Aerial load working condition category analysis method and system considering danger degree

Abstract

The invention belongs to the technical field of load working condition analysis, and particularly relates to an aerial load working condition category analysis method and system considering the danger degree, and the method comprises the steps: obtaining the section data of an aerial load and the flag bit of the aerial load; according to the obtained cross section data and flag bits, determining the aerial load working conditions, and respectively constructing a sorting prediction model and a classification prediction model of the aerial load working conditions; based on the constructed sorting prediction model, calculating a risk level score of the aerial load working condition, and obtaining a sorting of the risk levels of the aerial load working condition; based on the constructed classification prediction model, obtaining a classification result of the danger degree of the aerial load working condition; according to the obtained sorting and classification results of the danger degrees of the aerial load working conditions, screening the aerial load working conditions; and carrying out finite element analysis on the screened aerial load working conditions, and completing aerial load working condition category analysis considering the danger degree.

Description

Technical Field

[0001] The present invention belongs to the technical field of load condition analysis, and particularly relates to a method and system for analyzing aviation load condition categories considering the degree of danger. Background Technique

[0002] The statements in this part only provide background technical information related to the present invention, and do not necessarily constitute prior art.

[0003] In the field of aircraft design, due to the differences in the requirements of various aircraft models, hundreds of load conditions need to be considered and finite element analysis is carried out during the aircraft model design stage; however, the calculation of the detailed models of various conditions takes a long time. To solve this problem, a simplified aircraft grid model can be constructed, and different load conditions are applied to the constructed aircraft grid model to observe the stress and displacement conditions of each part under different conditions. At present, load screening mainly relies on the load envelope method, but the load envelope method is time-consuming, laborious and subjective; other simple methods can also achieve load screening, but they are only applicable to the load condition analysis of specific parts or specific situations.

[0004] Aircraft load screening based on neural network integration can obtain the ranking of the degree of danger of all load conditions and cluster and identify the load conditions to obtain the dangerous categories, realizing the identification and screening of dangerous conditions; however, this method can only realize the screening of dangerous conditions based on the existing load conditions, and cannot realize the offline classification prediction and ranking prediction for new aircraft models and new load conditions. Summary of the Invention

[0005] To solve the above problems, the present invention proposes a method and system for analyzing aviation load condition categories considering the degree of danger. By constructing a classification prediction model and a ranking prediction model, when a new load condition appears, the category and ranking position of the new condition can be quickly obtained to determine whether the newly added load condition is in a dangerous state.

[0006] According to some embodiments, the first solution of the present invention provides a method for analyzing aviation load condition categories considering the degree of danger, and adopts the following technical solution:

[0007] A method for analyzing aviation load condition categories considering the degree of danger includes:

[0008] Obtain the cross-sectional data of the aviation load and its flag bits;

[0009] According to the obtained cross-sectional data and flag bits, determine the aviation load conditions, and respectively construct a ranking prediction model and a classification prediction model for the aviation load conditions;

[0010] Based on the constructed sorting prediction model, calculate the risk level score of the aviation load conditions, and obtain the ranking of the risk levels of the aviation load conditions;

[0011] Based on the constructed classification prediction model, obtain the classification result of the risk level of the aviation load conditions;

[0012] According to the obtained ranking and classification result of the risk level of the aviation load conditions, conduct screening of the aviation load conditions;

[0013] Conduct finite element analysis on the screened aviation load conditions to complete the analysis of the categories of aviation load conditions considering the risk level.

[0014] As a further technical limitation, according to the obtained ranking result of the risk level of the aviation load conditions, and then according to the stress value of the aviation load condition with the highest risk level obtained based on the finite element analysis, conduct screening of the aviation load conditions.

[0015] As a further technical limitation, the classification prediction model adopts a clustering algorithm, and completes classification by calculating the similarity between the risk levels of different aviation load conditions. The classification result is related to the level of the risk level.

[0016] As a further technical limitation, conduct analysis on the finite element detailed model of the screened aviation load conditions, calculate the finite element structural stress value of the screened aviation load conditions, and complete the finite element analysis of the aviation load conditions by comparing the stress value with the stress threshold.

[0017] As a further technical limitation, the finite element analysis result of the screened aviation load condition is the stress value of each structure of the aviation load condition.

[0018] As a further technical limitation, divide the aviation load into six parts: the left and right wings, the left and right vertical tails, the left and right horizontal tails, the rear fuselage, the middle fuselage, and the front fuselage. Select several cross-sections for each part, extract the internal force metadata of each cross-section according to the finite element coarse model, determine the working conditions of each part according to the extracted internal force metadata and the finite element database, and determine the working conditions of the aviation load according to the determined working conditions of each part.

[0019] According to some embodiments, the second solution of the present invention provides a system for analyzing the categories of aviation load conditions considering the risk level, and adopts the following technical solution:

[0020] A system for analyzing the categories of aviation load conditions considering the risk level, comprising:

[0021] An acquisition module, which is configured to acquire the cross-section data of the aviation load and its flag bits;

[0022] A building module configured to determine an aviation load condition according to the acquired cross-sectional data and flag bits, and respectively construct a sorting prediction model and a classification prediction model for the aviation load condition;

[0023] A sorting module configured to calculate a risk level score for the aviation load condition based on the constructed sorting prediction model, and obtain a ranking of the risk levels of the aviation load conditions;

[0024] A classification module configured to obtain a classification result of the risk level of the aviation load condition based on the constructed classification prediction model;

[0025] A screening module configured to screen the aviation load conditions according to the obtained ranking and classification result of the risk levels of the aviation load conditions;

[0026] An analysis module configured to perform finite element analysis on the screened aviation load conditions to complete the analysis of the categories of aviation load conditions considering the risk level.

[0027] According to some embodiments, a third aspect of the present invention provides a computer-readable storage medium, adopting the following technical solution:

[0028] A computer-readable storage medium, on which a program is stored, and when the program is executed by a processor, it implements the steps in the method for analyzing the categories of aviation load conditions considering the risk level as described in the first aspect of the present invention.

[0029] According to some embodiments, a fourth aspect of the present invention provides an electronic device, adopting the following technical solution:

[0030] An electronic device includes a memory, a processor, and a program stored on the memory and running on the processor. When the processor executes the program, it implements the steps in the method for analyzing the categories of aviation load conditions considering the risk level as described in the first aspect of the present invention.

[0031] According to some embodiments, a fifth aspect of the present invention provides a computer program product, adopting the following technical solution:

[0032] A computer program product includes software code, and the program in the software code executes the steps in the method for analyzing the categories of aviation load conditions considering the risk level as described in the first aspect of the present invention.

[0033] Compared with the prior art, the beneficial effects of the present invention are:

[0034] The present invention identifies and classifies the risk levels of load conditions for aircraft and other aviation components, greatly reducing the time and computing resources required for traditional finite element analysis and improving the efficiency of design and analysis. It uses an objective method to identify and screen dangerous working conditions, reducing the interference of human factors that rely on subjective judgment in traditional load screening methods and improving the accuracy and reliability of the results. By training classification prediction models and ranking prediction models for load conditions of different aircraft models, the generalization performance of the obtained prediction models is enhanced, and thus they can be applied to different aircraft models, different parts, and different load conditions. For newly added load conditions, offline classification prediction and ranking prediction can be achieved, quickly obtaining the category and ranking position of the new working conditions to determine whether the newly added load conditions are dangerous. Through data augmentation and random sampling techniques, the number of data samples is increased to reduce the risk of overfitting of the prediction model and improve the generalization ability of the prediction model. Through the method of ensemble learning, the prediction and identification accuracy of dangerous working conditions is improved. In the prediction model, through activation functions and parameter adjustment, the generalization ability and accuracy of the prediction model are enhanced by adaptively selecting the optimal algorithm. Overall, the present invention reduces the dependence on complex computing resources, reduces the cost of aviation design and analysis, improves the analysis efficiency, reduces the labor cost, and at the same time reduces the safety risk while improving the analysis efficiency and accuracy of load conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings forming a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments and descriptions thereof of this embodiment are used to explain this embodiment and do not constitute an improper limitation of this embodiment.

[0036] Figure 1 It is a flowchart of the method for analyzing the categories of aviation load conditions considering the risk level in Embodiment 1 of the present invention;

[0037] Figure 2 It is a flowchart for constructing the ranking prediction model in Embodiment 1 of the present invention;

[0038] Figure 3 It is a flowchart for constructing the classification prediction model in Embodiment 1 of the present invention;

[0039] Figure 4 It is a structural block diagram of the system for analyzing the categories of aviation load conditions considering the risk level in Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0041] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs.

[0042] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular forms are also intended to include the plural forms. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0043] In the present invention, terms such as "upper", "lower", "left", "right", "front", "rear", "vertical", "horizontal", "side", "bottom", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. They are only relationship terms determined for the convenience of describing the structural relationship of each component or element of the present invention and do not specifically refer to any component or element of the present invention and should not be construed as limiting the present invention.

[0044] In the present invention, terms such as "fixed connection", "connected", "connected to" should be understood in a broad sense, which may mean a fixed connection, an integral connection or a detachable connection; it may be directly connected or indirectly connected through an intermediate medium. For those relevant scientific research or technical personnel in the field, the specific meanings of the above terms in the present invention can be determined according to specific circumstances and should not be construed as limiting the present invention.

[0045] In the case of no conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0046] Embodiment 1

[0047] Embodiment 1 of the present invention introduces a method for analyzing aviation load condition categories considering the degree of danger.

[0048] To solve the problems of identifying and classifying the degree of danger of newly added load conditions, offline classification prediction and ranking prediction of each part of a single aircraft type, and multi-aircraft type model training and generalization to achieve offline classification prediction and ranking prediction, the method for analyzing aviation load condition categories considering the degree of danger in this embodiment introduces two models (i.e., a ranking prediction model and a classification prediction model). When a newly added load condition is added, the category and ranking position of the new condition can be quickly obtained, and then it can be judged whether it is dangerous and whether a detailed model needs to be calculated. At the same time, by training the load conditions of different aircraft types, a model with strong generalization performance can be obtained, which is applicable to different aircraft types, different parts, and different load conditions.

[0049] As Figure 1 shown, a method for analyzing the category of aircraft load conditions considering the degree of danger includes:

[0050] Obtain the cross-sectional data of the aircraft load and its flag bits;

[0051] According to the obtained cross-sectional data and flag bits, determine the aircraft load conditions, and respectively construct a sorting prediction model and a classification prediction model for the aircraft load conditions;

[0052] Based on the constructed sorting prediction model, calculate the danger degree score of the aircraft load conditions to obtain the ranking of the danger degree of the aircraft load conditions;

[0053] Based on the constructed classification prediction model, obtain the classification result of the danger degree of the aircraft load conditions;

[0054] According to the obtained ranking and classification result of the danger degree of the aircraft load conditions, conduct screening of the aircraft load conditions;

[0055] Conduct finite element analysis on the screened aircraft load conditions to complete the analysis of the category of aircraft load conditions considering the degree of danger.

[0056] In this embodiment, the aircraft is divided into the left wing, right wing, left horizontal tail, right horizontal tail, left vertical tail, right vertical tail, rear fuselage, middle rear fuselage, middle front fuselage, and front fuselage as the original data. Taking the wing as an example, 7 cross-sections are intercepted on it, and the six-force elements, resultant force, and resultant moment of each cross-section are obtained using the FBD tool in Hypermash (that is, the forces acting on all structures on this cross-section are equivalent to a point, and the position of this point is automatically obtained by the Hypermesh software, and finally the six-force elements, resultant force, and resultant moment of the cross-section at this point are obtained). According to the previous work, it is known that the basic data should adopt all the data intercepted from the cross-section, that is, the six-force elements, resultant force, and resultant moment of 7 cross-sections, a total of 56 indicators. These 56 indicators are regarded as positive indicators, and the larger the obtained value, the more dangerous the condition.

[0057] It should be noted that the six elements of the moment in this embodiment are the force in the X direction, force in the Y direction, force in the Z direction, moment about the X axis, moment about the Y axis, and moment about the Z axis in the global coordinate system of the finite element model.

[0058] In finite element analysis, stress ranking is obtained from the coarse model. Through PCA (Principal Component Analysis), SVD (Singular Value Decomposition), Topsis method, entropy weight method, grey relational degree, improved CRITIC method, rank sum ratio method, CRITIC-GARP, CRITIC-Topsis, and CRITIC-entropy weight method, the load conditions are evaluated and ranked from the perspectives of force and moment. Before ranking, the risk level scores of each condition are obtained, and the ranking is based on these scores. Since the ranges of the risk level scores obtained by each ranking method are different, the scores of the load conditions obtained by each method are normalized so that the scores are uniformly within the range of [0, 1], which is convenient for subsequent integration.

[0059] In this embodiment, four algorithm verification indicators are set to quantify the similarity between pairwise ranking algorithms. By averaging the normalization of the four indicators, the similarity between two algorithms can be obtained. Specifically:

[0060] Indicator 1: The slope and intercept of the linear fit between the ranking positions of the two algorithms. If the similarity between the two algorithms is very high, the slope of the fitted line is close to 1 and the intercept is close to 0.

[0061] Indicator 2: The difference between the ranking positions of the two algorithms, divided by the number of working conditions, that is, the average position difference of the working conditions between the two algorithms.

[0062] Indicator 3: If the position difference of the working conditions between the two algorithms exceeds 5% of the number of working conditions, then mark it as 1, otherwise mark it as 0. Sum up the marked bits and divide by the number of working conditions, that is, what percentage of the total number of working conditions exceeds the limit error.

[0063] Indicator 4: The sum of the position differences of the working conditions of the two algorithms, divided by the product of the number of working conditions and 5% of the number of working conditions, that is, the position qualification rate. If this indicator is greater than 1, it fails, otherwise it passes.

[0064] In summary, the larger Indicator 1 is, the higher the similarity between the two algorithms; the smaller Indicator 2, Indicator 3, and Indicator 4 are, the higher the similarity between the two algorithms.

[0065] Each ranking algorithm is described and screened through multiple indicators. Select the top five algorithms that pass the four indicators test and are better (if there are not five methods that pass the test, directly use the methods that pass the test). In this way, the method screening is completed. When calculating the verification indicators between two algorithms, the index weights obtained from the stress ranking are adjusted to be larger, so that the results do not deviate from the stress results and are different from the stress results. The starting point of the ranking is that there are differences between the single stress ranking and the actual detailed model ranking. Supplementary ranking in the dimension of section internal force makes the ranking more reliable and accurate.

[0066] After algorithm screening, five sorting algorithms passed the test. Each of them has a risk level score for each working condition. After normalization, the scores of each working condition in each algorithm are weighted and aggregated. To ensure that the stress sorting dominates, the weight of the stress sorting score is correspondingly increased, and it has the same weight as the algorithm setting. Finally, the risk level scores of each working condition are obtained and sorted.

[0067] To reduce the risk of overfitting of the sorting prediction model and improve the generalization ability of the model, first, the features (i.e., internal force indicators) of each working condition are randomly sampled so that each new working condition contains 70% of the feature information of the original working conditions, and the scores of the new working conditions are the same as those of the original working conditions. Thus, on the basis of the original samples, random sampling is carried out, increasing the sample size and reducing the overfitting risk. After data augmentation, the training set and the validation set are divided according to a ratio of 3:7.

[0068] To ensure that each subsequent model learns the complete training set, the K-fold cross-validation method is used to construct different training sets for different sorting prediction algorithms and obtain a same validation set.

[0069] After data augmentation and division are completed, a multi-layer perceptron, 1D-CNN, Bayesian ridge regression, random forest regression, support vector machine regression, polynomial regression, and XGBoost regression are used to learn and train the data; the K-fold cross-validation is used to obtain the validation set for verification.

[0070] The results of each algorithm in the validation set are input into the ReLU activation function. According to the threshold setting, it is controlled whether the algorithm is activated, and the algorithms with insufficient accuracy are screened out; at the same time, the non-linearity degree of the model is increased; specifically, the accuracy on the validation set is x, the threshold is set to 95%, and the value input into the activation function is x - 95%. If this value is less than 0, that is, the accuracy is lower than 95%, the activation function is set to zero and not activated; otherwise, it is activated.

[0071] In this embodiment, the validation set obtained by random sampling is predicted. Each algorithm (multi-layer perceptron, 1D-CNN, Bayesian ridge regression, random forest regression, support vector machine regression, polynomial regression, XGBoost regression) will obtain a prediction score. The accuracy of each algorithm in its validation set is used as the weight to weight and aggregate the scores predicted by all algorithms, and finally, the scores are sorted according to the weighted scores.

[0072] Compare the prediction results in the validation set with the original sorting results, and describe its accuracy according to the above indicators one, two, three, and four. If the accuracy does not meet the requirements, model parameter tuning is carried out; the parameters to be adjusted include the number of selections in the algorithm screening layer, the random sampling method, the threshold of the activation function, etc. All parameters are traversed to find the optimal result; parameter setting and model training are completed; specifically,

[0073] Random sampling is the multiple of data augmentation. New data is generated from the original data by randomly sampling the features to achieve the purpose of data augmentation, and the number of newly generated data can be controlled (in this embodiment, it is 3-5 times that of the original data).

[0074] The activation function threshold can control the number of screened ones by adjusting the activation function threshold; in this embodiment, the initial threshold is set to 92%, the second level is 95%, and the third level is 97%; in the initial stage, the parameter of the algorithm screening layer is 5, that is, seven algorithms pass the screening, and the random sampling data augmentation is 3 times, and the activation function threshold is not set temporarily. If the final effect is not good, reduce the number of algorithms passing through the screening layer to 3, the random sampling data augmentation multiple is 4 times, and add the activation function threshold of 92%.

[0075] At this time, the Figure 2 sorting prediction model as shown is obtained.

[0076] In this embodiment, the aircraft dangerous load condition recognition system based on the neural network has distinguished dangerous conditions, relatively dangerous conditions until safe conditions. Therefore, flag bits can be added to add different labels to conditions of different danger levels.

[0077] For data augmentation, the same method of randomly sampling sample features is adopted to increase the number of original samples, improve the classification accuracy, reduce the risk of overfitting, and keep the sample labels consistent before and after sampling. The training set and the validation set are divided in a ratio of 3:7.

[0078] For the training set, the K-fold cross-validation method is also adopted to provide different training sets and the same validation set for classification algorithms such as support vector machine, random forest, multi-layer perceptron, Bayesian network, 1D-CNN, KNN, and BSNN. Ensure that the classification model can completely train the original data and ensure the accuracy of the model.

[0079] The results of each algorithm on the validation set are input into the ReLU activation function. According to the set threshold, the model with accurate prediction results is activated, and vice versa. The algorithm selection is completed adaptively, the generalization ability of the model is enhanced, and the accuracy is improved.

[0080] For the validation set obtained by random sampling, the prediction results are obtained by Stacking classification integration of multiple models. The validation set is passed through each activated algorithm to obtain the category to which the condition belongs. The accuracy of each algorithm in the validation set is used as the category score, and finally the probability of a certain condition in a certain category is obtained. The category score is input into the logistic regression model, and the category to which the condition belongs can be directly obtained.

[0081] It should be noted that the number of working condition categories depends on the location of the aviation load; the number of categories for different locations of the aviation load is different, but their categories are all from safe to dangerous; that is, the first category is the safest and the last category is the most dangerous.

[0082] In this embodiment, the classification accuracy is obtained by comparing the classification of the validation set with the true classification result, and it is judged whether the model needs to be tuned according to the final accuracy; the parameters to be adjusted include the way of random sampling, the activation threshold of the activation function, and the integration method; all parameters are traversed to find the optimal result, and the parameter setting and model training are completed; the specific process is exactly the same as that in the sorting prediction model, and this embodiment will not be elaborated here.

[0083] At this time, as shown in Figure 3 the classification prediction model shown.

[0084] After the sorting prediction model and the classification prediction model are trained, they start to accept new load conditions. For the new load condition data, random feature sampling is used to construct multiple samples, which are respectively input into the classification prediction model and the sorting prediction model.

[0085] In the sorting prediction model, multiple samples are constructed to obtain multiple risk level scores, and the average of these risk level scores is used as the final risk level score of the working condition; in the classification prediction model, multiple samples constructed from the new working condition may obtain different category results in the model, and the scores of each category are retained to achieve a soft classification, and the probability that the working condition belongs to a certain category is output.

[0086] This embodiment uses an objective method to realize the identification and screening of dangerous working conditions, reduces the interference of human factors that traditional load screening methods rely on subjective judgment, and improves the accuracy and reliability of the results; through the training of the classification prediction model and the sorting prediction model for the load conditions of different aircraft models, the generalization performance of the obtained prediction model is enhanced, and thus it can be applied to different aircraft models, different locations, and different load conditions; for the newly added load conditions, offline classification prediction and sorting prediction can be realized, and the category and sorting position of the new working condition can be quickly obtained to judge whether the newly added load condition is dangerous; through data augmentation and random sampling techniques, the number of data samples is increased to reduce the risk of overfitting of the prediction model and improve the generalization ability of the prediction model; through the method of ensemble learning, the prediction and identification accuracy of dangerous working conditions is improved; in the prediction model, through the activation function and parameter adjustment, the generalization ability and accuracy of the prediction model are enhanced by adaptively selecting the optimal algorithm; this embodiment reduces the dependence on complex computing resources as a whole, reduces the cost of aircraft design and analysis, improves the analysis efficiency, reduces the labor cost, and at the same time reduces the safety risk while improving the analysis efficiency and accuracy of load conditions..

[0087] Embodiment 2

[0088] Embodiment 2 of the present invention introduces an analysis system for aviation load condition categories considering the degree of danger.

[0089] As Figure 4 shown, an analysis system for aviation load condition categories considering the degree of danger includes:

[0090] An acquisition module configured to acquire cross-sectional data of the aviation load and its flag bits;

[0091] A construction module configured to determine the aviation load conditions based on the acquired cross-sectional data and flag bits, and respectively construct a sorting prediction model and a classification prediction model for the aviation load conditions;

[0092] A sorting module configured to calculate the danger degree score of the aviation load conditions based on the constructed sorting prediction model, and obtain the sorting of the danger degree of the aviation load conditions;

[0093] A classification module configured to obtain the classification result of the danger degree of the aviation load conditions based on the constructed classification prediction model;

[0094] A screening module configured to screen the aviation load conditions according to the obtained sorting and classification results of the danger degree of the aviation load conditions;

[0095] An analysis module configured to perform finite element analysis on the screened aviation load conditions to complete the analysis of the aviation load condition categories considering the degree of danger.

[0096] The detailed steps are the same as those of the method for analyzing aviation load condition categories considering the degree of danger provided in Embodiment 1, and will not be elaborated here.

[0097] Embodiment 3

[0098] Embodiment 3 of the present invention provides a computer-readable storage medium.

[0099] A computer-readable storage medium, on which a program is stored, and when the program is executed by a processor, it implements the steps in the method for analyzing aviation load condition categories considering the degree of danger as described in Embodiment 1 of the present invention.

[0100] The detailed steps are the same as those of the method for analyzing aviation load condition categories considering the degree of danger provided in Embodiment 1, and will not be elaborated here.

[0101] Embodiment 4

[0102] Embodiment 4 of the present invention provides an electronic device.

[0103] An electronic device includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, the steps in the method for analyzing aviation load condition categories considering the degree of danger as described in Embodiment 1 of the present invention are implemented.

[0104] The detailed steps are the same as those in the method for analyzing aviation load condition categories considering the degree of danger provided in Embodiment 1, and will not be elaborated here.

[0105] Embodiment 5

[0106] Embodiment 5 of the present invention provides a computer program product.

[0107] A computer program product includes software code, and the program in the software code executes the steps in the method for analyzing aviation load condition categories considering the degree of danger as described in Embodiment 1 of the present invention.

[0108] The detailed steps are the same as those in the method for analyzing aviation load condition categories considering the degree of danger provided in Embodiment 1, and will not be elaborated here.

[0109] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented in various computer languages, for example, object-oriented programming languages such as Java and interpreted scripting languages such as JavaScript.

[0110] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the specified functions in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0111] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction means that implements the functions specified in one or more of the processes and / or blocks Figure 1 one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the processes and / or blocks Figure 1 one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0113] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to cover the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0114] It is obvious that those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

[0115] The above are only the preferred embodiments of this example and are not used to limit this example. For those skilled in the art, this example can have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of this example shall be included within the protection scope of this example.

Claims

1. A method for analyzing aviation load conditions taking into account the degree of danger, characterized in that: include: Obtain the cross-sectional data and flags of aviation loads; According to the obtained cross-sectional data and flags, the aviation load conditions are determined, and a sorting prediction model and a classification prediction model of the aviation load conditions are respectively constructed; Based on the constructed ranking prediction model, the criticality scores of aviation load conditions are calculated to obtain the ranking of criticality of aviation load conditions; Based on the constructed classification prediction model, the classification results of the dangerousness of aviation load conditions are obtained; According to the obtained ranking and classification results of the dangerousness of aviation load conditions, the aviation load conditions are screened; Conduct finite element analysis on the selected aviation load conditions and complete the aviation load condition category analysis taking into account the degree of danger.

2. A method for analyzing aviation load conditions taking into account the degree of danger as claimed in claim 1, characterized in that: According to the ranking results of the dangerousness of the aviation load conditions obtained, the aviation load conditions are screened according to the stress value of the aviation load condition with the highest dangerousness obtained based on the finite element analysis.

3. The method for analyzing aviation load conditions taking into account the degree of danger as claimed in claim 1, characterized in that: The classification prediction model adopts a clustering algorithm and completes the classification by calculating the similarity between the dangerousness levels of different aviation load conditions. The classification result is related to the level of dangerousness.

4. The method for analyzing aviation load conditions taking into account the degree of danger as claimed in claim 1, characterized in that: The finite element detailed model is analyzed for the selected aviation load conditions, the finite element structural stress value of the selected aviation load conditions is calculated, and the finite element analysis of the aviation load conditions is completed by comparing the stress value with the stress threshold.

5. The method for analyzing aviation load conditions taking into account the degree of danger as claimed in claim 1, characterized in that: The finite element analysis results of the selected aviation load conditions are the stress values ​​of each structure of the aviation load conditions.

6. The method for analyzing aviation load conditions taking into account the degree of danger as claimed in claim 1, characterized in that: The aviation load is divided into six parts, namely, left and right wings, left and right vertical tails, left and right horizontal tails, rear fuselage, middle fuselage and front fuselage. Several sections are selected for each part, and the internal force metadata of each section is extracted according to the finite element rough model. The working condition of each part is determined according to the extracted internal force metadata and the finite element database, and the working condition of the aviation load is determined according to the determined working condition of each part.

7. An aviation load condition category analysis system taking into account the degree of danger, characterized in that: include: An acquisition module, which is configured to acquire cross-sectional data of the aviation load and its flag bit; A construction module is configured to determine the aviation load condition according to the obtained cross-sectional data and flags, and to respectively construct a sorting prediction model and a classification prediction model of the aviation load condition; A ranking module is configured to calculate the criticality scores of the aviation load conditions based on the constructed ranking prediction model, and obtain the ranking of the criticality of the aviation load conditions; A classification module, which is configured to obtain a classification result of the danger level of the aviation load condition based on the constructed classification prediction model; A screening module, configured to screen the aviation load conditions according to the obtained ranking and classification results of the danger levels of the aviation load conditions; The analysis module is configured to perform finite element analysis on the selected aviation load conditions and complete aviation load condition category analysis taking into account the degree of danger.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the aviation load condition category analysis method taking into account the degree of danger as described in any one of claims 1 to 6 are implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of the aviation load condition category analysis method taking into account the degree of danger as described in any one of claims 1 to 6 are implemented.

10. A computer program product comprising software code, characterized in that The program in the software code executes the steps of the aviation load condition category analysis method taking into account the degree of danger as described in any one of claims 1-6.

Images