CN114993373A - Aviation glass state monitoring method and device, computer equipment and medium - Google Patents

Aviation glass state monitoring method and device, computer equipment and medium Download PDF

Info

Publication number
CN114993373A
CN114993373A CN202210374228.1A CN202210374228A CN114993373A CN 114993373 A CN114993373 A CN 114993373A CN 202210374228 A CN202210374228 A CN 202210374228A CN 114993373 A CN114993373 A CN 114993373A
Authority
CN
China
Prior art keywords
state
monitoring
state evaluation
monitoring information
aircraft glass
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
Application number
CN202210374228.1A
Other languages
Chinese (zh)
Inventor
刘俊斌
黄云
路国光
周振威
孟苓辉
何世烈
时林林
俞鹏飞
洪丹妮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Electronic Product Reliability and Environmental Testing Research Institute
Original Assignee
China Electronic Product Reliability and Environmental Testing Research Institute
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Electronic Product Reliability and Environmental Testing Research Institute filed Critical China Electronic Product Reliability and Environmental Testing Research Institute
Priority to CN202210374228.1A priority Critical patent/CN114993373A/en
Publication of CN114993373A publication Critical patent/CN114993373A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • Tourism & Hospitality (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Primary Health Care (AREA)
  • Operations Research (AREA)

Abstract

The application relates to a method and a device for monitoring the state of aircraft glass, computer equipment and a medium, wherein monitoring information of the aircraft glass is obtained, the monitoring information is input into a state evaluation model to obtain a state evaluation result of the aircraft glass, the state evaluation result is used for evaluating the running state of the aircraft glass, the state evaluation model is a prediction model established after learning and training by using historical monitoring information, and when the state evaluation result is a preset result, an alarm signal is sent to alarm equipment. According to the aviation glass state monitoring method, the aviation glass state monitoring device, the computer equipment and the medium, the monitoring information is analyzed through the state evaluation model, so that real-time online monitoring of aviation glass can be efficiently realized, evaluation is made, crew members are reminded according to the evaluation result, the aviation glass state detection efficiency and accuracy can be effectively improved, and the stability and safety of an aircraft in the flying process are improved.

Description

Aviation glass state monitoring method and device, computer equipment and medium
Technical Field
The application relates to the field of aviation airplanes, in particular to a method and a device for monitoring the state of aviation glass, computer equipment and a medium.
Background
With the increasing development of the aviation industry, the aviation safety is more and more important. Aircraft glass (e.g., windshields, windows, etc.) as an important component of aircraft are directly related to aircraft and passenger safety. Aircraft glass is generally a relatively weak area, and bending stress, thermal stress and the like of the aircraft glass can accelerate the development of damage or crack propagation, and further can cause the aircraft glass to be damaged and fall off. In recent years, there have been many incidents of aircraft glass damage affecting aviation safety, leading to forced landing of an aircraft.
In the conventional technology, technicians can inspect engines and instruments and meters, but do not always carry out special detection and risk prediction on the aircraft glass before flying at every time, or carry out risk assessment through manual inspection, the condition of missed detection and the like easily occurs, and the efficiency and the accuracy of state monitoring of the aircraft glass are lower.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device and a medium for monitoring the state of aircraft glass, which can solve the problems of low efficiency and accuracy of monitoring the state of aircraft glass.
A method of condition monitoring aircraft glass, the method comprising the steps of:
acquiring monitoring information of the aircraft glass;
inputting the monitoring information into a state evaluation model to obtain a state evaluation result of the aircraft glass; the state evaluation result is used for evaluating the running state of the aircraft glass, and the state evaluation model is a prediction model established after learning and training by using historical monitoring information;
and when the state evaluation result is a preset result, sending an alarm signal to alarm equipment.
In one embodiment, the establishing process of the state evaluation model includes:
acquiring the historical monitoring information of the aircraft glass;
extracting the characteristics of the historical monitoring information to obtain environmental characteristics and a state label;
and establishing the state evaluation model according to the environment characteristics and the state label.
In one embodiment, the historical monitoring information includes marked monitoring data and unmarked monitoring data, and the establishing process of the state evaluation model further includes:
and acquiring the marked monitoring data and the unmarked monitoring data of the aircraft glass.
In one embodiment, the historical monitoring information includes tagged monitoring data and untagged monitoring data, the tagged monitoring data includes the environmental characteristics and the status label, and the establishing the status evaluation model according to the environmental characteristics and the status label includes:
generating a training set by using the marked monitoring data, and generating a verification set by using the unmarked monitoring data;
inputting the training set into a state evaluation algorithm, and performing learning training on the state evaluation algorithm by using the environmental characteristics of the labeled monitoring data and the state labels to obtain an initial state evaluation model;
and inputting the verification set into the initial state evaluation model, and verifying the initial state evaluation model by using the unmarked monitoring data in the verification set until the number of samples with correct verification results in the verification set meets a preset condition to obtain the state evaluation model.
In one embodiment, the monitoring information includes temperature information and stress information, and the acquiring the monitoring information of the aircraft glass includes:
acquiring the temperature information through a temperature sensor, and acquiring the stress information through a stress sensor; the temperature sensor and the stress sensor are both arranged on the aircraft glass.
In one embodiment, the inputting the monitoring information into the state evaluation model to obtain the state evaluation result of the aircraft glass includes:
performing feature extraction on the monitoring information to obtain an environmental feature corresponding to the monitoring information;
and inputting the environmental characteristics corresponding to the monitoring information into the state evaluation model, so that the state evaluation model predicts the running state of the aircraft glass to obtain the state evaluation result, wherein the state evaluation result comprises a normal state, a damaged state and an abnormal state.
In one embodiment, the preset result includes a damaged state and an abnormal state, and when the state evaluation result is the preset result, sending an alarm signal to an alarm device includes:
when the state evaluation result is a damaged state, sending a damaged alarm signal to alarm equipment;
and when the state evaluation result is an abnormal state, sending an abnormal alarm signal to alarm equipment.
A condition monitoring device for aircraft glass, the device comprising:
the data acquisition module is used for acquiring monitoring information of the aircraft glass;
the data processing module is used for inputting the monitoring information into a state evaluation model to obtain a state evaluation result of the aircraft glass; the state evaluation result is used for evaluating the running state of the aircraft glass, and the state evaluation model is a prediction model established by learning and training by using historical monitoring information;
and the alarm driving module is used for sending an alarm signal to alarm equipment when the state evaluation result is a preset result.
A computer device comprising a memory storing a computer program and a processor implementing the steps when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the above-mentioned steps.
According to the aviation glass state monitoring method, the aviation glass state monitoring device, the computer equipment and the medium, the monitoring information of the aviation glass is obtained, the monitoring information is input into the state evaluation model, the aviation glass state evaluation result is obtained, the state evaluation result is used for evaluating the operation state of the aviation glass, the state evaluation model is a prediction model established after learning and training are carried out by utilizing historical monitoring information, and when the state evaluation result is a preset result, an alarm signal is sent to the alarm equipment. According to the aviation glass state monitoring method, the aviation glass state monitoring device, the computer equipment and the medium, the monitoring information is analyzed through the state evaluation model, so that real-time online monitoring of aviation glass can be efficiently realized, evaluation is made, crew members are reminded according to the evaluation result, the aviation glass state detection efficiency and accuracy can be effectively improved, and the stability and safety of an aircraft in the flying process are improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments or the conventional technologies of the present application, the drawings used in the description of the embodiments or the conventional technologies will be briefly introduced below, it is obvious that the drawings in the description below are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic view of an application scenario of condition monitoring of aircraft glass in one embodiment;
FIG. 2 is a schematic flow chart diagram of a method for monitoring the condition of aircraft glass in one embodiment;
FIG. 3 is a schematic flow diagram of constructing a state estimation model in one embodiment;
FIG. 4 is a schematic flow diagram illustrating a refinement of the process of constructing a state estimation model in one embodiment;
FIG. 5 is a schematic diagram of a detailed process for constructing a state estimation model in another embodiment;
FIG. 6 is a schematic flow chart illustrating a detailed process of a method for monitoring the condition of aircraft glass in one embodiment;
FIG. 7 is a detailed flowchart of a state monitoring method for aircraft glass in another embodiment;
FIG. 8 is a flow diagram illustrating a refinement of a process involving a state evaluation result determination process in one embodiment;
FIG. 9 is a schematic structural view of a state monitoring device for aircraft glass in one embodiment;
FIG. 10 is a schematic structural view of a state monitoring device for aircraft glass in another embodiment;
FIG. 11 is a diagram showing an internal configuration of a computer device according to an embodiment.
Detailed Description
To facilitate an understanding of the present application, the present application will now be described more fully with reference to the accompanying drawings. Embodiments of the present application are set forth in the accompanying drawings. This application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
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 in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements should not be limited by these terms. These terms are only used to distinguish one element from another.
It will be understood that when an element is referred to as being "connected" to another element, it can be directly connected to the other element or be connected to the other element through intervening elements. Further, "connection" in the following embodiments is understood to mean "electrical connection", "communication connection", or the like, if there is a transfer of electrical signals or data between the connected objects.
As used herein, the singular forms "a", "an" and "the" may include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises/comprising," "includes" or "including," etc., specify the presence of stated features, integers, steps, operations, components, parts, or combinations thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, components, parts, or combinations thereof.
The application provides a state monitoring method and device for aircraft glass, computer equipment and a medium, which are used for monitoring the state of the aircraft glass. The monitoring information is analyzed through the state evaluation model, so that the real-time online monitoring of the aircraft glass can be efficiently realized, the evaluation can be made, the efficiency and the accuracy of the state detection of the aircraft glass can be effectively improved, and the stability and the safety of the aircraft in the flight process are improved. The method is suitable for the application scene shown in fig. 1, the sensor 10 is arranged on an aircraft glass such as a windshield, a porthole or other parts, the sensor 10 acquires monitoring information of the aircraft glass and sends the monitoring information to the controller 20, the controller 20 inputs the monitoring information into the state evaluation model, a state evaluation result corresponding to the monitoring information is calculated according to the state evaluation model, and when the state evaluation result is a preset result, an alarm signal is sent to alarm equipment.
In one embodiment, as shown in fig. 2, the present application provides a method for monitoring the condition of aircraft glass, which may be performed by the controller 20, wherein the controller 20 may be implemented by a stand-alone server or a server cluster composed of a plurality of servers, and the method includes:
and S100, acquiring monitoring information of the aircraft glass.
In particular, the aircraft glass does not refer to a specific component, including but not limited to a windshield, a porthole, and the like, and the state of the component can be monitored by those skilled in the art according to actual needs.
The monitoring information generally comprises information of the surrounding environment of the aircraft glass, such as temperature information, humidity information, wind speed information, wind direction information and the like, and also comprises information of the aircraft glass, such as stress information and the like, and the obtained monitoring information of the aircraft glass is favorable for completely and comprehensively evaluating the running state of the aircraft glass. Further, the monitoring information may be collected by providing the sensor 10 on each aircraft glass, and the sensor 10 transmits the collected monitoring information to the controller 20. The type of the sensor 10 is not exclusive, and may include a temperature sensor, a force sensor, a humidity sensor, and the like, which are respectively used to acquire temperature information, force information, and humidity information. Secondly, the time interval for acquiring the aircraft glass monitoring information is not unique, the monitoring information can be continuously acquired, and omission is avoided. A time interval may also be set to periodically acquire monitoring information to reduce the workload on the sensor 10. After acquiring the monitoring information of the aircraft glass, the sensor 10 sends the monitoring information to the controller 20 for subsequent evaluation operation.
And S200, inputting the monitoring information into a state evaluation model to obtain a state evaluation result of the aircraft glass.
Specifically, after receiving the monitoring information, the controller 20 inputs the monitoring information into a built-in state evaluation model, where the state evaluation model is a prediction model that is established after learning and training by using historical monitoring information, and for example, the state evaluation model may be a classification model obtained by learning and training a large amount of historical monitoring information based on a neural network or a support vector machine algorithm.
After the controller 20 acquires the monitoring information of the aircraft glass in each stage of the flight process of the aircraft, the state evaluation model is called to perform state evaluation on the acquired monitoring information, and a corresponding state evaluation result is obtained. And the state evaluation result is used for evaluating the running state of the aircraft glass, and further, the running state of the aircraft glass under each monitoring information is reflected by the state evaluation result. Illustratively, the condition evaluation results include a normal condition indicating that the aircraft key component is functioning normally at that time, and a damaged condition indicating that the aircraft glass is not functioning normally at that time.
Illustratively, the controller 20 acquires monitoring information of the aircraft glass through the sensor 10, wherein the monitoring information comprises temperature information, stress information and humidity information, and invokes a trained state evaluation model to perform state evaluation on the monitoring information. In this embodiment, the state estimation model is a classification model obtained by learning and training a large amount of historical monitoring information based on a support vector machine algorithm. Different characteristic weights are given to the temperature information, the stress information and the humidity information in the state evaluation model, and a state evaluation result corresponding to the monitoring information is accurately and effectively obtained according to the information and the corresponding characteristic weights.
And step S300, when the state evaluation result is a preset result, sending an alarm signal to alarm equipment.
Specifically, the state evaluation result reflects the operation state of the aircraft glass under each monitoring information, and the preset result is preset and used for determining the operation state of the aircraft glass. Illustratively, the state evaluation result includes a normal state, a damaged state and an abnormal state, the normal state indicates that the aircraft glass can normally function at the moment, the damaged state indicates that the aircraft glass can not normally function at the moment, and the abnormal state is between the normal state and the damaged state. The preset result includes a damaged state and an abnormal state.
When the state evaluation result is a normal state, the controller 20 does not send a signal to the alarm device, when the state evaluation result is a damaged state, the controller 20 sends a damaged alarm signal to the alarm device, and when the state evaluation result is an abnormal state, the controller 20 sends an abnormal alarm signal to the alarm device.
Further, the specific type of the alarm device is not unique, and an acoustic alarm or an optical alarm may be adopted, and the specific type of the alarm device may be selected according to actual requirements. For example, when the alarm device is an acoustic alarm, the acoustic alarm is connected to the controller 20, and the acoustic alarm receives the damage alarm signal or the abnormal alarm signal from the controller 20 and then gives an alarm by emitting an alarm sound. The sound alarm can be a voice playing device, and the voice playing device can play different alarm voices according to different alarm signals, so that the alarm content is rich. It is understood that in other embodiments, the alerting device may be of other types as long as one skilled in the art recognizes it as being practical.
According to the state monitoring method of the aircraft glass, the sensor 10 acquires monitoring information of the aircraft glass and sends the monitoring information to the controller 20, the controller 20 inputs the monitoring information into the state evaluation model to obtain a state evaluation result of the aircraft glass, and when the state evaluation result is a preset result, the controller 20 sends an alarm signal to alarm equipment. The real-time online monitoring of the aircraft glass is efficiently realized, and the assessment is made, so that the efficiency and the accuracy of the state detection of the aircraft glass can be effectively improved, and the stability and the safety of an airplane in the flying process are improved.
In one embodiment, as shown in fig. 3, the process of establishing the state estimation model includes steps S400 to S600:
and S400, acquiring historical monitoring information of the aircraft glass.
Specifically, the controller 20 obtains a large amount of historical monitoring information, which may be historical monitoring information acquired through a simulation experiment or historical monitoring information obtained from a third-party database.
And step S500, extracting the characteristics of the historical monitoring information to obtain the environmental characteristics and the state label.
Specifically, the controller 20 performs feature extraction on the obtained large amount of historical monitoring information, and the manner of performing the feature extraction is not unique, for example, the controller 20 may perform cluster analysis on the large amount of historical monitoring information by using a k-means clustering algorithm, so as to obtain the environmental features.
Further, the types of the environmental characteristics are not exclusive, and the environmental characteristics may include a temperature characteristic, a stress characteristic, a humidity characteristic, and the like. The mode of extracting the features of the historical monitoring information to obtain the status label is not unique, and for example, the operating status of the aircraft glass under each piece of historical monitoring information may be manually judged, and the corresponding label is attached to each piece of historical monitoring information according to the judgment result. Exemplarily, under certain historical monitoring information, the aircraft glass normally functions, and at the moment, the state label corresponding to the historical monitoring information is a normal state; under another historical monitoring, the aircraft glass is damaged, and the damaged aircraft glass can not normally function. For example, when the aircraft glass is a windshield glass, the windshield glass is broken and obviously cannot function normally, and the state label corresponding to the historical monitoring information is a damaged state.
Under certain historical monitoring information, the state of the aircraft glass is between a normal state and a damaged state, and at the moment, a state label corresponding to the historical monitoring information is an abnormal state, which is generally caused by fatigue loss caused by looseness of installation parts of the aircraft glass, sudden temperature change or overlarge long-term stress. Taking aviation glass as an example of a windshield, under the common conditions, the service lives of the windshields are different under different temperatures and different pressures, and when the temperature of the windshield suddenly rises and falls, the windshields can be damaged; windshields which are exposed to high stresses for long periods or temperatures below normal, even if not damaged for short periods, can affect glass life over long periods. In addition, the shape of the windshield is rectangular, four corners of the rectangular windshield need to be fixed to ensure that the windshield is firmly installed, and at the moment, if an installation part of one corner of the rectangular windshield is loosened, a stress model of the rectangular windshield is different from that of a normal state and a damaged state, namely, the abnormal state is obtained. Through labeling the running state of the aircraft glass, a large amount of data can be obtained for learning and training, and therefore the working efficiency and the accuracy of the state evaluation model are improved.
And S600, establishing a state evaluation model according to the environment characteristics and the state label.
The controller 20 extracts features of a large amount of historical monitoring information to obtain environmental features and state labels, selects a corresponding state evaluation algorithm, learns and trains an association relationship between the environmental features and the state labels, and constructs a corresponding state evaluation model. The state evaluation algorithm may be a classification algorithm based on a neural network, or a classification algorithm based on a support vector machine, or the like. It will be appreciated that the evaluation algorithm is not unique and can be selected by one skilled in the art based on the characteristics of the data.
In one embodiment, as shown in FIG. 4, step S400 includes step S410.
And S410, acquiring marked monitoring data and unmarked monitoring data of the aircraft glass.
Specifically, the historical monitoring information includes marked monitoring data and unmarked monitoring data. The controller 20 may obtain a large amount of historical monitoring information from a local database or a third party database in advance. A large amount of historical monitoring information is divided into marked monitoring data and unmarked monitoring data according to a certain proportion, so that subsequent modeling is facilitated.
In one embodiment, as shown in fig. 5, step S600 includes steps S610 to S630.
And step S610, generating a training set by using the marked monitoring data, and generating a verification set by using the unmarked monitoring data.
Specifically, the labeled monitoring data includes an environmental characteristic and a state label, wherein the environmental characteristic includes a temperature characteristic, a stress characteristic, a humidity characteristic and the like, the state label can be obtained by manually judging the operating state of the aircraft glass under each historical monitoring information, and attaching a corresponding label to each historical monitoring information according to the judgment result, for example, the state label can include a normal state, a damaged state, an abnormal state and the like. The controller 20 generates a training set using the large amount of labeled monitoring data and the controller 20 generates a training set using the large amount of unlabeled monitoring data.
And S620, inputting the training set into a state evaluation algorithm, and performing learning training on the evaluation algorithm by using the environmental characteristics and the state labels of the labeled monitoring data to obtain an initial state evaluation model.
The type of state estimation algorithm is not exclusive, and for example, the state estimation algorithm is a neural network model, and a network layer of the neural network model may include an activation function, a decision function, and a bias loss function, and for example, a fully-connected artificial neural network output through an LSTM layer also includes a corresponding activation function. The neural network model also comprises a calculation mode for determining errors, for example, a mean square error algorithm can be adopted; and determining an iterative updating mode of the weight parameter. The neural network model can also comprise a common neural network layer for outputting the dimensionality reduction of the result.
The controller 20 inputs the labeled monitoring data in the training set into the state evaluation algorithm for learning and training, and learns the association relationship between the labeled environmental features and the state labels in the labeled monitoring data. After the controller 20 trains a large amount of labeled monitoring data in the training set, feature weights and the like corresponding to a plurality of environmental features can be obtained, and then an initial state evaluation model is constructed according to the plurality of environmental features and the corresponding feature weights.
Step S630, inputting the verification set into the initial state evaluation model, and verifying the state evaluation model by using the unmarked monitoring data in the verification set until the number of samples with correct verification results in the verification set meets the preset conditions to obtain the state evaluation model.
The controller 20 obtains the initial state evaluation model, further obtains a verification set, and inputs the unlabeled monitoring data in the verification set to the initial state evaluation model for further training and verification. And stopping training until the number of the verification set data meeting the condition threshold reaches the verification threshold, and further obtaining a trained state evaluation model. Further, the controller 20 may also calculate a loss parameter during the process of training the state estimation model, and continuously update the state estimation model by using a gradient descent algorithm, so that the decision accuracy of the state estimation model is higher. By training and learning a large amount of historical monitoring information, a state evaluation model with high decision-making accuracy can be effectively constructed and trained, and therefore decision-making accuracy of monitoring data is effectively improved.
In one embodiment, as shown in FIG. 6, step S100 includes step S110.
And step S110, acquiring temperature information through a temperature sensor, and acquiring stress information through a stress sensor.
Specifically, the monitoring information includes temperature information and atress information, and temperature sensor and atress sensor all set up in aircraft glass. In the process of airplane flying, along with the change of flying height and external environment, the ambient temperature around the airplane also can correspondingly change, and the material strength of the aviation glass is different at different temperatures, namely the maximum pressure that the aviation glass can bear at different temperatures is different, so that the overall situation of the aviation glass can be more comprehensively and effectively evaluated by acquiring the temperature information of the aviation glass, sudden catastrophic accidents are avoided, the maintenance cost is reduced, and the service life is prolonged.
In this embodiment, the method for acquiring temperature information through the temperature sensor is not unique, and one of the methods is to arrange the temperature sensor on the outer surface of the aircraft glass, and the temperature sensor measures the ambient temperature of the aircraft glass at different moments, so that the temperature information is obtained, and the method is simple, convenient and wide in coverage. In another mode, the environmental temperatures of a plurality of aviation glasses acquired by the plane can be used, so that temperature information can be obtained.
Further, aircraft glass is typically subjected to complex cyclic fatigue loads and accidental impact loads during aircraft flight. Under different environmental temperature conditions, the material strength of the aircraft glass is different, namely the maximum pressure which can be borne by the aircraft glass is different, so that the fatigue degree of the aircraft glass can be evaluated in time by acquiring the stress information of the aircraft glass at different temperatures in real time, and corresponding measures can be taken, thereby avoiding sudden catastrophic accidents.
Secondly, stress information is obtained through the stress sensor, the type of the stress sensor is not unique, a strain gauge can be generally used, when the strain gauge generates mechanical deformation under the action of external force, the resistance value of the strain gauge changes correspondingly, the deformation quantity of the outer surface of the aircraft glass can be obtained through measuring and calculating the resistance value, and then the stress value of the aircraft glass is obtained. Illustratively, the strain gauge used is a resistance strain gauge, which is an element for measuring strain composed of a sensitive gate or the like. The working principle of the resistance strain gauge is based on the strain effect, namely, when a conductor or a semiconductor material is mechanically deformed under the action of external force, the resistance value of the conductor or the semiconductor material is correspondingly changed. That is, in the present embodiment, the stress information of the aircraft glass is obtained by measuring the change of the resistance value, and the stress information may include various resistance values of the aircraft in the air, such as a pressure difference resistance value.
In one embodiment, as shown in fig. 7, the step S200 includes a step S210 and a step S220.
Step S210, performing feature extraction on the monitoring information to obtain an environmental feature corresponding to the monitoring information.
After the controller 20 acquires the monitoring information, it extracts an environmental characteristic corresponding to the monitoring information, where the environmental characteristic may be two or more, for example, a temperature characteristic, a stress characteristic, a humidity characteristic, and the like.
And S220, inputting the environmental characteristics corresponding to the monitoring information into the state evaluation model, so that the state evaluation model can predict the running state of the aircraft glass to obtain a state evaluation result.
The state evaluation result includes a normal state, a damaged state and an abnormal state. Specifically, after acquiring the monitoring information, the controller 20 extracts a plurality of environmental characteristics of the monitoring information, such as a temperature characteristic, a stress characteristic, a humidity characteristic, and the like. And calling the trained state evaluation model, calculating the weights of the plurality of environmental features, classifying the running state of the aircraft glass by using the state evaluation model such as a classification model based on a neural network or a support vector machine algorithm according to the plurality of environmental features and the corresponding feature weights, and obtaining a state evaluation result, wherein the state evaluation result comprises a normal state, a damaged state and an abnormal state.
Exemplarily, under certain monitoring information, the aircraft glass is calculated through a state evaluation model to play a normal role, and at the moment, a state evaluation result corresponding to the monitoring information is a normal state; under another monitoring information, the aviation glass obtained by the calculation of the state evaluation model can not normally play a role, and at the moment, the state evaluation result corresponding to the monitoring information is the damaged state. The damaged state is represented by, for example, the aircraft glass being a windshield, and when the windshield is broken, it is apparently not functioning normally. Under certain monitoring information, the state of the aircraft glass is calculated and obtained to be between a normal state and a damaged state through a state evaluation model, and at the moment, the state evaluation result corresponding to the monitoring information is an abnormal state, which is generally caused by the fatigue loss caused by the looseness, the sudden temperature change or the overlarge long-term stress of the installation part of the aircraft glass. Taking aviation glass as an example of a windshield, under the common conditions, the service lives of the windshields are different under different temperatures and different pressures, and when the temperature of the windshield suddenly rises and falls, the windshields can be damaged; windshields are exposed to high stresses for long periods of time or temperatures below normal, which can affect glass life over long periods of time, even if not damaged for short periods of time. In addition, the shape of the windshield is rectangular, four corners of the rectangular windshield need to be fixed to ensure that the windshield is firmly installed, and at the moment, if an installation part of one corner of the rectangular windshield is loosened, a stress model of the rectangular windshield is different from that of a normal state and a damaged state, namely, the abnormal state is obtained.
And the trained state evaluation model is called to evaluate the state of the monitoring information obtained in real time, so that the state monitoring efficiency and accuracy of the aviation glass can be effectively improved.
In one embodiment, as shown in fig. 8, step S300 includes step S310 and step S320.
Step S310, when the state evaluation result is a damaged state, a damaged alarm signal is sent to the alarm device.
In step S320, when the state evaluation result is an abnormal state, an abnormal alarm signal is sent to the alarm device.
Specifically, the state evaluation result reflects the operating state of the aircraft glass under each monitoring information, and exemplarily includes a normal state, a damaged state and an abnormal state, the normal state indicates that the key components of the aircraft function normally at this time, the damaged state indicates that the aircraft glass cannot function normally at this time, the abnormal state is between the normal state and the damaged state, when the state evaluation result is the normal state, the controller 20 does not send a signal to the warning device, when the state evaluation result is the damaged state, the controller 20 sends a damaged warning signal to the warning device, and when the state evaluation result is the abnormal state, the controller 20 sends an abnormal warning signal to the warning device.
According to the state monitoring method of the aircraft glass, monitoring information of the aircraft glass is obtained, the monitoring information is input into the state evaluation model, a state evaluation result of the aircraft glass is obtained, the state evaluation result is used for evaluating the running state of the aircraft glass, the state evaluation model is a prediction model established after learning and training are carried out by utilizing historical monitoring information, and when the state evaluation result is a preset result, an alarm signal is sent to alarm equipment. The monitoring information is analyzed through the state evaluation model, so that the real-time online monitoring of the aircraft glass can be efficiently realized, the evaluation is made, the crew is reminded according to the evaluation result, the efficiency and the accuracy of the state detection of the aircraft glass can be effectively improved, and the stability and the safety of the aircraft in the flight process are improved.
It will be understood that although the various steps in the flow charts of fig. 2-8 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-8 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 9, there is provided a condition monitoring device 100 for aircraft glass, comprising: the system comprises a data acquisition module 101, a data processing module 102 and an alarm driving module 103, wherein:
the data acquisition module 101 is used for acquiring monitoring information of the aircraft glass;
the data processing module 102 is used for inputting the monitoring information into the state evaluation model to obtain a state evaluation result of the aircraft glass; the state evaluation result is used for evaluating the running state of the aircraft glass, and the state evaluation model is a prediction model established by learning and training by using historical monitoring information;
and the alarm driving module 103 is configured to send an alarm signal to the alarm device when the state evaluation result is a preset result.
In one embodiment, as shown in fig. 10, the status monitoring apparatus 100 for aircraft glass further includes a model building module 104, where the model building module 104 is configured to obtain historical monitoring information of the aircraft glass, perform feature extraction on the historical monitoring information to obtain an environmental feature and a status label, and build a status evaluation model according to the environmental feature and the status label.
In one embodiment, the model building module 104 is further configured to obtain tagged monitoring data and untagged monitoring data of the aircraft glass, where the tagged monitoring data includes an environmental characteristic and a state label, generate a training set using the tagged monitoring data, generate a verification set using the untagged monitoring data, input the training set to a state evaluation algorithm, perform learning training on the evaluation algorithm using the environmental characteristic and the state label of the tagged monitoring data to obtain an initial state evaluation model, input the verification set to the initial state evaluation model, and verify the state evaluation model using the untagged monitoring data in the verification set until the number of samples with correct verification results in the verification set meets a preset condition, so as to obtain the state evaluation model.
Specific limitations of the aircraft glass condition monitoring device can be found in the above limitations of the aircraft glass condition monitoring method, and are not described in detail here. The various modules in the aircraft glass condition monitoring device can be wholly or partially realized through software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules. It should be noted that, in the embodiment of the present application, the division of the module is schematic, and is only one logic function division, and there may be another division manner in actual implementation.
In one embodiment, a computer device is also provided, the internal structure of which may be as shown in fig. 11. The computer device comprises a processor, a memory and a network interface which are connected through a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of monitoring the condition of aircraft glass.
Those skilled in the art will appreciate that the architecture shown in fig. 11 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the above-described method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile memory may include Read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), for example.
In the description herein, references to the description of "one embodiment," "another embodiment," "an ideal embodiment," etc., 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 invention. In this specification, a schematic description of the above terminology may not necessarily refer to the same embodiment or example.
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A method for monitoring the condition of aircraft glass, comprising the steps of:
acquiring monitoring information of aircraft glass;
inputting the monitoring information into a state evaluation model to obtain a state evaluation result of the aircraft glass; the state evaluation result is used for evaluating the running state of the aircraft glass, and the state evaluation model is a prediction model established after learning and training by using historical monitoring information;
and when the state evaluation result is a preset result, sending an alarm signal to alarm equipment.
2. The method for monitoring the condition of aircraft glass according to claim 1, wherein the process for establishing the condition evaluation model comprises:
acquiring the historical monitoring information of the aircraft glass;
extracting the characteristics of the historical monitoring information to obtain environmental characteristics and a state label;
and establishing the state evaluation model according to the environment characteristics and the state label.
3. The method for monitoring the state of aircraft glass according to claim 2, wherein the historical monitoring information comprises marked monitoring data and unmarked monitoring data, and the obtaining the historical monitoring information of aircraft glass comprises:
and acquiring the marked monitoring data and the unmarked monitoring data of the aircraft glass.
4. The method of claim 2, wherein the historical monitoring information includes labeled monitoring data and unlabeled monitoring data, the labeled monitoring data includes the environmental characteristic and the status label, and the establishing the status assessment model based on the environmental characteristic and the status label includes:
generating a training set by using the marked monitoring data, and generating a verification set by using the unmarked monitoring data;
inputting the training set into a state evaluation algorithm, and performing learning training on the state evaluation algorithm by using the environmental characteristics of the labeled monitoring data and the state labels to obtain an initial state evaluation model;
and inputting the verification set into the initial state evaluation model, and verifying the initial state evaluation model by using the unmarked monitoring data in the verification set until the number of samples with correct verification results in the verification set meets a preset condition to obtain the state evaluation model.
5. The aircraft glass state monitoring method according to claim 1, wherein the monitoring information comprises temperature information and stress information, and the acquiring the aircraft glass monitoring information comprises:
acquiring the temperature information through a temperature sensor, and acquiring the stress information through a stress sensor; the temperature sensor and the stress sensor are both arranged on the aircraft glass.
6. The method for monitoring the state of aircraft glass according to claim 1, wherein the inputting the monitoring information into a state evaluation model to obtain the state evaluation result of aircraft glass comprises:
performing feature extraction on the monitoring information to obtain an environmental feature corresponding to the monitoring information;
inputting the environmental characteristics corresponding to the monitoring information into the state evaluation model, and enabling the state evaluation model to predict the running state of the aircraft glass to obtain the state evaluation result, wherein the state evaluation result comprises a normal state, a damaged state and an abnormal state.
7. The aircraft glass condition monitoring method according to claim 1, wherein the preset result includes a damaged condition and an abnormal condition, and when the condition evaluation result is the preset result, sending an alarm signal to an alarm device includes:
when the state evaluation result is a damaged state, sending a damaged alarm signal to alarm equipment;
and when the state evaluation result is an abnormal state, sending an abnormal alarm signal to alarm equipment.
8. A condition monitoring device for aircraft glass, the device comprising:
the data acquisition module is used for acquiring monitoring information of the aircraft glass;
the data processing module is used for inputting the monitoring information into a state evaluation model to obtain a state evaluation result of the aircraft glass; the state evaluation result is used for evaluating the running state of the aircraft glass, and the state evaluation model is a prediction model established by learning and training by using historical monitoring information;
and the alarm driving module is used for sending an alarm signal to alarm equipment when the state evaluation result is a preset result.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
CN202210374228.1A 2022-04-11 2022-04-11 Aviation glass state monitoring method and device, computer equipment and medium Pending CN114993373A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210374228.1A CN114993373A (en) 2022-04-11 2022-04-11 Aviation glass state monitoring method and device, computer equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210374228.1A CN114993373A (en) 2022-04-11 2022-04-11 Aviation glass state monitoring method and device, computer equipment and medium

Publications (1)

Publication Number Publication Date
CN114993373A true CN114993373A (en) 2022-09-02

Family

ID=83023867

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210374228.1A Pending CN114993373A (en) 2022-04-11 2022-04-11 Aviation glass state monitoring method and device, computer equipment and medium

Country Status (1)

Country Link
CN (1) CN114993373A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116147928A (en) * 2023-04-20 2023-05-23 清华大学 Method, device and equipment for determining health state of aeroengine thermal jet device

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116147928A (en) * 2023-04-20 2023-05-23 清华大学 Method, device and equipment for determining health state of aeroengine thermal jet device

Similar Documents

Publication Publication Date Title
US10891406B2 (en) Prediction methods and systems for structural repair during heavy maintenance of aircraft
CN104773304B (en) Load estimation system for aerodynamic structures
JP6313929B2 (en) Method and system for monitoring structures
CN110376522B (en) Motor fault diagnosis method of data fusion deep learning network
JP4875661B2 (en) Aircraft soundness diagnosis apparatus and method, and program
CN110567388A (en) Fault isolation and aircraft damage detection for automatic flight control surfaces by non-contact measurement
CN113569445A (en) Steel structure health monitoring system and method based on digital twinning technology
CN113760670A (en) Cable joint abnormity early warning method and device, electronic equipment and storage medium
CN115659673B (en) Bridge construction process safety monitoring system based on unmanned aerial vehicle image
CN114993373A (en) Aviation glass state monitoring method and device, computer equipment and medium
CN115146230A (en) Ancient building health monitoring system, method and equipment
US11772823B2 (en) Estimating fatigue damage in a structure
CN114580784A (en) Analysis method for predictive maintenance data of airplane components
Bandara et al. Sensory methods and machine learning based damage identification of fibre-reinforced composite structures: An introductory review
CN116756505B (en) Photovoltaic equipment intelligent management system and method based on big data
CN116664103B (en) Aircraft operation and maintenance management system based on data analysis
CN117706290A (en) Early warning method for potential breakdown fault of cable terminal
CN112560252A (en) Prediction method for residual life of aircraft engine
CN116151792A (en) CPS-based multi-rotor unmanned aerial vehicle health management system and method
CN113504302B (en) Method and system for monitoring fan blade state, electronic equipment and storage medium
Cross et al. Prediction of landing gear loads from flight test data using Gaussian process regression
CN117874905B (en) Method, system, equipment and storage medium for predicting damage of airplane windshield
CN116176860B (en) Fuel system testing method, system, equipment and readable storage medium
CN118210292A (en) SR20 type airplane fault detection method and system based on visualization technology
CN118408660A (en) Aviation wing load monitoring system and method

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