An intelligent operation and maintenance management method for energy technology based on low-altitude areas

Abstract

The present invention discloses an intelligent operation and maintenance management method for energy technology based on the low-altitude field, which relates to the field of energy technology operation and maintenance technology, and specifically includes the following steps: analyzing the acquired operating status information of each area of ​​the fan blade, and generating the turbulence stress intensity coefficient and the instantaneous load impact coefficient of each area respectively; constructing a turbulence impact assessment model for the generated turbulence stress intensity coefficient and the instantaneous load impact coefficient of each area, generating the load impact coefficient of each area, and analyzing it after generation, assessing the instantaneous load impact degree of turbulence on the fan blade, and dividing it into three categories of low load impact, medium load impact and high load impact according to the assessment results; taking corresponding measures according to the division results. The present invention solves the assessment problem of the instantaneous load impact of turbulence on the fan blade, and realizes the real-time optimization of the fan operation and safe and efficient operation.

Description

Technical Field

[0001] The present invention relates to the field of energy technology operation and maintenance technology, and in particular to an energy technology intelligent operation and maintenance management method based on a low-altitude area. Background Art

[0002] Energy technology refers to the scientific and technological and engineering methods involved in the development, utilization, transmission and management of energy. It is a key area for modern social security energy supply, improving energy utilization efficiency and promoting green development. The purpose of operation and maintenance management of energy technology is to ensure the efficient, safe and stable operation of the energy system and extend the service life of equipment. At the same time, it reduces operation and maintenance costs and reduces resource waste through intelligent means, thereby maximizing the economic and environmental benefits of energy technology. Energy technologies in the low-altitude field, such as low-altitude wind power generation and solar energy facilities, are affected by factors such as environmental complexity, meteorological variability and special operating conditions. Traditional operation and maintenance methods are difficult to meet the needs of efficient management. Therefore, real-time monitoring and optimization of low-altitude energy facilities through intelligent operation and maintenance management methods can not only ensure the stability of energy supply, but also effectively respond to dynamic changes in the low-altitude environment, and improve overall operation and maintenance efficiency and facility reliability.

[0003] The existing intelligent operation and maintenance management technology of energy technology based on low-altitude fields mainly realizes the operation and maintenance management of energy facilities through sensor networks, real-time data collection and remote monitoring platforms. Specifically, sensors are arranged on low-altitude wind power generation, solar power generation and other facilities to monitor key information such as equipment operation status, environmental conditions (such as wind speed, temperature, humidity, etc.) and output power, and these data are transmitted to the operation and maintenance platform through wireless communication networks. The operation and maintenance platform displays and records the collected data in real time. The operation and maintenance personnel can view the operation status of the equipment through the visual interface, and identify and locate abnormal problems such as equipment failure, abnormal power output or excessive environmental impact according to the preset alarm rules. Once a problem is detected, the platform can automatically generate a maintenance notification, or coordinate the operation and maintenance personnel to deal with the problem through the scheduling function. In addition, some technologies also introduce historical data comparison and trend analysis to predict potential problems and provide preventive maintenance suggestions, thereby improving operation and maintenance efficiency and reducing unplanned downtime of energy facilities.

[0004] The prior art has the following deficiencies:

[0005] During the operation of low-altitude wind power generation facilities, when turbulence occurs in the windward area in front of the wind turbine due to complex terrain (such as valleys or steep slopes) or the wake effect of adjacent wind turbine arrays, the data collected by the wind speed sensor at different heights will have significant differences due to the temporal and spatial non-uniformity of the turbulence. This turbulence phenomenon will cause a major instantaneous load impact on the wind turbine blades, and at the same time, it will be transmitted to the tower through the blades, which may cause additional vibration of the tower. However, the existing technology usually only analyzes the data of a single sensor independently, lacks the ability to jointly analyze multi-sensor data, and therefore it is difficult to scientifically evaluate the instantaneous load impact of turbulence on wind turbine blades. This limitation will lead to the underestimation or misjudgment of the impact of turbulence, causing the wind turbine to fail to take deceleration or shutdown measures in time under load impact, thereby increasing the accumulation of mechanical stress on the blades, leading to fatigue damage and failure risks of key components, significantly increasing maintenance costs and affecting the safety and efficiency of wind turbine operation.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide an intelligent operation and maintenance management method for energy technology based on the low-altitude field to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: an intelligent operation and maintenance management method of energy technology based on low-altitude areas, specifically comprising the following steps:

[0009] During the operation of low-altitude wind power generation facilities, the wind speed information in the windward area in front of the wind turbine is monitored in real time to detect whether turbulence occurs. When turbulence is detected, the operating status information of each area of ​​the wind turbine blade is obtained through the sensor network deployed on the wind turbine blade.

[0010] Analyze the acquired operating status information of each area of ​​the fan blade, and generate the turbulent stress intensity coefficient and instantaneous load impact coefficient of each area respectively;

[0011] A turbulence impact assessment model is constructed for the turbulence stress intensity coefficient and instantaneous load impact coefficient of each generated area, and the load impact coefficient of each area is generated. After the generation, the instantaneous load impact degree of turbulence on the wind turbine blades is evaluated, and it is divided into three categories according to the evaluation results: low load impact, medium load impact and high load impact;

[0012] According to the classification results, corresponding measures are taken for the fan blades under low load impact, medium load impact and high load impact conditions;

[0013] Continuously monitor the operating status and turbulence impact of wind turbine blades, and dynamically adjust the turbulence impact assessment model and wind turbine scheduling strategy based on real-time monitoring data to optimize the operating status of the wind turbine and improve its safety and operating efficiency.

[0014] Preferably, the acquired operating status information of each region of the fan blade is analyzed to generate the turbulence stress intensity coefficient and the instantaneous load impact coefficient of each region respectively, which specifically includes the following steps:

[0015] Preprocessing the acquired operating status information of each area of ​​the fan blade;

[0016] Extracting wind speed gradient information and vibration response information from the preprocessed operating status information of each area of ​​the fan blade;

[0017] The extracted wind speed gradient information and vibration response information are analyzed to generate the turbulence stress intensity coefficient and instantaneous load impact coefficient of each area respectively.

[0018] Preferably, the logic for obtaining the turbulent stress intensity coefficient of each region is as follows:

[0019] The wind speed gradient information is extracted from the preprocessed operating status information of each area of ​​the fan blade, including the average wind speed, blade vibration acceleration and air pressure fluctuation amplitude of each area at different times in a period of time, and the function FV is used to calculate the wind speed gradient information according to the time series. i (t), AV i (t) and PF i (t), t is the time point, FV i (t) represents the average wind speed of the ith area at time t within a period of time, AV i (t) represents the blade vibration acceleration of the ith region at time t within a period of time, PF i (t) represents the pressure fluctuation amplitude of the blade surface in the i-th region at time t within a period of time, and the time period is defined as [t1, t2], i = 1, 2, 3, ..., k, k is a positive integer;

[0020] Calculate the turbulent stress intensity coefficient of each area. The specific calculation formula is as follows:

[0021]

[0022] Where TSIC i is the turbulent stress intensity coefficient of the ith region.

[0023] Preferably, the logic for obtaining the instantaneous load impact coefficient of each area is as follows:

[0024] The vibration response information of the preprocessed operating status information of each area of ​​the fan blade is extracted, including the blade curvature, the amplitude of the blade surface force change and the blade vibration frequency in each area at different times within a period of time, and the function WD is used to calculate the vibration response information of the fan blade according to the time series. i (t), LA i (t) and YF i (t), t is the time point, WD i (t) represents the blade curvature of the i-th region at time t within a period of time, LA i (t) represents the magnitude of the force change on the blade surface in the ith region at time t within a period of time, YF i (t) represents the blade vibration frequency of the i-th region at time t within a period of time, and the time period is defined as [t1, t2], i = 1, 2, 3, ..., k, k is a positive integer;

[0025] Calculate the instantaneous load impact coefficient of each area. The specific calculation formula is as follows:

[0026]

[0027] Where, ILIC i is the instantaneous load impact coefficient of the ith region.

[0028] Preferably, a turbulence impact assessment model is constructed for the generated turbulence stress intensity coefficient and instantaneous load impact coefficient of each region to generate the load impact coefficient of each region, specifically comprising the following steps:

[0029] The turbulence stress intensity coefficients, instantaneous load impact coefficients and corresponding load impact coefficients of various regions generated in the past period of time are collected and calibrated as and x represents the turbulence stress intensity coefficients, instantaneous load impact coefficients and the numbers of the corresponding load impact coefficients of various regions generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time are formed into a historical data set;

[0030] The multivariate regression model is selected as the turbulence impact assessment model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula:

[0031]

[0032] Where β0, β1 and β2 are regression coefficients;

[0033] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined;

[0034] Using the final regression coefficient, the constructed turbulence impact assessment model is input with the turbulence stress intensity coefficient TSIC of each region generated in real time. i and transient load impact coefficient ILIC i , generate load impact coefficient LC of each area in real time i .

[0035] Preferably, the load impact coefficient LC for each region generated i Perform analysis and generate the impact assessment index IAI according to the formula: The generated impact assessment index IAI is compared with the pre-set impact assessment index threshold range [IAI min , IAI max ] to compare, and evaluate the instantaneous load impact of turbulence on wind turbine blades according to the comparison results, and divide them into three categories according to the evaluation results: low load impact, medium load impact and high load impact. The specific comparison analysis and classification are as follows:

[0036] If IAI <IAI min , if the instantaneous load impact degree of turbulence on the fan blades is low, it is classified as low load impact;

[0037] If IAI min ≤IAI≤IAI max , the instantaneous load impact degree of turbulence on the fan blades is moderate, then it is classified as medium load impact;

[0038] If IAI>IAI max If the instantaneous load impact degree of turbulence on the fan blades is high, it is classified as high load impact.

[0039] Preferably, according to the classification results, corresponding measures are taken for the fan blades under low load impact, medium load impact and high load impact, respectively, specifically:

[0040] For the fan blades classified as low load impact, the measures taken are: maintain the current operating state of the fan blades, ensure that they operate within the safe load range, and monitor the load of the blades in real time to ensure the stability of the fan blades;

[0041] For wind turbine blades classified as medium load impact, the measures taken are: adjust the operating parameters of the wind turbine, reduce load fluctuations, optimize the load distribution of the blades, and continuously monitor the operating status of the blades;

[0042] For wind turbine blades classified as high-load impact, the following measures are taken: immediately activate the protection mechanism, quickly reduce the wind turbine speed to prevent the blades from being subjected to impact force, and increase the steady-state support of the wind turbine tower through automatic system scheduling to share the load pressure of the blades; at the same time, monitor the vibration and stress data of the wind turbine blades in real time to issue early warnings for abnormal situations.

[0043] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0044] 1. The present invention overcomes the limitations of independent analysis of a single sensor in the prior art through the deployment of a multi-sensor network and real-time data collection, and realizes comprehensive monitoring of the operating status of different areas of the wind turbine blades. By obtaining high-precision quantitative data such as blade curvature, force change amplitude, and vibration frequency, and combining complex mathematical calculation formulas to generate turbulent stress intensity coefficients and instantaneous load impact coefficients, the uneven characteristics of turbulence in time and space are effectively captured, making the evaluation process more accurate and comprehensive. This multi-parameter joint analysis method significantly improves the scientificity and reliability of turbulence impact assessment.

[0045] 2. The present invention realizes the quantitative evaluation of the instantaneous load impact degree of turbulence on the fan blades by constructing a turbulence impact assessment model and generating a load impact coefficient. The introduction of the multivariate regression model not only makes it possible to make full use of historical data, but also ensures the adaptability and accuracy of the model to real-time turbulence conditions by dynamically adjusting the regression coefficient. In addition, through the calculation of the impact assessment index and the comparison with the preset threshold interval, the classification and quantitative processing of the turbulence impact are further refined, providing a scientific basis for the division of the operating status of the fan blades. This classification method based on quantitative analysis can help the fan take corresponding measures under different load impact conditions, which not only ensures the safety of operation but also avoids the waste of resources.

[0046] 3. The protection and scheduling measures taken by the present invention under low, medium and high load impact conditions respectively fully demonstrate the practicality and intelligence of the present invention. By maintaining normal operation under low load impact conditions, optimizing operating parameters under medium load impact conditions, and emergency protection under high load impact conditions, the present invention achieves a balance between wind turbine operating efficiency and safety. At the same time, the introduction of continuous monitoring and dynamic adjustment mechanisms enables the system to optimize turbulence impact assessment models and scheduling strategies in real time to ensure the real-time and accuracy of the assessment results. This closed-loop dynamic scheduling and evaluation design can not only effectively reduce the accumulation of mechanical stress on blades and towers and extend equipment life, but also significantly improve the overall operating efficiency of the wind turbine and reduce maintenance costs. It has strong industrial application value and market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0048] Figure 1 The present invention is a flowchart of an intelligent operation and maintenance management method for energy technology based on the low-altitude field. DETAILED DESCRIPTION

[0049] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0050] The present invention provides Figure 1 The method for intelligent operation and maintenance of energy technology based on low-altitude areas shown in the figure specifically includes the following steps:

[0051] During the operation of low-altitude wind power generation facilities, the wind speed information in the windward area in front of the wind turbine is monitored in real time to detect whether turbulence occurs. When turbulence is detected, the operating status information of each area of ​​the wind turbine blade is obtained through the sensor network deployed on the wind turbine blade.

[0052] In order to monitor the wind speed information in the windward area in front of the wind turbine in real time and detect whether turbulence occurs, multiple wind speed sensors can be installed in front of the wind turbine. These sensors should be arranged at different heights to ensure comprehensive monitoring of the wind field. The data of the sensor will be transmitted to the central data processing system in real time. Through the real-time collection of wind speed data, the system can analyze the fluctuation of wind speed. Turbulence usually causes violent fluctuations or unevenness in wind speed. The software can identify abnormal wind speed changes by analyzing the amplitude and frequency of these fluctuations. When the wind speed change is detected to exceed the set threshold, the system will automatically judge it as a turbulent phenomenon and issue an alarm. This process relies on the real-time data and analysis algorithm of the wind speed sensor to ensure that the wind turbine can respond in time and avoid the negative impact caused by turbulence.

[0053] When turbulence is detected, the system will further analyze the impact of turbulence on the fan based on the operating status information of the fan blades. This process is achieved through sensors deployed in different areas of the fan blades, including vibration sensors, temperature sensors, pressure sensors, etc., which are distributed at the root, middle and tip of the blades. Through the real-time data acquisition of these sensors, the system can monitor the various effects of turbulence on the fan blades, such as increased vibration and temperature fluctuations. By combining wind speed information and blade status information, the software can obtain the load impact conditions of different blade areas under the influence of turbulence, thereby providing a detailed basis for subsequent evaluation and fan adjustment. The high accuracy and real-time nature of data acquisition can effectively reflect the instantaneous load on the blades, so that the fan can make corresponding adjustments.

[0054] In order to accurately obtain the operating status information of each area of ​​the wind turbine blade, the sensor network deployed on the blade plays a key role. These sensors need to be optimized according to the load characteristics of different areas. For example, the root sensor of the blade can mainly monitor vibration and temperature changes, while the tip of the blade mainly monitors airflow characteristics such as wind speed and pressure. The sensor transmits the collected data to the data acquisition system in real time through the wireless communication module. The data acquisition system will perform preliminary processing and pre-analysis on these real-time data for further detailed analysis. In this way, the load changes in different areas of the wind turbine blade under the action of turbulence can be captured and fed back in real time, and the software can automatically analyze and generate relevant load assessment parameters. The real-time processing and analysis capabilities of data ensure that the system responds quickly to the impact of turbulence, so that the load condition of the blade can be evaluated in the first time.

[0055] This series of measures is intended to address the problem of insufficient assessment of turbulence phenomena in existing technologies. Traditional technologies often rely on a single sensor or ignore the joint analysis of multi-sensor data, which makes it difficult to accurately assess the impact of turbulence on wind turbine blades, and thus it is impossible to take necessary protective measures in a timely manner. The wind speed fluctuations and load impacts caused by turbulence behave differently in different areas of wind turbine blades. This non-uniformity makes it impossible for traditional methods to fully capture the impact of turbulence, resulting in the failure of wind turbines to slow down or shut down in time, increasing the mechanical stress of blades and towers, and thus increasing the risk of fatigue damage and failure. Through the multi-sensor network and real-time data analysis in this technical solution, it is possible to accurately assess the instantaneous load impact of turbulence on blades in different areas, provide a more scientific scheduling basis for wind turbines, reduce potential damage caused by turbulence, improve the safety and operating efficiency of wind turbines, and effectively reduce maintenance costs.

[0056] Analyze the acquired operating status information of each area of ​​the fan blade, and generate the turbulent stress intensity coefficient and instantaneous load impact coefficient of each area respectively;

[0057] In this embodiment, the acquired operating status information of each area of ​​the fan blade is analyzed to generate the turbulent stress intensity coefficient and the instantaneous load impact coefficient of each area respectively, which specifically includes the following steps:

[0058] Preprocessing the acquired operating status information of each area of ​​the fan blade;

[0059] Preprocessing the acquired operating status information of each area of ​​the wind turbine blade is a key step to ensure the accuracy of data analysis and the reliability of generated parameters, because the original data may be affected by factors such as sensor failure, environmental interference or network delay, and there may be problems such as outliers, noise, missing data or inconsistent formats. Preprocessing specifically includes the following: First, clean the data and use statistical distribution methods (such as the 3σ criterion) or trend analysis algorithms to eliminate outliers and erroneous data; second, fill in missing data through interpolation methods (such as linear interpolation or spline interpolation) to ensure data continuity; then, use denoising algorithms such as low-pass filtering or Kalman filtering to eliminate high-frequency noise interference in the data and retain key features; finally, unify the data format and synchronize the time to ensure that the data collected by each sensor has a consistent timestamp and unit, and map the values ​​to a unified range (such as between 0 and 1) through normalization processing to eliminate the magnitude differences of data of different dimensions. These preprocessing operations are automatically performed by software, which can significantly improve the integrity and quality of the data, and provide a reliable basis for the subsequent calculation of turbulent stress intensity coefficients and instantaneous load impact coefficients, thereby ensuring the accuracy and scientificity of the evaluation results.

[0060] Extracting wind speed gradient information and vibration response information from the preprocessed operating status information of each area of ​​the wind turbine blade, wherein the wind speed gradient information is used to characterize the turbulence intensity, and the vibration response information is used to characterize the instantaneous load impact;

[0061] The extracted wind speed gradient information and vibration response information are analyzed to generate the turbulence stress intensity coefficient and instantaneous load impact coefficient of each area respectively.

[0062] In this embodiment, the logic for obtaining the turbulent stress intensity coefficient of each region is as follows:

[0063] The wind speed gradient information is extracted from the preprocessed operating status information of each area of ​​the fan blade, including the average wind speed, blade vibration acceleration and air pressure fluctuation amplitude of each area at different times in a period of time, and the function FV is used to calculate the wind speed gradient information according to the time series. i (t), AV i (t) and PF i (t), t is the time point, FV i (t) represents the average wind speed of the ith area at time t within a period of time, AVi (t) represents the blade vibration acceleration of the ith region at time t within a period of time, PF i (t) represents the pressure fluctuation amplitude of the blade surface in the i-th region at time t within a period of time, and the time period is defined as [t1, t2], i = 1, 2, 3, ..., k, k is a positive integer;

[0064] In order to extract the wind speed gradient information, blade vibration acceleration and air pressure fluctuation amplitude from the preprocessed operating status information of each area of ​​the wind turbine blade, it is first necessary to collect data in real time through the sensor network deployed on the wind turbine blade. These sensors usually include wind speed sensors, acceleration sensors and pressure sensors, which are installed on different blade areas (such as the root, middle and tip of the blade). Through the sensor network, the wind speed changes, blade vibration response and air pressure fluctuation data in these areas can be continuously recorded. Through the data acquisition system, these data can be collected regularly and stored in the database, and then preprocessed using data processing software, such as denoising, interpolation, time synchronization, etc., to ensure the accuracy and consistency of the data. Next, statistical methods and signal processing algorithms (such as sliding average, Fourier transform, etc.) are used to extract the time series data of the average wind speed, vibration acceleration and air pressure fluctuation in each area. These data will serve as the basis for subsequent analysis and provide the required input for calculating the turbulent stress intensity coefficient.

[0065] Regarding the acquisition and interpretation of these three types of quantitative data, wind speed data is usually obtained through wind speed sensors. These sensors measure the wind speed changes in the windward area in front of the fan, and generate accurate wind speed records based on their installation accuracy and sampling frequency. Blade vibration acceleration is measured by acceleration sensors. These sensors can capture the tiny vibrations of fan blades in different wind speeds and turbulent environments. The dynamic response of the blades when impacted by turbulence can be inferred from the acceleration values. The air pressure fluctuation amplitude is collected by installing a pressure sensor on the blade surface. It can capture the air pressure changes when the airflow flows on the blade surface. These changes can reflect the impact of turbulence intensity on the blade. The data collected by these sensors will generate time series at specific time intervals. Subsequently, data processing methods such as average calculation and standardization can be used to extract indicators such as wind speed, vibration acceleration and air pressure fluctuation amplitude in each area, and analyze them to further calculate the turbulent stress intensity coefficient. The acquisition and processing of these data can provide the necessary basis for real-time evaluation of the stress state of fan blades.

[0066] Calculate the turbulent stress intensity coefficient of each area. The specific calculation formula is as follows:

[0067]

[0068] Where TSICi is the turbulent stress intensity coefficient of the ith region.

[0069] The calculation formula is designed to accurately evaluate the stress intensity of turbulence on wind turbine blades and take into account the impact of turbulence on different areas of the blade. First, the second-order derivative is calculated to capture the acceleration of wind speed changes, reflecting the severity of turbulence. Turbulence is essentially a highly unstable phenomenon in airflow, and its speed changes are not only manifested in the instantaneous wind speed, but also in the rate of change of wind speed. By calculating the acceleration of wind speed through the second-order derivative, the dynamic characteristics of turbulence can be obtained, so as to better capture the stress caused by turbulence on the blade surface. Next, the purpose of using the fourth power operation is to amplify the effect of turbulence intensity on the blade, because the pressure fluctuations caused by turbulence are highly nonlinear, and the increase in turbulence intensity usually leads to an exponential increase in stress. The fourth power operation can effectively emphasize the nonlinear effect of turbulence intensity on the blade surface. The third power is used to quantify the effect of vibration acceleration, which is the structural response of the blade under the action of airflow. The third power operation can amplify the mechanical stress it exerts on the blade, so as to more accurately evaluate its load impact. The multiplication of wind speed gradient, vibration acceleration and pressure fluctuation information takes into account the combined effect of these factors at the same time point. Turbulence, blade vibration and pressure fluctuation act together on the blade surface, directly affecting the instantaneous load impact of the blade. Finally, the definite integral is used to accumulate these instantaneous effects into a time period. Considering that turbulence is a time-varying phenomenon, the integral operation can combine the effects of different time points to obtain a comprehensive turbulent stress intensity assessment result. In general, this calculation formula can more accurately evaluate the stress intensity of wind turbine blades under turbulent conditions by comprehensively considering turbulence, vibration and air pressure fluctuations, combined with high-order nonlinear operations and integral processing.

[0070] Turbulence stress intensity coefficient TSIC of the i-th region i The size of directly reflects the intensity of the turbulence effect on the area, which in turn affects the instantaneous load impact degree of the wind turbine blades. The larger the coefficient, the stronger the turbulence stress in the area and the greater the load impact on the blades. Specifically, the turbulence stress intensity coefficient is calculated by integrating factors such as wind speed gradient, vibration acceleration and air pressure fluctuations. It can effectively quantify the nonlinear effects of turbulence. When the turbulence stress intensity coefficient is large, it means that the turbulence effect in the area is stronger, the load changes of the wind turbine blades in this area are more drastic, and the mechanical stress will also increase significantly, which makes the wind turbine blades face a higher risk of load impact. Therefore, by calculating the turbulence stress intensity coefficient, we can accurately evaluate the degree of instantaneous load impact in different areas, and then take corresponding scheduling or protection measures to prevent the wind turbine blades from fatigue damage or failure due to excessive instantaneous loads.

[0071] In this embodiment, the logic for obtaining the instantaneous load impact coefficient of each area is as follows:

[0072] The vibration response information of the preprocessed operating status information of each area of ​​the fan blade is extracted, including the blade curvature, the amplitude of the blade surface force change and the blade vibration frequency in each area at different times within a period of time, and the function WD is used to calculate the vibration response information of the fan blade according to the time series. i (t), LA i (t) and YF i (t), t is the time point, WD i 9t) represents the blade bending degree of the ith region at time t within a period of time, LA i (t) represents the magnitude of the force change on the blade surface in the ith region at time t within a period of time, YF i (t) represents the blade vibration frequency of the i-th region at time t within a period of time, and the time period is defined as [t1, t2], i = 1, 2, 3, ..., k, k is a positive integer;

[0073] To extract the vibration response information from the preprocessed operating status information of each area of ​​the fan blade, the data acquisition method of the sensor network can be used. First, multiple high-precision sensors, such as accelerometers, strain gauges and displacement sensors, are installed on the fan blades. These sensors can monitor the vibration, bending and force of the blades in real time during the operation of the fan. The sensors transmit the data to the central control system through a wireless network. The system uses data preprocessing and filtering algorithms to clean up noise and irrelevant information to ensure the accuracy of the data. According to the characteristics of blade curvature, force change amplitude and vibration frequency, the original data can be analyzed in the frequency domain using signal processing technologies such as Fourier transform to extract detailed vibration response data at different times and in different areas, so as to obtain the real-time operating status of each area of ​​the fan blade.

[0074] The acquisition process of the three types of quantitative data, namely, the curvature of the blades in different regions at different times over a period of time, the magnitude of the force change on the blade surface, and the vibration frequency of the blades, involves the coordinated work of multiple sensors. The curvature of the blades can be obtained by strain sensors installed on the surface of the blades, which can measure the degree of bending of the blades under the action of wind. The strain sensors record the deformation of the blades at various points, and the curvature of the blades can be calculated from these data. The magnitude of the force change on the blade surface is measured by strain gauges and force sensors to measure the deformation and stress changes of the blades under the action of wind. Based on the data fed back by the sensors, the force changes on the blades at different time points can be calculated. Finally, the vibration frequency of the blades can be obtained by capturing the vibration signals of the fan blades in various regions through acceleration sensors, and combining frequency analysis methods (such as fast Fourier transform) to obtain the frequency of blade vibration. Through the extraction and analysis of these data, the operating status of the fan blades can be fully understood, and key parameters can be provided for the subsequent turbulence impact assessment.

[0075] Calculate the instantaneous load impact coefficient of each area. The specific calculation formula is as follows:

[0076]

[0077] Where, ILIC i is the instantaneous load impact coefficient of the ith region.

[0078] The calculation formula of the instantaneous load impact coefficient adopts the form of definite integral, mainly because the load impact on the wind turbine blades during operation is instantaneous and changes frequently. This change not only depends on the time factor, but is also closely related to the specific regional position of the wind turbine blades, wind speed fluctuations and turbulence characteristics. By integrating the data such as blade force, curvature and vibration frequency in different regions, the dynamic changes of load impact can be accurately captured in time and space. First, in the calculation process, three types of quantitative data are defined, namely blade curvature, blade surface force change amplitude and blade vibration frequency. Each type of data is collected in real time through the sensor network and converted into a quantifiable digital signal. Then, by expressing these data in the form of functions, the blade force and vibration state at different times and in different regions can be reflected. For example, the blade curvature can be represented by the strain value measured by the strain sensor, while the blade force change amplitude is calculated by the force signal measured by the force sensor, and the vibration frequency is obtained by frequency domain analysis of the vibration data obtained by the acceleration sensor. These three types of data represent the different response characteristics of the blade under the influence of turbulence and wind speed changes. The purpose of multiplying and integrating the "blade curvature, the cube of the force change on the blade surface, and the fourth power of the blade vibration frequency" is to accurately capture the nonlinear effect of turbulence on the load impact of wind turbine blades. In actual operation, the interaction between the curvature of the blade, the force change on the surface, and the vibration frequency and turbulence usually shows strong nonlinear characteristics, and the degree of each influence increases with the change of wind speed and turbulence intensity. By performing cubic and quartic operations on these parameters, their effects on load impact under extreme conditions can be amplified, especially in strong winds and turbulent fluctuations, the blade response is more intense, and the exponential operation of the parameter value helps to accurately simulate this process. Using cubic and quartic operations can emphasize the accelerating effect of these parameters on load impact under high load conditions, and the cumulative calculation of the blade state at each time and region through definite integrals helps to comprehensively evaluate the degree of instantaneous load impact caused by turbulence, and ultimately provide a scientific basis for the safety assessment and scheduling decision of wind turbine blades.

[0079] The instantaneous load impact coefficient ILIC of the i-th area iThe size of directly reflects the degree of load impact in the area affected by turbulence. Specifically, the load impact coefficient is calculated by weighted summation and integration of the blade curvature, the cube of the surface force change amplitude, and the fourth power of the blade vibration frequency. The changes in these parameters can highly sensitively capture the instantaneous fluctuations and nonlinear effects caused by turbulence. When the load impact coefficient is large, it means that the blades in this area are more strongly affected by turbulence and the load impact they bear is more severe, indicating that the impact of turbulence on the wind turbine blades is particularly significant in this area. On the contrary, a small load impact coefficient indicates that the load impact in this area is lighter and the instantaneous load effect of turbulence on the blades is weaker. Therefore, by comparing the load impact coefficients of different areas and combining the comparison of the evaluation coefficient with the preset threshold, the degree of instantaneous load impact of turbulence on the wind turbine blades can be accurately evaluated, and then it can be determined whether scheduling or protection measures need to be taken to ensure the safety and operating efficiency of the wind turbine.

[0080] A turbulence impact assessment model is constructed for the turbulence stress intensity coefficient and instantaneous load impact coefficient of each generated area, and the load impact coefficient of each area is generated. After the generation, the instantaneous load impact degree of turbulence on the wind turbine blades is evaluated, and it is divided into three categories according to the evaluation results: low load impact, medium load impact and high load impact;

[0081] In this embodiment, a turbulence impact assessment model is constructed based on the generated turbulence stress intensity coefficient and instantaneous load impact coefficient of each region to generate the load impact coefficient of each region, specifically including the following steps:

[0082] The turbulence stress intensity coefficients, instantaneous load impact coefficients and corresponding load impact coefficients of various regions generated in the past period of time are collected and calibrated as and x represents the turbulence stress intensity coefficients, instantaneous load impact coefficients and the numbers of the corresponding load impact coefficients of various regions generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time are formed into a historical data set;

[0083] The collection of turbulent stress intensity coefficients, instantaneous load impact coefficients and corresponding load impact coefficients generated in various regions over a period of time can be carried out by combining a real-time monitoring system with a data storage system. First, high-precision sensors are arranged in various regions of the wind turbine blades. These sensors can collect data such as wind speed, airflow pressure, blade surface stress and vibration in real time. After preprocessing, these raw data are transmitted to the central computing unit through the communication network. Then, the real-time sensor data is combined with the historical data using the data acquisition system, and the turbulent stress intensity, load impact and other related data over a period of time are regularly stored and calibrated through the set data window. In order to ensure the accuracy and integrity of the data, the data acquisition cycle and transmission frequency can be set, such as batch storage of sensor data once every hour or every minute. Through the continuous collection and management of these data, a historical data set is formed, and combined with the real-time analysis system, the turbulent stress intensity coefficients, instantaneous load impact coefficients and load impact coefficients of each region are extracted. Finally, these data will be stored in the cloud database or local database for subsequent model training and real-time calculation. In addition, in order to ensure the validity of the data, a data quality detection mechanism can be introduced to monitor the integrity and accuracy of the data in real time to ensure that no abnormal data affects the analysis results.

[0084] Limiting x to a positive integer greater than or equal to 3 is to ensure that when constructing the turbulence impact assessment model, a sufficient set of equations can be formed to accurately calculate the value of the regression coefficient. Because there is only one target equation, and the number of regression coefficients to be calculated is three, at least three equations are required to form a set of equations, so that the calculation of the regression coefficient has a solution and the solution is unique. If there are less than three data points, it will not be possible to form enough equations to support the training of the regression model, which may lead to overfitting or inaccurate calculations, and it will not be possible to effectively estimate the impact of turbulence on the load impact of wind turbine blades. Therefore, it is necessary to collect at least three data points to ensure the adequacy of the data set and the accuracy of the regression model. Through such a limitation, a more stable and reliable regression coefficient estimation can be provided in practical applications, thereby improving the credibility of the evaluation results and the predictive ability of the system.

[0085] The multivariate regression model is selected as the turbulence impact assessment model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula:

[0086]

[0087] Where β0, β1 and β2 are regression coefficients;

[0088] The multivariate regression model is a statistical analysis method used to study the relationship between multiple independent variables and dependent variables. In the multivariate regression model, the dependent variable (i.e., the target variable) is predicted by a linear combination of multiple independent variables, where each independent variable has a corresponding regression coefficient, which indicates the degree of influence of the independent variable on the dependent variable. The multivariate regression model can handle the interrelationships between a variety of complex factors and is an effective tool for multi-factor analysis and prediction. In this technical solution, the multivariate regression model is selected as the turbulence impact assessment model because the two parameters of the turbulence stress intensity coefficient and the instantaneous load impact coefficient are interrelated, and they jointly affect the load impact of the fan blades. Therefore, the use of the multivariate regression model can effectively link these two parameters with the target load impact coefficient, and then evaluate the impact of turbulence on the fan blades. By training the model with a historical data set, the optimal value of the regression coefficient can be determined by comparing the error between the actual load impact coefficient in the historical data and the calculated value, so that the model can accurately predict future load impact conditions in practical applications.

[0089] In this regression model, the three regression coefficients β0, β1, and β2 correspond to a constant term (usually indicating a deviation or a reference value), a turbulent stress intensity coefficient, and an instantaneous load impact coefficient, respectively. β0 is usually a constant term that adjusts and corrects the model deviation, β1 reflects the degree of influence of the turbulent stress intensity coefficient on the load impact coefficient, and β2 reflects the influence of the instantaneous load impact coefficient. These three regression coefficients are determined through training of historical data sets, and ultimately can form an accurate evaluation model to evaluate the load impact of wind turbine blades under different turbulent conditions, thereby providing strong data support for the operation and maintenance of wind turbines.

[0090] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined;

[0091] The purpose of optimizing the regression coefficient by minimizing the error between the predicted value and the actual value is to ensure the accuracy and predictive ability of the model. In the multivariate regression model, the determination of the regression coefficient directly affects the accuracy of the prediction results. Each regression coefficient represents the degree of influence of the independent variable on the dependent variable. Therefore, the value of the regression coefficient must be continuously adjusted by comparing the gap between the load impact coefficient predicted by the model and the actual observed value. In order to achieve this goal, the least squares method is usually used as an optimization method. This method solves the optimal regression coefficient by minimizing the sum of squares of the differences between all predicted values ​​and actual values. Specifically, by constructing the error square sum function, the turbulent stress intensity coefficient and the instantaneous load impact coefficient of each region in the historical data set are substituted into the model, the error between the corresponding load impact coefficient and the actual observed value is calculated, and then the regression coefficient is adjusted to minimize the error. By continuously iterating this process, the optimal values ​​of the three regression coefficients can be obtained, thereby ensuring that the model can accurately evaluate the instantaneous load impact degree of turbulence on the wind turbine blades and improve the safety and efficiency of wind turbine operation.

[0092] Using the final regression coefficient, the constructed turbulence impact assessment model is input with the turbulence stress intensity coefficient TSIC of each region generated in real time. i and transient load impact coefficient ILIC i , generate load impact coefficient LC of each area in real time i .

[0093] In this embodiment, the load impact coefficient LC of each region is generated. i Perform analysis and generate the impact assessment index IAI according to the formula: The generated impact assessment index IAI is compared with the pre-set impact assessment index threshold range [IAI min , IAI max ] to compare, and evaluate the instantaneous load impact of turbulence on wind turbine blades according to the comparison results, and divide them into three categories according to the evaluation results: low load impact, medium load impact and high load impact. The specific comparison analysis and classification are as follows:

[0094] If IAI <IAI min , if the instantaneous load impact degree of turbulence on the fan blades is low, it is classified as low load impact;

[0095] When the impact assessment index is less than the minimum value of the pre-set impact assessment index threshold range, it means that the instantaneous load impact of turbulence on the fan blades is low. At this time, the fan blades are less disturbed by the airflow, and the intensity of turbulence is relatively weak, resulting in lower bending and vibration of the blades, and the load impact has less impact on the mechanical stress of the blades. For the operation of the fan, this situation indicates that the blades are in a relatively stable state during operation, the efficiency and safety of the fan are high, and there is no need to take too many adjustments or protection measures. The fan can maintain normal operation with a higher operating efficiency. At this time, the fan can continue to operate normally, reducing unnecessary shutdowns or adjustments, and improving the stability and production capacity of the overall system.

[0096] If IAI min ≤IAI≤IAI max , the instantaneous load impact degree of turbulence on the fan blades is moderate, then it is classified as medium load impact;

[0097] When the impact assessment index is within the pre-set impact assessment index threshold range, it means that the instantaneous load impact of turbulence on the fan blades is moderate. At this time, the impact of turbulence has a significant impact on the blades, causing a certain degree of vibration and bending of the blades, and the unevenness of the airflow may cause local fatigue of the blades. Although the impact of load shock on the blades is low, the stability of the fan system has been threatened to a certain extent at this time. If this state continues, the blades may gradually accumulate damage, affecting the operating efficiency and life of the fan. In this case, the fan may need to adjust operating parameters (such as speed or direction) to reduce the impact of turbulence and avoid further mechanical damage or efficiency loss.

[0098] If IAI>IAI max If the instantaneous load impact degree of turbulence on the fan blades is high, it is classified as high load impact.

[0099] When the impact assessment index is greater than the maximum value of the pre-set impact assessment index threshold range, it means that the instantaneous load impact of turbulence on the wind turbine blades is high. At this time, the wind turbine blades are subjected to a strong load impact, and the influence of turbulence causes the blades to bend, deform or vibrate to a large extent, which may cause significant mechanical stress to the blade structure and even cause fatigue damage or fracture of the blades. If the fan is in this high-load impact state for a long time, the risk of blade damage will greatly increase, which may cause the fan to shut down or require emergency repairs and adjustments. In this case, the fan needs to take protective measures quickly, such as slowing down, shutting down or adjusting the blade angle, to avoid further damage. At the same time, the fan's operating strategy also needs to be optimized in real time to reduce the negative impact of turbulence and ensure the safety and long-term operating stability of the fan.

[0100] The "pre-set impact assessment index threshold interval" can be determined by a data-driven approach, that is, according to the historical operating data and the actual operating conditions of the wind turbine blades, statistical analysis or machine learning algorithms are used to set the appropriate threshold interval. Specifically, a large amount of historical data can be collected first, including the operating status data of wind turbine blades under different climatic conditions, different turbulence intensities and load impacts, such as information such as the curvature, vibration frequency and force changes of the blades. By analyzing these data, the impact assessment index under different scenarios can be calculated, and statistical methods (such as quantile analysis and standard deviation method) can be used to determine the reasonable range of the impact assessment index. In addition, the relationship between the impact assessment index and parameters such as wind turbine blade damage and efficiency changes can be modeled through machine learning models (such as cluster analysis or regression analysis) to predict the performance changes of blades under different load impacts. These models can help identify the impact of different load impacts on wind turbine blades, and then determine the appropriate threshold interval. Through these methods, the threshold interval can be dynamically optimized, and the threshold can be updated according to real-time data to ensure that the wind turbine can obtain the best operation protection and scheduling strategy under different working conditions.

[0101] According to the classification results, corresponding measures are taken for the fan blades under low load impact, medium load impact and high load impact conditions;

[0102] In this embodiment, according to the classification results, corresponding measures are taken for the fan blades under low load impact, medium load impact and high load impact, respectively, specifically:

[0103] For the fan blades classified as low load impact, the measures taken are: maintain the current operating state of the fan blades, ensure that they operate within the safe load range, and monitor the load of the blades in real time to ensure the stability of the fan blades;

[0104] In the case of low load impact, maintaining the current operating state of the fan blades can be achieved through a real-time monitoring system and state retention logic. Specifically, the operating state of the fan blades includes the speed, blade angle and current load conditions, which are collected by sensors and transmitted to the central control system. The software will analyze the sensor data in real time to determine whether the current impact assessment index is within the low load impact range. If the result confirms that it belongs to the low load impact range, the system will execute the "state retention" logic, that is, maintain the current speed and blade angle to avoid unnecessary adjustments. At the same time, real-time monitoring of the load condition of the blades is to set the software to collect sensor data at a fixed time and dynamically compare it with the impact assessment index to ensure that the fan blades operate within a safe load range. This design can avoid over-adjustment in low impact conditions, improve the operating efficiency of the system, and reduce additional mechanical stress on the fan blades.

[0105] For wind turbine blades classified as medium load impact, the measures taken are: adjust the operating parameters of the fan, reduce load fluctuations, optimize the load distribution of the blades, and continuously monitor the operating status of the blades to ensure that they operate under optimal conditions.

[0106] In the case of moderate load impact, the load fluctuation is reduced by adjusting the operating parameters of the fan and the load distribution of the blades is optimized. This can be achieved through the parameter dynamic adjustment module in the fan control system. Specifically, the software needs to dynamically calculate the optimal speed and blade angle of the fan blades based on real-time sensor data (such as turbulent stress intensity coefficient and instantaneous load impact coefficient) to reduce the load impact caused by turbulence. For example, the system can optimize the aerodynamic performance and reduce the impact of uneven turbulence on the blade surface by adjusting the windward angle of the blade. At the same time, the software determines whether the load distribution is reasonable by monitoring the vibration frequency and load fluctuation amplitude, and optimizes the load adjustment strategy according to the algorithm. The purpose of this is to reduce fatigue damage while ensuring the normal operation of the fan blades, extend the service life of the blades, and improve the stability and efficiency of the fan operation.

[0107] For wind turbine blades classified as high-load impact, the following measures are taken: immediately activate the protection mechanism, quickly reduce the wind turbine speed to prevent the blades from being subjected to impact force, and increase the steady-state support of the wind turbine tower through automatic system scheduling to share the load pressure of the blades; at the same time, monitor the vibration and stress data of the wind turbine blades in real time, issue early warnings for abnormal situations, and initiate the emergency shutdown procedure and take protective measures to prevent blade failures such as excessive wear or breakage.

[0108] In the case of high load impact, blade damage is prevented by immediately starting the protection mechanism, reducing the speed, and monitoring the blade status in real time. This measure relies on the automatic detection and response logic of high load impact. When the impact assessment index exceeds the set high load threshold, the system triggers the emergency protection program and preferentially reduces the wind turbine speed to reduce the impact force on the blade. At the same time, the system adjusts the blade angle or enables auxiliary structures (such as tower support) to share the blade load pressure through the dynamic scheduling module to further reduce the mechanical stress caused by load concentration. In addition, real-time monitoring of blade vibration and stress data is completed through the sensor network. After these data are transmitted to the software analysis module, they are compared with the warning threshold under high load conditions. Once an abnormal signal (such as vibration frequency exceeding the critical value or stress increasing sharply) is detected, the system will start the emergency shutdown procedure and generate a protection measure report. This design can protect the structural integrity of wind turbine blades and towers under high load impact conditions, avoid catastrophic failures, and ensure the long-term operation safety of wind turbines.

[0109] Continuously monitor the operating status and turbulence impact of wind turbine blades, and dynamically adjust the turbulence impact assessment model and wind turbine scheduling strategy based on real-time monitoring data to optimize the operating status of the wind turbine and improve its safety and operating efficiency.

[0110] Continuous monitoring of the operating status and turbulence effects of wind turbine blades can be achieved by deploying distributed sensor networks and real-time data acquisition systems. Specifically, a variety of sensors (such as strain sensors, accelerometers, wind speed sensors, and pressure sensors) are installed in different areas of the wind turbine blades. These sensors can capture the vibration, force, bending of the blades, and changes in the surrounding turbulence intensity in real time. These data are transmitted to the central control system via a wireless or wired network, and the software uses the data acquisition module to integrate and preprocess the sensor data (such as noise filtering and signal standardization). In this way, the system can grasp the operating status of the blades and the impact of turbulence on the blades in real time, providing reliable data support for subsequent analysis. This continuous monitoring design can ensure the transparency of the wind turbine operating status, allowing the system to capture potential risks or anomalies at any time and provide timely protection and optimization measures.

[0111] Dynamically adjusting the turbulence impact assessment model and the fan scheduling strategy based on real-time monitoring data can be achieved through adaptive models and real-time optimization algorithms. Specifically, the software needs to input the real-time monitored turbulence intensity, instantaneous load impact, and operating status data of the fan blades into the turbulence impact assessment model, and compare the output results of the model with the actual monitoring data. If there is a deviation between the assessment results and the actual operating data, the system adjusts the parameters of the turbulence impact assessment model, such as regression coefficients, threshold intervals, etc., through the dynamic optimization module to ensure that the model can accurately reflect the blade stress under the current turbulent conditions. At the same time, the fan scheduling strategy analyzes the current load distribution of the blades and dynamically adjusts key parameters such as fan speed and blade angle in combination with the model output results to optimize the fan operation status. This dynamic adjustment mechanism enables the model and strategy to always adapt to the real-time changing turbulent environment, thereby avoiding operational problems caused by assessment errors or lags.

[0112] Continuously monitoring the operating status and turbulence effects of wind turbine blades and dynamically adjusting the evaluation model and scheduling strategy is to ensure that the wind turbine can operate safely and efficiently under complex and dynamically changing turbulent conditions. The temporal and spatial non-uniformity of turbulence will lead to increased volatility of blade loads. If it cannot be accurately evaluated and adjusted in time, it may cause damage to the blade structure or reduce efficiency. Through real-time monitoring data and dynamic adjustment mechanisms, the system can quickly update the evaluation results and operating strategies when turbulent conditions change, thereby reducing the instantaneous load impact of turbulence on the blades and preventing mechanical failures or efficiency losses caused by lagging or inaccurate evaluation models. In addition, this design can extend the service life of wind turbine blades and key components, reduce maintenance costs, improve the economy and safety of wind turbine operation, and ultimately achieve the goal of intelligent wind turbine operation and maintenance.

[0113] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0114] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center containing one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0115] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0116] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0117] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0118] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0119] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0120] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent operation and maintenance management method for energy technology based on low-altitude areas, characterized in that: The specific steps include: During the operation of low-altitude wind power generation facilities, the wind speed information in the windward area in front of the wind turbine is monitored in real time to detect whether turbulence occurs. When turbulence is detected, the operating status information of each area of ​​the wind turbine blade is obtained through the sensor network deployed on the wind turbine blade. Analyze the acquired operating status information of each area of ​​the fan blade, and generate the turbulent stress intensity coefficient and instantaneous load impact coefficient of each area respectively; The acquired operating status information of each area of ​​the fan blade is analyzed to generate the turbulent stress intensity coefficient and the instantaneous load impact coefficient of each area, which specifically includes the following steps: Preprocessing the acquired operating status information of each area of ​​the fan blade; Extracting wind speed gradient information and vibration response information from the preprocessed operating status information of each area of ​​the fan blade; The extracted wind speed gradient information and vibration response information are analyzed to generate the turbulence stress intensity coefficient and instantaneous load impact coefficient of each area respectively; The logic for obtaining the turbulent stress intensity coefficient of each region is as follows: The wind speed gradient information is extracted from the preprocessed operating status information of each area of ​​the fan blade, including the average wind speed, blade vibration acceleration and air pressure fluctuation amplitude of each area at different times in a period of time, and the function FV is used to calculate the wind speed gradient information according to the time series. i (t), AV i (t) and PF i (t), t is the time point, FV i (t) represents the average wind speed of the ith area at time t within a period of time, AV i (t) represents the blade vibration acceleration of the ith region at time t within a period of time, PF i (t) represents the pressure fluctuation amplitude of the blade surface in the i-th region at time t within a period of time, and the time period is defined as [t1, t2], i = 1, 2, 3, ..., k, k is a positive integer; Calculate the turbulent stress intensity coefficient of each area. The specific calculation formula is as follows: Where TSIC i is the turbulence stress intensity coefficient of the ith region; The logic for obtaining the instantaneous load impact coefficient of each area is as follows: The vibration response information of the preprocessed operating status information of each area of ​​the fan blade is extracted, including the blade curvature, the amplitude of the blade surface force change and the blade vibration frequency in each area at different times within a period of time, and the function WD is used to calculate the vibration response information of the fan blade according to the time series. i (t), LA i (t) and YF i (t), t is the time point, WD i (t) represents the blade curvature of the i-th region at time t within a period of time, LA i (t) represents the magnitude of the force change on the blade surface in the ith region at time t within a period of time, YF i (t) represents the blade vibration frequency of the i-th region at time t within a period of time, and the time period is defined as [t1, t2], i = 1, 2, 3, ..., k, k is a positive integer; Calculate the instantaneous load impact coefficient of each area. The specific calculation formula is as follows: Where, ILIC i is the instantaneous load impact coefficient of the ith region; A turbulence impact assessment model is constructed for the turbulence stress intensity coefficient and instantaneous load impact coefficient of each generated area, and the load impact coefficient of each area is generated. After the generation, the instantaneous load impact degree of turbulence on the wind turbine blades is evaluated, and it is divided into three categories according to the evaluation results: low load impact, medium load impact and high load impact; According to the classification results, corresponding measures are taken for the fan blades under low load impact, medium load impact and high load impact conditions; Continuously monitor the operating status and turbulence impact of wind turbine blades, and dynamically adjust the turbulence impact assessment model and wind turbine scheduling strategy based on real-time monitoring data to optimize the operating status of the wind turbine and improve its safety and operating efficiency.

2. According to claim 1, a method for intelligent operation and maintenance management of energy technology based on low-altitude areas is characterized in that: A turbulence impact assessment model is constructed for the generated turbulence stress intensity coefficient and instantaneous load impact coefficient of each region to generate the load impact coefficient of each region, specifically including the following steps: The turbulence stress intensity coefficients, instantaneous load impact coefficients and corresponding load impact coefficients of various regions generated in the past period of time are collected and calibrated as and x represents the turbulence stress intensity coefficients, instantaneous load impact coefficients and the numbers of the corresponding load impact coefficients of various regions generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time are formed into a historical data set; The multivariate regression model is selected as the turbulence impact assessment model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula: Where β0, β1 and β2 are regression coefficients; By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined; Using the final regression coefficient, the constructed turbulence impact assessment model is input with the turbulence stress intensity coefficient TSIC of each region generated in real time. i and transient load impact coefficient ILIC i , generate load impact coefficient LC of each area in real time i .

3. According to claim 2, a method for intelligent operation and maintenance management of energy technology based on low-altitude areas is characterized in that: The load impact coefficient LC for each generated area i Perform analysis and generate the impact assessment index IAI according to the formula: The generated impact assessment index IAI is compared with the pre-set impact assessment index threshold range [IAI min , IAI max ] to compare, and evaluate the instantaneous load impact of turbulence on wind turbine blades according to the comparison results, and divide them into three categories according to the evaluation results: low load impact, medium load impact and high load impact. The specific comparison analysis and classification are as follows: If IAI <IAI min , if the instantaneous load impact degree of turbulence on the fan blades is low, it is classified as low load impact; If IAI min ≤IAI≤IAI max , the instantaneous load impact degree of turbulence on the fan blades is moderate, then it is classified as medium load impact; If IAI>IAI max If the instantaneous load impact degree of turbulence on the fan blades is high, it is classified as high load impact.

4. According to claim 3, a method for intelligent operation and maintenance management of energy technology based on low-altitude areas is characterized in that: According to the classification results, corresponding measures are taken for the fan blades under low load impact, medium load impact and high load impact, specifically: For the fan blades classified as low load impact, the measures taken are: maintain the current operating state of the fan blades, ensure that they operate within the safe load range, and monitor the load of the blades in real time to ensure the stability of the fan blades; For wind turbine blades classified as medium load impact, the measures taken are: adjust the operating parameters of the wind turbine, reduce load fluctuations, optimize the load distribution of the blades, and continuously monitor the operating status of the blades; For wind turbine blades classified as high-load impact, the following measures are taken: immediately activate the protection mechanism, quickly reduce the wind turbine speed to prevent the blades from being subjected to impact force, and increase the steady-state support of the wind turbine tower through automatic system scheduling to share the load pressure of the blades; at the same time, monitor the vibration and stress data of the wind turbine blades in real time to issue early warnings for abnormal situations.

Images