Wind power tower safety monitoring method and system

Abstract

The invention discloses a wind power tower safety monitoring method and system, and belongs to the technical field of wind power tower monitoring, and the method comprises the steps: S1, obtaining the roll data of a corresponding fan of a wind power tower, and carrying out the fusion processing, and obtaining a roll angle; s2, the foundation settlement amount is calculated according to the roll angle and the foundation ring diameter of the wind power tower, and the historical foundation settlement amount of the wind power tower is obtained; s3, performing slope analysis based on the foundation settlement amount and the historical foundation settlement amount to obtain a settlement trend, and evaluating the settlement crisis of the wind power tower based on the settlement trend to obtain a crisis report; s4, the corresponding wind power tower safety monitoring system responds to the crisis report to execute an alarm action; the problem that the wind power tower roll monitoring accuracy is low due to the fact that influences of external factors such as weather are not considered in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power tower monitoring, and in particular to a wind power tower safety monitoring method and system. Background Art

[0002] With the development of the power network, more and more wind farms have been built as the main renewable energy power generation source. The tower carrying the wind turbine is erected in the wind farm as the main load-bearing device. The tower is formed by connecting multiple cylindrical metal towers through bolts and other connecting devices. This causes the tower to bear complex stresses during daily work. When the bolts are damaged or corroded, the complex stresses change, causing the tower to sink, and then safety accidents occur. On the other hand, the natural environmental factors at the construction location of the wind farm may also cause the tower to sink, so it is necessary to monitor the settlement of the tower in order to detect abnormal settlement in time.

[0003] Chinese patent, publication number: CN118793573B, publication date: December 27, 2024, discloses a tower tilt monitoring method and device based on a camera Internet network, including: measuring and recording the actual height of the target tower; placing a camera at the center of the adjacent tower top according to the actual height and the surrounding environment; using the current data of the target tower as initialization data, and shooting the target tower in real time; processing the real-time image and the projection line laser image respectively; calculating the tilt angle and settlement data according to the edge line of the target tower and the laser center straight line; comparing and calculating the tilt angle of the target tower with the tilt angle of the reference wind turbine, if the difference between the two exceeds the preset safety threshold, an alarm reminder is issued; comparing the settlement data of the target tower with the initialization data, if a height settlement occurs, an alarm reminder is issued; and the invention is easily affected by external factors such as weather, resulting in monitoring failure. Summary of the invention

[0004] The purpose of the present invention is to address the problem that the prior art does not take into account the influence of external factors such as weather, resulting in low accuracy in monitoring the roll of wind turbines; a method and system for monitoring the safety of wind turbines are proposed, which fuse the collected roll data to obtain the roll angle of the wind turbine, calculate the foundation settlement according to the roll angle and the foundation ring diameter of the wind turbine, and evaluate the settlement crisis of the wind turbine based on the foundation settlement and historical foundation settlement to obtain a crisis report; finally, the corresponding wind turbine safety monitoring system executes an alarm action in response to the crisis report, thereby significantly improving the accuracy of monitoring the roll of wind turbines.

[0005] In a first aspect, a technical solution provided in an embodiment of the present invention is a wind power tower safety monitoring method, comprising the following steps: S1, obtaining the roll data of the wind turbine corresponding to the wind turbine tower and performing fusion processing to obtain the roll angle; S2. Calculate the foundation settlement according to the tilt angle and the foundation ring diameter of the wind tower, and obtain the historical foundation settlement of the wind tower; S3. Perform slope analysis based on foundation settlement and historical foundation settlement to obtain settlement trend, and evaluate wind tower settlement risk based on settlement trend to obtain crisis report; S4. The corresponding wind power tower safety monitoring system executes an alarm action in response to the crisis report.

[0006] In this solution, the roll data of the wind turbine corresponding to the wind tower is obtained and fused to obtain the roll angle, which can integrate the measurement data of multiple acquisition devices into one data, effectively avoiding measurement errors caused by factors such as equipment aging, improper calibration, and tower shaking caused by strong winds; secondly, when the wind tower tilts, based on the material mechanics theory, it is known that the corresponding foundation ring undergoes a certain proportion of positive proportional deformation, and the foundation settlement is calculated based on the roll angle and the foundation ring diameter of the wind tower, so that the foundation settlement of the wind tower can be accurately obtained; based on the foundation settlement and the historical foundation settlement, the slope analysis is performed to obtain the settlement trend, and the difference between the real-time settlement of the wind tower and the historical settlement is clarified. Through the historical foundation settlement, the complex stress borne by the tower of the wind tower and the natural environment in which the wind tower is located are all included in the difference analysis conditions. Then, based on the settlement trend, the settlement crisis of the wind tower is evaluated to obtain a crisis report, and the corresponding wind tower safety monitoring system executes an alarm action in response to the crisis report, which significantly improves the accuracy of wind tower roll monitoring.

[0007] Preferably, in S1, the specific process of fusing the roll data to obtain the roll angle is: S11, synchronizing the roll data based on the sampling timestamps of the corresponding acquisition devices to obtain a synchronized data set, and removing abnormal data in the synchronized data set based on a preset angle interval to obtain a denoised data set; S12, inputting the denoised data set into the Kalman filter algorithm for fusion to obtain angle data, and adjusting the angle data based on the residual characteristics of the corresponding acquisition device to obtain the roll angle.

[0008] In this solution, the time series of the roll data are aligned based on the sampling timestamp of the acquisition device. If the roll data are all synchronous data, they are directly aligned. If the roll data contain asynchronous data, the earliest time point is used as the initial time point of all the data, and then the linear interpolation method is used to fill the missing data time points, thereby obtaining a synchronous data set with accurate and complete data and aligned time series; secondly, the angle corresponding to the roll data has been changing within a reasonable range during the operation of the wind tower. The range is set to an angle interval, and the data in the synchronous data set whose corresponding angle exceeds the angle interval is marked as abnormal data. At the same time, the abnormal data is deleted to obtain a denoised data set, which effectively improves the accuracy of the data; when the corresponding angle in the synchronous data set exceeds the angle interval for a long time, it can be directly determined that the corresponding acquisition device is faulty.

[0009] Preferably, in S12, the specific process of inputting the denoised data set into the Kalman filter algorithm for fusion to obtain the angle data is: Obtain historical angle data and historical roll data of the wind turbine tower, and extract roll angle change characteristics based on the historical angle data; Extract the correlation features between the measured angle and the real angle based on the historical roll data and historical angle data; The state equation is constructed based on the rolling angle variation characteristics, and the observation equation is constructed based on the associated characteristics; The tilt angle of the wind turbine tower is predicted based on the state equation and the denoised data set, and the measured angle is predicted based on the observation equation and the denoised data set; the predicted measured angle is used to correct the predicted wind turbine tower tilt angle to obtain angle data.

[0010] In this scheme, a state equation is constructed based on the roll angle change characteristics of historical angle data to describe the change law of the roll angle over time. What is actually obtained is the dynamic characteristics of the wind tower, so as to realize the prediction of the roll angle of the wind tower; an observation equation is constructed based on the historical roll data and the correlation characteristics between the measured angle and the real angle contained in the historical angle data to describe the relationship between the measured value of the corresponding acquisition device and the real roll angle of the wind tower. What is actually obtained is the measurement characteristics of the acquisition device, so as to realize the prediction of the measurement value of the acquisition device; then, a plurality of predicted measurement angles of the corresponding acquisition device are weighted according to preset weights and fused into a virtual observation value, and the Kalman gain is calculated according to the covariance of the predicted wind tower roll angle and the noise variance corresponding to the virtual observation value, and then the predicted wind tower roll angle is corrected based on the Kalman gain and the virtual observation value to obtain the angle data; the initial weight of the predicted measurement angle is set based on the accuracy of the corresponding acquisition device.

[0011] Preferably, in S12, the specific process of adjusting the angle data based on the residual characteristics of the corresponding acquisition device to obtain the roll angle is: Calculate the residual of the acquisition device according to the angle data and the measurement value of the corresponding acquisition device, and compare the residual with a preset residual range. If the residual is within the residual range, the acquisition device is determined to be normal; if the residual is outside the residual range, the acquisition device is determined to be abnormal; When the acquisition device is abnormal, the noise of the acquisition device is updated based on the noise formula, and the weight of the acquisition device is calculated based on the noise; the weight parameter of the Kalman filter algorithm is adjusted based on the weight, and the angle data is adjusted using the adjusted Kalman filter algorithm to obtain the roll angle.

[0012] In this solution, the measurement value of the corresponding acquisition device is actually the data in the denoised data set. The residual of the acquisition device is calculated based on the angle data and the denoised data set, and the residual is compared with the residual range to determine whether the acquisition device is normal. When the acquisition device is determined to be abnormal, it is necessary to re-estimate the noise of the acquisition device because the noise of the acquisition device may change over time due to temperature drift, and the re-estimated noise needs to meet the condition that the acquisition device is not determined to be faulty, that is, the acquisition device determined to be abnormal is removed from the fusion calculation of the current angle data, and the noise is re-estimated based on the remaining acquisition devices. In combination with the fact that the weight of the acquisition device in the Kalman filter algorithm is inversely proportional to the noise variance, the weight can be directly calculated based on the re-estimated noise, and finally the weight parameter of the Kalman filter algorithm is adjusted based on the weight, and the angle data is re-calculated using the adjusted Kalman filter algorithm to obtain the roll angle; the residual range needs to be set according to the noise type of the corresponding acquisition device; the residual represents the difference between the measurement value of the acquisition device and the angle data obtained by fusion, and is used to detect abnormal noise or fault conditions of the acquisition device.

[0013] Preferably, in S2, the calculation formula of foundation settlement is specifically: L = 0.7 × D × tg (α); Where L is the foundation settlement, D is the foundation ring diameter of the wind tower, α is the tilt angle, and tg(·) represents the tangent function in the trigonometric function.

[0014] Preferably, in S3, the specific process of performing slope analysis based on foundation settlement and historical foundation settlement to obtain the settlement trend is: S311, drawing a settlement curve based on the foundation settlement, and drawing a historical settlement curve based on the historical foundation settlement; S312, extracting the change trend of the settlement curve to obtain the settlement slope, and extracting the change trend of the historical settlement curve to obtain the historical settlement slope; S313. Based on the time line of the settlement curve diagram and the time line of the historical settlement curve diagram, the settlement slope is subtracted from the historical settlement slope to obtain the settlement trend.

[0015] In this scheme, the foundation settlement is divided into a set of data points with a time correlation based on the time series of the foundation settlement, and the time series is used as the horizontal axis and the values ​​of the data points are used as the vertical axis to draw a settlement curve corresponding to the foundation settlement, and similarly, a historical settlement curve is obtained; at this time, in order to obtain the difference between the current settlement of the wind tower and the historical settlement, the corresponding slope is extracted based on the changing trend of the curve graph, that is, the settlement slope and the historical settlement slope, and the settlement slope and the historical settlement slope at the same time point are subtracted to obtain the settlement trend corresponding to the difference.

[0016] Preferably, in S312, both the sedimentation slope and the historical sedimentation slope are extracted by integration.

[0017] In this solution, the settlement slope and the historical settlement slope are actually the areas of the corresponding derivative functions, which can be solved using the definite integral formula.

[0018] Preferably, in S3, the specific process of evaluating the wind tower settlement crisis based on the settlement trend to obtain a crisis report is as follows: S321, compare the settlement trend with the preset settlement range. If the settlement trend is within the settlement range, determine that the corresponding wind turbine is normal. If the settlement trend is outside the settlement range, determine that the corresponding wind turbine is in a settlement crisis, and execute S322; S322, extract the operation and maintenance information in the corresponding operation and maintenance information library based on the wind turbine, and establish a crisis report based on the location coordinates, settlement trend, settlement curve diagram and operation and maintenance information of the wind turbine; The operation and maintenance information at least includes a list of operation and maintenance personnel and operation and maintenance telephone numbers.

[0019] In this solution, since wind towers may be installed in areas with poor natural environments, such as soft geology, there are two situations when wind towers are working normally: no settlement and stable settlement. The common feature of the two situations is that the real-time settlement of the wind tower maintains relative changes with the historical settlement, that is, the settlement curve and the historical settlement curve are maintained within a certain range, and the range is specified by relevant design specifications. The settlement trend can be compared with the preset settlement range to determine whether the wind tower is in a settlement crisis. When the wind tower is in a settlement crisis, the operation and maintenance information corresponding to the wind tower is extracted from the real-time management operation and maintenance information library, and the wind tower location coordinates, settlement trend, settlement curve diagram, operation and maintenance information, etc. are organized into an overall report file.

[0020] Preferably, in said S4, the specific process of the corresponding wind power tower safety monitoring system executing the alarm action in response to the crisis report is: Extracting the operation and maintenance telephone number in the crisis report, and converting the crisis report into a text message and sending it to the operation and maintenance telephone number; A fault alarm light is determined based on the wind tower position coordinates in the crisis report, and the fault alarm light remains on.

[0021] In this solution, the crisis report is converted into a text message and sent to the corresponding operation and maintenance phone number, so that the corresponding operation and maintenance personnel can have a preliminary understanding of the settlement of the wind turbine tower, which helps the operation and maintenance personnel to make preparations in advance, and determine the fault alarm light based on the location of the wind turbine tower, so that the fault alarm light remains on, and the light of the fault alarm light can be used to warn surrounding personnel, and the operation and maintenance personnel can also find the location of the corresponding wind turbine tower in time.

[0022] On the other hand, a technical solution also provided in an embodiment of the present invention is a wind power tower safety monitoring system, comprising: a data acquisition module, a settlement calculation module, a crisis analysis module and an alarm module; The data acquisition module is used to collect the roll data of the wind turbine corresponding to the wind turbine tower, and upload the roll data to the settlement calculation module; the settlement calculation module calculates the foundation settlement based on the roll data transmitted by the data acquisition module, and transmits the foundation settlement to the crisis analysis module; The crisis analysis module evaluates the wind tower settlement crisis based on the basic settlement amount transmitted by the settlement calculation module to obtain a crisis report, and uploads the crisis report to the alarm module; The alarm module performs corresponding alarm actions based on the crisis report uploaded by the crisis analysis module.

[0023] Beneficial effects of the present invention: (1) The acquired roll data is fused to obtain the roll angle, and the measurement data of multiple acquisition devices can be integrated into one data, effectively avoiding measurement errors caused by factors such as equipment aging, improper calibration, and tower shaking caused by strong winds. In addition, the slope analysis is performed based on the foundation settlement and historical foundation settlement to obtain the settlement trend, clarify the difference between the real-time settlement of the wind turbine tower and the historical settlement. Through the historical foundation settlement, the complex stress borne by the tower of the wind turbine tower and the natural environment in which the wind turbine tower is located are all included in the difference analysis conditions. Based on the settlement trend, the wind turbine tower settlement crisis is evaluated to obtain a crisis report. The corresponding wind turbine tower safety monitoring system responds to the crisis report and executes an alarm action, which significantly improves the accuracy of wind turbine tower roll monitoring. (2) Since wind turbines may be installed in areas with poor natural environments, such as soft geology, there are two situations when wind turbines are working normally: no settlement and stable settlement. The common feature of the two situations is that the real-time settlement of the wind turbines keeps relative changes with the historical settlement, that is, the settlement curve and the historical settlement curve are maintained within a certain range, which is specified by relevant design specifications. The settlement trend can be compared with the preset settlement range to determine whether the wind turbine is in a settlement crisis. When a wind turbine is in a settlement crisis, the operation and maintenance information corresponding to the wind turbine is extracted from the real-time management operation and maintenance information database, and the wind turbine location coordinates, settlement trend, settlement curve diagram, operation and maintenance information, etc. are organized into an overall report file, which effectively avoids incorrect judgment of the operation status of the wind turbine due to natural environmental conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. Also, the same reference symbols are used throughout the drawings to represent the same parts.

[0025] Figure 1 A schematic diagram of a wind tower safety monitoring method; Figure 2 The figure is a structural diagram of a wind power tower safety monitoring system. DETAILED DESCRIPTION

[0026] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation method described herein is only an optimal embodiment of the present invention, which is only used to explain the present invention and does not limit the scope of protection of the present invention. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0027] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the operations (or steps) as sequential processes, many of the operations (or steps) therein can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the drawings; the process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0028] Embodiment 1: like Figure 1As shown, this embodiment provides a wind power tower safety monitoring method, comprising the following steps: S1, obtaining the roll data of the wind turbine corresponding to the wind turbine tower and performing fusion processing to obtain the roll angle; S11, synchronizing the roll data based on the sampling timestamps of the corresponding acquisition devices to obtain a synchronized data set, and removing abnormal data in the synchronized data set based on a preset angle interval to obtain a denoised data set; S12, inputting the denoised data set into the Kalman filter algorithm for fusion to obtain angle data, and adjusting the angle data based on the residual characteristics of the corresponding acquisition device to obtain the roll angle.

[0029] In this embodiment, each wind turbine installs a sensor bracket on the inner wall of the foundation ring of the foundation pedestal, and fixes the sensor on the bracket so that the sensor and the foundation ring become a whole. In addition, when fixing the sensor, the positive direction of the sensor's X-axis needs to point to the main wind direction of the wind farm. The sensor is specifically a high-precision dynamic inclinometer. When a foundation settlement event occurs in the wind tower, the sensor will tilt as the corresponding foundation ring of the wind tower sinks. At this time, the sensor can measure the specific tilt angle. In view of the large volume of the wind tower and the possibility of uneven settlement, at least two sensors are installed. This also divides the roll data measured by the sensor obtained when the wind tower settles into multiple groups. If only one group of data is selected, it is difficult to fully reflect the settlement of the wind tower. If all the data are selected, problems such as inconsistent measurement time of different sensors and abnormal data may occur. At this time, all the data are selected. The data of the part is used as the data for analyzing the settlement of the wind turbine tower, and the time series of the roll data is aligned based on the sampling timestamp of the acquisition device. If the roll data are all synchronous data, they are directly aligned. If the roll data contains asynchronous data, the earliest time point is used as the initial time point of all the data, and then the linear interpolation method is used to fill the time points of the missing data, so as to obtain a synchronous data set with accurate and complete data and aligned time series; secondly, the angle corresponding to the roll data has been changing within a reasonable range during the operation of the wind turbine tower. The range is set to an angle interval, and the data in the synchronous data set whose corresponding angle exceeds the angle interval is marked as abnormal data, and the abnormal data is deleted to obtain a denoised data set, which effectively improves the accuracy of the data; when the corresponding angle in the synchronous data set exceeds the angle interval for a long time, it can be directly determined that the corresponding acquisition equipment is faulty.

[0030] In one embodiment, the specific process of inputting the denoised data set into the Kalman filter algorithm for fusion to obtain the angle data is: Obtain historical angle data and historical roll data of the wind turbine tower, and extract roll angle change characteristics based on the historical angle data; Extract the correlation features between the measured angle and the real angle based on the historical roll data and historical angle data; The state equation is constructed based on the rolling angle variation characteristics, and the observation equation is constructed based on the associated characteristics; The tilt angle of the wind turbine tower is predicted based on the state equation and the denoised data set, and the measured angle is predicted based on the observation equation and the denoised data set; the predicted measured angle is used to correct the predicted wind turbine tower tilt angle to obtain angle data.

[0031] In this embodiment, a state equation is constructed based on the roll angle change characteristics of the historical angle data to describe the change law of the roll angle over time. In essence, the dynamic characteristics of the wind tower are obtained to achieve the prediction of the roll angle of the wind tower. The mathematical expression of the state equation is specifically: θ k =θ k-1 +w k ; In the formula, θ k is the wind tower tilt angle at the kth moment, which is also the value to be predicted, θ k-1 is the wind tower tilt angle at the k-1th moment, w k is the noise at the kth moment, and the noise conforms to the Gaussian distribution w k ~N(0,Q), Q is the covariance matrix of the noise; introducing noise into the state equation can reflect the severity of the change in the tilt angle of the wind tower.

[0032] Based on the correlation characteristics between the measured angle and the real angle contained in the historical roll data and the historical angle data, an observation equation is constructed to describe the relationship between the measured value of the corresponding acquisition device and the real roll angle of the wind turbine tower. In essence, the measurement characteristics of the acquisition device are obtained to achieve the prediction of the measurement value of the acquisition device. The mathematical expression of the observation equation is specifically: z i,k =θ k +v i,k , i=1,2,...,n; In the formula, z i,k is the measurement value of the i-th acquisition device at the k-th time, where the acquisition device is specifically a sensor, θ k is the wind tower tilt angle at the kth moment, v i,k is the measurement noise of the i-th acquisition device at the k-th time, and the measurement noise conforms to the Gaussian distribution v i,k ~N(0,R i ), R i is the measurement noise variance of the ith acquisition device, and n is the total number of acquisition devices.

[0033] Next, multiple predicted measurement angles of the corresponding acquisition devices are weighted and fused into a virtual observation value according to preset weights. The mathematical expression of the fusion calculation is specifically as follows: In the formula, z k is the virtual observation value, R v is the virtual observation noise variance, is the weight expression for the measurement value of the acquisition device.

[0034] The Kalman gain is calculated based on the covariance of the predicted wind tower tilt angle and the noise variance corresponding to the virtual observation value. The calculation formula of the Kalman gain is specifically as follows: In the formula, K k is the gain matrix, P k|k-1 The covariance of the wind tower tilt angle at time k is predicted by the state equation for the k-1 time data, satisfying P k|k-1 =P k-1|k-1 +Q,P k-1|k-1 is the covariance of the predicted wind tower tilt angle at time k-1, and Q is the prediction process noise variance, which changes with external factors. For example, Q is larger in strong winds.

[0035] The angle data is obtained by correcting the predicted wind tower roll angle based on the Kalman gain and the virtual observation value. The mathematical expression of the corrected predicted wind tower roll angle is specifically: θ k|k =θ k|k-1 +K k (z k -θ k|k-1 ); P k|k =(1-K k ) k|k-1 ; In the formula, θ k|k is the predicted wind tower tilt angle at time k, θ k|k-1 is the wind turbine tower tilt angle at time k predicted by the state equation based on the k-1 time data, P k|k is the covariance of the wind tower tilt angle predicted at time k; the initial weight of the predicted measurement angle is set based on the accuracy of the corresponding acquisition equipment.

[0036] In one embodiment, the specific process of adjusting the angle data based on the residual characteristics of the corresponding acquisition device to obtain the roll angle is: Calculate the residual of the acquisition device according to the angle data and the measurement value of the corresponding acquisition device, and compare the residual with a preset residual range. If the residual is within the residual range, the acquisition device is determined to be normal; if the residual is outside the residual range, the acquisition device is determined to be abnormal; When the acquisition device is abnormal, the noise of the acquisition device is updated based on the noise formula, and the credibility of the acquisition device is calculated based on the noise; the weight parameters of the Kalman filter algorithm are adjusted based on the credibility, and the angle data is adjusted using the adjusted Kalman filter algorithm to obtain the roll angle.

[0037] In this embodiment, the measurement value of the corresponding acquisition device is actually the data in the denoised data set. The residual of the acquisition device is calculated based on the angle data and the denoised data set. The calculation formula of the residual is specifically: r i,k =z i,k -θ f,k ; In the formula, r i,k is the residual of the i-th acquisition device at time k, z i,k is the measurement value of the i-th acquisition device at time k, θ f,k is the angle data at time k, that is, the output data of the Kalman filter algorithm; the residual is compared with the residual range to determine whether the acquisition device is normal. When the acquisition device is determined to be abnormal, the noise of the acquisition device may change with time due to temperature drift, etc., and the noise of the acquisition device needs to be re-estimated. The re-estimated noise needs to meet the condition that the acquisition device is not determined to be faulty, that is, the acquisition device determined to be abnormal is removed from the fusion calculation of the current angle data, and the noise is re-estimated based on the remaining acquisition devices. The noise estimation formula is specifically: In the formula, is the re-estimated noise variance, W is the adaptive adjustment window, its time series is set to 50 sampling points, k and t are the corresponding time of the sampling points, r i,t is the residual of the i-th acquisition device at time t; In combination with the Kalman filter algorithm, the weight of the acquisition device is inversely proportional to the noise variance, and the weight can be directly calculated according to the re-estimated noise. The calculation formula of the weight is specifically as follows: In the formula, w i,k is the weight, and ε is the minimum value to prevent division by zero error, which is set to 1×10 -6 ; Finally, the weight parameters of the Kalman filter algorithm are adjusted based on the weights, and the adjusted Kalman filter algorithm is used to calculate the angle data again to obtain the roll angle; the residual range needs to be set according to the noise type of the corresponding acquisition device; the residual represents the difference between the measurement value of the acquisition device and the fused angle data, and is used to detect abnormal noise or fault conditions of the acquisition device.

[0038] S2. Calculate the foundation settlement according to the tilt angle and the foundation ring diameter of the wind tower, and obtain the historical foundation settlement of the wind tower; The calculation formula of the foundation settlement is specifically: L = 0.7 × D × tg (α); Where L is the foundation settlement, D is the foundation ring diameter of the wind tower, α is the tilt angle, and tg(·) represents the tangent function in the trigonometric function.

[0039] S3. Perform slope analysis based on foundation settlement and historical foundation settlement to obtain settlement trend, and evaluate wind tower settlement risk based on settlement trend to obtain crisis report.

[0040] In one embodiment, the specific process of performing slope analysis based on foundation settlement and historical foundation settlement to obtain the settlement trend is as follows: S311, drawing a settlement curve based on the foundation settlement, and drawing a historical settlement curve based on the historical foundation settlement; S312, extracting the change trend of the settlement curve to obtain the settlement slope, and extracting the change trend of the historical settlement curve to obtain the historical settlement slope; The said settlement slope and historical settlement slope are extracted by integration; S313. Based on the time line of the settlement curve diagram and the time line of the historical settlement curve diagram, the settlement slope is subtracted from the historical settlement slope to obtain the settlement trend.

[0041] In this embodiment, the foundation settlement is divided into a set of data points with a time correlation based on the time series of the foundation settlement, and the time series is used as the horizontal axis and the values ​​of the data points are used as the vertical axis to draw a settlement curve corresponding to the foundation settlement, and similarly, a historical settlement curve is obtained; at this time, in order to obtain the difference between the current settlement of the wind tower and the historical settlement, the corresponding slope is extracted based on the changing trend of the curve graph, that is, the settlement slope and the historical settlement slope, and the settlement slope and the historical settlement slope at the same time point are subtracted to obtain the settlement trend corresponding to the difference. The settlement slope and the historical settlement slope are essentially the areas of the corresponding derivative functions, which can be solved using the definite integral formula.

[0042] In one embodiment, the specific process of evaluating the wind tower settlement risk based on the settlement trend to obtain a crisis report is as follows: S321, compare the settlement trend with the preset settlement range. If the settlement trend is within the settlement range, determine that the corresponding wind turbine is normal. If the settlement trend is outside the settlement range, determine that the corresponding wind turbine is in a settlement crisis, and execute S322; S322, extract the operation and maintenance information in the corresponding operation and maintenance information library based on the wind turbine, and establish a crisis report based on the location coordinates, settlement trend, settlement curve diagram and operation and maintenance information of the wind turbine; The operation and maintenance information at least includes a list of operation and maintenance personnel and operation and maintenance telephone numbers.

[0043] In this embodiment, since the wind tower may be installed in an area with a poor natural environment, such as soft geology, there are two situations when the wind tower is working normally: no settlement and stable settlement. The common feature of the two situations is that the real-time settlement of the wind tower and the historical settlement maintain relative changes, that is, the settlement curve and the historical settlement curve are maintained within a certain range, and the range is specified by the relevant design specifications. The settlement trend can be compared with the preset settlement range to determine whether the wind tower is in a settlement crisis. When the wind tower is in a settlement crisis, the operation and maintenance information corresponding to the wind tower is extracted from the real-time managed operation and maintenance information library, and the wind tower location coordinates, settlement trend, settlement curve diagram, operation and maintenance information, etc. are organized into an overall report file.

[0044] S4, the corresponding wind tower safety monitoring system performs an alarm action in response to the crisis report; Extracting the operation and maintenance telephone number in the crisis report, and converting the crisis report into a text message and sending it to the operation and maintenance telephone number; A fault alarm light is determined based on the wind tower position coordinates in the crisis report, and the fault alarm light remains on.

[0045] In this embodiment, the crisis report is converted into a text message and sent to the corresponding operation and maintenance telephone, so that the corresponding operation and maintenance personnel can have a preliminary understanding of the settlement of the wind tower, which is helpful for the operation and maintenance personnel to make preparations in advance, and determine the fault alarm light based on the location of the wind tower, so that the fault alarm light remains on, and the light of the fault alarm light can be used to warn surrounding personnel, and the operation and maintenance personnel can also find the location of the corresponding wind tower in time.

[0046] On the other hand, Figure 2 As shown, a technical solution also provided in the embodiment of the present invention is a wind power tower safety monitoring system, comprising: a data acquisition module, a settlement calculation module, a crisis analysis module and an alarm module; The data acquisition module is used to collect the roll data of the wind turbine corresponding to the wind turbine tower, and upload the roll data to the settlement calculation module; the settlement calculation module calculates the foundation settlement based on the roll data transmitted by the data acquisition module, and transmits the foundation settlement to the crisis analysis module; The crisis analysis module evaluates the wind tower settlement crisis based on the basic settlement amount transmitted by the settlement calculation module to obtain a crisis report, and uploads the crisis report to the alarm module; The alarm module performs corresponding alarm actions based on the crisis report uploaded by the crisis analysis module.

[0047] This embodiment has at least the following substantial effects: (1) The acquired roll data is fused to obtain the roll angle, and the measurement data of multiple acquisition devices can be integrated into one data, effectively avoiding measurement errors caused by factors such as equipment aging, improper calibration, and tower shaking caused by strong winds. In addition, the slope analysis is performed based on the foundation settlement and historical foundation settlement to obtain the settlement trend, clarify the difference between the real-time settlement of the wind turbine tower and the historical settlement. Through the historical foundation settlement, the complex stress borne by the tower of the wind turbine tower and the natural environment in which the wind turbine tower is located are all included in the difference analysis conditions. Based on the settlement trend, the wind turbine tower settlement crisis is evaluated to obtain a crisis report. The corresponding wind turbine tower safety monitoring system responds to the crisis report and executes an alarm action, which significantly improves the accuracy of wind turbine tower roll monitoring. (2) Since wind turbines may be installed in areas with poor natural environments, such as soft geology, there are two situations when wind turbines are working normally: no settlement and stable settlement. The common feature of the two situations is that the real-time settlement of the wind turbines keeps relative changes with the historical settlement, that is, the settlement curve and the historical settlement curve are maintained within a certain range, which is specified by relevant design specifications. The settlement trend can be compared with the preset settlement range to determine whether the wind turbine is in a settlement crisis. When a wind turbine is in a settlement crisis, the operation and maintenance information corresponding to the wind turbine is extracted from the real-time management operation and maintenance information database, and the wind turbine location coordinates, settlement trend, settlement curve diagram, operation and maintenance information, etc. are organized into an overall report file, which effectively avoids incorrect judgment of the operation status of the wind turbine due to natural environmental conditions.

[0048] The above specific embodiments are preferred embodiments of the present invention, and are not intended to limit the specific implementation scope of the present invention. The scope of the present invention includes but is not limited to the present specific embodiments. All equivalent changes made in accordance with the shape, structure, and method of the present invention are within the protection scope of the present invention.

Claims

1. A wind power tower safety monitoring method, characterized in that: The following steps are involved: S1, obtaining the roll data of the wind turbine corresponding to the wind turbine tower and performing fusion processing to obtain the roll angle; S2. Calculate the foundation settlement according to the tilt angle and the foundation ring diameter of the wind tower, and obtain the historical foundation settlement of the wind tower; S3. Perform slope analysis based on foundation settlement and historical foundation settlement to obtain settlement trend, and evaluate wind tower settlement risk based on settlement trend to obtain crisis report; S4. The corresponding wind power tower safety monitoring system executes an alarm action in response to the crisis report.

2. A wind power tower safety monitoring method according to claim 1, characterized in that: In S1, the specific process of fusing the roll data to obtain the roll angle is as follows: S11, synchronizing the roll data based on the sampling timestamps of the corresponding acquisition devices to obtain a synchronized data set, and removing abnormal data in the synchronized data set based on a preset angle interval to obtain a denoised data set; S12, inputting the denoised data set into the Kalman filter algorithm for fusion to obtain angle data, and adjusting the angle data based on the residual characteristics of the corresponding acquisition device to obtain the roll angle.

3. A wind power tower safety monitoring method according to claim 2, characterized in that: In S12, the specific process of inputting the denoised data set into the Kalman filter algorithm for fusion to obtain the angle data is: Obtain historical angle data and historical roll data of the wind turbine tower, and extract roll angle change characteristics based on the historical angle data; Extract the correlation features between the measured angle and the real angle based on the historical roll data and historical angle data; The state equation is constructed based on the rolling angle variation characteristics, and the observation equation is constructed based on the associated characteristics; The wind tower tilt angle is predicted based on the state equation and the denoised data set, and the measured angle is predicted based on the observation equation and the denoised data set; the predicted measured angle is used to correct the predicted wind tower tilt angle to obtain angle data.

4. A wind power tower safety monitoring method according to claim 2, characterized in that: In S12, the specific process of adjusting the angle data based on the residual characteristics of the corresponding acquisition device to obtain the roll angle is: Calculate the residual of the acquisition device according to the angle data and the measurement value of the corresponding acquisition device, and compare the residual with a preset residual range. If the residual is within the residual range, the acquisition device is determined to be normal; if the residual is outside the residual range, the acquisition device is determined to be abnormal; When the acquisition device is abnormal, the noise of the acquisition device is updated based on the noise formula, and the credibility of the acquisition device is calculated based on the noise; The weight parameters of the Kalman filter algorithm are adjusted based on the credibility, and the angle data is adjusted using the adjusted Kalman filter algorithm to obtain the roll angle.

5. A wind power tower safety monitoring method according to claim 1, characterized in that: In S2, the calculation formula of foundation settlement is specifically: L = 0.7 × D × tg (α); Where L is the foundation settlement, D is the foundation ring diameter of the wind tower, α is the tilt angle, and tg(·) represents the tangent function in the trigonometric function.

6. A wind power tower safety monitoring method according to claim 1, characterized in that: In S3, the specific process of obtaining the settlement trend by slope analysis based on the foundation settlement and historical foundation settlement is as follows: S311, drawing a settlement curve based on the foundation settlement, and drawing a historical settlement curve based on the historical foundation settlement; S312, extracting the change trend of the settlement curve to obtain the settlement slope, and extracting the change trend of the historical settlement curve to obtain the historical settlement slope; S313. Based on the time line of the settlement curve diagram and the time line of the historical settlement curve diagram, the settlement slope is subtracted from the historical settlement slope to obtain the settlement trend.

7. A wind power tower safety monitoring method according to claim 6, characterized in that: In S312, both the settlement slope and the historical settlement slope are extracted by integration.

8. A wind power tower safety monitoring method according to claim 6, characterized in that: In S3, the specific process of evaluating the wind tower settlement crisis based on the settlement trend to obtain a crisis report is as follows: S321, comparing the settlement trend with a preset settlement range, if the settlement trend is within the settlement range, determining that the corresponding wind turbine tower is normal, if the settlement trend is outside the settlement range, determining that the corresponding wind turbine tower is in a settlement crisis, and executing S322; S322, extracting operation and maintenance information from a corresponding operation and maintenance information database based on the wind turbine tower, and establishing a crisis report based on the location coordinates, settlement trend, settlement curve diagram and operation and maintenance information of the wind turbine tower; The operation and maintenance information at least includes a list of operation and maintenance personnel and operation and maintenance telephone numbers.

9. A wind power tower safety monitoring method according to claim 1, characterized in that: In S4, the specific process of the corresponding wind power tower safety monitoring system executing the alarm action in response to the crisis report is: Extracting the operation and maintenance telephone number in the crisis report, and converting the crisis report into a text message and sending it to the operation and maintenance telephone number; A fault alarm light is determined based on the wind tower position coordinates in the crisis report, and the fault alarm light remains on.

10. A wind power tower safety monitoring system, applicable to a wind power tower safety monitoring method as claimed in any one of claims 1 to 9, characterized in that: Includes: data acquisition module, settlement calculation module, crisis analysis module and alarm module; The data acquisition module is used to collect the roll data of the wind turbine corresponding to the wind turbine tower, and upload the roll data to the settlement calculation module; the settlement calculation module calculates the foundation settlement based on the roll data transmitted by the data acquisition module, and transmits the foundation settlement to the crisis analysis module; The crisis analysis module evaluates the wind tower settlement risk based on the basic settlement amount transmitted by the settlement calculation module to obtain a crisis report. And upload the crisis report to the alarm module; The alarm module performs corresponding alarm actions based on the crisis report uploaded by the crisis analysis module.

Images