Method and system for predicting service life of wind power equipment based on multi-source data and acceleration effect

Abstract

The invention provides a wind power equipment service life prediction method and system based on multi-source data and an acceleration effect, and relates to the field of wind power equipment service life prediction.The wind power equipment service life prediction method comprises the steps that operation environment data and degradation fault information of wind power equipment are collected, and a wind power equipment basic performance degradation model is constructed; performing mechanism analysis on blade crack propagation data in the degradation fault information, and constructing a first wind power equipment accelerated degradation model based on a primary acceleration stress, a secondary acceleration stress and a comprehensive acceleration equation; constructing a wind power equipment state multi-source data set based on the degradation fault information, and performing data updating on the first wind power equipment accelerated degradation model according to the wind power equipment state multi-source data set, a Bayesian function and an EM algorithm to obtain a second wind power equipment accelerated degradation model; and according to the degradation process multi-condition hypothesis function and the second wind power equipment accelerated degradation model, a wind power equipment multi-stage degradation process model is constructed to predict the residual life of the wind power equipment, the self-adaptive capability of the accelerated degradation model is enhanced, and the prediction accuracy of the residual life of the wind power equipment is improved.

Description

Technical Field

[0001] The present invention relates to the field of wind power equipment life prediction, and in particular to a wind power equipment life prediction method and system based on multi-source data and acceleration effect. Background Art

[0002] Social progress and development cannot be separated from the support of new energy power. However, the contradiction between the growing energy demand and increasingly severe environmental conditions and the increasingly depleted non-renewable energy reserves has become increasingly acute. Since the beginning of the 21st century, energy security issues and the new energy revolution have attracted widespread attention from the international community. In order to meet the demand for energy supply and achieve sustainable energy development, the transformation of the fossil energy system to a sustainable energy system has become a basic trend in energy development in countries around the world. As one of the earliest developed and most important renewable energy sources in the comprehensive energy system, wind energy has great potential in greenhouse gas emission reduction due to its rich storage, renewable, clean and pollution-free characteristics. It has become the mainstream direction of global renewable energy development and an important force in promoting industrial upgrading and driving the adjustment of the energy system.

[0003] A Chinese patent with publication number CN117743939A discloses a method, system and electronic device for predicting the remaining useful life of wind power equipment, the method comprising obtaining current monitoring data of the wind power equipment to be predicted; determining the remaining useful life of the wind power equipment to be predicted using a remaining useful life prediction model based on the current monitoring data; wherein the remaining useful life prediction model is obtained by training a parallel multi-scale fusion network using a training data set; the training data set includes processed monitoring data of the training wind power equipment and corresponding remaining useful life labels. However, the method provided in the above application assumes that the performance of the unit gradually deteriorates over time, and does not take into account new operating conditions and data changes. It is difficult to accurately describe the evolution law of the actual degradation of the wind power equipment, resulting in inaccurate prediction of the remaining useful life of the wind power equipment. Therefore, it is very necessary to provide a method and system for predicting the life of wind power equipment based on multi-source data and acceleration effect to improve the accuracy of predicting the remaining useful life of wind power equipment. Summary of the invention

[0004] In view of this, the present invention proposes a method and system for predicting the life of wind power equipment based on multi-source data and acceleration effect. By systematically collecting and analyzing the operating environment data and degradation fault information of wind power equipment, combined with the second wind power equipment accelerated degradation model and multi-condition hypothesis function, it helps to improve the prediction accuracy of the remaining life of wind power equipment.

[0005] The present invention provides a method for predicting the life of wind power equipment based on multi-source data and acceleration effect, the method comprising:

[0006] Collecting operating environment data and degradation fault information of wind power equipment, and building a basic performance degradation model of wind power equipment based on the operating environment data and the degradation fault information;

[0007] Performing a mechanism analysis on the blade crack growth data in the degradation fault information, respectively obtaining the main acceleration stress and the secondary acceleration stress of the wind power equipment, and constructing a first wind power equipment accelerated degradation model based on the main acceleration stress, the secondary acceleration stress and the comprehensive acceleration equation;

[0008] Constructing a wind power equipment state multi-source data set based on degradation fault information, and updating the first wind power equipment accelerated degradation model according to the wind power equipment state multi-source data set, Bayesian function and EM algorithm to obtain a second wind power equipment accelerated degradation model;

[0009] According to the multi-condition hypothesis function of the degradation process and the second accelerated degradation model of wind power equipment, a multi-stage degradation process model of wind power equipment is constructed to predict the remaining life of the wind power equipment.

[0010] On the basis of the above technical solution, preferably, the basic performance degradation model of wind power equipment is constructed based on the operating environment data and the degradation fault information, specifically including:

[0011] Determine the main influencing indicators of wind power equipment performance degradation according to the operating environment data and the degradation failure mechanism and failure form in the degradation fault information;

[0012] Based on the main influencing indicators, the nonlinear Gamma correction function and the blade crack growth data in the degradation fault information, a basic performance degradation model of wind power equipment is constructed.

[0013] On the basis of the above technical solution, preferably, after constructing the basic performance degradation model of wind power equipment, the method further includes:

[0014] Calculate the basic performance degradation model of the wind power equipment based on the MAE index to obtain the mean absolute error of the basic performance degradation model of the wind power equipment;

[0015] Calculating the basic performance degradation model of the wind power equipment based on the MSE index to obtain the mean square error of the basic performance degradation model of the wind power equipment;

[0016] Calculating the basic performance degradation model of the wind power equipment based on the MAPE index, the average absolute error percentage of the basic performance degradation model of the wind power equipment;

[0017] The distance between the training sample deviation and the test sample deviation in the basic performance degradation model of the wind power equipment is calculated based on the DIC criterion.

[0018] More preferably, the expression of the comprehensive acceleration equation is:

[0019]

[0020] Among them, R(K,σ t ) represents the comprehensive acceleration equation, K represents the temperature in the service environment of the wind power equipment, σ t represents tensile stress, γ0 represents the comprehensive accelerated stress index value, E a represents the activation energy, γ1 represents the first accelerating stress coefficient, γ2 represents the second accelerating stress coefficient, and κ represents the Boltzmann constant.

[0021] More preferably, the wind power equipment status multi-source data set includes degradation cause data and degradation result data, the degradation cause data includes temperature monitoring quantity, stress intensity and corrosive medium content, and the degradation result data includes crack extension length, material residual strength and elongation.

[0022] More preferably, updating the data of the first wind power equipment accelerated degradation model according to the wind power equipment state multi-source data set, the Bayesian function and the EM algorithm specifically includes:

[0023] Based on the prior information and sample information in the wind power equipment state multi-source data set, the degradation parameters in the first wind power equipment accelerated degradation model are updated in real time by using a Bayesian function to obtain posterior distribution parameters of the degradation parameters;

[0024] The maximum likelihood estimate of the degradation parameters in the first wind power equipment accelerated degradation model is obtained through iteration of the EM algorithm, and the remaining parameter update values ​​corresponding to the maximum likelihood estimate in the first wind power equipment accelerated degradation model are calculated according to a parameter update function.

[0025] More preferably, the expression of the parameter update function is:

[0026]

[0027] Among them, μ β Indicates that the drift coefficient follows the mean of the normal distribution, k represents the number of iterations, n represents the number of products, and a i represents the mean of the posterior distribution of the i-th monomer, Indicates that the variance of the drift coefficient follows a normal distribution, b i represents the variance of the posterior distribution of the i-th monomer, σ 2 The variance of the diffusion coefficient follows a normal distribution, Δt j represents the time interval, Δx ij Indicates that from time t j-1 At time tj The degradation increment of the ith monomer in the process, m represents the number of degradation data.

[0028] More preferably, the expression of the multi-condition hypothesis function of the degradation process is:

[0029]

[0030] Among them, X(t) represents the multi-condition hypothesis function of the degradation process, X(0) represents the initial degradation amount, μ l represents the drift parameter in the lth degradation stage, ∑N l (μ l ,σ l 2 ) is the total degradation amount of the product in the lth degradation stage, σ l 2 It represents the variance of the diffusion coefficient in the lth degradation stage that follows the normal distribution.

[0031] In a second aspect of the present application, a wind power equipment life prediction system based on multi-source data and acceleration effect is provided, wherein the wind power equipment life prediction system comprises an information acquisition module, a degradation integration module and a life prediction module, wherein:

[0032] The information collection module is used to collect operating environment data and degradation fault information of the wind power equipment, and to construct a basic performance degradation model of the wind power equipment based on the operating environment data and the degradation fault information;

[0033] The degradation integration module is used to perform a mechanism analysis on the blade crack extension data in the degradation fault information, respectively obtain the main acceleration stress and the secondary acceleration stress of the wind power equipment, and construct a first wind power equipment accelerated degradation model based on the main acceleration stress, the secondary acceleration stress and the comprehensive acceleration equation; construct a wind power equipment state multi-source data set based on the degradation fault information, and update the data of the first wind power equipment accelerated degradation model according to the wind power equipment state multi-source data set, the Bayesian function and the EM algorithm to obtain a second wind power equipment accelerated degradation model;

[0034] The life prediction module is used to construct a multi-stage degradation process model of wind power equipment according to the multi-condition hypothesis function of the degradation process and the second wind power equipment accelerated degradation model to predict the remaining life of the wind power equipment.

[0035] In a third aspect of the present application, an electronic device is provided, comprising a processor, a memory, a user interface and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory.

[0036] The wind power equipment life prediction method and system based on multi-source data and acceleration effect provided by the present invention has the following beneficial effects compared with the prior art:

[0037] (1) By systematically collecting and analyzing the operating environment data and degradation fault information of wind power equipment, the basic performance degradation model constructed can reflect the actual performance changes of the equipment under different environmental conditions, thereby improving the accuracy and practicality of the model. At the same time, through the mechanism analysis of blade crack propagation data, the main acceleration stress and secondary acceleration stress that affect crack propagation can be effectively identified. The Bayesian function and EM algorithm are used to dynamically update the accelerated degradation model to enhance the adaptive ability of the accelerated degradation model. Combined with the second wind power equipment accelerated degradation model and the multi-condition hypothesis function, it is helpful to improve the prediction accuracy of the remaining life of wind power equipment.

[0038] (2) The model performance is comprehensively evaluated using multiple indicators such as MAE, MSE, MAPE and DIC, so that the analysis of prediction quality is not limited to a single indicator, which enhances the depth and effectiveness of the result interpretation. Combining the calculation results of different indicators, it supports the continuous monitoring and optimization of the wind power equipment performance degradation model, ensuring that the model can adapt to new operating conditions and data changes in a timely manner, thereby enhancing its prediction ability.

[0039] (3) By using the Bayesian function to update the degradation parameters in real time, the model can be continuously adjusted according to the new observation data during the operation of the equipment, which significantly enhances the flexibility and response speed of the model to changes in the operating environment, thereby reducing the prediction errors caused by environmental changes. The EM algorithm can effectively handle missing values ​​in the sample data, ensuring that even when the data is incomplete, the model can still give reasonable parameter estimates and state assessments, thereby improving the integrity and reliability of data processing. At the same time, the application of the parameter update function enables the model to adjust related parameters other than the degradation parameters, which enhances the overall coordination of the model and makes the relationship between the parameters more accurate, thereby improving the prediction ability of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A schematic flow chart of a method for predicting the life of wind power equipment based on multi-source data and acceleration effect provided by the present invention;

[0042] Figure 2A schematic diagram of the performance degradation simulation results of the basic performance degradation model of wind power equipment provided by the present invention;

[0043] Figure 3 A schematic diagram of the framework of the wind power equipment life prediction system provided by the present invention;

[0044] Figure 4 This is a schematic structural diagram of an electronic device provided by the present invention.

[0045] Explanation of the accompanying drawings: 1. Wind power equipment life prediction system; 11. Information acquisition module; 12. Degradation integration module; 13. Life prediction module; 2. Electronic device; 21. Processor; 22. Communication bus; 23. User interface; 24. Network interface; 25. Memory. DETAILED DESCRIPTION

[0046] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] The present invention discloses a wind power equipment life prediction method based on multi-source data and acceleration effect, referring to Figure 1 The method includes steps S1 to S4.

[0048] Step S1, collecting operating environment data and degradation fault information of wind power equipment, and constructing a basic performance degradation model of wind power equipment based on the operating environment data and degradation fault information.

[0049] In this step, the operating environment data includes environmental parameter data such as wind speed, wind direction, temperature, humidity, and vibration. The above operating environment data can be monitored and recorded in real time using sensor equipment. The degradation fault information can be collected by establishing a sound fault information database to record various degradation failure modes and failure forms, such as blade crack extension, gear wear, etc. Analyze the fault information, determine the main degradation failure mechanism, such as fatigue, corrosion, wear, etc., and collect detailed information on the failure process, such as the time of failure, failure degree, and failure cause.

[0050] This step also includes steps S11 to S12.

[0051] Step S11, determining the main influencing indicators of the performance degradation of the wind power equipment according to the operating environment data and the degradation failure mechanism and failure form in the degradation fault information.

[0052] In this step, based on the collected degradation fault information, identify the main degradation failure modes in the degradation fault information, such as blade fatigue cracks, gear wear, bearing failure, etc. Analyze the physical mechanism of each failure mode, such as stress concentration, surface wear, material fatigue, etc. For each failure mode, determine the key operating environment factors that affect its occurrence and development, such as wind, vibration, temperature, humidity, etc. Through experimental analysis or engineering experience, determine the quantitative influence of these environmental factors on the failure mechanism. Comprehensively analyze the key influencing factors in various failure modes and screen out the indicators that are most sensitive to overall performance degradation. For example, for blade fatigue cracks, wind and vibration may be the most important influencing indicators, while for gear wear, temperature and load may be more critical.

[0053] Step S12: constructing a basic performance degradation model of wind power equipment based on the main influencing indicators, the nonlinear Gamma correction function and the blade crack growth data in the degradation fault information.

[0054] In this step, when the nonlinear Gamma correction function satisfies the following conditions,

[0055] 1) X(0) = 0;

[0056] 2) X(t) has independent increments;

[0057] 3) For any t≥0 and Δt, X(t+Δt)-X(t)~Ga(Δα(t),β), where Δα(t)≥0 is a non-decreasing continuous function. Define the function α(t) to satisfy α(0)=0 and Δα(t)=α(t+Δt)-α(t). The function α(t) is called the shape function, and β>0 is the scale parameter. Choose a shape function with a convex shape, usually α(t)=at b , where b is used to describe the nonlinear process above; the scale parameter β of the nonlinear Gamma degradation model is set as a random variable. In order to facilitate the subsequent reliability calculation, β is made to obey the Gamma distribution, that is, β~Ga(δ,γ). Therefore, the model can be expressed as:

[0058]

[0059] Based on the total probability formula of continuous random variables, the distribution density of the degradation amount X(t) at time t is obtained. The calculation formula is:

[0060]

[0061] where F represents an F distribution with 2α(t) and 2δ degrees of freedom.

[0062] WinBUGS is used to simulate and solve the wind power equipment degradation model based on the Gibbs sampling method and estimate the parameters, and obtain the posterior distribution of the parameters and their mean, standard deviation, confidence interval, and parameter changes during the iteration process, such as Figure 2 As shown, Figure 2 Schematic diagram of performance degradation simulation results of the basic performance degradation model of wind power equipment.

[0063] 1) Initialize the sample

[0064] 2) From the fully conditional distribution Extract samples from

[0065] 3) From the full conditional distribution Extract samples from

[0066] 4) From the fully conditional distribution Extract samples from

[0067] In this embodiment, the basic performance degradation model of the wind power equipment is calculated based on the MAE index to obtain the mean absolute error of the basic performance degradation model of the wind power equipment. The calculation formula is expressed as:

[0068]

[0069] Where N is the sample size, y i is the true value of the sample, is the predicted output.

[0070] The basic performance degradation model of wind power equipment is calculated based on the MSE index to obtain the mean square error of the basic performance degradation model of wind power equipment. The calculation formula is expressed as:

[0071]

[0072] The basic performance degradation model of wind power equipment is calculated based on the MAPE index. The average absolute error percentage of the basic performance degradation model of wind power equipment is calculated as follows:

[0073]

[0074] Based on the DIC criterion, the distance between the training sample deviation and the test sample deviation in the basic performance degradation model of wind power equipment is calculated. The calculation formula is expressed as:

[0075]

[0076] in, is the mean of the posterior distribution of θ, is a known a posteriori parameter Likelihood function under the condition.

[0077] The model performance is comprehensively evaluated using multiple indicators such as MAE, MSE, MAPE and DIC, so that the analysis of prediction quality is not limited to a single indicator, which enhances the depth and effectiveness of the interpretation of the results. Combining the calculation results of different indicators, it supports the continuous monitoring and optimization of the performance degradation model of wind power equipment, ensuring that the model can adapt to new operating conditions and data changes in a timely manner and enhance its prediction ability. By quantifying the performance of the model, the conclusion can provide more scientific data support for equipment operation and maintenance decisions, and improve the efficiency and reliability of wind farm management. By reducing the error index and ensuring the generalization ability of the model, the service life of the equipment can be effectively extended, the maintenance cycle can be optimized, and the long-term economic and environmental benefits of the wind farm can be ultimately improved.

[0078] Step S2, performing a mechanism analysis on the blade crack growth data in the degradation fault information, respectively obtaining the primary acceleration stress and secondary acceleration stress of the wind power equipment, and constructing a first wind power equipment accelerated degradation model based on the primary acceleration stress, the secondary acceleration stress and the comprehensive acceleration equation.

[0079] In this step, the main accelerating stress includes the common and key factors that affect the failure of wind power equipment, such as basic performance parameters such as tensile strength; the secondary accelerating stress includes the minor factors that affect the failure of wind power equipment, such as equipment maintenance frequency, overall equipment structure, enterprise management model, personnel quality, etc.

[0080] Furthermore, the mechanism analysis of the crack propagation failure process of wind turbine blades is used to obtain the key main accelerating stress and secondary accelerating stress that affect the degradation process, that is, the failure mechanism of crack propagation is used to determine the main accelerating stress factors, that is, the stress that directly causes crack propagation; for fatigue failure, the main accelerating stress may include wind load, vibration load, etc.; for corrosion failure, it may include chemical corrosion environment, etc. In addition to the direct main accelerating stress, some stress factors that indirectly affect crack propagation, namely secondary accelerating stress, need to be analyzed; for blade crack propagation, secondary accelerating stress may include environmental factors such as temperature, humidity, and salt spray, which may indirectly promote crack propagation by affecting material properties and surface conditions.

[0081] The expression of the comprehensive acceleration equation is:

[0082]

[0083] Among them, R(K,σ t ) represents the comprehensive acceleration equation, K represents the temperature in the service environment of the wind power equipment, σ t represents tensile stress, γ0 represents the comprehensive accelerated stress index value, E arepresents the activation energy, γ1 represents the first accelerating stress coefficient, γ2 represents the second accelerating stress coefficient, and κ represents the Boltzmann constant.

[0084] The continuous time random process {X(t), t≥0} is a nonlinear accelerated Gamma process considering random effects. The role of the acceleration equation in the nonlinear Gamma process is to adjust the size of the shape parameter in the incremental distribution of the degradation process according to the size of various accelerating stresses to change the degradation rate at this time. The random process should satisfy the following conditions:

[0085] 1) X(0) = 0;

[0086] 2) X(t) has independent increments;

[0087] 3) For any t ≥ 0 and Δt, X(t + Δt) - X(t) ~ Ga(Δα(t), β), where Δα(t) ≥ 0 is a non-decreasing continuous function;

[0088] Where α(t)=R(K,σ t )·t b , and β~Ga(δ,γ).

[0089] Based on the construction and calculation of the primary accelerated stress analysis and secondary accelerated stress index system, the final accelerated degradation model is obtained. The calculation formula is:

[0090]

[0091] The parameters in the crack growth acceleration degradation model of wind turbine blades are reasonably set to ensure that the acceleration factor remains unchanged. The calculation formula is:

[0092]

[0093] Here, α' represents an arbitrary degradation amount.

[0094] Based on the principle of constant acceleration factor, the life distribution prediction of wind power equipment under normal working stress is obtained, and the calculation formula is:

[0095]

[0096] Among them, ξ is the failure threshold of wind power equipment, and F(t) is the probability distribution function of the remaining service life of wind power equipment.

[0097] Step S3, constructing a wind power equipment status multi-source data set based on the degradation fault information, and updating the first wind power equipment accelerated degradation model according to the wind power equipment status multi-source data set, the Bayesian function and the EM algorithm to obtain a second wind power equipment accelerated degradation model.

[0098] The wind power equipment status multi-source data set includes degradation cause data and degradation result data. The degradation cause data includes temperature monitoring quantity, stress intensity and corrosive medium content, and the degradation result data includes crack extension length, material residual strength and elongation.

[0099] This step also includes steps S31 to S32.

[0100] Step S31 : Based on the prior information and sample information in the wind power equipment state multi-source data set, the degradation parameters in the first wind power equipment accelerated degradation model are updated in real time by using a Bayesian function to obtain the posterior distribution parameters of the degradation parameters.

[0101] The conditional distribution form of the actual degradation data is obtained according to the equipment drift coefficient given in the degradation model. The calculation formula is:

[0102]

[0103] Among them, Δt j =t j -t j-1 Indicates a time interval.

[0104] Let Ω=(μ1,μ2,…,μ n ) and regard X and Ω as observable values ​​to obtain the complete log-likelihood function corresponding to all samples. The calculation formula is:

[0105]

[0106] The Bayesian idea is used to describe the parameter update process to obtain the posterior distribution expression of the device drift coefficient. The calculation formula is:

[0107]

[0108] Step S32, iteratively obtaining the maximum likelihood estimate of the degradation parameters in the first wind power equipment accelerated degradation model through the EM algorithm, and calculating the remaining parameter update values ​​corresponding to the maximum likelihood estimate in the first wind power equipment accelerated degradation model according to the parameter update function.

[0109] Under the conditions of degraded data and prior parameter estimates, the expectation of the complete log-likelihood function of the latent variable Ω is obtained, and the calculation formula is:

[0110]

[0111] Maximize the expectation of the complete log-likelihood function as follows:

[0112]

[0113] The expression of the parameter update function is:

[0114]

[0115] Among them, μ β Indicates that the drift coefficient follows the mean of the normal distribution, k represents the number of iterations, n represents the number of products, and a i represents the mean of the posterior distribution of the i-th monomer, Indicates that the variance of the drift coefficient follows a normal distribution, b i represents the variance of the posterior distribution of the i-th monomer, σ 2 The variance of the diffusion coefficient follows a normal distribution, Δt j represents the time interval, Δx ij Indicates that from time t j-1 At time t j The degradation increment of the ith monomer in the process, m represents the number of degradation data.

[0116] By using the Bayesian function to update the degradation parameters in real time, the model can be continuously adjusted according to new observation data during the operation of the equipment, which significantly enhances the flexibility and response speed of the model to changes in the operating environment, so as to reduce the prediction errors caused by environmental changes. The EM algorithm can effectively handle the missing values ​​in the sample data, ensuring that even in the case of incomplete data, the model can still give reasonable parameter estimates and state assessments, thereby improving the integrity and reliability of data processing. At the same time, the application of the parameter update function enables the model to adjust related parameters other than the degradation parameters, which enhances the overall coordination of the model, makes the relationship between the parameters more accurate, and thus improves the prediction ability of the model.

[0117] Step S4: constructing a multi-stage degradation process model of wind power equipment according to the degradation process multi-condition hypothesis function and the second wind power equipment accelerated degradation model to predict the remaining life of the wind power equipment.

[0118] The expression of the multi-condition assumption function of the degradation process is:

[0119]

[0120] Among them, X(t) represents the multi-condition hypothesis function of the degradation process, X(0) represents the initial degradation amount, μ l represents the drift parameter in the lth degradation stage, ∑N l (μ l ,σ l 2 ) is the total degradation amount of the product in the lth degradation stage, σ l 2 It represents the variance of the diffusion coefficient in the lth degradation stage that follows the normal distribution.

[0121] Based on multiple updates of accelerated stress, the degradation path of the equipment has entered the nth stage. At this time, the degradation process satisfies the following assumptions:

[0122]

[0123] Among them, μ n ~N(μ βn ,σ βn 2 ).

[0124] The real-time remaining life distribution prediction results of wind power equipment in the degradation process of accelerated stress update are obtained. The calculation formula is:

[0125]

[0126] By systematically collecting and analyzing the operating environment data and degradation fault information of wind power equipment, the basic performance degradation model constructed can reflect the actual performance changes of the equipment under different environmental conditions, thereby improving the accuracy and practicality of the model. At the same time, through the mechanism analysis of blade crack propagation data, the main acceleration stress and secondary acceleration stress that affect crack propagation can be effectively identified. The accelerated degradation model is dynamically updated using the Bayesian function and the EM algorithm to enhance the adaptive ability of the accelerated degradation model. Then, combined with the second wind power equipment accelerated degradation model and the multi-condition hypothesis function, a high-precision prediction of the remaining life of wind power equipment can be achieved.

[0127] Based on the above method, the embodiment of the present application discloses a wind power equipment life prediction system based on multi-source data and acceleration effect, referring to Figure 3 The wind power equipment life prediction system 1 includes an information collection module 11, a degradation integration module 12 and a life prediction module 13, wherein:

[0128] The information collection module 11 is used to collect the operating environment data and degradation fault information of the wind power equipment, and to construct a basic performance degradation model of the wind power equipment based on the operating environment data and degradation fault information;

[0129] The degradation integration module 12 is used to perform a mechanism analysis on the blade crack extension data in the degradation fault information, respectively obtain the main acceleration stress and the secondary acceleration stress of the wind power equipment, and construct a first wind power equipment accelerated degradation model based on the main acceleration stress, the secondary acceleration stress and the comprehensive acceleration equation; construct a wind power equipment state multi-source data set based on the degradation fault information, and update the data of the first wind power equipment accelerated degradation model according to the wind power equipment state multi-source data set, the Bayesian function and the EM algorithm to obtain a second wind power equipment accelerated degradation model;

[0130] The life prediction module 13 is used to construct a multi-stage degradation process model of wind power equipment according to the degradation process multi-condition hypothesis function and the second wind power equipment accelerated degradation model to predict the remaining life of the wind power equipment.

[0131] In one example, the information acquisition module 11 is used to determine the main influencing indicators of wind power equipment performance degradation based on the operating environment data and the degradation failure mechanism and failure form in the degradation fault information; and to construct a basic performance degradation model of wind power equipment based on the main influencing indicators, the nonlinear Gamma correction function and the blade crack extension data in the degradation fault information.

[0132] In one example, after building a basic performance degradation model of wind power equipment, the following is also included:

[0133] Calculate the basic performance degradation model of wind power equipment based on the MAE index to obtain the mean absolute error of the basic performance degradation model of wind power equipment;

[0134] The basic performance degradation model of wind power equipment is calculated based on the MSE index to obtain the mean square error of the basic performance degradation model of wind power equipment;

[0135] The basic performance degradation model of wind power equipment is calculated based on the MAPE index, and the average absolute error percentage of the basic performance degradation model of wind power equipment;

[0136] The distance between the training sample deviation and the test sample deviation in the basic performance degradation model of wind power equipment is calculated based on the DIC criterion.

[0137] In one example, the comprehensive acceleration equation is expressed as:

[0138]

[0139] Among them, R(K,σ t ) represents the comprehensive acceleration equation, K represents the temperature in the service environment of the wind power equipment, σ t represents tensile stress, γ0 represents the comprehensive accelerated stress index value, E a represents the activation energy, γ1 represents the first accelerating stress coefficient, γ2 represents the second accelerating stress coefficient, and κ represents the Boltzmann constant.

[0140] In one example, the wind power equipment status multi-source data set includes degradation cause data and degradation result data, wherein the degradation cause data includes temperature monitoring quantity, stress intensity and corrosive medium content, and the degradation result data includes crack extension length, material residual strength and elongation.

[0141] In one example, the degradation integration module 12 is used to update the degradation parameters in the first wind power equipment accelerated degradation model in real time through a Bayesian function based on the prior information and sample information in the multi-source data set of wind power equipment status to obtain the posterior distribution parameters of the degradation parameters; to iteratively obtain the maximum likelihood estimate of the degradation parameters in the first wind power equipment accelerated degradation model through the EM algorithm, and to calculate the remaining parameter update values ​​corresponding to the maximum likelihood estimate in the first wind power equipment accelerated degradation model according to the parameter update function.

[0142] In an example, the expression of the parameter update function is:

[0143]

[0144] Among them, μ β Indicates that the drift coefficient follows the mean of the normal distribution, k represents the number of iterations, n represents the number of products, and a i represents the mean of the posterior distribution of the i-th monomer, Indicates that the variance of the drift coefficient follows a normal distribution, b i represents the variance of the posterior distribution of the i-th monomer, σ 2 The variance of the diffusion coefficient follows a normal distribution, Δt j represents the time interval, Δx ij Indicates that from time t j-1 At time t j The degradation increment of the ith monomer in the process, m represents the number of degradation data.

[0145] In one example, the expression of the multi-condition assumption function of the degradation process is:

[0146]

[0147] Among them, X(t) represents the multi-condition hypothesis function of the degradation process, X(0) represents the initial degradation amount, μ l represents the drift parameter in the lth degradation stage, ΣN l (μ l ,σ l 2 ) is the total degradation amount of the product in the lth degradation stage, σ l 2 It represents the variance of the diffusion coefficient in the lth degradation stage that follows the normal distribution.

[0148] See also Figure 4 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4 As shown, the electronic device 2 may include: at least one processor 21 , at least one network interface 24 , a user interface 23 , a memory 25 , and at least one communication bus 22 .

[0149] The communication bus 22 is used to realize the connection and communication between these components.

[0150] The user interface 23 may include a display screen (Display) and a camera (Camera), and the optional user interface 23 may also include a standard wired interface and a wireless interface.

[0151] The network interface 24 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0152] Among them, the processor 21 may include one or more processing cores. The processor 21 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 25, and calling data stored in the memory 25. Optionally, the processor 21 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 21 can integrate one or more combinations of a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 21, and it can be implemented separately through a chip.

[0153] Among them, the memory 25 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 25 includes a non-transitory computer-readable storage medium. The memory 25 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 25 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 25 may also be optionally at least one storage device located away from the aforementioned processor 21. As Figure 4 As shown, the memory 25 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a wind power equipment life prediction method based on multi-source data and acceleration effect.

[0154] exist Figure 4 In the electronic device 2 shown, the user interface 23 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 21 can be used to call an application program stored in the memory 25 for a wind power equipment life prediction method based on multi-source data and acceleration effect. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.

[0155] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A wind power equipment life prediction method based on multi-source data and acceleration effect, characterized in that: The method comprises: Collecting operating environment data and degradation fault information of wind power equipment, and building a basic performance degradation model of wind power equipment based on the operating environment data and the degradation fault information; Performing a mechanism analysis on the blade crack growth data in the degradation fault information, respectively obtaining the main acceleration stress and the secondary acceleration stress of the wind power equipment, and constructing a first wind power equipment accelerated degradation model based on the main acceleration stress, the secondary acceleration stress and the comprehensive acceleration equation; Constructing a wind power equipment state multi-source data set based on degradation fault information, and updating the first wind power equipment accelerated degradation model according to the wind power equipment state multi-source data set, Bayesian function and EM algorithm to obtain a second wind power equipment accelerated degradation model; According to the multi-condition hypothesis function of the degradation process and the second accelerated degradation model of wind power equipment, a multi-stage degradation process model of wind power equipment is constructed to predict the remaining life of the wind power equipment.

2. The method according to claim 1, characterized in that The step of constructing a basic performance degradation model of wind power equipment based on the operating environment data and the degradation fault information specifically includes: Determine the main influencing indicators of wind power equipment performance degradation according to the operating environment data and the degradation failure mechanism and failure form in the degradation fault information; Based on the main influencing indicators, the nonlinear Gamma correction function and the blade crack growth data in the degradation fault information, a basic performance degradation model of wind power equipment is constructed.

3. The method according to claim 1, characterized in that After the basic performance degradation model of wind power equipment is constructed, the method further includes: Calculate the basic performance degradation model of the wind power equipment based on the MAE index to obtain the mean absolute error of the basic performance degradation model of the wind power equipment; Calculating the basic performance degradation model of the wind power equipment based on the MSE index to obtain the mean square error of the basic performance degradation model of the wind power equipment; Calculating the basic performance degradation model of the wind power equipment based on the MAPE index, the average absolute error percentage of the basic performance degradation model of the wind power equipment; The distance between the training sample deviation and the test sample deviation in the basic performance degradation model of the wind power equipment is calculated based on the DIC criterion.

4. The method according to claim 1, characterized in that The expression of the comprehensive acceleration equation is: Among them, R(K,σ t ) represents the comprehensive acceleration equation, K represents the temperature in the service environment of the wind power equipment, σ t represents tensile stress, γ0 represents the comprehensive accelerated stress index value, E a represents the activation energy, γ1 represents the first accelerating stress coefficient, γ2 represents the second accelerating stress coefficient, and κ represents the Boltzmann constant.

5. The method according to claim 1, characterized in that The wind power equipment status multi-source data set includes degradation cause data and degradation result data. The degradation cause data includes temperature monitoring quantity, stress intensity and corrosive medium content, and the degradation result data includes crack extension length, material residual strength and elongation.

6. The method according to claim 1, characterized in that The updating of data of the first wind power equipment accelerated degradation model according to the wind power equipment state multi-source data set, the Bayesian function and the EM algorithm specifically includes: Based on the prior information and sample information in the wind power equipment state multi-source data set, the degradation parameters in the first wind power equipment accelerated degradation model are updated in real time by using a Bayesian function to obtain posterior distribution parameters of the degradation parameters; The maximum likelihood estimate of the degradation parameters in the first wind power equipment accelerated degradation model is obtained through iteration of the EM algorithm, and the remaining parameter update values ​​corresponding to the maximum likelihood estimate in the first wind power equipment accelerated degradation model are calculated according to a parameter update function.

7. The method according to claim 6, characterized in that The expression of the parameter update function is: Among them, μ β Indicates that the drift coefficient follows the mean of the normal distribution, k represents the number of iterations, n represents the number of products, and a i represents the mean of the posterior distribution of the i-th monomer, Indicates that the drift coefficient follows the variance of the normal distribution, b i represents the variance of the posterior distribution of the i-th monomer, σ 2 The variance of the diffusion coefficient follows a normal distribution, Δt j represents the time interval, Δx ij Indicates that from time t j-1 At time t j The degradation increment of the ith monomer in the process, m represents the number of degradation data.

8. The method according to claim 1, characterized in that The expression of the multi-condition assumption function of the degradation process is: Among them, X(t) represents the multi-condition hypothesis function of the degradation process, X(0) represents the initial degradation amount, μ l represents the drift parameter in the lth degradation stage, ∑N l (μ l ,σ l 2 ) is the total degradation amount of the product in the lth degradation stage, σ l 2 It represents the variance of the diffusion coefficient in the lth degradation stage that follows the normal distribution.

9. A wind power equipment life prediction system based on multi-source data and acceleration effect, characterized in that: The wind power equipment life prediction system (1) comprises an information collection module (11), a degradation integration module (12) and a life prediction module (13), wherein: The information collection module (11) is used to collect operating environment data and degradation fault information of the wind power equipment, and to construct a basic performance degradation model of the wind power equipment based on the operating environment data and the degradation fault information; The degradation integration module (12) is used to perform a mechanism analysis on the blade crack extension data in the degradation fault information, respectively obtain the main acceleration stress and the secondary acceleration stress of the wind power equipment, and construct a first wind power equipment accelerated degradation model based on the main acceleration stress, the secondary acceleration stress and the comprehensive acceleration equation; construct a wind power equipment state multi-source data set based on the degradation fault information, and update the data of the first wind power equipment accelerated degradation model according to the wind power equipment state multi-source data set, the Bayesian function and the EM algorithm to obtain a second wind power equipment accelerated degradation model; The life prediction module (13) is used to construct a multi-stage degradation process model of wind power equipment based on the degradation process multi-condition hypothesis function and the second wind power equipment accelerated degradation model to predict the remaining life of the wind power equipment.

10. An electronic device, characterized in that: The electronic device (2) comprises a processor (21), a memory (25), a user interface (23) and a network interface (24), wherein the memory (25) is used to store instructions, the user interface (23) and the network interface (24) are used to communicate with other devices, and the processor (21) is used to execute the instructions stored in the memory (25) so that the electronic device (2) executes the method according to any one of claims 1 to 8.

Images