Method and device for evaluating service life of main bearing of wind turbine generator

Abstract

The invention relates to the technical field of wind power generation, and discloses a wind power plant main bearing life evaluation method and device. The method comprises the following steps: firstly, constructing a main bearing life response surface model, and determining a mapping relation between a wind load parameter taking an average wind speed and turbulence intensity as a core and the main bearing life; then, joint probability distribution is constructed based on actually-measured wind parameters, discretization sampling is conducted on the joint probability distribution, and environment feature pairs containing the average wind speed and the turbulence intensity and corresponding probability weights of the environment feature pairs are determined; determining the fatigue life corresponding to each environment feature pair by using the response surface model, coupling the fatigue life with the probability weight, and calculating to obtain the comprehensive fatigue life of the main bearing; and finally, realizing individualized evaluation of the service life of the main bearing of each fan by traversing actually measured wind parameters of units of the same model in the wind power plant. According to the method, the efficiency of evaluating the service life of the main bearing of the wind power plant group can be remarkably improved on the premise of ensuring accuracy.

Description

Technical Field

[0001] This invention relates to the field of wind power generation technology, specifically to a method and apparatus for assessing the lifespan of the main bearing of a wind turbine. Background Technology

[0002] Wind turbine bearings are critical components of wind turbine generators, primarily used in systems such as the main shaft, gearbox, and yaw / pitch control. They bear the weight of the blades and hub and transmit power. As a key component in the transmission chain, the failure of the wind turbine main bearing leads to high maintenance costs and power generation losses. The basic rated lifespan of wind turbine main bearings is significantly affected by complex environmental conditions (wind speed distribution, turbulence intensity, etc.).

[0003] The existing methods for assessing the lifespan of the main bearings of wind turbine generators can only assess the lifespan of a single unit based on its design conditions. For large wind farms with dozens or even hundreds of units, it is necessary to assess each wind turbine generator, resulting in low efficiency in assessing the lifespan of wind turbine generators. Summary of the Invention

[0004] This invention provides a method and apparatus for assessing the life of wind turbine main bearings, aiming to solve the technical problems in the prior art of large computational load and difficulty in balancing the efficiency of overall field assessment and the accuracy of single-unit assessment in wind turbine main bearing life assessment.

[0005] In a first aspect, the present invention provides a method for assessing the lifespan of a wind turbine main bearing, the method comprising: A main bearing life response surface model is constructed; wherein, the main bearing life response surface model is used to characterize the quantitative mapping relationship between wind load parameters composed of average wind speed and turbulence intensity and main bearing life. The measured wind parameter data of each wind turbine in the target wind farm are obtained. Based on the measured wind parameter data, a joint probability distribution of average wind speed and turbulence intensity is constructed. The joint probability distribution is discretized and sampled to obtain multiple pairs of single-unit environmental characteristic parameters and the probability weights of the single-unit environmental characteristic parameter pairs. The basic rated life of the main bearing under each set of single-machine environmental characteristic parameters is determined by inputting multiple sets of single bearing life response surface models. By using the probability weights of the single-unit environmental characteristic parameter pairs, the basic rated life under each set of characteristic parameters is calculated in a weighted coupling manner to obtain the comprehensive fatigue life of the main bearing of a single wind turbine. The system iterates through all wind turbines in the target wind farm and generates a life assessment result for the main bearing of the wind turbine based on the comprehensive fatigue life of the main bearing of each individual wind turbine.

[0006] This invention provides a method for assessing the lifespan of wind turbine main bearings. By pre-constructing a main bearing lifespan response surface model covering the entire wind field envelope, it establishes the mapping relationship between simulation results and wind load parameters. This avoids the time-consuming aeroelastic simulation of each wind turbine in the wind farm, enabling individualized lifespan assessments for ultra-large wind farm clusters containing hundreds or thousands of turbines to be completed in a very short time, significantly reducing computational and time costs. Furthermore, this method deeply couples high-precision dynamic simulations with SCADA measured wind parameter data for each turbine. By constructing a joint probability distribution for individual turbine locations and performing discretized sampling, it can accurately capture the load fluctuation characteristics at different locations caused by terrain or wake, thereby providing individualized lifespan predictions that are closer to the actual operating conditions. Finally, the main bearing lifespan response surface model is based on a DOE design of the global envelope interval and statistical averaging of multiple random seeds and multiple wind directions, effectively eliminating the interference of random wind conditions on the assessment results and ensuring the universality and stability of the model across the entire field.

[0007] In one alternative implementation, a main bearing life response surface model is constructed, including: Obtain measured wind parameter data at the locations of the wind turbine units to be evaluated within the target wind farm, and determine the union of the average wind speed range and the turbulence intensity range for each unit as the global envelope interval. The simulation condition matrix is ​​generated by uniformly distributing points within the global envelope. The simulation condition matrix covers multiple combinations of wind load environmental parameters corresponding to the wind turbine locations. The wind load environmental parameter combinations include the average wind speed and turbulence intensity under different simulation conditions. Dynamic simulation of the target wind turbine was performed based on the simulation working condition matrix to obtain the radial load sequence and axial load sequence of the main bearing under each simulation working condition. Calculate the characteristic life response value of the main bearing based on the radial load sequence and the axial load sequence; Using the average wind speed and turbulence intensity under different simulation conditions as input variables, and the characteristic life response value of the main bearing as the target variable, a life response surface model of the main bearing is constructed by fitting.

[0008] The present invention provides a method for assessing the life of the main bearing of a wind turbine. By pre-constructing a mapping relationship between simulation results and environmental parameters, it avoids the need for repetitive and time-consuming simulations for each turbine during actual assessment, thus significantly improving the efficiency of wind farm-level life assessment.

[0009] In one optional implementation, the characteristic life response value of the main bearing is calculated based on the radial load sequence and the axial load sequence, including: The instantaneous equivalent load at each sampling time is calculated based on the radial load sequence and axial load sequence of the main bearing under various simulation conditions. Obtain the main bearing speed, simulation step size, and life index, and calculate the average equivalent dynamic load corresponding to each simulation sub-condition based on the instantaneous equivalent load, speed, and simulation step size; Obtain the basic rated dynamic load of the main bearing, and calculate the basic rated life corresponding to each simulation sub-condition based on the average equivalent dynamic load. The basic rated life of the main bearing is obtained by averaging the basic rated life of multiple simulated sub-conditions under the same wind load environmental parameters.

[0010] This invention provides a method for assessing the life of wind turbine main bearings. Based on the real-time synthesis of instantaneous equivalent loads from the radial and axial loads of the main bearing, it accurately reconstructs the true three-dimensional stress state of the main bearing under complex aerodynamic loads, effectively avoiding life prediction deviations caused by single-direction load assessment. By calculating the average equivalent dynamic load for each time series based on the instantaneous equivalent load, main bearing speed, single simulation step size, and life index, it better reflects typical operating conditions within a time series, rather than unrealistic static loads. It employs a hierarchical calculation strategy of "first calculating the life of a single sub-condition, then statistically analyzing the average life of multiple samples," covering different... A total of 36 simulated sub-conditions with random seeds (12 groups) and wind direction angle (3 groups) were used for life assessment. This not only preserved the load differences caused by the randomness of turbulence in each sub-condition, but also effectively eliminated the excessive interference of extreme instantaneous loads (such as short-term heavy loads and extreme gust signals) on life assessment in a single sub-condition through statistical averaging. The arithmetic mean of the life of multiple simulated sub-conditions was used as the final characteristic life response value of the response surface model. This not only reflects the global fatigue level of the main bearing under a specific combination of average wind speed and turbulence intensity, but also ensures the stability and reliability of the response surface fitting sample data, laying a solid model foundation for subsequent individualized assessment of the entire field.

[0011] In one optional implementation, measured wind parameter data of each wind turbine in the target wind farm are obtained. Based on the measured wind parameter data, a joint probability distribution of average wind speed and turbulence intensity is constructed. The joint probability distribution is then discretized and sampled to obtain multiple pairs of individual turbine environmental characteristic parameters and their probability weights, including: The measured wind parameter data for a preset time period are extracted from the SCADA system of each wind turbine. The measured wind parameter data includes the average wind speed and wind speed standard deviation for each statistical period. Real-time turbulence intensity is calculated based on the average wind speed and standard deviation of wind speed for each statistical period. Based on the average wind speed and real-time turbulence intensity for each statistical period, a joint probability distribution model of average wind speed and turbulence intensity is constructed. Discretize the joint probability distribution model to obtain multiple discrete sampling points of the wind condition envelope of the coverage point, and use the multiple discrete sampling points of the wind condition envelope of the coverage point as single-machine environmental feature parameter pairs; Calculate the area integral of each discrete sampling point in the joint probability distribution model, and use the area integral as the probability weight of the single-machine environment feature parameter pair.

[0012] This invention provides a method for assessing the lifespan of wind turbine main bearings. By constructing a joint probability distribution of measured wind speed and turbulence intensity and performing discretized sampling, rather than relying solely on a single annual average wind speed or industry standard value, it achieves accurate quantification of the microscopic operating environment of a single unit. This method can truly reveal the uneven lifespan distribution caused by environmental differences such as terrain complexity and wake effects within the wind farm, providing a scientific basis for individualized operation and maintenance of main bearings.

[0013] In one optional implementation, the basic rated life under each set of characteristic parameters is calculated using a weighted coupling method based on the probability weights of the single-unit environmental characteristic parameter pairs to obtain the comprehensive fatigue life of the main bearing of a single wind turbine; wherein, the formula for calculating the comprehensive fatigue life of the main bearing of a single wind turbine is:

[0014] in, This indicates the overall fatigue life of the main bearing of a single wind turbine unit. Indicates the first The probability weights corresponding to each discrete sampling point This represents the lifespan correction factor. Indicates the first The fatigue life of the main bearing corresponding to each discrete sampling point. This represents the total number of discrete sampling points.

[0015] This invention provides a method for assessing the lifespan of wind turbine main bearings. It employs a reciprocal weighted summation coupling method, which is based on the linear cumulative fatigue damage theory. By weighting and coupling the predicted lifespan under various characteristic operating conditions with probability weights, it can accurately assess the cumulative damage state of the main bearing throughout its entire lifespan. Compared to a simple arithmetic mean, this formula can more objectively reflect the decisive impact of low-life operating conditions (high-load operating conditions) on the overall service life, thereby significantly improving the conservatism and safety of lifespan prediction.

[0016] In one alternative implementation, it further includes: The reliability coefficient and system correction factor are obtained. The reliability coefficient and system correction factor are used to perform reliability correction and system correction on the comprehensive fatigue life of the main bearing of a single wind turbine, respectively, to obtain the corrected comprehensive fatigue life of the main bearing.

[0017] This invention provides a method for assessing the lifespan of wind turbine main bearings. By introducing reliability correction and system correction, it fully considers the multidimensional influencing factors in actual service conditions. Reliability correction provides quantitative support for differentiated maintenance decisions for different sites or units, meeting the assessment requirements for higher safety levels. System correction incorporates system variables such as lubrication and materials into the assessment system, enabling the prediction results to more sensitively reflect changes in the actual engineering environment. This multi-level correction mechanism not only improves the scientific nature of the assessment results but also provides a more solid and accurate data foundation for preventive maintenance and asset management throughout the entire life cycle of wind turbines.

[0018] In a second aspect, the present invention provides a wind turbine main bearing life assessment device, the device comprising: The model building module is used to build the main bearing life response surface model; the main bearing life response surface model is used to characterize the quantitative mapping relationship between wind load parameters composed of average wind speed and turbulence intensity and the main bearing life. The environmental feature quantification module is used to acquire measured wind parameter data of each wind turbine in the target wind farm, construct a joint probability distribution of average wind speed and turbulence intensity based on the measured wind parameter data, and discretize the joint probability distribution to obtain multiple pairs of single-unit environmental feature parameters and the probability weights of the single-unit environmental feature parameter pairs. The life determination module is used to input the main bearing life response surface model with multiple sets of single-machine environmental characteristic parameters and determine the basic rated life of the main bearing under each set of characteristic parameters. The weighted coupling module is used to perform weighted coupling calculations on the basic rated life under each set of characteristic parameters by using the probability weights of the single-machine environmental characteristic parameter pairs, so as to obtain the comprehensive fatigue life of the main bearing of a single wind turbine. The traversal module is used to traverse each wind turbine in the target wind farm and generate the life assessment result of the main bearing of the wind turbine based on the comprehensive fatigue life of the main bearing of a single wind turbine.

[0019] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the wind turbine main bearing life assessment method of the first aspect or any corresponding embodiment described above.

[0020] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the wind turbine main bearing life assessment method of the first aspect or any corresponding embodiment thereof.

[0021] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the wind turbine main bearing life assessment method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0022] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of a method for assessing the life of a wind turbine main bearing according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the second process of a wind turbine main bearing life assessment method according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the third process of a wind turbine main bearing life assessment method according to an embodiment of the present invention; Figure 5 This is a structural block diagram of a wind turbine main bearing life assessment device according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0026] As an optional application scenario of this invention, such as Figure 1 As shown, this wind turbine main bearing life assessment system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0027] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0028] For large wind farms with dozens or even hundreds of turbines, the micro-environmental characteristics (such as wind speed frequency distribution and turbulence intensity envelope) at each turbine site vary significantly due to topographic undulations, wake interference, and complex local meteorological effects. This non-uniformity of the micro-environment directly leads to differences in the main bearing load history, resulting in inconsistent fatigue life across the entire wind farm. Current wind turbine main bearing life assessment methods struggle to balance high assessment efficiency with precise quantification of individual turbines when dealing with large wind farms, making it impossible to provide accurate reliability difference maps and overall failure probability distributions for wind farm assets.

[0029] The relevant wind turbine main bearing life assessment methods adopt the calculation method of ISO 281 standard or the SCADA (Supervisory Control And Data Acquisition) data statistical analysis method.

[0030] The advantages of using the ISO 281 standard calculation method for main bearing life assessment are that it is based on mature bearing life theory and can provide relatively accurate life predictions for a single wind turbine under specific environmental conditions. However, the disadvantages are: high computational cost: generating massive load data through aeroelastic simulation and then performing statistical analysis results in a huge amount of computation, which is time-consuming and labor-intensive. For batch assessments of multiple units in a wind farm under various environmental conditions, the computational efficiency of the simulation method is low; sensitivity to input parameters: the calculation results of the ISO 281 model are highly sensitive to input loads, bearing parameters, temperature, etc., and these input parameters themselves have uncertainties; difficulty in directly reflecting the actual operating differences of the wind farm: although the simulation can cover various operating conditions, it is difficult to directly capture and utilize the micro-environmental differences (such as wind speed distribution, turbulence intensity, etc.) of each wind turbine in the actual wind farm.

[0031] SCADA data statistical analysis methods can extract measured wind parameters such as average wind speed and standard deviation by analyzing SCADA data from wind turbines. The advantages of this method are: it directly reflects the actual operation of the wind farm and can reflect the real environment and operating status; the disadvantages are: it is difficult to use directly for life calculations: SCADA data itself does not directly contain bearing load information, requiring complex mapping or auxiliary models for life assessment; and it does not fully utilize the differences in the wind farm environment: although SCADA data reflects the environment of a single unit, it is not effectively coupled with a life model to create a life "map" of the entire wind farm.

[0032] In summary, the relevant methods for assessing the lifespan of wind turbine main bearings have the following problems: While high-precision aeroelastic simulation is accurate, it cannot meet the efficiency requirements for batch assessment of the lifespan of wind farm-level main bearings, especially when performing reliability or sensitivity analysis, where its computational cost is too high.

[0033] The failure to fully integrate the impact of the actual operating environment of each wind turbine in the wind farm on the life of the main bearing makes it impossible to accurately quantify the differences in lifespan among the units within the wind farm.

[0034] There is a lack of a method that can effectively combine bearing load calculation with macroscopic wind farm environmental data to achieve refined and efficient wind farm main bearing life assessment.

[0035] This invention provides a method for assessing the lifespan of main bearings in wind turbines. By combining aeroelastic simulation and actual SCADA data, the lifespan of main bearings in each wind turbine in a wind farm is assessed efficiently and accurately. This invention can be used to assess the lifespan performance of main bearings in different wind farm layouts and with the same turbine model under specific environments, providing an important basis for the planning of new wind farms and the reassessment of existing wind farm assets.

[0036] According to an embodiment of the present invention, a method for assessing the life of a wind turbine main bearing is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0037] This embodiment provides a method for assessing the lifespan of a wind turbine main bearing, which can be used in the aforementioned terminal equipment. Figure 2 This is a flowchart of a wind turbine main bearing life assessment method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Construct the main bearing life response surface model; wherein, the main bearing life response surface model is used to characterize the quantitative mapping relationship between the wind load parameters composed of average wind speed and turbulence intensity and the main bearing life.

[0038] Among them, the main bearing life response surface model uses mean wind speed and turbulence intensity as input variables, and the main bearing as the input variable. L 10 The lifespan is a mathematical mapping model of the output response value, and the wind load environmental parameters of the main bearing are the 10-minute average wind speed and turbulence intensity.

[0039] Specifically, by performing envelope analysis on wind parameters at all points in the target wind farm, generating a simulation matrix using Design of Experiments (DOE), and combining the dynamic simulation results of multiple random seeds and multiple wind directions to perform function fitting, a high-precision life prediction model, namely the main bearing life response surface model, is established.

[0040] Step S202: Obtain measured wind parameter data of each wind turbine in the target wind farm, construct a joint probability distribution of average wind speed and turbulence intensity based on the measured wind parameter data, and discretize the joint probability distribution to obtain multiple pairs of single-unit environmental characteristic parameters and the probability weights of the single-unit environmental characteristic parameter pairs.

[0041] Specifically, by collecting long-term SCADA data of each unit in the target wind farm, the average wind speed and wind speed standard deviation for each statistical period are extracted and the real-time turbulence intensity is calculated. Subsequently, a joint probability distribution model of average wind speed and turbulence intensity for a single unit location is constructed and discretized sampling is performed. Each set of sampling points constitutes a "single unit environmental feature pair (wind speed, turbulence)," and the probability integral of the sampling point in the distribution model is its corresponding probability weight.

[0042] Step S203: Input multiple sets of single-machine environmental characteristic parameters into the main bearing life response surface model to determine the basic rated life of the main bearing under each set of characteristic parameters.

[0043] Specifically, the individual environmental feature pairs sampled in step S202 are used as input variables and input into the pre-constructed main bearing life response surface model. Using the mapping logic inside the model, the basic rated life of the main bearing corresponding to each set of environmental feature pairs is directly predicted and calculated. This avoids the computational process of performing massive time-series dynamic simulations on a single unit.

[0044] Step S204: The basic rated life under each set of characteristic parameters is calculated by weighted coupling using the probability weights of the single-machine environmental characteristic parameter pairs to obtain the comprehensive fatigue life of the main bearing of a single wind turbine.

[0045] Specifically, the frequency sequence (i.e. probability weight) obtained from SCADA statistics is weighted and integrated with the life values ​​of each working condition output by the main bearing life response surface model using the reciprocal weighted coupling formula. This process fully considers the impact of the frequency of different wind conditions on the long-term cumulative damage of the bearing.

[0046] Step S205: Traverse all wind turbine units in the target wind farm and generate the wind turbine main bearing life assessment result based on the comprehensive fatigue life of the main bearing of a single wind turbine unit.

[0047] Specifically, all turbines of the same model within the target wind farm are traversed, and steps S201-S204 are repeated based on the unique joint probability distribution of each turbine, ultimately achieving a differentiated and refined assessment of the lifespan of the main bearing of each wind turbine in the entire farm.

[0048] Furthermore, based on the comprehensive fatigue life of each unit in the entire wind farm obtained from the assessment, a life map of the wind farm's main bearings is generated. Using this life map, operation and maintenance personnel can implement condition-based predictive maintenance, prioritize inspections and preventive maintenance of units in high-risk areas (i.e., units with shorter remaining life), thereby extending the service life of the main bearings, significantly reducing operation and maintenance costs caused by unplanned shutdowns, and improving the overall economic benefits of the wind farm.

[0049] This embodiment provides a method for assessing the lifespan of wind turbine main bearings. By establishing a mapping relationship between high-precision simulation data and environmental parameters, this invention avoids the expensive and repetitive aeroelastic simulation of each wind turbine in the field, enabling the lifespan assessment of hundreds or even thousands of units to be completed in a very short time, significantly reducing computational costs. Simultaneously, by coupling measured SCADA data from individual turbine locations, it can accurately capture the load distribution characteristics caused by differences in the microenvironment within the field, providing individualized lifespan prediction results that more closely approximate engineering realities.

[0050] This embodiment provides a method for assessing the lifespan of a wind turbine main bearing, which can be used in the aforementioned terminal equipment. Figure 3 This is a flowchart of a wind turbine main bearing life assessment method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Construct the main bearing life response surface model; wherein, the main bearing life response surface model is used to characterize the quantitative mapping relationship between the wind load parameters composed of average wind speed and turbulence intensity and the main bearing life.

[0051] Specifically, step S301 includes: Step S3011: Obtain the measured wind parameter data of the wind turbine locations to be evaluated within the target wind farm, and determine the union of the average wind speed range and the turbulence intensity range of each turbine as the global envelope interval.

[0052] Step S3012: Distribute points evenly within the global envelope to generate a simulation condition matrix; wherein, the simulation condition matrix covers multiple combinations of wind load environmental parameters corresponding to the wind turbine locations; wherein, the combination of wind load environmental parameters is a combination of average wind speed and turbulence intensity under different simulation conditions.

[0053] Specifically, to ensure that the main bearing life response surface model can achieve accurate interpolation prediction across the entire field, the simulation conditions should be designed based on the union of measured wind parameters at all turbine locations in the target wind farm. This will comprehensively cover the operating envelope of the turbines under different average wind speeds and turbulence intensities. In other words, measured wind parameter data of all turbine locations to be evaluated within the target wind farm should be obtained, and the union of the average wind speed range and turbulence intensity range for each turbine should be determined as the global envelope interval. Experimental design methods should be used to uniformly sample within the global envelope interval to generate a simulation condition matrix, ensuring that the simulation samples cover all possible wind load environmental parameter combinations at all turbine locations.

[0054] For example, the wind speed range is set to (3–26 m / s, step size 1 m / s) and the turbulence intensity range is set to 0.05–0.25 (step size is set according to the coverage area). For each simulation condition combination (wind speed-turbulence pair), multiple random turbulence seeds (e.g., 12) and multiple inflow wind direction angles (e.g., -8°, 0°, 8°) are set to eliminate the influence of random load fluctuations on the evaluation results, forming a total of, for example, 36 sets of simulation sub-conditions.

[0055] Step S3013: Perform dynamic simulation on the target wind turbine based on the simulation condition matrix to obtain the radial load sequence and axial load sequence of the main bearing under each simulation condition.

[0056] Specifically, dynamic simulation of the target wind turbine is performed based on the simulation condition matrix; for each set of wind load environmental parameters, multiple sets of simulation sub-conditions are generated by setting a preset number of random seeds and multiple wind direction angles, and the radial load sequence and axial load sequence of the main bearing under each sub-condition are obtained.

[0057] Furthermore, a complete fully coupled dynamic model of the wind turbine is constructed using professional aeroelastic simulation software (such as HAWC2, Bladed, or OpenFAST). This model is then used to perform DLC1.2 (fatigue analysis under normal operating conditions) load simulation on the target wind turbine. This model covers the aeroelastic characteristics of the blades, the stiffness and damping characteristics of the transmission chain, the dynamics of the tower structure, and the control logic of the control system, thereby enabling the output of the dynamic load time series at the main bearing location.

[0058] Step S3014: Calculate the characteristic life response value of the main bearing based on the radial load sequence and the axial load sequence.

[0059] Specifically, for each 10-minute time-series load under each simulation condition, the equivalent dynamic load and corresponding basic rated life of the main bearing are calculated according to the ISO 281 standard. The ISO 281 standard calculation method provides a way to calculate the basic rated life of a bearing. The framework takes into account parameters such as the dynamic load capacity and equivalent dynamic load of the bearing. In the field of wind turbines, high-precision aeroelastic simulation software (such as HAWC2, Bladed, FAST, etc.) is usually used to calculate the complex load spectrum of the bearing, and then the data is input into the ISO 281 model for life assessment.

[0060] In this embodiment, a "10-minute time series" is set as the simulation statistical period, mainly based on the following core considerations: 1) Compliant with international industry standards: According to the IEC 61400-1 standard and general specifications of the wind power industry, the fatigue load analysis of wind turbine generators must use 10 minutes as the standard statistical duration.

[0061] 2) Capturing turbulent statistical characteristics: The 10-minute duration can cover the short-term random characteristics of wind speed dynamic fluctuations over time, and also meet the statistical stationarity requirements, ensuring that the obtained mean, standard deviation and turbulence intensity and other parameters are physically representative, thereby accurately identifying the load differences in different working conditions.

[0062] 3) Matching the definition of equivalent dynamic load for bearings: The basic rated life calculation of bearings is based on equivalent dynamic loads, which require integration calculation based on a statistically significant load sequence. The 10-minute sequence length ensures both the completeness of the load sample and matches the dynamic response scale of the bearing in actual service.

[0063] In some optional implementations, step S3014 above includes: Step a1: Calculate the instantaneous equivalent load at each sampling time based on the radial load sequence and axial load sequence of the main bearing under each simulation condition.

[0064] Specifically, the load time series corresponding to each simulation sub-condition is extracted, and the instantaneous equivalent load at each sampling moment is calculated based on the radial load series and axial load series of the main bearing.

[0065] Furthermore, for main bearings subjected to radial and axial loads, the instantaneous equivalent load... The calculation formula is as follows: (1) in, and These represent radial load and axial load, respectively. and These are the radial load factor and the axial load factor, respectively.

[0066] Step a2: Obtain the main bearing speed, simulation step size, and life index. Calculate the average equivalent dynamic load corresponding to each simulation sub-condition based on the instantaneous equivalent load, speed, and simulation step size.

[0067] Specifically, the average equivalent dynamic load for the entire simulation sub-condition (e.g., a 10-minute time period) is calculated by integrating and accumulating the instantaneous equivalent load, rotational speed, and simulation step size.

[0068] Furthermore, the average equivalent dynamic load over a 10-minute time series (Where k represents the number of 10-minute time series, k = 1, 2, ..., N) The calculation formula is: (2) in, This indicates the main bearing speed at each point in time. This represents the total number of simulation steps in a single 10-minute session (i.e.) ,in The simulation duration is 600 seconds. (Simulation time step or sampling interval) This is the life index (10 / 3 for roller bearings).

[0069] Step a3: Obtain the basic rated dynamic load of the main bearing, and calculate the basic rated life corresponding to each simulation sub-condition based on the average equivalent dynamic load.

[0070] Specifically, the basic rated life of the bearing This refers to the number of revolutions (or operating hours at constant speed) that 90% of the bearings in a group of identical ball or roller bearings can reach before reaching or exceeding the failure criterion.

[0071] Furthermore, The unit is 10 6 The formula for calculating the rotation is as follows: (3) When lifetime is measured in hours, it refers to the basic rated lifetime for each time series. The calculation formula is: (4) in, For the basic rated dynamic load, Life index (for ball bearings, For roller bearings, ), Rotational speed (rpm) This is the equivalent dynamic load (N).

[0072] Step a4: Average the basic rated life of multiple simulated sub-conditions under the same wind load environmental parameters to obtain the characteristic life response value of the main bearing.

[0073] Specifically, for each environmental condition node in the DOE design (a specific combination of average wind speed and turbulence intensity), the basic rated life of all sub-conditions is obtained by traversing a preset number of inflow wind directions and random turbulence seeds (e.g., a total of 36 sub-conditions). The average value is taken as the characteristic life response value of the main bearing under this working condition.

[0074] Furthermore, the basic rated life of 36 simulated sub-conditions generated by different combinations of random seeds (e.g., 12 groups) and different wind direction angles (e.g., 3 groups) under the same wind load environmental parameters was statistically analyzed. L 10 The arithmetic mean of the 36 basic rated lifespans is calculated, and this arithmetic mean is used as the characteristic life response value of the main bearing under the wind load parameter combination.

[0075] Step S3015: Using the average wind speed and turbulence intensity under different simulation conditions as input variables and the characteristic life response value of the main bearing as the target variable, a fitting is performed to construct the life response surface model of the main bearing.

[0076] Specifically, using the environmental parameter nodes (i.e., the combination of average wind speed and turbulence intensity) determined by the experimental design and their corresponding characteristic lifetime response values, an offline lifetime response surface model covering the entire wind condition envelope space is constructed through parametric mapping. During the construction process, multiple regression analysis, radial basis function (RBF) interpolation, or Kriging response surface methods are used to fit the discrete simulated lifetime values ​​into a continuous function surface, establishing a model with average wind speed and turbulence intensity as input variables and the basic rated lifetime of the main bearing as the reference value. L 10 This provides a high-precision mathematical mapping relationship for the output variables.

[0077] Furthermore, the main bearing life response surface model can not only accurately characterize the influence trend of environmental parameters on life, but also achieve rapid interpolation prediction of non-sampling point operating conditions, providing a computational basis for individualized life assessment of large-scale units across the entire field.

[0078] Step S302: Obtain measured wind parameter data for each wind turbine in the target wind farm. Based on the measured wind parameter data, construct a joint probability distribution of average wind speed and turbulence intensity. Discretize the joint probability distribution to obtain multiple pairs of individual turbine environmental characteristic parameters and their probability weights. For details, please refer to [link to relevant documentation]. Figure 2 Step S202 of the illustrated embodiment will not be described again here.

[0079] Step S303 involves inputting multiple sets of single-machine environmental characteristic parameters into the main bearing life response surface model to determine the basic rated life of the main bearing under each set of characteristic parameters. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0080] Step S304: Using the probability weights of the individual wind turbine environmental characteristic parameter pairs, a weighted coupled calculation is performed on the basic rated life under each set of characteristic parameters to obtain the comprehensive fatigue life of the main bearing of a single wind turbine. For details, please refer to [link to relevant documentation]. Figure 2 Step S204 of the illustrated embodiment will not be described again here.

[0081] Step S305: Iterate through all wind turbines within the target wind farm and generate a wind turbine main bearing life assessment result based on the comprehensive fatigue life of the main bearing of each individual wind turbine. For details, please refer to [link to details]. Figure 2 Step S205 of the illustrated embodiment will not be described again here.

[0082] This embodiment provides a method for assessing the lifespan of wind turbine main bearings. Based on the real-time synthesis of instantaneous equivalent loads from the radial and axial loads of the main bearing, it can accurately reconstruct the true three-dimensional stress state of the main bearing under aerodynamic forces, thus avoiding prediction deviations caused by single-direction load assessments from a physical perspective. By comprehensively considering instantaneous loads, real-time rotational speed, simulation step size, and lifespan index, the high-frequency fluctuating time-series loads are transformed into average equivalent dynamic loads reflecting the characteristics of 10-minute simulated sub-conditions. Compared to static simplified loads, this method can better capture the typical dynamic characteristics within the turbine's operating cycle. In terms of the calculation process, a hierarchical strategy of "first capturing sub-condition load characteristics, then performing multi-sub-condition lifespan statistical averaging" is adopted. This effectively preserves the load difference information under different random wind conditions and smooths out the interference caused by load spikes at a single moment through statistical methods. Finally, by using the arithmetic mean of lifetime based on multiple random seeds and inflow wind direction (such as 36 sub-conditions) as the characteristic lifetime response value, it can not only comprehensively reflect the global fatigue level of the main bearing under a specific combination of average wind speed and turbulence intensity, but also effectively eliminate the excessive influence of extreme gusts or abnormal seed signals on the evaluation results, significantly improving the robustness and reliability of the response surface model prediction results.

[0083] This embodiment provides a method for assessing the lifespan of a wind turbine main bearing, which can be used in the aforementioned terminal equipment. Figure 4 This is a flowchart of a wind turbine main bearing life assessment method according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps: Step S401: Construct the main bearing life response surface model; wherein, the main bearing life response surface model is used to characterize the quantitative mapping relationship between wind load parameters composed of average wind speed and turbulence intensity and the main bearing life. For details, please refer to... Figure 3 Step S301 of the illustrated embodiment will not be described again here.

[0084] Step S402: Obtain measured wind parameter data of each wind turbine in the target wind farm, construct a joint probability distribution of average wind speed and turbulence intensity based on the measured wind parameter data, and discretize the joint probability distribution to obtain multiple pairs of single-unit environmental characteristic parameters and the probability weights of the single-unit environmental characteristic parameter pairs.

[0085] Specifically, step S402 includes: Step S4021: Extract measured wind parameter data within a preset time period from the SCADA system of each wind turbine. The measured wind parameter data includes the average wind speed and wind speed standard deviation for each statistical period.

[0086] Specifically, for each wind turbine in the wind farm, the average wind speed within each statistical period (10 minutes) is extracted from its SCADA measured wind data. and wind speed standard deviation .

[0087] Step S4022: Calculate the real-time turbulence intensity based on the average wind speed and wind speed standard deviation for each statistical period.

[0088] Specifically, the quotient of the 10-minute standard deviation of wind speed and the 10-minute average wind speed... As turbulence intensity.

[0089] Step S4023: Based on the average wind speed and real-time turbulence intensity for each statistical period, construct a joint probability distribution model of average wind speed and turbulence intensity.

[0090] Specifically, the SCADA measured wind data of each wind turbine were fitted with a joint probability distribution of wind parameters. That is, based on the full average wind speed and real-time turbulence intensity data, a joint probability distribution model of average wind speed and turbulence intensity reflecting the microclimate characteristics of the single turbine location was constructed using statistical fitting methods.

[0091] Furthermore, using kernel density estimation or multivariate probability distribution fitting methods, a two-dimensional joint probability distribution model of "mean wind speed-turbulence intensity" is constructed for each wind turbine to reflect the microclimate characteristics of its specific turbine location. Compared with one-dimensional wind speed distribution, this model can more accurately quantify the fluctuation characteristics of turbulence intensity under different wind speed levels.

[0092] Step S4024: Discretize the joint probability distribution model to obtain multiple discrete sampling points of the wind condition envelope of the coverage point, and use the multiple discrete sampling points of the wind condition envelope of the coverage point as single-machine environmental feature parameter pairs.

[0093] Specifically, the joint probability distribution model is discretized and sampled to obtain the wind envelope covering the location. A set of discrete sampling points is used as a pair of characteristic parameters for a single-machine environment.

[0094] Step S4025: Calculate the area integral of each discrete sampling point in the joint probability distribution model, and use the area integral as the probability weight of the single-machine environment feature parameter pair.

[0095] Specifically, the above two-dimensional joint probability distribution model is discretized and sampled to obtain a representation of the unit's service environment. Each individual environmental feature pair (i.e., discrete combinations of wind speed and turbulence intensity) is paired, and the probability integral (i.e., the corresponding grid area integral) of each feature pair in the distribution model is calculated, which serves as the probability weight for the corresponding environmental feature pair. .

[0096] Step S403 involves inputting multiple sets of single-machine environmental characteristic parameters into the main bearing life response surface model to determine the basic rated life of the main bearing under each set of characteristic parameters. For details, please refer to [link to relevant documentation]. Figure 3 Step S303 of the illustrated embodiment will not be described again here.

[0097] Step S404: The basic rated life under each set of characteristic parameters is calculated by weighted coupling using the probability weights of the single-machine environmental characteristic parameter pairs to obtain the comprehensive fatigue life of the main bearing of a single wind turbine.

[0098] Specifically, based on the Palmgren-Miner linear damage accumulation criterion (Miner's criterion, a classic theory in fatigue mechanics used to determine whether a material or structure will fail under variable amplitude cyclic loading, its core is to quantify the total fatigue damage by linearly superimposing the damage amounts under each load level to determine the risk of fatigue failure), the comprehensive basic rated life of the wind turbine main bearing under the full wind speed envelope is calculated. The formula for calculating the comprehensive basic rated life of the main bearing is as follows: (5) in, This indicates the overall basic rated life of the main bearing of a single wind turbine unit; Indicates the first The probability weights corresponding to the group environmental features (obtained by discretization of the two-dimensional joint probability distribution); This represents the lifespan correction factor; Indicates the first The average basic rated lifetime value is predicted using a response surface model under the single-unit environmental characteristics. This represents the total number of single-machine environment feature pairs.

[0099] Furthermore, the reliability coefficient and system correction factor are obtained, and the reliability coefficient and system correction factor are used to perform reliability correction and system correction on the comprehensive fatigue life of the main bearing of a single wind turbine, respectively, to obtain the corrected comprehensive fatigue life of the main bearing.

[0100] Furthermore, based on the target wind farm's pre-set maintenance strategy and reliability requirements, a corresponding reliability coefficient (such as a correction value for 95% or 99% reliability requirements) is selected to adjust the preliminary calculated comprehensive fatigue life. Adjustments will be made.

[0101] Furthermore, taking into account systematic factors such as the lubrication conditions of the main bearing, the fatigue limit of the material, the influence of contaminants, and the actual assembly environment, a system correction factor is introduced to further verify the life results.

[0102] Furthermore, by adjusting the lifespan correction factor The value of enables evaluation across different dimensions: when When, the comprehensive basic rated life of the main bearing is calculated; when At that time, a reliability correction factor was obtained. The overall basic rated life of the main bearing; when At that time, the final life of the main bearing was calculated after comprehensive consideration of environmental, lubrication and reliability corrections.

[0103] Step S405: Iterate through all wind turbines within the target wind farm and generate a wind turbine main bearing life assessment result based on the comprehensive fatigue life of the main bearing of each individual wind turbine. For details, please refer to [link to details]. Figure 3 Step S305 of the illustrated embodiment will not be described again here.

[0104] This embodiment extracts average wind speed and turbulence intensity, reflecting the microclimate characteristics of individual wind turbines, from SCADA measured wind data of each turbine, and constructs a two-dimensional joint probability distribution model to achieve accurate quantification of the service environment of individual turbines. Compared with simply applying industry standard values, this method can truly capture the load distribution differences within the wind farm caused by terrain features, wake interference, etc., making the assessment results closer to engineering reality and revealing the true uneven lifespan distribution among turbines within the wind farm. In addition, by introducing a multi-level correction mechanism, the comprehensive basic rated lifespan of the main bearing is respectively corrected for reliability and system, allowing for flexible adjustment of the assessment dimensions according to the operation and maintenance strategies of different sites. The above-mentioned multi-factor coupled correction method not only provides accurate lifespan prediction support for turbines with different reliability requirements, but also provides a corrected lifespan assessment system that conforms to complex service environments, laying a solid technical foundation for reliability-based predictive maintenance decisions for wind turbines.

[0105] The following specific embodiment illustrates the specific steps of a method for assessing the life of a wind turbine main bearing.

[0106] Example 1: The lifespan of the main bearings of wind turbines in a wind farm with 100 units was calculated. The specific evaluation steps of the wind turbine main bearing lifespan assessment method are as follows: Step 1: Main Bearing Lifetime response surface model construction (offline mechanism modeling): The simulation platform uses HAWC2 aeroelastic simulation software to build a complete dynamic model of the wind turbine, covering blade aerodynamic characteristics, transmission chain stiffness and control system.

[0107] Main bearing parameters: Taking a certain unit as an example, the main bearing is equivalent to a FAG 230 / 800 double row spherical roller bearing with a basic rated dynamic load C=3500 kN.

[0108] Full-factor operating condition matrix: Average wind speed range: m / s, step size 1 m / s; turbulence intensity ( ): [0.05–0.25], step size 0.01; randomness handling: each "wind speed-turbulence" combination is configured with 3 inflow wind direction angles and 12 random turbulence seeds, and a total of 17388 standard 10-minute time series simulation calculations are performed.

[0109] Equivalent load and node life calculation: Extract the radial and axial loads of the main bearing from the simulation output, and calculate the equivalent dynamic load for each 10-minute time series; then, by averaging the loads under different seeds and wind directions, the basic rated life of the main bearing under this working condition node is obtained.

[0110] Generating the response surface: Establishing a three-dimensional response surface function This model stores the sensitivity characteristics of the main bearing life to environmental parameters, eliminating the burden of real-time calculation.

[0111] Step 2: Quantification of single-machine micro-environment characteristics (online data-driven): Data preprocessing: Retrieve the three-year average SCADA data of all units in the target wind farm over three years, and remove outages, underpowered units, and missing data points.

[0112] Joint probability distribution fitting: For each machine location, based on its measured 10-minute average wind speed and turbulence intensity, a two-dimensional joint probability distribution model of "average wind speed-turbulence intensity" is fitted and generated.

[0113] Discretize the model to generate pairs of environmental features representing the location and their probability weights. .

[0114] Results Export: Generate a standalone environment characteristic table.

[0115] Step 3, Lifetime Map Generation (Data-Model Fusion Application): Unit lifetime mapping: By inputting the environmental characteristics of each unit into the response surface model, the basic lifetime corresponding to that unit can be quickly retrieved. .

[0116] Inverse weighted coupling: combining probability weights By coupling with lifespan, the comprehensive basic rated lifespan of each machine position is obtained. .

[0117] Lifetime correction calculation: Reliability Correction: Introducing a reliability correction factor The lifetime is mapped under different failure probabilities (such as 1% or 5%) by a three-parameter Weibull distribution.

[0118] System Correction: Considering the effect of the actual operating temperature of the main bearing (feedback from SCADA) on the viscosity of Klüberplex BEM41-301 grease, calculate the system correction factor. .

[0119] This embodiment also provides a wind turbine main bearing life assessment device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0120] This embodiment provides a device for assessing the lifespan of a wind turbine main bearing, such as... Figure 5 As shown, it includes: Model building module 501 is used to build the main bearing life response surface model; wherein, the main bearing life response surface model is used to characterize the quantitative mapping relationship between wind load parameters composed of average wind speed and turbulence intensity and main bearing life. The environmental feature quantification module 502 is used to acquire measured wind parameter data of each wind turbine in the target wind farm, construct a joint probability distribution of average wind speed and turbulence intensity based on the measured wind parameter data, and discretize the joint probability distribution to obtain multiple pairs of single-unit environmental feature parameters and the probability weights of the single-unit environmental feature parameter pairs. The life determination module 503 is used to input the main bearing life response surface model with multiple sets of single-machine environmental characteristic parameters and determine the basic rated life of the main bearing under each set of characteristic parameters. The weighted coupling module 504 is used to perform weighted coupling calculation on the basic rated life under each set of characteristic parameters by using the probability weights of the single-machine environmental characteristic parameter pairs, so as to obtain the comprehensive fatigue life of the main bearing of a single wind turbine. Traversal module 505 is used to traverse each wind turbine in the target wind farm and generate the life assessment result of the main bearing of the wind turbine based on the comprehensive fatigue life of the main bearing of a single wind turbine.

[0121] In some alternative implementations, the model building module 501 includes: The acquisition unit is used to acquire measured wind parameter data of the wind turbine locations to be evaluated within the target wind farm, and to determine the union of the average wind speed range and the turbulence intensity range of each turbine as the global envelope interval. The generation unit is used to uniformly distribute points within the global envelope to generate a simulation condition matrix. The simulation condition matrix covers multiple combinations of wind load environmental parameters corresponding to the wind turbine locations. The wind load environmental parameter combinations include the average wind speed and turbulence intensity under different simulation conditions. The simulation unit is used to perform dynamic simulation of the target wind turbine based on the simulation condition matrix, and obtain the radial load sequence and axial load sequence of the main bearing under each simulation condition. The first calculation unit is used to calculate the characteristic life response value of the main bearing based on the radial load sequence and the axial load sequence; The fitting unit is used to fit the average wind speed and turbulence intensity under different simulation conditions as input variables and the characteristic life response value of the main bearing as the target variable to construct the life response surface model of the main bearing.

[0122] In some alternative implementations, the first computing unit includes: The first calculation subunit is used to calculate the instantaneous equivalent load at each sampling time based on the radial load sequence and axial load sequence of the main bearing under each simulation condition. The second calculation subunit is used to obtain the main bearing speed, simulation step size and life index, and calculate the average equivalent dynamic load corresponding to each simulation sub-condition based on the instantaneous equivalent load, speed and simulation step size. The third calculation subunit is used to obtain the basic rated dynamic load of the main bearing and calculate the basic rated life corresponding to each simulation sub-condition based on the average equivalent dynamic load. The fourth calculation subunit is used to average the basic rated life corresponding to multiple simulation sub-conditions under the same wind load environmental parameters to obtain the characteristic life response value of the main bearing.

[0123] In some alternative implementations, the environmental feature quantification module 502 includes: The extraction unit is used to extract measured wind parameter data within a preset time period from the SCADA system of each wind turbine. The measured wind parameter data includes the average wind speed and wind speed standard deviation for each statistical period. The second calculation unit is used to calculate the real-time turbulence intensity based on the average wind speed and wind speed standard deviation for each statistical period. The building unit is used to construct a joint probability distribution model of average wind speed and turbulence intensity based on the average wind speed and real-time turbulence intensity for each statistical period. The sampling unit is used to discretize the joint probability distribution model to obtain multiple discrete sampling points of the wind condition envelope of the coverage point, and use the multiple discrete sampling points of the wind condition envelope of the coverage point as single-machine environmental feature parameter pairs. The third calculation unit is used to calculate the area integral of each discrete sampling point in the joint probability distribution model, and uses the area integral as the probability weight of the single-machine environment feature parameter pair.

[0124] In some optional implementations, the formula for calculating the overall fatigue life of the typhoon generator main bearing in the weighted coupling module 504 is as follows:

[0125] in, This indicates the overall fatigue life of the main bearing of a single wind turbine unit. Indicates the first The probability weights corresponding to each discrete sampling point This represents the lifespan correction factor. Indicates the first The fatigue life of the main bearing corresponding to each discrete sampling point. This represents the total number of discrete sampling points.

[0126] In some alternative implementations, it also includes: The correction module is used to obtain the reliability coefficient and system correction factor. The reliability coefficient and system correction factor are used to perform reliability correction and system correction on the comprehensive fatigue life of the main bearing of a single wind turbine, respectively, to obtain the corrected comprehensive fatigue life of the main bearing.

[0127] The wind turbine main bearing life assessment device provided in this embodiment of the invention can execute the wind turbine main bearing life assessment method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0128] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0129] The following is a detailed reference. Figure 6 This diagram illustrates a suitable structural design for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0130] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0131] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the wind turbine main bearing life assessment method of the embodiments of the present invention.

[0132] Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0133] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, it implements the wind turbine main bearing life assessment method shown in the above embodiments.

[0134] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0135] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method of wind turbine main bearing lifetime assessment, characterized in that, The method includes: A main bearing life response surface model is constructed; wherein, the main bearing life response surface model is used to characterize the quantitative mapping relationship between wind load parameters composed of average wind speed and turbulence intensity and main bearing life; The measured wind parameter data of each wind turbine in the target wind farm are obtained. Based on the measured wind parameter data, a joint probability distribution of average wind speed and turbulence intensity is constructed. The joint probability distribution is discretized and sampled to obtain multiple pairs of single-unit environmental characteristic parameters and the probability weights of the single-unit environmental characteristic parameter pairs. The basic rated life of the main bearing is determined by inputting multiple sets of single-machine environmental characteristic parameters into the main bearing life response surface model for each set of characteristic parameters. The basic rated life under each set of characteristic parameters is calculated by weighted coupling using the probability weights of the single-machine environmental characteristic parameter pairs to obtain the comprehensive fatigue life of the main bearing of a single wind turbine. The wind turbine generator sets within the target wind farm are traversed, and the life assessment results of the main bearings of the wind turbine generator sets are generated based on the comprehensive fatigue life of the main bearings of each individual wind turbine generator set.

2. The method of claim 1, wherein, The construction of the main bearing life response surface model includes: Obtain measured wind parameter data of the wind turbine locations to be evaluated within the target wind farm, and determine the union of the average wind speed range and the turbulence intensity range for each turbine as the global envelope interval. Within the global envelope, points are evenly distributed to generate a simulation condition matrix; wherein, the simulation condition matrix covers multiple combinations of wind load environmental parameters corresponding to the wind turbine locations; wherein, the combination of wind load environmental parameters includes a combination of average wind speed and turbulence intensity under different simulation conditions. Based on the simulation condition matrix, dynamic simulation of the target wind turbine is performed to obtain the radial load sequence and axial load sequence of the main bearing under each simulation condition. The characteristic life response value of the main bearing is calculated based on the radial load sequence and the axial load sequence; Using the average wind speed and turbulence intensity under different simulation conditions as input variables, and the characteristic life response value of the main bearing as the target variable, a life response surface model of the main bearing is constructed by fitting.

3. The method of claim 2, wherein, The calculation of the main bearing characteristic life response value based on the radial load sequence and the axial load sequence includes: The instantaneous equivalent load at each sampling moment is calculated based on the radial load sequence and axial load sequence of the main bearing under each simulation condition. Obtain the main bearing speed, simulation step size, and life index, and calculate the average equivalent dynamic load corresponding to each simulation sub-condition based on the instantaneous equivalent load, speed, and simulation step size; Obtain the basic rated dynamic load of the main bearing, and calculate the basic rated life corresponding to each simulation sub-condition based on the average equivalent dynamic load. The basic rated life corresponding to multiple simulated sub-conditions under the same wind load environmental parameters is averaged to obtain the characteristic life response value of the main bearing.

4. The method of claim 1, wherein, The process involves acquiring measured wind parameter data for each wind turbine in the target wind farm, constructing a joint probability distribution of average wind speed and turbulence intensity based on the measured wind parameter data, and discretizing the joint probability distribution to obtain multiple pairs of individual turbine environmental characteristic parameters and their probability weights, including: The measured wind parameter data for a preset time period are extracted from the SCADA system of each wind turbine. The measured wind parameter data includes the average wind speed and wind speed standard deviation for each statistical period. Real-time turbulence intensity is calculated based on the average wind speed and wind speed standard deviation for each statistical period. Based on the average wind speed and the real-time turbulence intensity for each statistical period, a joint probability distribution model of the average wind speed and turbulence intensity is constructed. Discretize the joint probability distribution model to obtain multiple discrete sampling points of the wind condition envelope of the coverage point, and use the multiple discrete sampling points of the wind condition envelope of the coverage point as the single-machine environmental feature parameter pair; Calculate the area integral of each discrete sampling point in the joint probability distribution model, and use the area integral as the probability weight of the single-machine environment feature parameter pair.

5. The method of claim 1, wherein, The basic rated life under each set of characteristic parameters is calculated by weighted coupling using the probability weights of the single-unit environmental characteristic parameter pairs to obtain the comprehensive fatigue life of the main bearing of a single wind turbine; wherein, the calculation formula for the comprehensive fatigue life of the main bearing of a single wind turbine is: in, This indicates the overall fatigue life of the main bearing of a single wind turbine unit. Indicates the first The probability weights corresponding to each discrete sampling point This represents the lifespan correction factor. Indicates the first The fatigue life of the main bearing corresponding to each discrete sampling point. This represents the total number of discrete sampling points.

6. The method according to claim 1, characterized in that, Also includes: The reliability coefficient and system correction factor are obtained. The reliability coefficient and system correction factor are used to perform reliability correction and system correction on the comprehensive fatigue life of the main bearing of the single wind turbine, respectively, to obtain the corrected comprehensive fatigue life of the main bearing.

7. A device for assessing the lifespan of a wind turbine main bearing, characterized in that, The device includes: The model building module is used to build a main bearing life response surface model; wherein, the main bearing life response surface model is used to characterize the quantitative mapping relationship between wind load parameters composed of average wind speed and turbulence intensity and main bearing life. The environmental feature quantification module is used to acquire measured wind parameter data of each wind turbine in the target wind farm, construct a joint probability distribution of average wind speed and turbulence intensity based on the measured wind parameter data, and discretize the joint probability distribution to obtain multiple pairs of single-unit environmental feature parameters and the probability weights of the single-unit environmental feature parameter pairs. The life determination module is used to input multiple sets of single-machine environmental characteristic parameters into the main bearing life response surface model to determine the basic rated life of the main bearing under each set of characteristic parameters. The weighted coupling module is used to perform weighted coupling calculation on the basic rated life under each set of characteristic parameters by using the probability weights of the single-machine environmental characteristic parameter pairs, so as to obtain the comprehensive fatigue life of the main bearing of a single wind turbine. The traversal module is used to traverse each wind turbine in the target wind farm and generate a wind turbine main bearing life assessment result based on the comprehensive fatigue life of the main bearing of the individual wind turbine.

8. An electronic device, characterized in that, include: A memory and a processor are interconnected, the memory stores computer instructions, and the processor executes the computer instructions to perform the wind turbine main bearing life assessment method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the wind turbine main bearing life assessment method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes computer instructions for causing a computer to execute the wind turbine main bearing life assessment method according to any one of claims 1 to 6.

Images