Aircraft wing monitoring system and aircraft

Abstract

The invention relates to the technical field of aviation, in particular to a wing monitoring system of an aircraft and the aircraft, which are used for sensing vibration and deformation of a wing in high precision and real-time performance and accurately evaluating the state of the wing. The wing monitoring system comprises a sensor system and a monitoring platform which are in communication connection, the sensor system comprises a TENG module, an EMG module and a PENG module, and the sensor system is installed on a wing of an aircraft and used for outputting a first electric signal and a second electric signal representing wing vibration information and a third electric signal representing wing deformation information; and the monitoring platform is used for acquiring the first electric signal, the second electric signal and the third electric signal, analyzing the first electric signal, the second electric signal and the third electric signal based on a pre-trained neural network model, and predicting vibration information and deformation quantity of the wing.

Description

Technical Field

[0001] This application relates to the field of aviation technology, and particularly to a wing monitoring system for an aircraft and an aircraft. Background Art

[0002] With the development of modern aircraft towards higher speeds, lighter structures and higher mission loads, load-bearing components such as wings are subjected to continuous complex aerodynamic loads during flight, and are prone to problems such as structural vibration, deformation and fatigue damage. The aeroelastic response of the wing not only directly affects lift and stability, but may also induce serious consequences such as stall, material microcrack propagation and even structural disintegration.

[0003] Therefore, establishing a high-precision and real-time wing vibration and deformation monitoring mechanism is the key prerequisite for realizing structural health assessment and safety warning. Summary of the Invention

[0004] This application discloses a wing monitoring system for an aircraft and an aircraft, which are used to accurately sense the vibration and deformation of the wing with high precision and in real time, and accurately evaluate the state of the wing.

[0005] To achieve the above object, this application provides the following technical solutions: In a first aspect, this application provides a wing monitoring system for an aircraft, including: a sensor system and a monitoring platform connected by communication, wherein, The sensor system includes a triboelectric nanogenerator (TENG) module, an electromagnetic generator (EMG) module, and a piezoelectric nanogenerator (PENG) module, which are installed on the wing of the aircraft and are used to output a first electrical signal, a second electrical signal characterizing the wing vibration information, and a third electrical signal characterizing the wing deformation information. The TENG module and the EMG module are respectively used to output the first electrical signal and the second electrical signal, and the PENG module is used to output the third electrical signal; The monitoring platform is used to acquire the first electrical signal, the second electrical signal, and the third electrical signal, and based on a pre-trained neural network model, analyze the first electrical signal, the second electrical signal and the third electrical signal to predict the wing vibration information and the amount of deformation.

[0006] The wing monitoring system of the aircraft provided by the embodiment of the present application respectively senses the vibration and deformation of the wing through multiple self-powered modules, so that without an external power source, the vibration information and deformation information of the wing can be accurately distinguished in a complex dynamic environment, realizing high-precision and real-time sensing of the vibration and deformation of the wing. At the same time, on the monitoring platform, based on a pre-trained neural network model, the electrical signals output by the sensor system are analyzed to predict the vibration information and deformation amount of the wing, realizing remote digital evaluation of the dynamic response of the wing structure.

[0007] Further, the pre-trained neural network model is generated by the following method: Obtain training sample data, where each training sample data includes a first sample electrical signal, a second sample electrical signal, a third sample electrical signal, sample vibration information, and a sample deformation amount; Perform the following operations on any training sample data until all the training sample data are processed or the prediction accuracy reaches a preset requirement to generate the neural network model: Preprocess the first sample electrical signal, the second sample electrical signal, and the third sample electrical signal to obtain three groups of time series signals with a preset length; Use a preset convolution kernel to process the three groups of time series signals with a preset length respectively, and extract the time features of each group of time series signals according to the target weights of each sample electrical signal, where the time features represent the relationship between the signal parameters and time in the time series signal; Concatenate the time features of each group of time series signals to obtain a concatenated feature, and extract dynamic evolution features from the concatenated feature through a bidirectional long short-term memory (LSTM) layer, where the dynamic evolution features represent the change relationship of the signal with time in the time series signal; Output estimated vibration information and an estimated deformation amount based on the dynamic evolution features, calculate the prediction error through a preset loss function based on the estimated vibration information, the estimated deformation amount, the sample vibration information, and the sample deformation amount, and adjust the target weights of each sample electrical signal through the backpropagation algorithm, where the preset loss function includes a regularization loss term based on the vibration physical formula.

[0008] Further, the regularization loss term based on the vibration physical formula is as follows Formula 1: Formula 1 Where is the regularization loss term, MSE is the mean square error, represents the vibration acceleration in the estimated vibration information, represents the vibration frequency in the estimated vibration information, It represents the vibration amplitude in the estimated vibration information.

[0009] Further, the preset convolution kernel is a one-dimensional convolution kernel of three different scales.

[0010] Further, the monitoring platform is also used for: displaying the change curves of the first electrical signal, the second electrical signal, and the third electrical signal.

[0011] Further, the monitoring platform is also used for: triggering an alarm prompt when it is determined that the vibration information and / or the amount of deformation meet the preset alarm conditions.

[0012] Further, the TENG module includes: a first electrode, a second electrode, a permanent magnet, a plurality of support columns, and a first load component, where The plurality of support columns are arranged between the first electrode and the second electrode, a cavity is formed between the plurality of support columns, the permanent magnet is placed in the cavity, a first material is arranged on the surface of the permanent magnet, a second material is arranged on the surface of the first electrode opposite to the permanent magnet, a second material or a third material is arranged on the surface of the second electrode opposite to the permanent magnet, the electronegativity of the first material is different from that of the second material, the electronegativity of the first material is different from that of the third material, the first end of the first load component is connected to the first electrode, and the second end is connected to the second electrode.

[0013] Further, the EMG module includes: a coil, a non-magnetic conductive housing, and a second load component. The non-magnetic conductive housing surrounds the permanent magnet and is arranged in the cavity. The coil is wound around the non-magnetic conductive housing. The first end of the second load component is connected to one end of the coil, and the second end is connected to the other end of the coil.

[0014] Further, the PENG module includes: a first piezoelectric unit, a second piezoelectric unit, and a differential circuit. The first piezoelectric unit is fixed to the wing surface by silica gel, the second piezoelectric unit is rigidly fixed to the first piezoelectric unit, and the input ends of the differential circuit are respectively connected to the first piezoelectric unit and the second piezoelectric unit.

[0015] In a second aspect, an embodiment of the present application provides an aircraft, which includes a fuselage, wings, and the wing monitoring system provided in the first aspect of the embodiment of the present application, where The wing monitoring system is used to sense the wing vibration information and deformation information, and predict the wing vibration information and the amount of deformation. Description of the Drawings

[0016] Figure 1Schematic diagram of the architecture of a wing monitoring system for an aircraft provided by an embodiment of the present application; Figure 2 Schematic diagram of the structure of a TENG module provided by an embodiment of the present application; Figure 3 Schematic diagram of the structure of another TENG module provided by an embodiment of the present application; Figure 4 Schematic diagram of the structure of an EMG module provided by an embodiment of the present application; Figure 5 Schematic diagram of the working principle of the TENG module and the EMG module provided by an embodiment of the present application; Figure 6 Schematic diagram of the structure of a PENG module provided by an embodiment of the present application; Figure 7 Schematic diagram of the working principle of the PENG module provided by an embodiment of the present application; Figure 8 Schematic diagram of the integrated structure of a sensor system provided by an embodiment of the present application; Figure 9 Schematic diagram of the integrated structure of another sensor system provided by an embodiment of the present application; Figure 10 Schematic diagram of the signal response characteristics of the TENG module during the process of increasing wind speed provided by an embodiment of the present application; Figure 11 Schematic diagram of the signal response characteristics of the EMG module during the process of increasing wind speed provided by an embodiment of the present application; Figure 12 Schematic diagram of the signal response characteristics of the PENG module during the process of increasing deformation provided by an embodiment of the present application; Figure 13 Schematic diagram of the principle of the training process of the neural network model provided by an embodiment of the present application. Detailed implementation manners

[0017] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0018] The application scenarios described in the embodiments of this application are for more clearly explaining the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those of ordinary skill in the art will know that with the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems. Among them, in the description of this application, unless otherwise specified, "a plurality of" means two or more.

[0019] Before introducing the wing monitoring system and the aircraft provided by the embodiments of this application, for the convenience of understanding, the technical background of the embodiments of this application will be introduced in detail first.

[0020] With the development of modern aircraft towards higher speeds, lighter structures and higher mission loads, load-bearing components such as wings are subjected to continuous complex aerodynamic loads during flight, and are prone to structural vibration, deformation and fatigue damage problems. The aeroelastic response of the wing not only directly affects lift and stability, but may also induce serious consequences such as stall, material microcrack propagation and even structural disintegration.

[0021] Therefore, establishing a high-precision and real-time wing vibration and deformation monitoring mechanism is the key prerequisite for realizing structural health assessment and safety warning.

[0022] In view of this, in the embodiments of this application, a wing monitoring system and an aircraft of an aircraft are provided. The wing monitoring system of the aircraft provided by the embodiments of this application respectively senses the vibration and deformation of the wing through a plurality of self-powered modules, so that without an external power source, the vibration information and deformation information of the wing can be accurately distinguished in a complex dynamic environment, realizing high-precision and real-time sensing of the vibration and deformation of the wing. At the same time, on the monitoring platform, based on a pre-trained neural network model, the electrical signals output by the sensor system are analyzed to predict the vibration information and deformation amount of the wing, realizing remote digital assessment of the dynamic response of the wing structure.

[0023] It should be noted that the wing monitoring system of the aircraft provided by the embodiments of this application can be applied to various types of aircraft, such as fixed-wing aircraft, helicopters, drones, etc., and can also be extended to real-time state sensing and health assessment of flexible structures such as wind turbine blades, bridges, track beams, and ship masts.

[0024] After introducing the background technology of the embodiments of this application, the overall concept of the embodiments of this application will be described below.

[0025] At present, the wings of aircraft face the coupled behavior of vibration and deformation under complex aerodynamic loads during long-term service. This is not only the fundamental cause of material fatigue, structural cracks, and aerodynamic performance degradation, but also directly threatens flight safety and the life assessment of aircraft. However, the existing solutions still have the following technical problems that urgently need to be broken through in terms of sensing principle, structural design, energy supply, and data processing capabilities: 1. The signal modal aliasing is serious, and it is difficult to effectively decouple and identify vibration and deformation.

[0026] Existing sensors can usually only collect single physical modal signals and are easily interfered by the overlap of structural responses, making it difficult to accurately distinguish vibration and deformation effects in complex dynamic environments.

[0027] 2. The structure has strong invasiveness and significant flow interference, making it difficult to meet the high aerodynamic performance requirements.

[0028] Existing sensors need to be destructively embedded or externally attached for installation, which destroys the integrity of the wing surface and causes boundary layer separation, vortex excitation, and a decrease in aerodynamic efficiency.

[0029] 3. Dependent on external power supply systems, it is difficult to achieve distributed deployment and long-term monitoring.

[0030] Existing sensors require external power supply or centralized wiring, increasing system complexity, weight, and reliability risks.

[0031] 4. The signals are seriously interfered, and it is difficult to achieve high-stability and reliability monitoring.

[0032] In high-flow-rate and strong-vibration environments, existing contact sensors have problems such as signal drift, adhesion failure, and response lag.

[0033] 5. Strong dependence on manual operation, with insufficient intelligent recognition accuracy and generalization ability.

[0034] Most traditional solutions rely on manually setting parameters (such as the window length of the Fast Fourier Transform (FFT), filtering frequency bands, etc.) and are difficult to adapt to non-linear and non-stationary vibration-deformation coupling responses.

[0035] To address the above technical problems, the wing monitoring system of an aircraft provided by the embodiments of the present application integrates a TENG module, an EMG module, and a PENG module in the sensor system, constructs a magnetic levitation vibration detection structure and a hard-soft integrated differential deformation detection structure, optimizes the aerodynamic performance through a streamlined shell and a vortex generator, and deploys a neural network model integrating physical constraint learning and an attention mechanism in the monitoring platform to improve signal recognition ability and accurately evaluate the health status of the wing, so as to solve the above technical problems. Specifically: In the wing monitoring system of the aircraft provided by the embodiments of the present application, in terms of the sensor system, vibration information is sensed through the TENG module and the EMG module, and deformation information is sensed through the double-layer piezoelectric unit + differential decoupling mechanism in the PENG module, realizing physical differentiation and high-precision identification of coupled signals under in-situ sensing conditions; the TENG module and the EMG module adopt a magnetic levitation triboelectric-electromagnetic dual power generation structure, combined with a flexible piezoelectric film, to achieve self-powered operation, support multi-point distribution and lightweight deployment, significantly improving system integration and maintenance convenience; moreover, the magnetic levitation structure is adopted to avoid mechanical wear, enhance fatigue resistance, and verify its stability through a 24-hour wind tunnel fatigue test. The signal attenuation rates of TENG and PENG are both better than the prior art level; finally, the TENG module, the EMG module, and the PENG module are integrated in the same housing, and through the integrated design of the streamlined housing and the vortex generator, they can be installed at appropriate positions on the wing to achieve the optimal aerodynamic performance layout, minimizing resistance and increasing lift to the greatest extent, taking into account the monitoring function and aerodynamic stability from the source.

[0036] In terms of the monitoring platform, a neural network model integrating physical constraint learning and attention mechanism is deployed on the monitoring platform to process the electrical signals output by the sensor system, achieving end-to-end, highly robust, and transferable signal recognition capabilities while ensuring the prediction accuracy.

[0037] After introducing the background technology and overall concept of the embodiments of the present application, the wing monitoring system and aircraft provided by the embodiments of the present application will be described in detail below in conjunction with specific embodiments.

[0038] Refer to Figure 1 As shown, it is a schematic architecture diagram of a wing monitoring system of an aircraft in an embodiment of the present application, including: a sensor system 10 and a monitoring platform 11 that are communicatively connected.

[0039] The sensor system 10 includes a TENG module, an EMG module, and a PENG module, which are installed on the wing of the aircraft and are used to output a first electrical signal and a second electrical signal representing the wing vibration information, and a third electrical signal representing the wing deformation information. Among them, the TENG module and the EMG module are respectively used to output the first electrical signal and the second electrical signal, and the PENG module is used to output the third electrical signal; The monitoring platform 11 is used to acquire the first electrical signal, the second electrical signal, and the third electrical signal, and based on a pre-trained neural network model, analyze the first electrical signal, the second electrical signal, and the third electrical signal to predict the vibration information and deformation amount of the wing.

[0040] Among them, the monitoring platform can be a Web-based visualization platform built based on ECharts and jQuery.

[0041] The following will combine specific embodiments to first elaborate in detail on the structures of each module in the sensor system provided in the embodiments of the present application.

[0042] As Figure 2 shown, the TENG module includes: a first electrode 21, a second electrode 22, a permanent magnet 23, a plurality of support columns (not shown in the figure), and a first load component 24. The plurality of support columns are disposed between the first electrode 21 and the second electrode 22. A cavity is formed between the plurality of support columns. The permanent magnet 23 is placed in the cavity. A first material is provided on the surface of the permanent magnet 23. A second material is provided on the surface of the first electrode 21 opposite to the permanent magnet 23. A second material or a third material is provided on the surface of the second electrode 22 opposite to the permanent magnet 23. The electronegativity of the first material is different from that of the second material, and the electronegativity of the first material is different from that of the third material. The first end of the first load component 24 is connected to the first electrode 21, and the second end is connected to the second electrode 22.

[0043] Among them, the first material and the second material can be any pair of material combinations with different electronegativities, such as nylon film, polyamide PA, polytetrafluoroethylene PTFE, fluorinated ethylene propylene copolymer FEP, polyimide Kapton, polyvinylidene fluoride PVDF, etc. Similarly, the first material and the third material can also be any pair of material combinations with different electronegativities, such as nylon film, PA, PTFE, FEP, Kapton, PVDF, etc.

[0044] As Figure 3 shown, in the TENG module of the embodiments of the present application, a four-pole support column (four support columns 30) is used to support the permanent magnet in an equidistant arrangement manner. This structure can be extended to other magnetic arrangement schemes, including but not limited to three-pole, six-pole, or even annular permanent magnet array structures. At the same time, in the embodiments of the present application, a cylindrical permanent magnet is used for the permanent magnet. Of course, it can also be replaced with a spherical, ellipsoidal, or multi-segment laminated structure according to actual vibration response requirements.

[0045] Taking the example that a nylon film is provided on the surface of the permanent magnet, and PTFE films are provided on the surfaces of the first electrode and the second electrode opposite to the permanent magnet, the TENG module in the embodiments of the present application is based on a magnetic levitation design and adopts an up-and-down symmetric triboelectric structure. During the up-and-down movement of the permanent magnet, the nylon film alternately contacts and separates from the upper and lower PTFE films, generating a periodic triboelectric signal. By extracting this triboelectric signal through the first load component, it can be used as an electrical signal characterizing the vibration information of the object.

[0046] During specific implementation, as Figure 4As shown, the EMG module includes: a coil 41, a non-magnetic housing, and a second load component. The non-magnetic housing surrounds the permanent magnet and is disposed within the cavity. The coil 41 is wound around the non-magnetic housing. One end of the second load component is connected to one end of the coil, and the other end is connected to the other end of the coil.

[0047] In practical applications, the coil in the EMG module can be a copper coil. The number of turns of the coil can be adjusted within the range of 1500 ± 100 according to the sensitivity requirements. The coil material can be copper, silver-plated copper wire, alloy wire, or printed conductive ink. Additionally, the magnetic flux cutting path can be enhanced by optimizing the slotting method of the structural housing, adjusting the angle of the support column, designing a spiral magnetic flux guiding groove, etc., to improve the signal response ability under low-amplitude conditions.

[0048] In the EMG module provided by the embodiments of the present application, when an object vibrates, the permanent magnet cuts the magnetic field lines during vibration, and an EMG electrical signal is generated according to Faraday's law of electromagnetic induction. By extracting this EMG electrical signal through the second resistance component, it can be used as an electrical signal characterizing the vibration information of the object.

[0049] Next, in conjunction with Figure 5 the working principles of the TENG module and the EMG module in the sensor system provided by the embodiments of the present application will be described.

[0050] As Figure 5 shown, the initial states of the TENG module and the EMG module are as shown in (A) of Figure 5 When the object vibrates, the permanent magnet generates a periodic vertical movement under the vibration excitation. From the state of (A) in Figure 5 to the state of (B) in Figure 5 , the magnet cuts the copper coil to generate an electromagnetic induction current, and its direction is determined by the magnetic field change. From the state of (B) in Figure 5 to the state of (D) in Figure 5 , the nylon film on the magnet makes contact-separation with the PTFE on the cylinder wall, generating a frictional charge transfer and forming a frictional current. The frictional current and the electromagnetic induction current jointly characterize the vibration characteristics, and their generation process is directly related to the mechanical stimulus.

[0051] Specifically, in implementation, the PENG module provided by the embodiments of the present application, as Figure 6 shown, includes: a first piezoelectric unit 61, a second piezoelectric unit 62, and a differential circuit 63. The first piezoelectric unit 61 is fixed to the wing surface through silica gel. The second piezoelectric unit 62 is rigidly fixed on the first piezoelectric unit 61. The input ends of the differential circuit 63 are respectively connected to the first piezoelectric unit 61 and the second piezoelectric unit 62.

[0052] Among them, both the first piezoelectric unit 61 and the second piezoelectric unit 62 can adopt the form of two electrode layers and one PVDF film layer, and the PVDF film layer is sandwiched between the two electrode layers. The electrode layer material can be copper, aluminum, gold, silver, carbon nanotube ink, etc., and the PVDF film layer can also be replaced with other piezoelectric materials such as PZT piezoelectric ceramics, PVDF-TrFE composite films, BaTiO microfilms, ZnO nanowire arrays, etc.

[0053] In practical applications, the first piezoelectric unit 61 can be embedded in the silicone layer to sense the comprehensive strain of the object, and the second piezoelectric unit 62 can be installed on the rigid upper shell 64 to only respond to the vibration of the object. The electrical signals generated by both are decoupled by the differential circuit 63 to extract the deformation signal.

[0054] It should be noted that the PENG module in the embodiment of the present application includes two layers of piezoelectric units. In other embodiments of the present application, the PENG module can also be extended to a structure with three or more layers to achieve multi-layer sensitization. The embodiment of the present application does not limit the number of piezoelectric units in the PENG module.

[0055] The following combines Figure 7 to illustrate the working principle of the PENG module in the sensor system provided by the embodiment of the present application.

[0056] As Figure 7 shown, the initial state of the PENG module is as Figure 7 shown in (A) in the figure. The double-layer piezoelectric structure is used to synchronously collect deformation and vibration signals. The upper piezoelectric unit is installed on a rigid bottom plate (for example, a PLA rigid bottom plate) and only responds to vibration; the lower piezoelectric unit is embedded in flexible silicone and is sensitive to both vibration and deformation, generating a composite current. The pure deformation signal can be extracted through differential operation. As vibration and deformation occur, the distributed current in the PENG module throughout the process is as Figure 7 shown in (B), (C), and (D) in the figure, and the final output is the differential signal of currents i PENG1 and i PENG2 .

[0057] In practical applications, taking the TENG module and the EMG module as a whole, it and the PENG module can be deployed distributively or integrated and deployed inside a housing.

[0058] In the case where the TENG module, the EMG module, and the PENG module are integrated into the same housing, in order to improve the aerodynamic compatibility of the sensor system in a high-speed flight environment, the embodiment of the present application implements aerodynamic optimization on the housing of the sensor system. Specifically, the housing can adopt a streamlined structure, and a vortex generator structure and / or an air flow guiding channel can also be provided on the housing. The air flow attachment and boundary layer control are optimized through CFD simulation to reduce the air flow separation area at high angles of attack.

[0059] In specific implementation, a streamlined outer shell is adopted for aerodynamic optimization. Multiple front and rear diversion holes, vortex - generating ridges, and curved - surface contraction channels can be designed to match different angle - of - attack flow fields, and their geometric arrangements can be extended to asymmetric hole - arranging, variable - angle adjustable structures, or foldable outer - shell designs. The outer - shell materials can include, but are not limited to, polycarbonate, PETG, carbon - fiber - reinforced composite materials, aerospace - grade PEEK, etc.

[0060] As Figure 8 shown, the TENG module, EMG module, and PENG module are integrated into the same housing 80. The TENG module and EMG module adopt a magnetic - levitation structure 81 with multiple support columns. Specifically, four equally - spaced magnetic columns can be used to support a cylindrical permanent magnet to achieve contactless suspension vibration response; the PENG module serves as the bottom plate 82. Specifically, a soft - hard composite bottom plate can be adopted, with a double - layer PVDF piezoelectric film embedded. One is fixed by silicone to simultaneously sense vibration and deformation, and the other is rigidly fixed to the bottom plate and only responds to vibration, so as to achieve signal decoupling through a differential structure.

[0061] Next, with reference to the top - view, the internal structure when the TENG module, EMG module, and PENG module are integrated into the same housing will be described. As Figure 9 shown, a cavity is formed between four equally - spaced magnetic columns 90. A cylindrical permanent magnet can be placed in the cavity, and a non - magnetic housing 91 is also arranged in the cavity. Coils can be wound on the non - magnetic housing 91.

[0062] Next, with reference to Figures 10 - 12 , the wind - tunnel experiment verification results of each module in the sensor system provided by the embodiments of the present application will be described.

[0063] As Figure 10 shown, Figure 10 shows the signal - response characteristics of the TENG module during the increasing - wind - speed process. From 9.6 m / s to 36.9 m / s, the signal intensity increases significantly, indicating that the sensor system is sensitive to changes in the vibration state. Among them, the TENG signal increases significantly after 20.9 m / s, characterizing the critical amplitude triggering the contact layer.

[0064] As Figure 11 shown, Figure 11 shows the signal - response characteristics of the EMG module during the increasing - wind - speed process. From 9.6 m / s to 36.9 m / s, the signal intensity increases significantly, indicating that the sensor system is sensitive to changes in the vibration state.

[0065] As Figure 12 shown, Figure 12It shows the voltage response of the PENG module during the process of the deformation amount ranging from 0 to 10 mm. The signal amplitude shows a significant linear increase, verifying the deformation perception ability of the PVDF film and the reliability of the decoupling structure.

[0066] The above has introduced the sensor system in the wing monitoring system of the aircraft provided by the embodiments of the present application in combination with specific embodiments. Next, the monitoring platform will be described in detail in combination with specific embodiments.

[0067] In the embodiments of the present application, a multi-scale physical perception attention network is constructed in the monitoring platform to perform regression inference training on vibration information and deformation amount. A frequency-deformation amount joint training mechanism is adopted, so that the inference accuracy of the neural network model is improved, and the inference curve is highly consistent with the real signal.

[0068] When training the neural network model, first obtain training sample data. Each training sample data includes at least a first sample electrical signal, a second sample electrical signal, a third sample electrical signal, sample vibration information, and sample deformation amount. The specific training process of the neural network model is as Figure 13 shown. For any training sample data, the following operations are performed until all training sample data are processed or the prediction accuracy reaches the preset requirement, and a neural network model is generated: Operation 1: Preprocessing. That is, preprocess the first sample electrical signal (TENG signal), the second sample electrical signal (EMG signal), and the third sample electrical signal (PENG signal) to obtain three groups of time series signals with a preset length.

[0069] Among them, the preprocessing includes normalization processing, band-pass filtering, etc. to ensure the consistency and stability of the model input data. The specific methods of normalization processing and band-pass filtering can adopt the methods in related technologies, and the embodiments of the present application do not limit this. The preset length can be set according to experience. For example, the preset length is 15 seconds.

[0070] Operation 2: Feature extraction. Specifically, first, use preset convolution kernels to process the three groups of time series signals with a preset length respectively. According to the target weights of each sample electrical signal, extract the time features of each group of time series signals to capture short-term and medium- and long-term physical response patterns and fully express the relationship between the signal parameters (such as frequency) and time in each electrical signal. Among them, the time feature characterizes the relationship between the signal parameters and time in the time series signal.

[0071] Among them, the preset convolution kernels are three groups of 1D convolution kernels with different scales. For example, the sizes of the preset convolution kernels are 10, 50, and 100. Use the convolution kernel with a size of 10 to process the first sample electrical signal, use the convolution kernel with a size of 50 to process the second sample electrical signal, and use the convolution kernel with a size of 100 to process the third sample electrical signal.

[0072] Secondly, splice the time characteristics of each group of timing signals to obtain spliced features, and extract dynamic evolution features from the spliced features through a bidirectional LSTM layer to enhance the model's perception ability and expression dimension of timing information. Among them, the dynamic evolution features represent the variation relationship of signals over time in the timing signals.

[0073] In specific implementation, the bidirectional LSTM network layer can be implemented in the manner of related technologies, and this application embodiment does not make any limitations in this regard.

[0074] Operation 3: Prediction. Specifically, based on the dynamic evolution features, estimated vibration information and estimated deformation amounts are output. Based on the estimated vibration information, estimated deformation amounts, sample vibration information, and sample deformation amounts, the prediction error is calculated through a preset loss function, and the target weights of each sample electrical signal are adjusted through the backpropagation algorithm. Among them, the preset loss function includes a regularization loss term based on the vibration physical formula.

[0075] The regularization loss term based on the vibration physical formula is as follows Formula 1: Formula 1 Among them, is the regularization loss term, MSE is the mean square error, represents the vibration acceleration in the estimated vibration information, represents the vibration frequency in the estimated vibration information, represents the vibration amplitude in the estimated vibration information.

[0076] It should be noted that the above is the neural network model of this application embodiment. In other embodiments of this application, the deep learning inference model can be extended to models of other structural forms, including but not limited to the Transformer series, temporal convolutional network, lightweight hybrid network (such as MobileNet+LSTM), etc. The input signal can also be extended to image signals, vibration sound signals, or structural stress map data, etc. according to the application scenario; the predicted value can also be extended from vibration information and deformation amounts to fatigue accumulation values, crack risk scores, and structural health indexes, etc.

[0077] In practical applications, after the neural network model is generated, the neural network model can be deployed on the monitoring platform to parse the first electrical signal, second electrical signal, and third electrical signal obtained by the monitoring platform from the sensor system, so as to predict the vibration information and deformation amounts of the wing.

[0078] It should be noted that when the sensor system transmits the first electrical signal, the second electrical signal, and the third electrical signal to the monitoring platform via wireless transmission, it is also necessary to convert the electrical signals into digital signals and use a specific frequency band for transmission. For example, it uses the 433 MHz frequency band for transmission. This frequency band has the advantages of strong penetration ability, high anti-interference ability, and long transmission distance (up to 300 m), and is suitable for deployment in complex flight platform environments.

[0079] In some embodiments, the monitoring platform provided by the embodiments of the present application can also implement the following functions, such as displaying the change curves of the first electrical signal, the second electrical signal, and the third electrical signal; providing FFT spectrograms and power distribution diagrams; providing historical data query and export services; dynamically displaying the health index of the wing structure; and triggering an alarm prompt when it is determined that the vibration information and / or the deformation amount meet the preset alarm conditions.

[0080] Based on the same concept, the embodiments of the present application also provide an aircraft, including a fuselage, a wing, and the wing monitoring system provided by the embodiments of the present application. The wing monitoring system is used to sense the wing vibration information and deformation information, and predict the wing vibration information and deformation amount.

[0081] The aircraft provided by the embodiments of the present application can accurately distinguish the wing vibration information and deformation information in a complex dynamic environment by carrying the wing monitoring system provided by the embodiments of the present application, realize high-precision and real-time perception of the wing vibration and deformation, and monitor and evaluate the health status of the wing.

[0082] Further, after the TENG module and the EMG module in the sensor system of the wing monitoring system are integrated, they are distributed on the wing with the PENG module, or the TENG module, the EMG module, and the PENG module are integrated and arranged on the wing.

[0083] Further, the sensor system can be installed at any position on the wing, and the lift can be increased by up to 1.75% at most, and the drag can be reduced by up to 0.8% at most. When the distance between the installation position of the sensor system and the leading edge point of the wing is equal to 30% of the wing chord length, the lift can be increased by 1.75% and the drag is reduced by 0.8%.

[0084] The above are only the specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An aircraft wing monitoring system, characterized in that, Including: A sensor system and a monitoring platform that are communicatively connected, wherein the sensor system includes a triboelectric nanogenerator (TENG) module, an electromagnetic generator (EMG) module, and a piezoelectric nanogenerator (PENG) module, which are installed on the wing of the aircraft and are used to output a first electrical signal, a second electrical signal representing the wing vibration information, and a third electrical signal representing the wing deformation information. Among them, the TENG module and the EMG module are respectively used to output the first electrical signal and the second electrical signal, and the PENG module is used to output the third electrical signal; the monitoring platform is used to acquire the first electrical signal, the second electrical signal, and the third electrical signal, and based on a pre-trained neural network model, analyze the first electrical signal, the second electrical signal, and the third electrical signal to predict the vibration information and deformation amount of the wing.

2. The system according to claim 1, wherein The pre-trained neural network model is generated by the following method: Obtain training sample data, and each training sample data includes a first sample electrical signal, a second sample electrical signal, a third sample electrical signal, sample vibration information, and a sample deformation amount; Perform the following operations on any training sample data until all the training sample data are processed or the prediction accuracy reaches a preset requirement to generate the neural network model: Preprocess the first sample electrical signal, the second sample electrical signal, and the third sample electrical signal to obtain three groups of time series signals with a preset length; Use preset convolution kernels to process the three groups of time series signals with a preset length respectively, and extract the time features of each group of time series signals according to the target weights of each sample electrical signal. The time features represent the relationship between the signal parameters and time in the time series signal; Concatenate the time features of each group of time series signals to obtain a concatenated feature, and extract the dynamic evolution feature from the concatenated feature through a bidirectional long short-term memory (LSTM) layer. The dynamic evolution feature represents the change relationship of the signal with time in the time series signal; Output the estimated vibration information and estimated deformation amount based on the dynamic evolution feature, calculate the prediction error through a preset loss function based on the estimated vibration information, estimated deformation amount, sample vibration information, and sample deformation amount, and adjust the target weights of each sample electrical signal through the backpropagation algorithm. Among them, the preset loss function includes a regularization loss term based on the vibration physical formula.

3. The system according to claim 2, wherein The regularization loss term based on the vibration physical formula is as follows formula one: Formula 1 wherein, is the regularization loss term, and MSE is the mean square error, represents the vibration acceleration in the predicted vibration information, represents the vibration frequency in the predicted vibration information, represents the vibration amplitude in the predicted vibration information.

4. The system according to claim 2, wherein The preset convolution kernels are three groups of 1D convolution kernels with different scales.

5. The system according to claim 1, wherein The monitoring platform is further used to: display the change curves of the first electrical signal, the second electrical signal, and the third electrical signal.

6. The system according to claim 1, wherein The monitoring platform is further used to: trigger an alarm prompt when it is determined that the vibration information and / or deformation amount meet the preset alarm conditions.

7. The system according to any one of claims 1-6, characterized in that, The TENG module includes: a first electrode, a second electrode, a permanent magnet, a plurality of support columns, and a first load component, wherein The plurality of support columns are disposed between the first electrode and the second electrode, a cavity is formed between the plurality of support columns, the permanent magnet is disposed in the cavity, a first material is disposed on the surface of the permanent magnet, a second material is disposed on the surface of the first electrode opposite to the permanent magnet, a second material or a third material is disposed on the surface of the second electrode opposite to the permanent magnet, the first material and the second material have different electronegativities, the first material and the third material have different electronegativities, a first end of the first load component is connected to the first electrode, and a second end is connected to the second electrode.

8. The system according to claim 7, characterized in that, The EMG module includes: a coil, a non-magnetic housing, and a second load component. The non-magnetic housing surrounds the permanent magnet and is disposed in the cavity. The coil is wound around the non-magnetic housing. A first end of the second load component is connected to one end of the coil, and a second end is connected to the other end of the coil.

9. The system according to claim 1, characterized in that, The PENG module includes: a first piezoelectric unit, a second piezoelectric unit, and a differential circuit. The first piezoelectric unit is fixed to the surface of the wing by silica gel. The second piezoelectric unit is rigidly fixed to the first piezoelectric unit. Input ends of the differential circuit are respectively connected to the first piezoelectric unit and the second piezoelectric unit.

10. An aircraft, characterized in that, The aircraft includes a fuselage, a wing, and the wing monitoring system according to any one of claims 1-9, wherein The wing monitoring system is configured to sense the wing vibration information and deformation information, and predict the wing vibration information and deformation amount.

Images