Offshore wind power project risk assessment method and system

Abstract

The invention relates to the technical field of risk analysis, in particular to an offshore wind power project risk assessment method and system, and the method comprises the following steps: collecting a wind speed value according to the hub height of multiple units of an offshore wind power plant, obtaining the unit power, yaw angle change and vibration amplitude, and calculating the wind speed change rate; according to the method, through combination of blade vibration, yaw driving feedback and tower stress monitoring data and multi-source information cross analysis, the calculation precision of the unit load fluctuation rate is improved, the wind shear influence is quantified through the wind shear strength coefficient, and the risk prediction capability under the condition of dramatic change of the wind speed is improved; yaw error cumulative effect dynamic evaluation optimizes unit yaw precision management and control, reduces influence of long-term operation deviation on equipment stability, computes unit operation state unstable factors through multi-dimensional data fusion, comprehensively quantifies wind speed change, load fluctuation and yaw error influence, perfects a risk evaluation system, optimizes a wind turbine generator risk evaluation model, and improves wind turbine generator risk evaluation accuracy. And the safety management level of offshore wind power projects is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of risk analysis, and in particular to a risk assessment method and system for offshore wind power projects. Background Art

[0002] The field of risk analysis technology encompasses the identification, assessment, and management of various risk factors to mitigate potential losses and optimize decision-making. This technology primarily involves key processes such as data collection, modeling and analysis, risk quantification, and risk prediction. Its applications span a wide range of industries, including finance, insurance, production safety, and environmental protection. In the offshore wind power sector, risk analysis technology comprehensively evaluates data on the offshore environment, equipment operating status, and construction management to establish risk assessment models. Combining historical data with real-time monitoring information, it provides risk warning and management solutions to enhance project safety and controllability.

[0003] The offshore wind power project risk assessment method is a technical solution for identifying, analyzing, and evaluating various risk factors for offshore wind power projects. This method covers multiple aspects, including wind resource fluctuations, marine environmental changes, equipment operational reliability, construction safety, and maintenance management. It uses data acquisition technology to obtain environmental and equipment status information, employs probabilistic statistical analysis to quantify risk indicators, incorporates machine learning modeling to predict risk trends, and assesses risk levels through a multi-dimensional weighting method. Ultimately, based on the assessment results, it develops risk classifications and response strategy recommendations, providing data support for the full lifecycle safety management of offshore wind power projects.

[0004] Existing technologies rely on a single data source to assess unit load changes and lack collaborative analysis of multi-source information, resulting in deviations in the calculation of load fluctuation rates and difficulty in accurately reflecting the actual stress conditions of the equipment. Wind shear analysis lacks the extraction of key indicators, making it difficult to effectively quantify the impact of sudden changes in wind speed, which affects the assessment of unit operational stability. The risk assessment of the yaw system does not form a dynamic analysis of error accumulation, but relies solely on static yaw error calculations, making the long-term impact of deviations difficult to predict. Data processing methods are mainly based on historical statistical analysis and cannot adapt to the rapid changes in the wind farm environment, affecting the accuracy of real-time risk assessments. The interactive effects of multiple factors have not been fully modeled, and the coupling effects between wind speed, load, and yaw have not been deeply analyzed, reducing the overall risk prediction capability. The lack of systematic evaluation of complex environmental factors affects the long-term safety management and decision-making optimization of wind power projects. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the existing technology and propose a risk assessment method and system for offshore wind power projects.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: A risk assessment method for an offshore wind power project comprises the following steps: S1: Based on the hub height of multiple turbines in an offshore wind farm, wind speed values are collected, and turbine power, yaw angle change, and vibration amplitude are obtained. The wind speed change rate is calculated, and the wind speed fluctuation frequency and amplitude are extracted to establish the wind speed fluctuation amplitude value. S2: Based on the wind speed fluctuation amplitude value, calling the blade vibration monitoring data, yaw drive feedback data, and tower stress monitoring device data, calculating the vibration frequency difference of the blade vibration monitoring device, analyzing the tower force of the tower stress monitoring device, and combining the wind speed measurement point data at the hub height of the unit to obtain the unit load fluctuation rate; S3: Calculate the wind speed changes at multiple measuring points of the blade vibration monitoring device based on the load fluctuation rate of the unit, extract key wind shear indicators, and establish a wind shear intensity coefficient; S4: Calculating the response delay of the yaw drive based on the wind shear intensity coefficient, comparing the yaw record with the real-time yaw, determining the yaw error, and obtaining a yaw drive predicted deviation; S5: Call the yaw drive prediction deviation, combine the unit load fluctuation rate and wind shear intensity coefficient, calculate the operating state instability coefficient of the offshore wind turbine structure monitoring, analyze the cumulative impact of wind speed changes, load fluctuations and yaw errors, and obtain the unit operation risk coefficient.

[0007] As a further solution of the present invention, the wind speed fluctuation amplitude value is specifically the wind speed change rate, wind speed fluctuation frequency, and wind speed fluctuation amplitude; the unit load fluctuation rate includes the vibration frequency difference of the blade vibration monitoring device, the tower force of the tower stress monitoring device, and the wind speed measurement point data at the unit hub height; the wind shear intensity coefficient is specifically the wind speed change at multiple measuring points and the key wind shear indicators; the yaw drive prediction deviation includes the response delay of the yaw drive, the comparison result between the yaw record and the real-time yaw, and the yaw error; the unit operation risk coefficient specifically refers to the impact of wind speed changes, the impact of load fluctuations, and the cumulative impact of yaw errors.

[0008] As a further solution of the present invention, the step of obtaining the wind speed fluctuation amplitude value is specifically as follows: S101: Obtain hub-height wind speed values for multiple turbines in an offshore wind farm, normalize the wind speeds at multiple height measurement points using multi-sensor data fusion, calculate the mean and standard deviation of wind speeds at hub height for multiple turbines, screen and eliminate abnormal wind speed data, and obtain wind speed characteristic values; S102: Based on the wind speed characteristic values, power output data, yaw angle change data, and vibration amplitude data of multiple units are obtained, the wind speed change rate over time is calculated, the wind speed change trend is solved using a discrete differential method, and a wind speed change rate sequence is calculated; S103: Call the wind speed change rate sequence, use Fourier transform to perform spectrum analysis on the wind speed change rate, extract key fluctuation frequency components, and calculate the amplitude by combining the time domain data of the wind speed change rate, using the formula: ; Calculate and obtain the main frequency and amplitude of wind speed fluctuations, and establish the wind speed fluctuation amplitude value; in, Represents the wind speed fluctuation amplitude value, represents the i-th wind speed change rate data point, represents the mean of the wind speed change rate series, Represents the total number of wind speed data points, represents the absolute deviation of the wind speed change rate, Represents the sum of the variances of the wind speed change rate.

[0009] As a further solution of the present invention, the steps for obtaining the unit load fluctuation rate are specifically as follows: S201: Based on the wind speed fluctuation amplitude value, calling blade vibration monitoring data, yaw drive feedback data, and tower stress monitoring device data, calculating the vibration frequency difference of the blade vibration monitoring device, extracting the maximum and minimum differences of the vibration frequencies, screening the frequency differences that exceed the set threshold range, and obtaining the abnormal blade vibration frequency difference; S202: Based on the abnormal blade vibration frequency difference, call the tower stress monitoring device data to calculate the tower stress change rate using the formula: ; Obtain tower stress change value by calculation, compare the tower stress change value with the set tower safety stress range, and obtain the tower stress abnormality coefficient; in, Represents the tower stress change value, Represents the abnormal frequency value of blade vibration, Represents the reference vibration frequency value, Represents the number of data points in the monitoring period, Represents the force value of the tower at the current moment, Represents the tower force value at all times during the monitoring period, Represents the total number of data points in the monitoring period; S203: Based on the tower stress anomaly coefficient and combined with the wind speed measurement point data at the unit hub height, the influence ratio of the wind speed change on the tower stress is calculated to obtain the unit load fluctuation rate.

[0010] As a further solution of the present invention, the steps for obtaining the wind shear intensity coefficient are specifically as follows: S301: Based on the load fluctuation rate of the unit, calculating the wind speed change rates of multiple measuring points of the blade vibration monitoring device, calling the wind speed measurement values and time series data of the differentiated measuring points, calculating the wind speed change gradients of the multiple measuring points, and obtaining the wind speed change gradient values of the measuring points; S302: calling the wind speed change gradient value of the measuring point, calculating the wind shear degree of multiple measuring points, comparing the differences in wind speed change rates of the measuring points, screening the measuring points with significant wind speed changes, and obtaining key wind shear measuring points; S303: Calculate the wind shear intensity coefficient based on the data of the key wind shear measurement points using the formula: ; Obtain wind shear intensity at the measuring point through calculation and establish wind shear intensity coefficient; Where S represents the wind shear intensity coefficient, Represents the height of the i+1th wind shear key measurement point Wind speed data at the location, Represents the height of the i-th wind shear key measurement point Wind speed data at the location, Represents the total number of wind shear key measurement points used to calculate the wind shear intensity coefficient, Represents the height measured at the i-th wind shear key measurement point and height The denominator of the time difference calculation is the normalized square root of the sum of the squares of the time differences.

[0011] As a further solution of the present invention, the step of obtaining the yaw drive predicted deviation is specifically as follows: S401: Based on the wind shear intensity coefficient, historical yaw records and real-time yaw data are called to calculate the time deviation between the two, and then the response delay of the yaw drive is calculated using the formula: ; The yaw drive response delay is calculated; in, Represents the yaw drive response delay, Represents the real-time yaw angle, represents the historical yaw angle, represents the wind shear intensity coefficient, represents the wind speed influence coefficient, represents the wind speed at the jth time point, represents the number of time points used for wind speed weighted calculation, represents the weighted contribution of wind speed to the yaw response; S402: calling the yaw drive response delay, comparing historical yaw records with real-time yaw data, calculating an angle deviation between the two, and comparing the calculated deviation value with a yaw error threshold to determine whether it exceeds a set range; if it exceeds the set range, marking the yaw error as abnormal and obtaining the yaw error angle; S403: Based on the yaw error angle, calculate the correction amount of the yaw drive system, adjust the yaw drive control parameters according to the correction amount, recalculate the yaw angle adjustment value, evaluate the yaw correction amplitude in combination with the wind speed change trend, and obtain the yaw drive predicted deviation amount.

[0012] As a further solution of the present invention, the steps for obtaining the unit operation risk coefficient are specifically as follows: S501: calling the yaw drive predicted deviation, obtaining the unit load fluctuation rate and wind shear intensity coefficient based on the unit operation data, calculating the yaw error change trend in multiple time periods, selecting a wind speed change range, determining the error distribution characteristics of multiple wind speed intervals, extracting the error fluctuation value, classifying the error change according to the wind speed interval, analyzing the increase and decrease relationship between the error and the wind speed, screening the error intervals under differentiated wind speed conditions, and generating a wind speed-yaw error correlation value; S502: Based on the wind speed-yaw error correlation value and combined with the unit load fluctuation rate, the operating state instability under the influence of wind speed fluctuation is calculated using the formula: ; The operational instability coefficient under the combined effects of wind speed and load changes is calculated, and combined with the wind shear intensity coefficient, the stability difference within the wind speed range is calculated, the operational instability characteristics of multiple wind speed ranges are identified, and a wind speed-operation instability mapping value is generated; in, Represents the operating state instability coefficient, represents a single data point in the wind speed-yaw error correlation, Represents the unit load fluctuation rate, represents the wind shear intensity coefficient, Represents the offset amplitude of load fluctuation in multiple time periods, The time integral value representing the wind speed variation amplitude, represents the total number of observation time periods; S503: Based on the wind speed-operation instability mapping value, analyze the cumulative impact of the yaw error, calculate the operation risk of the computer group under differentiated wind speed and load fluctuation conditions, select a combination of wind speed and load fluctuations, evaluate the changing trend of the operating status, identify high-frequency fluctuation areas, screen key wind speed and load combinations with abnormal operating status, analyze the long-term cumulative impact in combination with long-term data, screen the risk interval, and obtain the unit operation risk coefficient.

[0013] The present invention also provides an offshore wind power project risk assessment system, which is used to implement the above-mentioned offshore wind power project risk assessment method. The offshore wind power project risk assessment system includes a wind speed fluctuation monitoring module, a load fluctuation calculation module, a wind shear assessment module, a yaw error calculation module and an operation risk assessment module; The wind speed fluctuation monitoring module obtains the wind speed measurement point data at the hub height of multiple units in the offshore wind farm, collects the wind speed value at the corresponding height, and extracts the unit power, yaw angle change, and vibration amplitude, calculates the wind speed change rate, compares the wind speed change rate with the unit vibration amplitude change, extracts the wind speed fluctuation frequency and amplitude, calculates the wind speed fluctuation amplitude value, and establishes the wind speed fluctuation amplitude value; The load fluctuation calculation module calls the blade vibration monitoring data, yaw drive feedback data, and tower stress monitoring device data based on the wind speed fluctuation amplitude value, calculates the vibration frequency difference of the blade vibration monitoring device, compares the stress state of the tower stress monitoring device, and combines the wind speed measurement point data at the hub height of the unit to calculate the unit load fluctuation rate to obtain the unit load fluctuation rate; The wind shear assessment module calls the load fluctuation rate of the unit, calculates the wind speed changes at multiple measuring points of the blade vibration monitoring device, extracts the gradient of the wind speed change rate, compares the gradient change amplitude, selects the key wind shear indicators, calculates the wind speed vertical gradient change rate based on the wind shear key indicators, compares the wind speed vertical gradient change rate with the vibration frequency of the blade vibration monitoring device, and establishes the wind shear intensity coefficient; The yaw error calculation module calculates the response delay of the yaw drive based on the wind shear intensity coefficient, compares the yaw record with the real-time yaw, calculates the offset angle of the yaw error, screens the key influencing factors of the yaw offset, calculates the influence of multiple factors on the yaw drive, and obtains the predicted yaw drive deviation; The operation risk assessment module calls the yaw drive prediction deviation, combines the unit load fluctuation rate and the wind shear intensity coefficient, calculates the operation state instability coefficient of the offshore wind turbine structure monitoring, analyzes the cumulative impact of wind speed changes, load fluctuations and yaw errors, and obtains the unit operation risk coefficient.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, the dynamic characteristics of wind speed changes are accurately extracted through data collection and calculation, thereby enhancing the ability to identify wind resource fluctuations. Combined with blade vibration, yaw drive feedback and tower stress monitoring data, multi-source information is cross-analyzed to improve the calculation accuracy of the unit load fluctuation rate. The establishment of the wind shear intensity coefficient enables the quantitative analysis of the impact of wind shear and improves the risk prediction ability under drastic changes in wind speed. The dynamic evaluation of the cumulative effect of yaw error optimizes the yaw accuracy control of the unit and reduces the impact of long-term operating deviations on equipment stability. Multi-dimensional data fusion calculates the unstable factors of the computer unit's operating status, comprehensively quantifies the effects of wind speed changes, load fluctuations, and yaw errors, and improves the risk assessment system. Through dynamic data analysis, real-time monitoring feedback and multi-variable calculations, the risk assessment model of wind turbines is optimized and the safety management level of offshore wind power projects is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the workflow of the present invention; Figure 2 Flowchart of the steps for obtaining the wind speed fluctuation amplitude value of the present invention; Figure 3 Flowchart of the steps for obtaining the load fluctuation rate of the unit according to the present invention; Figure 4 Flowchart of the steps for obtaining the wind shear intensity coefficient of the present invention; Figure 5 This is a flow chart of the steps for obtaining the yaw drive predicted deviation amount of the present invention; Figure 6 The figure is a flow chart of the steps for obtaining the unit operation risk coefficient of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0018] Example 1 See also Figure 1 The present invention provides a technical solution: a risk assessment method for an offshore wind power project, comprising the following steps: S1: Acquire real-time operating data of multiple wind turbines in an offshore wind farm, including wind speed values at the turbine hub height wind speed measurement point, turbine power output monitoring data, yaw angle changes of the yaw angle sensor, and vibration amplitude of the blade vibration monitoring device. Calculate the wind speed change rate between the turbine hub height wind speed measurement points, extract the wind speed fluctuation frequency and amplitude, and establish the wind speed fluctuation amplitude value. S2: Based on the wind speed fluctuation amplitude value, the vibration data of the blade vibration monitoring device, the feedback data of the yaw drive and the stress measurement data of the tower stress monitoring device are called to calculate the vibration frequency change of the blade vibration monitoring device at the differentiated measurement point, analyze the force difference of the tower at multiple heights monitored by the tower stress monitoring device, calculate the dynamic stress change rate of the blade vibration monitoring device and the tower stress monitoring device, and combine the wind speed change at the wind speed measurement point at the hub height of the unit to calculate the instantaneous load change rate of the unit to obtain the unit load fluctuation rate; S3: Based on the unit load fluctuation rate, calculate the wind speed change rate of the blade vibration monitoring device at the differentiated measurement points, extract the wind shear influencing factor, call the data of the offshore wind farm wind resource measurement points to analyze the wind speed gradient at the wind turbine hub height wind speed measurement point, and obtain the wind shear intensity coefficient; S4: Based on the wind shear intensity coefficient, calculate the response delay time of the yaw drive, collect the unit yaw angle change data, analyze the error impact of the wind direction adjustment recorded by the yaw angle sensor on the wind speed prediction, calculate the response hysteresis error of the yaw drive, and obtain the yaw drive prediction deviation; S5: Based on the yaw drive prediction deviation, combined with the unit load fluctuation rate and wind shear intensity coefficient, the operating state instability coefficient of the offshore wind turbine structure monitoring is calculated, the cumulative impact of wind speed changes, load fluctuations and yaw errors is analyzed, and the unit operation risk coefficient is established.

[0019] The wind speed fluctuation amplitude value specifically includes the wind speed change rate, wind speed fluctuation frequency, and wind speed fluctuation amplitude. The unit load fluctuation rate includes the vibration frequency difference of the blade vibration monitoring device, the tower force of the tower stress monitoring device, and the wind speed measurement point data at the unit hub height. The wind shear intensity coefficient specifically includes the wind speed change at multiple measuring points and the key wind shear indicators. The yaw drive prediction deviation includes the response delay of the yaw drive, the comparison result between the yaw record and the real-time yaw, and the yaw error. The unit operation risk factor specifically refers to the impact of wind speed changes, load fluctuations, and the cumulative impact of yaw errors.

[0020] See also Figure 2 , the specific steps for obtaining the wind speed fluctuation amplitude value are: S101: Obtain hub-height wind speed values for multiple turbines in an offshore wind farm, normalize the wind speeds at multiple height measurement points using multi-sensor data fusion, calculate the mean and standard deviation of wind speeds at hub height for multiple turbines, screen and eliminate abnormal wind speed data, and obtain wind speed characteristic values; Specifically, to obtain the hub-height wind speed values of multiple units in an offshore wind farm, it is necessary to call the wind speed sensor data of each wind turbine separately, match the data according to the sampling time, and form a set of wind speed data of multiple units at the same time. The wind speed sensor is installed at the hub height and collects wind speed data at a frequency of 1 per second and stores it in the database. The multi-sensor data fusion method is used, that is, the wind speed data of multiple height measurement points are normalized. The normalization formula is: ; in, Representative Wind speed data of wind speed measurement points, and Represent the maximum and minimum values of the collected wind speed data respectively. The normalized data are averaged to obtain the wind speed characteristic value. The calculation method is: ; in, = The number of sensor measurement points. After calculating the wind speed characteristic value, the abnormal wind speed data in the data set is eliminated. The abnormal wind speed data is determined by calculating the standard deviation of the data and setting the threshold. , if a wind speed data point satisfy: ; It is determined to be abnormal data and removed. Usually, the typical value of the wind speed standard deviation is between 0.5m / s and 1.5m / s to ensure data quality. After removing the abnormal data, the mean is recalculated to obtain the wind speed characteristic value.

[0021] S102: Based on the wind speed characteristic values, power output data, yaw angle change data, and vibration amplitude data of multiple units are obtained, the wind speed change rate over time is calculated, the wind speed change trend is solved using a discrete differential method, and a wind speed change rate sequence is calculated; Specifically, the power data of the wind turbine is recorded by the SCADA system in kW and stored once every minute. The yaw angle change data is collected by the yaw system sensor in degrees and stored once every 5 seconds. The vibration amplitude data is collected by the vibration sensor in mm / s2 and stored once per second. The rate of change of wind speed over time is calculated, and the discrete differential method is used to solve the wind speed change trend. The calculation method is: ; in, represents the i-th wind speed change rate data point, and Represents wind speed data at adjacent time points, and Representing the corresponding time point, after calculating the wind speed change rate sequence, it is smoothed by a sliding window to reduce the impact of data fluctuations. The sliding window size is 3 to 5 data points, and finally the smoothed wind speed change rate sequence is obtained.

[0022] S103: Call the wind speed change rate sequence, use Fourier transform to perform spectrum analysis on the wind speed change rate, extract the key fluctuation frequency components, and combine the time domain data of the wind speed change rate to calculate the amplitude using the formula: ; Calculate and obtain the main frequency and amplitude of wind speed fluctuations, and establish the wind speed fluctuation amplitude value; in, Represents the wind speed fluctuation amplitude value, represents the i-th wind speed change rate data point, represents the mean of the wind speed change rate series, Represents the total number of wind speed data points, represents the absolute deviation of the wind speed change rate, Represents the sum of the variances of the wind speed change rate.

[0023] Specifically, before Fourier transform, the wind speed change rate is first processed to zero mean: ; Then perform a fast Fourier transform (FFT) to extract the key fluctuation frequency components and calculate the amplitude using the formula: ; in, Represents the wind speed fluctuation amplitude value, represents the i-th wind speed change rate data point, represents the mean of the wind speed change rate series, Represents the total number of wind speed data points, Represents the sum of the variances of the wind speed change rate. The parameter values are shown in Table 1: Table 1 Parameters for calculating wind speed change rate

[0024] Calculation Example: Assume , , a set of data points of wind speed change rate: ; Its amplitude is calculated as: ; The results show that the amplitude of wind speed fluctuation is larger, the more severe the wind speed fluctuation is, and the more significant the impact on the operation of the wind turbine is. It reflects the average deviation of the wind speed change rate data points relative to the mean, and measures the overall trend of wind speed change; Part II The total variance of the secondary wind speed change rate is calculated to measure the severity of wind speed changes. Ultimately, the combination of these two quantities is used to characterize the comprehensive amplitude of wind speed fluctuations. This result can be further used to optimize wind turbine control strategies to address the operational impacts of wind speed changes.

[0025] See also Figure 3 , the specific steps for obtaining the unit load fluctuation rate are as follows: S201: Based on the wind speed fluctuation amplitude value, blade vibration monitoring data, yaw drive feedback data, and tower stress monitoring device data are called to calculate the vibration frequency difference of the blade vibration monitoring device, extract the maximum and minimum difference of the vibration frequency, filter out the frequency difference that exceeds the set threshold range, and obtain the abnormal blade vibration frequency difference; Specifically, wind speed fluctuation data is collected by the wind turbine wind speed sensor and recorded once per second; blade vibration monitoring data is recorded by the acceleration sensor installed on the turbine blade and stored in millisecond sampling; yaw drive feedback data is provided by the turbine yaw system controller, with a data sampling period of 1 second; tower stress monitoring data is obtained through strain sensors installed at key parts of the tower, with a sampling frequency of 100Hz. Then, the vibration frequency difference of the blade vibration monitoring device is calculated. First, the vibration frequency at different time points is extracted from the blade vibration monitoring data, and a sliding window method with a time window of 1 minute is used to calculate the maximum vibration frequency within the time window. and minimum vibration frequency , the vibration frequency difference calculation formula is as follows: ; Assume that the normal vibration frequency of the wind turbine blade is within the range of 2.5Hz to 3.2Hz. If the vibration frequency exceeds this range within a certain time window, calculate the vibration frequency difference of the window. Assuming that within a certain time window, the maximum vibration frequency is 3.5Hz and the minimum vibration frequency is 2.4Hz, calculate: ; Filter out the frequency difference that exceeds the set threshold range, set the threshold to 0.3Hz, if , then it is determined that the blade vibration is abnormal in the time window, and the corresponding As the abnormal frequency difference of blade vibration, the result shows that the vibration frequency of the blade fluctuated greatly within this time window, which may be related to wind speed changes, yaw system adjustments or unit load changes, and its impact needs to be further analyzed.

[0026] S202: Based on the abnormal frequency difference of the blade vibration, call the data of the tower stress monitoring device to calculate the tower stress change rate using the formula: ; Obtain tower stress change value by calculation, compare the tower stress change value with the set tower safety stress range, and obtain the tower stress abnormality coefficient; in, Represents the tower stress change value, Representative Abnormal frequency value of blade vibration, Represents the reference vibration frequency value, Represents the number of data points in the monitoring period, Represents the force value of the tower at the current moment, Represents the tower force value at all times during the monitoring period, Represents the total number of data points in the monitoring period; Specifically, the tower stress data is collected by strain gauge sensors in MPa and recorded once per second. First, the corresponding tower stress data is extracted from the abnormal time window. , and then calculate the average tower force of all normal time periods in the same time window , set the reference vibration frequency value , assuming the number of data points in the monitoring period , the tower force data is shown in Table 2: Table 2 Tower force data during the monitoring period

[0027] Then, calculate the tower stress change value, assuming that within a certain time window: ; ; ; Then calculate: ; Compare the tower stress change value with the set tower safety stress range, which is set to 30MPa to 40MPa, and calculate It is much smaller than this range, indicating that the tower force changes of this unit are small within this time window and will not cause structural safety problems.

[0028] S203: Based on the tower stress anomaly coefficient and combined with the wind speed measurement point data at the unit hub height, the influence ratio of the wind speed change on the tower stress is calculated to obtain the unit load fluctuation rate.

[0029] Specifically, wind speed data is collected by the wind speed sensor at the hub height of the turbine, sampling once per second to obtain the wind speed change rate. , calculate the ratio of the effect of wind speed change on tower stress: ; Set wind speed change rate , brought into the calculation: ; Computer group load fluctuation rate: ; Assumptions ,but: ; The results show that the impact of wind speed changes on tower stress within this time window accounts for 4.4% of the total influencing factors, indicating that wind speed fluctuations have little impact on unit load fluctuations. Load fluctuations are mainly affected by other factors (such as yaw adjustment or blade adjustment). The calculation results can be used to further adjust the unit operation strategy.

[0030] See also Figure 4 , the specific steps for obtaining the wind shear intensity coefficient are: S301: Based on the unit load fluctuation rate, the wind speed change rates of multiple measuring points of the blade vibration monitoring device are calculated, the wind speed measurement values and time series data of the differentiated measuring points are called, the wind speed change gradients of the multiple measuring points are calculated, and the wind speed change gradient values of the measuring points are obtained; Specifically, the wind speed data of the blade vibration monitoring device is obtained through wind speed sensors at multiple measuring points, sampled once per second, and a sliding window method with a time window of 1 minute is used to extract the data sequence of wind speed changes at the measuring points over time. , call the wind speed measurement values and time series data of the differentiated measurement points to calculate the wind speed change gradient of multiple measurement points. The calculation method of the wind speed change gradient is: ; in, Representative The wind speed at each measuring point, The time point representing the measurement point, assuming that the wind speed data of a unit's measurement point is as shown in Table 3: Table 3 Multi-point wind speed data table

[0031] Calculate the wind speed gradient at the measuring point. Assume that measuring point 1 is at Hourly wind speed ,exist Hourly wind speed , then calculate: ; Get the wind speed change gradient value at the measuring point.

[0032] S302: Calling the wind speed change gradient value of the measuring point, calculating the wind shear degree of multiple measuring points, comparing the differences in wind speed change rates of the measuring points, screening the measuring points with significant wind speed changes, and obtaining the key wind shear measuring points; Specifically, the wind shear degree is calculated as follows: ; in, and Represents the wind speed of two adjacent measuring points. Assume that measuring point 1 and measuring point 2 are The wind speeds at 10.2m / s and 10.4m / s are: ; The wind speed change rate difference threshold is set to 0.3 m / s. If the difference between the wind speed change rate of a measuring point and that of its adjacent measuring points exceeds the threshold, it is determined that there is significant wind shear at the measuring point. The measuring points with significant wind speed changes are screened to obtain the key wind shear measuring points.

[0033] S303: Based on the data of the key wind shear measurement points, calculate the wind shear intensity coefficient using the formula: ; Obtain wind shear intensity at the measuring point through calculation and establish wind shear intensity coefficient; in, represents the wind shear intensity coefficient, Represents the height of the i+1th wind shear key measurement point Wind speed data at the location, Represents the height of the i-th wind shear key measurement point Wind speed data at the location, Represents the total number of wind shear key measurement points used to calculate the wind shear intensity coefficient, Represents the height measured at the i-th wind shear key measurement point and height The time difference corresponding to the wind speed change. The denominator in the formula calculates the sum of the squares of the time differences. .

[0034] set up , and assume that the wind speed data of key measuring points are as shown in Table 4: Table 4 Wind speed data at key measuring points

[0035] As shown in Table 4, calculate the wind shear intensity: ; Compute the sum of squares of time intervals: ; Take the square root: ; Substitute into the formula: ; The results show that the wind shear intensity coefficient in this time window is 0.106, indicating that the wind shear in this area is relatively mild, and the wind speed varies little between different measuring points, which will not cause severe load fluctuations on the wind turbine.

[0036] See also Figure 5 The specific steps for obtaining the yaw drive predicted deviation are as follows: S401: Based on the wind shear intensity coefficient, historical yaw records and real-time yaw data are called to calculate the time deviation between the two, and then the response delay of the yaw drive is calculated using the formula: ; The yaw drive response delay is calculated; in, Represents the yaw drive response delay, Represents the real-time yaw angle, represents the historical yaw angle, represents the wind shear intensity coefficient, represents the wind speed influence coefficient, represents the wind speed at the jth time point, represents the number of time points used for wind speed weighted calculation, represents the weighted contribution of wind speed to the yaw response; Specifically, real-time yaw data is collected by the angle sensor in the wind turbine control system and recorded once per second. The historical yaw records are stored in the database and the real-time yaw data is called and historical yaw data , calculate the angular deviation between the two: ; Then calculate the response delay of the yaw drive. Set the wind shear intensity coefficient , historical yaw angle , real-time yaw angle , wind speed influence coefficient and wind speed data are shown in Table 5: Table 5 Yaw response wind speed impact data

[0037] Calculate the weighted contribution of wind speed to the yaw response: ; Calculate the yaw drive response delay: ; The results show that the response time of the yaw system under the current wind shear condition is 0.12 seconds, indicating that the wind speed change causes a certain delay in the yaw drive response.

[0038] S402: Calling the yaw drive response delay, comparing historical yaw records with real-time yaw data, calculating the angle deviation between the two, and comparing the calculated deviation value with the yaw error threshold to determine whether it exceeds the set range. If so, marking the yaw error abnormal and obtaining the yaw error angle; Call the yaw drive response delay, compare the historical yaw record with the real-time yaw data, and calculate the angle deviation between the two: ; Bring in known data: ; Set the yaw error threshold to ,like , it is determined that the yaw error is abnormal and the yaw error angle is recorded. The result indicates that the current yaw adjustment deviation exceeds the preset range, which may affect the wind turbine's ability to face the wind and obtain the yaw error angle.

[0039] S403: Based on the yaw error angle, calculate the correction amount of the yaw drive system, adjust the yaw drive control parameters according to the correction amount, recalculate the yaw angle adjustment value, evaluate the yaw correction amplitude based on the wind speed change trend, and obtain the yaw drive predicted deviation amount.

[0040] Based on the yaw error angle, the correction amount of the yaw drive system is calculated. The correction amount is calculated as follows: ; in, represents the yaw angle correction, represents the yaw error angle, Represents the yaw error threshold, and substitutes the known data: ; Adjust the yaw drive control parameters according to the correction amount and recalculate the yaw angle adjustment value: ; Bring in data: ; Combined with the wind speed change trend to evaluate the yaw correction amplitude, the yaw drive prediction deviation is obtained. The result shows that the current yaw system should adjust the yaw angle to , in order to reduce the impact of yaw error on wind turbine operation.

[0041] See also Figure 6 , the specific steps for obtaining the unit operation risk coefficient are as follows: S501: Calling the yaw drive prediction deviation, obtaining the unit load fluctuation rate and wind shear intensity coefficient based on the unit operation data, calculating the yaw error change trend in multiple time periods, selecting the wind speed change range, determining the error distribution characteristics of multiple wind speed intervals, extracting the error fluctuation value, classifying the error change according to the wind speed interval, analyzing the relationship between the error increase and decrease with wind speed, screening the error intervals under different wind speed conditions, and generating the wind speed-yaw error correlation value; Specifically, the unit operation data is collected through wind speed sensors, load monitoring devices and wind direction sensors, recorded once per second, and the yaw error data in multiple time periods is called to calculate the yaw error change trend. First, the wind speed at each time point is obtained. and the corresponding yaw error , calculate the error distribution characteristics of multiple wind speed intervals, and set the wind speed intervals as: low wind speed interval (4-8m / s), medium wind speed interval (8-12m / s), and high wind speed interval (12-16m / s); In each wind speed range, extract the yaw error data of the corresponding time period and calculate the error mean And the error fluctuation value: ; According to the change of wind speed interval classification error, the relationship between error and wind speed is analyzed, the error interval under differentiated wind speed conditions is screened, and the wind speed data for a certain time period is set as shown in Table 6: Table 6 Wind speed and yaw error data

[0042] Calculate the error fluctuation value in the low wind speed range: ; Calculate the error fluctuation value in the high wind speed range: ; The results show that in the high wind speed range, the fluctuation amplitude of the yaw error is larger, generating a wind speed-yaw error correlation value.

[0043] S502: Based on the wind speed-yaw error correlation value and combined with the unit load fluctuation rate, the operating state instability under the influence of wind speed fluctuation is calculated using the formula: ; The operational instability coefficient under the combined effects of wind speed and load changes is obtained by calculation. Combined with the wind shear intensity coefficient, the stability difference within the wind speed range is calculated, the operational instability characteristics of multiple wind speed ranges are identified, and a wind speed-operational instability mapping value is generated.

[0044] in, Represents the operating state instability coefficient, represents a single data point in the wind speed-yaw error correlation, Represents the unit load fluctuation rate, represents the wind shear intensity coefficient, Represents the offset amplitude of load fluctuation in multiple time periods, The time integral value representing the wind speed variation amplitude, Represents the total number of observation time periods.

[0045] Set observation time period , take the load fluctuation rate , wind shear intensity coefficient ,calculate: ; Set wind speed-yaw error correlation value data: ; Calculate the error term: ; Calculate the sum of squares of load fluctuation offsets: ; Take the square root: ; Set the time integral value of wind speed variation: ; Calculate the sum: ; Bring it into calculation: ; The results show that the current wind speed fluctuation has a greater impact on the operating status of the unit, and the wind speed-operation instability mapping value is high.

[0046] S503: Based on the wind speed-operation instability mapping value, analyze the cumulative impact of yaw error, calculate the operation risk of the computer group under differentiated wind speed and load fluctuation conditions, select wind speed and load fluctuation combinations, evaluate the changing trend of the operating status, identify high-frequency fluctuation areas, screen key wind speed and load combinations with abnormal operating status, analyze the long-term cumulative impact in combination with long-term data, screen the risk range, and obtain the unit operation risk coefficient.

[0047] Set wind speed group: wind speed 5-10m / s, corresponding , wind speed 10-15m / s, corresponding ; Identify high-frequency fluctuation areas and set thresholds for abnormal operating conditions , judge: If Then mark the wind speed range as unstable. It is judged to be running normally; In the wind speed range of 10-15m / s: ; In the wind speed range of 5-10m / s: ; The results show that in the wind speed range of 10-15m / s, the unit operation status becomes unstable and the risk is relatively high. By combining long-term data to analyze the long-term cumulative impact, the risk range is screened and the unit operation risk coefficient is obtained.

[0048] In summary, the present invention further provides an offshore wind power project risk assessment system, which is capable of executing the above-mentioned offshore wind power project risk assessment method, specifically comprising: The wind speed fluctuation monitoring module obtains data from wind speed measurement points at the hub height of multiple turbines in an offshore wind farm, collects wind speed values at corresponding heights, extracts turbine power, yaw angle change, and vibration amplitude, calculates the wind speed change rate, compares the wind speed change rate with the turbine vibration amplitude change, extracts the wind speed fluctuation frequency and amplitude, calculates the wind speed fluctuation amplitude value, and establishes the wind speed fluctuation amplitude value; The load fluctuation calculation module, based on the wind speed fluctuation amplitude value, calls the blade vibration monitoring data, yaw drive feedback data, and tower stress monitoring device data, calculates the vibration frequency difference of the blade vibration monitoring device, compares the stress state of the tower stress monitoring device, and combines the wind speed measurement point data at the hub height of the unit to calculate the unit load fluctuation rate and obtain the unit load fluctuation rate; The wind shear assessment module uses the unit load fluctuation rate to calculate the wind speed changes at multiple measuring points of the blade vibration monitoring device, extracts the gradient of the wind speed change rate, compares the gradient change amplitude, selects key wind shear indicators, calculates the wind speed vertical gradient change rate based on the key wind shear indicators, compares the wind speed vertical gradient change rate with the vibration frequency of the blade vibration monitoring device, and establishes the wind shear intensity coefficient; The yaw error calculation module calculates the response delay of the yaw drive based on the wind shear intensity coefficient, compares the yaw record with the real-time yaw, calculates the offset angle of the yaw error, screens the key influencing factors of the yaw offset, calculates the impact of multiple factors on the yaw drive, and obtains the predicted yaw drive deviation; The operation risk assessment module calls the yaw drive prediction deviation, combines the unit load fluctuation rate and wind shear intensity coefficient, calculates the operating state instability coefficient of offshore wind turbine structure monitoring, analyzes the cumulative impact of wind speed changes, load fluctuations and yaw errors, and obtains the unit operation risk coefficient.

[0049] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A risk assessment method for an offshore wind power project, characterized in that: The following steps are involved: S1: Based on the hub height of multiple turbines in the offshore wind farm, wind speed values, turbine power, yaw angle change, and vibration amplitude are collected to calculate the wind speed change rate, extract the wind speed fluctuation frequency and amplitude, and establish the wind speed fluctuation amplitude value; S2: Based on the wind speed fluctuation amplitude value, calling the blade vibration monitoring data, yaw drive feedback data, and tower stress monitoring device data, calculating the vibration frequency difference of the blade vibration monitoring device, analyzing the tower force of the tower stress monitoring device, and combining the wind speed measurement point data at the hub height of the unit to obtain the unit load fluctuation rate; S3: Calculate the wind speed changes at multiple measuring points of the blade vibration monitoring device based on the load fluctuation rate of the unit, extract key wind shear indicators, and establish a wind shear intensity coefficient; S4: Calculating the response delay of the yaw drive based on the wind shear intensity coefficient, comparing the yaw record with the real-time yaw, determining the yaw error, and obtaining a yaw drive predicted deviation; S5: Calling the yaw drive prediction deviation, combining the unit load fluctuation rate and wind shear intensity coefficient, calculating the operating state instability coefficient of the offshore wind turbine structure monitoring, analyzing the cumulative impact of wind speed changes, load fluctuations and yaw errors, and obtaining the unit operation risk coefficient.

2. The offshore wind power project risk assessment method according to claim 1, characterized in that: The wind speed fluctuation amplitude value includes the wind speed change rate, wind speed fluctuation frequency and wind speed fluctuation amplitude; the unit load fluctuation rate includes the vibration frequency difference of the blade vibration monitoring device, the tower force of the tower stress monitoring device, and the wind speed measurement point data at the unit hub height; the wind shear intensity coefficient includes the wind speed change at multiple measuring points and the key indicators of wind shear; the yaw drive prediction deviation includes the response delay of the yaw drive, the comparison result between the yaw record and the real-time yaw, and the yaw error; the unit operation risk coefficient specifically refers to the impact of wind speed changes, load fluctuations, and the cumulative impact of yaw errors.

3. The offshore wind power project risk assessment method according to claim 2, characterized in that: The steps for obtaining the wind speed fluctuation amplitude value are specifically as follows: S101: Obtain hub-height wind speed values for multiple turbines in an offshore wind farm, normalize the wind speeds at multiple height measurement points using multi-sensor data fusion, calculate the mean and standard deviation of the wind speeds at hub height for multiple turbines, screen and eliminate abnormal wind speed data, and obtain wind speed characteristic values; S102: Based on the wind speed characteristic values, power output data, yaw angle change data, and vibration amplitude data of multiple units are obtained, the wind speed change rate over time is calculated, the wind speed change trend is solved using a discrete differential method, and a wind speed change rate sequence is calculated; S103: Call the wind speed change rate sequence, use Fourier transform to perform spectrum analysis on the wind speed change rate, extract key fluctuation frequency components, and calculate the amplitude by combining the time domain data of the wind speed change rate, using the formula: ； Calculate and obtain the main frequency and amplitude of wind speed fluctuations, and establish the wind speed fluctuation amplitude value; in, Represents the wind speed fluctuation amplitude value, represents the i-th wind speed change rate data point, represents the mean of the wind speed change rate series, Represents the total number of wind speed data points, represents the absolute deviation of the wind speed change rate, Represents the sum of the variances of the wind speed change rate.

4. The offshore wind power project risk assessment method according to claim 3, characterized in that: The steps for obtaining the unit load fluctuation rate are specifically as follows: S201: Based on the wind speed fluctuation amplitude value, calling blade vibration monitoring data, yaw drive feedback data, and tower stress monitoring device data, calculating the vibration frequency difference of the blade vibration monitoring device, extracting the maximum and minimum differences of the vibration frequencies, screening the frequency differences that exceed the set threshold range, and obtaining the abnormal blade vibration frequency difference; S202: Based on the abnormal blade vibration frequency difference, call the tower stress monitoring device data to calculate the tower stress change rate using the formula: ； Obtain tower stress change value by calculation, compare the tower stress change value with the set tower safety stress range, and obtain the tower stress abnormality coefficient; in, Represents the tower stress change value, Represents the abnormal frequency value of blade vibration, Represents the reference vibration frequency value, Represents the number of data points in the monitoring period, Represents the force value of the tower at the current moment, Represents the tower force value at all times during the monitoring period, Represents the total number of data points in the monitoring period; S203: Based on the tower stress anomaly coefficient and combined with the wind speed measurement point data at the unit hub height, the influence ratio of the wind speed change on the tower stress is calculated to obtain the unit load fluctuation rate.

5. The offshore wind power project risk assessment method according to claim 4, characterized in that: The steps for obtaining the wind shear intensity coefficient are specifically as follows: S301: Based on the load fluctuation rate of the unit, calculating the wind speed change rates of multiple measuring points of the blade vibration monitoring device, calling the wind speed measurement values and time series data of the differentiated measuring points, calculating the wind speed change gradients of the multiple measuring points, and obtaining the wind speed change gradient values of the measuring points; S302: calling the wind speed change gradient value of the measuring point, calculating the wind shear degree of multiple measuring points, comparing the differences in wind speed change rates of the measuring points, screening the measuring points with significant wind speed changes, and obtaining key wind shear measuring points; S303: Calculate the wind shear intensity coefficient based on the data of the key wind shear measurement points using the formula: ； Obtain wind shear intensity at the measuring point through calculation and establish wind shear intensity coefficient; in, represents the wind shear intensity coefficient, Represents the height of the i+1th wind shear key measurement point Wind speed data at the location, Represents the height of the i-th wind shear key measurement point Wind speed data at the location, Represents the total number of wind shear key measurement points used to calculate the wind shear intensity coefficient, Represents the height measured at the i-th wind shear key measurement point and height The denominator of the time difference calculation is the normalized square root of the sum of the squares of the time differences.

6. The offshore wind power project risk assessment method according to claim 5, characterized in that: The steps for obtaining the yaw drive predicted deviation are specifically as follows: S401: Based on the wind shear intensity coefficient, historical yaw records and real-time yaw data are called to calculate the time deviation between the two, and then the response delay of the yaw drive is calculated using the formula: ； The yaw drive response delay is calculated; in, Represents the yaw drive response delay, Represents the real-time yaw angle, represents the historical yaw angle, represents the wind shear intensity coefficient, represents the wind speed influence coefficient, represents the wind speed at the jth time point, represents the number of time points used for wind speed weighted calculation, represents the weighted contribution of wind speed to the yaw response; S402: calling the yaw drive response delay, comparing historical yaw records with real-time yaw data, calculating an angle deviation between the two, and comparing the calculated deviation value with a yaw error threshold to determine whether it exceeds a set range; if it exceeds the set range, marking the yaw error as abnormal and obtaining the yaw error angle; S403: Based on the yaw error angle, calculate the correction amount of the yaw drive system, adjust the yaw drive control parameters according to the correction amount, recalculate the yaw angle adjustment value, evaluate the yaw correction amplitude in combination with the wind speed change trend, and obtain the yaw drive predicted deviation amount.

7. The offshore wind power project risk assessment method according to claim 6, characterized in that: The steps for obtaining the unit operation risk coefficient are specifically as follows: S501: calling the yaw drive predicted deviation, obtaining the unit load fluctuation rate and wind shear intensity coefficient based on the unit operation data, calculating the yaw error change trend in multiple time periods, selecting a wind speed change range, determining the error distribution characteristics of multiple wind speed intervals, extracting the error fluctuation value, classifying the error change according to the wind speed interval, analyzing the increase and decrease relationship between the error and the wind speed, screening the error intervals under differentiated wind speed conditions, and generating a wind speed-yaw error correlation value; S502: Based on the wind speed-yaw error correlation value and combined with the unit load fluctuation rate, the operating state instability under the influence of wind speed fluctuation is calculated using the formula: ； The operational instability coefficient under the combined effects of wind speed and load changes is calculated, and combined with the wind shear intensity coefficient, the stability difference within the wind speed range is calculated, the operational instability characteristics of multiple wind speed ranges are identified, and a wind speed-operation instability mapping value is generated; in, Represents the operating state instability coefficient, represents a single data point in the wind speed-yaw error correlation, Represents the unit load fluctuation rate, represents the wind shear intensity coefficient, Represents the offset amplitude of load fluctuation in multiple time periods, The time integral value representing the wind speed variation amplitude, represents the total number of observation time periods; S503: Based on the wind speed-operation instability mapping value, analyze the cumulative impact of the yaw error, calculate the operation risk of the computer group under differentiated wind speed and load fluctuation conditions, select a combination of wind speed and load fluctuations, evaluate the changing trend of the operating status, identify high-frequency fluctuation areas, screen key wind speed and load combinations with abnormal operating status, analyze the long-term cumulative impact in combination with long-term data, screen the risk interval, and obtain the unit operation risk coefficient.

8. An offshore wind power project risk assessment system, characterized in that: The offshore wind power project risk assessment system is used to run the offshore wind power project risk assessment method according to any one of claims 1 to 7, and the offshore wind power project risk assessment system includes a wind speed fluctuation monitoring module, a load fluctuation calculation module, a wind shear assessment module, a yaw error calculation module and an operation risk assessment module; The wind speed fluctuation monitoring module obtains the wind speed measurement point data at the hub height of multiple units in the offshore wind farm, collects the wind speed value at the corresponding height, and extracts the unit power, yaw angle change, and vibration amplitude, calculates the wind speed change rate, compares the wind speed change rate with the unit vibration amplitude change, extracts the wind speed fluctuation frequency and amplitude, calculates the wind speed fluctuation amplitude value, and establishes the wind speed fluctuation amplitude value; The load fluctuation calculation module calls the blade vibration monitoring data, yaw drive feedback data, and tower stress monitoring device data based on the wind speed fluctuation amplitude value, calculates the vibration frequency difference of the blade vibration monitoring device, compares the stress state of the tower stress monitoring device, and combines the wind speed measurement point data at the hub height of the unit to calculate the unit load fluctuation rate to obtain the unit load fluctuation rate; The wind shear assessment module calls the load fluctuation rate of the unit, calculates the wind speed changes at multiple measuring points of the blade vibration monitoring device, extracts the gradient of the wind speed change rate, compares the gradient change amplitude, selects the key wind shear indicators, calculates the wind speed vertical gradient change rate based on the wind shear key indicators, compares the wind speed vertical gradient change rate with the vibration frequency of the blade vibration monitoring device, and establishes the wind shear intensity coefficient; The yaw error calculation module calculates the response delay of the yaw drive based on the wind shear intensity coefficient, compares the yaw record with the real-time yaw, calculates the offset angle of the yaw error, screens the key influencing factors of the yaw offset, calculates the influence of multiple factors on the yaw drive, and obtains the predicted yaw drive deviation; The operation risk assessment module calls the yaw drive prediction deviation, combines the unit load fluctuation rate and the wind shear intensity coefficient, calculates the operation state instability coefficient of the offshore wind turbine structure monitoring, analyzes the cumulative impact of wind speed changes, load fluctuations and yaw errors, and obtains the unit operation risk coefficient.

Images