Aircraft spectrum feature library construction method and system based on eddy current detection

Abstract

The invention provides an aircraft spectrum feature library construction method and system based on eddy current detection. The method comprises the following steps: firstly, acquiring an unsteady state pressure signal of an aircraft in each flight state, and then repeatedly performing joint fusion processing on the unsteady state pressure signal of each flight state and an electromagnetic scattering signal of the aircraft to generate an eddy current electromagnetic spectrum data set corresponding to different flight states; the method comprises the steps that firstly, an eddy current electromagnetic spectrum data set is obtained, then structured organization is conducted on the eddy current electromagnetic spectrum data set according to configuration features of the aircraft, a spectrum feature set with an incidence relation is generated, finally, systematic arrangement is conducted on the spectrum feature set according to flight state parameters, and a spectrum feature library of the aircraft is constructed; according to the technical scheme provided by the invention, the characterization precision and integrity of the feature library on the real physical characteristics of the aircraft are improved, and continuous and uninterrupted data support is provided for analysis, identification and prediction of the aircraft in various states.

Description

Technical Field

[0001] This application relates to the field of feature library construction technology, and in particular to a method and system for constructing a spectrum feature library for aircraft based on eddy current detection. Background Technology

[0002] In the fields of aircraft design, testing and condition monitoring, building a high-fidelity spectral feature library is of great significance for achieving accurate aerodynamic characteristic analysis, stealth performance evaluation and fault diagnosis. Traditional single physical field features are difficult to fully reflect the true state of an aircraft in a complex cross-domain coupling environment.

[0003] Currently, there is a scheme for constructing a feature library for aircraft in the existing technology. It collects structural vibration signals by deploying a sensor array on the surface of the aircraft and simultaneously records the scattered echo of the airborne radar. The method first extracts features from the vibration signal and the radar echo to obtain modal feature vectors and electromagnetic feature vectors, respectively. Then, the two types of feature vectors are concatenated to form a joint feature vector, which is then classified and stored according to flight parameters to finally construct the feature library.

[0004] However, the existing solutions mentioned above have obvious drawbacks. The method only focuses on the simple splicing of features at the signal level and fails to reveal the intrinsic coupling mechanism between the surface pulsating pressure caused by aerodynamics and the electromagnetic scattering physical field. Due to the lack of correlation organization based on the aerodynamic layout of the aircraft, the constructed feature library is essentially a discrete set of feature vectors. It fails to reflect the mutual influence of various components of the aircraft under the real airflow path, which limits the physical representation ability of the feature library and its extrapolation performance under complex conditions. Summary of the Invention

[0005] This application provides a method and system for constructing a spectrum feature library for aircraft based on eddy current detection, in order to solve the problem that the existing technology has insufficient physical characterization ability of the feature library and cannot reflect the actual airflow influence relationship between components due to only shallow feature splicing of aerodynamic effects and electromagnetic scattering characteristics.

[0006] Firstly, this application provides a method for constructing a spacecraft spectral feature library based on eddy current detection, including:

[0007] The unsteady pressure signal generated by the surface airflow of the aircraft in multiple flight states is collected by a pressure sensing unit installed on the surface of the aircraft, and the unsteady pressure signal of the aircraft in each flight state is obtained.

[0008] The unsteady pressure signal of each flight state is repeatedly subjected to joint fusion processing with the electromagnetic scattering signal of the aircraft itself to generate eddy current electromagnetic spectrum datasets corresponding to different flight states.

[0009] The eddy current electromagnetic spectrum dataset is structured and organized according to the configuration characteristics of the aircraft to generate a group of spectrum features with correlations.

[0010] The spectral feature groups are systematically arranged according to flight state parameters to construct the spectral feature library of the aircraft.

[0011] Optionally, a pressure sensing unit disposed on the surface of the aircraft collects unsteady pressure signals generated by surface airflow in multiple flight states, obtaining the unsteady pressure signal of the aircraft in each flight state, including:

[0012] In the aerodynamic shape of the aircraft, multiple pressure sensing units are arranged on the leading edge of the wing, the surface of the flaps and the root of the vertical tail.

[0013] The pressure sensing unit is controlled to synchronously record the air pressure change waveform caused by surface airflow stripping when the aircraft enters the predetermined flight state;

[0014] From the air pressure change waveform recorded by each of the pressure sensing units, extract the pressure signal segment corresponding to the stable segment of the current flight state of the aircraft;

[0015] The pressure signal segments captured by different pressure sensing units at the same time are combined to form the unsteady pressure signal of the current flight state.

[0016] Optionally, the unsteady pressure signal for each flight state is repeatedly subjected to joint fusion processing with the electromagnetic scattering signal of the aircraft itself to generate an eddy current electromagnetic spectrum dataset corresponding to different flight states, including:

[0017] The unsteady pressure signal is converted from the time domain to the frequency domain to obtain the pressure spectrum;

[0018] The electromagnetic scattering signal is converted from the time domain to the frequency domain to obtain the electromagnetic spectrum;

[0019] The pressure spectrum is multiplied by all amplitude values ​​in the electromagnetic spectrum corresponding to the same frequency point to generate a fused spectrum;

[0020] The process of converting from the time domain to the generated fused spectrum is repeated for each flight state, and the fused spectra corresponding to all flight states are integrated to obtain the eddy current electromagnetic spectrum dataset.

[0021] Optionally, the pressure spectrum is multiplied by all amplitude values ​​in the electromagnetic spectrum corresponding to the same frequency point to generate a fused spectrum, including:

[0022] Read the first amplitude value at the first frequency point in the pressure spectrum;

[0023] Find a second frequency point in the electromagnetic spectrum that is the same as the first frequency point, and read the second amplitude value of the second frequency point;

[0024] The first amplitude value and the second amplitude value are multiplied to obtain the fused amplitude value at the first frequency point;

[0025] According to a preset order, the operations of reading the first amplitude value, reading the second amplitude value, and performing numerical multiplication are repeated for each frequency point in the pressure spectrum and electromagnetic spectrum until all frequency points have been processed.

[0026] The fusion amplitude values ​​calculated for each frequency point are arranged in the corresponding frequency order to form a complete fusion spectrum.

[0027] Optionally, the eddy current electromagnetic spectrum dataset is structured according to the configuration characteristics of the aircraft to generate a group of spectrum features with correlations, including:

[0028] The wings, tail, and control surfaces of the aircraft are identified as the main configuration partitions.

[0029] Each fused spectrum in the eddy current electromagnetic spectrum dataset is categorized on the surface of the aircraft according to the main configuration partition to which it belongs, based on the pressure sensing unit used when acquiring the fused spectrum.

[0030] Within the same primary configuration partition, fused spectra that meet preset conditions are combined to form a partitioned spectrum group;

[0031] Based on the aerodynamic layout of the aircraft, the airflow influence relationship between different main configuration zones is determined;

[0032] Based on the airflow influence relationship, multiple correlated partition spectrum groups are combined to generate a spectrum feature group with correlation.

[0033] Optionally, based on the airflow influence relationship, multiple correlated partition spectrum groups are combined to generate a spectrum feature group with correlation, including:

[0034] The airflow path of the aircraft during flight is analyzed, from the leading edge of the wing to the trailing edge of the wing and then to the surface of the tail. The wing section and the tail section are identified as related sections with upstream and downstream influence.

[0035] The partition spectrum groups belonging to the associated partition are connected in series according to the order of the airflow path;

[0036] In the series connection, a correspondence is established between the output frequency characteristics of the wing partition spectrum group and the input frequency characteristics of the tail partition spectrum group;

[0037] Based on the aforementioned correspondence, the wing partition spectrum group and the tail partition spectrum group are combined into a cross-partition joint spectrum group.

[0038] The series connection and merging operation is repeated for all associated partitions on the aircraft that have upstream and downstream influence relationships to generate the associated spectral feature groups.

[0039] Optionally, the spectral feature groups are systematically arranged according to flight state parameters to construct the spectral feature library of the aircraft, including:

[0040] Determine the range of the flight state parameters, wherein the flight state parameters include flight speed parameters and flight attitude parameters;

[0041] A two-dimensional parameter grid is constructed using the flight speed parameter as the first dimension and the flight attitude parameter as the second dimension.

[0042] The spectral feature set is placed into the grid cell in the two-dimensional parameter grid that corresponds to the actual flight state parameter that generated the spectral feature set;

[0043] For grid cells where no spectral feature set falls, fill them according to the spectral feature sets in adjacent grid cells;

[0044] The contents of all grid cells are integrated to form the spectral feature library of the aircraft.

[0045] Secondly, this application provides a system for constructing a spacecraft spectral feature library based on eddy current detection, including:

[0046] The acquisition module is used to acquire the unsteady pressure signal generated by the surface airflow of the aircraft in multiple flight states through a pressure sensing unit set on the surface of the aircraft, and obtain the unsteady pressure signal of the aircraft in each flight state;

[0047] The processing module is used to repeatedly perform joint fusion processing on the unsteady pressure signal of each flight state and the electromagnetic scattering signal of the aircraft itself to generate eddy current electromagnetic spectrum datasets corresponding to different flight states.

[0048] An organization module is used to structure the eddy current electromagnetic spectrum dataset according to the configuration characteristics of the aircraft, and generate spectrum feature groups with correlation relationships.

[0049] The module is used to systematically arrange the spectral feature groups according to flight state parameters to build the spectral feature library of the aircraft.

[0050] Thirdly, this application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the method for constructing an aircraft spectrum feature library based on eddy current detection as described in the first aspect above.

[0051] Fourthly, this application provides a computer storage medium storing a computer program, which, when executed by a computer, implements a method for constructing an aircraft spectrum feature library based on eddy current detection as described in the first aspect.

[0052] This application first collects unsteady pressure signals caused by airflow on the aircraft surface and fuses them with the aircraft's own electromagnetic scattering signals, achieving deep coupling of aerodynamic effects and electromagnetic scattering characteristics at the data level. Second, based on the aircraft's configuration characteristics, the fused data is structured and organized, and finally systematically arranged according to flight state parameters. This makes the constructed spectral feature library not only contain cross-physical field collaborative information, but also reflect the structural correlation and state continuity between components, significantly improving the accuracy and completeness of the feature library's representation of the aircraft's true physical characteristics.

[0053] Furthermore, by constructing a two-dimensional parametric grid with flight speed and flight attitude as dimensions, and mapping spectral feature groups to corresponding grid cells, the discretized systematic arrangement of feature data in the flight state space is realized. Then, by filling empty grid cells based on adjacent features, the continuity and completeness of the feature library in the parameter space are effectively guaranteed, so that the final feature library can seamlessly cover the entire flight envelope, providing continuous and uninterrupted data support for the analysis, identification and prediction of aircraft in various states.

[0054] These or other aspects of this application will become more apparent in the following description of the embodiments. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 A flowchart of a method for constructing a spacecraft spectral feature library based on eddy current detection, as provided in this application, is shown.

[0057] Figure 2 A schematic diagram of the structure of a spacecraft spectral feature library construction system based on eddy current detection provided in this application is shown;

[0058] Figure 3 A schematic diagram of the structure of a computing device provided in this application is shown. Detailed Implementation

[0059] To enable those skilled in the art to better understand the present application, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0060] In some of the processes described in the specification, claims, and accompanying drawings of this application, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not themselves represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a chronological order, nor do they limit "first" and "second" to different types.

[0061] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0062] Figure 1 This application provides a flowchart of a method for constructing a spacecraft spectral feature library based on eddy current detection, as shown in the flowchart. Figure 1 As shown, the method includes:

[0063] Step 101: Collect the unsteady pressure signals generated by surface airflow in multiple flight states of the aircraft by a pressure sensing unit installed on the surface of the aircraft, and obtain the unsteady pressure signal of the aircraft in each flight state.

[0064] Optionally, step 101 may specifically include:

[0065] Step 1011: In the aerodynamic shape of the aircraft, multiple pressure sensing units are arranged on the leading edge of the wing, the surface of the flaps and the root of the vertical tail.

[0066] Step 1012: Control the pressure sensing unit to synchronously record the air pressure change waveform caused by surface airflow stripping when the aircraft enters the predetermined flight state;

[0067] Step 1013: Extract the pressure signal segment corresponding to the stable segment of the current flight state of the aircraft from the air pressure change waveform recorded by each pressure sensing unit.

[0068] Step 1014: Combine the pressure signal segments captured by different pressure sensing units at the same time to form the unsteady pressure signal of the current flight state.

[0069] In this step, the pressure sensing unit refers to a sensor device installed on the surface of the aircraft body to sense and record minute fluctuations in local air pressure. It is used to convert physical pressure signals into recordable electrical signals, which are obtained by deploying the sensor at key aerodynamic locations on the aircraft.

[0070] Multiple flight states refer to the various stable operating points of an aircraft during flight with different flight speeds and attitudes. These states are used to cover different aerodynamic environments of the aircraft and are obtained by setting different combinations of flight speed and attitude parameters.

[0071] Unsteady pressure signals generated by surface airflow refer to signals in which the pressure on the surface of an aircraft changes rapidly and irregularly over time due to phenomena such as separation and vortex. They are used to characterize the dynamic aerodynamic loads on the surface of an aircraft and are obtained by collecting and combining the waveforms of air pressure changes through a pressure sensing unit.

[0072] The predetermined flight state refers to a flight state with specific flight speed and attitude parameters that is pre-planned before data acquisition. It is used to ensure the representativeness and systematic nature of the acquired data and is obtained through flight mission planning.

[0073] The air pressure change waveform caused by surface airflow stripping refers to the original recorded curve of the pressure change over time near the separation zone when the airflow separates over the surface of the aircraft. It is used to directly reflect the unsteady characteristics of the local airflow and is synchronously recorded by the pressure sensing unit when the aircraft is in a predetermined flight state.

[0074] The pressure signal segment corresponding to the stable segment of the current flight state of the aircraft refers to the signal portion extracted from the recorded air pressure change waveform during the time interval in which the aircraft's flight parameters remain stable. It is used to exclude transitional data during state transitions to ensure data purity. It is obtained by analyzing and extracting the complete waveform based on timestamps.

[0075] In this step, firstly, based on the aircraft's aerodynamic design, multiple pressure sensing units are installed at key locations sensitive to airflow changes, such as the wing leading edge, flap surfaces, and vertical tail root, to complete the physical deployment of the sensor network. Secondly, the flight control system controls the aircraft to enter a predetermined flight state (e.g., a specific Mach number and angle of attack), and in this state, all the deployed pressure sensing units are synchronously triggered to start working, recording the air pressure change waveform caused by surface airflow stripping, ensuring that all measurement data are strictly synchronized in time. Next, by analyzing the flight parameter records, the time period during which the current flight state remains stable is determined, and based on the timestamp corresponding to this time period, the pressure signal segment corresponding to the stable segment is extracted from the complete air pressure change waveform recorded by each pressure sensing unit to eliminate unstable data during transition processes such as takeoff, climb, or maneuvering. Finally, by collecting and combining the pressure signal segments extracted from pressure sensing units at all different locations at the same time according to their spatial position, a complete unsteady-state pressure signal that comprehensively reflects the surface pressure distribution of the aircraft in the current flight state is formed.

[0076] For example, technicians installed dozens of highly dynamic response miniature pressure sensors (i.e., pressure sensing units) on the leading edge of the wing, the surface of the flaps, and the root of the vertical tail of a certain type of demonstrator aircraft (hereinafter referred to as "Aircraft A"). When Aircraft A enters a predetermined flight state (e.g., altitude H1, Mach number M1, angle of attack α1) in the test airspace according to a preset program and maintains stable flight, the ground control station issues a command to simultaneously activate all these sensors. The sensors record the waveform of air pressure change on the surface of the aircraft caused by airflow separation. After the data is retrieved, the technicians extract (e.g.) 10 seconds of data from the stable level flight phase of Aircraft A in the (M1, α1) state based on the flight parameter data. They extract the pressure signal segment of this 10 seconds from the complete record of each sensor and finally combine the signal segments of all sensors within this 10 seconds according to their spatial positions to form the non-steady-state pressure signal dataset of Aircraft A in this specific flight state.

[0077] This step involves deploying a sensor network at key locations sensitive to airflow changes and simultaneously acquiring high-fidelity raw pressure waveforms under various predetermined flight conditions. After removing transition segments and spatially combining multiple signals, a clean signal is obtained that accurately and comprehensively reflects the spatial distribution of dynamic surface pressure of the aircraft under different flight conditions. This provides a high-quality and highly reliable aerodynamic data foundation for subsequent cross-domain signal fusion and feature library construction.

[0078] Step 102: Repeatedly perform joint fusion processing on the unsteady pressure signal of each flight state and the electromagnetic scattering signal of the aircraft itself to generate eddy current electromagnetic spectrum datasets corresponding to different flight states.

[0079] Optionally, step 102 may specifically include:

[0080] Step 1021: Convert the unsteady pressure signal from the time domain to the frequency domain to obtain the pressure spectrum;

[0081] Step 1022: Convert the electromagnetic scattering signal from the time domain to the frequency domain to obtain the electromagnetic spectrum;

[0082] Step 1023: Multiply the pressure spectrum with all amplitude values ​​in the electromagnetic spectrum corresponding to the same frequency point to generate a fused spectrum;

[0083] Optionally, step 1023 may specifically include:

[0084] Read the first amplitude value of the first frequency point in the pressure spectrum; find the second frequency point in the electromagnetic spectrum that is the same as the first frequency point, and read the second amplitude value of the second frequency point; perform a numerical multiplication operation on the first amplitude value and the second amplitude value to obtain the fused amplitude value of the first frequency point; repeat the operation of reading the first amplitude value, reading the second amplitude value and performing the numerical multiplication operation on each frequency point in the pressure spectrum and the electromagnetic spectrum in a preset order until all frequency points have been processed; arrange the fused amplitude values ​​calculated for each frequency point according to the corresponding frequency order to form a complete fused spectrum.

[0085] Step 1024: Repeat the process of converting from the time domain to the generated fused spectrum for each flight state, and integrate the fused spectra corresponding to all flight states to obtain the eddy current electromagnetic spectrum dataset.

[0086] In this step, the electromagnetic scattering signal of the aircraft itself refers to the reflected echo signal generated by the aircraft body to the electromagnetic waves irradiated by the radar during flight. It is used to characterize the electromagnetic scattering characteristics of the aircraft and is collected by airborne or ground radar systems.

[0087] Eddy current electromagnetic spectrum datasets refer to datasets containing multiple flight states, where the data for each state is a collection of fused spectra. These datasets are used to systematically characterize the coupling relationship between aerodynamic and electromagnetic properties under different flight states. The datasets are obtained by repeatedly performing signal conversion and fusion operations on all flight states.

[0088] Pressure spectrum refers to the form of an unsteady pressure signal after conversion from the time domain to the frequency domain. It shows the intensity distribution of different frequency components in the signal and is used to analyze the frequency characteristics of aerodynamic pressure. It is obtained by processing the unsteady pressure signal through time-frequency conversion techniques such as Fourier transform.

[0089] The electromagnetic spectrum refers to the form of an electromagnetic scattering signal after it has been converted from the time domain to the frequency domain. It shows the intensity distribution of different frequency components in the signal and is used to analyze the frequency characteristics of electromagnetic scattering. It is obtained by processing the electromagnetic scattering signal through time-frequency conversion techniques such as Fourier transform.

[0090] Amplitude refers to the strength of a signal at a specific frequency in the spectrum. It is used to quantify the energy strength of that frequency component and is obtained by reading the vertical coordinate value of the corresponding frequency point on the spectrum.

[0091] The fused spectrum refers to the new spectrum obtained by multiplying the amplitude values ​​of the pressure spectrum and the electromagnetic spectrum at each frequency point. It is used to characterize the coupling effect of aerodynamic pressure and electromagnetic scattering in the frequency domain. It is obtained by multiplying the amplitude values ​​of corresponding frequency points in the two spectra point by point.

[0092] The fusion amplitude value refers to the new amplitude value obtained by multiplying the amplitude value of the pressure spectrum and the amplitude value of the electromagnetic spectrum at a certain frequency point when generating the fusion spectrum. It is used to represent the combined strength of the aerodynamic and electromagnetic signals at that frequency point and is obtained through numerical multiplication.

[0093] Preset order refers to the fixed sequence followed when processing all frequency points in the spectrum, from one frequency to another, to ensure that each frequency point is processed without repetition or omission. It is usually achieved through a linear sequence from low frequency to high frequency or from high frequency to low frequency.

[0094] In this step, firstly, the unsteady pressure signal under each flight state is converted from the time domain to the frequency domain using Fast Fourier Transform (FFT) technology, and the pressure spectrum displaying the intensity of each frequency component is calculated. Secondly, the electromagnetic scattering signal of the aircraft itself, synchronously acquired under the same flight state, is converted from the time domain to the frequency domain using FFT technology, and the corresponding electromagnetic spectrum is calculated.

[0095] Secondly, the pressure spectrum and electromagnetic spectrum are processed by a point-by-point multiplication fusion algorithm. Starting from the first frequency point (lowest frequency) of the pressure spectrum, its amplitude value is read as the first amplitude value; at the same time, a point with the same frequency is found in the electromagnetic spectrum, and its amplitude value is read as the second amplitude value; then the two amplitude values ​​are multiplied to obtain the fused amplitude value of that frequency point; the above reading and multiplication operation is repeated for each frequency point in the spectrum in a preset order from low frequency to high frequency until all frequency points have been processed.

[0096] Next, the fused amplitude values ​​calculated for all frequency points are arranged in order from low to high according to their corresponding frequencies to form a complete fused spectrum. Through a loop control process, the above process from time-frequency conversion to generating the fused spectrum is repeated for each flight state. Finally, the fused spectra generated by all flight states are gathered together to construct an eddy current electromagnetic spectrum dataset containing fused data of all flight states.

[0097] Following the embodiment of step 101, while aircraft A acquires unsteady-state pressure signals in state (altitude H1, Mach number M1, angle of attack α1), a matching measurement radar simultaneously records the electromagnetic scattering signals of aircraft A in this state. During data processing, a fast Fourier transform algorithm is first used to convert this 10-second unsteady-state pressure signal into a pressure spectrum, which shows the intensity of pressure fluctuations at different frequencies. Simultaneously, a fast Fourier transform is also performed on the synchronous electromagnetic scattering signal to obtain the electromagnetic spectrum. Then, a processing program is developed that starts from the lowest frequency of the pressure spectrum (…). Starting at 0Hz, the amplitude value (let's say Pa1) is read, and the amplitude value (let's say Pe1) is read at the same frequency point (0Hz) in the electromagnetic spectrum. Pa1 and Pe1 are multiplied to get the fused amplitude value Pf1 at 0Hz. The program then processes the next frequency point (e.g., 1Hz) in sequence, repeating this process until all frequency points are processed (e.g., the highest frequency 500Hz). Finally, the fused amplitude values ​​of all frequency points are arranged in sequence to form the fused spectrum of this flight state. This process is performed on all other predetermined flight states (e.g., M2 / α2, M3 / α3, etc.) within the test envelope of aircraft A. All the obtained fused spectra are stored together to form the eddy current electromagnetic spectrum dataset of aircraft A.

[0098] This step involves converting aerodynamic pressure signals and electromagnetic scattering signals to the frequency domain and then performing deep fusion within the frequency domain through the core operation of amplitude multiplication. This results in a strong correlation between signals with different physical properties in the frequency dimension. The final dataset not only retains their respective characteristics but also highlights the synergistic relationship between the two, laying a solid data foundation for the subsequent construction of a feature library that can profoundly reflect the physical essence of aerodynamic-electromagnetic coupling in aircraft.

[0099] Step 103: Organize the eddy current electromagnetic spectrum dataset in a structured manner according to the configuration characteristics of the aircraft to generate a spectrum feature group with correlation.

[0100] Optionally, step 103 may specifically include:

[0101] Step 1031: Identify the wings, tail, and control surfaces of the aircraft as the main configuration partitions;

[0102] Step 1032: Each fused spectrum in the eddy current electromagnetic spectrum dataset is categorized according to the main configuration partition on the surface of the aircraft, based on the pressure sensing unit used when collecting the fused spectrum.

[0103] Step 1033: Within the same main configuration partition, the fused spectra that meet the preset conditions are combined to form a partitioned spectrum group;

[0104] Step 1034: Based on the aerodynamic layout of the aircraft, determine the airflow influence relationship between different main configuration zones;

[0105] Step 1035: Based on the airflow influence relationship, combine multiple correlated partition spectrum groups to generate a spectrum feature group with correlation.

[0106] Optionally, step 1035 may specifically include:

[0107] Analyzing the airflow path of the aircraft during flight—from the leading edge of the wing, through the trailing edge, and to the tail surface—the wing and tail sections are identified as related sections with upstream and downstream influence. The spectrum groups belonging to these related sections are then connected in series according to the airflow path sequence. In this series connection, a correspondence is established between the output frequency characteristics of the wing section's spectrum group and the input frequency characteristics of the tail section's spectrum group. Based on this correspondence, the wing and tail section spectrum groups are combined into a cross-section joint spectrum group. This series connection and merging operation is repeated for all related sections with upstream and downstream influence on the aircraft to generate the related spectrum feature groups.

[0108] In this step, the configuration features of the aircraft refer to the division of the main physical structural regions of the aircraft body that have significant aerodynamic functional differences. This is used as a framework for organizing spectral data and is obtained by analyzing the aircraft's design drawings to identify its main parts such as wings, tail, and control surfaces.

[0109] A correlated spectral feature group refers to a larger unit formed by combining spectral data from different body regions that are physically related by airflow. It is used to characterize the collaborative working characteristics of various components of the aircraft under real airflow. It is obtained by combining multiple partitioned spectral groups according to the airflow influence relationship.

[0110] The main configuration partitions refer to several key component regions identified based on the configuration characteristics of the aircraft, such as wings, tail, and control surfaces. These regions are used to perform preliminary classification of the fused spectrum and are obtained by identifying the main aerodynamic structures of the aircraft.

[0111] The fusion spectrum that meets the preset conditions refers to the fusion spectrum from sensors that are spatially adjacent or functionally similar within the same main configuration partition. It is used to form a representative data set within the partition. The fusion spectrum within the partition is obtained by filtering and combining the fusion spectrum by setting conditions such as spatial proximity.

[0112] A partitioned spectrum group refers to a data group formed by combining multiple fused spectra that meet preset conditions within the same primary configuration partition. It is used to represent the spectral characteristics of that partition under specific flight conditions and is obtained by combining fused spectra that meet the conditions within the partition.

[0113] The aerodynamic layout of an aircraft refers to the relative positions and geometric relationships between the main components of the aircraft (such as wings, fuselage, and tail), which are used to infer the flow and influence of airflow between them during flight. It is obtained by analyzing the three-dimensional model or design drawings of the aircraft.

[0114] Airflow influence relationship refers to the causal relationship between airflow disturbances (such as vortices) generated by one component and the aerodynamic characteristics of another component during aircraft flight. It is used to determine which spectral groups need to be associated and is obtained by analyzing aerodynamic layout and airflow path.

[0115] A pair of partitions with upstream and downstream influence refers to a configuration partition that has a sequential relationship in the airflow path and where the airflow in the upstream partition affects the airflow in the downstream partition. It is used to identify partition pairs that need to be strongly correlated and is obtained by analyzing the path of airflow from upstream to downstream.

[0116] Output frequency characteristics refer to specific frequency fluctuation patterns contained in the upstream partition spectrum group that may affect downstream components. They are used as source characteristics affecting downstream components and are obtained by analyzing the frequency components of the upstream partition spectrum group.

[0117] Input frequency characteristics refer to specific frequency fluctuation patterns contained in the downstream spectral group of the airflow that may be affected by upstream components. They are used as target characteristics to be affected and are obtained by analyzing the frequency components of the downstream spectral group.

[0118] A cross-regional joint spectrum group refers to a larger, cross-regional data group formed by combining the spectrums of a pair of related zones with upstream and downstream influence relationships. It is used to comprehensively characterize the complete spectral characteristics of the airflow influence link and is obtained by merging the related zone spectrum groups based on the correspondence of frequency characteristics.

[0119] In this step, the main physical structural components of the aircraft are first identified by analyzing its design drawings or 3D model. The wings, tail, and control surfaces are clearly defined as the main configuration partitions, establishing a top-level framework for data organization. Secondly, by querying the acquisition source information of each fused spectrum in step 101, that is, recording the signal acquired by the pressure sensing unit located at which the fused spectrum was generated, each fused spectrum in the eddy current electromagnetic spectrum dataset is classified into the main configuration partitions such as wings, tail, or control surfaces according to the physical location of the pressure sensing unit.

[0120] Next, within each major configuration partition, a clustering algorithm based on spatial proximity is applied to select the fused spectra from pressure sensing units that are spatially close to each other within that partition, and combine them to form a partition spectrum group that can represent the characteristics of that local area. Then, through computational fluid dynamics simulation or empirical knowledge based on aerodynamic layout, the dominant flow path of airflow from the leading edge of the wing, through the trailing edge of the wing, and finally to the tail surface is analyzed, thereby determining the upstream and downstream airflow influence relationships between different major configuration partitions. For example, it is determined that the wing partition is the upstream influence source of the tail partition. Finally, based on the determined airflow influence relationships, data linking technology is used to connect the related partition spectrum groups (such as the wing partition spectrum group and the tail partition spectrum group) in series according to the airflow path sequence.

[0121] In this cascaded model, a pattern matching method is used to establish a one-to-one correspondence between the specific frequency patterns (output frequency features) characterizing vortex shedding in the upstream wing partition spectrum group and the response frequency patterns (input frequency features) generated by the downstream tail wing partition spectrum group under its excitation. Based on this correspondence, the two partition spectrum groups are integrated into a single, cross-partition joint spectrum group through a data merging operation. This cascaded and merged operation is repeated for all partition pairs on the aircraft that have similar upstream and downstream influence relationships to generate a series of spectrum feature groups that can reflect the aerodynamic coupling between components and have correlation relationships.

[0122] Following the embodiment of step 102, after obtaining the eddy current electromagnetic spectrum dataset of aircraft A (containing fused spectra of multiple flight states), the aircraft body is first divided into main configuration partitions such as "left wing," "right wing," "horizontal tail," and "vertical tail" according to the design drawing of aircraft A. Then, based on the metadata (recording which sensor each fused spectrum comes from), each fused spectrum in the dataset is classified into the corresponding partition. For example, the fused spectrum from the sensor on the left wing is classified into the "left wing" partition. Within the "left wing" partition, the fused spectra corresponding to adjacent sensors (such as the 5 sensors in a row at the leading edge of the left wing) are combined to form a "left wing leading edge partition spectrum group."

[0123] Next, aerodynamic analysis confirmed that the wingtip vortex generated by the left wing significantly affects the airflow environment of the left horizontal tail, thus determining that there is an upstream and downstream airflow influence relationship between the "left wing" and the "left horizontal tail", which are a pair of correlated partitions. Therefore, the "left wing trailing edge partition spectrum group" (output side) and the "left horizontal tail partition spectrum group" (input side) are connected in series, and a feature correspondence is established (for example, a frequency peak representing a vortex feature in the wing spectrum is associated with a forced vibration frequency peak in the tail spectrum). Finally, the arrays of these two groups are merged to form a "left wing-left horizontal tail joint spectrum group". After performing the same operation on all such correlated partitions, the set of correlated spectrum feature groups of aircraft A is obtained.

[0124] This step involves first dividing and classifying the data according to its physical structure, then aggregating it within each division to form local feature groups, and finally merging related feature groups across divisions based on the actual airflow influence. This transforms the spectral data from a simple collection into a structured organization with physical spatial correlation and causal logic, enabling the final generated spectral feature groups to inherently reflect the mutual coupling effects of various aircraft components under real aerodynamic environments. This greatly enhances the physical representation capability and engineering application value of the feature library.

[0125] Step 104: Systematically arrange the spectral feature groups according to flight state parameters to construct the spectral feature library of the aircraft.

[0126] Optionally, step 104 may specifically include:

[0127] Step 1031: Determine the range of the flight state parameters, wherein the flight state parameters include flight speed parameters and flight attitude parameters;

[0128] Step 1032: Construct a two-dimensional parameter grid with the flight speed parameter as the first dimension and the flight attitude parameter as the second dimension;

[0129] Step 1033: Place the spectral feature set into the grid cell in the two-dimensional parameter grid that corresponds to the actual flight state parameter that generated the spectral feature set;

[0130] Step 1034: For grid cells where no spectral feature group falls, fill them according to the spectral feature groups in adjacent grid cells;

[0131] Step 1035: Integrate the contents of all grid cells to form the spectral feature library of the aircraft.

[0132] In this step, the range of flight state parameters refers to the interval between the minimum and maximum values ​​of flight speed and flight attitude that needs to be covered when constructing the feature library. It is used to define the boundary of the feature library and is obtained by analyzing the actual flight envelope of the aircraft or by experimental planning.

[0133] Flight speed parameters refer to parameters that describe how fast an aircraft flies. They are usually expressed as Mach number or airspeed and are used as a major dimension of the organizational feature library. They are measured by the aircraft's pitot tube or inertial navigation system.

[0134] Flight attitude parameters refer to parameters that describe the orientation of an aircraft in the air. They are usually expressed as angle of attack, sideslip angle, etc., and are used as another major dimension of the organizational feature library. They are measured by the aircraft's attitude gyroscope or inertial measurement unit.

[0135] A two-dimensional parametric grid refers to a regular array of cells divided on a two-dimensional plane with one flight state parameter as the horizontal axis and another flight state parameter as the vertical axis. It is used to provide a unique storage location for each flight state point and is constructed by setting the value range of the two dimensions and the grid division precision.

[0136] The first dimension refers to the horizontal dimension selected when constructing a two-dimensional parametric mesh to represent one aspect of the flight state; in this method, it specifically refers to the flight speed parameter.

[0137] The second dimension refers to the dimension selected as the vertical direction when constructing a two-dimensional parametric mesh, used to represent another aspect of the flight state, specifically the flight attitude parameters in this method.

[0138] The grid cell corresponding to the actual flight state parameters that generate the spectrum feature group refers to the specific cell in the two-dimensional parameter grid whose horizontal and vertical coordinate values ​​exactly match the actual flight speed and flight attitude values ​​of a certain spectrum feature group during acquisition. This cell is used to store the spectrum feature group and is obtained by matching the actual flight state parameters with the grid coordinates.

[0139] Grid cells without spectral feature groups refer to those empty cells in the two-dimensional parameter grid whose corresponding flight state parameter combinations were not collected in the actual test. These cells need to be filled by interpolation or other methods and are identified by checking whether the grid cells are empty.

[0140] In this step, the complete range of values ​​for flight speed parameters (such as Mach number from 0.3 to 0.9) and flight attitude parameters (such as angle of attack from -5 degrees to 20 degrees) to be covered by the feature library is first determined by analyzing the design flight envelope or test outline of the aircraft. That is, the range of flight state parameters. Then, by using data gridding technology, with the flight speed parameters as the horizontal axis (first dimension) and the flight attitude parameters as the vertical axis (second dimension), within the determined range of values, rectangular grid cells are divided according to the set intervals (such as Mach number interval of 0.1 and angle of attack interval of 1 degree), thereby constructing a two-dimensional parameter grid covering the entire target state space.

[0141] Next, through data mapping operations, all spectral feature groups are located in a unique grid cell in the two-dimensional parameter grid, based on the actual flight speed and flight attitude parameters recorded at the time of their generation, and the spectral feature group is stored in this cell. Then, through spatial interpolation algorithms (such as bilinear interpolation), for those state points in the two-dimensional parameter grid that were not covered in the actual flight test (i.e., grid cells where no spectral feature group has fallen), an estimated spectral feature group is calculated and generated using the data information of the spectral feature groups that already exist in the surrounding adjacent grid cells to fill the empty cell, so as to ensure the integrity of the grid.

[0142] Finally, through data aggregation operations, the contents of all grid cells in the two-dimensional parametric grid (including directly stored and interpolated spectral feature groups) are systematically linked together to form a structured spectral feature library that can be quickly queried and accessed through flight status parameters.

[0143] Following the embodiment of step 103, after obtaining a series of related spectral feature groups of aircraft A, a spectral feature library covering Mach numbers from 0.4 to 0.8 and angles of attack from 0 to 15 degrees is first constructed, and the range of this flight state parameter is determined. Then, a two-dimensional parameter grid is established in the computer with Mach number as the X-axis (first dimension, interval 0.05) and angle of attack as the Y-axis (second dimension, interval 1 degree). Each spectral feature group is then placed into the grid according to its corresponding actual flight state (for example, a feature group corresponds to a Mach number of 0.55 and an angle of attack of 8 degrees). For the corresponding cell, at the state point of Mach number 0.6 and angle of attack 5 degrees, no experiment was conducted at the time, resulting in the empty grid cell (i.e., a grid cell in which no spectral feature set falls). Therefore, a bilinear interpolation algorithm was used to calculate and generate an estimated feature set to fill the empty cell by using the feature set data from the surrounding grid cells with Mach numbers of 0.55 / 0.6 and angles of attack of 4 degrees / 6 degrees. Finally, the feature sets of all cells in the entire grid (whether measured or interpolated) were integrated into a complete data structure, and the spectral feature library of aircraft A was successfully constructed.

[0144] This step systematically maps discrete spectral feature sets onto a continuous grid space spanned by flight state parameters and fills in the missing positions with reasonable interpolation, ultimately constructing a continuous and complete spectral feature library in the state space. This allows for the search for corresponding feature data for any state point within the flight envelope, greatly improving the completeness and usability of the feature library and providing seamless data support for the analysis, identification, and simulation of aircraft under various states.

[0145] Figure 2 This application provides a schematic diagram of the structure of a system for constructing a spacecraft spectral feature library based on eddy current detection, as shown in the following figure. Figure 2 As shown, the system includes:

[0146] The acquisition module 21 is used to acquire the unsteady pressure signal generated by the surface airflow of the aircraft in multiple flight states through a pressure sensing unit set on the surface of the aircraft, and obtain the unsteady pressure signal of the aircraft in each flight state;

[0147] Processing module 22 is used to repeatedly perform joint fusion processing on the unsteady pressure signal of each flight state and the electromagnetic scattering signal of the aircraft itself to generate eddy current electromagnetic spectrum datasets corresponding to different flight states.

[0148] Organization module 23 is used to structure the eddy current electromagnetic spectrum dataset according to the configuration characteristics of the aircraft, and generate spectrum feature groups with correlation.

[0149] The construction module 24 is used to systematically arrange the spectrum feature groups according to flight state parameters to construct the spectrum feature library of the aircraft.

[0150] Figure 2 The aforementioned system for constructing a spacecraft spectral feature database based on eddy current detection can perform... Figure 1 The implementation principle and technical effects of the eddy current detection-based aircraft spectrum feature library construction method described in the illustrated embodiment will not be repeated here. The specific methods by which each module and unit performs operations in the eddy current detection-based aircraft spectrum feature library construction system described in the above embodiments have been detailed in the embodiments related to this method, and will not be elaborated upon here.

[0151] In one possible design, Figure 2 The aircraft spectral feature database construction system based on eddy current detection, as shown in the embodiment, can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0152] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0153] The processing component 32 is used for the above Figure 1 The embodiment describes a method for constructing a spacecraft spectral feature library based on eddy current detection.

[0154] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0155] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0156] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0157] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0158] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0159] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0160] This application also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The embodiment shown illustrates a method for constructing a spacecraft spectral feature library based on eddy current detection.

[0161] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0162] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0163] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0164] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for constructing a spacecraft spectral feature database based on eddy current detection, characterized in that, include: The unsteady pressure signal generated by the surface airflow of the aircraft in multiple flight states is collected by a pressure sensing unit installed on the surface of the aircraft, and the unsteady pressure signal of the aircraft in each flight state is obtained. The unsteady pressure signal of each flight state is repeatedly subjected to joint fusion processing with the electromagnetic scattering signal of the aircraft itself to generate eddy current electromagnetic spectrum datasets corresponding to different flight states. The eddy current electromagnetic spectrum dataset is structured and organized according to the configuration characteristics of the aircraft to generate a spectrum feature group with correlation. The spectral feature groups are systematically arranged according to flight state parameters to construct the spectral feature library of the aircraft.

2. The method according to claim 1, characterized in that, By acquiring unsteady pressure signals generated by surface airflow in multiple flight states through pressure sensing units installed on the surface of the aircraft, the unsteady pressure signal of the aircraft in each flight state is obtained, including: In the aerodynamic shape of the aircraft, multiple pressure sensing units are arranged on the leading edge of the wing, the surface of the flaps and the root of the vertical tail. The pressure sensing unit is controlled to synchronously record the air pressure change waveform caused by surface airflow stripping when the aircraft enters the predetermined flight state; From the air pressure change waveform recorded by each of the pressure sensing units, extract the pressure signal segment corresponding to the stable segment of the current flight state of the aircraft; The pressure signal segments captured by different pressure sensing units at the same time are combined to form the unsteady pressure signal of the current flight state.

3. The method according to claim 1, characterized in that, The unsteady pressure signal for each flight state is repeatedly subjected to joint fusion processing with the electromagnetic scattering signal of the aircraft itself to generate eddy current electromagnetic spectrum datasets corresponding to different flight states, including: The unsteady pressure signal is converted from the time domain to the frequency domain to obtain the pressure spectrum; The electromagnetic scattering signal is converted from the time domain to the frequency domain to obtain the electromagnetic spectrum; The pressure spectrum is multiplied by all amplitude values ​​in the electromagnetic spectrum corresponding to the same frequency point to generate a fused spectrum; The process of converting from the time domain to the generated fused spectrum is repeated for each flight state, and the fused spectra corresponding to all flight states are integrated to obtain the eddy current electromagnetic spectrum dataset.

4. The method according to claim 3, characterized in that, The pressure spectrum is multiplied by all amplitude values ​​corresponding to the same frequency point in the electromagnetic spectrum to generate a fused spectrum, including: Read the first amplitude value at the first frequency point in the pressure spectrum; Find a second frequency point in the electromagnetic spectrum that is the same as the first frequency point, and read the second amplitude value of the second frequency point; The first amplitude value and the second amplitude value are multiplied to obtain the fused amplitude value at the first frequency point; According to a preset order, the operations of reading the first amplitude value, reading the second amplitude value, and performing numerical multiplication are repeated for each frequency point in the pressure spectrum and electromagnetic spectrum until all frequency points have been processed. The fusion amplitude values ​​calculated for each frequency point are arranged in the corresponding frequency order to form a complete fusion spectrum.

5. The method according to claim 1, characterized in that, The eddy current electromagnetic spectrum dataset is structured and organized according to the configuration characteristics of the aircraft to generate related spectral feature groups, including: The wings, tail, and control surfaces of the aircraft are identified as the main configuration partitions; Each fused spectrum in the eddy current electromagnetic spectrum dataset is categorized on the surface of the aircraft according to the main configuration partition to which it belongs, based on the pressure sensing unit used when acquiring the fused spectrum. Within the same primary configuration partition, fused spectra that meet preset conditions are combined to form a partitioned spectrum group; Based on the aerodynamic layout of the aircraft, the airflow influence relationship between different main configuration zones is determined; Based on the airflow influence relationship, multiple correlated partition spectrum groups are combined to generate a spectrum feature group with correlation.

6. The method according to claim 5, characterized in that, Based on the airflow influence relationship, multiple correlated partition spectrum groups are combined to generate a spectrum feature group with correlation, including: The airflow path of the aircraft during flight is analyzed, from the leading edge of the wing to the trailing edge of the wing and then to the surface of the tail. The wing section and the tail section are identified as related sections with upstream and downstream influence. The partition spectrum groups belonging to the associated partition are connected in series according to the order of the airflow path; In the series connection, a correspondence is established between the output frequency characteristics of the wing partition spectrum group and the input frequency characteristics of the tail partition spectrum group; Based on the aforementioned correspondence, the wing partition spectrum group and the tail partition spectrum group are combined into a cross-partition joint spectrum group. The series connection and merging operation is repeated for all associated partitions on the aircraft that have upstream and downstream influence relationships to generate the associated spectrum feature groups.

7. The method according to claim 1, characterized in that, The spectral feature groups are systematically arranged according to flight state parameters to construct the spectral feature library of the aircraft, including: Determine the range of the flight state parameters, wherein the flight state parameters include flight speed parameters and flight attitude parameters; A two-dimensional parameter grid is constructed using the flight speed parameter as the first dimension and the flight attitude parameter as the second dimension. The spectral feature set is placed into the grid cell in the two-dimensional parameter grid that corresponds to the actual flight state parameter that generated the spectral feature set; For grid cells where no spectral feature set falls, fill them according to the spectral feature sets in adjacent grid cells; The contents of all grid cells are integrated to form the spectral feature library of the aircraft.

8. A system for constructing a spectrum feature database for aircraft based on eddy current detection, characterized in that, include: The acquisition module is used to acquire the unsteady pressure signal generated by the surface airflow of the aircraft in multiple flight states through a pressure sensing unit set on the surface of the aircraft, and obtain the unsteady pressure signal of the aircraft in each flight state; The processing module is used to repeatedly perform joint fusion processing on the unsteady pressure signal of each flight state and the electromagnetic scattering signal of the aircraft itself to generate eddy current electromagnetic spectrum datasets corresponding to different flight states. An organization module is used to structure the eddy current electromagnetic spectrum dataset according to the configuration characteristics of the aircraft, and generate spectrum feature groups with correlation relationships. The construction module is used to systematically arrange the spectral feature groups according to flight state parameters to construct the spectral feature library of the aircraft.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the method for constructing a spacecraft spectrum feature library based on eddy current detection as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The system contains a computer program that, when executed by a computer, implements a method for constructing a spacecraft spectrum feature library based on eddy current detection as described in any one of claims 1 to 7.

Images