A civil aircraft component reliability assessment technology and migration method based on operation and maintenance data

Abstract

The present invention provides a civil aircraft component reliability assessment technology and migration method based on operation and maintenance data, belonging to the fields of intelligent operation and maintenance and composite materials technology. The method includes: constructing a component damage prediction database for benchmark aircraft models; performing environmental classification on the component damage prediction data to obtain a damage characteristic parameter distribution association model, and constructing an aircraft age-damage characteristic parameter distribution function based on the environmental classification results to obtain an aircraft age-damage characteristic parameter prediction model; deriving a reliability function based on the damage characteristic parameter distribution association model and the aircraft age-damage characteristic parameter prediction model to obtain a reliability assessment strategy; obtaining a migration coefficient through accelerated aging testing, and generating a preset civil aircraft equivalent damage prediction database through data conversion, and using a reliability assessment strategy to generate a reliability curve for the preset aircraft model. The present invention solves the problem that existing civil aircraft component reliability assessments lack operation and maintenance data, resulting in low accuracy in civil aircraft component damage prediction.

Description

Technical Field

[0001] The present invention belongs to the technical fields of intelligent operation and maintenance and composite materials, and in particular relates to a civil aircraft component reliability assessment technology and migration method based on operation and maintenance data. Background Art

[0002] To ensure that civil aircraft meet continued airworthiness requirements throughout their long-term operations, the industry has gradually developed a comprehensive operational and maintenance technology system encompassing monitoring, prediction, decision-making, and maintenance. Over the years, this system has evolved from planned maintenance based on statistical optimization techniques to condition-based maintenance based on predictive technology. This system utilizes data analysis and predictive technology to optimize maintenance strategies for aircraft systems and components. The core concept is to monitor the status of aircraft systems and components in real time, predict potential failures and damage, and conduct inspections and maintenance before they become threatening flight safety, thereby reducing downtime and maintenance costs.

[0003] Existing technology uses the SKYWISE platform to perform predictive maintenance on the environmental control systems, power systems, and landing gear systems of Airbus benchmark aircraft and A330 models, reducing the probability of unplanned maintenance by 10-50%. Existing technology uses the AVIATER platform to predict damage to aircraft components, reducing the number of unplanned part replacements to 30-40%.

[0004] Most existing fault or damage prediction technologies rely directly on visual data from operational operations. These technologies use real-time monitoring data (such as QAR data) to perform state analysis and fault / damage prediction using methods such as backpropagation neural networks and grayscale prediction models. These methods are not suitable for sensorless civil aircraft components. Component damage data can only be obtained from maintenance data collected by civil aircraft maintenance and repair facilities (MROs), which is diverse and fragmented. Currently, there is limited research on civil aircraft component damage prediction methods based on maintenance data. Furthermore, some existing civil aircraft have only been in operation for a short time, requiring a significant period of time to accumulate maintenance data. Summary of the Invention

[0005] In response to the above-mentioned deficiencies in the prior art, the present invention provides a civil aircraft component reliability assessment technology and migration method based on operation and maintenance data, which solves the problem that the reliability assessment of existing civil aircraft components lacks operation and maintenance data, resulting in low accuracy in damage prediction of civil aircraft components.

[0006] To achieve the above objectives, the present invention adopts a technical solution: a civil aircraft component reliability assessment technology and migration method based on operation and maintenance data, which is applied to damage prediction of preset civil aircraft components, including the following steps:

[0007] S1. Collect historical operation and maintenance data of benchmark model components, extract typical damage characteristics and damage characteristic parameters of benchmark model components, and collect environmental data of the corresponding management areas of the typical damage characteristics of benchmark model components to build a damage prediction database;

[0008] S2. Based on the damage prediction database and the damage characteristic parameters of the benchmark aircraft components, the component damage prediction data is classified by environment. A damage characteristic parameter distribution association model and an aircraft age-damage characteristic parameter prediction model are constructed. The cumulative distribution function is used for derivation. By obtaining the reliability curve of the benchmark aircraft, a reliability assessment strategy is obtained.

[0009] S3. Based on the environmental classification of component damage prediction data, damage characteristic parameters of typical test pieces of components of the preset model and the benchmark model are collected using accelerated aging tests to obtain the damage characteristic parameter migration coefficient;

[0010] S4. Based on the damage characteristic parameter migration coefficient, use data conversion and reliability assessment strategies to generate the reliability curve of the preset model and complete the reliability assessment technology and migration of civil aircraft components.

[0011] The beneficial effects of the present invention are as follows: the present invention provides a reliability assessment strategy through a multi-factor coupled damage, environment and aircraft age modeling mechanism, with damage characteristic parameters as the link, and migrates the damage development trend of the benchmark model to the preset civil aircraft; it solves the practical problem of the lack of operation and maintenance data in the reliability assessment of existing civil aircraft components, realizes the predictive operation and maintenance of preset civil aircraft components, and improves the accuracy of damage prediction of civil aircraft components.

[0012] Furthermore, the S1 includes the following steps:

[0013] S101. Collect historical operation and maintenance data of components of benchmark models, extract maintenance data from the historical operation and maintenance data, and obtain typical damage characteristics and damage characteristic parameters of the components;

[0014] S102. Based on the typical damage characteristics and damage characteristic parameters of the components, collect environmental data of the corresponding value management area of ​​the typical damage characteristics of the components of the benchmark model;

[0015] S103. Combine historical operation and maintenance data and environmental data to build a damage prediction database.

[0016] The beneficial effect of the above further scheme is: the present invention improves the pertinence, accuracy and reliability of the damage prediction database by obtaining a damage prediction database, extracting typical damage characteristics and damage characteristic parameters of components, and then collecting environmental data in combination with typical damage characteristics.

[0017] Furthermore, the S2 includes the following steps:

[0018] S201. Based on the damage prediction database, use a cluster analysis method to classify the component damage prediction data by environment, and use mathematical statistics theory to construct a damage characteristic parameter distribution correlation model;

[0019] S202. Fitting an age-damage characteristic parameter distribution function based on environment classification based on damage characteristic parameters of components of the benchmark aircraft model, and solving the distribution parameters to obtain an age-damage characteristic parameter prediction model;

[0020] S203. Based on the damage characteristic parameter distribution association model and the aircraft age-damage characteristic parameter prediction model, the reliability function is derived using the cumulative distribution function, and the reliability assessment strategy is obtained by obtaining the reliability curve of the benchmark aircraft model.

[0021] Furthermore, the S201 includes the following steps:

[0022] S2011. Based on the damage prediction database, a dynamic cluster analysis is performed on the aircraft environment data containing the control area in the damage prediction database to obtain a result of the component damage prediction data environment classification;

[0023] S2012. Based on the results of the component damage prediction data environment classification, the distribution characteristics of the damage characteristic parameter data are preliminarily identified and analyzed using the quantile-quantile diagram to determine the initial damage distribution type;

[0024] S2013. The Kolmogorov-Smirnov method is used to test the initial damage distribution type. By verifying the goodness of fit between the damage characteristic parameter data and the initial damage distribution type, a damage characteristic parameter distribution correlation model is constructed.

[0025] The beneficial effects of the above further scheme are as follows: the present invention uses cluster analysis methods and mathematical statistics theory to perform environmental classification of component damage prediction data, and constructs a damage characteristic parameter distribution association model, thereby improving the fit and accuracy of the distribution association model.

[0026] Furthermore, the S202 includes the following steps:

[0027] S2021. Based on the damage characteristic parameters of the benchmark aircraft components, use the curve estimation method to fit the age-damage characteristic parameter distribution function type based on the environment classification to obtain the initial age-damage characteristic parameter prediction model with distribution parameters;

[0028] S2022. Use the maximum likelihood estimation method to solve the distribution parameters to obtain the optimal distribution parameters, and obtain the age-damage characteristic parameter prediction model by updating the initial age-damage characteristic parameter prediction model.

[0029] The beneficial effects of the above further scheme are: the present invention fully considers key influencing factors such as service environment differences and aircraft age changes, introduces environmental classification and aircraft age variables, and makes the aircraft age damage characteristic parameter prediction model more in line with the actual operation and maintenance scenario. Compared with the traditional single feature modeling method, it has stronger applicability and generalization ability, and can be applied to complex service environment conditions.

[0030] Furthermore, the step S203 is specifically as follows:

[0031] Based on the damage characteristic parameter distribution association model and the aircraft age-damage characteristic parameter prediction model, the statistical distribution characteristics of the damage characteristic parameters are described using the cumulative distribution function, the reliability function is derived, and the reliability evaluation of the damage evolution law under different service times is carried out. By obtaining the reliability curve of the benchmark model, the reliability evaluation strategy is obtained.

[0032] The beneficial effects of the above-mentioned further scheme are as follows: the present invention realizes the prediction of aircraft structural damage evolution and reliability evaluation of benchmark aircraft models by constructing an age-damage characteristic parameter prediction model and deriving a reliability function, establishes a reliability evaluation system driven by operation and maintenance data, obtains a reliability evaluation strategy, and provides a scientific basis for making maintenance decisions and aircraft health management strategies.

[0033] Furthermore, the S3 is specifically:

[0034] Based on the environmental classification of component damage prediction data and typical test pieces of benchmark model components, accelerated aging tests are used in combination with preset mechanical properties experiments to collect damage characteristic parameters of typical test pieces of preset model and benchmark model components, and trend lines are fitted. The damage characteristic parameter migration coefficient is obtained by calculating the ratio of the damage characteristic parameters of the benchmark model and the preset model in the preset mechanical properties experiment.

[0035] Furthermore, the S4 is specifically as follows:

[0036] According to the damage characteristic parameter migration coefficient, data conversion is used to convert the damage characteristic parameter data of the benchmark model into estimated data of the preset model, and an equivalent damage characteristic parameter database of the preset model is obtained. Based on the reliability assessment strategy, the reliability curve of the preset model is generated, completing the reliability assessment technology and migration of civil aircraft components.

[0037] The beneficial effects of the above-mentioned further scheme are as follows: the present invention extracts key damage parameters and establishes migration mapping relationships through typical structural damage data of benchmark models and preset models obtained under typical environmental conditions, and proposes a quantitative calculation method for the "migration coefficient" to achieve effective migration of damage data between different models, effectively solving the problem of data scarcity in the initial operation of preset models. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 Flow chart of the method of the present invention.

[0039] Figure 2 This is the technical roadmap of this embodiment.

[0040] Figure 3 This is a fitting curve diagram of the nonlinear regression of pit depth in the high temperature, high humidity and high precipitation area in this embodiment.

[0041] Figure 4 This is a reliability curve diagram of the benchmark model in high temperature, high humidity and high precipitation areas in this embodiment.

[0042] Figure 5 Graph 1 is a fitting curve of damage characteristic parameters of a typical test piece of the lower inner flap lower wall panel in a high temperature, high humidity and high precipitation area in this embodiment.

[0043] Figure 6 : is a reliability curve diagram of the inner flap lower wall panel components of the domestic aircraft model in the high temperature, high humidity and high precipitation area in this embodiment. DETAILED DESCRIPTION

[0044] The specific embodiments of the present invention are described below to facilitate understanding of the present invention by those skilled in the art. However, it should be clear that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the appended claims, these changes are obvious, and all inventions and creations utilizing the concepts of the present invention are protected.

[0045] Before describing this embodiment, the following terms are explained:

[0046] CDF: cumulative distribution function;

[0047] QQ plot: quantile-quantile plot;

[0048] Logistic distribution: logistic regression distribution;

[0049] KS test: Kolmogorov-Smirnov test.

[0050] Example

[0051] like Figure 1 As shown, the present invention provides a civil aircraft component reliability assessment technology and migration method based on operation and maintenance data, and its implementation method is as follows:

[0052] S1. Collect historical operation and maintenance data of benchmark model components, extract typical damage characteristics and damage characteristic parameters of benchmark model components, and collect environmental data of the corresponding management areas of the typical damage characteristics of benchmark model components to build a damage prediction database. The specific steps are as follows:

[0053] S101. Collect historical operation and maintenance data of components of benchmark models, extract maintenance data from the historical operation and maintenance data, and obtain typical damage characteristics and damage characteristic parameters of the components;

[0054] S102. Based on the typical damage characteristics and damage characteristic parameters of the components, collect environmental data of the corresponding value management area of ​​the typical damage characteristics of the components of the benchmark model;

[0055] S103. Combine historical operation and maintenance data and environmental data to build a damage prediction database.

[0056] In this embodiment, the preset model is a domestic model;

[0057] like Figure 2 As shown, historical operation and maintenance data of benchmark aircraft components are collected. The historical operation and maintenance data includes: flight information, maintenance data, and flight mission information; flight information includes but is not limited to aircraft registration number, aircraft model, age, and duty area; maintenance data includes but is not limited to damage time, damage level, maintenance method, and maintenance time; flight mission information includes but is not limited to flight time, take-off and landing points, overnight airports, and flight time;

[0058] Preset mechanical performance experiments are selected based on the actual usage environment, operation and maintenance conditions, and stress conditions. Typical damage characteristics and damage characteristic parameters of components are then extracted through these selected pre-set mechanical performance experiments. For example, when a flap structure is impacted by runway gravel, the depth of the dent after the impact is used as the damage characteristic parameter. When a sliding door structure delaminates under long-term conditions of damp heat and vibration, prefabricated defects of different sizes are used as damage characteristic parameters.

[0059] Based on the typical damage characteristics and damage characteristic parameters of the components, atmospheric environmental data is collected. Monthly data on meteorological environmental indicators for the corresponding areas with the typical damage characteristics of the benchmark aircraft components over the past ten years are collected. Environmental factors include but are not limited to temperature, humidity, precipitation, and the number of days with high temperature and high humidity.

[0060] Combining historical operation and maintenance data with environmental data, a damage prediction database is constructed. The damage prediction database includes four tags: source, classification index, index / variable, and type, as shown in Table 1.

[0061] Table 1

[0062]

[0063] S2. Based on the damage prediction database and the damage characteristic parameters of the benchmark aircraft components, the component damage prediction data is classified by environment. A damage characteristic parameter distribution association model and an aircraft age-damage characteristic parameter prediction model are constructed. The cumulative distribution function is used for derivation. By obtaining the reliability curve of the benchmark aircraft, a reliability assessment strategy is obtained. The specific steps are as follows:

[0064] S201. Based on the damage prediction database, use the cluster analysis method to classify the component damage prediction data by environment, and use mathematical statistics theory to construct a damage characteristic parameter distribution correlation model. The specific steps are as follows:

[0065] S2011. Based on the damage prediction database, a dynamic cluster analysis is performed on the aircraft environment data containing the control area in the damage prediction database to obtain a result of the component damage prediction data environment classification;

[0066] S2012. Based on the results of the component damage prediction data environment classification, the distribution characteristics of the damage characteristic parameter data are preliminarily identified and analyzed using the quantile-quantile diagram to determine the initial damage distribution type;

[0067] S2013. The Kolmogorov-Smirnov method is used to test the initial damage distribution type. By verifying the goodness of fit between the damage characteristic parameter data and the initial damage distribution type, a damage characteristic parameter distribution correlation model is constructed.

[0068] In this embodiment, based on the damage prediction database, dynamic cluster analysis is performed on the aircraft environment data of the included management area, and data mining technology is used to establish the environmental classification of component damage prediction data, and the environmental classification results of component damage prediction data are obtained; the environment is divided by the environmental factor clustering method; the aircraft service environment influencing factor set is , n Represents the total number of environmental factors; clustering is performed using the K-means dynamic clustering algorithm, and the expression of the objective function of the K-means dynamic clustering algorithm is as follows:

[0069] ;

[0070] in, represents the clustering objective function, which is used to measure the sum of intra-class variance. Indicates the i The first cluster j samples, Indicates the i clusters, k Indicates the total number of clusters. Indicates the i The mean of the clusters, represents the Euclidean distance; through iterative optimization, each environmental factor has the smallest intra-class variance in the region with similar damage patterns; the service environment is divided into four categories with similar damage patterns, and the results of the component damage prediction data environment classification are obtained;

[0071] The environmental classification of component damage prediction data is specifically: low temperature and low humidity area, relatively low temperature and low humidity area, medium temperature and medium humidity area, and high temperature, high humidity and high precipitation area. The specific classification standards and their corresponding characteristics are shown in Table 2:

[0072] Table 2

[0073]

[0074] In this embodiment, in order to systematically analyze the distribution characteristics of aircraft structural damage characteristic parameters, mathematical statistics theory is used to establish a damage characteristic parameter distribution correlation model, specifically:

[0075] First, based on the environmental classification of component damage prediction data, the distribution characteristics of the damage characteristic parameter data were preliminarily identified and analyzed using quantile-quantile plots. Based on the complex service environment of aircraft structures and previous engineering experience, the exponential distribution, Weibull distribution, lognormal distribution, and logistic distribution were selected as candidate models for the damage characteristic parameter distribution. By plotting QQ plots between the damage characteristic parameter data and each candidate distribution, the fit between the sample data and the theoretical distribution was visually compared, and the possible distribution type was preliminarily determined, resulting in the initial damage distribution type.

[0076] The KS test is further used to quantitatively test the initial damage distribution type, verify the goodness of fit between the damage characteristic parameter data and the theoretical distribution, calculate the KS statistic and its corresponding p-value, and make judgments based on the p-value to obtain the damage characteristic parameter distribution association model.

[0077] S202: Based on the damage characteristic parameters of the benchmark aircraft components, fit the age-damage characteristic parameter distribution function based on the environment classification, and solve the distribution parameters to obtain the age-damage characteristic parameter prediction model. The specific steps are as follows:

[0078] S2021. Based on the damage characteristic parameters of the benchmark aircraft components, use the curve estimation method to fit the age-damage characteristic parameter distribution function type based on the environment classification to obtain the initial age-damage characteristic parameter prediction model with distribution parameters;

[0079] S2022. Use the maximum likelihood estimation method to solve the distribution parameters to obtain the optimal distribution parameters, and obtain the age-damage characteristic parameter prediction model by updating the initial age-damage characteristic parameter prediction model.

[0080] In this embodiment, based on the damage characteristic parameters of the benchmark aircraft components, a curve estimation method is used to perform a fitting analysis on the relationship between the aircraft age and the damage characteristic parameters based on the environmental classification;

[0081] Based on the environmental classification results, a fitness test was conducted in a medium temperature and medium humidity environment. It was determined that the statistical distribution characteristics of the aircraft age and damage characteristic parameters in a high temperature, high humidity, and high precipitation environment conform to the exponential distribution. The initial aircraft age-damage characteristic parameter prediction model with the corresponding distribution parameters was obtained. The expression is as follows:

[0082] ;

[0083] in, represents the damage characteristic parameter, Indicates the age of the aircraft, a and b All represent distribution parameters;

[0084] The maximum likelihood estimation method is used to estimate the parameters, and by constructing the likelihood function, the distribution parameter values ​​are iteratively optimized to make them conform to the distribution characteristics of the observed data to the greatest extent possible, and the optimal distribution parameters are obtained. ;

[0085] In addition, under high temperature, high humidity and high precipitation environment, the damage characteristic parameters obey the exponential distribution. The nonlinear regression method is used for fitting, and the maximum likelihood estimation method is used to obtain the distribution parameters. Figure 3 The nonlinear regression fitting curve of pit depth in high temperature, high humidity and high precipitation areas is shown in the figure. The expression of the relevant regression equation is as follows:

[0086] ;

[0087] In low temperature and low humidity environments, as well as relatively low temperature and low humidity environments, the damage characteristic parameters obey linear regression, and the expressions of the relevant regression equations are as follows:

[0088] ;

[0089] .

[0090] S203. Based on the damage characteristic parameter distribution association model and the aircraft age-damage characteristic parameter prediction model, the reliability function is derived using the cumulative distribution function. By obtaining the reliability curve of the benchmark aircraft model, a reliability assessment strategy is obtained, specifically:

[0091] Based on the damage characteristic parameter distribution association model and the aircraft age-damage characteristic parameter prediction model, the statistical distribution characteristics of the damage characteristic parameters are described using the cumulative distribution function, the reliability function is derived, and the reliability evaluation of the damage evolution law under different service times is carried out. By obtaining the reliability curve of the benchmark model, the reliability evaluation strategy is obtained.

[0092] In this embodiment, a reliability assessment of the damage evolution patterns at different service times is performed based on a distribution correlation model of damage characteristic parameters and a prediction model between aircraft age and damage characteristic parameters. CDF is used to describe the statistical distribution characteristics of the damage characteristic parameters, and a reliability function is further derived to quantitatively characterize the probability of benchmark aircraft components maintaining normal operating conditions at different service stages.

[0093] In areas with high temperature, high humidity and high precipitation, the damage characteristic parameter data obeys the logistic distribution, so the CDF expression is as follows:

[0094] ;

[0095] in, represents the cumulative distribution function of the damaged area, represents the location parameter, represents the median of the lesion area, It represents the scale parameter, reflecting the degree of dispersion of the distribution;

[0096] Based on the distribution association model of the corresponding damage characteristic parameters and the prediction model between aircraft age and damage characteristic parameters, the corresponding probability distribution model and the relationship between damage characteristic parameters and aircraft age are obtained. The relationship between reliability and aircraft age is derived and solved. The reliability expression is as follows:

[0097] ;

[0098] in, represents the reliability function, Indicates the age of the aircraft, Indicated by aircraft age The predicted damage characteristic parameters are obtained from the age prediction model; the reliability function is used to describe the probability of a component maintaining a normal working state at different service times, thereby reflecting its fault propagation law, as shown in the following example: Figure 4 As shown, the reliability curve of the benchmark model in high temperature, high humidity and high precipitation areas is obtained, and the reliability assessment strategy is obtained;

[0099] According to the reliability assessment strategy, the reliability functions of aircraft structures under the other three types of service environments are derived; specifically, based on the environmental characteristics of different regions, such as temperature, humidity and climate change laws, the reliability of aircraft structures in each region is calculated separately.

[0100] S3. Based on the environmental classification of component damage prediction data, the damage characteristic parameters of typical test pieces of components of the preset model and the benchmark model are collected using accelerated aging tests to obtain the damage characteristic parameter migration coefficient, which is specifically:

[0101] Based on the environmental classification of component damage prediction data and typical test pieces of benchmark model components, accelerated aging tests are used in combination with preset mechanical properties experiments to collect damage characteristic parameters of typical test pieces of preset model and benchmark model components, and trend lines are fitted. The damage characteristic parameter migration coefficient is obtained by calculating the ratio of the damage characteristic parameters of the benchmark model and the preset model in the preset mechanical properties experiment.

[0102] In this embodiment, based on the environmental classification of component damage prediction data and typical test pieces of domestic aircraft components, accelerated aging tests are conducted under these environmental conditions. Combined with preset mechanical property experiments, the accelerated aging tests accelerate the damage accumulation process. Damage characteristic parameters of the benchmark aircraft and typical test pieces of domestic aircraft components are collected. The resulting data can truly reflect the damage change trends of the two types of aircraft under similar environmental conditions, and a migration relationship is obtained.

[0103] Specifically, the damage characteristic parameters of the benchmark model and the domestic model are measured, and the trend line is fitted. By calculating the ratio of the damage characteristic parameters of the benchmark model and the domestic model under the corresponding impact, the damage characteristic parameter migration coefficient is obtained. The expression is as follows:

[0104] ;

[0105] in, Indicates the h The damage characteristic parameter migration coefficient under these environments is Indicates the h The damage characteristic parameters of the benchmark model under different environments, Indicates the h The damage characteristic parameters of domestic aircraft models under different environments, Indicates the type of environment.

[0106] In this embodiment, the typical test piece of the domestic aircraft model component is selected as a flap component, and the preset mechanical performance test corresponding to the flap component is an impact test;

[0107] Taking the pit damage, the most common type of damage to the flap rudder surface, as an example, the impact tests of different energies were carried out on the typical test pieces of the inner flap lower wall. The pit depth of the typical test pieces after impact was measured, and the damage characteristic parameters of the inner flap lower wall of the benchmark aircraft and the domestic aircraft were obtained. Based on the high temperature, high humidity and high precipitation areas, the following were obtained: Figure 5 As shown, the damage characteristic parameters of the typical test piece of the lower wall panel of the inner flap in the high temperature, high humidity and high precipitation area.

[0108] S4. Based on the damage characteristic parameter migration coefficient, using data conversion and reliability assessment strategies, generate the reliability curve of the preset aircraft model and complete the reliability assessment technology and migration of civil aircraft components. Specifically:

[0109] According to the damage characteristic parameter migration coefficient, data conversion is used to convert the damage characteristic parameter data of the benchmark model into estimated data of the preset model, and an equivalent damage characteristic parameter database of the preset model is obtained. Based on the reliability assessment strategy, the reliability curve of the preset model is generated, completing the reliability assessment technology and migration of civil aircraft components.

[0110] In this embodiment, the damage characteristic parameter transfer coefficient is used to convert the damage characteristic parameter data of the existing benchmark model into the estimated data of the domestic model by data transfer. The data transfer expression is as follows:

[0111] ;

[0112] Without directly obtaining the operation and maintenance data of domestic aircraft models, the damage data set of domestic aircraft models can be inferred based on the historical data of the benchmark models. The reliability assessment strategy obtained in S2 is used to perform reliability analysis on the converted domestic aircraft model data, and the reliability curves of domestic aircraft models under four types of environments are established. The reliability assessment technology and migration of civil aircraft components are realized, and the predictive operation and maintenance of domestic civil aircraft components are realized. Based on the high temperature, high humidity and high precipitation areas, the following are obtained: Figure 6 As shown in Figure 2, the reliability curve of the inner flap lower wall panel components of domestic aircraft models in high temperature, high humidity and high precipitation areas.

[0113] This embodiment provides a multi-factor coupled damage-environment-age modeling mechanism. This comprehensively considers the relationship between service environment, aircraft age, and typical damage types, and proposes a modeling strategy based on environment classification and an age-based dynamic estimation method. This enables quantitative prediction of damage evolution patterns under different service scenarios, enhancing the model's generalization and engineering adaptability.

[0114] A data-driven aircraft structural reliability assessment strategy was developed. Using historical maintenance data from benchmark aircraft models, a damage characteristic distribution model was constructed, cumulative distribution functions were derived, and reliability curves were generated. This strategy breaks away from the traditional physical modeling's strong reliance on failure mechanisms, improves the efficiency and applicability of reliability assessments, and provides scientific support for condition monitoring and maintenance strategies.

[0115] The migration of damage characteristic parameters was also realized, and the damage characteristic parameters were converted with the same damage source (the damage source of the flap component was the impact of foreign objects with different energies) as the equivalent point; the damage characteristic parameters were extracted and a migration mapping relationship was established, and a quantitative calculation method for the "migration coefficient" was proposed to achieve effective migration of damage data between different aircraft models. At the same time, this method can be combined with environmental aging experiments to improve the authenticity of damage migration and environmental simulation capabilities, effectively solving the problem of data scarcity in the early stages of operation of domestic aircraft models.

Claims

1. A civil aircraft component reliability assessment technology and migration method based on operation and maintenance data, applied to damage prediction of preset civil aircraft components, characterized by: The following steps are involved: S1. Collect historical operation and maintenance data of benchmark model components, extract typical damage characteristics and damage characteristic parameters of benchmark model components, and collect environmental data of the corresponding management areas of the typical damage characteristics of benchmark model components to build a damage prediction database; S2. Based on the damage prediction database and the damage characteristic parameters of the benchmark aircraft components, the component damage prediction data is classified by environment. A damage characteristic parameter distribution association model and an aircraft age-damage characteristic parameter prediction model are constructed. The cumulative distribution function is used for derivation. By obtaining the reliability curve of the benchmark aircraft, a reliability assessment strategy is obtained. Specifically, the following are the steps: S201. Based on the damage prediction database, use a cluster analysis method to classify the component damage prediction data by environment, and use mathematical statistics theory to construct a damage characteristic parameter distribution correlation model; S202. Fitting an age-damage characteristic parameter distribution function based on environment classification based on damage characteristic parameters of components of the benchmark aircraft model, and solving the distribution parameters to obtain an age-damage characteristic parameter prediction model; S203. Based on the damage characteristic parameter distribution association model and the aircraft age-damage characteristic parameter prediction model, the reliability function is derived using the cumulative distribution function, and the reliability assessment strategy is obtained by obtaining the reliability curve of the benchmark aircraft model; S3. Based on the environmental classification of component damage prediction data, damage characteristic parameters of typical test pieces of components of the preset model and the benchmark model are collected using accelerated aging tests to obtain the damage characteristic parameter migration coefficient; S4. Based on the damage characteristic parameter migration coefficient, use data conversion and reliability assessment strategies to generate the reliability curve of the preset model and complete the reliability assessment technology and migration of civil aircraft components.

2. The civil aircraft component reliability assessment technology and migration method based on operation and maintenance data according to claim 1 is characterized in that: Said S1 comprises the following steps: S101. Collect historical operation and maintenance data of components of benchmark models, extract maintenance data from the historical operation and maintenance data, and obtain typical damage characteristics and damage characteristic parameters of the components; S102. Based on the typical damage characteristics and damage characteristic parameters of the components, collect environmental data of the corresponding value management area of ​​the typical damage characteristics of the components of the benchmark model; S103. Combine historical operation and maintenance data and environmental data to build a damage prediction database.

3. The civil aircraft component reliability assessment technology and migration method based on operation and maintenance data according to claim 1 is characterized in that: The S201 includes the following steps: S2011. Based on the damage prediction database, a dynamic cluster analysis is performed on the aircraft environment data containing the control area in the damage prediction database to obtain a result of the component damage prediction data environment classification; S2012. Based on the results of the component damage prediction data environment classification, the distribution characteristics of the damage characteristic parameter data are preliminarily identified and analyzed using the quantile-quantile diagram to determine the initial damage distribution type; S2013. The Kolmogorov-Smirnov method is used to test the initial damage distribution type. By verifying the goodness of fit between the damage characteristic parameter data and the initial damage distribution type, a damage characteristic parameter distribution correlation model is constructed.

4. The civil aircraft component reliability assessment technology and migration method based on operation and maintenance data according to claim 1 is characterized in that: The S202 includes the following steps: S2021. Based on the damage characteristic parameters of the benchmark aircraft components, use the curve estimation method to fit the age-damage characteristic parameter distribution function type based on the environment classification to obtain the initial age-damage characteristic parameter prediction model with distribution parameters; S2022. Use the maximum likelihood estimation method to solve the distribution parameters to obtain the optimal distribution parameters, and obtain the age-damage characteristic parameter prediction model by updating the initial age-damage characteristic parameter prediction model.

5. The civil aircraft component reliability assessment technology and migration method based on operation and maintenance data according to claim 1 is characterized in that: The S203 is specifically as follows: Based on the damage characteristic parameter distribution association model and the aircraft age-damage characteristic parameter prediction model, the statistical distribution characteristics of the damage characteristic parameters are described using the cumulative distribution function, the reliability function is derived, and the reliability evaluation of the damage evolution law under different service times is carried out. By obtaining the reliability curve of the benchmark model, the reliability evaluation strategy is obtained.

6. The civil aircraft component reliability assessment technology and migration method based on operation and maintenance data according to claim 1 is characterized in that: The S3 is specifically: Based on the environmental classification of component damage prediction data and typical test pieces of benchmark model components, accelerated aging tests are used in combination with preset mechanical properties experiments to collect damage characteristic parameters of typical test pieces of preset model and benchmark model components, and trend lines are fitted. The damage characteristic parameter migration coefficient is obtained by calculating the ratio of the damage characteristic parameters of the benchmark model and the preset model in the preset mechanical properties experiment.

7. The civil aircraft component reliability assessment technology and migration method based on operation and maintenance data according to claim 1 is characterized in that: The S4 is specifically: According to the damage characteristic parameter migration coefficient, data conversion is used to convert the damage characteristic parameter data of the benchmark model into estimated data of the preset model, and an equivalent damage characteristic parameter database of the preset model is obtained. Based on the reliability assessment strategy, the reliability curve of the preset model is generated, completing the reliability assessment technology and migration of civil aircraft components.

Images