Aircraft structural member reliability analysis and prediction method

Abstract

The invention belongs to the technical field of model prediction, and particularly relates to an aircraft structural member reliability analysis and prediction method, which comprises the following steps: acquiring physical characteristics, working environment and historical data of an aircraft structural member; analyzing the physical characteristics, the working environment and the historical data of the aircraft structural component, and establishing a structural component characteristic mathematical model; the elements in the model comprise characteristics for simulating behaviors of the aircraft structural member under different working conditions; determining influence degrees, namely influence factor weights, of different characteristics on reliability of the aircraft structural component through statistical analysis; a composite probability model is adopted to distribute the certainty degree of each characteristic; combining the certainty degree information of different sources by applying a combination rule; carrying out reliability evaluation analysis on the aircraft structural component; and calculating the overall reliability of the aircraft structural component based on the evaluation result and the certainty degree distribution, and carrying out sensitivity analysis on the characteristics based on the reliability calculation result. And by calculating the reliability and carrying out sensitivity analysis, the performance and the service life of the structural member are accurately predicted.

Description

Technical Field

[0001] The invention belongs to the technical field of model prediction, and in particular relates to a reliability analysis and prediction method for aircraft structural parts. Background Art

[0002] Traditional aircraft structural component reliability prediction methods mainly rely on statistical analysis of historical failure data and the construction of empirical models. This method provides a reference for the safety and durability of aircraft structures to a certain extent, but its limitations are becoming increasingly prominent. Specifically, it is often difficult to fully capture the various complex factors that affect the reliability of structural components.

[0003] First, with the continuous advancement of manufacturing technology, the application of new materials and new processes is becoming more and more extensive, and these changes may have a significant impact on the reliability of components. However, traditional methods often find it difficult to accurately assess the potential risks brought about by these new technologies. Secondly, the difference in material properties is also a problem that traditional methods find difficult to overcome. Aircraft structural components are usually made of a variety of materials, which have significant differences in mechanical properties, corrosion resistance, fatigue life, etc. Traditional methods usually regard materials as homogeneous bodies, ignoring the impact of these differences on reliability, which may lead to inaccurate prediction results. Furthermore, the complexity of actual working conditions is also one of the factors that traditional methods find difficult to fully consider. Aircraft will experience various complex environmental conditions during flight, such as high temperature, low temperature, high pressure, corrosion, etc. These environmental conditions have an important impact on the reliability of structural components. However, traditional methods often make predictions based on simplified working condition assumptions, which cannot accurately reflect the complexity of actual working conditions and their impact on reliability.

[0004] Therefore, it is particularly important to develop a more comprehensive reliability prediction method for aircraft structural components. Summary of the invention

[0005] In view of the problem that traditional methods are difficult to fully capture the various complex factors that affect the reliability of structural components, the present invention provides a reliability analysis and prediction method for aircraft structural parts, which comprehensively considers multiple factors such as changes in the manufacturing process, differences in material properties, and the complexity of actual working conditions, thereby improving the accuracy and reliability of the prediction.

[0006] The technical solution of the present invention provides a method for analyzing and predicting the reliability of aircraft structural parts, comprising the following steps: Obtain physical properties, working environment, and historical data of aircraft structural parts; Analyze the physical properties, working environment, and historical data of aircraft structural parts to establish a mathematical model of structural part characteristics; elements in the model include characteristics that simulate the behavior of aircraft structural parts under different working conditions; Determine the influence of different characteristics on the reliability of aircraft structural parts through statistical analysis, that is, the weight of the influence factor of each characteristic; A composite probability model is used to assign the degree of confidence of each characteristic; Applying combining rules to merge confidence information from different sources; Conduct reliability assessment and analysis of aircraft structural parts; Based on the evaluation results and confidence allocation, the overall reliability of aircraft structural components is calculated and sensitivity analysis of characteristics is performed based on the reliability calculation results.

[0007] As a further limitation of the technical solution of the present invention, in the step of obtaining physical properties, working environment, and historical data of aircraft structural parts, the physical properties include material properties, structural design, and manufacturing process; The working environment includes temperature and humidity, vibration and shock, corrosion and oxidation, and external loads; Historical data includes maintenance data, usage data, and accident records.

[0008] Among them, material properties include: Material Type: Aircraft structural parts may be made of different types of materials, such as metal alloys, composite materials, etc.

[0009] Strength and stiffness: The strength and stiffness of materials are important physical properties for evaluating the load capacity and deformation degree of structural parts.

[0010] Structural design includes: Geometry: The shape of a structural component plays a key role in its force distribution and stress transfer.

[0011] Connection method: Consider the impact of connection methods, such as welding, bolt connection, etc., on the overall reliability of the structure.

[0012] The manufacturing process includes: Manufacturing accuracy: The manufacturing process has a direct impact on the size and shape accuracy of structural parts.

[0013] Quality control: Quality control measures during the production process directly affect the reliability of structural parts.

[0014] Temperature and humidity include: Aircraft fly at different altitudes and climate conditions, so the effects of changes in temperature and humidity on structural components must be considered.

[0015] Vibration and shock include: Aircraft are subject to various vibrations and shocks during flight, and these environmental factors may affect the fatigue life of structural parts.

[0016] Corrosion and oxidation include: Aircraft in wet environments may be affected by corrosion and oxidation, especially metal structures.

[0017] External loads include: Aircraft may be affected by external factors such as lightning strikes, bird strikes, etc. These loads may cause damage to structural parts.

[0018] Maintenance data includes: The past maintenance records of structural components, including the history of repairs and replacement parts, can provide clues to the health status of structural components.

[0019] Usage data includes: The aircraft's service history, including flight hours, number of take-offs and landings, etc., is used to evaluate the fatigue life and damage accumulation of structural parts.

[0020] The accident record includes: Aircraft accident records, including the performance of structural components in accidents, help evaluate the strength and reliability of structural components.

[0021] As a further limitation of the technical solution of the present invention, in the step of analyzing the physical properties, working environment, and historical data of aircraft structural parts and establishing a mathematical model of structural part characteristics, the mathematical model is as follows: (X={a_1x_1^2+b_1y_1^3,a_2x_2^2+b_2y_2^3,...,a_nx_n^2+b_ny_n^3}) Among them, each term (a_ix_i^2+b_iy_i^3) represents a characteristic of the physical properties of the structural component, the working environment, and the historical data.

[0022] As a further limitation of the technical solution of the present invention, in the step of determining the influence of different characteristics on the reliability of aircraft structural parts through statistical analysis, that is, the weight of the influence factor of each characteristic, the weight calculation formula is as follows: (W={w_1\cdot\log(x_1),w_2\cdot\log(x_2),...,w_n\cdot\log(x_n)}) Among them, (w_i) represents the weight of the (i)th feature, and (\log(x_i)) represents the role of logarithmic transformation in weight allocation.

[0023] As a further limitation of the technical solution of the present invention, in the step of using a composite probability model to allocate the confidence of each characteristic, the composite probability model is as follows: (m(A)=1-\prod_{i=1}^{n}(1-w_i\cdot\text{Conf}(x_i))) Where (A) is a set of events and (\text{Conf}(x_i)) is the confidence corresponding to feature (x_i).

[0024] As a further limitation of the technical solution of the present invention, in the step of combining the confidence information from different sources by applying the combination rule, the combination rule formula is as follows: (m_{comb}(A)=\frac{\sum_{i=1}^{k}m_i(A)}{k}-\frac{\sum_{i=1}^{k}m_i(\bar{A})}{k}) Among them, (m_i(A)) represents the confidence of the (i)th information source about event (A), and (m_i(\bar{A})) represents the confidence about event not (A).

[0025] As a further limitation of the technical solution of the present invention, in the step of performing reliability evaluation analysis of aircraft structural parts, the reliability evaluation formula is as follows: (R(t)=e^{-\int_0^t\lambda(x)dx}) Among them, (\lambda(x)) is the failure rate function, and the reliability evaluation formula is used to reflect the probability that the component will not fail before time (t).

[0026] As a further limitation of the technical solution of the present invention, in the step of calculating the overall reliability of the aircraft structure based on the evaluation results and the confidence distribution and performing sensitivity analysis of the characteristics based on the reliability calculation results, The reliability calculation formula is as follows: (R=\sum_{X\inF^c}m(X)) Among them, (F^c) represents the complement of all fault states, that is, the normal working state; The sensitivity analysis formula is as follows: (S_i=\frac{\partialR}{\partialx_i}), Where (S_i) represents the sensitivity of reliability (R) to the (i)th characteristic (x_i).

[0027] As a further limitation of the technical solution of the present invention, the method further includes: comparing the measured data with the calculated overall reliability, and in the step of updating the model parameters and the confidence distribution, the updating formula is as follows: (m_{new}(A)=\alpha\cdotm_{old}(A)+(1-\alpha)\cdot\text{Feedback}(A)) Among them, (\alpha) is a parameter between 0 and 1, which determines the weight ratio of the original data and the newly measured data.

[0028] As a further limitation of the technical solution of the present invention, the method further includes: Continuously monitor the status of aircraft structural parts and update models and strategies based on new data and information fed back; the feedback loop formula is as follows: (\DeltaP=f(P_{current},P_{new},\Deltat)) Where (\DeltaP) represents the change of performance indicators, (P_{current}) and (P_{new}) represent the current and newly collected performance data respectively, and (\Deltat) is the time interval.

[0029] It can be seen from the above technical solutions that the present invention has the following advantages: various influencing factors are clearly considered, and the actual reliability of aircraft structural parts can be predicted more accurately. From collecting and processing data, to analyzing and calculating the weights of influencing factors, to integrating information through confidence allocation and combining rules, a reliability model of aircraft structural parts is jointly constructed. By dealing with uncertainty, calculating reliability, and conducting sensitivity analysis, the performance and life of structural parts can be predicted more accurately. Finally, through feedback and updating of results, continuous improvement and effective communication of the model are ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0031] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0033] like Figure 1 As shown, an embodiment of the present invention provides a method for analyzing and predicting the reliability of aircraft structural parts, comprising the following steps: Step 1: Obtain the physical properties, working environment, and historical data of aircraft structural parts; Physical characteristics include material properties, structural design, and manufacturing processes; The working environment includes temperature and humidity, vibration and shock, corrosion and oxidation, and external loads; Historical data includes maintenance data, usage data, and accident records.

[0034] Among them, material properties include: Material Type: Aircraft structural parts may be made of different types of materials, such as metal alloys, composite materials, etc.

[0035] Strength and stiffness: The strength and stiffness of materials are important physical properties for evaluating the load capacity and deformation degree of structural parts.

[0036] Structural design includes: Geometry: The shape of a structural component plays a key role in its force distribution and stress transfer.

[0037] Connection method: Consider the impact of connection methods, such as welding, bolt connection, etc., on the overall reliability of the structure.

[0038] The manufacturing process includes: Manufacturing accuracy: The manufacturing process has a direct impact on the size and shape accuracy of structural parts.

[0039] Quality control: Quality control measures during the production process directly affect the reliability of structural parts.

[0040] Temperature and humidity include: Aircraft fly at different altitudes and climate conditions, so the effects of changes in temperature and humidity on structural components must be considered.

[0041] Vibration and shock include: Aircraft are subject to various vibrations and shocks during flight, and these environmental factors may affect the fatigue life of structural parts.

[0042] Corrosion and oxidation include: Aircraft in wet environments may be affected by corrosion and oxidation, especially metal structures.

[0043] External loads include: Aircraft may be affected by external factors such as lightning strikes, bird strikes, etc. These loads may cause damage to structural parts.

[0044] Maintenance data includes: The past maintenance records of structural components, including the history of repairs and replacement parts, can provide clues to the health status of structural components.

[0045] Usage data includes: The aircraft's service history, including flight hours, number of take-offs and landings, etc., is used to evaluate the fatigue life and damage accumulation of structural parts.

[0046] The accident record includes: Aircraft accident records, including the performance of structural components in accidents, help evaluate the strength and reliability of structural components.

[0047] Step 2: Analyze the physical properties, working environment, and historical data of aircraft structural parts to establish a mathematical model of structural part characteristics; the elements in the model include characteristics that simulate the behavior of aircraft structural parts under different working conditions; The information obtained in step 1 is critical when building reliability models and formulating maintenance strategies. Ensuring that these physical characteristics, operating environment, and historical data are fully considered can more accurately predict the life and performance of structural components.

[0048] Based on the analysis of physical properties, working environment and historical data, a mathematical model is established to simulate the behavior of structural parts under different working conditions. The mathematical model is shown in the following formula: (X={a_1x_1^2+b_1y_1^3,a_2x_2^2+b_2y_2^3,...,a_nx_n^2+b_ny_n^3}) Among them, each term (a_ix_i^2+b_iy_i^3) represents a characteristic of the physical properties of the structural component, the working environment, and the historical data.

[0049] It should be noted that during the data processing stage, there is a large amount of data collected from different sensors and records, which may be missing, noisy or inconsistent in format. These problems are handled through data cleaning and conversion techniques to ensure data quality. Data preprocessing, including filling missing values ​​and removing outliers, is used to ensure data quality and consistency; Normalization is used to convert data of different scales to the same scale to facilitate subsequent statistical analysis and machine learning models; The normalization formula is shown below: (x_{norm}= \frac{(x-x_{mean})}{\sqrt{\sum_{i=1}^{n}(x_i-x_{mean})^2 / n}}) Here, ( x_{mean} ) is the mean of the data, and the standard deviation is used for normalization.

[0050] Step 3: Determine the influence of different characteristics on the reliability of aircraft structural parts through statistical analysis, that is, the weight of the influence factor of each characteristic; Determine the influence of different characteristics on the reliability of aircraft structural parts through statistical analysis and expert knowledge, and determine the influence of each characteristic, i.e., the weight; The weight calculation formula is as follows: (W={w_1\cdot\log(x_1),w_2\cdot\log(x_2),...,w_n\cdot\log(x_n)}) Among them, (w_i) represents the weight of the (i)th feature, and (\log(x_i)) represents the role of logarithmic transformation in weight allocation.

[0051] Step 4: Use a composite probability model to assign confidence to each feature; When allocating confidence, let the state space be S, the structural component characteristics be X∈S, and for each unit subset of the state space S, define a mapping: m:2^S → [0,1] Used to represent the confidence of each possible event, the mapping must satisfy m( )=0, and ∑_A∈_S m(A)=1; A composite probability model is used to combine the confidence of each characteristic. The composite probability model is shown in the following formula: (m(A)=1-\prod_{i=1}^{n}(1-w_i\cdot\text{Conf}(x_i))) Among them, (A) is a specific set of events, (\text{Conf}(x_i)) is the confidence corresponding to the feature (x_i).

[0052] Step 5: Apply the combination rule to combine the confidence information from different sources; The combination rule is used to deal with the conflict and consistency problems between different information sources. The combination rule formula is as follows: (m_{comb}(A)=\frac{\sum_{i=1}^{k}m_i(A)}{k}-\frac{\sum_{i=1}^{k}m_i(\bar{A})}{k}) Among them, (m_i(A)) represents the confidence of the (i)th information source about event (A), and (m_i(\bar{A})) represents its confidence in event non-(A). The formula is used to balance the contradictions of various information sources and find a reasonable middle value.

[0053] Step 6: Conduct reliability assessment and analysis of aircraft structural parts; The reliability of aircraft structural parts in the future is predicted by calculation. The reliability evaluation formula is shown as follows: (R(t)=e^{-\int_0^t\lambda(x)dx}) Among them, (\lambda(x)) is the failure rate function, and the reliability evaluation formula is used to reflect the probability that the component will not fail before time (t).

[0054] Based on the above analysis and models, we can also build a decision support system. This system will provide suggestions for maintenance, replacement and other operations based on real-time data and historical analysis results. The design of this system usually includes user interface, database management and background analysis algorithms.

[0055] Use machine learning models, such as random forests or neural networks, to predict the future state of structural components. These models calculate the future reliability of components based on input characteristic data.

[0056] Step 7: Based on the evaluation results and confidence allocation, calculate the overall reliability of the aircraft structure and perform sensitivity analysis of the characteristics based on the reliability calculation results; Based on the evaluation results and confidence allocation, the overall reliability of the structural parts is calculated and the model is optimized; The reliability calculation formula is as follows: (R=\sum_{X\inF^c}m(X)) Among them, (F^c) represents the complement of all fault states, that is, the normal working state.

[0057] The sensitivity analysis formula is shown as follows: (S_i=\frac{\partialR}{\partialx_i}), Where (S_i) represents the sensitivity of reliability (R) to the (i)th characteristic (x_i).

[0058] The method further includes step 8: comparing the measured data with the calculated overall reliability, and in the step of updating the model parameters and the confidence distribution, the updating formula is as follows: Update formula: (m_{new}(A)=\alpha\cdotm_{old}(A)+(1-\alpha)\cdot\text{Feedback}(A)) Where (\alpha) is a parameter between 0 and 1, which determines the weight ratio of old data and new feedback.

[0059] We need to continuously monitor the status of aircraft structures and update our models and strategies based on new data and information. This feedback loop ensures the effectiveness and timeliness of the entire system.

[0060] Feedback loop formula: (\DeltaP=f(P_{current},P_{new},\Deltat)), where (\DeltaP) represents the change in performance indicators, (P_{current}) and (P_{new}) represent the current and newly collected performance data respectively, and (\Deltat) is the time interval.

[0061] Compared with traditional methods, this reliability prediction method for aircraft structural parts based on the confidence reliability theory explicitly considers various influencing factors and can more accurately predict the actual reliability of aircraft structural parts. From collecting and processing data, to analyzing and calculating the weights of influencing factors, to integrating information through confidence allocation and combination rules, a reliability model for aircraft structural parts is jointly constructed. By dealing with uncertainty, calculating reliability, and conducting sensitivity analysis, the performance and life of structural parts can be predicted more accurately. Finally, through feedback and updating of results, continuous improvement and effective communication of the model are ensured.

[0062] The embodiment of the present invention also provides an aircraft structural component reliability analysis and prediction device, including a data acquisition module, a model building module, a weight calculation module, a confidence allocation module, a merging processing module, an evaluation analysis module, and a reliability analysis module; Data acquisition module, used to obtain physical properties, working environment, and historical data of aircraft structural parts; Physical characteristics include material properties, structural design, and manufacturing processes; The working environment includes temperature and humidity, vibration and shock, corrosion and oxidation, and external loads; Historical data includes maintenance data, usage data, and accident records.

[0063] Among them, material properties include: Material Type: Aircraft structural parts may be made of different types of materials, such as metal alloys, composite materials, etc.

[0064] Strength and stiffness: The strength and stiffness of materials are important physical properties for evaluating the load capacity and deformation degree of structural parts.

[0065] Structural design includes: Geometry: The shape of a structural component plays a key role in its force distribution and stress transfer.

[0066] Connection method: Consider the impact of connection methods, such as welding, bolt connection, etc., on the overall reliability of the structure.

[0067] The manufacturing process includes: Manufacturing accuracy: The manufacturing process has a direct impact on the size and shape accuracy of structural parts.

[0068] Quality control: Quality control measures during the production process directly affect the reliability of structural parts.

[0069] Temperature and humidity include: Aircraft fly at different altitudes and climate conditions, so the effects of changes in temperature and humidity on structural components must be considered.

[0070] Vibration and shock include: Aircraft are subject to various vibrations and shocks during flight, and these environmental factors may affect the fatigue life of structural parts.

[0071] Corrosion and oxidation include: Aircraft in wet environments may be affected by corrosion and oxidation, especially metal structures.

[0072] External loads include: Aircraft may be affected by external factors such as lightning strikes, bird strikes, etc. These loads may cause damage to structural parts.

[0073] Maintenance data includes: The past maintenance records of structural components, including the history of repairs and replacement parts, can provide clues to the health status of structural components.

[0074] Usage data includes: The aircraft's service history, including flight hours, number of take-offs and landings, etc., is used to evaluate the fatigue life and damage accumulation of structural parts.

[0075] The accident record includes: Aircraft accident records, including the performance of structural components in accidents, help evaluate the strength and reliability of structural components.

[0076] Model building module, which is used to analyze the physical characteristics, working environment, and historical data of aircraft structural parts and establish a mathematical model of structural part characteristics; elements in the model include characteristics that simulate the behavior of aircraft structural parts under different working conditions; The information obtained by the data acquisition module is crucial when building reliability models and formulating maintenance strategies. Ensuring that these physical characteristics, working environment and historical data are fully considered can more accurately predict the life and performance of structural components.

[0077] Based on the analysis of physical properties, working environment and historical data, a mathematical model is established to simulate the behavior of structural parts under different working conditions. The mathematical model is shown in the following formula: (X={a_1x_1^2+b_1y_1^3,a_2x_2^2+b_2y_2^3,...,a_nx_n^2+b_ny_n^3}) Among them, each term (a_ix_i^2+b_iy_i^3) represents a characteristic of the physical properties of the structural component, the working environment, and the historical data.

[0078] It should be noted that during the data processing stage, there is a large amount of data collected from different sensors and records, which may be missing, noisy or inconsistent in format. These problems are handled through data cleaning and conversion techniques to ensure data quality. Data preprocessing, including filling missing values ​​and removing outliers, is used to ensure data quality and consistency; Normalization is used to convert data of different scales to the same scale to facilitate subsequent statistical analysis and machine learning models; The normalization formula is shown below: (x_{norm}= \frac{(x-x_{mean})}{\sqrt{\sum_{i=1}^{n}(x_i-x_{mean})^2 / n}}) Here, ( x_{mean} ) is the mean of the data, and the standard deviation is used for normalization.

[0079] The weight calculation module is used to determine the influence of different characteristics on the reliability of aircraft structural parts through statistical analysis, that is, the weight of the influence factor of each characteristic; Determine the influence of different characteristics on the reliability of aircraft structural parts through statistical analysis and expert knowledge, and determine the influence of each characteristic, i.e., the weight; The weight calculation formula is as follows: (W={w_1\cdot\log(x_1),w_2\cdot\log(x_2),...,w_n\cdot\log(x_n)}) Among them, (w_i) represents the weight of the (i)th feature, and (\log(x_i)) represents the role of logarithmic transformation in weight allocation.

[0080] The confidence allocation module is used to allocate the confidence of each characteristic using a composite probability model. When allocating confidence, let the state space be S, the structural component characteristic be X∈S, and for each unit subset of the state space S, define a mapping: m:2^S → [0,1] is used to represent the confidence of each possible event. This mapping must satisfy m( )=0, and ∑_A∈_S m(A)=1; A composite probability model is used to combine the confidence of each characteristic. The composite probability model is shown in the following formula: (m(A)=1-\prod_{i=1}^{n}(1-w_i\cdot\text{Conf}(x_i))) Among them, (A) is a specific set of events, (\text{Conf}(x_i)) is the confidence corresponding to the feature (x_i).

[0081] The merging processing module is used to merge the confidence information from different sources by applying the combining rule; the combining rule is used to handle the conflict and consistency problems between different information sources. The combining rule formula is as follows: (m_{comb}(A)=\frac{\sum_{i=1}^{k}m_i(A)}{k}-\frac{\sum_{i=1}^{k}m_i(\bar{A})}{k}) Among them, (m_i(A)) represents the confidence of the (i)th information source about event (A), and (m_i(\bar{A})) represents its confidence in event non-(A). The formula is used to balance the contradictions of various information sources and find a reasonable middle value.

[0082] The evaluation and analysis module is used to evaluate the reliability of aircraft structural parts. It predicts the reliability of aircraft structural parts in the future through calculation. The reliability evaluation formula is as follows: (R(t)=e^{-\int_0^t\lambda(x)dx}) Among them, (\lambda(x)) is the failure rate function, and the reliability evaluation formula is used to reflect the probability that the component will not fail before time (t).

[0083] Based on the above analysis and models, we can also build a decision support system. This system will provide suggestions for maintenance, replacement and other operations based on real-time data and historical analysis results. The design of this system usually includes user interface, database management and background analysis algorithms.

[0084] Use machine learning models, such as random forests or neural networks, to predict the future state of structural components. These models calculate the future reliability of components based on input characteristic data.

[0085] The reliability analysis module is used to calculate the overall reliability of the aircraft structure based on the evaluation results and the confidence distribution, and to perform sensitivity analysis of the characteristics based on the reliability calculation results; the reliability calculation formula is as follows: (R=\sum_{X\inF^c}m(X)) Among them, (F^c) represents the complement of all fault states, that is, the normal working state.

[0086] The sensitivity analysis formula is shown as follows: (S_i=\frac{\partialR}{\partialx_i}), Where (S_i) represents the sensitivity of reliability (R) to the (i)th characteristic (x_i).

[0087] The device also includes an update module for comparing the measured data with the calculated overall reliability, updating the weights of the influencing factors and the confidence distribution. Comparing the prediction results with the actual observations, updating the model parameters and the confidence distribution. Update formula: (m_{new}(A)=\alpha\cdotm_{old}(A)+(1-\alpha)\cdot\text{Feedback}(A)) Where (\alpha) is a parameter between 0 and 1, which determines the weight ratio of old data and new feedback.

[0088] We need to continuously monitor the status of aircraft structures and update our models and strategies based on new data and information. This feedback loop ensures the effectiveness and timeliness of the entire system.

[0089] Feedback loop formula: (\DeltaP=f(P_{current},P_{new},\Deltat)), where (\DeltaP) represents the change in performance indicators, (P_{current}) and (P_{new}) represent the current and newly collected performance data respectively, and (\Deltat) is the time interval.

[0090] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0091] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.

Claims

1. A reliability analysis and prediction method for aircraft structural parts, characterized in that: The steps include: Obtain physical properties, working environment, and historical data of aircraft structural parts; Analyze the physical properties, working environment, and historical data of aircraft structural parts to establish a mathematical model of structural part characteristics; elements in the model include characteristics that simulate the behavior of aircraft structural parts under different working conditions; Determine the influence of different characteristics on the reliability of aircraft structural parts through statistical analysis, that is, the weight of the influence factor of each characteristic; A composite probability model is used to assign the degree of confidence of each characteristic; Applying combining rules to merge confidence information from different sources; Conduct reliability assessment and analysis of aircraft structural parts; Based on the evaluation results and confidence allocation, the overall reliability of aircraft structural components is calculated and sensitivity analysis of characteristics is performed based on the reliability calculation results.

2. The aircraft structural component reliability analysis and prediction method according to claim 1, characterized in that: In the step of obtaining physical characteristics, working environment, and historical data of aircraft structural parts, the physical characteristics include material properties, structural design, and manufacturing process; The working environment includes temperature and humidity, vibration and shock, corrosion and oxidation, and external loads; Historical data includes maintenance data, usage data, and accident records.

3. The aircraft structural component reliability analysis and prediction method according to claim 2, characterized in that: The physical properties, working environment, and historical data of aircraft structural parts are analyzed to establish a mathematical model of structural part characteristics. The mathematical model is as follows: (X={a_1x_1^2+b_1y_1^3,a_2x_2^2+b_2y_2^3,...,a_nx_n^2+b_ny_n^3}) Among them, each term (a_ix_i^2+b_iy_i^3) represents a characteristic of the physical properties of the structural component, the working environment, and the historical data.

4. The aircraft structural component reliability analysis and prediction method according to claim 3, characterized in that: In the step of determining the influence of different characteristics on the reliability of aircraft structural parts through statistical analysis, that is, the weight of the influencing factor of each characteristic, the weight calculation formula is as follows: (W={w_1\cdot\log(x_1),w_2\cdot\log(x_2),...,w_n\cdot\log(x_n)}) Among them, (w_i) represents the weight of the (i)th feature, and (\log(x_i)) represents the role of logarithmic transformation in weight allocation.

5. The aircraft structural component reliability analysis and prediction method according to claim 4, characterized in that: In the step of using a composite probability model to allocate the confidence of each characteristic, the composite probability model is as follows: (m(A)=1-\prod_{i=1}^{n}(1-w_i\cdot\text{Conf}(x_i))) Where (A) is a set of events and (\text{Conf}(x_i)) is the confidence corresponding to feature (x_i).

6. The aircraft structural component reliability analysis and prediction method according to claim 5, characterized in that: In the step of applying the combination rule to combine the confidence information from different sources, the combination rule formula is as follows: (m_{comb}(A)=\frac{\sum_{i=1}^{k}m_i(A)}{k}-\frac{\sum_{i=1}^{k}m_i(\bar{A})}{k}) Among them, (m_i(A)) represents the confidence of the (i)th information source about event (A), and (m_i(\bar{A})) represents the confidence about event not (A).

7. The aircraft structural component reliability analysis and prediction method according to claim 6, characterized in that: In the steps of reliability assessment analysis of aircraft structural parts, the reliability assessment formula is as follows: (R(t)=e^{-\int_0^t\lambda(x)dx}) Among them, (\lambda(x)) is the failure rate function, and the reliability evaluation formula is used to reflect the probability that the component will not fail before time (t).

8. The aircraft structural component reliability analysis and prediction method according to claim 7, characterized in that: In the step of calculating the overall reliability of aircraft structural parts based on the evaluation results and the confidence distribution and performing sensitivity analysis of characteristics based on the reliability calculation results, The reliability calculation formula is as follows: (R=\sum_{X\inF^c}m(X)) Among them, (F^c) represents the complement of all fault states, that is, the normal working state; The sensitivity analysis formula is as follows: (S_i=\frac{\partialR}{\partialx_i}), Where (S_i) represents the sensitivity of reliability (R) to the (i)th characteristic (x_i).

9. The aircraft structural component reliability analysis and prediction method according to claim 8, characterized in that: The method further includes: comparing the measured data with the calculated overall reliability, and updating the model parameters and the confidence distribution step, wherein the updating formula is as follows: (m_{new}(A)=\alpha\cdotm_{old}(A)+(1-\alpha)\cdot\text{Feedback}(A)) Among them, (\alpha) is a parameter between 0 and 1, which determines the weight ratio of the original data and the newly measured data.

10. The aircraft structural component reliability analysis and prediction method according to claim 9, characterized in that: The method further includes: Continuously monitor the status of aircraft structural parts and update models and strategies based on new data and information fed back; the feedback loop formula is as follows: (\DeltaP=f(P_{current},P_{new},\Deltat)) Where (\DeltaP) represents the change of performance indicators, (P_{current}) and (P_{new}) represent the current and newly collected performance data respectively, and (\Deltat) is the time interval.

Images