CN114459644A - Identification method of landing gear drop load based on optical fiber strain response and Gaussian process - Google Patents

Abstract

The invention relates to an undercarriage drop load identification method based on optical fiber strain response and Gaussian process, which is characterized in that S FBG sensors distributed along the direction of a bearing structure at preset positions on a target undercarriage supporting arm are used for constructing drop load prediction data which respectively comprise noise at each time point in the sinking duration of a test working condition and correspond to a target undercarriage according to Gaussian process regression models f-GP (mu (-) and k (-) on the basis of S FBG sensors

Training under training conditions and testing conditions in each constructed sample by combining with the corresponding overflow conditions compared with the actual measured values to obtain a falling load identification model corresponding to the target undercarriage; further, in practical application, the falling shock can be passedThe load identification model realizes real-time identification of the falling load of the target undercarriage, and can effectively improve the working efficiency of health monitoring of the target undercarriage.

Description

Identification method of landing gear drop load based on optical fiber strain response and Gaussian process

technical field

The invention relates to a landing gear drop shock load identification method based on optical fiber strain response and Gaussian process, and belongs to the technical field of landing gear drop shock load identification.

Background technique

Studies have shown that flight accidents often occur during take-off and landing, and more than 50% of safety accidents occur during take-off and landing. The fundamental reason is that only the static strength of the structure is considered in the design of the landing gear, and the fatigue strength and durability of the structure are not affected. Sexual consideration is less. Therefore, carrying out real-time monitoring of landing gear shock loads has become an important part of aircraft health management, which can provide technical support for future multi-functional/integrated landing gear designs.

SUMMARY OF THE INVENTION

The technical problem to be solved by the present invention is to provide a landing gear drop shock load identification method based on optical fiber strain response and Gaussian process, and the characteristic characterization method can realize efficient and fast drop shock load monitoring for the landing gear.

In order to solve the above-mentioned technical problems, the present invention adopts the following technical solutions: the present invention designs a landing gear drop shock load identification method based on optical fiber strain response and Gaussian process, based on the preset positions on the target landing gear support arm distributed along the direction of the bearing structure. S FBG sensors to realize the shock load identification for the target landing gear; according to step A to step H, obtain the shock load identification model corresponding to the target landing gear; then execute step i in real time to realize the shock load of the target landing gear real-time identification;

Step A. Based on the preset number M working conditions composed of preset different delivery weights carried on the support arm of the target landing gear and preset different sinking speeds corresponding to the target landing gear, obtain each time within the sinking duration of each working condition point, the strain response data set corresponding to each FBG sensor on the support arm of the target landing gear, and the measurement data of the drop shock load of the target landing gear at each time point within the sinking duration of various working conditions, and then enter step B;

Step B. Based on m≤M/2, randomly select m working conditions among the M working conditions to form each training condition, and at the same time select m working conditions randomly from the remaining working conditions in the M working conditions to form Each test condition is constructed, and a random one-to-one relationship between each training condition and each test condition is constructed to form m samples, and then proceed to step C;

Step C. The s FBG sensors randomly selected from the S FBG sensors are used as each target FBG sensor, and then step D is entered;

Step D. Based on the input of the strain response data set corresponding to each FBG sensor on the support arm of the target landing gear at each time point in the sinking duration of the working condition and the corresponding noise contained in the target landing gear at each time point in the sinking duration of the working condition and the target landing gear. The predicted data of the drop load is the output Gaussian process regression model f, combined with f ~ GP(μ( ), k( )), the target landing gear support arm at each time point in the training condition sinking duration in the sample The strain response data set X _i corresponding to each FBG sensor above, the measured data F i, of the drop shock load of the target landing gear at each time point within the sinking duration of the training condition in this sample, and the measured data F _{i, measured} under the sinking duration of the test condition in this sample, within the sinking duration of the test condition in this sample For the strain response data set Y _j corresponding to each FBG sensor on the target landing gear support arm at each time point, the following model is constructed:

Among them, 1≤i≤I, I represents the number of each time point in the subsidence duration of the training condition in the sample; J represents the number of each time point in the subsidence duration of the test condition in the corresponding sample, F _{j, predenotes} the In the sample, the noise-free drop load prediction data corresponding to the target landing gear at each time point in the subsidence duration of the test condition; μ( ^· ) represents the mean function, μ(·) includes μ _i and μ _j ; The noise variance corresponding to the load history response of the landing gear drop shock, I' represents the unit matrix, K(X _i , X _i ) is the covariance matrix of the strain response characteristic of the landing gear drop shock history corresponding to the sample training condition, K(X _i , Y _j ) is the covariance matrix between the training condition and the test condition in the sample corresponding to the strain response characteristic of the landing gear drop history, K(Y _j , Y _j ) is the landing gear drop history strain response characteristic corresponding to the sample The covariance matrix of the test condition, μ _i and μ _j represent the mean function of the landing gear drop shock history strain response characteristic corresponding to the training condition and the test condition in the sample; k( ) represents the covariance function; N represents the joint Normal distribution symbol; then go to step E;

Step E. Calculate and obtain the value of each hyperparameter involved in the covariance function k( ), and combine the model constructed in step D and the Bayesian principle to obtain the subsidence duration of the test condition in the sample. The time point, the target landing gear corresponds to the noise-free drop load prediction data F _{j, the pre-} posterior distribution, and then enter step F;

然后进入步骤G；Step F. According to the predicted posterior distribution of the noise-free drop load _Fj corresponding to the target landing gear at each time point within the subsidence duration of the test condition in the sample, the subsidence duration of the test condition in the sample is obtained. Prediction data of drop shock load including noise corresponding to each time point in the target landing gear

Then enter step G;

以及该样本中测试工况下沉时长内各时间点、目标起落架落震载荷测量数据F_j,测，以两者之间差值与预设差值阈值的比较构成溢出条件，然后进入步骤H；Step G. According to the predicted data of the drop shock load containing noise corresponding to the target landing gear at each time point within the subsidence duration of the test condition in the sample

And each time point in the test condition subsidence duration in this sample, the measured data _{Fj of the drop shock load of the target landing gear is measured} , and the comparison between the difference between the two and the preset difference threshold constitutes an overflow condition, and then enters the step H;

Step H. Based on each sample, according to the above-mentioned steps D to step G, training is carried out for the Gaussian process regression model f, and the Gaussian process regression model after the training is obtained, which is the shock load identification model corresponding to the target landing gear;

Step i. Obtain the strain response data set corresponding to each FBG sensor on the support arm of the target landing gear at each time point within the sinking duration of the real-time working condition of the target landing gear, and apply the shock load identification model corresponding to the target landing gear to obtain the target landing gear. The landing gear corresponds to each time point in the sinking duration of the working condition, and the target landing gear corresponds to the drop shock load prediction data containing noise, so as to realize the real-time identification of the target landing gear drop shock load.

As a preferred technical solution of the present invention: the μ _i =0, μ _j =0, the covariance function k(·) is as follows:

k(a,b)=λ ₁ k _RBF (a,b)+λ ₂ k _PKF (a,b)+λ ₃ k _Noise (a,b)

in:

k _PKF (a,b)=(a·b+1) ^q

k _Noise (a,b)=σ _N ² δ ^*

In the formula, λ ₁ , λ ₂ , λ ₃ represent preset weighting factors, and satisfy 0<λ ₁ ≤0.5, 0<λ ₂ ≤0.5, 0<λ ₃ ≤0.5, λ ₁ +λ ₂ +λ ₃ =1 ; σ _f , σ _l , σ _N represent the hyperparameters involved in the covariance function k(·); q represents the polynomial degree; δ ^* represents the Kronecker function.

As a preferred technical solution of the present invention: in the step E, calculate and obtain the value of each hyperparameter involved in the covariance function k( ) as follows;

Firstly, the maximum likelihood function is constructed by using the seismic history strain response characteristics of the target landing gear corresponding to the test conditions in the sample, and the unknown hyperparameters involved in the covariance function k( ), and according to the Bayesian principle, according to the likelihood The integral of P(f _j |f _i ,X _i ,θ) and the prior P(f _i |X _i ,θ), that is, the edge likelihood P(f _j |X _i ,θ) is as follows:

P(f _j |X _i ,θ)=∫P(f _j |f _i ,X _i ,θ)P(f _i |X _i ,θ)df _i =N(f _i |0,K(X _i , X _i )+σ ² I)

Among them, θ represents the vector composed of unknown hyperparameters involved in the covariance function k( );

Then for the edge likelihood P(f _j |X _i ,θ), take the logarithm to obtain the logarithmic edge likelihood as follows:

Among them, N' represents the number of time points in the subsidence duration of the working condition, that is, the sampling frequency;

Finally, according to the principle of matrix calculus, for each unknown hyperparameter θ _i involved in the covariance function k(·), the following formulas are used:

T表示转置。Obtain the value of θ _i corresponding to the maximum probability by derivation, that is, obtain the value of the hyperparameter involved in the covariance function k( ), and then obtain the value of each unknown hyperparameter involved in the covariance function k( ); where Tr represents the trace of the matrix,

T stands for transpose.

As a preferred technical solution of the present invention: in the step F, according to each time point within the subsidence duration of the test condition in the sample and the noise-free shock load prediction data F _j corresponding to the target landing gear, the predicted The test distribution, according to the following formula:

cov(F _{j, pre} )=K(Y _j ,Y _j )-K(Y _j ,X _i )[K(X _i ,X _i )+σ ² I'] ^-1 K(X _i ,Y _j )

其中，cov(F_j,预)表示目标起落架落震载荷历程响应预测值的置信水平。Obtain the predicted data of the drop shock load including noise corresponding to the target landing gear at each time point in the subsidence duration of the test condition in this sample

Among them, cov(F _{j, pre} ) represents the confidence level of the predicted value of the target landing gear drop shock load history response.

The method for identifying the landing gear drop shock load based on the optical fiber strain response and the Gaussian process of the present invention adopts the above technical solution and has the following technical effects compared with the prior art:

并结合与实际测量值之间比较所对应的溢出条件，在所构建各样本中训练工况、测试工况下进行训练，获得目标起落架所对应的落震载荷辨识模型；进而在实际应用中，即可通过该落震载荷辨识模型，对目标起落架的落震载荷实现实时辨识，能够有效提高目标起落架健康监测的工作效率。(1) The landing gear drop shock load identification method based on the optical fiber strain response and Gaussian process is designed in the present invention, based on S FBG sensors distributed at the preset position on the target landing gear support arm along the direction of the load-bearing structure, according to the Gaussian process regression Model f～GP(μ(·),k(·)), construct the prediction data of drop shock load including noise corresponding to each time point in the subsidence duration of the test condition and the target landing gear

Combined with the corresponding overflow conditions compared with the actual measured values, training is carried out under the training conditions and test conditions in each constructed sample to obtain the shock load identification model corresponding to the target landing gear; and then in practical applications , the drop load identification model can be used to realize real-time identification of the drop load of the target landing gear, which can effectively improve the work efficiency of the target landing gear health monitoring.

Description of drawings

1 is a schematic diagram of the application structure of the optical fiber identification of the landing gear drop shock load in the design of the present invention;

Fig. 2 is a flowchart of the optical fiber identification of landing gear drop shock load based on Gaussian process regression.

Detailed ways

The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

The invention designs a landing gear drop shock load identification method based on optical fiber strain response and Gaussian process, and based on S FBG sensors distributed at preset positions on the support arm of the target landing gear along the direction of the load-bearing structure, the landing gear landing gear landing gear is designed in the present invention. Seismic load identification.

Regarding the above design of distributing S FBG sensors at preset positions, in practical applications, as shown in Figure 1, such as selecting a monitoring area along the direction of the bearing structure on the outer surface of the support arm of the target landing gear, and arranging 4 FBG sensors in the monitoring area FBG sensors are recorded as FBG1, FBG2, FBG3, ..., FBGk respectively, where 1≤S≤10; the arrangement position of the FBG sensor should be based on the structural form of the support arm and the load characteristics, when the strain amplitude is large and the strain gradient is large. The number of FBG sensors can be appropriately increased in the key parts of the measurement; in areas with small strain gradients, the number of FBG sensors can be reduced; wavelength division multiplexing technology is used to connect the S FBG sensors in series, and then connect the These FBG sensors are pasted on the outer surface of the support arm structure to form a FBG sensor monitoring network, as shown in Figure 1, which is used to collect the strain response signal of the support arm during the fall of the target landing gear.

The reason why FBG sensors are selected is that fiber Bragg grating sensors (FBGs) use optical signals as carriers and have unique advantages such as corrosion resistance, light weight, and anti-electromagnetic interference. They can also realize multi-parameter monitoring and distributed sensing arrangements. The large-scale and complex structure in the spacecraft can better reflect its unique advantages.

Based on the distribution setting of the preset positions of the S FBG sensors on the support arm of the target landing gear along the direction of the bearing structure, in practical application, as shown in Figure 2, according to steps A to H, the shock load corresponding to the target landing gear is obtained Identify the model.

Step A. Based on the preset number M working conditions composed of preset different delivery weights carried on the support arm of the target landing gear and preset different sinking speeds corresponding to the target landing gear, obtain each time within the sinking duration of each working condition point, the strain response data set corresponding to each FBG sensor on the support arm of the target landing gear, and the measurement data of the drop shock load of the target landing gear at each time point within the sinking duration of various working conditions, and then go to step B.

Step B. Based on m≤M/2, randomly select m working conditions among the S working conditions to form each training condition, and at the same time select m working conditions randomly from the remaining working conditions in the M working conditions to form Each test condition is constructed, and a random one-to-one relationship between each training condition and each test condition is constructed to form m samples, and then step C is entered.

Step C. The s FBG sensors randomly selected from the S FBG sensors are used as the target FBG sensors, and then step D is entered.

Step D. Based on the input of the strain response data set corresponding to each FBG sensor on the support arm of the target landing gear at each time point in the sinking duration of the working condition and the corresponding noise contained in the target landing gear at each time point in the sinking duration of the working condition and the target landing gear. The predicted data of the drop load is the output Gaussian process regression model f, combined with f ~ GP(μ( ), k( )), the target landing gear support arm at each time point in the training condition sinking duration in the sample The strain response data set X _i corresponding to each FBG sensor above, the measured data F i, of the drop shock load of the target landing gear at each time point within the sinking duration of the training condition in this sample, and the measured data F _{i, measured} under the sinking duration of the test condition in this sample, within the sinking duration of the test condition in this sample For the strain response data set Y _j corresponding to each FBG sensor on the target landing gear support arm at each time point, the following model is constructed:

Among them, 1≤i≤I, I represents the number of each time point in the subsidence duration of the training condition in the sample; J represents the number of each time point in the subsidence duration of the test condition in the corresponding sample, F _{j, predenotes} the In the sample, the noise-free drop load prediction data corresponding to the target landing gear at each time point in the subsidence duration of the test condition; μ( ^· ) represents the mean function, μ(·) includes μ _i and μ _j ; The noise variance corresponding to the load history response of the landing gear drop shock, I' represents the unit matrix, K(X _i , X _i ) is the covariance matrix of the strain response characteristic of the landing gear drop shock history corresponding to the sample training condition, K(X _i , Y _j ) is the covariance matrix between the training condition and the test condition in the sample corresponding to the strain response characteristic of the landing gear drop history, K(Y _j , Y _j ) is the landing gear drop history strain response characteristic corresponding to the sample The covariance matrix of the test condition, μ _i and μ _j represent the mean function of the landing gear drop shock history strain response characteristic corresponding to the training condition and the test condition in the sample; k( ) represents the covariance function; N represents the joint Normal distribution symbol; then go to step E.

In the specific calculation application, based on μ _i =0, μ _j =0, the above covariance function k(·) is as follows:

k(a,b)=λ ₁ k _RBF (a,b)+λ ₂ k _PKF (a,b)+λ ₃ k _Noise (a,b)

in:

k _PKF (a,b)=(a·b+1) ^q

k _Noise (a,b)=σ _N ² δ ^*

In the formula, λ ₁ , λ ₂ , λ ₃ represent preset weighting factors, and satisfy 0<λ ₁ ≤0.5, 0<λ ₂ ≤0.5, 0<λ ₃ ≤0.5, λ ₁ +λ ₂ +λ ₃ =1 ; σ _f , σ _l , σ _N represent the hyperparameters involved in the covariance function k(·); q represents the polynomial degree; δ ^* represents the Kronecker function.

In practical applications, according to the Bayesian principle, the model constructed in step D can obtain the noise-free drop shock load prediction of the target landing gear at each time point in the subsidence duration of the test condition in this sample and the target landing gear The data _{Fj, predistributed} as follows:

Step E. Calculate and obtain the value of each hyperparameter involved in the covariance function k( ), and combine the model constructed in step D and the Bayesian principle to obtain the subsidence duration of the test condition in the sample. The time point, the target landing gear corresponds to the noise-free shock load prediction data F _{j, the pre-} posterior distribution, and then go to step F.

In the above step E, the value of each hyperparameter involved in the covariance function k(·) is calculated and obtained in the following manner.

Firstly, the maximum likelihood function is constructed by using the seismic history strain response characteristics of the target landing gear corresponding to the test conditions in the sample, and the unknown hyperparameters involved in the covariance function k( ), and according to the Bayesian principle, according to the likelihood The integral of P(f _j |f _i ,X _i ,θ) and the prior P(f _i |X _i ,θ), that is, the edge likelihood P(f _j |X _i ,θ) is as follows:

P(f _j |X _i ,θ)=∫P(f _j |f _i ,X _i ,θ)P(f _i |X _i ,θ)df _i =N(f _i |0,K(X _i , X _i )+σ ² I)

Among them, θ represents the vector of unknown hyperparameters involved in the covariance function k(·).

Then for the edge likelihood P(f _j |X _i ,θ), take the logarithm to obtain the logarithmic edge likelihood as follows:

Among them, N' represents the number of each time point in the subsidence duration of the working condition, that is, the sampling frequency.

Finally, according to the principle of matrix calculus, for each unknown hyperparameter θ _i involved in the covariance function k(·), the following formulas are used:

T表示转置。Obtain the value of θ _i corresponding to the maximum probability by derivation, that is, obtain the value of the hyperparameter involved in the covariance function k( ), and then obtain the value of each unknown hyperparameter involved in the covariance function k( ); where Tr represents the trace of the matrix,

T stands for transpose.

After obtaining the value of each hyperparameter involved in the covariance function k( ), determine the covariance function k( ) based on the value of each hyperparameter, and combine the model constructed in step D and the Bayesian principle , obtain the _{pre-posterior distribution of the noise-free drop load prediction data F j} corresponding to the target landing gear at each time point within the subsidence duration of the test condition in the sample, and then enter step F.

Step F. According to the predicted data F _{j of the drop shock load without noise corresponding to the target landing gear at each time point within the subsidence duration of the test condition in the sample, the pre-} posterior distribution is as follows:

cov(F _{j, pre} )=K(Y _j ,Y _j )-K(Y _j ,X _i )[K(X _i ,X _i )+σ ² I'] ^-1 K(X _i ,Y _j )

其中，cov(F_j,预)表示目标起落架落震载荷历程响应预测值的置信水平，然后进入步骤G。Obtain the predicted data of the drop shock load including noise corresponding to the target landing gear at each time point in the subsidence duration of the test condition in this sample

Among them, cov(F _{j, pre} ) represents the confidence level of the predicted value of the target landing gear drop shock load history response, and then go to step G.

以及该样本中测试工况下沉时长内各时间点、目标起落架落震载荷测量数据F_j,测，以两者之间差值与预设差值阈值的比较构成溢出条件，然后进入步骤H。Step G. According to the predicted data of the drop shock load containing noise corresponding to the target landing gear at each time point within the subsidence duration of the test condition in the sample

And each time point in the test condition subsidence duration in this sample, the measured data _{Fj of the drop shock load of the target landing gear is measured} , and the comparison between the difference between the two and the preset difference threshold constitutes an overflow condition, and then enters the step H.

Step H. Based on each sample, according to the above steps D to G, train the Gaussian process regression model f to obtain the trained Gaussian process regression model, which is the shock load identification model corresponding to the target landing gear.

Based on the acquisition of the drop shock load identification model corresponding to the target landing gear, and further based on this model, step i is executed in real time to realize the real-time identification of the drop shock load of the target landing gear.

Step i. Obtain the strain response data set corresponding to each FBG sensor on the support arm of the target landing gear at each time point within the sinking duration of the real-time working condition of the target landing gear, and apply the shock load identification model corresponding to the target landing gear to obtain the target landing gear. The landing gear corresponds to each time point in the sinking duration of the working condition, and the target landing gear corresponds to the drop shock load prediction data containing noise, so as to realize the real-time identification of the target landing gear drop shock load.

并结合与实际测量值之间比较所对应的溢出条件，在所构建各样本中训练工况、测试工况下进行训练，获得目标起落架所对应的落震载荷辨识模型；进而在实际应用中，即可通过该落震载荷辨识模型，对目标起落架的落震载荷实现实时辨识，能够有效提高目标起落架健康监测的工作效率。The above technical solution designs a landing gear drop shock load identification method based on optical fiber strain response and Gaussian process, based on S FBG sensors arranged at preset positions on the target landing gear support arm along the direction of the load-bearing structure, according to the Gaussian process regression model f ～GP(μ(·),k(·)), construct the drop shock load prediction data including noise corresponding to the target landing gear at each time point in the subsidence duration of the test condition

Combined with the corresponding overflow conditions compared with the actual measured values, training is carried out under the training conditions and test conditions in each constructed sample to obtain the shock load identification model corresponding to the target landing gear; and then in practical applications , the drop load identification model can be used to realize real-time identification of the drop load of the target landing gear, which can effectively improve the work efficiency of the target landing gear health monitoring.

The embodiments of the present invention have been described in detail above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned embodiments, and can also be made within the scope of knowledge possessed by those of ordinary skill in the art without departing from the purpose of the present invention. Various changes.

Claims (4)

1. The landing gear drop load identification method based on optical fiber strain response and Gaussian process, based on S FBG sensors distributed at the preset position on the target landing gear support arm along the direction of the bearing structure, to achieve the target landing gear drop load identification; it is characterized in that: according to step A to step H, obtain the shock load identification model corresponding to the target landing gear; then perform step i in real time to realize the real-time identification of the target landing gear shock load; Step A. Based on the preset number M working conditions composed of preset different delivery weights carried on the support arm of the target landing gear and preset different sinking speeds corresponding to the target landing gear, obtain each time within the sinking duration of each working condition point, the strain response data set corresponding to each FBG sensor on the support arm of the target landing gear, and the measurement data of the drop shock load of the target landing gear at each time point within the sinking duration of various working conditions, and then enter step B; Step B. Based on m≤M/2, randomly select m working conditions among the M working conditions to form each training condition, and at the same time select m working conditions randomly from the remaining working conditions in the M working conditions to form Each test condition is constructed, and a random one-to-one relationship between each training condition and each test condition is constructed to form m samples, and then proceed to step C; Step C. The s FBG sensors randomly selected from the S FBG sensors are used as each target FBG sensor, and then step D is entered; Step D. Based on the input of the strain response data set corresponding to each FBG sensor on the support arm of the target landing gear at each time point in the sinking duration of the working condition and the corresponding noise contained in the target landing gear at each time point in the sinking duration of the working condition and the target landing gear. The predicted data of the drop load is the output Gaussian process regression model f, combined with f ~ GP(μ( ), k( )), the target landing gear support arm at each time point in the training condition sinking duration in the sample The strain response data set X _i corresponding to each FBG sensor above, the measured data F i of the drop shock load of the target landing gear at each time point within the subsidence duration of the training condition in this sample, the measured data F _{i of the} drop shock load of the target landing gear in this sample, the subsidence duration of the test condition in this sample is For the strain response data set Y _j corresponding to each FBG sensor on the target landing gear support arm at each time point, the following model is constructed:

Among them, 1≤i≤I, I represents the number of each time point in the subsidence duration of the training condition in the sample; J represents the number of each time point in the subsidence duration of the test condition in the corresponding sample, F _{j, pre-} represents the In the sample, the noise-free drop load prediction data corresponding to the target landing gear at each time point in the subsidence duration of the test condition; μ( ^· ) represents the mean function, μ(·) includes μ _i and μ _j ; The noise variance corresponding to the load history response of the landing gear drop shock, I′ represents the unit matrix, K(X _i , X _i ) is the covariance matrix of the strain response characteristic of the landing gear drop shock history corresponding to the sample training condition, K(X _i , Y _j ) is the covariance matrix between the training condition and the test condition in the sample corresponding to the strain response characteristics of the landing gear drop history, K(Y _j , Y _j ) is the landing gear drop history strain response characteristic corresponding to the sample The covariance matrix of the test condition, μ _i and μ _j represent the mean function of the landing gear drop shock history strain response characteristic corresponding to the training condition and the test condition in the sample; k( ) represents the covariance function; N represents the joint Normal distribution symbol; then go to step E; Step E. Calculate and obtain the value of each hyperparameter involved in the covariance function k( ), and combine the model constructed in step D and the Bayesian principle to obtain the subsidence duration of the test condition in the sample. Time point, the target landing gear corresponds to the noise-free shock load prediction data F _{j, the pre-} posterior distribution, and then enter step F; Step F. According to the _{pre-posterior distribution of the noise-free drop load prediction data F j} corresponding to the target landing gear at each time point within the subsidence duration of the test condition in the sample, the subsidence duration of the test condition in the sample is obtained. Prediction data of drop shock load including noise corresponding to each time point in the target landing gear

Then enter step G; Step G. According to the predicted data of the drop shock load containing noise corresponding to the target landing gear at each time point within the subsidence duration of the test condition in the sample

and the measured data _{Fj of the} drop shock load of the target landing gear at each time point in the subsidence duration of the test condition in the sample, and the comparison between the difference between the two and the preset difference threshold constitutes an overflow condition, and then enters the step H; Step H. Based on each sample, according to the above-mentioned steps D to step G, training is carried out for the Gaussian process regression model f, and the Gaussian process regression model after the training is obtained, which is the shock load identification model corresponding to the target landing gear; Step i. Obtain the strain response data set corresponding to each FBG sensor on the support arm of the target landing gear at each time point within the sinking duration of the real-time working condition of the target landing gear, and apply the shock load identification model corresponding to the target landing gear to obtain the target landing gear. The landing gear corresponds to each time point in the sinking duration of the working condition, and the target landing gear corresponds to the drop shock load prediction data containing noise, so as to realize the real-time identification of the target landing gear drop shock load. 2. The method for identifying the landing gear drop shock load based on optical fiber strain response and Gaussian process according to claim 1, characterized in that: the μ _i =0, μ _j =0, and the covariance function k(·) is as follows : k(a, b)=λ ₁ k _RBF (a, b)+λ ₂ k _PKF (a, b)+λ ₃ k _Noise (a, b) in:

k _PKF (a, b)=(a·b+1) ^q k _Noise (a, b)=σ _N ² δ ^* In the formula, λ ₁ , λ ₂ , λ ₃ represent preset weighting factors, and satisfy 0<λ ₁ ≤0.5, 0<λ ₂ ≤0.5, 0<λ ₃ ≤0.5, λ ₁ +λ ₂ +λ ₃ =1 ; σ _f , σ _l , σ _N represent the hyperparameters involved in the covariance function k(·); q represents the polynomial degree; δ ^* represents the Kronecker function. 3. The landing gear drop shock load identification method based on optical fiber strain response and Gaussian process according to claim 2, characterized in that: in the step E, in the following manner, calculate and obtain the covariance function k ( ) involved in value of each hyperparameter; first, the maximum likelihood function is constructed by using the seismic history strain response characteristics of the target landing gear corresponding to the test conditions in the sample, and the unknown hyperparameters involved in the covariance function k( ). Yeas's principle, according to the integral of the likelihood P(f _j |f _i , X _i , θ) and the prior P(f _i |X _i , θ), that is, the edge likelihood P(f _j |X _i , θ) as follows: P(f _j |X _i , θ)=∫P(f _j |f _i ,X _i ,θ)P(f _i |X _i ,θ)df _i =N(f _i |0,K(X _i , X _i )+σ ² I) Among them, θ represents the vector composed of unknown hyperparameters involved in the covariance function k( ); Then for the edge likelihood P(f _j |X _i ,θ), take the logarithm to obtain the logarithmic edge likelihood as follows:

Among them, N' represents the number of time points in the subsidence duration of the working condition, that is, the sampling frequency; Finally, according to the principle of matrix calculus, for each unknown hyperparameter θ _i involved in the covariance function k(·), the following formulas are used:

Obtain the value of θ _i corresponding to the maximum probability by derivation, that is, obtain the value of the hyperparameter involved in the covariance function k( ), and then obtain the value of each unknown hyperparameter involved in the covariance function k( ); where Tr represents the trace of the matrix,

T stands for transpose. 4. The method for identifying the landing gear drop shock load based on optical fiber strain response and Gaussian process according to claim 1, characterized in that: in the step F, according to each time point and target in the subsidence duration of the test condition in the sample The _{pre-posterior distribution of the landing gear corresponding to the noise-free drop load prediction data F j,} is as follows:

cov(F _{j, pre} )=K(Y _j ,Y _j )-K(Y _j ,X _i )[K(X _i ,X _i )+σ ² I'] ^-1 K(X _i ,Y _j ) Obtain the predicted data of the drop shock load including noise corresponding to the target landing gear at each time point in the subsidence duration of the test condition in this sample

Among them, cov(F _{j, pre} ) represents the confidence level of the predicted value of the target landing gear drop shock load history response.

Images