Method, apparatus, computer device and medium for monitoring the state of aviation glass

Abstract

The present application relates to a method, device, computer equipment and medium for monitoring the state of aviation glass, obtaining monitoring information of the aviation glass, inputting the monitoring information into a state evaluation model to obtain a state evaluation result of the aviation glass, where the state evaluation result is used to evaluate the operating state of the aviation glass, and the state evaluation model is a prediction model established after learning and training using historical monitoring information. When the state evaluation result is a preset result, an alarm signal is sent to an alarm device. The above-mentioned method, device, computer equipment and medium for monitoring the state of aviation glass analyze the monitoring information through the state evaluation model, so as to be able to efficiently realize real-time online monitoring and evaluation of the aviation glass, remind the flight crew according to the evaluation result, thereby effectively improving the efficiency and accuracy of the state detection of the aviation glass, and improving the stability and safety of the aircraft during flight.

Description

Technical Field

[0001] The present application relates to the field of aviation aircraft, and particularly to a method, device, computer equipment and medium for monitoring the state of aviation glass. Background Art

[0002] With the increasing development of the aviation industry, aviation safety has become increasingly important. Aviation glass (such as windshield, porthole, etc.), as an important part of an aircraft, is directly related to the safety of the aircraft and passengers. Generally speaking, aviation glass is a relatively weak area. The bending stress, thermal stress, etc. of aviation glass can exacerbate the development of damage or crack propagation, which may lead to the damage and detachment of aviation glass. In recent years, there have been many incidents where the damage of aviation glass has affected aviation safety and caused the forced landing of an aviation aircraft.

[0003] In traditional technologies, technicians will check engines and instruments, but they do not necessarily conduct special inspections and risk predictions on aviation glass every time before a flight, or conduct risk assessments through manual inspections, which are prone to missed inspections and other situations, resulting in low efficiency and accuracy of the state monitoring of aviation glass. Summary of the Invention

[0004] Based on this, in view of the problems of low efficiency and accuracy in the state monitoring of the above-mentioned aviation glass, it is necessary to provide a method, device, computer equipment and medium for monitoring the state of aviation glass.

[0005] A method for monitoring the state of aviation glass, the method comprising the following steps:

[0006] Obtain the monitoring information of the aviation glass;

[0007] Input the monitoring information into a state evaluation model to obtain a state evaluation result of the aviation glass; the state evaluation result is used to evaluate the operating state of the aviation glass, and the state evaluation model is a prediction model established after learning and training using historical monitoring information;

[0008] When the state evaluation result is a preset result, send an alarm signal to an alarm device.

[0009] In one embodiment, the establishment process of the state evaluation model includes:

[0010] Obtain the historical monitoring information of the aviation glass;

[0011] Extract features from the historical monitoring information to obtain environmental features and state labels;

[0012] Establish the state evaluation model according to the environmental features and the state labels.

[0013] In one embodiment, the historical monitoring information includes labeled monitoring data and unlabeled monitoring data, and the process of establishing the state evaluation model further includes:

[0014] Obtain the labeled monitoring data and the unlabeled monitoring data of the aircraft glass.

[0015] In one embodiment, the historical monitoring information includes labeled monitoring data and unlabeled monitoring data, the labeled monitoring data includes the environmental characteristics and the state labels, and establishing the state evaluation model according to the environmental characteristics and the state labels includes:

[0016] Generate a training set by using the labeled monitoring data, and generate a validation set by using the unlabeled monitoring data;

[0017] Input the training set into a state evaluation algorithm, and perform learning and training on the state evaluation algorithm by using the environmental characteristics and the state labels of the labeled monitoring data to obtain an initial state evaluation model;

[0018] Input the validation set into the initial state evaluation model, and verify the initial state evaluation model by using the unlabeled monitoring data in the validation set until the number of samples with correct verification results in the validation set meets a preset condition, and then obtain the state evaluation model.

[0019] In one embodiment, the monitoring information includes temperature information and stress information, and obtaining the monitoring information of the aircraft glass includes:

[0020] Obtain the temperature information through a temperature sensor, and obtain the stress information through a stress sensor; both the temperature sensor and the stress sensor are arranged on the aircraft glass.

[0021] In one embodiment, inputting the monitoring information into the state evaluation model to obtain the state evaluation result of the aircraft glass includes:

[0022] Extract features from the monitoring information to obtain environmental characteristics corresponding to the monitoring information;

[0023] Input the environmental characteristics corresponding to the monitoring information into the state evaluation model, and enable the state evaluation model to predict the operating state of the aircraft glass to obtain the state evaluation result, where the state evaluation result includes a normal state, a damaged state, and an abnormal state.

[0024] In one embodiment, the preset results include a damaged state and an abnormal state, and when the state evaluation result is a preset result, sending an alarm signal to an alarm device includes:

[0025] When the state evaluation result is in a damaged state, send a damaged alarm signal to the alarm device;

[0026] When the state evaluation result is in an abnormal state, send an abnormal alarm signal to the alarm device.

[0027] A state monitoring device for an aviation glass, the device comprising:

[0028] A data acquisition module for acquiring monitoring information of the aviation glass;

[0029] A data processing module for inputting the monitoring information into a state evaluation model to obtain a state evaluation result of the aviation glass; the state evaluation result is used to evaluate the operating state of the aviation glass, and the state evaluation model is a prediction model established by learning and training using historical monitoring information;

[0030] An alarm driving module for sending an alarm signal to the alarm device when the state evaluation result is a preset result.

[0031] A computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above steps when executing the computer program.

[0032] A computer-readable storage medium having stored thereon a computer program, and the computer program implementing the above steps when executed by a processor.

[0033] The above state monitoring method, device, computer device and medium for aviation glass, acquire monitoring information of the aviation glass, input the monitoring information into a state evaluation model to obtain a state evaluation result of the aviation glass, the state evaluation result is used to evaluate the operating state of the aviation glass, the state evaluation model is a prediction model established by learning and training using historical monitoring information, and when the state evaluation result is a preset result, send an alarm signal to the alarm device. The above state monitoring method, device, computer device and medium for aviation glass analyze the monitoring information through the state evaluation model, so as to be able to efficiently realize real-time online monitoring and evaluation of the aviation glass, remind the flight crew according to the evaluation result, thereby being able to effectively improve the efficiency and accuracy of the state detection of the aviation glass, and improve the stability and safety of the aircraft during flight. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0035] Figure 1 Schematic diagram of the application scenario for the status monitoring of aircraft glass in one embodiment;

[0036] Figure 2 Schematic flowchart of the method for status monitoring of aircraft glass in one embodiment;

[0037] Figure 3 Schematic flowchart of the process for constructing a status evaluation model in one embodiment;

[0038] Figure 4 Schematic diagram of the detailed process for constructing a status evaluation model in one embodiment;

[0039] Figure 5 Schematic diagram of the detailed process for constructing a status evaluation model in another embodiment;

[0040] Figure 6 Schematic diagram of the detailed process for the method for status monitoring of aircraft glass in one embodiment;

[0041] Figure 7 Schematic diagram of the detailed process for the method for status monitoring of aircraft glass in another embodiment;

[0042] Figure 8 Schematic diagram of the detailed process for the process of judging the status evaluation result in one embodiment;

[0043] Figure 9 Schematic diagram of the structure of the status monitoring device for aircraft glass in one embodiment;

[0044] Figure 10 Schematic diagram of the structure of the status monitoring device for aircraft glass in another embodiment;

[0045] Figure 11 Schematic diagram of the internal structure of a computer device in one embodiment. Detailed implementation manners

[0046] To facilitate the understanding of this application, the following will describe this application more comprehensively with reference to the relevant accompanying drawings. Embodiments of this application are given in the drawings. However, this application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of this application more thorough and comprehensive.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used in the description of this application herein are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0048] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from another element.

[0049] It should be noted that when an element is considered to be "connected" to another element, it may be directly connected to the other element or connected to the other element through an intermediate element. In addition, in the following embodiments, "connection", if there is a transmission of electrical signals or data between the connected objects, should be understood as "electrical connection", "communication connection", etc.

[0050] As used herein, the singular forms "a", "an" and "the" may also include the plural forms unless the context clearly dictates otherwise. It should also be understood that the terms "comprise / include" or "have" etc. specify the presence of the stated features, wholes, steps, operations, components, parts or combinations thereof, but do not preclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof.

[0051] The method, device, computer equipment and medium for monitoring the state of aviation glass provided by this application are used to monitor the state of aviation glass. By analyzing the monitoring information through a state evaluation model, the real-time online monitoring and evaluation of aviation glass can be efficiently realized, thereby effectively improving the efficiency and accuracy of the state detection of aviation glass, and improving the stability and safety of the aircraft during flight. Applicable to Figure 1 In the application scenario shown, the sensor 10 is arranged on the aviation glass such as the windshield, porthole or other parts. The sensor 10 acquires the monitoring information of the aviation glass and sends the monitoring information to the controller 20. The controller 20 inputs the monitoring information into the state evaluation model, calculates the state evaluation result corresponding to the monitoring information according to the state evaluation model, and when the state evaluation result is a preset result, sends an alarm signal to the alarm device.

[0052] In one embodiment, as Figure 2 shown, this application provides a method for monitoring the state of aviation glass. This method can be executed by the controller 20. Among them, the controller 20 can be implemented by an independent server or a server cluster composed of multiple servers. This method includes:

[0053] Step S100, acquire the monitoring information of the aviation glass.

[0054] Specifically, the aviation glass does not refer to a specific component, including but not limited to the windshield, porthole, etc. Those skilled in the art can monitor the state of the above components according to actual needs.

[0055] Monitoring information usually includes information about the environment around the aircraft glass, such as temperature information, humidity information, wind speed information, wind direction information, etc., and also includes information about the aircraft glass itself, such as force information, etc. Obtaining the monitoring information of the aircraft glass is beneficial to comprehensively evaluate the operating state of the aircraft glass. Further, the monitoring information can be collected by setting sensors 10 on each aircraft glass, and the sensors 10 send the collected monitoring information to the controller 20. Among them, the types of the sensors 10 are not unique and can include temperature sensors, force sensors, humidity sensors, etc., which are respectively used to obtain temperature information, force information, and humidity information. Secondly, the time interval for obtaining the monitoring information of the aircraft glass is not unique either. The monitoring information can be continuously obtained to avoid omission. Or a time interval can be set to obtain the monitoring information periodically, thereby reducing the workload of the sensors 10. After obtaining the monitoring information of the aircraft glass, the sensors 10 send the monitoring information to the controller 20 for subsequent evaluation operations.

[0056] Step S200, input the monitoring information into the state evaluation model to obtain the state evaluation result of the aircraft glass.

[0057] Specifically, after receiving the monitoring information, the controller 20 inputs the monitoring information into the built-in state evaluation model. Among them, the state evaluation model is a prediction model established by learning and training using historical monitoring information. For example, the state evaluation model can be a classification model obtained by learning and training a large amount of historical monitoring information based on neural network or support vector machine algorithms.

[0058] After the controller 20 obtains the monitoring information of the aircraft glass in each stage of the flight process of the aircraft, it calls the state evaluation model to perform state evaluation on the obtained monitoring information to obtain the corresponding state evaluation result. The state evaluation result is used to evaluate the operating state of the aircraft glass. Further, the state evaluation result reflects the operating state of the aircraft glass under each monitoring information. Exemplarily, the state evaluation result includes a normal state and a damaged state. The normal state indicates that the key components of the aircraft are functioning properly at this moment, and the damaged state indicates that the aircraft glass cannot function properly at this moment.

[0059] Exemplarily, the controller 20 obtains the monitoring information of the aircraft glass through the sensors 10. The monitoring information includes temperature information, force information, and humidity information, and calls the trained state evaluation model to perform state evaluation on the monitoring information. In this embodiment, the state evaluation model is a classification model obtained by learning and training a large amount of historical monitoring information based on the support vector machine algorithm. Different feature weights are assigned to the temperature information, force information, and humidity information in the state evaluation model, and the state evaluation result corresponding to the monitoring information is accurately and effectively obtained according to multiple information and the corresponding feature weights.

[0060] Step S300: When the status evaluation result is the preset result, send an alarm signal to the alarm device.

[0061] Specifically, the status evaluation result reflects the operating status of the aircraft glass under each monitoring information, and the preset result is pre-set and used to determine the operating status of the aircraft glass. Exemplarily, the status evaluation result includes a normal state, a damaged state, and an abnormal state. The normal state indicates that the aircraft glass is functioning properly at this moment, the damaged state indicates that the aircraft glass cannot function properly at this moment, and the abnormal state is between the normal state and the damaged state. The preset results include the damaged state and the abnormal state.

[0062] When the status evaluation result is the normal state, the controller 20 does not send a signal to the alarm device. When the status evaluation result is the damaged state, the controller 20 sends a damaged alarm signal to the alarm device. When the status evaluation result is the abnormal state, the controller 20 sends an abnormal alarm signal to the alarm device.

[0063] Furthermore, the specific type of the alarm device is not unique. A sound alarm or a light alarm can be used, and the specific type of the alarm device can be set according to actual needs. For example, when the alarm device is a sound alarm, the sound alarm is connected to the controller 20. After receiving the damaged alarm signal or the abnormal alarm signal from the controller 20, the sound alarm alarms by emitting an alarm sound. The sound alarm can be a voice playback device, and the voice playback device can play different alarm voices according to different alarm signals, with rich alarm content. It can be understood that in other embodiments, the alarm device can also be of other types as long as those skilled in the art think it can be implemented.

[0064] For the above method for monitoring the status of the aircraft glass, the sensor 10 obtains the monitoring information of the aircraft glass and sends the monitoring information to the controller 20. The controller 20 inputs the monitoring information into the status evaluation model to obtain the status evaluation result of the aircraft glass. When the status evaluation result is the preset result, the controller 20 sends an alarm signal to the alarm device. It efficiently realizes the real-time online monitoring and evaluation of the aircraft glass, thereby effectively improving the efficiency and accuracy of the aircraft glass status detection, and improving the stability and safety of the aircraft during flight.

[0065] In one embodiment, as Figure 3 shown, the process of establishing the status evaluation model includes steps S400 to S600:

[0066] Step S400: Obtain the historical monitoring information of the aircraft glass.

[0067] Specifically, the controller 20 obtains a large amount of historical monitoring information, which can be the historical monitoring information collected through simulation experiments or the historical monitoring information obtained from a third-party database.

[0068] Step S500: Extract features from the historical monitoring information to obtain environmental features and status labels.

[0069] Specifically, the controller 20 extracts features from the large amount of historical monitoring information obtained. The method of feature extraction is not unique. For example, the controller 20 can use the k-means clustering algorithm to perform clustering analysis on the large amount of historical monitoring information to obtain environmental features.

[0070] Furthermore, the types of environmental features are not unique. Environmental features can include temperature features, stress features, humidity features, etc. The method of extracting features from the historical monitoring information to obtain status labels is also not unique. For example, the operating state of the aviation glass under each historical monitoring information can be manually judged, and corresponding labels can be attached to each historical monitoring information according to the judgment results. Exemplarily, under a certain historical monitoring information, the aviation glass functions normally, and the status label corresponding to this historical monitoring information is the normal state; under another historical monitoring information, the aviation glass is damaged, and the damage is manifested as the aviation glass not being able to function normally. For example, when the aviation glass is a windshield and the windshield is broken, it is obvious that it cannot function normally, and the status label corresponding to this historical monitoring information is the damaged state.

[0071] Under a certain historical monitoring information, the state of the aviation glass is between the normal state and the damaged state. At this time, the status label corresponding to this historical monitoring information is the abnormal state, which is usually caused by the loosening of the installation components of the aviation glass, sudden temperature changes, or fatigue loss caused by excessive long-term stress. Taking the aviation glass as a windshield as an example, generally, the expected life of the windshield is different under different temperatures and pressures. When the glass temperature rises and falls suddenly, it may cause damage to the windshield; when the windshield is under high stress for a long time or the temperature is lower than the normal temperature, even if it is not damaged in the short term, it will affect the glass life in the long run. In addition, the shape of the windshield is rectangular. To ensure the windshield is firmly installed, the four corners of the rectangular windshield need to be fixed. At this time, if the installation component of one of the corners of the rectangular windshield is loose, its stress model is different from both the normal state and the damaged state, that is, the abnormal state. By labeling the operating state of the aviation glass, a large amount of data can be obtained for learning and training, thereby improving the working efficiency and accuracy of the state evaluation model.

[0072] Step S600: Establish a state evaluation model based on the environmental features and status labels.

[0073] The controller 20 extracts features from a large amount of historical monitoring information to obtain environmental features and status labels, selects corresponding state evaluation algorithms, learns and trains the correlation between the environmental features and the status labels, and constructs a corresponding state evaluation model. Among them, the state evaluation algorithm can be a classification algorithm based on a neural network or a classification algorithm based on a support vector machine, etc. It can be understood that the selection of the evaluation algorithm is not unique, and those skilled in the art can select according to the characteristics of the data.

[0074] In one embodiment, as Figure 4 shown, step S400 includes step S410.

[0075] Step S410, obtaining the labeled monitoring data and unlabeled monitoring data of the aviation glass.

[0076] Specifically, the historical monitoring information includes labeled monitoring data and unlabeled monitoring data. The controller 20 can pre-obtain a large amount of historical monitoring information from a local database or a third-party database. Among them, a large amount of historical monitoring information is divided into labeled monitoring data and unlabeled monitoring data according to a certain ratio for subsequent modeling.

[0077] In one embodiment, as Figure 5 shown, step S600 includes step S610 to step S630.

[0078] Step S610, generating a training set using the labeled monitoring data and generating a validation set using the unlabeled monitoring data.

[0079] Specifically, the labeled monitoring data includes environmental features and status labels. Among them, the environmental features include temperature features, stress features, humidity features, etc. The status label can be obtained by manually judging the operating status of the aviation glass under each historical monitoring information and attaching corresponding labels to each historical monitoring information according to the judgment results. For example, the status labels can include normal status, damaged status, abnormal status, etc. The controller 20 generates a training set using a large amount of labeled monitoring data, and the controller 20 generates a training set using a large amount of unlabeled monitoring data.

[0080] Step S620, inputting the training set into the state evaluation algorithm, and using the environmental features and status labels of the labeled monitoring data to learn and train the evaluation algorithm to obtain an initial state evaluation model.

[0081] The types of state evaluation algorithms are not unique. Exemplarily, the state evaluation algorithm is a neural network model. The network layers of the neural network model may include an activation function, a decision function, and a bias loss function. For example, a fully connected artificial neural network output by an LSTM layer also includes a corresponding activation function. The neural network model also includes a calculation method for determining the error. For example, the mean square error algorithm can be used; it also includes an iterative update method for determining the weight parameters. The neural network model may also include an ordinary neural network layer for dimensionality reduction of the output results.

[0082] The controller 20 then inputs the labeled monitoring data in the training set into the state evaluation algorithm for learning and training, by learning the correlation between the labeled environmental features and state labels in the labeled monitoring data, etc. After training a large amount of labeled monitoring data in the training set, the controller 20 can obtain the feature weights corresponding to multiple environmental features, etc., and then construct an initial state evaluation model based on the multiple environmental features and the corresponding feature weights.

[0083] Step S630: Input the validation set into the initial state evaluation model, and use the unlabeled monitoring data in the validation set to verify the state evaluation model until the number of samples with correct verification results in the validation set meets the preset conditions, then obtain the state evaluation model.

[0084] The controller 20 obtains the initial state evaluation model, further obtains the validation set, and inputs the unlabeled monitoring data in the validation set into the initial state evaluation model for further training and verification. Until the number of data in the validation set that meets the condition threshold reaches the verification threshold, the training is stopped, and then the trained state evaluation model is obtained. Further, during the process of training the state evaluation model, the controller 20 can also calculate the loss parameters and continuously update the state evaluation model using the gradient descent algorithm, making the decision accuracy of the state evaluation model higher. By training and learning a large amount of historical monitoring information, an effective state evaluation model with a high decision accuracy can be constructed and trained, thus effectively improving the decision accuracy of the monitoring data.

[0085] In one embodiment, as Figure 6 shown, step S100 includes step S110.

[0086] Step S110: Obtain temperature information through a temperature sensor and obtain force information through a force sensor.

[0087] Specifically, the monitoring information includes temperature information and force information. The temperature sensor and the force sensor are both arranged on the aircraft glass. During the flight of the aircraft, as the flight altitude and the external environment change, the ambient temperature around the aircraft will also change accordingly. Moreover, the material strength of the aircraft glass varies at different temperatures, that is, the maximum pressure that the aircraft glass can withstand is different at different temperatures. Therefore, obtaining the temperature information of the aircraft glass can more comprehensively and effectively evaluate the overall condition of the aircraft glass, avoid causing sudden catastrophic accidents, reduce maintenance costs, and extend the service life.

[0088] In this embodiment, the method for obtaining temperature information through the temperature sensor is not unique. One way is to arrange the temperature sensor on the outer surface of the aircraft glass. The temperature sensor measures the ambient temperature of the aircraft glass at different times, thereby obtaining the temperature information, which is simple, convenient, and has a wide coverage range. In another way, the ambient temperatures of multiple aircraft glasses collected by the aircraft itself can also be used to obtain the temperature information. Using this method, no new sensors need to be added, which can reduce costs.

[0089] Furthermore, during the flight of the aircraft, the aircraft glass usually bears complex cyclic fatigue loads and accidental impact loads, etc. And under different ambient temperature conditions, the material strength of the aircraft glass is different, that is, the maximum pressure that the aircraft glass can withstand is different. Therefore, obtaining the force information of the aircraft glass at different temperatures in real time can timely evaluate the fatigue degree of the aircraft glass and then take corresponding measures to avoid causing sudden catastrophic accidents.

[0090] Secondly, the force information is obtained through the force sensor. The type of the force sensor is not unique. Usually, strain gauges can be used. When the strain gauge undergoes mechanical deformation under the action of an external force, its resistance value changes accordingly. By measuring the resistance value, the deformation amount on the outer surface of the aircraft glass can be obtained, and then the force value of the aircraft glass can be obtained. Exemplarily, the strain gauge used is a resistance strain gauge. The resistance strain gauge is an element for measuring strain composed of a sensitive grid and other devices. The working principle of the resistance strain gauge is based on the strain effect, that is, when a conductor or semiconductor material undergoes mechanical deformation under the action of an external force, its resistance value changes accordingly. That is, in this embodiment, the force information of the aircraft glass is obtained by measuring the change in the resistance value. The force information can include various resistance values of the aircraft in the air, such as the pressure difference resistance value.

[0091] In one embodiment, as Figure 7 shown, step S200 includes step S210 and step S220.

[0092] Step S210, extract features from the monitoring information to obtain environmental features corresponding to the monitoring information.

[0093] After the controller 20 obtains the monitoring information, it extracts the corresponding environmental features of the monitoring information. There can be more than two environmental features, such as temperature feature, force feature, humidity feature, etc.

[0094] Step S220: Input the environmental features corresponding to the monitoring information into the state evaluation model, so that the state evaluation model predicts the operating state of the aircraft glass and obtains a state evaluation result.

[0095] Among them, the state evaluation results include normal state, damaged state, and abnormal state. Specifically, after the controller 20 obtains the monitoring information, it extracts multiple environmental features of the monitoring information, such as temperature feature, force feature, humidity feature, etc. It calls the trained state evaluation model, calculates the weights of multiple environmental features, and based on the multiple environmental features and the corresponding feature weights, uses a state evaluation model, such as a classification model based on neural network or support vector machine algorithm, to classify the operating state of the aircraft glass and obtain a state evaluation result. The state evaluation results include normal state, damaged state, and abnormal state.

[0096] Exemplarily, under a certain monitoring information, it is calculated through the state evaluation model that the aircraft glass functions normally. At this time, the state evaluation result corresponding to this monitoring information is the normal state; under another monitoring information, it is calculated through the state evaluation model that the aircraft glass cannot function normally. At this time, the state evaluation result corresponding to this monitoring information is the damaged state. The manifestation of the damaged state is, for example, when the aircraft glass is a windshield and the windshield is broken, it is obvious that it cannot function normally. Under a certain monitoring information, it is calculated through the state evaluation model that the state of the aircraft glass is between the normal state and the damaged state. At this time, the state evaluation result corresponding to this monitoring information is the abnormal state, which is usually caused by loose installation parts of the aircraft glass, sudden temperature changes, or fatigue loss caused by excessive long-term stress. Taking the aircraft glass as a windshield as an example, generally, the expected life of the windshield is different at different temperatures and different pressures. When the glass temperature rises or drops suddenly, it may cause damage to the windshield; when the windshield is under high stress for a long time or the temperature is lower than the normal temperature, even if it is not damaged in the short term, it will affect the glass life in the long run. In addition, the shape of the windshield is rectangular. To ensure the windshield is firmly installed, the four corners of the rectangular windshield need to be fixed. At this time, if the installation part of one of the corners of the rectangular windshield is loose, its force model is different from both the normal state and the damaged state, which is the abnormal state.

[0097] Calling the trained state evaluation model to perform state evaluation on the real-time obtained monitoring information can effectively improve the state monitoring efficiency and accuracy of the aircraft glass.

[0098] In one embodiment, as Figure 8As shown, step S300 includes step S310 and step S320.

[0099] Step S310, when the status evaluation result is the damaged state, send a damaged alarm signal to the alarm device.

[0100] Step S320, when the status evaluation result is the abnormal state, send an abnormal alarm signal to the alarm device.

[0101] Specifically, the status evaluation result reflects the operating status of the aircraft glass under each monitoring information. Exemplarily, the status evaluation result includes the normal state, the damaged state, and the abnormal state. The normal state indicates that the key components of the aircraft are functioning properly at this moment. The damaged state indicates that the aircraft glass cannot function properly at this moment. The abnormal state is between the normal state and the damaged state. When the status evaluation result is the normal state, the controller 20 does not send a signal to the alarm device. When the status evaluation result is the damaged state, the controller 20 sends a damaged alarm signal to the alarm device. When the status evaluation result is the abnormal state, the controller 20 sends an abnormal alarm signal to the alarm device.

[0102] The above method for monitoring the status of aircraft glass obtains the monitoring information of the aircraft glass, inputs the monitoring information into the status evaluation model, and obtains the status evaluation result of the aircraft glass. The status evaluation result is used to evaluate the operating status of the aircraft glass. The status evaluation model is a prediction model established by learning and training using historical monitoring information. When the status evaluation result is the preset result, an alarm signal is sent to the alarm device. By analyzing the monitoring information through the status evaluation model, the real-time online monitoring and evaluation of the aircraft glass can be efficiently realized, and the flight crew can be reminded according to the evaluation result, so as to effectively improve the efficiency and accuracy of the aircraft glass status detection, and improve the stability and safety of the aircraft during flight.

[0103] It can be understood that although Figure 2-8 the steps in the flowchart of Figure 2-8 are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover,

[0104] In one embodiment, as Figure 9As shown, a state monitoring device 100 for aviation glass is provided, including: a data acquisition module 101, a data processing module 102, and an alarm driving module 103, where:

[0105] The data acquisition module 101 is used to acquire monitoring information of the aviation glass;

[0106] The data processing module 102 is used to input the monitoring information into a state evaluation model to obtain a state evaluation result of the aviation glass; the state evaluation result is used to evaluate the operating state of the aviation glass, and the state evaluation model is a prediction model established by learning and training using historical monitoring information;

[0107] The alarm driving module 103 is used to send an alarm signal to an alarm device when the state evaluation result is a preset result.

[0108] In one embodiment, as Figure 10 shown, the state monitoring device 100 for aviation glass further includes a model construction module 104. The model construction module 104 is used to acquire historical monitoring information of the aviation glass, extract features from the historical monitoring information to obtain environmental features and state labels, and establish a state evaluation model according to the environmental features and state labels.

[0109] In one embodiment, the model construction module 104 is further used to acquire labeled monitoring data and unlabeled monitoring data of the aviation glass. The labeled monitoring data includes environmental features and state labels. A training set is generated using the labeled monitoring data, and a validation set is generated using the unlabeled monitoring data. The training set is input into a state evaluation algorithm, and the evaluation algorithm is learned and trained using the environmental features and state labels of the labeled monitoring data to obtain an initial state evaluation model. The validation set is input into the initial state evaluation model, and the state evaluation model is verified using the unlabeled monitoring data in the validation set until the number of samples with correct verification results in the validation set meets a preset condition, and then the state evaluation model is obtained.

[0110] For the specific limitations of the state monitoring device for aviation glass, reference can be made to the limitations of the state monitoring method for aviation glass in the above text, which will not be elaborated here. Each module in the above state monitoring device for aviation glass can be implemented in whole or in part through software, hardware, and their combinations. The above modules can be embedded in the processor of a computer device in hardware form or be independent of it, or be stored in the memory of the computer device in software form so that the processor can call and execute the operations corresponding to the above modules. It should be noted that the division of modules in the embodiments of the present application is illustrative, only a logical function division, and there may be other division methods in actual implementation.

[0111] In one embodiment, a computer device is further provided. The internal structure diagram of the computer device can be asFigure 11 As shown. The computer device includes a processor, a memory, and a network interface connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile 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 the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for monitoring the state of aircraft glass.

[0112] Those skilled in the art can understand that Figure 11 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0113] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the steps in the above method embodiments are implemented.

[0114] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0115] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0116] In the description of this specification, the descriptions referring to terms such as "one embodiment", "other embodiments", "ideal embodiment", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic descriptions of the above terms do not necessarily refer to the same embodiment or example.

[0117] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0118] The above embodiments only represent several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A method for monitoring the state of aircraft glass, characterized in that, The method includes the following steps: Obtain the monitoring information of the aircraft glass; Input the monitoring information into the state evaluation model to obtain the state evaluation result of the aircraft glass; the state evaluation result is used to evaluate the operating state of the aircraft glass, and the state evaluation model is a prediction model established by learning and training using historical monitoring information. The historical monitoring information includes labeled monitoring data and unlabeled monitoring data, and the labeled monitoring data includes environmental characteristics and state labels; When the state evaluation result is a preset result, send an alarm signal to the alarm device; The establishment process of the state evaluation model includes: Obtain the historical monitoring information of the aircraft glass; Extract features from the historical monitoring information to obtain the environmental characteristics and the state labels; Establish the state evaluation model according to the environmental characteristics and the state labels; The establishment of the state evaluation model according to the environmental characteristics and the state labels includes: Generate a training set using the labeled monitoring data and generate a validation set using the unlabeled monitoring data; Input the training set into the state evaluation algorithm, and use the environmental characteristics and state labels of the labeled monitoring data to learn and train the state evaluation algorithm to obtain an initial state evaluation model; Input the validation set into the initial state evaluation model, and use the unlabeled monitoring data in the validation set to verify the initial state evaluation model until the number of samples with correct verification results in the validation set meets the preset conditions, and obtain the state evaluation model.

2. The method for monitoring the state of the aviation glass according to claim 1, wherein, The obtaining of the historical monitoring information of the aircraft glass includes: Obtain the labeled monitoring data and the unlabeled monitoring data of the aircraft glass.

3. The method for monitoring the state of the aircraft glass according to claim 1, characterized in that, The monitoring information includes temperature information and force information. The obtaining of the monitoring information of the aircraft glass includes: Obtain the temperature information through a temperature sensor and obtain the force information through a force sensor; both the temperature sensor and the force sensor are arranged on the aircraft glass.

4. The method for monitoring the state of the aviation glass according to claim 1, characterized in that, The inputting of the monitoring information into the state evaluation model to obtain the state evaluation result of the aircraft glass includes: Extract features from the monitoring information to obtain environmental characteristics corresponding to the monitoring information; Input the environmental characteristics corresponding to the monitoring information into the state evaluation model, and enable the state evaluation model to predict the operating state of the aircraft glass to obtain the state evaluation result. The state evaluation result includes a normal state, a damaged state, and an abnormal state.

5. The method for monitoring the state of the aviation glass according to claim 1, characterized in that, The preset result includes a damaged state and an abnormal state. The sending of an alarm signal to the alarm device when the state evaluation result is a preset result includes: When the state evaluation result is a damaged state, send a damaged alarm signal to the alarm device; When the state evaluation result is an abnormal state, send an abnormal alarm signal to the alarm device.

6. A state monitoring device for an aviation glass, characterized in that, The device includes: A data acquisition module for obtaining the monitoring information of the aircraft glass; A data processing module, configured to input the monitoring information into a state evaluation model to obtain a state evaluation result of the aviation glass; the state evaluation result is used to evaluate the operating state of the aviation glass, and the state evaluation model is a prediction model established by learning and training using historical monitoring information; An alarm driving module, configured to send an alarm signal to an alarm device when the state evaluation result is a preset result.

7. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images