Airworthiness testing method, apparatus, device, and medium for an aircraft

Abstract

The application discloses an airworthiness test method, device, equipment and medium of an aircraft, and belongs to the technical field of the aircraft. The method comprises the following steps: receiving an airworthiness test instruction for a to-be-tested aircraft; based on the airworthiness test instruction, collecting multi-modal data of the to-be-tested aircraft in a flight state according to a preset data collection period; after the to-be-tested aircraft finishes flying, generating an airworthiness evidence package based on the collected multi-modal data, wherein the airworthiness evidence package is used for determining whether the to-be-tested aircraft is suitable for flying; wherein the airworthiness evidence package comprises predefined data rules and target data associated with the data rules in the multi-modal data.

Description

Technical Field

[0001] This application relates to the field of aircraft technology, and in particular to an airworthiness testing method, apparatus, equipment and medium for aircraft. Background Technology

[0002] With the development of urban air mobility (UAM), the flight testing and verification of electric vertical take-off and landing (eVTOL) aircraft has entered a stage characterized by high frequency, multiple operating conditions, and high complexity. Unlike traditional aircraft flight testing, eVTOL flight testing requires the simultaneous acquisition of multimodal flight data, followed by a series of analyses based on this data, such as determining the suitability of eVTOL for flight. The multimodal flight data sources are characterized by diversity (airborne bus, sensors, video, voice), multiple data rates (from 10Hz to 1000Hz), and massive data volume (up to TB per flight).

[0003] Currently, there is a frequent need to test whether eVTOLs are suitable for navigation, which requires generating an airworthiness compliance evidence chain for review by the authorities. However, the existing airworthiness compliance evidence chains mainly rely on manual compilation, which wastes a lot of human resources. Summary of the Invention

[0004] In view of the above problems, this application is made in order to provide an airworthiness testing method, apparatus, equipment and medium for aircraft that solves the above problems, which can save human resources for generating airworthiness evidence packages.

[0005] In a first aspect, this application provides an airworthiness testing method for an aircraft, the method comprising: Receive airworthiness test instructions for the aircraft under test; Based on the airworthiness test instructions, multimodal data of the aircraft under test in flight state are collected according to a preset data collection cycle; After the test aircraft completes its flight, an airworthiness evidence package is generated based on the collected multimodal data. The airworthiness evidence package is used to determine whether the test aircraft is suitable for flight. The airworthiness evidence package includes: predefined data rules, and target data associated with the data rules in the multimodal data.

[0006] In one embodiment, before generating the airworthiness evidence package based on the collected multimodal data, the method further includes: Feature extraction is performed on the multimodal data collected in each cycle to obtain the data features corresponding to each cycle; The generation of the airworthiness evidence package based on the collected multimodal data includes: After the flight of the aircraft under test is completed, target data associated with the data rules is obtained from the multimodal data collected in each cycle; and target data features associated with predefined data feature rules are obtained from the data features corresponding to each cycle. The airworthiness evidence package is generated based on at least one of the data rules, the data feature rules, the target data, and the target data features.

[0007] In one embodiment, the step of extracting features from the multimodal data collected in each cycle to obtain the data features corresponding to each cycle includes: For each cycle of multimodal data, the multimodal data is synchronized in time to obtain the corresponding synchronization data for each cycle; Feature extraction is performed on the synchronization data corresponding to each cycle; The extracted features are used as the data features corresponding to each period.

[0008] In one embodiment, the multimodal data includes: satellite positioning data, bus data, and media data; The step of time synchronization of the multimodal data to obtain the synchronization data corresponding to each cycle includes: A reference timestamp is determined based on the satellite positioning data; The reference timestamp is distributed to the bus of the aircraft under test, so that the bus data has the reference timestamp; The estimated timestamp of the media data is determined by the media timestamp corresponding to the media data and the cross-correlation algorithm, and the difference between the estimated timestamp and the base timestamp is within a preset difference range. The global data carrying the reference timestamp, the bus data carrying the reference timestamp, and the global data carrying the estimated timestamp are used as the synchronization data.

[0009] In one embodiment, after collecting multimodal data of the aircraft under test in flight according to a preset data acquisition cycle, the method further includes: Quality monitoring is performed on the multimodal data collected in each cycle and the corresponding data features to generate quality indicators; If the quality indicators meet the first preset condition, then control the aircraft under test to stop flying; If the quality index meets the second preset condition, then the aircraft under test is adjusted and controlled to maintain flight.

[0010] In one embodiment, the quality index includes at least one of packet loss rate and the state of the target sensor in the aircraft under test, wherein the packet loss rate includes the packet loss rate of multimodal data and / or the packet loss rate of data features of multimodal data; If the quality index meets the second preset condition, then the aircraft under test is adjusted, including: If the packet loss rate is included in the quality indicators, then if the packet loss rate is greater than a preset packet loss rate threshold, the aircraft under test shall be inspected and / or its parameters adjusted to reduce the packet loss rate. If the quality indicators include the status of the target sensor, then if the target sensor is in a failed state, the aircraft under test is controlled to activate the backup sensor of the target sensor.

[0011] In one embodiment, after collecting multimodal data of the aircraft under test in flight according to a preset data acquisition cycle based on the airworthiness test command, the method further includes: Data blocks are generated based on the collected multimodal data; Calculate the hash value of the data block and store the hash value in the blockchain; The step of generating the airworthiness evidence package based on at least one of the data rules, the data feature rules, the target data, and the target data features includes: After the test aircraft finishes its flight, the hash value is obtained from the blockchain; The airworthiness evidence package is generated based on the hash value, the data rules, the data feature rules, the target data, and at least one of the target data features.

[0012] In one embodiment, the method further includes: After the test aircraft completes its flight, a flight record package for that flight is generated and added to a record package set; the record package set includes flight record packages generated from multiple flights by multiple aircraft. Receive key query information; Based on the key query information, the target record package corresponding to the query keyword is retrieved from the flight record package set.

[0013] Secondly, this application provides an airworthiness testing apparatus for an aircraft, the apparatus comprising: The receiving module is used to receive airworthiness test commands for the aircraft under test. The data acquisition module is used to acquire multimodal data of the aircraft under test in flight state according to the airworthiness test instructions and a preset data acquisition cycle. The generation module is used to generate an airworthiness evidence package based on the collected multimodal data after the flight of the aircraft under test is completed. The airworthiness evidence package is used to determine whether the aircraft under test is suitable for flight. The airworthiness evidence package includes: predefined data rules, and target data associated with the data rules in the multimodal data.

[0014] Thirdly, this application provides an electronic device, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method as described in the first aspect.

[0015] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing the computer to perform the method described in the first aspect.

[0016] The technical solutions provided in this application embodiment have at least the following technical effects or advantages: This application provides an airworthiness testing apparatus, device, and medium for an aircraft. Upon receiving an airworthiness test instruction for an aircraft under test, this application can automatically collect multimodal data of the aircraft under test in flight according to a preset data collection cycle based on the airworthiness test instruction. After the aircraft under test has completed its flight, an airworthiness evidence package is generated based on the collected multimodal data. The airworthiness evidence package is used to determine whether the aircraft under test is suitable for flight. Specifically, the airworthiness evidence package includes: predefined data rules and target data associated with the data rules in the multimodal data. The above process is automatically executed by the machine, eliminating the need for manual processing to generate the airworthiness evidence package, thus saving human resources.

[0017] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0018] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a flowchart of an airworthiness testing method for an aircraft provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the time synchronization of multimodal data provided in an embodiment of this application; Figure 3 This is a structural diagram of an airworthiness testing device for an aircraft provided in an embodiment of this application; Figure 4 This is a structural diagram of an electronic device. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the embodiments of this disclosure and the specific features in the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. Unless otherwise specified, the embodiments of this application and the technical features in the embodiments can be combined with each other.

[0020] The English and Chinese explanations of the terms used in this application are as follows: Data Acquisition Unit (DAU); Pulse Per Second (PPS) signal (GPS high-precision time synchronization); Inter-Range Instrumentation Group Time Code B (IRIG-B); Aeronautical Radio, Incorporated (ARINC) bus standard. Pulse Code Modulation (PCM); Controller Area Network (CAN); Fast Fourier Transform (FFT); Military Specification - Flying Qualities of Piloted Airplanes (MIL-F-8785C); Aeronautical Design Standard - Handling Qualities Requirements for Military Rotorcraft (ADS-33E-PRF); Flight Information Exchange Model (FIXM); Aeronautical Information Exchange Model (AIXM); Practical Byzantine Fault Tolerance (PBFT) consensus algorithm.

[0021] Figure 1 This is a flowchart of an airworthiness testing method for an aircraft provided in an embodiment of this application, such as... Figure 1 As shown, the method can be performed by a ground-based testing system, and the method includes: Step S101: Receive airworthiness test instructions for the aircraft under test; The aircraft under test refers to the eVTOL that is to be tested; The testing system receives airworthiness test commands input by the user on the system's interface. These commands are used to indicate whether the aircraft under test is suitable for flight testing.

[0022] Step S102: Based on the airworthiness test instructions, collect multimodal data of the aircraft under test in flight state according to the preset data acquisition cycle; The aircraft under test generates multimodal data in real time during flight. The test system collects this multimodal data according to the preset data acquisition cycle based on the airworthiness test instructions.

[0023] Step S103: After the flight of the aircraft under test is completed, an airworthiness evidence package is generated based on the collected multimodal data. The airworthiness evidence package is used to determine whether the aircraft under test is suitable for flight. The airworthiness evidence package includes: predefined data rules and target data associated with the data rules in the multimodal data.

[0024] The process of generating an airworthiness evidence package based on the collected multimodal data includes: extracting target data associated with data rules from the collected multimodal data, and generating an airworthiness evidence package based on the data rules and the target data.

[0025] Based on the data rules and target data in the airworthiness evidence package, it can be determined whether the target data conforms to the data rules, and based on the determination result, whether the aircraft under test is suitable for flight can be determined. Specifically, determining whether the aircraft under test is suitable for flight based on the determination result includes: if the target data conforms to the data rules, then the aircraft under test is determined to be suitable for flight; if the target data does not conform to the data rules, then the aircraft under test is determined to be unsuitable for flight.

[0026] The data rules define the range of values ​​for the target data. To determine whether the target data conforms to the data rules, the following criteria are used: if the value of the target data is within the range, then the target data conforms to the data rules; if the value of the target data is not within the range, then the target data does not conform to the data rules.

[0027] Upon receiving an airworthiness test instruction for the aircraft under test, this application can automatically collect multimodal data of the aircraft under test in flight according to a preset data collection cycle based on the airworthiness test instruction. After the aircraft under test has completed its flight, an airworthiness evidence package is generated based on the collected multimodal data. The airworthiness evidence package is used to determine whether the aircraft under test is suitable for flight. Specifically, the airworthiness evidence package includes: predefined data rules and target data associated with the data rules in the multimodal data. The above process is executed automatically by the machine, eliminating the need for manual processing to generate the airworthiness evidence package, thus saving human resources.

[0028] In one embodiment, multimodal data is primarily collected via an airborne DAU, and a ground-based testing system receives the multimodal data collected by the DAU. The multimodal data specifically includes: Bus data: ARINC429, ARINC664, CAN, and PCM, etc., with a bus data sampling rate of 10-1000Hz; High-bandwidth sensors: data from vibration sensors (sampling rate > 10kHz), strain gauges, and temperature sensors, etc. Video data: Data collected from cockpit cameras, external cameras, infrared thermal imagers, etc. Voice data: pilot conversations, tower communication voices, cockpit voices, etc.; Environmental data: meteorological station data, satellite positioning data, and atmospheric data system data; satellite positioning data includes Global Positioning System (GPS) data and / or BeiDou positioning data.

[0029] Test equipment status: sensor self-test status, data acquisition unit status, and power supply status.

[0030] In one embodiment, before generating the airworthiness evidence package based on the collected multimodal data, the method further includes: Feature extraction is performed on the multimodal data collected in each cycle to obtain the data features corresponding to each cycle; The generation of the airworthiness evidence package based on the collected multimodal data includes: After the flight of the aircraft under test is completed, target data associated with the data rules is obtained from the multimodal data collected in each cycle; and target data features associated with predefined data feature rules are obtained from the data features corresponding to each cycle. The airworthiness evidence package is generated based on at least one of the data rules, the data feature rules, the target data, and the target data features.

[0031] In this implementation, the airworthiness testing method for the aircraft executed by the aforementioned testing system can be specifically executed by the edge computing module within the testing system. Before generating the airworthiness evidence package based on the collected multimodal data, the method further includes: the edge computing module preprocessing the multimodal data collected in each cycle, wherein the preprocessing specifically includes: Data cleaning of multimodal data includes: setting a normal data threshold based on experience, removing outliers from the multimodal data based on the normal data threshold, and imputing missing values ​​in the multimodal data through linear interpolation or spline interpolation; Feature extraction of multimodal data includes: extracting features from multimodal data collected in each cycle to obtain at least one data feature, any data feature can be bandwidth, phase lag, overshoot or steady-state error; Multimodal data compression includes: using an adaptive lossless compression algorithm to compress data with a compression ratio of ≥5:1, thereby reducing storage pressure.

[0032] Currently, the multimodal data of the aircraft under test are all manually screened, cleaned, and labeled after the aircraft under test has finished its flight. The flight and data processing of the aircraft under test are carried out in sequence, which prolongs the test cycle of the aircraft under test. However, the preprocessing of multimodal data in this application is completed during the test flight of the aircraft under test, rather than after the flight is over, which reduces the test cycle of the aircraft under test.

[0033] In this embodiment, the flight quality specification clauses include data rules, and the flight quality specification clauses can be mapped to specific data feature rules, such as bandwidth requirements being mapped to frequency domain analysis results; the flight quality specification clauses include: MIL-F-8785C, and / or ADS-33E-PRF.

[0034] Obtaining target data associated with data rules from the multimodal data collected in each cycle means that multiple types of multimodal data can be collected in each cycle. Data rules are the value rules or constraints for a certain type of multimodal data. After obtaining the multimodal data of that type from the multimodal data collected in each cycle and generating an airworthiness evidence package, it can be determined whether the multimodal data in the airworthiness evidence package conforms to the value rules or constraints of that type of multimodal data. For example, voice data and video data are different types of multimodal data, as are data sensed by vibration sensors, strain gauges, and temperature sensors.

[0035] The process of obtaining target data features associated with predefined data feature rules from the data features corresponding to each cycle refers to the following: Data feature rules are value rules or constraints for a certain type of data features. After obtaining the data features of that type from multiple types of data features and generating an airworthiness evidence package, it can be determined whether the data features in the airworthiness evidence package conform to the value rules or constraints of that type of data features. For example, bandwidth and phase lag are two different types of data characteristics.

[0036] After the test aircraft completes its flight, the testing system automatically generates an airworthiness evidence package, which includes: Flight quality specifications and their applicability descriptions; the flight quality specifications include data rules, and the flight quality specifications can be mapped to data characteristic rules. The target data and its features, for example, the target data is the original multimodal data, and the target data features can be feature curves; The analysis method for the target data and its features defines which algorithm to use, the sampling rate and / or window function during analysis, and the version of the algorithm. The compliance conclusion indicates whether the target data and its features comply with the data rules and data feature rules, respectively.

[0037] In this embodiment, the airworthiness evidence package may also include data feature rules.

[0038] In this embodiment, the airworthiness evidence package is output in a standard format and can be directly imported into the airworthiness certification system. The airworthiness certification system then uses this airworthiness evidence package to determine whether the aircraft under test is suitable for flight. Standard formats include XML, JSON, FIXM, or AIXM.

[0039] It should be noted that, in this application, in addition to determining whether the target data and target data features conform to the data rules and data feature rules respectively after the flight of the aircraft under test is completed, generating a conformity conclusion, and then generating an airworthiness evidence package based on the conformity conclusion, it is also possible to compare the data features with the data feature rules in real time during the flight of the aircraft under test and generate a pre-judgment of the conformity conclusion.

[0040] In this embodiment, the conformity conclusion can specifically indicate whether the target data and / or target data features conform to the corresponding rules.

[0041] This application can automatically generate an airworthiness evidence package, reducing the preparation time of the airworthiness evidence package from several weeks to several hours, and significantly reducing the workload of the airworthiness team.

[0042] In existing solutions, it is difficult to accurately align multimodal data with different sampling rates and time bases, leading to time-domain misalignment in subsequent multimodal data analysis. To address this issue, this application includes a multi-baseline hierarchical synchronization mechanism in the testing system, which can synchronize the multimodal data in time. Specifically: In one embodiment, the step of extracting features from the multimodal data collected in each cycle to obtain data features corresponding to each cycle includes: performing time synchronization on the multimodal data for each cycle to obtain synchronized data corresponding to each cycle; extracting features from the synchronized data corresponding to each cycle; and using the extracted features as the data features corresponding to each cycle.

[0043] In one embodiment, the multimodal data includes: satellite positioning data, bus data, and media data; the step of time synchronization of the multimodal data to obtain synchronization data corresponding to each cycle includes: determining a reference timestamp based on the satellite positioning data; distributing the reference timestamp to the bus of the aircraft under test, so that the bus data has the reference timestamp; determining an estimated timestamp of the media data using the media timestamp corresponding to the media data and a cross-correlation algorithm, wherein the difference between the estimated timestamp and the reference timestamp is within a preset difference range; and using global data carrying the reference timestamp, bus data carrying the reference timestamp, and global data carrying the estimated timestamp as the synchronization data.

[0044] In this embodiment, after collecting multimodal data for one period, it is necessary to first synchronize the multimodal data in time. After obtaining the synchronized data, feature extraction is then performed on the synchronized data to obtain data features. The specific data synchronization process is as follows: like Figure 2 As shown, the multimodal data includes bus data, sensor data, video data, audio data, and environmental data. The bus data is acquired at a frequency of 10 to 1000 Hz, and the sensor data is acquired at a frequency greater than 10 Hz. Primary reference: If the multimodal data mentioned above includes environmental data, and the environmental data includes satellite positioning data, high-precision GPS and / or BeiDou time synchronization (pulse per second (PPS) signal, accuracy ±100ns), it serves as the global primary time reference (or master clock) to obtain the reference timestamp; Secondary reference: According to the IRIG-B code or IEEE 1588 precision time protocol, the reference timestamp is distributed to the bus of the aircraft under test, so that the bus data has the reference timestamp; This allows for the synchronization of data on buses such as ARINC429, ARINC664, CAN, and PCM. After synchronization, the time deviation of the data on these four bus types must be less than 10µs. Level 3 baseline: Video and / or audio data are synchronized using intra-frame interpolation. Media data includes video and / or audio data. The estimated timestamp of the media data is determined using the media timestamps corresponding to the media data and a cross-correlation algorithm. The media timestamps corresponding to the media data include the video timestamps corresponding to the video data and / or the audio timestamps corresponding to the audio data. This enables sub-millisecond alignment between video data and bus data, and / or sub-millisecond alignment between audio data and bus data.

[0045] Video data, or video streams, are transmitted in frames per second (fps) at a rate of 30 to 60 fps.

[0046] The audio data is the audio stream shown in the diagram.

[0047] In addition to GPS-PPS, BeiDou-3 short message time service or a server based on the Network Time Protocol from the National Time Service Center can be used as the primary reference; video data can be interpolated with higher precision using deep learning optical flow method.

[0048] This application can also perform synchronization accuracy monitoring: monitor whether the difference between the timestamp of each data stream and the reference timestamp in multiple data streams is within a preset difference range; the data streams include bus data streams, video data streams, or audio data streams.

[0049] The difference between the video data stream or the audio data stream and the reference timestamp must be less than 1ms; At the same time, the time synchronization of multimodal data will be automatically triggered again after the time limit is exceeded.

[0050] As can be seen, this application achieves the synchronization of multimodal data, which can improve the synchronization accuracy of multimodal data to the sub-millisecond level (<1ms), meet the requirements of dynamic response analysis of eVTOL transition segment, and reduce the synchronization error by 90% compared with the traditional GPS synchronization method alone.

[0051] The testing system in this application can also perform real-time data quality monitoring, specifically: In one embodiment, after collecting multimodal data of the aircraft under test in flight according to a preset data acquisition cycle, the method further includes: Quality monitoring is performed on the multimodal data collected in each cycle and the corresponding data features to generate quality indicators; If the quality indicators meet the first preset condition, then control the aircraft under test to stop flying; If the quality index meets the second preset condition, then the aircraft under test is adjusted and controlled to maintain flight.

[0052] This application not only needs to monitor the quality of multimodal data collected in each cycle, but also needs to monitor the quality of data characteristics corresponding to each cycle and generate quality indicators. The quality indicators include at least one of the following: packet loss rate, sampling rate stability, sensor self-test status, and data range rationality. Specifically, it can monitor the packet loss rate of multimodal data and the packet loss rate of data features; it can monitor the sampling rate stability of multimodal data; it can obtain the self-test status of target sensors in multimodal data; and it can monitor whether the value range formed by the values ​​of multimodal data is within the corresponding reasonable value range to obtain the reasonableness of the corresponding data range, and monitor whether the value range formed by the values ​​of data features is within the corresponding reasonable value range to obtain the reasonableness of the corresponding data range. In one embodiment, the quality index includes at least one of packet loss rate and the state of the target sensor in the aircraft under test, wherein the packet loss rate includes the packet loss rate of multimodal data and / or the packet loss rate of data features of multimodal data; If the quality index meets the second preset condition, then the aircraft under test is adjusted, including: If the packet loss rate is included in the quality indicators, then if the packet loss rate is greater than a preset packet loss rate threshold, the aircraft under test shall be inspected and / or its parameters adjusted to reduce the packet loss rate. If the quality indicators include the status of the target sensor, then if the target sensor is in a failed state, the aircraft under test is controlled to activate the backup sensor of the target sensor.

[0053] In this embodiment, a three-level alarm mechanism can be set up, specifically including: Yellow alert: If the packet loss rate of multimodal data and / or the packet loss rate of multimodal data data features are greater than the preset packet loss rate threshold (here, the preset packet loss rate threshold can be called the first packet loss rate threshold, to distinguish it from the preset second packet loss rate threshold and third packet loss rate threshold), then a suggested inspection prompt will be displayed on the screen interface of the test system and the aircraft under test, so that maintenance personnel can perform equipment hardware maintenance and / or aircraft parameter adjustment on the aircraft under test to reduce the packet loss rate of multimodal data and / or the packet loss rate of multimodal data data features; In this embodiment, the preset packet loss rate threshold can be 1%; Orange Alert: If the packet loss rate of multimodal data and / or the packet loss rate of the data features of multimodal data are greater than the preset second packet loss rate threshold, then it is further determined whether the target sensor is in a failed state. If the target sensor is in a failed state, the aircraft under test is controlled to automatically switch to the backup sensor of the target sensor.

[0054] Red Termination Flight: If data integrity cannot be guaranteed, control the aircraft under test to stop flying.

[0055] If at least one of the following conditions is met, it can be determined that data integrity cannot be guaranteed: The conditions include: the packet loss rate of multimodal data and / or the packet loss rate of the data features of multimodal data is greater than the preset third packet loss rate threshold; the sampling rate stability is less than the preset stability threshold; more than one sensor self-test state failure; and the data range is excessively unreasonable, that is, the difference between the data and the corresponding reasonable value range exceeds the corresponding threshold.

[0056] As can be seen, this application monitors data quality indicators in real time and implements a three-level alarm mechanism, which can identify problems such as sensor failure and data packet loss in advance, and avoid repeated test flights of the aircraft under test due to data quality issues.

[0057] The test system in this application has a blockchain-based trusted evidence storage and data anti-tampering mechanism, specifically: In one embodiment, after collecting multimodal data of the aircraft under test in flight according to a preset data acquisition cycle based on the airworthiness test command, the method further includes: Data blocks are generated based on the collected multimodal data; Calculate the hash value of the data block and store the hash value in the blockchain; The step of generating the airworthiness evidence package based on at least one of the data rules, the data feature rules, the target data, and the target data features includes: After the test aircraft finishes its flight, the hash value is obtained from the blockchain; The airworthiness evidence package is generated based on the hash value, the data rules, the data feature rules, the target data, and at least one of the target data features.

[0058] In this embodiment, the constructed blockchain network includes the following nodes: airborne nodes: airborne blockchain nodes carried by each aircraft; ground nodes: which may be flight test command center systems, airworthiness certification systems, or third-party evidence storage systems.

[0059] Data on-chain mechanism: Multimodal data from each flight is generated into data blocks and hash values ​​are calculated according to time slices; Multimodal data in a time slice can be multimodal data collected within one cycle, or multimodal data collected within multiple cycles, or multimodal data collected within one cycle can be divided into multimodal data in multiple time slices; The hash value and metadata are packaged into a transaction, which includes timestamp, flight status, aircraft number, and pilot identifier; the transaction is then verified by the consensus mechanism and written to each node of the blockchain. Blockchain data integrity verification specifically involves: airworthiness evidence also including hash values ​​obtained from nodes in the blockchain. By comparing the hash value of the original multimodal data with the hash value stored by nodes in the blockchain, it is possible to quickly verify whether the multimodal data has been tampered with, thus proving the authenticity of the multimodal data.

[0060] The blockchain in this application supports retrieving evidence records stored in nodes based on conditions such as time range, operating condition type, and sensor channel.

[0061] This application uses blockchain notarization to prevent data tampering. The hash value of the airworthiness evidence package can prove that the multimodal data has not been tampered with, thus making the conformity evidence in the airworthiness evidence package more credible.

[0062] The testing system described in this application can also manage multiple flight record packets from multiple aircraft, specifically: In one embodiment, the method further includes: after the flight of the aircraft under test is completed, generating a flight record package for the flight of the aircraft under test and adding it to a record package set; the record package set includes flight record packages generated by multiple flights of multiple aircraft; receiving key query information; and based on the key query information, querying the flight record package set to obtain a target record package corresponding to the query keyword.

[0063] The testing system includes a flight test data platform that performs the following functions: Data Catalog: The flight record package collection is organized by at least one dimension, including aircraft type, number of flights, operating conditions, and sensors. The flight record package collection includes multiple flight record packages. A flight record package refers to all the data generated by an aircraft in one flight. The flight record package includes multimodal data collected by an aircraft during a complete flight process. Intelligent retrieval: Based on key query information, retrieve one or more target record packets corresponding to the key query information from the flight record packet set. Natural language query is supported (e.g., "find all flights with pitch bandwidth > 2 rad / s under hovering conditions").

[0064] Visualization analysis: simultaneous playback of multiple curves, reconstruction of 3D flight trajectory, and linkage between video and data; Version management: Records the processing history of multimodal data, including the original multimodal data, cleaned multimodal data, and extracted features of multimodal data, supporting data traceability.

[0065] As can be seen, the testing system of this application can manage multiple flight record packages of multiple aircraft, thereby enabling the retrieval of key query information across sorties and operating conditions, improving the reuse rate of historical data, and providing valuable data assets for subsequent model development.

[0066] The implementation method of this application will be described below using a typical eVTOL hovering test flight scenario.

[0067] 1. Preparations before test flight Deploy a DAU on the eVTOL airborne terminal and connect to the following data sources to collect data: Connect to the bus to collect bus data, which includes: pitch angle, roll angle, yaw angle, angular velocity, etc. Connect vibration sensors to collect main rotor vibration data; The cockpit camera is connected to capture video of the pilot's actions. Connect to a voice recorder to collect conversations between the pilot and the control tower; Initialize the blockchain node and establish a connection with the blockchain node on the ground.

[0068] 2. Flight test execution and real-time processing.

[0069] The hovering condition begins, and the test system collects multimodal data. Multimodal data is synchronized in time; the specific synchronization methods will not be elaborated here. The test calculation module preprocesses the synchronization data, including: calculating the pitch bandwidth, roll bandwidth, and phase lag during the hovering phase; comparing it with the constraints of the ADS-33E-PRF clause (the ADS-33E-PRF clause thresholds define that the bandwidth must be greater than or equal to 2.0 rad / s and the phase lag must be less than or equal to 150 ms); if the real-time bandwidth value is 2.3 rad / s and the phase lag is 120 ms, the constraints are met, and it is judged as Level 1, and the multimodal data detection passes; Data quality monitoring: The packet loss rate of the multimodal data was detected to be 0.3%, which is less than 1%, indicating a normal packet loss rate; the vibration sensor status was also detected to be normal. Data on-chain: Every second, multimodal data generates a data block, calculates the hash value, packages the transactions, and writes them to the blockchain after PBFT consensus.

[0070] After the test flight, an airworthiness evidence package is generated: The testing system automatically generates an airworthiness evidence package for the hovering condition, including: the original text of the ADS-33E-PRF clause; target data characteristics, including pitch angle time-domain curves and frequency-domain analysis curves; analysis process: FFT algorithm version v2.1, sampling rate 100Hz, defined window function; hash value of blockchain evidence: 0x7a3f...8e2d; compliance conclusion: Level 1 (Satisfactory). The airworthiness evidence package is exported in a standard format for use in airworthiness certification.

[0071] Flight record package management and retrieval: Flight record packages are stored in the test flight data platform and labeled "Hovering Condition - 20260305-01"; the key query information is: "Display all flights with pilot scores > 8 points under hovering conditions", and return all record packages that match the key query information.

[0072] Based on the same concept, embodiments of the present invention also provide an airworthiness testing apparatus for an aircraft. Figure 3 This is a structural block diagram of an airworthiness testing device for an aircraft provided in an embodiment of this application, as shown below. Figure 3 As shown, the device 300 includes: The receiving module 301 is used to receive airworthiness test commands for the aircraft under test. The acquisition module 302 is used to acquire multimodal data of the aircraft under test in flight state according to the airworthiness test command and a preset data acquisition cycle. The generation module 303 is used to generate an airworthiness evidence package based on the collected multimodal data after the flight of the aircraft under test is completed. The airworthiness evidence package is used to determine whether the aircraft under test is suitable for flight. The airworthiness evidence package includes: predefined data rules, and target data associated with the data rules in the multimodal data.

[0073] In one embodiment, the device further includes a feature extraction module, which is used to extract features from the multimodal data collected in each cycle before the acquisition module 302 generates an airworthiness evidence package based on the acquired multimodal data, so as to obtain the data features corresponding to each cycle. The generation module 303 is specifically used for: After the flight of the aircraft under test is completed, target data associated with the data rules is obtained from the multimodal data collected in each cycle; and target data features associated with predefined data feature rules are obtained from the data features corresponding to each cycle. The airworthiness evidence package is generated based on at least one of the data rules, the data feature rules, the target data, and the target data features.

[0074] In one embodiment, the feature extraction module is specifically used to perform time synchronization on the multimodal data for each period to obtain the synchronization data corresponding to each period. Feature extraction is performed on the synchronization data corresponding to each cycle; The extracted features are used as the data features corresponding to each period.

[0075] In one embodiment, the multimodal data includes: satellite positioning data, bus data, and media data; In one embodiment, when the feature extraction module performs time synchronization on the multimodal data to obtain the synchronization data corresponding to each cycle, it is specifically used for: A reference timestamp is determined based on the satellite positioning data; The reference timestamp is distributed to the bus of the aircraft under test, so that the bus data has the reference timestamp; The estimated timestamp of the media data is determined by the media timestamp corresponding to the media data and the cross-correlation algorithm, and the difference between the estimated timestamp and the base timestamp is within a preset difference range. The global data carrying the reference timestamp, the bus data carrying the reference timestamp, and the global data carrying the estimated timestamp are used as the synchronization data.

[0076] In one embodiment, the device further includes a quality monitoring module, which, after the acquisition module 301 acquires multimodal data of the aircraft under test in flight according to a preset data acquisition cycle, performs quality monitoring on the multimodal data acquired in each cycle and the corresponding data features, and generates quality indicators. If the quality indicators meet the first preset condition, then control the aircraft under test to stop flying; If the quality index meets the second preset condition, then the aircraft under test is adjusted and controlled to maintain flight.

[0077] In one embodiment, the quality index includes at least one of packet loss rate and the state of the target sensor in the aircraft under test, wherein the packet loss rate includes the packet loss rate of multimodal data and / or the packet loss rate of data features of multimodal data; When the quality monitoring module adjusts the aircraft under test if the quality indicators meet the second preset condition, it is specifically used for: If the packet loss rate is included in the quality indicators, then if the packet loss rate is greater than a preset packet loss rate threshold, the aircraft under test shall be inspected and / or its parameters adjusted to reduce the packet loss rate. If the quality indicators include the status of the target sensor, then if the target sensor is in a failed state, the aircraft under test is controlled to activate the backup sensor of the target sensor.

[0078] In one embodiment, the device further includes a storage module for use after the acquisition module acquires multimodal data of the aircraft under test in flight state according to the airworthiness test instructions and a preset data acquisition cycle: Data blocks are generated based on the collected multimodal data; Calculate the hash value of the data block and store the hash value in the blockchain; When generating the airworthiness evidence package based on at least one of the data rules, the data feature rules, the target data, and the target data features, the generation module 303 is specifically used for: After the test aircraft finishes its flight, the hash value is obtained from the blockchain; The airworthiness evidence package is generated based on the hash value, the data rules, the data feature rules, the target data, and at least one of the target data features.

[0079] In one embodiment, the device further includes a query module, configured to generate a flight record package for the test aircraft after the test aircraft has completed its flight, and add it to a record package set; the record package set includes flight record packages generated from multiple flights by multiple aircraft; Receive key query information; Based on the key query information, the target record package corresponding to the query keyword is retrieved from the flight record package set.

[0080] It is understood that the device provided in the above embodiments is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0081] Reference Figure 4 The present invention also provides an electronic device, which may include a processor and a memory, wherein the processor and the memory can communicate with each other via a bus or other means.

[0082] The processor 402 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application, or it may be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or other chips, or combinations of the above types of chips.

[0083] Memory 401 may include mass storage for data or instructions. For example, and not limitingly, memory may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory may include removable or non-removable (or fixed) media. Where appropriate, memory may be internal or external to an electronic device. In a particular embodiment, memory may be non-volatile solid-state memory.

[0084] In one instance, memory 401 may be read-only memory (ROM). In one instance, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0085] The processor 402 reads and executes computer program instructions stored in the memory to implement any of the airworthiness testing methods for aircraft in the above embodiments.

[0086] In one example, the electronic device may further include a communication interface and a bus. The processor, memory, and communication interface are connected via the bus to communicate with each other. The communication interface is primarily used to enable communication between the various modules, devices, units, and / or equipment in the embodiments of this application. Where appropriate, the bus may include one or more buses.

[0087] Furthermore, in conjunction with the airworthiness testing method for an aircraft described in the above embodiments, this invention can be implemented using a computer-readable storage medium. This computer-readable storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the airworthiness testing methods for aircraft described in the above embodiments.

[0088] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The storage medium can be read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0089] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0090] Similarly, it should be understood that, in order to simplify this disclosure and aid in understanding one or more of the various aspects of the invention, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.

[0091] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

Claims

1. A method of airworthiness testing of an aircraft, characterized in that, The method comprises: receiving airworthiness test instructions for a to-be-tested aircraft; collecting multi-modal data of the to-be-tested aircraft in a flight state according to a preset data collection period based on the airworthiness test instructions; generating an airworthiness evidence package based on the collected multi-modal data after the to-be-tested aircraft finishes the flight, the airworthiness evidence package being used to determine whether the to-be-tested aircraft is suitable for flight; wherein the airworthiness evidence package comprises predefined data rules and target data in the multi-modal data associated with the data rules.

2. The method of claim 1, wherein, Before the airworthiness evidence package is generated based on the collected multi-modal data, the method further comprises: extracting features from each period of collected multi-modal data to obtain data features corresponding to each period; the airworthiness evidence package is generated based on at least one of the data rules, the data feature rules, the target data, and the target data features. extracting features from each period of collected multi-modal data to obtain data features corresponding to each period, comprising: synchronizing the multi-modal data of each period to obtain synchronized data corresponding to each period; 3. The method of claim 2, wherein, extracting features from the synchronized data corresponding to each period; the extracted features are used as the data features corresponding to each period. The multi-modal data comprises satellite positioning data, bus data, and media data; synchronizing the multi-modal data to obtain synchronized data corresponding to each period, comprising:

4. The method of claim 3, wherein, determining a reference timestamp based on the satellite positioning data; distributing the reference timestamp to the bus of the to-be-tested aircraft so that the bus data has the reference timestamp; determining an estimated timestamp of the media data through a media timestamp corresponding to the media data and a cross-correlation algorithm, the difference between the estimated timestamp and the reference timestamp being within a preset difference range; global data carrying the reference timestamp, bus data carrying the reference timestamp, and global data carrying the estimated timestamp are used as the synchronized data. After the multi-modal data of the to-be-tested aircraft in a flight state is collected according to a preset data collection period, the method further comprises: monitoring the quality of each period of collected multi-modal data and corresponding data features to generate a quality index; 5. The method according to any one of claims 2 to 4, characterized in that, if the quality index meets a first preset condition, the to-be-tested aircraft is controlled to stop flying; if the quality index meets a second preset condition, the to-be-tested aircraft is adjusted and controlled to remain in a flight state. The quality index comprises at least one of a packet loss rate and a state of a target sensor in the to-be-tested aircraft, the packet loss rate comprising a packet loss rate of multi-modal data and / or a packet loss rate of data features of multi-modal data; ​ 6. The method of claim 5, wherein, ​ If the quality index meets the second preset condition, then the aircraft under test is adjusted, including: If the packet loss rate is included in the quality indicators, then if the packet loss rate is greater than a preset packet loss rate threshold, the aircraft under test shall be inspected and / or its parameters adjusted to reduce the packet loss rate. If the quality indicators include the status of the target sensor, then if the target sensor is in a failed state, the aircraft under test is controlled to activate the backup sensor of the target sensor.

7. The method of claim 2, wherein, After collecting multimodal data of the aircraft under test in flight according to a preset data acquisition cycle based on the airworthiness test command, the method further includes: Data blocks are generated based on the collected multimodal data; Calculate the hash value of the data block and store the hash value in the blockchain; The step of generating the airworthiness evidence package based on at least one of the data rules, the data feature rules, the target data, and the target data features includes: After the test aircraft finishes its flight, the hash value is obtained from the blockchain; The airworthiness evidence package is generated based on the hash value, the data rules, the data feature rules, the target data, and at least one of the target data features.

8. The method according to any one of claims 1 to 4, characterized in that, The method further includes: After the test aircraft completes its flight, a flight record package for that flight is generated and added to a record package set; the record package set includes flight record packages generated from multiple flights by multiple aircraft. Receive key query information; Based on the key query information, the target record package corresponding to the query keyword is retrieved from the flight record package set.

9. An airworthiness testing apparatus for an aircraft, characterized in that, The device includes: The receiving module is used to receive airworthiness test commands for the aircraft under test. The data acquisition module is used to acquire multimodal data of the aircraft under test in flight state according to the airworthiness test instructions and a preset data acquisition cycle. The generation module is used to generate an airworthiness evidence package based on the collected multimodal data after the flight of the aircraft under test is completed. The airworthiness evidence package is used to determine whether the aircraft under test is suitable for flight. The airworthiness evidence package includes: predefined data rules, and target data associated with the data rules in the multimodal data.

10. An electronic device, comprising: include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1-8.

11. A computer readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method of any one of claims 1-8.

Images