Method and device for predicting service life of gas turbine blade and electronic equipment

Abstract

The invention provides a gas turbine blade life prediction method and device and electronic equipment. The method comprises the following steps: simulating the gas turbine to obtain first degradation data, and simulating blades of the gas turbine based on the first degradation data to obtain second degradation data; determining a first mapping relationship between the first degradation data and the second degradation data, and establishing a blade life prediction model based on the first mapping relationship; according to the material characteristic parameters and the distribution information, correcting the blade life prediction model to obtain a target blade life prediction model; based on the monitoring parameters of the target blade and a target blade life prediction model, determining a candidate residual cycle period of the target blade and a confidence coefficient; and performing kernel density estimation on the candidate residual cycle period, and determining the residual life of the target blade according to the confidence coefficient. Therefore, according to the scheme, the complexity and uncertainty of the blade in the actual operation process are fully considered, so that the residual life of the blade can be predicted more accurately.

Description

Technical Field

[0001] The present application relates to the technical field of gas turbines, and in particular to a method, device and electronic equipment for predicting the life of gas turbine blades. Background Art

[0002] Gas turbine blades operate under harsh conditions of high temperature, high pressure, high load, and high speed for extended periods, simultaneously enduring alternating loads such as centrifugal, thermal, aerodynamic, and vibration stresses. Under these alternating loads, the blade material undergoes both creep deformation and fatigue damage. When the number of alternating load cycles reaches a certain limit, the blade will experience fatigue failure. Blade failure can severely impact the stability, safety, and economic efficiency of gas turbine operation. Therefore, predicting the lifespan of gas turbine blades is crucial, providing operators with information to inform inspection and maintenance decisions and reducing the probability of operating under failure risk. Summary of the Invention

[0003] The present application aims to solve one of the technical problems in the related art at least to a certain extent.

[0004] To this end, the first purpose of this application is to propose a life prediction method for gas turbine blades, so as to fully consider the complexity and uncertainty of the blades during actual operation, so as to more accurately predict the remaining life of the blades.

[0005] The second objective of the present application is to provide a life prediction device for gas turbine blades.

[0006] The third objective of this application is to provide an electronic device.

[0007] The fourth object of this application is to provide a computer-readable storage medium.

[0008] A fifth object of this application is to provide a computer program product.

[0009] To achieve the above-mentioned purpose, the first embodiment of the present application proposes a life prediction method for gas turbine blades, comprising: simulating the performance of the gas turbine to obtain first degradation data of the gas turbine, and performing failure simulation on the blades of the gas turbine based on the first degradation data to obtain second degradation data of the blades; determining a first mapping relationship between the first degradation data and the second degradation data, and establishing an initial blade life prediction model based on the first mapping relationship; obtaining material characteristic parameters of the blade and distribution information of the material characteristic parameters, and correcting the initial blade life prediction model based on the material characteristic parameters and the distribution information to obtain a target blade life prediction model; inputting the monitoring parameters of the target blade whose remaining life is to be predicted into the target blade life prediction model, outputting candidate remaining cycle periods of the target blade, and the confidence corresponding to the candidate remaining cycle periods; performing kernel density estimation on the candidate remaining cycle periods, and determining the remaining life of the target blade from the candidate remaining cycle periods based on the confidence.

[0010] To achieve the above-mentioned purpose, the second embodiment of the present application proposes a life prediction device for a gas turbine blade, comprising: a simulation module, configured to simulate the performance of a gas turbine to obtain first degradation data of the gas turbine, and perform failure simulation on the blade of the gas turbine based on the first degradation data to obtain second degradation data of the blade; an establishment module, configured to determine a first mapping relationship between the first degradation data and the second degradation data, and establish an initial blade life prediction model based on the first mapping relationship; a correction module, configured to obtain material characteristic parameters of the blade and distribution information of the material characteristic parameters, and correct the initial blade life prediction model based on the material characteristic parameters and the distribution information to obtain a target blade life prediction model; a prediction module, configured to input monitoring parameters of a target blade whose remaining life is to be predicted into the target blade life prediction model, and output candidate remaining cycle periods of the target blade and confidence levels corresponding to the candidate remaining cycle periods; a determination module, configured to perform kernel density estimation on the candidate remaining cycle periods, and determine the remaining life of the target blade from the candidate remaining cycle periods based on the confidence levels.

[0011] To achieve the above-mentioned purpose, the third aspect embodiment of the present application proposes an electronic device, comprising: a processor; and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, so that the processor can execute the life prediction method of the gas turbine blade described in the first aspect embodiment above.

[0012] To achieve the above-mentioned purpose, the fourth embodiment of the present application proposes a computer-readable storage medium having a computer program stored thereon, wherein the computer instructions are used to enable the computer to execute the life prediction method of the gas turbine blade described in the first embodiment above.

[0013] To achieve the above-mentioned purpose, the fifth embodiment of the present application proposes a computer program product, including a computer program, which, when executed by a processor, implements the life prediction method of the gas turbine blade described in the first embodiment above.

[0014] The gas turbine blade life prediction method, device, and electronic device provided in this application obtain first degradation data of the gas turbine and second degradation data of the gas turbine blade, and determine an initial blade remaining life prediction model based on a first mapping relationship between the first degradation data and the second degradation data. Furthermore, material characteristic parameters of the blade are obtained to modify the initial blade remaining life prediction model based on the material characteristic parameters to obtain a target blade life prediction model. By inputting the monitoring parameters of the target blade into the target blade life prediction model, multiple candidate remaining cycles corresponding to the target blade can be obtained. By performing kernel density estimation on the candidate remaining cycles, the remaining life of the target blade can be determined. Establishing a prediction model based on the mapping relationship can improve the accuracy of the model prediction and enhance the applicability of the model. Determining the target blade remaining life based on the kernel density estimation method fully considers the complexity and uncertainty of the target blade during actual operation, thereby enabling a more accurate prediction of the blade remaining life.

[0015] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0017] Figure 1 A schematic flow chart of a method for predicting the life of a gas turbine blade provided in an embodiment of the present application;

[0018] Figure 2 A schematic flow chart of another method for predicting the life of a gas turbine blade provided in an embodiment of the present application;

[0019] Figure 3 A schematic flow chart of another method for predicting the life of a gas turbine blade provided in an embodiment of the present application;

[0020] Figure 4A schematic flow chart of another method for predicting the life of a gas turbine blade provided in an embodiment of the present application;

[0021] Figure 5 A schematic diagram of a process for predicting the remaining life of a gas turbine blade provided in an embodiment of the present application;

[0022] Figure 6 A schematic structural diagram of a gas turbine blade life prediction device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0024] The following describes the life prediction method and device for gas turbine blades according to embodiments of the present application with reference to the accompanying drawings.

[0025] Figure 1 FIG. 1 is a flow chart showing a method for predicting the life of a gas turbine blade according to an exemplary embodiment. Figure 1 As shown, the life prediction method of the gas turbine blade of the embodiment of the present application includes but is not limited to the following steps:

[0026] S101 , simulating the performance of a gas turbine to obtain first degradation data of the gas turbine, and performing failure simulation on blades of the gas turbine based on the first degradation data to obtain second degradation data of the blades.

[0027] It should be noted that the execution subject of the gas turbine blade life prediction method provided in the embodiments of the present application is an electronic device, which may be a terminal device. Optionally, the terminal device may be a mobile electronic device or a non-mobile electronic device. For example, the mobile electronic device may be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc., while the non-mobile electronic device may be a personal computer (PC), etc. This embodiment of the present application does not specifically limit this.

[0028] In some implementations, a gas turbine performance simulation model can be used to simulate gas turbine performance, and a blade failure model can be used to simulate gas turbine blade failure. Alternatively, gas turbine performance can be simulated by inputting gas turbine operating parameters, atmospheric parameters, and degradation factors into the performance simulation model to obtain first degradation data. The first degradation data includes: gas turbine cross-sectional temperature, cross-sectional pressure, and turbine speed.

[0029] Furthermore, the first degradation data is input into a blade failure model to perform failure simulation on the gas turbine blade to obtain second degradation data, wherein the second degradation data includes temperature distribution, stress distribution, and cycle period of the blade.

[0030] Optionally, sample input parameters and first sample degradation data may be acquired in advance, and a performance simulation model may be trained based on the sample input parameters and the first sample degradation data. Optionally, a blade failure model may be established in advance based on blade geometric parameters, such as shape and size, and blade material properties, such as thermal conductivity and linear expansion coefficient. The blade failure model may be a three-dimensional finite element model.

[0031] S102: Determine a first mapping relationship between the first degradation data and the second degradation data, and establish an initial blade life prediction model based on the first mapping relationship.

[0032] Optionally, the first mapping relationship may be obtained by fitting the first degradation data and the second degradation data, for example, by fitting the first degradation data and the second degradation data using a least squares method.

[0033] Optionally, the first mapping relationship between the first degradation data and the second degradation data may be determined based on a machine learning algorithm, for example, using a multi-layer perceptron neural network.

[0034] Furthermore, after determining the first mapping relationship, the type of model can be determined according to the first mapping relationship, such as a linear regression model, and then the training set and test set for model training can be determined according to the first degradation data, the second degradation data and the first mapping relationship, so as to train the model using the training set, and verify the model performance using the test set after the training, and adjust the model to obtain an initial blade life prediction model.

[0035] Optionally, the input of the initial blade life prediction model is the parameters of the blade, including material characteristic parameters, temperature parameters, stress parameters, etc. The input of the initial blade life prediction model is the remaining cycle period of the blade.

[0036] S103 , obtaining material characteristic parameters and distribution information of the material characteristic parameters of the blade, and modifying the initial blade life prediction model according to the material characteristic parameters and the distribution information to obtain a target blade life prediction model.

[0037] In some implementations, the material characteristic parameters include thermal conductivity, linear expansion coefficient, elastic modulus, Poisson's ratio, yield strength and tensile limit. By determining the distribution information of the material characteristic parameters and using the material characteristic parameters and distribution information as input information of the initial blade life prediction model, the initial blade life prediction model determines the dispersion band range of the data based on the distribution information, and simulates the material characteristic parameters within the dispersion band range to obtain the dispersion band range of the remaining cycle period of the blade.

[0038] Furthermore, the model can be modified based on the dispersion band range of the blade's remaining cycle period. Alternatively, the sample dispersion band range of the blade's sample remaining cycle period can be obtained, and then a loss function can be calculated based on the sample dispersion band range and the dispersion band range. The model can be modified based on the loss function to obtain a target blade life prediction model.

[0039] S104 , inputting monitoring parameters of the target blade whose remaining life is to be predicted into a target blade life prediction model, and outputting candidate remaining cycles of the target blade and confidence levels corresponding to the candidate remaining cycles.

[0040] Optionally, the target blade for which the remaining life is to be predicted can be monitored in real time to obtain the temperature distribution and stress distribution of the target blade as monitoring parameters. By inputting the monitoring parameters into the target blade life prediction model, the target blade life prediction model predicts the remaining life of the target blade based on the monitoring parameters. Multiple predicted remaining cycle periods corresponding to the target blade and the confidence level corresponding to each predicted remaining cycle period can be output. The predicted remaining cycle period can be used as a candidate remaining cycle period, and the confidence level corresponding to the candidate remaining cycle period can be determined.

[0041] S105 , performing kernel density estimation on the candidate remaining cycle periods, and determining the remaining life of the target blade from the candidate remaining cycle periods according to the confidence level.

[0042] Optionally, kernel density estimation can be performed on the candidate remaining cycle periods based on the kernel function and bandwidth to determine the probability density estimation value corresponding to each candidate remaining cycle period, and the kernel density estimation map corresponding to the candidate remaining cycle period can be determined based on the probability density estimation value and confidence level.

[0043] Furthermore, by determining the confidence interval of the candidate remaining cycle period and judging whether the kernel density estimation graph is within the confidence interval, the candidate remaining cycle period corresponding to the kernel density estimation graph within the confidence interval is used as the remaining life of the target blade.

[0044] In the life prediction method for gas turbine blades provided in an embodiment of the present application, first degradation data of the gas turbine and second degradation data of the gas turbine blades are obtained, and an initial blade remaining life prediction model is determined based on a first mapping relationship between the first degradation data and the second degradation data. Furthermore, the material characteristic parameters of the blades are obtained to correct the initial blade remaining life prediction model based on the material characteristic parameters to obtain a target blade life prediction model. By inputting the monitoring parameters of the target blades into the target blade life prediction model, a plurality of candidate remaining cycles corresponding to the target blades can be obtained. By performing kernel density estimation on the candidate remaining cycles, the remaining life of the target blades can be determined. Establishing a prediction model based on the mapping relationship can improve the accuracy of the model prediction and improve the applicability of the model. Determining the remaining life of the target blade based on the kernel density estimation method fully takes into account the complexity and uncertainty of the target blades during actual operation, thereby being able to more accurately predict the remaining life of the blades.

[0045] Figure 2 FIG. 1 is a flow chart showing a method for predicting the life of a gas turbine blade according to an exemplary embodiment. Figure 2 As shown, the life prediction method of the gas turbine blade of the embodiment of the present application includes but is not limited to the following steps:

[0046] S201, obtaining operating parameters, atmospheric parameters, and degradation factors of the gas turbine, and simulating the performance of the gas turbine based on the operating parameters, atmospheric parameters, and degradation factors to obtain a cross-sectional temperature, a cross-sectional pressure, and a combustion engine speed of the gas turbine as first degradation data.

[0047] It's understood that operating parameters generally refer to parameters directly related to the operating status of equipment, systems, or processes. These parameters, such as speed, power, voltage, and current, reflect the performance and efficiency of equipment under different operating conditions. They are crucial for monitoring equipment's operating status, optimizing operating conditions, and ensuring system safety.

[0048] Atmospheric parameters are a general term used to describe the physical conditions of the atmosphere, including atmospheric pressure, temperature, and humidity. These parameters are crucial for understanding the atmospheric environment, predicting weather changes, assessing environmental quality, and conducting weather forecasts. The measurement and analysis of atmospheric parameters is a crucial research topic in fields such as meteorology and environmental science.

[0049] Degradation factors are associated with system performance degradation, performance degradation, or system instability in certain directions. In optimization problems, degradation factors may indicate a system's sensitivity to perturbations in a certain direction—that is, a small perturbation in that direction may result in a significant deviation in system performance. In physical systems or algorithms, degradation factors can be used to assess system robustness and stability.

[0050] In some implementations, the gas turbine may be monitored in real time to obtain the operating parameters and degradation factors of the gas turbine, and the atmospheric pressure, temperature, humidity, etc. of the environment in which the gas turbine is located may be obtained as atmospheric parameters.

[0051] Furthermore, the operating parameters, atmospheric parameters and degradation factors are input into a pre-trained gas turbine performance simulation model, and the performance simulation model simulates the performance of the gas turbine. The cross-sectional temperature, cross-sectional pressure and engine speed of the gas turbine can be output, and the cross-sectional temperature, cross-sectional pressure and engine speed are used as the first degradation data.

[0052] S202 : Based on the first degradation data and a reference failure mode of the blade, a failure simulation is performed on the blade to obtain a temperature distribution, a stress distribution, and a cycle period of the blade as second degradation data.

[0053] Optionally, the reference failure mode may be a low-cycle fatigue failure mode, or a failure mode such as creep deformation and high-cycle fatigue.

[0054] In some implementations, a pre-trained blade failure model is called, and the first degradation data and the reference failure mode are input into the blade failure model, so that failure simulation of the blade is performed according to the reference failure model based on the first degradation data, the dangerous failure position of the blade is determined, and the failure process under different stress distributions is simulated to obtain the limit cycle period corresponding to the different stress distributions, that is, the temperature distribution, stress distribution and cycle period are output, and the temperature distribution, stress distribution and cycle period are used as the second degradation data.

[0055] S203: Determine a first mapping relationship between the first degradation data and the second degradation data, and establish an initial blade life prediction model based on the first mapping relationship.

[0056] In some implementations, the monitorable parameters and reliability parameters of the gas turbine can be determined from the first degradation data and the second degradation data, and a first mapping relationship between the monitorable parameters and the reliability parameters of the gas turbine can be determined to establish an initial blade life prediction model based on the first mapping relationship.

[0057] Optionally, the monitorable parameters and reliability parameters of the gas turbine may be determined based on the operating parameters, atmospheric parameters, degradation factors, and the first degradation data and the second degradation data. Optionally, the operating parameters, atmospheric parameters, degradation factors, and the first degradation data are used as the monitorable parameters of the gas turbine, and the second degradation data is used as the reliability parameter of the gas turbine.

[0058] Furthermore, the monitorable parameter and the reliability parameter are fitted to obtain a first mapping relationship. Optionally, the monitorable parameter and the reliability parameter can be fitted using a least squares method to obtain the first mapping relationship. Optionally, the first mapping relationship between the monitorable parameter and the reliability parameter can also be determined based on a machine learning algorithm.

[0059] In some implementations, in order to improve the prediction accuracy of the initial blade life prediction model, the first mapping relationship may be corrected, and the corrected first mapping relationship may be used to establish the initial blade life prediction model.

[0060] Optionally, an initial blade life prediction model is established by determining intermediate variables of the first mapping relationship and correcting the first mapping relationship based on the intermediate variables to obtain a corrected first mapping relationship. The intermediate variables include, but are not limited to, thermal load, aerodynamic load, and centrifugal load.

[0061] Alternatively, the temperature from a certain point on the blade to the root can be calculated as the thermal load. The thermal load can be calculated based on the cross-sectional temperature output by the performance simulation model. The calculation formula is as follows:

[0062]

[0063] Among them, K represents the temperature distribution coefficient, H0 is a constant value, which refers to the blade height, H is a variable, which refers to the distance from a certain point on the blade to the blade root, T blade Refers to the temperature from a certain point on the blade to the root of the blade, that is, the heat load.

[0064] Alternatively, aerodynamic load refers to the pressure on the blade surface caused by the erosion of the gas flow during high-speed rotation, and satisfies the theoretical aerodynamic calculation formula, where the aerodynamic force at a specific section of the blade increases with increasing radial height. Centrifugal load refers to the application of a corresponding rotational speed at the blade's center of rotation, which can be achieved by applying a centrifugal load.

[0065] S204 , obtaining material characteristic parameters and distribution information of the material characteristic parameters of the blade, and modifying the initial blade life prediction model according to the material characteristic parameters and the distribution information to obtain a target blade life prediction model.

[0066] In the embodiment of the present application, the implementation method of step S204 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0067] S205 , inputting monitoring parameters of the target blade whose remaining life is to be predicted into a target blade life prediction model, and outputting candidate remaining cycles of the target blade and confidence levels corresponding to the candidate remaining cycles.

[0068] In the embodiment of the present application, the implementation method of step S205 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0069] S206 , performing kernel density estimation on the candidate remaining cycle periods, and determining the remaining life of the target blade from the candidate remaining cycle periods according to the confidence level.

[0070] In the embodiment of the present application, the implementation method of step S206 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0071] In a gas turbine blade life prediction method provided in an embodiment of the present application, first degradation data is obtained by simulating the gas turbine's operating parameters, atmospheric parameters, and degradation factors. Based on the first degradation data, the blade is simulated to obtain second degradation data. A first mapping relationship between a monitorable parameter and a reliability parameter is determined from the first and second degradation data to determine an initial blade remaining life prediction model. Furthermore, material property parameters of the blade are obtained and the initial blade remaining life prediction model is modified based on the material property parameters to obtain a target blade life prediction model. By inputting the monitoring parameters of the target blade into the target blade life prediction model, multiple candidate remaining cycles corresponding to the target blade are obtained. The remaining life of the target blade can be determined by performing kernel density estimation on the candidate remaining cycles. Establishing a prediction model based on this mapping relationship improves the accuracy of the model's prediction and enhances its applicability. Determining the target blade's remaining life using kernel density estimation fully accounts for the complexity and uncertainty of the target blade during actual operation, thereby enabling more accurate prediction of the blade's remaining life.

[0072] Figure 3 FIG. 1 is a flow chart showing a method for predicting the life of a gas turbine blade according to an exemplary embodiment. Figure 3 As shown, the life prediction method of the gas turbine blade of the embodiment of the present application includes but is not limited to the following steps:

[0073] S301 , simulating the performance of a gas turbine to obtain first degradation data of the gas turbine, and performing failure simulation on blades of the gas turbine based on the first degradation data to obtain second degradation data of the blades.

[0074] In the embodiment of the present application, the implementation method of step S301 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0075] S302: Determine a first mapping relationship between the first degradation data and the second degradation data, and establish an initial blade life prediction model based on the first mapping relationship.

[0076] In the embodiment of the present application, the implementation method of step S302 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0077] S303 , obtaining material characteristic parameters and distribution information of the material characteristic parameters of the blade, and modifying the initial blade life prediction model according to the material characteristic parameters and the distribution information to obtain a target blade life prediction model.

[0078] In the embodiment of the present application, the implementation method of step S303 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0079] S304 , inputting monitoring parameters of the target blade whose remaining life is to be predicted into a target blade life prediction model, and outputting candidate remaining cycles of the target blade and confidence levels corresponding to the candidate remaining cycles.

[0080] In the embodiment of the present application, the implementation method of step S304 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0081] S305 , determining a kernel function and bandwidth used in kernel density estimation, and determining a probability density estimation value of each candidate remaining cycle period based on the kernel function and bandwidth.

[0082] In some implementations, kernel functions include but are not limited to: rectangular kernel function K(x)=0.5, foliar kernel function K(x)=0.75(1-x 2 ), Gaussian kernel function And the triangular kernel function K(x)=1-|x|. In this application, a Gaussian kernel function can be selected to calculate the probability density estimate.

[0083] In some implementations, the bandwidth can be determined based on the error value of the kernel density estimate. The asymptotic mean integrated square error of the kernel density estimate is determined by determining the average integrated square error of the kernel density estimate and, based on the average integrated square error, determining the asymptotic mean integrated square error of the kernel density estimate. Furthermore, the minimum of the asymptotic mean integrated square error can be determined, and the bandwidth can be obtained based on the minimum. In other words, the minimum of the asymptotic mean integrated square error can be used as the bandwidth.

[0084] Alternatively, the formula for calculating the mean integrated square error MISE is as follows:

[0085]

[0086] Where h represents bandwidth, E represents mathematical expectation, Represents the estimated probability density function, the bandwidth is h, and f represents the true value.

[0087] Alternatively, the formula for calculating the asymptotic mean integrated square error AMISE is as follows:

[0088]

[0089] Where n is the number of samples, h is the bandwidth, and R(K) = ∫K(x) 2 dx,m(K)=∫x 2 K(x)dx.

[0090] Furthermore, we can differentiate formula (3) to determine the point where the first-order derivative is 0, which is the minimum value of the asymptotic mean integrated square error, that is, the bandwidth. The formula for calculating the bandwidth is as follows:

[0091]

[0092] Among them, h AMISE Indicates bandwidth.

[0093] Furthermore, the probability density estimate of each candidate remaining cycle period can be calculated based on the determined kernel function and bandwidth. The calculation formula is as follows:

[0094]

[0095] in, Represents the probability density estimate, n represents the number of samples, that is, the number of candidate remaining cycles, h represents the bandwidth, and K(x) represents the kernel function.

[0096] S306 , determining a candidate kernel density estimation graph corresponding to the candidate remaining cycle period based on the probability density value and the confidence level.

[0097] S307 : Determine a confidence interval based on the number of candidate remaining cycles, and determine the remaining life of the target blade based on the confidence interval and the candidate kernel density estimation map.

[0098] As you can understand, a kernel density estimation plot is a nonparametric estimation method used to estimate the probability density function of a random variable. It displays the distribution characteristics of data by smoothly estimating the probability density function of the data, and is particularly suitable for continuous variables. Kernel density estimation plots can intuitively display the distribution of data, including peaks, valleys, and distribution shapes.

[0099] Optionally, a candidate kernel density estimate plot can be drawn based on the probability density value and confidence level.

[0100] In some implementations, the confidence interval is related to the sample size. In this application, the sample size is the number of candidate remaining cycles. If the number of candidate remaining cycles is less than a set threshold, the confidence interval 1-α is: in, is the mean, is the t-value corresponding to the two-sided test level of α, S is the sample standard deviation, and n is the number of candidate remaining cycles.

[0101] Optionally, if the number of candidate remaining cycles is greater than or equal to a set threshold, the confidence interval 1-α is: in, is the mean, It is the value corresponding to the standard normal distribution when the probability value on both sides is α. S is the sample standard deviation, and n is the number of candidate remaining cycles.

[0102] In some implementations, after determining the candidate kernel density estimation map corresponding to the candidate remaining cycle period and the confidence interval, the kernel density estimation map within the confidence interval can be determined from the candidate kernel density estimation map, and the candidate remaining cycle period corresponding to the kernel density estimation map can be used as the remaining life of the target blade.

[0103] In the life prediction method for a gas turbine blade provided in an embodiment of the present application, first degradation data of the gas turbine and second degradation data of the gas turbine blade are obtained, and an initial blade remaining life prediction model is determined based on a first mapping relationship between the first degradation data and the second degradation data. Furthermore, material characteristic parameters of the blade are obtained to correct the initial blade remaining life prediction model based on the material characteristic parameters to obtain a target blade life prediction model. By inputting the monitoring parameters of the target blade into the target blade life prediction model, multiple candidate remaining cycle periods corresponding to the target blade can be obtained. By determining the probability density estimate corresponding to the candidate remaining cycle periods, the remaining life of the target blade can be determined based on the probability density estimate. Establishing a prediction model based on the mapping relationship can improve the accuracy of the model prediction and improve the applicability of the model. Determining the remaining life of the target blade based on the kernel density estimation method fully considers the complexity and uncertainty of the target blade during actual operation, thereby enabling a more accurate prediction of the remaining life of the blade.

[0104] Figure 4 FIG. 1 is a flow chart showing a method for predicting the life of a gas turbine blade according to an exemplary embodiment. Figure 4 As shown, the life prediction method of the gas turbine blade of the embodiment of the present application includes but is not limited to the following steps:

[0105] S401 , simulating the performance of a gas turbine to obtain first degradation data of the gas turbine, and performing failure simulation on blades of the gas turbine based on the first degradation data to obtain second degradation data of the blades.

[0106] In the embodiment of the present application, the implementation method of step S401 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0107] S402 : Determine a first mapping relationship between the first degradation data and the second degradation data, and establish an initial blade life prediction model based on the first mapping relationship.

[0108] In the embodiment of the present application, the implementation method of step S402 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0109] S403: Acquire material characteristic parameters of the blade and distribution information of the material characteristic parameters.

[0110] In the embodiment of the present application, the implementation method of step S403 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0111] S404: Inputting the material characteristic parameters and distribution information into an initial blade life prediction model. The initial blade life prediction model simulates the material characteristic parameters based on the distribution information to obtain the distribution information of the remaining cycle period of the blade.

[0112] In some implementations, the material characteristic parameters include thermal conductivity, linear expansion coefficient, elastic modulus, Poisson's ratio, yield strength, and tensile strength. The material characteristic parameter C is expressed as follows:

[0113]

[0114] Where n represents the total number of material characteristic parameters, X i It refers to the distribution of the characteristic parameters of the i-th material.

[0115] The distribution of thermal conductivity γ is as follows: The distribution of linear expansion coefficient α is: The distribution of elastic modulus E is: The distribution of Poisson's ratio μ is: Yield strength σ 0.2 The distribution of is: Tensile limit σ b The distribution of is:

[0116] Optionally, by taking the material characteristic parameters and distribution information as the input of the initial blade life prediction model, the initial blade life prediction model simulates the material characteristic parameters multiple times within the dispersion band determined based on the distribution information, and the distribution information of the remaining cycle period of the blade can be obtained.

[0117] S405 , establishing a second mapping relationship between the monitorable parameters and the distribution information of the remaining cycle periods, and based on the second mapping relationship, correcting the initial blade life prediction model to obtain a target blade life prediction model.

[0118] In some implementations, to improve the accuracy of the blade life prediction model, the blade life prediction model can be modified. Optionally, the blade life prediction model can be modified based on a mapping relationship. A second mapping relationship between the monitored parameters and the distribution information of the remaining cycle period is established by fitting the distribution information of the monitored parameters and the distribution information of the remaining cycle period. The second mapping relationship is then used to modify the initial blade life prediction model to obtain a target blade life prediction model.

[0119] S406 , inputting the monitoring parameters of the target blade whose remaining life is to be predicted into the target blade life prediction model, and outputting the candidate remaining cycle period of the target blade and the confidence level corresponding to the candidate remaining cycle period.

[0120] In the embodiment of the present application, the implementation method of step S406 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0121] S407 , performing kernel density estimation on the candidate remaining cycle periods, and determining the remaining life of the target blade from the candidate remaining cycle periods according to the confidence level.

[0122] In the embodiment of the present application, the implementation method of step S407 can be implemented by any method in the various embodiments of the present application, which is not limited here and will not be repeated.

[0123] In a gas turbine blade life prediction method provided in an embodiment of the present application, first degradation data of the gas turbine and second degradation data of the gas turbine blade are obtained, and an initial blade remaining life prediction model is determined based on a first mapping relationship between the first degradation data and the second degradation data. Furthermore, material property parameters and distribution information of the blade are obtained, and the material property parameters are used as inputs to the initial blade remaining life prediction model to determine the distribution information of the blade's remaining cycles. A second mapping relationship is established based on the distribution information of the blade's remaining cycles, and the model is corrected using the second mapping relationship to obtain a target blade life prediction model. By inputting the monitoring parameters of the target blade into the target blade life prediction model, multiple candidate remaining cycles corresponding to the target blade are obtained. The remaining life of the target blade can be determined by performing kernel density estimation on the candidate remaining cycles. Establishing a prediction model based on the mapping relationship can improve the accuracy of the model prediction and enhance the model's applicability. Determining the target blade's remaining life based on the kernel density estimation method fully considers the complexity and uncertainty of the target blade during actual operation, thereby enabling more accurate prediction of the blade's remaining life.

[0124] like Figure 5 The flowchart for predicting the remaining life of gas turbine blades is shown in FIG. Figure 5 The method includes step S1, obtaining a degradation data set, step S2, establishing a mapping relationship, and step S3, predicting the remaining life.

[0125] In step S1, the gas turbine's operating parameters, atmospheric parameters, and degradation factors are acquired and input into a gas turbine performance simulation model to simulate the gas turbine's performance. The gas turbine's cross-sectional temperature, cross-sectional pressure, and turbine speed are obtained as first degradation data. Furthermore, the first degradation data is input into a blade failure model to perform a blade failure simulation, obtaining the blade's temperature distribution, stress distribution, and cycle time as second degradation data. The operating parameters, atmospheric parameters, degradation factors, and first degradation data are used as monitorable gas turbine parameters, and the second degradation data is used as reliability parameters. A degradation dataset is then established based on the monitorable and reliability parameters.

[0126] In step S2, the monitorable parameters and reliability parameters are fitted to establish a first mapping relationship between the monitorable parameters and the reliability parameters, and the training set and test set for model training are determined based on the monitorable parameters, reliability parameters and the first mapping relationship, so as to train the model using the training set, and verify the model performance using the test set after the training, and adjust the model to obtain an initial blade life prediction model.

[0127] In step S3, the material characteristic parameters and distribution information of the blade are obtained and input into an initial blade life prediction model. The initial blade life prediction model simulates the material characteristic parameters based on the distribution information to obtain the distribution information of the blade's remaining cycle period. A second mapping relationship between the monitorable parameters and the distribution information of the remaining cycle period is established, and based on the second mapping relationship, the initial blade life prediction model is modified to obtain a target blade life prediction model. Furthermore, the target blade for which the remaining life is to be predicted is monitored in real time to obtain the temperature distribution and stress distribution of the target blade as monitoring parameters. The monitoring parameters are input into the target blade life prediction model, which then predicts the remaining life of the target blade based on the monitoring parameters. Multiple candidate remaining cycle periods corresponding to the target blade and a confidence level corresponding to each candidate remaining cycle period are output. Kernel density estimation is then performed on the candidate remaining cycle periods, and the remaining life of the target blade is determined from the candidate remaining cycle periods based on the confidence level.

[0128] In order to implement the above embodiment, the present application also proposes a life prediction device for gas turbine blades.

[0129] Figure 6 A schematic structural diagram of a gas turbine blade life prediction device provided in an embodiment of the present application.

[0130] like Figure 6As shown, the life prediction device 600 for a gas turbine blade includes:

[0131] a simulation module 601 configured to simulate the performance of a gas turbine to obtain first degradation data of the gas turbine, and perform failure simulation on a blade of the gas turbine based on the first degradation data to obtain second degradation data of the blade;

[0132] Establishing module 602, configured to determine a first mapping relationship between the first degradation data and the second degradation data, and establish an initial blade life prediction model based on the first mapping relationship;

[0133] A correction module 603 is configured to obtain material characteristic parameters of the blade and distribution information of the material characteristic parameters, and to correct the initial blade life prediction model based on the material characteristic parameters and the distribution information to obtain a target blade life prediction model;

[0134] The prediction module 604 is configured to input the monitoring parameters of the target blade whose remaining life is to be predicted into the target blade life prediction model, and output a candidate remaining cycle period of the target blade and a confidence level corresponding to the candidate remaining cycle period;

[0135] The determination module 605 is configured to perform kernel density estimation on the candidate remaining cycle periods and determine the remaining life of the target blade from the candidate remaining cycle periods according to the confidence level.

[0136] In a possible implementation of an embodiment of the present application, the simulation module 601 is further used to: obtain the operating parameters, atmospheric parameters and degradation factors of the gas turbine, and simulate the performance of the gas turbine based on the operating parameters, the atmospheric parameters and the degradation factors, and obtain the cross-sectional temperature, cross-sectional pressure and engine speed of the gas turbine as the first degradation data; based on the first degradation data and the reference failure mode of the blade, perform failure simulation on the blade, and obtain the temperature distribution, stress distribution and cycle period of the blade as the second degradation data.

[0137] In a possible implementation of an embodiment of the present application, the establishment module 602 is further used to: determine the monitorable parameters and reliability parameters of the gas turbine based on the operating condition parameters, the atmospheric parameters and the degradation factor, as well as the first degradation data and the second degradation data; and fit the monitorable parameters and the reliability parameters to obtain the first mapping relationship.

[0138] In a possible implementation of an embodiment of the present application, the establishment module 602 is also used to: determine the intermediate variables of the first mapping relationship, and correct the first mapping relationship based on the intermediate variables to obtain a corrected first mapping relationship; and establish the initial blade life prediction model based on the corrected first mapping relationship.

[0139] In a possible implementation of an embodiment of the present application, the determination module 605 is further used to: determine the kernel function and bandwidth used in kernel density estimation, and determine the probability density estimation value of each candidate remaining cycle period based on the kernel function and the bandwidth; determine the candidate kernel density estimation map corresponding to the candidate remaining cycle period based on the probability density value and the confidence level; determine the confidence interval based on the number of candidate remaining cycle periods, and determine the remaining life of the target blade based on the confidence interval and the candidate kernel density estimation map.

[0140] In a possible implementation of an embodiment of the present application, the determination module 605 is also used to: determine a kernel density estimation map within the confidence interval from the candidate kernel density estimation map, and use the candidate remaining cycle period corresponding to the kernel density estimation map as the remaining life of the target blade.

[0141] In a possible implementation of an embodiment of the present application, the determination module 605 is further used to: determine the average integrated square error of the kernel density estimation, and based on the average integrated square error, determine the asymptotic mean integrated square error of the kernel density estimation; determine the minimum value of the asymptotic mean integrated square error, and obtain the bandwidth based on the minimum value.

[0142] In a possible implementation of an embodiment of the present application, the correction module 603 is also used to: input the material characteristic parameters and the distribution information into the initial blade life prediction model, and the initial blade life prediction model simulates the material characteristic parameters based on the distribution information to obtain the distribution information of the remaining cycle period of the blade; establish a second mapping relationship between the monitorable parameters and the distribution information of the remaining cycle period, and based on the second mapping relationship, correct the initial blade life prediction model to obtain a target blade life prediction model.

[0143] In a possible implementation of the embodiment of the present application, the material characteristic parameters include thermal conductivity, linear expansion coefficient, elastic modulus, Poisson's ratio, yield strength and tensile limit.

[0144] In the life prediction device for gas turbine blades provided in an embodiment of the present application, first degradation data of the gas turbine and second degradation data of the gas turbine blades are obtained, and an initial blade remaining life prediction model is determined based on a first mapping relationship between the first degradation data and the second degradation data. Furthermore, the material characteristic parameters of the blades are obtained to correct the initial blade remaining life prediction model based on the material characteristic parameters to obtain a target blade life prediction model. By inputting the monitoring parameters of the target blades into the target blade life prediction model, a plurality of candidate remaining cycles corresponding to the target blades can be obtained. By performing kernel density estimation on the candidate remaining cycles, the remaining life of the target blades can be determined. Establishing a prediction model based on the mapping relationship can improve the accuracy of the model prediction and improve the applicability of the model. Determining the remaining life of the target blade based on the kernel density estimation method fully takes into account the complexity and uncertainty of the target blades during actual operation, thereby enabling a more accurate prediction of the remaining life of the blades.

[0145] It should be noted that the above explanation of the embodiment of the method for predicting the life of a gas turbine blade is also applicable to the device for predicting the life of a gas turbine blade in this embodiment, and will not be repeated here.

[0146] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0147] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0148] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0149] The collection, storage, use, processing, transmission, provision and application of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0150] It is important to note that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold beyond these legitimate uses. Furthermore, such collection / sharing should be conducted only after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes the relevant user information before using the feature. Furthermore, any necessary steps must be taken to safeguard and secure access to such personal information and ensure that others with access to personal information comply with its privacy policy and procedures.

[0151] This application contemplates providing implementation options for users to selectively block the use or access of personal information data. Specifically, this application contemplates providing hardware and / or software to prevent or block access to such personal information data. Risks can be minimized by limiting data collection and deleting data once it is no longer needed. Furthermore, where applicable, such personal information can be de-identified to protect user privacy.

[0152] In the descriptions of the foregoing embodiments, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are mutually inconsistent.

[0153] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0154] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0155] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0156] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0157] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0158] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0159] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for predicting the life of a gas turbine blade, characterized in that: include: Simulating the performance of a gas turbine to obtain first degradation data of the gas turbine, and performing failure simulation on a blade of the gas turbine based on the first degradation data to obtain second degradation data of the blade; Determining a first mapping relationship between the first degradation data and the second degradation data, and establishing an initial blade life prediction model based on the first mapping relationship; Acquiring material characteristic parameters of the blade and distribution information of the material characteristic parameters, and modifying the initial blade life prediction model according to the material characteristic parameters and the distribution information to obtain a target blade life prediction model; Inputting monitoring parameters of a target blade whose remaining life is to be predicted into the target blade life prediction model, and outputting a candidate remaining cycle period of the target blade and a confidence level corresponding to the candidate remaining cycle period; Kernel density estimation is performed on the candidate remaining cycle periods, and the remaining life of the target blade is determined from the candidate remaining cycle periods according to the confidence level.

2. The method according to claim 1, characterized in that: The simulating the performance of the gas turbine to obtain first degradation data of the gas turbine, and performing failure simulation on the blades of the gas turbine based on the first degradation data to obtain second degradation data of the blades, comprises: Acquiring operating parameters, atmospheric parameters and degradation factors of the gas turbine, and simulating the performance of the gas turbine based on the operating parameters, the atmospheric parameters and the degradation factors, to obtain a cross-sectional temperature, a cross-sectional pressure and a rotation speed of the gas turbine as the first degradation data; Based on the first degradation data and a reference failure mode of the blade, a failure simulation is performed on the blade to obtain a temperature distribution, a stress distribution and a cycle period of the blade as the second degradation data.

3. The method according to claim 2, characterized in that The determining a first mapping relationship between the first degradation data and the second degradation data includes: Determining a monitorable parameter and a reliability parameter of the gas turbine according to the operating condition parameter, the atmospheric parameter and the degradation factor, and the first degradation data and the second degradation data; The monitorable parameter and the reliability parameter are fitted to obtain the first mapping relationship.

4. The method according to claim 1 or 3, characterized in that: The establishing of an initial blade life prediction model based on the first mapping relationship further includes: Determining an intermediate variable of the first mapping relationship, and modifying the first mapping relationship based on the intermediate variable to obtain a modified first mapping relationship; Based on the corrected first mapping relationship, the initial blade life prediction model is established.

5. The method according to claim 1, characterized in that: The performing kernel density estimation on the candidate remaining cycle periods and determining the remaining life of the target blade from the candidate remaining cycle periods according to the confidence level comprises: Determine a kernel function and a bandwidth used in kernel density estimation, and determine a probability density estimate of each candidate remaining cycle period based on the kernel function and the bandwidth; Determine, based on the probability density value and the confidence level, a candidate kernel density estimation graph corresponding to the candidate remaining cycle period; A confidence interval is determined based on the number of candidate remaining cycles, and a remaining life of the target blade is determined based on the confidence interval and the candidate kernel density estimate map.

6. The method according to claim 5, characterized in that The determining the remaining life of the target blade based on the confidence interval and the candidate kernel density estimation map includes: A kernel density estimation map within the confidence interval is determined from the candidate kernel density estimation maps, and the candidate remaining cycle period corresponding to the kernel density estimation map is used as the remaining life of the target blade.

7. The method according to claim 5, characterized in that The process of determining the bandwidth includes: Determining a mean integrated square error of the kernel density estimate, and based on the mean integrated square error, determining an asymptotic mean integrated square error of the kernel density estimate; A minimum value of the asymptotic mean integrated square error is determined, and the bandwidth is obtained based on the minimum value.

8. The method according to claim 1, characterized in that The initial blade life prediction model is modified according to the material characteristic parameters and the distribution information to obtain a target blade life prediction model, including: Inputting the material characteristic parameters and the distribution information into the initial blade life prediction model, the initial blade life prediction model simulates the material characteristic parameters based on the distribution information to obtain the distribution information of the remaining cycle period of the blade; A second mapping relationship between the monitorable parameter and the distribution information of the remaining cycle period is established, and based on the second mapping relationship, the initial blade life prediction model is corrected to obtain a target blade life prediction model.

9. The method according to claim 1, characterized in that: The material characteristic parameters include thermal conductivity, linear expansion coefficient, elastic modulus, Poisson's ratio, yield strength and tensile limit.

10. A life prediction device for a gas turbine blade, characterized in that: include: a simulation module, configured to simulate the performance of a gas turbine to obtain first degradation data of the gas turbine, and perform failure simulation on a blade of the gas turbine based on the first degradation data to obtain second degradation data of the blade; An establishing module, configured to determine a first mapping relationship between the first degradation data and the second degradation data, and to establish an initial blade life prediction model based on the first mapping relationship; A correction module, used for obtaining material characteristic parameters of the blade and distribution information of the material characteristic parameters, and correcting the initial blade life prediction model according to the material characteristic parameters and the distribution information to obtain a target blade life prediction model; A prediction module, used for inputting monitoring parameters of a target blade whose remaining life is to be predicted into the target blade life prediction model, and outputting a candidate remaining cycle period of the target blade and a confidence level corresponding to the candidate remaining cycle period; A determination module is used to perform kernel density estimation on the candidate remaining cycle periods and determine the remaining life of the target blade from the candidate remaining cycle periods according to the confidence level.

11. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 9 when executed by a processor.

13. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 9 when being executed by a processor.

Images