate of the tower drum; performing safety assessment based on the calculated parameters and a preset safety threshold, and determining a basic safety state and a risk mode; and finally, generating graded early warning information and decision information including risk positioning and trend prediction according to an evaluation result. Through the above mode, the method achieves the precise separation and monitoring of the dynamic deformation characteristics of the tower drum, improves the accuracy of safety evaluation and the timeliness of early warning, and provides an effective data support for the operation and maintenance decision of a wind generating set.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind power generation infrastructure safety monitoring, in particular to a wind turbine generator tower settlement and inclination dynamic monitoring method and system. BACKGROUND

[0002] As a clean and renewable energy conversion device, wind turbines have been widely used all over the world. With the rapid development of wind energy industry, wind turbines are developing towards large-scale and high-tower, and their structural safety and long-term stable operation become increasingly important. The tower of the wind turbine is a key load-bearing structure supporting the entire nacelle and impeller, and its foundation bears huge static load (self-weight of the unit) and complex dynamic load (wind load, unit operation load, etc.) for a long time. In particular, wind turbines built on poor geological conditions such as coastal beaches, soft soil foundations, and mountain backfill areas face severe challenges in terms of safety and stability of the tower foundation.

[0003] Currently, the settlement of the wind turbine foundation, especially the uneven settlement, is one of the main hidden dangers threatening the structural safety of the wind turbine. Uneven settlement can cause the tower to tilt, shift the center of gravity, and generate additional bending moments inside the tower, significantly aggravating the fatigue damage of the tower flange connection bolts, and even possibly causing catastrophic accidents such as tower buckling and collapse. Traditional settlement monitoring methods (such as manual leveling) have obvious limitations: first, the measurement period is long and the frequency is low, making it difficult to capture the dynamic development process of settlement in a timely manner; second, it is greatly affected by environmental factors such as weather and line of sight, and has low automation, making it impossible to achieve continuous monitoring in all weather conditions; third, it can usually only monitor a small number of points around the foundation ring, making it difficult to fully reflect the deformation posture of the entire tower structure in the height direction and accurately calculate the uneven settlement.

[0004] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0005] The main purpose of the present application is to provide a wind turbine generator tower settlement and inclination dynamic monitoring method and system, which aims to solve the technical problem of being unable to accurately separate the dynamic response of the tower and the deformation of the foundation in the prior art.

[0006] To achieve the above-mentioned purpose, the present application provides a wind turbine generator tower settlement and inclination dynamic monitoring method, which comprises: synchronously collecting inclination data and positioning data of each monitoring point, and performing space-time alignment on the inclination data and the positioning data to obtain a fusion data set; decoupling a dynamic elastic response of the tower from a base steady-state deformation in the fusion dataset, calculating an overall tilt rate, a settlement amount and a differential settlement rate of the tower according to the dynamic elastic response and the base steady-state deformation; performing a safety assessment based on the overall tilt rate, the settlement amount, the differential settlement rate and corresponding safety thresholds respectively, obtaining a base safety state and a risk pattern; generating a hierarchical early warning information and a decision information containing risk positioning and trend prediction according to the base safety state and the risk pattern.

[0007] In an embodiment, the step of decoupling a dynamic elastic response of the tower from a base steady-state deformation in the fusion dataset, calculating an overall tilt rate, a settlement amount and a differential settlement rate of the tower according to the dynamic elastic response and the base steady-state deformation comprises: performing a frequency domain analysis on time-series tilt data in the fusion dataset, decomposing the time-series tilt data into a high-frequency component and a low-frequency component through a preset cutoff frequency, wherein the high-frequency component corresponds to a dynamic elastic response of the tower caused by wind load and wind turbine operation, and the low-frequency component corresponds to a base steady-state deformation caused by foundation change; performing trend fitting on the low-frequency component to obtain a base steady-state deformation curve, and calculating the overall tilt rate of the tower according to a slope of the base steady-state deformation curve; extracting time-series positioning data of different monitoring points from the fusion dataset, compensating and correcting deformation values at corresponding time points of the base steady-state deformation curve based on the time-series positioning data to obtain pure settlement time-series data of each monitoring point; calculating an average settlement amount of the tower center based on the pure settlement time-series data, and calculating the differential settlement rate according to settlement differences of different azimuth monitoring points around the tower.

[0008] In an embodiment, the step of performing a frequency domain analysis on time-series tilt data in the fusion dataset, decomposing the time-series tilt data into a high-frequency component and a low-frequency component through a preset cutoff frequency comprises: performing a fast Fourier transform on the time-series tilt data in the fusion dataset to obtain frequency spectrum data; determining a cutoff frequency according to a first natural frequency of the tower; filtering out signal components with frequencies higher than the cutoff frequency in the frequency spectrum data as the high-frequency component, and filtering out signal components with frequencies lower than the cutoff frequency in the frequency spectrum data as the low-frequency component.

[0009] In an embodiment, the step of performing trend fitting on the low-frequency component to obtain a base steady-state deformation curve, and calculating an overall tilt rate of the tower drum according to a slope of the base steady-state deformation curve comprises: performing smoothing processing on the low-frequency component based on a time window sliding average method to obtain a smoothed low-frequency component; performing linear regression fitting on the smoothed low-frequency component based on a least square method to obtain a base steady-state deformation curve; determining a slope of the base steady-state deformation curve, and taking the slope as the overall tilt rate of the tower drum.

[0010] In an embodiment, the step of compensating and correcting a deformation value at a corresponding time according to the time-series positioning data based on the base steady-state deformation curve to obtain pure settlement time-series data of each monitoring point comprises: calculating, according to a geometric model of the tower drum and the base steady-state deformation curve, a deformation value at a corresponding time under a target timestamp, the deformation value being a horizontal displacement amount of the tower drum at each monitoring point; compensating and correcting the horizontal displacement amount according to the time-series positioning data to obtain corrected positioning data; extracting an elevation component in the corrected positioning data to obtain pure settlement time-series data of each monitoring point.

[0011] In an embodiment, the step of performing safety evaluation based on the overall tilt rate, the settlement amount, the uneven settlement rate and corresponding safety threshold values respectively to obtain a base safety state and a risk mode comprises: presetting a multi-level safety threshold system corresponding to the overall tilt rate, the settlement amount and the uneven settlement rate, the multi-level safety threshold system comprising setting safety threshold values, warning threshold values and danger threshold values for each index respectively; comparing the overall tilt rate, the settlement amount and the uneven settlement rate with corresponding multi-level safety threshold values respectively to determine a safety level of each index; performing weighted or logical combination judgment on the safety levels of each index based on a preset comprehensive evaluation rule to obtain a base safety state; when the base safety state is a target safety state, determining an out-of-limit index, and identifying a dominant risk mode according to a type, severity and combination relationship of the out-of-limit index.

[0012] In an embodiment, the step of performing weighted or logical combination judgment on the safety levels of each index based on a preset comprehensive evaluation rule to obtain a base safety state comprises: when a safety level of any index among the overall tilt rate, the settlement amount and the uneven settlement rate reaches a danger threshold value, determining that the base safety state is dangerous. when the safety level of all indexes does not reach the danger threshold value and the safety level of any index reaches the warning threshold value, the basic safety state is determined as warning; when the safety level of all indexes does not reach the warning threshold value and the safety level of any index reaches the attention threshold value, the basic safety state is determined as attention; when the safety levels of the overall tilt rate, the settlement amount and the uneven settlement rate are all within the safety threshold range, the basic safety state is determined as safe.

[0013] In an embodiment, the step of generating graded early warning information and decision information containing risk positioning and trend prediction according to the basic safety state and the risk pattern comprises: mapping the basic safety state and the risk pattern to a graded early warning relationship to obtain a target early warning level; generating graded early warning information based on the target early warning level; performing trend prediction according to the risk positioning, the basic safety state and the risk pattern to obtain trend prediction information; obtaining decision information according to the risk positioning and the trend prediction information.

[0014] In an embodiment, after the step of generating graded early warning information and decision information containing risk positioning and trend prediction according to the basic safety state and the risk pattern, the method further comprises: sending the graded early warning and decision information to a remote monitoring platform and a user terminal, and triggering a sound and light alarm device; based on the risk pattern and the early warning level, automatically adjusting the collection frequency of monitoring data or starting targeted review monitoring; storing the fusion data set, the safety evaluation result, the early warning information and the decision information of this monitoring to a historical database, and generating a monitoring report for model optimization and threshold updating.

[0015] In addition, to achieve the above-mentioned purpose, the application further provides a wind turbine tower settlement and tilt dynamic monitoring system, which comprises: a data acquisition and fusion module, configured to synchronously acquire tilt data and positioning data of each monitoring point, and perform space-time alignment on the tilt data and the positioning data to obtain a fusion data set; a deformation decoupling and calculation module, configured to decouple dynamic elastic response and basic steady-state deformation of the tower from the fusion data set, and calculate an overall tilt rate, a settlement amount and an uneven settlement rate of the tower according to the dynamic elastic response and the basic steady-state deformation; a safety evaluation module configured to perform safety evaluation based on the overall tilt rate, the settlement amount, the uneven settlement rate and corresponding safety thresholds respectively, to obtain a basic safety state and a risk mode; a pre-warning and decision module configured to generate hierarchical pre-warning information and decision information containing risk positioning and trend prediction according to the basic safety state and the risk mode.

[0016] In addition, to achieve the above-mentioned purpose, the present application also provides a wind turbine tower settlement and tilt dynamic monitoring device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the wind turbine tower settlement and tilt dynamic monitoring method as described above.

[0017] In addition, to achieve the above-mentioned purpose, the present application also provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the wind turbine tower settlement and tilt dynamic monitoring method as described above.

[0018] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the wind turbine tower settlement and tilt dynamic monitoring method as described above.

[0019] The present application provides a wind turbine tower settlement and tilt dynamic monitoring method, which synchronously collects tilt data and positioning data of each monitoring point, and performs time and space alignment to obtain a fusion data set; decouples dynamic elastic response of the tower and steady-state deformation of the foundation from the fusion data through frequency domain analysis, and then calculates overall tilt rate, settlement amount and uneven settlement rate of the tower; performs safety evaluation based on the calculated parameters and preset safety thresholds to determine a basic safety state and a risk mode; and finally generates hierarchical pre-warning information and decision information containing risk positioning and trend prediction according to the evaluation results. In the above manner, the present method realizes accurate separation and monitoring of the dynamic characteristics of the tower deformation, improves the accuracy of safety evaluation and the timeliness of pre-warning, and provides effective data support for operation and maintenance decision of the wind turbine. BRIEF DESCRIPTION OF DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application.

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating an embodiment of the dynamic monitoring method for settlement and tilt of wind turbine towers in this application. Figure 2 This is a schematic diagram of wind turbine tower settlement and tilting, representing an embodiment of the wind turbine tower settlement and tilting dynamic monitoring method of this application. Figure 3 This is a schematic diagram of the module structure of the dynamic monitoring system for settlement and tilt of wind turbine towers according to an embodiment of this application; Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the dynamic monitoring method for settlement and tilt of wind turbine towers in this application embodiment.

[0023] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0024] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0025] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0026] The main solution of this application embodiment is: synchronously collect tilt data and positioning data of each monitoring point, perform spatiotemporal alignment of the tilt data and the positioning data, and obtain a fused dataset; The dynamic elastic response of the tower and the steady-state deformation of the foundation are decoupled from the fused dataset, and the overall tilt rate, settlement and uneven settlement rate of the tower are calculated based on the dynamic elastic response and the steady-state deformation of the foundation. Safety assessments are conducted based on the overall tilt rate, the settlement amount, the non-uniform settlement rate, and the corresponding safety thresholds to obtain the basic safety status and risk mode. Based on the basic security status and the risk model, tiered early warning information and decision information including risk identification and trend prediction are generated.

[0027] At present, wind turbines as a clean, renewable energy conversion equipment has been widely used in the world. With the rapid development of wind energy industry, wind turbine is developing towards large-scale and high tower, its structural safety and long-term stable operation becomes increasingly important. The tower of wind turbine as the key load-bearing structure to support the entire nacelle and impeller, its foundation bears huge static load (self weight) and complex dynamic load (wind load, turbine operation load, etc.) for a long time. Especially for wind turbines built on poor geological conditions such as coastal beach, soft soil foundation, mountain backfill area, the safety and stability of its tower foundation face severe challenges.

[0028] At present, the settlement of wind turbine foundation, especially the uneven settlement, is one of the main hidden dangers threatening the safety of wind turbine structure. Uneven settlement will cause the tower to tilt, shift the center of gravity, and generate additional bending moment inside the tower, significantly aggravate the fatigue damage of the tower flange connection bolt, and even may cause catastrophic accidents such as tower buckling and collapse. The traditional settlement monitoring method (such as manual leveling) has obvious limitations: first, the measurement period is long and the frequency is low, it is difficult to capture the dynamic development process of settlement in time; second, it is greatly affected by weather, line of sight and other environmental factors, and has low automation degree, it cannot realize all-weather continuous monitoring; third, it can usually only monitor a small number of points around the foundation ring, it is difficult to fully reflect the deformation posture of the entire tower structure in the height direction, and it cannot accurately calculate the uneven settlement.

[0029] The present application provides a solution, by synchronously collecting the inclination data and positioning data of each monitoring point, and performing space-time alignment to obtain a fusion data set; by frequency domain analysis, the dynamic elastic response of the tower and the steady-state deformation of the foundation are decoupled from the fusion data, and then the overall tilt rate, settlement and uneven settlement rate of the tower are calculated; based on the calculated parameters and the preset safety threshold, the safety is evaluated, and the foundation safety state and risk mode are determined; finally, the evaluation results are used to generate graded warning information and decision information containing risk positioning and trend prediction. Through the above method, the dynamic characteristics of the tower deformation are accurately separated and monitored, the accuracy of safety evaluation and the timeliness of early warning are improved, and effective data support is provided for the operation and maintenance decision of wind turbine generator.

[0030] It should be noted that the execution subject of the present embodiment can be a computing service device with data processing, network communication and program running functions, such as tablet computers, personal computers, mobile phones, etc., or an electronic device capable of realizing the above functions, a wind turbine tower settlement and inclination dynamic monitoring device, etc., and the present embodiment does not make specific limitation thereon. In the following, the wind turbine tower settlement and inclination dynamic monitoring device is taken as an example to explain the present embodiment and each of the following embodiments.

[0031] All actions of obtaining signals, information or data in this application are carried out in compliance with the corresponding data protection regulations and policies of the country where the device is located, and with the authorization given by the owner of the corresponding device.

[0032] The embodiment of the application provides a wind turbine tower settlement and inclination dynamic monitoring method, referring to Figure 1 , Figure 1 The embodiment of the application provides a wind turbine tower settlement and inclination dynamic monitoring method, referring to

[0033] In the embodiment, the wind turbine tower settlement and inclination dynamic monitoring method comprises steps S10-S40: Step S10, synchronously collecting inclination data and positioning data of each monitoring point, and performing space-time alignment on the inclination data and the positioning data to obtain a fusion data set.

[0034] It should be noted that the wind turbine tower refers to a key high-altitude structure supporting a wind turbine nacelle and a wind wheel. The inclination data refers to an angle change amount of a tower axis relative to a plumb line measured by an inclination sensor installed on a monitoring point at different heights of the tower. The positioning data refers to three-dimensional coordinate information obtained by a high-precision GNSS receiver installed on a monitoring point around a tower foundation. The fusion data set refers to a standardized data set formed by associating and integrating data of different sensors under a unified time stamp and a spatial coordinate system.

[0035] In a specific implementation, high-precision inclination sensors and Beidou / GPS dual-mode positioning modules are respectively installed on a foundation ring of a wind turbine tower and at least two different-height tower platforms distributed along a height direction of the tower, to form a three-dimensional monitoring network with spatial redundancy checking capability. The positions where the high-precision inclination sensors and the Beidou / GPS dual-mode positioning modules are installed are monitoring points. A high-precision timing module (such as a GPS clock) is usually used to provide a synchronous clock signal for all sensors, to ensure time consistency of data collection. Meanwhile, a local coordinate system of the tower is established, and spatial position relationships of all monitoring points are accurately calibrated, so that inclination data (angle observation) and positioning data (coordinate observation) are aligned in space, to form a space-time synchronous fusion data set that can be used for subsequent analysis.

[0036] Step S20, decoupling a dynamic elastic response of the tower and a steady-state deformation of the foundation from the fusion data set, and calculating an overall inclination rate, a settlement amount and a non-uniform settlement rate of the tower according to the dynamic elastic response and the steady-state deformation of the foundation.

[0037] It should be noted that the dynamic elastic response of the tower refers to the periodic and recoverable elastic bending and vibration of the tower structure under the action of wind load, unit operation and other transient dynamic loads; the foundation steady-state deformation refers to the slowly changing and non-recoverable permanent displacement of the tower foundation caused by factors such as consolidation of the foundation soil body and long-term change of the environmental temperature; the overall inclination rate is the change rate of the foundation steady-state deformation in the horizontal direction; the settlement amount is the cumulative sinking amount of the foundation center point in the vertical direction due to the steady-state deformation; and the uneven settlement rate is the difference change rate of the settlement amounts of different positions (such as the two edge points) of the foundation, which is a key index for evaluating the development speed of the foundation inclination.

[0038] It can be understood that generally, a digital signal processing technology such as a high-pass filter is used to separate the high-frequency dynamic response from the time-series fusion data, and a low-pass filter or a time-series model (such as a moving average or Kalman filter) is used to extract the low-frequency steady-state deformation trend, and then based on the separated steady-state deformation data sequence, the change rate and the settlement amount are calculated through linear fitting or statistical analysis.

[0039] In a feasible implementation, the step of decoupling the dynamic elastic response of the tower and the foundation steady-state deformation from the fusion data set and calculating the overall inclination rate, the settlement amount and the uneven settlement rate of the tower according to the dynamic elastic response and the foundation steady-state deformation comprises: performing frequency domain analysis on the time-series inclination data in the fusion data set, and decomposing the time-series inclination data into high-frequency components and low-frequency components through a preset cutoff frequency, wherein the high-frequency components correspond to the dynamic elastic response of the tower caused by wind load and wind turbine operation, and the low-frequency components correspond to the foundation steady-state deformation caused by foundation changes; performing trend fitting on the low-frequency components to obtain a foundation steady-state deformation curve, and calculating the overall inclination rate of the tower according to the slope of the foundation steady-state deformation curve; extracting time-series positioning data of different monitoring points from the fusion data set, and compensating and correcting the deformation values at the corresponding time of the foundation steady-state deformation curve based on the time-series positioning data to obtain pure settlement time-series data of each monitoring point; based on the pure settlement time-series data, calculating the average settlement amount of the tower center, and calculating the uneven settlement rate according to the settlement difference of the monitoring points at different directions around the tower.

[0040] It should be noted that the time series tilt data refers to a series of tower tilt angle observations measured by the tilt sensor in time sequence. Frequency domain analysis is a mathematical method of converting time domain signals to frequency domain to analyze their frequency components, which is often implemented by fast Fourier transform (FFT). The preset cutoff frequency is a threshold frequency used to distinguish high-frequency vibration and low-frequency deformation, which is usually set according to the first-order natural frequency of the tower and the characteristics of the foundation, for example, it can be set to 0.1 Hz, and frequencies higher than this value are considered high frequencies. High-frequency components mainly reflect the instantaneous and periodic elastic bending of the tower under dynamic excitations such as wind load and unit start-stop. Low-frequency components represent slow and continuous foundation tilt deformation caused by foundation consolidation and soil creep. The foundation steady-state deformation curve is a smooth curve obtained by polynomial or linear fitting of the low-frequency components, and its slope is the overall tilt rate, which represents the change trend of the foundation tilt.

[0041] In a specific implementation, with reference to Figure 2 , Figure 2 is a schematic diagram of wind turbine tower settlement tilt. Time series positioning data is a time series of three-dimensional coordinates of the monitoring point recorded by a high-precision GNSS receiver. Compensation correction refers to deducting the influence of the horizontal displacement of the tower top caused by the foundation tilt (i.e. attitude change) on the elevation coordinate from the original positioning data, so as to extract pure settlement time series data caused only by foundation vertical settlement. Its principle can be simplified as the formula: , wherein is the pure settlement value, is the original elevation value measured by GNSS, is the equivalent height of the monitoring point from the tower root hinge point, is the foundation steady-state tilt angle at the corresponding time. Based on the pure settlement data of each monitoring point, the average settlement of the tower center can be obtained by calculating the arithmetic mean of the settlement values of all surrounding monitoring points at the same time. The uneven settlement rate is quantitatively evaluated by calculating the rate of change of the difference between the pure settlement values of two monitoring points symmetrically arranged on the tower foundation (such as east-west or north-south) with time, i.e. .

[0042] In a feasible implementation, the step of performing frequency domain analysis on the time series tilt data in the fusion data set by decomposing the time series tilt data into high-frequency components and low-frequency components through a preset cutoff frequency includes: performing fast Fourier transform on the time series tilt data in the fusion data set to obtain frequency spectrum data; determining the cutoff frequency according to the first-order natural frequency of the tower; filtering out signal components with frequencies higher than the cutoff frequency in the frequency spectrum data as high-frequency components, and signal components with frequencies lower than the cutoff frequency in the frequency spectrum data as low-frequency components.

[0043] It can be understood that the time series tilt data refers to the time series tilt angle sequence continuously collected by the tilt sensor in time sequence, which can be expressed as , wherein is a timestamp. Fast Fourier transform: an efficient algorithm for calculating the discrete Fourier transform, which can convert the time domain signal into a frequency domain representation , thereby revealing the amplitude and phase of different frequency components in the signal. Its formula is , wherein is the number of sampling points, corresponding to the frequency. Spectral data: the frequency-amplitude relationship diagram obtained after FFT transformation, with the horizontal axis as the frequency and the vertical axis as the energy or amplitude of the corresponding frequency component, which can intuitively show the main frequency components of the tower vibration. First-order natural frequency: the lowest order natural frequency of the tower as an elastic body bending vibration, which is one of the most important dynamic characteristics of the structure, and is usually obtained by finite element model calculation or field measurement. Cutoff frequency: here as a threshold value for filter design, used to strictly distinguish high-frequency signals representing tower elastic vibration and low-frequency signals representing foundation deformation.

[0044] It should be understood that the time series tilt data is first detrended and windowed to reduce spectral leakage, and then the FFT algorithm is applied to convert it to the frequency spectrum . The determination of the cutoff frequency is crucial to ensure that the structure dynamic response and the foundation deformation can be effectively separated. Usually, the cutoff frequency is set to be slightly lower than the first-order natural frequency of the tower (for example . The purpose of this is to retain the true information related to the foundation deformation that may be contained in the low frequency band, while completely assigning the main vibration mode of the structure to the high frequency band.

[0045] The separation process is completed in the frequency domain: by constructing an ideal low-pass filter (frequency response function when , otherwise 0) and a high-pass filter ( when , otherwise 0), respectively multiplied by the frequency spectrum , the low-frequency component spectrum and the high-frequency component spectrum can be obtained. Finally, the inverse fast Fourier transform is performed on and , respectively, to reconstruct the low-frequency tilt signal (foundation steady-state deformation) and high-frequency tilt signal (dynamic elastic response) in the time domain.

[0046] ​In an implementation, the step of performing trend fitting on the low-frequency component to obtain a base steady-state deformation curve, and calculating an overall tilt rate of the tower drum based on a slope of the base steady-state deformation curve comprises: performing smoothing on the low-frequency component based on a time-windowed moving average method to obtain a smoothed low-frequency component; performing linear regression fitting on the smoothed low-frequency component based on a least square method to obtain a base steady-state deformation curve; determining a slope of the base steady-state deformation curve, and taking the slope as the overall tilt rate of the tower drum.

[0047] It can be understood that the smoothed low-frequency component refers to the low-frequency tilt data after smoothing filtering such as moving average, which retains the long-term trend of the base deformation, and filters out the residual short-term fluctuations and noises.

[0048] Linear regression fitting refers to a process of linear fitting using a least square method, and the result is a straight line shaped like y = kx + b, where the dependent variable y is the tilt angle, and the independent variable x is the time. The base steady-state deformation curve refers to the straight line obtained by linear regression fitting, which represents the overall and steady-state trend of the base tilt angle changing with time. The overall tilt rate is the slope k of the base steady-state deformation curve, which reflects the long-term average speed of the tower drum base tilt.

[0049] It should be understood that the low-frequency component (angle time series ) is first smoothed by applying the moving average method. Assuming that the time window length is N (such as N = 24, representing 24 hours), then the smoothed value at time t is The calculation formula is:

[0050] It aims to further eliminate fluctuations that may be caused by measurement noise or minor environmental disturbances, and make the trend of the base deformation clearer.

[0051] Subsequently, the smoothed data sequence is linearly regressed and fitted. Assuming that the time series has m points , the goal is to find the slope k (i.e., the overall tilt rate) and the intercept b, so that the total error is minimized. According to the principle of least square method, the calculation formula of k is:

[0052] The final fitted straight line is the base steady-state deformation curve, and the slope The value and sign (positive or negative) directly gives the rate and direction of the overall tilt of the tower drum.

[0053] In an implementable embodiment, the step of compensating and correcting the deformation value of the corresponding time of the basic steady-state deformation curve based on the time-series positioning data to obtain the pure settlement time-series data of each monitoring point comprises: According to the geometric model of the tower drum and the basic steady-state deformation curve, the deformation value of the corresponding time at the target timestamp is calculated, and the deformation value is the horizontal displacement amount of the tower drum at each monitoring point; According to the time-series positioning data, the horizontal displacement amount is compensated and corrected to obtain corrected positioning data; Extracting the elevation component in the corrected positioning data obtains the pure settlement time-series data of each monitoring point.

[0054] It should be noted that the geometric model of the tower drum is a mathematical model that simplifies the tower drum into a geometric shape, which is usually a circular cone or a circular cylinder. It contains key size parameters such as tower drum height, bottom diameter, top diameter, and vertical height of each monitoring point (GNSS antenna installation point) from the top surface of the tower drum foundation .

[0055] The deformation value / horizontal displacement amount refers to the displacement amount in the horizontal direction of the top monitoring point of the tower drum caused by the inclination of the tower drum foundation. This displacement is a rigid body motion, not an elastic bending of the tower drum.

[0056] Compensation and correction refers to the process of subtracting the geometric impact of horizontal displacement on elevation calculation caused by foundation inclination from the original three-dimensional coordinates measured by the GNSS receiver, thereby separating the pure vertical settlement information. The corrected positioning data refers to the three-dimensional coordinate data obtained after the above compensation calculation, which has eliminated the influence of foundation inclination.

[0057] The pure settlement time-series data refers to the sequence of changes in the elevation component over time extracted from the corrected positioning data. It more truly reflects the vertical displacement caused by the compression and consolidation of the foundation soil, and is the core indicator for evaluating the stability of foundation settlement.

[0058] In a specific implementation, first, based on the geometric model of the tower drum, the tower drum is regarded as a rigid whole (approximately reasonable under low-frequency steady-state deformation). For a target timestamp , the foundation inclination angle at this time is obtained from the foundation steady-state deformation curve . Assuming that the inclination occurs in a dominant direction (the direction angle can be determined by the two-axis data of the inclination sensor), the horizontal displacement amount of the monitoring point installed at a height due to foundation inclination is This displacement can be calculated by simple geometric relations. In the case of small inclination angles, the approximate formula is: This displacement can be decomposed into components in the plane coordinates (e.g. East E and North N):

[0059]

[0060] Subsequently, a compensation correction is performed. The original coordinates of the monitoring points measured directly by GNSS are Subtracting the calculated horizontal displacement components from them, the corrected positioning data (the elevation is temporarily unchanged) are obtained:

[0061] It needs to be emphasized that the direct purpose of this correction is to more accurately calculate the settlement subsequently. Since the elevation solution of GNSS is geometrically coupled with the horizontal position, when the tower tube tilts to cause the horizontal displacement of the top, the projection in the elevation direction will also introduce errors. Through the above correction of the horizontal position, the elevation value is closer to the true vertical elevation of the monitoring point. Finally, the at all time stamps are extracted to form the sequence of pure settlement time series data. This data eliminates the interference of the tower tube "sway" and can more accurately reflect the actual settlement amount of the foundation.

[0062] Step S30, safety evaluation is performed based on the overall inclination rate, the settlement amount, the uneven settlement rate and the corresponding safety threshold value respectively, to obtain the foundation safety state and the risk mode.

[0063] It needs to be noted that the overall inclination rate refers to the average angular velocity of the overall inclination of the tower tube foundation, which is usually calculated from the slope of the foundation steady-state deformation curve, and the unit is usually rad / year or ° / year. The settlement amount refers to the cumulative vertical subsidence of the tower tube foundation monitoring point relative to the initial state or absolute reference, which is an absolute value obtained from the pure settlement time series data. The uneven settlement rate refers to the change rate of the settlement difference between different monitoring points of the tower tube. The safety threshold value refers to the critical value preset for the above monitoring indexes for judging whether the tower tube foundation is in a safe state.

[0064] It can be understood that the real-time calculated overall inclination rate, settlement amount and uneven settlement rate are automatically compared with the preset safety threshold values at all levels in the database, according to the comparison results, the current foundation safety state level is comprehensively determined through the predefined decision logic, and at the same time, the specific risk mode is diagnosed and output according to which index or indexes triggered the alarm, so as to realize the automatic output of the structured safety conclusion from the original data.

[0065] In an implementable embodiment, the step of performing safety evaluation based on the overall inclination rate, the settlement amount, the uneven settlement rate and corresponding safety threshold values respectively, to obtain a basic safety state and a risk mode comprises: presetting a multi-level safety threshold value system corresponding to the overall inclination rate, the settlement amount and the uneven settlement rate, the multi-level safety threshold value system comprising safety threshold values, warning threshold values and danger threshold values respectively set for each index; comparing the overall inclination rate, the settlement amount and the uneven settlement rate respectively with corresponding multi-level safety threshold values to determine the safety level of each index; based on a preset comprehensive evaluation rule, weighting or logically combining the safety levels of each index to obtain a basic safety state; when the basic safety state is a target safety state, determining an out-of-limit index, and identifying a dominant risk mode according to the type, severity and combination relationship of the out-of-limit index.

[0066] In a specific implementation, firstly, a preset multi-level safety threshold value system based on engineering specifications and structural analysis is relied on. The system compares each monitoring index (the overall inclination rate , the settlement amount , the uneven settlement rate ) calculated in real time with the respective threshold value interval. For example, for the inclination rate, the judgment logic is: if , the level is safe; if , the level is warning; if , the level is dangerous (wherein and are the safety threshold value and the warning threshold value of the inclination rate respectively).

[0067] Subsequently, the system makes a comprehensive judgment according to a preset comprehensive evaluation rule. For example, a veto logic is adopted: if any index is dangerous, the basic safety state is directly determined as dangerous; if there is no danger but at least one index is warning, the state is pre-warning; and when all indexes are safe, the state is safe. A more complex rule can adopt a weighted scoring method, assigning a value to each level (such as safe = 1, warning = 2, dangerous = 3), calculating the comprehensive score (wherein is the weight, and is the level value), and then determining the final state according to the total score interval.

[0068] When the basic safety state is determined as a target safety state such as pre-warning or danger, the system locks all out-of-limit indexes, and then identifies the risk mode. For example, if only the settlement amount is out of limit while other indexes are normal, the risk mode is settlement amount out of limit; if the inclination rate and uneven settlement rate If both are exceeded, it can be identified as an increased risk of overturning, as the coupling of the two will significantly increase the bending moment at the bottom of the tower. This pattern recognition process converts abstract numerical alarms into specific engineering risks, guiding subsequent maintenance decisions.

[0069] In a feasible implementation, the step of judging the safety level of each index by weighting or logical combination based on the preset comprehensive evaluation rule to obtain the basic safety state comprises: When the safety level of any index among the overall tilt rate, the settlement amount, and the uneven settlement rate reaches the danger threshold, the basic safety state is determined as dangerous; When the safety level of all indexes does not reach the danger threshold, and the safety level of any index reaches the warning threshold, the basic safety state is determined as warning; When the safety level of all indexes does not reach the warning threshold, and the safety level of any index reaches the attention threshold, the basic safety state is determined as attention; When the safety level of the overall tilt rate, the settlement amount, and the uneven settlement rate are all within the safety threshold range, the basic safety state is determined as safe.

[0070] In a specific implementation, the system first needs to predefine four threshold intervals for each monitoring index (overall tilt rate , settlement amount , and uneven settlement rate ), corresponding to: safety threshold , attention threshold , warning threshold , and danger threshold . The numerical relationship is When evaluating, the program compares the current measured value of each index with the four thresholds to determine its independent safety level (such as safety = 1, attention = 2, warning = 3, and danger = 4).

[0071] Subsequently, the system performs a strict step-by-step judgment process, and the logic is usually represented as an if-elseif statement chain in the code, with the priority arranged from high (most dangerous) to low (safest). This process can be described with the following decision logic: Dangerous determination: The basic safety state is "dangerous".

[0072] Warning determination: The basic safety state is "warning".

[0073] Attention determination: The basic safety state is "attention".

[0074] Safety determination: The basic safety state is "safe".

[0075] The advantage of this implementation is that the logic is clear, the calculation is efficient, and the timeliness of risk response is ensured. Any indicator reaching the danger level will trigger the highest level of alarm, which conforms to the principle of the wood barrel effect in engineering safety, that is, the overall safety of the structure is determined by the weakest link. By setting the two intermediate states of attention and warning, the system can achieve early warning and leave valuable buffer time for maintenance decisions, thus forming a complete closed-loop management from normal monitoring to emergency disposal.

[0076] Step S40, generating hierarchical warning information and decision information containing risk positioning and trend prediction according to the basic safety state and the risk pattern.

[0077] It should be noted that hierarchical warning information refers to notification information corresponding to the basic safety state level, which is used to trigger different response actions, for example, the safe state corresponds to regular monitoring, the attention state issues observation reminders, the warning state starts an enhanced monitoring plan, and the danger state issues an emergency alarm and suggests on-site intervention. Decision information refers to more operational guidance information provided to management personnel based on the warning. It usually includes risk positioning and trend prediction.

[0078] It can be understood that the system calls the corresponding hierarchical warning information from the pre-set template library according to the determined basic safety state level and automatically sends it to the relevant person in charge; at the same time, combined with the specific risk pattern, the system will generate detailed decision information - complete risk positioning by marking the over-standard indicators, and use time series prediction algorithm for extrapolation analysis of key indicators, and integrate the prediction results into the decision information in the form of visual charts or concise texts, thus forming a complete and automated output from state perception to action guidance.

[0079] In one possible implementation, the step of generating hierarchical warning information and decision information containing risk positioning and trend prediction according to the basic safety state and the risk pattern comprises: Mapping the basic safety state and the risk pattern to a hierarchical warning relationship to obtain a target warning level; Generating hierarchical warning information based on the target warning level; Performing trend prediction according to the risk positioning, the basic safety state and the risk pattern to obtain trend prediction information; Decision information is obtained according to the risk positioning and the trend prediction information.

[0080] In a specific implementation, first, the system uses a structured early warning level-risk pattern mapping table as the hierarchical early warning relationship, such as a two-dimensional query table, with rows representing basic safety states and columns representing main risk patterns, and the intersection being the target early warning level. The program quickly maps the evaluation result (e.g., state warning, pattern tilting intensification) to a specific "level 3 (orange) early warning" by querying this table.

[0081] Next, the system enters the prediction phase. It extracts the time series data of the key indicators pointed to by the risk positioning from the database and selects appropriate prediction models, such as simple linear regression or more complex ARIMA models, to generate trend prediction information for the next N periods . Finally, the system fills these elements (target early warning level, risk positioning description, trend prediction curve or key numerical value) into the pre-set template, automatically generates the final hierarchical early warning information containing specific action suggestions and forward-looking decision information, and pushes it to the monitoring platform or mobile terminal through the API interface, completing the closed loop from data to intelligent decision-making.

[0082] In a feasible implementation, after the step of generating hierarchical early warning information and decision information containing risk positioning and trend prediction according to the basic safety state and the risk pattern, the method further comprises: sending the hierarchical early warning and decision information to a remote monitoring platform and a user terminal, and triggering an audible and visual alarm device; based on the risk pattern and the early warning level, automatically adjusting the collection frequency of monitoring data or starting targeted review monitoring; storing the fusion data set, safety evaluation result, early warning information, and decision information of this monitoring into a historical database, and generating a monitoring report for model optimization and threshold updating.

[0083] In a specific implementation, first, information pushing is completed by calling a series of pre-defined API interfaces. The system sends the formatted hierarchical early warning and decision information (usually in JSON or XML format data packets) to the database and message queue of the remote monitoring platform through HTTP / MQTT communication protocols, and to the specified user terminal through the SMS gateway, email server, or push service (such as HuaWei Push, Firebase Cloud Messaging). At the same time, for high-level early warning (such as "dangerous"), the system sends a trigger signal (such as a high-level signal) to the audible and visual alarm device in the field or monitoring center through the network relay or industrial control protocol (such as Modbus TCP), starting the alarm.

[0084] Secondly, the system has the intelligent ability to dynamically adjust the monitoring strategy. It will query a "warning level-monitoring strategy" configuration table according to the current risk pattern and warning level. For example, when the warning level is "attention", the system may adjust the data acquisition frequency from the regular 1 time / hour to 1 time / 30 minutes through the configuration instruction, and the adjustment logic can be abstracted as (wherein is the adjustment coefficient determined according to the warning level). If a specific risk pattern (such as "overall tilt too fast") is identified, the system will automatically generate and issue instructions to start the preset targeted review monitoring scheme, such as controlling the unmanned aerial vehicle to perform a round of panoramic scanning on the tower.

[0085] Finally, to form a closed loop and support system self-optimization, all data and results of the current evaluation period are packaged and stored in the historical database. The system will use a template engine (such as Jinja2, Apache FreeMarker) to automatically fill in the fusion data set, evaluation results, and other key information into the Word or PDF monitoring report template. This report is not only for archiving, but more importantly, the cases it accumulates will provide valuable data basis for subsequent iterative improvement of the evaluation model through machine learning algorithms (such as through historical data regression analysis to optimize thresholds) or expert systems.

[0086] The embodiment provides a wind turbine tower sinking and tilting dynamic monitoring method, which synchronously collects the tilting data and positioning data of each monitoring point, and performs time and space alignment to obtain a fusion data set; the dynamic elastic response and the foundation steady-state deformation of the tower are decoupled from the fusion data through frequency domain analysis, and then the overall tilting rate, the sinking amount and the uneven sinking rate of the tower are calculated; the safety is evaluated based on the calculated parameters and the preset safety threshold, and the foundation safety state and the risk pattern are determined; finally, the grading warning information and the decision information containing the risk positioning and the trend prediction are generated according to the evaluation result. Through the above manner, the method realizes accurate separation and monitoring of the deformation dynamic characteristics of the tower, improves the accuracy of safety evaluation and the timeliness of early warning, and provides effective data support for the operation and maintenance decision of the wind turbine.

[0087] It should be noted that the above examples are only used for understanding the present application and do not constitute a limitation on the wind turbine tower sinking and tilting dynamic monitoring method of the present application, and more forms of simple transformation based on the technical concept are within the protection scope of the present application.

[0088] The present application also provides a wind turbine tower sinking and tilting dynamic monitoring system, please refer to Figure 3 The wind turbine tower sinking and tilting dynamic monitoring system comprises: The data acquisition and fusion module 10 is configured to synchronously acquire the inclination data and the positioning data of each monitoring point, perform space-time alignment on the inclination data and the positioning data, and obtain a fusion data set; The deformation decoupling and calculation module 20 is configured to decouple the dynamic elastic response of the tower and the foundation steady-state deformation from the fusion data set, and calculate the overall inclination rate, the settlement amount and the uneven settlement rate of the tower according to the dynamic elastic response and the foundation steady-state deformation; The safety evaluation module 30 is configured to perform safety evaluation based on the overall inclination rate, the settlement amount, the uneven settlement rate and corresponding safety thresholds respectively, and obtain a foundation safety state and a risk mode; The early warning and decision module 40 is configured to generate hierarchical early warning information and decision information containing risk positioning and trend prediction according to the foundation safety state and the risk mode.

[0089] In an embodiment, the data acquisition and fusion module 10 is further configured to perform frequency domain analysis on the time-series inclination data in the fusion data set, decompose the time-series inclination data into high-frequency components and low-frequency components through a preset cutoff frequency, wherein the high-frequency components correspond to the dynamic elastic response of the tower caused by wind load and wind turbine operation, and the low-frequency components correspond to the foundation steady-state deformation caused by foundation changes; The low-frequency components are subjected to trend fitting to obtain a foundation steady-state deformation curve, and the overall inclination rate of the tower is calculated according to the slope of the foundation steady-state deformation curve; The time-series positioning data of different monitoring points are extracted from the fusion data set, and the deformation values of the foundation steady-state deformation curve at corresponding time points are compensated and corrected based on the time-series positioning data to obtain pure settlement time-series data of each monitoring point; Based on the pure settlement time-series data, the average settlement amount of the tower center is calculated, and the uneven settlement rate is calculated according to the settlement difference of different azimuth monitoring points around the tower.

[0090] In an embodiment, the data acquisition and fusion module 10 is further configured to perform fast Fourier transform on the time-series inclination data in the fusion data set to obtain frequency spectrum data; The cutoff frequency is determined according to the first-order natural frequency of the tower; Signal components with frequencies higher than the cutoff frequency in the frequency spectrum data are filtered out as high-frequency components, and signal components with frequencies lower than the cutoff frequency in the frequency spectrum data are taken as low-frequency components.

[0091] In an embodiment, the data acquisition and fusion module 10 is further configured to perform smoothing processing on the low-frequency components based on a time window sliding average method to obtain smoothed low-frequency components; linearly fitting the smoothed low-frequency component based on a least square method to obtain a basic steady-state deformation curve; determining a slope of the basic steady-state deformation curve, and taking the slope as an overall inclination rate of the tower drum.

[0092] In a feasible implementation, the data acquisition and fusion module 10 is further configured to calculate, according to the geometric model of the tower drum and the basic steady-state deformation curve, a deformation value at a corresponding moment at a target timestamp, the deformation value being a horizontal displacement amount of the tower drum at each monitoring point; compensating and correcting the horizontal displacement amount according to the time-series positioning data to obtain corrected positioning data; extracting an elevation component in the corrected positioning data to obtain pure settlement time-series data of each monitoring point.

[0093] In a feasible implementation, the safety evaluation module 30 is further configured to preset a multi-level safety threshold system corresponding to the overall inclination rate, the settlement amount and the uneven settlement rate, the multi-level safety threshold system including setting a safety threshold, a warning threshold and a danger threshold for each index respectively; comparing the overall inclination rate, the settlement amount and the uneven settlement rate with the corresponding multi-level safety thresholds respectively to determine a safety level of each index; judging the safety levels of each index by weighting or logical combination based on a preset comprehensive evaluation rule to obtain a basic safety state; when the basic safety state is a target safety state, determining an out-of-limit index, and identifying a dominant risk mode according to a type, a severity and a combination relationship of the out-of-limit index.

[0094] In a feasible implementation, the safety evaluation module 30 is further configured to determine that the basic safety state is dangerous when a safety level of any one of the overall inclination rate, the settlement amount and the uneven settlement rate reaches a danger threshold. when the safety levels of all indexes do not reach the danger threshold and a safety level of any one of the indexes reaches a warning threshold, determine that the basic safety state is a warning; when the safety levels of all indexes do not reach the warning threshold and a safety level of any one of the indexes reaches a warning threshold, determine that the basic safety state is a warning; when the safety levels of all indexes do not reach the warning threshold and a safety level of any one of the indexes reaches a warning threshold, determine that the basic safety state is a warning.

[0095] In an implementable embodiment, the early warning and decision module 40 is further configured to map the basic safety state and the risk pattern to a hierarchical early warning relationship to obtain a target early warning level; generate hierarchical early warning information based on the target early warning level; perform trend prediction based on the risk positioning, the basic safety state and the risk pattern to obtain trend prediction information; obtain decision information based on the risk positioning and the trend prediction information.

[0096] In an implementable embodiment, the early warning and decision module 40 is further configured to send the hierarchical early warning and decision information to a remote monitoring platform and a user terminal, and trigger an audible and light alarm device; based on the risk pattern and the early warning level, automatically adjust the collection frequency of monitoring data or start targeted review monitoring; store the fusion data set, the safety evaluation result, the early warning information and the decision information of this monitoring into a historical database, and generate a monitoring report for model optimization and threshold updating.

[0097] The wind turbine tower sinking and tilting dynamic monitoring system provided by the application adopts the wind turbine tower sinking and tilting dynamic monitoring method in the above embodiment, and can solve the technical problem that the dynamic response of the tower and the deformation of the foundation cannot be accurately separated. Compared with the prior art, the wind turbine tower sinking and tilting dynamic monitoring system provided by the application has the same beneficial effects as the wind turbine tower sinking and tilting dynamic monitoring method provided by the above embodiment, and the other technical features of the wind turbine tower sinking and tilting dynamic monitoring system are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0098] The application provides a wind turbine tower sinking and tilting dynamic monitoring device, which comprises at least one processor and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the wind turbine tower sinking and tilting dynamic monitoring method in the above embodiment one.

[0099] Reference will be made to the drawings below Figure 4This document illustrates a structural schematic diagram of a dynamic monitoring device for the settlement and tilt of a wind turbine tower suitable for implementing embodiments of this application. The dynamic monitoring device for the settlement and tilt of a wind turbine tower in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The wind turbine tower settlement and tilt dynamic monitoring device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0100] like Figure 4 As shown, the wind turbine tower settlement and tilt dynamic monitoring device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in ROM (Read Only Memory) 1002 or the program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the wind turbine tower settlement and tilt dynamic monitoring device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, LCDs (Liquid Crystal Displays), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the wind turbine tower settlement and tilt dynamic monitoring equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows wind turbine tower settlement and tilt dynamic monitoring equipment with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0101] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for executing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network through a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiments disclosed in the present application are executed.

[0102] The wind turbine tower settlement and inclination dynamic monitoring device provided by the present application adopts the wind turbine tower settlement and inclination dynamic monitoring method in the above-mentioned embodiments, and can solve the technical problem of wind turbine tower settlement and inclination dynamic monitoring. Compared with the prior art, the wind turbine tower settlement and inclination dynamic monitoring device provided by the present application has the same beneficial effects as the wind turbine tower settlement and inclination dynamic monitoring method provided by the above-mentioned embodiments, and other technical features in the wind turbine tower settlement and inclination dynamic monitoring device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0103] It should be understood that various parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0104] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0105] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e. computer program) for executing the wind turbine tower settlement and inclination dynamic monitoring method in the above-mentioned embodiments.

[0106] The computer readable storage medium provided in the application may be, for example, a U disk, but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of the computer readable storage medium may include, but are not limited to, an electrical connection with one or more conductive wires, a portable computer disk, a hard disk, a RAM (Random Access Memory), a ROM (Read Only Memory), an EPROM (Erasable Programmable Read Only Memory or flash memory), an optical fiber, a CD-ROM (CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the embodiment, the computer readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system, or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to an electrical wire, an optical cable, an RF (Radio Frequency), and the like, or any suitable combination thereof.

[0107] The computer readable storage medium described above may be contained in the wind turbine generator set tower cylinder settlement and inclination dynamic monitoring device, or may exist separately without being assembled into the wind turbine generator set tower cylinder settlement and inclination dynamic monitoring device.

[0108] The computer readable storage medium described above carries one or more programs, when the one or more programs are executed by the wind turbine generator set tower cylinder settlement and inclination dynamic monitoring device, the wind turbine generator set tower cylinder settlement and inclination dynamic monitoring device synchronously collects inclination data and positioning data of each monitoring point, and performs space-time alignment on the inclination data and the positioning data to obtain a fusion data set. The dynamic elastic response of the tower cylinder and the steady-state deformation of the foundation are decoupled from the fusion data set, and the overall inclination rate, the settlement amount, and the uneven settlement rate of the tower cylinder are calculated according to the dynamic elastic response and the steady-state deformation of the foundation. The safety evaluation is respectively performed based on the overall inclination rate, the settlement amount, the uneven settlement rate, and the corresponding safety threshold to obtain a foundation safety state and a risk mode. The hierarchical early warning information and the decision information containing risk positioning and trend prediction are generated according to the foundation safety state and the risk mode.

[0109] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0110] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0111] The modules involved in the embodiments of the present application can be implemented in software or hardware. In some cases, the names of the modules do not limit the modules themselves.

[0112] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e., computer programs) for executing the wind turbine tower settlement and inclination dynamic monitoring method described above, and can solve the technical problem that the dynamic response of the tower and the deformation of the foundation cannot be accurately separated in the prior art. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the wind turbine tower settlement and inclination dynamic monitoring method provided by the above-mentioned embodiments, and will not be described here.

[0113] The application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the wind turbine tower settlement and inclination dynamic monitoring method as described above.

[0114] The computer program product provided by the application can solve the technical problem of wind turbine tower settlement and inclination dynamic monitoring. Compared with the prior art, the beneficial effects of the computer program product provided by the application are the same as those of the wind turbine tower settlement and inclination dynamic monitoring method provided by the above-mentioned embodiments, and will not be repeated here.

[0115] The above is only some embodiments of the application, and does not limit the patent scope of the application. Any equivalent structural transformation made by using the content of the application specification and drawings, or direct / indirect application in other related technical fields is included in the patent protection scope of the application.

Claims

1. A method for dynamic monitoring of settlement and tilt of wind turbine towers, characterized in that, Methods for dynamic monitoring of settlement and tilt of wind turbine towers include: Simultaneously collect tilt data and positioning data from each monitoring point, and perform spatiotemporal alignment on the tilt data and positioning data to obtain a fused dataset; The dynamic elastic response of the tower and the steady-state deformation of the foundation are decoupled from the fused dataset, and the overall tilt rate, settlement and uneven settlement rate of the tower are calculated based on the dynamic elastic response and the steady-state deformation of the foundation. Safety assessments are conducted based on the overall tilt rate, the settlement amount, the non-uniform settlement rate, and the corresponding safety thresholds to obtain the basic safety status and risk mode. Based on the basic security status and the risk model, tiered early warning information and decision information including risk identification and trend prediction are generated.

2. The method as described in claim 1, characterized in that, The step of decoupling the dynamic elastic response of the tower from the fused dataset and the steady-state deformation of the foundation, and calculating the overall tilt rate, settlement, and uneven settlement rate of the tower based on the dynamic elastic response and the steady-state deformation of the foundation, includes: Frequency domain analysis is performed on the time-series tilt data in the fused dataset. The time-series tilt data is decomposed into high-frequency components and low-frequency components by a preset cutoff frequency. The high-frequency components correspond to the dynamic elastic response of the tower caused by wind load and wind turbine operation, and the low-frequency components correspond to the foundation steady-state deformation caused by ground changes. The low-frequency components are trend-fitted to obtain the basic steady-state deformation curve, and the overall tilt rate of the tower is calculated based on the slope of the basic steady-state deformation curve. Temporal location data of different monitoring points are extracted from the fused dataset. Based on the temporal location data, the deformation value of the basic steady-state deformation curve at the corresponding time is compensated and corrected to obtain the pure settlement time series data of each monitoring point. Based on the pure settlement time series data, the average settlement at the center of the tower is calculated, and the uneven settlement rate is calculated based on the settlement differences of monitoring points at different locations around the tower.

3. The method as described in claim 2, characterized in that, The step of performing frequency domain analysis on the time-series tilt data in the fused dataset, and decomposing the time-series tilt data into high-frequency and low-frequency components using a preset cutoff frequency, includes: Perform a Fast Fourier Transform on the time-series skew data in the fused dataset to obtain spectral data; The cutoff frequency is determined based on the first natural frequency of the tower. Signal components with frequencies higher than the cutoff frequency in the spectrum data are filtered out as high-frequency components, and signal components with frequencies lower than the cutoff frequency in the spectrum data are selected as low-frequency components.

4. The method as described in claim 2, characterized in that, The step of performing trend fitting on the low-frequency components to obtain the basic steady-state deformation curve, and calculating the overall tilt rate of the tower based on the slope of the basic steady-state deformation curve includes: The low-frequency components are smoothed using a time-window-based moving average method to obtain smoothed low-frequency components. The basic steady-state deformation curve is obtained by performing linear regression fitting on the smoothed low-frequency components based on the least squares method. The slope of the foundation steady-state deformation curve is determined, and the slope is used as the overall tilt rate of the tower.

5. The method as described in claim 2, characterized in that, The step of compensating and correcting the deformation value of the foundation steady-state deformation curve at the corresponding time based on the time-series positioning data to obtain the pure settlement time-series data of each monitoring point includes: Based on the geometric model of the tower and the steady-state deformation curve of the foundation, the deformation value at the target timestamp is calculated, and the deformation value is the horizontal displacement of the tower at each monitoring point. The horizontal displacement is compensated and corrected based on the time-series positioning data to obtain corrected positioning data. The elevation component is extracted from the corrected positioning data to obtain the pure settlement time series data of each monitoring point.

6. The method as described in claim 1, characterized in that, The steps of conducting safety assessments based on the overall tilt rate, the settlement amount, the non-uniform settlement rate, and the corresponding safety thresholds to obtain the basic safety status and risk mode include: A multi-level safety threshold system is preset to correspond to the overall tilt rate, the settlement amount, and the non-uniform settlement rate. The multi-level safety threshold system includes setting a safety threshold, a warning threshold, and a danger threshold for each indicator. The overall tilt rate, the settlement amount, and the uneven settlement rate are compared with the corresponding multi-level safety thresholds to determine the safety level of each indicator. Based on the preset comprehensive evaluation rules, the security level of each indicator is weighted or logically combined to determine the basic security status. When the basic security state is the target security state, the out-of-standard indicators are determined, and the dominant risk pattern is identified based on the type, severity, and combination relationship of the out-of-standard indicators.

7. The method as described in claim 6, characterized in that, The step of determining the basic security status by weighting or logically combining the security levels of each indicator based on preset comprehensive evaluation rules includes: When the safety level of any one of the following indicators—the overall tilt rate, the settlement amount, and the uneven settlement rate—reaches the danger threshold, the basic safety status is determined to be dangerous. If the safety level of all indicators has not reached the danger threshold, but the safety level of any one indicator has reached the warning threshold, then the basic safety status will be judged as a warning. If the safety level of all indicators has not reached the warning threshold, and the safety level of any one indicator has reached the attention threshold, then the basic safety status is determined to be at attention. When the safety levels of the overall tilt rate, the settlement amount, and the uneven settlement rate are all within the safety threshold range, the basic safety status is determined to be safe.

8. The method as described in claim 1, characterized in that, The steps of generating graded early warning information and decision information including risk location and trend prediction based on the basic security status and the risk model include: The basic security status and the risk pattern are mapped to a hierarchical early warning relationship to obtain the target early warning level; Based on the target warning level, generate graded warning information; Based on the risk identification, the basic security status, and the risk pattern, trend prediction is performed to obtain trend prediction information; Decision information is obtained based on the risk assessment and trend prediction information.

9. The method as described in claim 1, characterized in that, After the step of generating graded early warning information and decision information including risk location and trend prediction based on the basic security status and the risk model, the method further includes: The tiered early warning and decision-making information is sent to the remote monitoring platform and user terminal, and the audible and visual alarm device is triggered. Based on the aforementioned risk patterns and warning levels, the frequency of monitoring data collection will be automatically adjusted or targeted review monitoring will be initiated. The fused dataset, security assessment results, early warning information, and decision-making information from this monitoring will be stored in the historical database, and a monitoring report will be generated for model optimization and threshold updates.

10. A dynamic monitoring system for settlement and tilt of wind turbine towers, characterized in that, The wind turbine tower settlement and tilt dynamic monitoring system includes: The data acquisition and fusion module is used to synchronously acquire tilt data and positioning data from each monitoring point, and perform spatiotemporal alignment on the tilt data and positioning data to obtain a fused dataset. The deformation decoupling and calculation module is used to decouple the dynamic elastic response of the tower from the fused dataset and the steady-state deformation of the foundation, and to calculate the overall tilt rate, settlement and uneven settlement rate of the tower based on the dynamic elastic response and the steady-state deformation of the foundation. The safety assessment module is used to perform safety assessments based on the overall tilt rate, the settlement amount, the non-uniform settlement rate, and the corresponding safety thresholds, respectively, to obtain the basic safety status and risk mode. The early warning and decision-making module is used to generate graded early warning information and decision-making information including risk location and trend prediction based on the basic security status and the risk model.

Images