CN117874905A - Method, system, equipment and storage medium for predicting damage of airplane windshield - Google Patents
Method, system, equipment and storage medium for predicting damage of airplane windshield Download PDFInfo
- Publication number
- CN117874905A CN117874905A CN202311725250.7A CN202311725250A CN117874905A CN 117874905 A CN117874905 A CN 117874905A CN 202311725250 A CN202311725250 A CN 202311725250A CN 117874905 A CN117874905 A CN 117874905A
- Authority
- CN
- China
- Prior art keywords
- damage
- data
- prediction
- windshield
- aircraft windshield
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 71
- 238000004088 simulation Methods 0.000 claims abstract description 62
- 238000003062 neural network model Methods 0.000 claims abstract description 33
- 238000012795 verification Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 5
- 238000000926 separation method Methods 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 abstract description 13
- 230000009286 beneficial effect Effects 0.000 abstract description 7
- 238000001514 detection method Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 13
- 230000003902 lesion Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 7
- 239000000463 material Substances 0.000 description 7
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000013178 mathematical model Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 230000002123 temporal effect Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 210000000653 nervous system Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method, a system, equipment and a storage medium for predicting damage of an aircraft windshield, wherein the method can predict damage conditions of future time nodes through damage parameter data and damage image data of a target aircraft windshield in a historical time period based on a configured neural network model, perform physical simulation by using damage modeling data, determine simulation result data of the target aircraft windshield at the future time nodes, and then check a first prediction result by taking the simulation result data as a judging reference condition, so as to determine damage prediction results corresponding to the target aircraft windshield. The method can predict the possible damage condition of the target aircraft windshield in the future, has relatively high prediction accuracy, can facilitate the maintenance work of the aircraft, improves the maintenance efficiency, and is beneficial to improving the safety of the aircraft. The method and the device can be widely applied to the technical field of damage detection.
Description
Technical Field
The application relates to the technical field of damage detection, in particular to a damage prediction method, a damage prediction system, damage prediction equipment and a storage medium for an aircraft windshield.
Background
The aircraft windshield is a transparent glass plate arranged in front of the cockpit and at the side of the fuselage, and is used for protecting pilots and crews in the cockpit from external factors such as wind pressure, air flow, flying objects, weather and the like. During the operation of the aircraft, due to factors such as collision, temperature difference, corrosion, fatigue and the like, cracks may appear on the windshield of the aircraft, and the cracks may limit the vision of the pilot, thereby reducing the flight safety. More seriously, due to the characteristics of materials, once cracks of an airplane windshield are expanded to a certain program, under the condition of high-altitude complex stress, the cracks can instantaneously burst, and the safety standard is exceeded, so that the flight safety is affected. Therefore, the method is an important work for crack damage detection of the airplane windshield.
In the related technology, most of the current aircraft maintenance fields stay in the experience judging stage for detecting the damage of the aircraft windshield, and the aircraft windshield is difficult to prevent in a targeted manner depending on the professional ability of maintenance personnel, so that the aircraft windshield can be replaced in time only when the damage of serious damage of the aircraft windshield is found, and a certain potential safety hazard exists.
In view of the above, there is a need to solve the problems of the related art.
Disclosure of Invention
The present application aims to solve at least one of the technical problems existing in the related art to a certain extent.
It is therefore an object of embodiments of the present application to provide methods, systems, devices and storage media for damage prediction for aircraft windshields.
In order to achieve the technical purpose, the technical scheme adopted by the embodiment of the application comprises the following steps:
in one aspect, embodiments of the present application provide a method of damage prediction for an aircraft windshield, the method comprising:
acquiring damage record data of a target aircraft windshield in a historical time period; the damage record data comprises damage parameter data, damage image data and damage modeling data;
based on a configured neural network model, predicting the damage condition of the target aircraft windshield at a future time node through the damage parameter data and the damage image data to obtain a first prediction result;
according to the damage modeling data, performing physical simulation on the damage condition of the target aircraft windshield at the future time node to obtain simulation result data;
taking the simulation result data as a judging reference condition, and checking the first prediction result;
And if the first prediction result passes the verification, determining the first prediction result as a damage prediction result corresponding to the windshield of the target aircraft.
In addition, the method for predicting damage to an aircraft windshield according to the above embodiment of the present application may further have the following additional technical features:
further, in one embodiment of the present application, after the step of obtaining damage record data for the target aircraft windshield over a historical period of time, the method further comprises:
and performing data separation operation, data cleaning operation and data conversion operation on the damage record data.
Further, in one embodiment of the present application, performing a data cleansing operation on the damage record data includes:
performing supplementary recording on lost data in the damage record data;
or, correcting the abnormal data in the damage record data.
Further, in an embodiment of the present application, the neural network model includes an image recognition prediction model and a time series prediction model, and the predicting, based on the configured neural network model, the damage condition of the target aircraft windshield at the future time node by using the damage parameter data and the damage image data, to obtain a first prediction result includes:
Inputting the damage parameter data into the time series prediction model for prediction to obtain a second prediction result; the second prediction result is used for representing the damage condition of the target aircraft windshield output by the time series prediction model at a future time node;
inputting the damaged image data into the image recognition prediction model for prediction to obtain a third prediction result; the third prediction result is used for representing the damage condition of the target aircraft windshield output by the image recognition prediction model at a future time node;
and obtaining a first prediction result according to the second prediction result and the third prediction result.
Further, in one embodiment of the present application, the method further comprises:
when the first prediction result does not pass the verification, determining a loss value according to the first prediction result and the simulation result data;
and optimizing and adjusting parameters of the neural network model through the loss value.
Further, in an embodiment of the present application, the performing physical simulation on the damage condition of the target aircraft windshield at the future time node according to the damage modeling data, to obtain simulation result data includes:
Performing finite element analysis on the target aircraft windshield according to the damage modeling data;
and determining simulation result data of the target aircraft windshield at the future time node according to the result of the finite element analysis.
Further, in one embodiment of the present application, the method further comprises:
and storing the damage prediction result corresponding to the windshield of the target aircraft into a database.
In another aspect, embodiments of the present application provide a damage prediction system for an aircraft windshield, the system comprising:
the acquisition unit is used for acquiring damage record data of the windshield of the target aircraft in a historical time period; the damage record data comprises damage parameter data, damage image data and damage modeling data;
the prediction unit is used for predicting the damage condition of the target aircraft windshield at a future time node through the damage parameter data and the damage image data based on the configured neural network model to obtain a first prediction result;
the simulation unit is used for carrying out physical simulation on the damage condition of the target aircraft windshield at the future time node according to the damage modeling data to obtain simulation result data;
The verification unit is used for verifying the first prediction result by taking the simulation result data as a judging reference condition;
and the processing unit is used for determining the first prediction result as the damage prediction result corresponding to the target aircraft windshield if the first prediction result passes the verification.
In another aspect, an embodiment of the present application provides an electronic device, including:
at least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement the method of damage prediction for an aircraft windshield described above.
In another aspect, embodiments of the present application further provide a computer readable storage medium having stored therein a processor executable program, which when executed by a processor is configured to implement the method for predicting damage to an aircraft windshield described above.
The advantages and benefits of the present application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the present application.
According to the method, the system, the equipment and the storage medium for predicting the damage of the airplane windshield, the damage condition of the future time node can be predicted through damage parameter data and damage image data of the target airplane windshield in a historical time period based on the configured neural network model, physical simulation is carried out by using damage modeling data, simulation result data of the target airplane windshield in the future time node is determined, then the simulation result data is taken as a judging reference condition, and the first prediction result is checked, so that the damage prediction result corresponding to the target airplane windshield is determined. The method can predict the possible damage condition of the target aircraft windshield in the future, has relatively high prediction accuracy, can facilitate the maintenance work of the aircraft, improves the maintenance efficiency, and is beneficial to improving the safety of the aircraft.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following description is made with reference to the accompanying drawings of the embodiments of the present application or the related technical solutions in the prior art, it should be understood that, in the following description, the drawings are only for convenience and clarity to describe some embodiments in the technical solutions of the present application, and other drawings may be obtained according to these drawings without any inventive effort for those skilled in the art.
FIG. 1 is a schematic view of an environment for implementing a method for predicting damage to an aircraft windshield according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of a method for predicting damage to an aircraft windshield according to an embodiment of the present disclosure;
fig. 3 is a schematic flowchart of a specific implementation of a method for predicting damage to an aircraft windshield according to an embodiment of the present application;
FIG. 4 is a schematic structural diagram of an aircraft windshield damage prediction system provided in an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The present application is further described below with reference to the drawings and specific examples. The described embodiments should not be construed as limitations on the present application, and all other embodiments, which may be made by those of ordinary skill in the art without the exercise of inventive faculty, are intended to be within the scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the present application.
The aircraft windshield is a transparent glass plate arranged in front of the cockpit and at the side of the fuselage, and is used for protecting pilots and crews in the cockpit from external factors such as wind pressure, air flow, flying objects, weather and the like. During the operation of the aircraft, due to factors such as collision, temperature difference, corrosion, fatigue and the like, cracks may appear on the windshield of the aircraft, and the cracks may limit the vision of the pilot, thereby reducing the flight safety. More seriously, due to the characteristics of materials, once cracks of an airplane windshield are expanded to a certain program, under the condition of high-altitude complex stress, the cracks can instantaneously burst, and the safety standard is exceeded, so that the flight safety is affected. Therefore, the method is an important work for crack damage detection of the airplane windshield.
In the related technology, most of the current aircraft maintenance fields stay in the experience judging stage for detecting the damage of the aircraft windshield, and the aircraft windshield is difficult to prevent in a targeted manner depending on the professional ability of maintenance personnel, so that the aircraft windshield can be replaced in time only when the damage of serious damage of the aircraft windshield is found, and a certain potential safety hazard exists.
In view of this, an embodiment of the present application provides a method for predicting damage to an aircraft windshield, where the method may predict damage to a future time node by using damage parameter data and damage image data of a target aircraft windshield in a historical time period based on a configured neural network model, perform physical simulation using damage modeling data, determine simulation result data of the target aircraft windshield at the future time node, and then check a first prediction result with the simulation result data as a decision reference condition, so as to determine a damage prediction result corresponding to the target aircraft windshield. The method can predict the possible damage condition of the target aircraft windshield in the future, has relatively high prediction accuracy, can facilitate the maintenance work of the aircraft, improves the maintenance efficiency, and is beneficial to improving the safety of the aircraft.
Referring to fig. 1, fig. 1 is a schematic view illustrating an implementation environment of a method for predicting damage to an aircraft windshield according to an embodiment of the present application. In this implementation environment, the main hardware and software body includes a terminal device 110 and a background server 120.
In this embodiment of the present application, a relevant application program may be installed in the terminal device 110, and the application program may be used to implement damage prediction of an aircraft windshield. In some embodiments, the platform end of the application may include a desktop end on which a desktop application using an operating system such as Windows, mac OS, etc. may run; in some embodiments, the platform end of the application program may include a mobile end, on which a mobile application program using a mobile operating system such as iOS and Android may be running; in some embodiments, the platform side of the application may include a Web page (Web) side on which the application may be run based on various types of browsers; in some embodiments, the platform end of the application program may include an applet end, on which various portable applications implemented based on the host application program, that is, applets, are run, which also belong to a deployment form of the application program, and in this embodiment, the specific kind of the host application program is not limited.
In the embodiment of the present application, the background server 120 may be a background server of the application program. The terminal device 110 and the background server 120 can be in communication connection with each other, and the background server 120 can be used for processing service data related to application programs and realizing related application program functions through interaction with the terminal device 110. The method for predicting the damage to the aircraft windshield provided in the embodiment of the application may be implemented by the terminal device 110 alone, or may be implemented based on interaction between the terminal device 110 and the background server 120.
The terminal device 110 of the above embodiment may include, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart watch, and a vehicle-mounted terminal.
The background server 120 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs (Content Delivery Network, content delivery networks), basic cloud computing services such as big data and artificial intelligence platforms, and the like.
A communication connection may be established between the terminal device 110 and the background server 120 through a wireless network or a wired network. The wireless network or wired network may be configured as the internet, using standard communication techniques and/or protocols, or any other network including, for example, but not limited to, a local area network (Local Area Network, LAN), metropolitan area network (Metropolitan Area Network, MAN), wide area network (Wide Area Network, WAN), mobile, wired or wireless network, a private network, or any combination of virtual private networks. The software and hardware main bodies may be connected by the same communication method or by different communication methods, which is not particularly limited in this application.
Of course, it can be understood that the implementation environment in fig. 1 is only some optional application scenarios of the method for predicting damage to an aircraft windshield provided in the embodiments of the present application, and the actual application is not fixed to the software and hardware environment shown in fig. 1.
The method for predicting damage to an aircraft windshield provided in the embodiments of the present application will be described and illustrated with reference to the foregoing description of the implementation environment.
Referring to fig. 2, fig. 2 is a schematic diagram of a method for predicting damage to an aircraft windshield according to an embodiment of the present application, where the method includes, but is not limited to:
Step 210, acquiring damage record data of a target aircraft windshield in a historical time period; the damage record data comprises damage parameter data, damage image data and damage modeling data;
in this step, when damage prediction is performed on the aircraft windshield, the aircraft windshield to be predicted may be noted as a target aircraft windshield. When damage prediction is required to the target aircraft windshield, damage record data of the target aircraft windshield in a historical time period can be obtained. In the embodiment of the application, a database can be used for recording relevant damage data obtained when each aircraft windshield is overhauled, and the damage data are recorded as damage record data. In particular, the lesion record data may include lesion parameter data, lesion image data, and lesion modeling data. The damage parameter data refers to relevant parameter information for recording the damage condition of the aircraft windshield, and the parameters can include, but are not limited to, damage position, damage degree, damage type, damage size and the like. The location of the lesion refers to the specific location on the windshield where the lesion occurs and may be described by coordinates or areas. The damage degree refers to the influence degree of damage on the windshield, and can be expressed by numerical values or descriptive terms (such as mild, moderate, severe). The damage type describes what type of damage is on the windshield, such as cracks, scratches, breaks, etc. The lesion size refers to the size of the lesion and can be described by parameters such as length, width, area, etc. The damage image data is image data of damage to the windshield of the aircraft obtained by photographing or scanning. These images may be in the form of photographs, video or scanned images, etc. The lesion image data may provide visual information that helps analyze the shape, location, and extent of the lesion. The damage modeling data is data related to the modeling of the damage condition of the aircraft windshield, and can be used for carrying out physical simulation on the aircraft windshield so as to determine the subsequent damage development condition.
In the embodiment of the present application, the obtaining channel and mode of the damage record data are not limited, and the damage record data may be extracted from a local database, or may be obtained from other devices through communication transmission. Also, the period of their damage log data acquisition for each aircraft windshield can be flexibly set as desired, for example, for a week, day, or other time period, as is not limited in this regard.
Step 220, predicting the damage condition of the target aircraft windshield at a future time node through the damage parameter data and the damage image data based on the configured neural network model to obtain a first prediction result;
in this step, after obtaining damage record data of the target aircraft windshield in the historical time period, damage condition of the target aircraft windshield at a future time node may be predicted using the damage record data. Specifically, in the embodiment of the present application, the prediction function may be implemented using a neural network model. Here, the neural network model is a mathematical model that mimics the principle of operation of the human nervous system. In general, a neural network model is composed of a large number of neuronal nodes that communicate and process information with each other through connections (weights), and is generally divided into an input layer, a hidden layer, and an output layer. The input layer accepts external input data such as images, text, or sensor data. The hidden layer is an intermediate layer that is responsible for processing the incoming data and passing it on to the next layer. The output layer generates the final model prediction result. The neural network model can be trained through supervised learning or unsupervised learning, and in the training process, the neural network model can be used for continuously adjusting the connection weight so as to minimize the error between input data and expected output, thereby obtaining better prediction performance.
In the embodiment of the application, the type and structure of the specific neural network model are not limited. Specifically, the damage reference data and the damage image data may be input into a neural network model, and the damage condition of the target aircraft windshield at the future time node may be predicted by the neural network model, so as to obtain a prediction result, which in the embodiment of the present application is denoted as a first prediction result.
Step 230, according to the damage modeling data, performing physical simulation on the damage condition of the target aircraft windshield at the future time node to obtain simulation result data;
in the step, according to the damage modeling data, physical simulation can be performed by utilizing factors such as material properties, traffic environment, flight parameters and the like of the aircraft windshield, and damage conditions of the target aircraft windshield at future time nodes can be predicted. Parameters such as stress, deformation, breakage and the like of an airplane windshield can be obtained through physical simulation, so that decisions on airplane design, flight operation, maintenance and the like can be made. In addition, the simulation result data can be used in the fields of flight accident investigation, aircraft design optimization and the like so as to improve the flight safety and the overall performance of the aircraft.
Specifically, in the embodiment of the application, when the target aircraft windshield is subjected to physical simulation, finite element analysis can be performed on the target aircraft windshield according to damage modeling data. Finite element analysis (Finite Element Analysis, FEA for short) is a numerical calculation method for solving physical phenomena such as stress, deformation, vibration and the like of an engineering structure. It can divide a complex structure into a finite number of small cells (finite elements) and describe the mechanical behavior of each cell in a mathematical model. By discretizing these units, an overall mathematical model can be built and solved using numerical methods.
In the embodiment of the application, in finite element analysis on the target aircraft windshield, the geometric model and the material characteristics of the target aircraft windshield can be acquired, and then the geometric model of the target aircraft windshield is subjected to mesh subdivision and divided into a plurality of small finite element units. Each finite element has its nodes and connections, and stresses and deformations at the nodes can be calculated by discretizing the model. According to the mechanical property, external load, boundary conditions and the like of the material, a finite element equation set can be established, and the equation set is solved by a numerical solution method. And finally, obtaining the results of stress, deformation and the like of the target aircraft windshield in a future time period.
From the results of the finite element analysis, simulation result data for the target aircraft windshield at a future time node may be determined. Specifically, parameters such as stress, deformation, and breakage of the target aircraft windshield at future time nodes may be obtained, for example, by finite element analysis of the target aircraft windshield. In the embodiment of the application, the specific content of the obtained simulation result data is not limited.
Step 240, checking the first prediction result by taking the simulation result data as a judging reference condition;
in this step, after the simulation result data is obtained, the first prediction result may be checked using the simulation result data as a determination reference condition. Specifically, in the embodiment of the present application, when the first prediction result is checked, some values may be checked in a matching manner, for example, some data related to damage may be included in the simulation result data, whether the data in the first prediction result and the simulation result data are consistent may be compared, and if the deviation between the data and the simulation result data is small, it may be determined that the two match and check is passed; in contrast, if the deviation of the two is large, it can be determined that the two match checks do not pass.
In the embodiment of the present application, the simulation result data is taken as a determination reference condition, and a part of parameters may be determined as the determination reference condition according to the simulation result data. When the first predicted result is checked, the number or proportion of the first predicted result which needs to meet the judging reference condition can be restrained, when the first predicted result meets the judging reference condition of the designated number or proportion, the first predicted result can be considered to pass the check, otherwise, the first predicted result is considered to not pass the check.
In the embodiment of the application, the simulation result data is used as the judging reference condition, and the first prediction result is checked, so that the accuracy of the first prediction result can be improved, and the operation safety of the aircraft can be improved.
And 250, if the first prediction result passes the verification, determining the first prediction result as a damage prediction result corresponding to the windshield of the target aircraft.
In this step, if the first prediction result passes the verification, the first prediction result may be determined as a damage prediction result corresponding to the target aircraft windshield, that is, a prediction result of the damage condition of the target aircraft windshield at the future time node is obtained. In contrast, if the first prediction result does not pass the verification, a loss value may be determined according to the first prediction result and the simulation result data, where the loss value may be used to represent a deviation degree of the first prediction result and the simulation result data, and the greater the deviation degree of the first prediction result and the simulation result data, the greater the magnitude of the loss value, the smaller the deviation degree of the first prediction result and the simulation result data, and the smaller the magnitude of the loss value, and the specific functional relationship among the first prediction result, the simulation result data and the loss value is not limited in this application. After obtaining the loss value, the loss value can be used to perform optimization adjustment on parameters of the neural network model. Therefore, the prediction performance of the neural network model can be improved, and more accurate prediction results can be given out by the follow-up neural network model.
It may be appreciated that in the embodiment of the present application, the method for predicting damage of an aircraft windshield may predict a damage condition of a future time node by using damage parameter data and damage image data of a target aircraft windshield in a historical time period based on a configured neural network model, perform physical simulation by using damage modeling data, determine simulation result data of the target aircraft windshield at the future time node, and then check a first prediction result by using the simulation result data as a decision reference condition, so as to determine a damage prediction result corresponding to the target aircraft windshield. The method can predict the possible damage condition of the target aircraft windshield in the future, has relatively high prediction accuracy, can facilitate the maintenance work of the aircraft, improves the maintenance efficiency, and is beneficial to improving the safety of the aircraft.
Specifically, in some embodiments, after the step of obtaining damage log data for the target aircraft windshield over a historical period of time, the method further comprises:
and performing data separation operation, data cleaning operation and data conversion operation on the damage record data.
In this embodiment of the present application, after obtaining the damage record data, the data separation operation, the data cleaning operation, and the data conversion operation may be performed on the damage record data. Specifically, the data separation operation refers to dividing damage record data into damage parameter data, damage image data and damage modeling data so as to be stored separately for later use; the data cleaning operation refers to optimizing the damage record data, for example, in some embodiments, whether the damage record data has a data loss condition can be detected, if the damage record data has a data loss condition, the lost data can be subjected to supplementary recording, and in particular, the lost data can be filled by adopting secondary acquisition and recording or processing through a statistical method; in some embodiments, whether abnormal data exists in the damage record data can also be detected, and if the abnormal data exists, the abnormal data can be corrected. The data conversion operation is used for carrying out standardization and normalization processing on the data, so that the format of the data can be unified. Therefore, the quality of damage record data can be improved, and the accuracy of damage prediction of the airplane windshield is further improved.
Specifically, in some embodiments, the neural network model includes an image recognition prediction model and a time series prediction model, and the predicting, based on the configured neural network model, the damage condition of the target aircraft windshield at a future time node through the damage parameter data and the damage image data, to obtain a first prediction result includes:
inputting the damage parameter data into the time series prediction model for prediction to obtain a second prediction result; the second prediction result is used for representing the damage condition of the target aircraft windshield output by the time series prediction model at a future time node;
inputting the damaged image data into the image recognition prediction model for prediction to obtain a third prediction result; the third prediction result is used for representing the damage condition of the target aircraft windshield output by the image recognition prediction model at a future time node;
and obtaining a first prediction result according to the second prediction result and the third prediction result.
Referring to fig. 3, in an embodiment of the present application, the neural network model may include an image recognition prediction model and a temporal sequence prediction model. For the numerical data (i.e., the damage parameter data) in the damage record data, a temporal sequence prediction model may be used to perform prediction processing to obtain result data based on temporal sequence prediction, which is denoted as a second prediction result in the embodiment of the present application. For the image data in the damage record data (i.e. the damage image data), the image recognition prediction model may be used to perform prediction processing to obtain result data based on image recognition prediction, which is denoted as a third prediction result in the embodiment of the present application. Then, the second prediction result and the third prediction result can be integrated to obtain the first prediction result.
In the embodiment of the application, the first prediction result is checked by taking the simulation result data as a judging reference condition. If the verification is not passed, the image recognition prediction model and the time series prediction model can be corrected to improve the prediction accuracy. When the verification result passes, the damage prediction result can be stored, and the damage prediction result can be stored in a database to be used as a record of damage condition of the windshield of the target aircraft at a future time node. When the future time node is reached, if the damage prediction result is consistent with the real situation, the stored content can be reserved, and if the damage prediction result is inconsistent with the real situation, modification and adjustment can be carried out according to the real situation.
It will be appreciated that in embodiments of the present application, a database of aircraft windshield damage data may be established. When the data volume of the database is small, a neural network model is used for short-term prediction, a short-term prompting result can be obtained, and therefore the method is applied to airplane inspection, helps engineers to know the next damage change condition of a windshield, and transmits data after inspection and verification back to the database for database supplement, and the database is continuously expanded. When a large enough amount of original acquired data is accumulated, the data is fused into a complete change process of the windshield damage, so that overall change analysis can be performed, the stored result is further corrected, and meanwhile, the change analysis of the windshield life damage can be performed by combining with the working route environment of the airplane windshield. The system has a certain growth, can repeatedly utilize the stored reliable data to carry out parameter adjustment on the self neural network model while applying, thereby improving the accuracy of the neural network, and achieving the state of 'more intelligent' of the neural network model.
Referring to fig. 4, an aircraft windshield damage prediction system according to an embodiment of the present application includes:
an acquisition unit 410 for acquiring damage record data of a target aircraft windshield over a historical period of time; the damage record data comprises damage parameter data, damage image data and damage modeling data;
the prediction unit 420 is configured to predict, based on the configured neural network model, a damage condition of the target aircraft windshield at a future time node according to the damage parameter data and the damage image data, so as to obtain a first prediction result;
the simulation unit 430 is configured to perform physical simulation on the damage condition of the target aircraft windshield at the future time node according to the damage modeling data, so as to obtain simulation result data;
a verification unit 440, configured to verify the first prediction result by using the simulation result data as a decision reference condition;
and the processing unit 450 is configured to determine the first prediction result as a damage prediction result corresponding to the target aircraft windshield if the first prediction result passes the verification.
It can be understood that the content in the above method embodiment is applicable to the embodiment of the present device, and the specific functions implemented by the embodiment of the present device are the same as those of the embodiment of the above method, and the achieved beneficial effects are the same as those of the embodiment of the above method.
Referring to fig. 5, an embodiment of the present application provides an electronic device, including:
at least one processor 510;
at least one memory 520 for storing at least one program;
the at least one program, when executed by the at least one processor 510, causes the at least one processor 510 to implement a method of damage prediction for an aircraft windshield.
Similarly, the content in the above method embodiment is applicable to the present electronic device embodiment, and the functions specifically implemented by the present electronic device embodiment are the same as those of the above method embodiment, and the beneficial effects achieved by the present electronic device embodiment are the same as those achieved by the above method embodiment.
The present embodiment also provides a computer readable storage medium in which a program executable by the processor 510 is stored, the program executable by the processor 510 when executed by the processor 510 being configured to perform the method for predicting damage to an aircraft windshield described above.
Similarly, the content in the above method embodiment is applicable to the present computer-readable storage medium embodiment, and the functions specifically implemented by the present computer-readable storage medium embodiment are the same as those of the above method embodiment, and the beneficial effects achieved by the above method embodiment are the same as those achieved by the above method embodiment.
In some alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flowcharts of this application are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed, and in which sub-operations described as part of a larger operation are performed independently.
Furthermore, while the present application is described in the context of functional modules, it should be appreciated that, unless otherwise indicated, one or more of the functions and/or features may be integrated in a single physical device and/or software module or one or more of the functions and/or features may be implemented in separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary to an understanding of the present application. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be apparent to those skilled in the art from consideration of their attributes, functions and internal relationships. Thus, those of ordinary skill in the art will be able to implement the present application as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative and are not intended to be limiting upon the scope of the application, which is to be defined by the appended claims and their full scope of equivalents.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing an apparatus (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium may even be paper or other suitable medium upon which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the foregoing description of the present specification, descriptions of the terms "one embodiment/example", "another embodiment/example", "certain embodiments/examples", and the like, are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the application, the scope of which is defined by the claims and their equivalents.
While the preferred embodiments of the present application have been described in detail, the present application is not limited to the embodiments, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the present application, and these equivalent modifications and substitutions are intended to be included in the scope of the present application as defined in the appended claims.
Claims (10)
1. A method of predicting damage to an aircraft windshield, the method comprising:
acquiring damage record data of a target aircraft windshield in a historical time period; the damage record data comprises damage parameter data, damage image data and damage modeling data;
based on a configured neural network model, predicting the damage condition of the target aircraft windshield at a future time node through the damage parameter data and the damage image data to obtain a first prediction result;
according to the damage modeling data, performing physical simulation on the damage condition of the target aircraft windshield at the future time node to obtain simulation result data;
taking the simulation result data as a judging reference condition, and checking the first prediction result;
and if the first prediction result passes the verification, determining the first prediction result as a damage prediction result corresponding to the windshield of the target aircraft.
2. The method of claim 1, wherein after the step of obtaining damage log data for the target aircraft windshield over a historical period of time, the method further comprises:
And performing data separation operation, data cleaning operation and data conversion operation on the damage record data.
3. The method of claim 2, wherein performing a data cleansing operation on the damage log data comprises:
performing supplementary recording on lost data in the damage record data;
or, correcting the abnormal data in the damage record data.
4. A method of predicting damage to an aircraft windshield according to any one of claims 1-3, wherein the neural network model comprises an image recognition prediction model and a time series prediction model, and wherein the predicting damage to the target aircraft windshield at a future time node based on the configured neural network model based on the damage parameter data and the damage image data comprises:
inputting the damage parameter data into the time series prediction model for prediction to obtain a second prediction result; the second prediction result is used for representing the damage condition of the target aircraft windshield output by the time series prediction model at a future time node;
Inputting the damaged image data into the image recognition prediction model for prediction to obtain a third prediction result; the third prediction result is used for representing the damage condition of the target aircraft windshield output by the image recognition prediction model at a future time node;
and obtaining a first prediction result according to the second prediction result and the third prediction result.
5. A method of predicting damage to an aircraft windshield as recited in claim 1, further comprising:
when the first prediction result does not pass the verification, determining a loss value according to the first prediction result and the simulation result data;
and optimizing and adjusting parameters of the neural network model through the loss value.
6. The method for predicting damage to an aircraft windshield according to claim 1, wherein performing physical simulation on damage condition of the target aircraft windshield at the future time node according to the damage modeling data to obtain simulation result data comprises:
performing finite element analysis on the target aircraft windshield according to the damage modeling data;
and determining simulation result data of the target aircraft windshield at the future time node according to the result of the finite element analysis.
7. A method of predicting damage to an aircraft windshield as recited in claim 1, further comprising:
and storing the damage prediction result corresponding to the windshield of the target aircraft into a database.
8. A damage prediction system for an aircraft windshield, the system comprising:
the acquisition unit is used for acquiring damage record data of the windshield of the target aircraft in a historical time period; the damage record data comprises damage parameter data, damage image data and damage modeling data;
the prediction unit is used for predicting the damage condition of the target aircraft windshield at a future time node through the damage parameter data and the damage image data based on the configured neural network model to obtain a first prediction result;
the simulation unit is used for carrying out physical simulation on the damage condition of the target aircraft windshield at the future time node according to the damage modeling data to obtain simulation result data;
the verification unit is used for verifying the first prediction result by taking the simulation result data as a judging reference condition;
and the processing unit is used for determining the first prediction result as the damage prediction result corresponding to the target aircraft windshield if the first prediction result passes the verification.
9. An electronic device, comprising:
at least one processor;
at least one memory for storing at least one program;
when said at least one program is executed by said at least one processor, said at least one processor implements a method for predicting damage to an aircraft windshield as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium having stored therein a program executable by a processor, characterized in that: the processor executable program when executed by a processor is for implementing a method of damage prediction for an aircraft windshield as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311725250.7A CN117874905A (en) | 2023-12-14 | 2023-12-14 | Method, system, equipment and storage medium for predicting damage of airplane windshield |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311725250.7A CN117874905A (en) | 2023-12-14 | 2023-12-14 | Method, system, equipment and storage medium for predicting damage of airplane windshield |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117874905A true CN117874905A (en) | 2024-04-12 |
Family
ID=90595951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311725250.7A Pending CN117874905A (en) | 2023-12-14 | 2023-12-14 | Method, system, equipment and storage medium for predicting damage of airplane windshield |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117874905A (en) |
-
2023
- 2023-12-14 CN CN202311725250.7A patent/CN117874905A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6840529B2 (en) | Aircraft maintenance and inspection with data analysis expansion | |
| US10891406B2 (en) | Prediction methods and systems for structural repair during heavy maintenance of aircraft | |
| CN111274737A (en) | Method and system for predicting remaining service life of mechanical equipment | |
| EP2092401B1 (en) | Hard landing detection | |
| JP6313929B2 (en) | Method and system for monitoring structures | |
| Tian et al. | Relationship modeling between vehicle‐induced girder vertical deflection and cable tension by BiLSTM using field monitoring data of a cable‐stayed bridge | |
| DE112020003380T5 (en) | DETERMINING THE STATUS OF THE INFRASTRUCTURE IN AN AREA OF INTEREST | |
| Edwards et al. | Impact of input uncertainty on failure prognostic algorithms: Extending the remaining useful life of nonlinear systems | |
| CN112085869A (en) | Civil aircraft flight safety analysis method based on flight parameter data | |
| US11772823B2 (en) | Estimating fatigue damage in a structure | |
| WO2016012387A1 (en) | Device and method for identifying errors and attacks, for a motor vehicle | |
| CN112799950A (en) | Background service load capacity test system and method, storage medium and electronic device | |
| CN111027859B (en) | Driving risk prevention method and system based on motor vehicle state monitoring data mining | |
| CN117874905A (en) | Method, system, equipment and storage medium for predicting damage of airplane windshield | |
| CN112802011A (en) | Fan blade defect detection method based on VGG-BLS | |
| CN115031994B (en) | Vehicle endurance test method and system | |
| CN116521406A (en) | Method for detecting anomaly of non-overrun flight parameter data of aero-engine based on residual gate GRU-VAE model | |
| CN114993373A (en) | Aviation glass state monitoring method and device, computer equipment and medium | |
| CN112528510B (en) | Method for predicting repairable aviation material spare parts based on life-extinction process model | |
| CN112990329B (en) | System abnormality diagnosis method and device | |
| CN114565004A (en) | Method and device for eliminating abnormal scattered points of power curve of wind turbine generator | |
| CN112560252A (en) | Prediction method for residual life of aircraft engine | |
| CN111832834A (en) | Airport pavement service performance prediction method and device and electronic equipment | |
| CN116992310B (en) | Airplane ice accumulation real-time monitoring and early warning method, system, electronic equipment and medium | |
| EP3705407B1 (en) | Smart aircraft skin impact area positioning method based on truncated reverse weighted sum |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |