Aircraft wing section testing method and system based on DDS (Direct Digital Synthesizer)

Abstract

The invention provides a DDS-based airplane wing section test method and system. The DDS-based airplane wing section test method comprises the following steps: establishing a data communication link among a test platform, a DDS Agent end and one or more hardware test modules through a DDS; enabling the test platform to send a test instruction; meanwhile, the hardware test module executes wing test operation to obtain real-time test data; the hardware test module feeds back the real-time test data to the test platform; in the test instruction sending and real-time test data feedback process, calculating a communication quality Q value, and dynamically adjusting a data distribution strategy according to the Q value; and the test platform receives and analyzes the real-time test data, executes fault diagnosis at the same time, determines a fault reason, and locates a fault position on a digital twin model in the test platform. According to the method, digital twinning, machine learning and DDS communication optimization are fused, so that the intuition, the fault diagnosis efficiency and the data transmission robustness of the aircraft wing section test are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of aircraft testing, and specifically, to an aircraft wing section testing method and system based on DDS. Background Art

[0002] In the research and development and testing of complex systems such as modern industrial control, autonomous driving, and aerospace, a large number of distributed devices and nodes are often involved. Traditional test communication architectures, such as the client-server mode or the message queue-based method, are often restricted by the centralized architecture and difficult to meet the requirements when facing scenarios with a large number of nodes, frequent data interaction, and strict real-time requirements.

[0003] Data Distribution Service (DDS), as an advanced communication middleware, can provide high-performance, high-reliability, and low-latency data communication services for distributed systems with its decentralized publish-subscribe mode and flexible Quality of Service (QoS) strategies. In DDS, the publisher and the subscriber are independent of each other, and data is organized and managed through topics. Subscribers can directly obtain relevant data based on topics without caring about the source or path of the data, thus realizing a communication model centered on data, effectively alleviating the existing problems of the centralized architecture, and improving communication efficiency.

[0004] During the factory test of an aircraft, the aircraft needs to be tested at the section level. The wing section covers multiple groups of function integrity and status consistency checks, such as wing rotation angle, fuel tank oil temperature, cable continuity, and AC measurement. Currently, the above tests mainly rely on testers to perform operations and read results in different areas such as flaps, ailerons, and fuel tanks, which leads to many problems: First, there is a lack of intuitive and comprehensive status monitoring and alarming means. Currently, the test data of the wing section is often recorded and presented in the form of scattered numerical values or independent charts. It is difficult for testers to grasp the integrated status and dynamic behavior of the entire wing section in real time and intuitively, and it increases the labor cost and the test cycle is long.

[0005] Second, fault analysis is difficult and inefficient. Limited by the serious fragmentation of test data records and the lack of real-time relevance, it becomes extremely difficult to trace the root cause of the fault and understand its propagation path. Especially for some faults caused by multiple factors or with hidden manifestations, it is very easy to miss key links during manual troubleshooting.

[0006] Moreover, it is difficult to guarantee the reliability of critical data during transmission. When the network condition is poor, there is a lack of a mechanism to quantitatively evaluate the real-time network communication quality, and it is impossible to actively perceive and make transmission strategy adjustments, which may lead to the delay in the delivery of critical test instructions, the loss or damage of important status data, directly affecting the accuracy of test results.

[0007] The Chinese patent document with the publication number CN118964184A discloses a vehicle test system and a test method based on DDS simulation service. The vehicle test system includes: an industrial control computer, on which a test framework is deployed, and the test framework is used to obtain test cases corresponding to test requests in response to the test requests; a DDS server, which is connected to the industrial control computer through a switch, and a simulation service program is deployed on the DDS server. The DDS server is used to receive the test cases sent by the test framework and construct a simulation service program for a virtual target test scenario according to the test cases; the hardware under test is communicatively connected to the DDS server and is used to receive the simulation service program of the virtual target test scenario and execute test programs according to the simulation service program; the test cases include one or more of factory flashing test cases, self-test cases, and OTA test cases. By constructing a virtual test scenario, the test requirements for various different working condition scenarios are realized, thereby improving the reliability of test results.

[0008] The above problems still exist in the prior art. Therefore, there is an urgent need for a DDS-based test method and system for aircraft wing segments. Summary of the Invention

[0009] Aiming at the defects in the prior art, the purpose of the present invention is to provide a DDS-based test method and system for aircraft wing segments.

[0010] According to a DDS-based test method for aircraft wing segments provided by the present invention, it includes: Step S1: Establish a data communication link between the test platform, the DDS Agent proxy and one or more hardware test modules through DDS; Step S2: Make the test platform send test instructions, and the test instructions are forwarded to one or more of the hardware test modules through the DDS Agent proxy; at the same time, make the hardware test module perform wing test operations to obtain real-time test data; Step S3: The hardware test module feeds back the real-time test data to the test platform through DDS; Step S4: During the process of sending test instructions and feeding back real-time test data, make the DDS Agent proxy calculate the communication quality Q value and dynamically adjust the distribution strategy according to the Q value; Step S5: Based on the adjusted distribution strategy, the test platform receives and analyzes real-time test data, simultaneously performs fault diagnosis to determine the cause of the fault, and locates the fault position on the digital twin model in the test platform.

[0011] Preferably, the step S1 includes: Step S1.1: Configure the test platform, the DDS Agent client, and all hardware test modules within the same DDS domain; where the number of hardware test modules is one or more, and they are configured at specific positions on the wing according to requirements; Step S1.2: Let the test platform, the DDS Agent client, and the hardware test modules establish data communication links with each other through DDS in sequence; specifically, between the test platform and the DDS Agent client, and between the DDS Agent client and one or more hardware test modules, establish a data communication link with a publish-subscribe relationship based on predefined DDS topics for forwarding test instructions and real-time test data; where the real-time test data includes sequential test data and static test data.

[0012] Preferably, the step S4 includes: Step S4.1: The DDS Agent client monitors the key performance indicators (KPIs) of the data communication link in real time; Step S4.2: Normalize the monitored key performance indicators (KPIs) to obtain a normalized key performance indicator score; Step S4.3: Preset a weight coefficient, perform weighted summation on the normalized key performance indicator score, and calculate the communication quality Q value; Step S4.4: Set a high-quality threshold Q high and a low-quality threshold Q low , and determine the threshold interval where the Q value is located; Step S4.5: According to the interval where the Q value is located, perform the adjustment of the preset hierarchical data distribution strategy; Among them, the key performance indicators (KPIs) include: end-to-end delay L, packet loss rate P, delay jitter J, effective throughput T eff and the occupancy rate B of the client buffer occ .

[0013] Preferably, step S4 includes: Step S4.2 includes: Normalize the key performance indicators (KPIs), and calculate the normalized scores of the key performance indicators respectively; specifically, Calculate the delay score : Set the maximum delay and the ideal delay ; When the scoring function is designed, the latency score is 1 at and 0 at , with a linear decrease in between:

[0014] Calculate the packet loss score : Set the maximum tolerable packet loss rate ; When the scoring function is designed, the packet loss score is 1 at and 0 at :

[0015] Calculate the jitter score : Set the maximum jitter and the ideal jitter , and when the scoring function is designed, the jitter score is 1 at and 0 at , with a linear decrease in between:

[0016] Calculate the throughput score : Set the minimum throughput required for the current test task , and when the scoring function is designed, the throughput score is 1 at and decreases proportionally when the throughput score is lower than the minimum throughput:

[0017] Calculate the buffer score : Set the warning threshold and critical threshold of the buffer occupancy rate and , and when the scoring function is designed, the buffer score is 1 at and 0 at , with a linear decrease in between:

[0018] In the above functions, min(·) represents calculating the minimum value, and max(·) represents calculating the maximum value; Step S4.3 includes: calculating the Q value; specifically, Set the weight coefficient , and make the weight coefficient satisfy ; Then the Q value is

[0019] Among them, correspond to the weight coefficients of the KPIs respectively; Step S4.5 includes: selecting a distribution strategy for hierarchical data according to the interval where the Q value is located, and correspondingly adjusting at least one of the data publishing rate, the internal message cache of the DDS Agent proxy, and the quality of service of DDS; specifically, When it indicates that the current network link state is excellent, the adjustment strategy is: lifting or relaxing the restriction on the data publishing rate, reducing the cache occupancy, setting the maximum data transmission throughput, and minimizing the end-to-end communication delay; When it indicates that the current network link quality has declined to a certain extent, the adjustment strategy is: taking preventive measures, reducing the publishing frequency of non-critical or high-delay-tolerant data, moderately increasing the cache, and improving the QoS service quality, actively alleviating the network pressure, and giving priority to ensuring the transmission quality of important data; When it indicates that the current network link quality has deteriorated severely, the adjustment strategy is: adopting the most conservative transmission strategy, reserving the transmission channel for the highest-priority data and ensuring priority transmission, and expanding the internal message cache capacity to the preset maximum allowable value to ensure the reliable transmission of the highest-priority core instructions and key safety status data.

[0020] Preferably, the said Step S5 includes: Step S5.1: The test platform receives and analyzes the real-time test data. If abnormal real-time test data is analyzed, it enters Step S5.2. If normal real-time test data is analyzed, it continues to receive data; Step S5.2: The test platform extracts the time-series data features and static data features from the abnormal real-time test data; Step S5.3: Input the time-series data features into the time-series processing branch of the pre-trained machine learning model for processing to obtain a time-series processing result; Step S5.4: Input the static data features into the static data processing branch of the pre-trained machine learning model for processing to obtain a static processing result; Step S5.5: Fuse the time-series processing result and the static processing result; Step S5.6: According to the fused result, output the prediction of the cause of the fault. At the same time, in combination with the real-time test data, the test platform simulates the actual situation of the wing to form a digital twin model, locates the fault position on the digital twin model, and performs high-light display and annotation.

[0021] According to an aircraft wing section test system based on DDS provided by the present invention, it includes: A test platform, a DDS Agent proxy, and one or more hardware test modules are connected in sequence through a data communication link established by DDS between the test platform, the DDS Agent proxy, and the hardware test modules; Test platform: The test platform is built based on digital twins and is used to load and run the digital twin model of the wing section. It receives and analyzes the real-time test data fed back by the hardware test module through the internal test platform DDS communication module to achieve real-time mapping between the physical hardware state and the virtual model state of the wing; it is used to monitor the test data and perform visual warnings; it integrates intelligent fault diagnosis capabilities and is used to automatically track and visually locate the fault chain using machine learning; it is used to manage real-time test data; it is also used to send test instructions; DDS Agent proxy: Connected to the test platform and the hardware test module, it is based on DDS topics and is used to forward test instructions and real-time data bidirectionally; it sets the communication quality evaluation Q value, which is used to evaluate the network communication quality in real time and dynamically adjusts the data distribution strategy according to the Q value to ensure the reliability of data transmission; Hardware test module: Configured at specific positions on the wing, it is used to actually measure or control specific parameters of the aircraft wing according to the test instructions issued by the test platform and feedback the real-time test data to the test platform through DDS.

[0022] Preferably, the test platform includes: Test platform DDS communication module: Used to create DDS publishers and subscribers, associated with the DDS Agent proxy through DDS topics, and perform data transceiver and parsing based on a predefined standardized instruction frame format; Wing twin model module: Used to load, manage, and run the three-dimensional digital twin model of the wing section, and update the model state according to the real-time test data received by the test platform DDS communication module to achieve synchronization between the physical test of the wing and the test state of the virtual wing section; Monitoring and warning module: Used to verify according to the real-time test data fed back by the operation of the hardware test module and the preset data range, and trigger visual warnings when abnormalities are found; Intelligent fault diagnosis module: Based on machine learning technology, it is used to establish the mapping relationship between fault modes and data characteristics by cleaning historical data and training models; when the monitoring and warning module detects an abnormality, it automatically extracts the abnormal data characteristics, inputs them into the pre-trained model for calculation, predicts the cause of the fault, traces its propagation path, highlights the fault source and associated components on the visualization interface of the wing twin model module, and outputs diagnostic suggestions; Test management module: Used for the configuration, import, saving, and execution control of test cases, and is responsible for collecting test process data, warning records, and diagnostic results.

[0023] Preferably, the intelligent fault diagnosis module includes: Pre-trained fault diagnosis model sub-module: Based on historical time-series test data and static test data and their corresponding known fault cause labels, it is a fault classification model trained through a hybrid input neural network model architecture; the core function of the fault classification model is to establish a mapping relationship between the input data features and specific fault cause categories, and give predicted fault causes for abnormal test data; Test data extraction sub-module: Used to obtain the currently monitored abnormal test data from the monitoring and alarm module in real time during the test, and perform feature engineering processing, including calculating statistical features and performing normalization processing; Fault location sub-module: Used to receive the fault category prediction result output by the pre-trained fault diagnosis model for the current test data feature vector; when the prediction result indicates a specific fault, it is used to parse and map this fault category information to specific components or three-dimensional spatial positions in the digital twin model of the aircraft wing section, trigger the wing twin model module, and highlight and label the located components or areas on the visualization interface.

[0024] Preferably, the hardware test module includes: Hardware test DDS communication module: Used to handle the connection with DDS and data transceiver, and send data in a predefined standard format; according to the test instructions, it is used to identify whether a specific field is relevant to itself. If it is relevant, the test is executed, and if it is not relevant, the message is discarded; Physical measurement and control module: Includes sensors and actuators, which are used to directly interact with the aircraft wing section, perform measurement or control operations, and feedback real-time measurement data; Data preprocessing module: After filtering and calibrating the raw data from the physical measurement and control module locally, it is sent through the hardware test DDS communication module; It also includes multiple test channels, and each test channel corresponds to a different control word, which is used to execute different test operations.

[0025] Preferably, the DDS Agent proxy includes: Data forwarding module: Used to forward the test platform and hardware test module instructions and real-time test data bidirectionally, and is in the same DDS domain as the test platform and hardware test module; the same type of hardware test module and the DDS Agent proxy are associated with the same topic. When the DDS Agent proxy receives the test instructions from the test platform, it is used to forward the data to all hardware test modules associated with the topic at the same time; Q-value real-time calculation module: used to calculate the communication quality evaluation index Q-value; used to quantitatively evaluate communication quality, by continuously monitoring the key performance indicators of the communication link, and used to normalize the key performance indicators; Communication strategy dynamic adjustment module: according to the preset Q-value threshold interval, used to automatically execute the corresponding adjustment and distribution strategy, and the adjusted content includes: adjusting the data publishing rate, adjusting the internal message cache size of the Agent, and dynamically modifying the QoS service quality of DDS.

[0026] Compared with the prior art, the present invention has the following beneficial effects: 1. The test platform constructed based on digital twin in the present invention enables testers to intuitively and comprehensively monitor the integration status and dynamic behavior of the aircraft wing section through real-time mapping and visualization interface, and timely discover problems through visual alarm.

[0027] 2. The present invention integrates an intelligent fault diagnosis module, uses machine learning to automatically track the fault chain and locate the root cause, and visually presents the results on the digital twin model, greatly shortening the fault troubleshooting time and improving the diagnostic accuracy.

[0028] 3. The present invention innovatively introduces the Q-index to evaluate the network quality in real time at the DDS Agent proxy end, and dynamically adjusts the communication strategy according to the Q-value, which can actively cope with network fluctuations, effectively avoid the loss or delay of key test data, and ensure the reliability of test results.

[0029] 4. The present invention integrates the system architecture to achieve unified, efficient and intelligent management of distributed hardware test modules, improving the test automation level and overall efficiency. Description of the Drawings

[0030] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, purposes and advantages of the present invention will become more obvious: Figure 1 It is a schematic flow chart of a method for testing an aircraft wing section based on DDS of the present invention; Figure 2 It is a schematic diagram of the composition of a test system for an aircraft wing section based on DDS in Embodiment 1 of the present invention; Figure 3 It is a block diagram of a test platform of a test system for an aircraft wing section in Embodiment 1 of the present invention; Figure 4 It is a block diagram of a communication protocol format of the present invention in Embodiment 1. Detailed Embodiments

[0031] The present invention will be described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several changes and improvements can still be made. These all belong to the protection scope of the present invention.

[0032] The object of the present invention is to provide a method and system for testing aircraft wing segments based on DDS, so as to solve the problems of complicated functional integrity and state consistency test steps, low test efficiency, and lack of efficient and unified test control in the existing wing test scenarios.

[0033] A method for testing aircraft wing segments based on DDS includes: Step S1: Establish a data communication link between the test platform, the DDS Agent proxy and one or more hardware test modules through DDS; Step S2: Make the test platform send a test instruction, and the test instruction is forwarded to one or more hardware test modules through the DDS Agent proxy; at the same time, make the hardware test module execute the wing test operation to obtain real-time test data; Step S3: The hardware test module feeds back the real-time test data to the test platform through the DDS communication environment; Step S4: During the process of sending the test instruction and feeding back the real-time test data, make the DDS Agent proxy calculate the communication quality Q value for the DDS communication environment, and dynamically adjust the data distribution strategy of the data distribution service according to the Q value; Step S5: Based on the adjusted distribution strategy, the test platform receives and analyzes the real-time test data, performs fault diagnosis based on machine learning. The fault diagnosis processes the time-series test data and static test data respectively, and fuses the processing results to determine the cause of the fault, and locates the fault position on the digital twin model in the test platform.

[0034] Specifically, step S1 includes: Step S1.1: Configure the test platform, the DDS Agent proxy and all hardware test modules in the same DDS domain; among them, there are one or more hardware test modules, which are configured at specific positions on the wing according to needs; Step S1.2: Make the test platform, the DDS Agent proxy and the hardware test module establish a data communication link through DDS in sequence; specifically, between the test platform and the DDS Agent proxy, and between the DDS Agent proxy and one or more hardware test modules, establish a data communication link with a publish-subscribe relationship based on a predefined DDS topic for forwarding test instructions and real-time test data; among them, the real-time test data includes time-series test data and static test data.

[0035] Specifically, step S4 includes: Step S4.1: The DDS Agent proxy end real-time monitors the key performance indicators (KPIs) of the data communication link; Step S4.2: Normalize the monitored key performance indicators (KPIs) to obtain the normalized key performance indicator scores; Step S4.3: Preset the weight coefficients, perform weighted summation on the normalized key performance indicator scores, and calculate the communication quality Q value; Step S4.4: Set the high-quality threshold Q high and the low-quality threshold Q low , and determine the threshold interval where the Q value is located; Step S4.5: According to the interval where the Q value is located, execute the adjustment of the preset hierarchical data distribution strategy; the adjustment actions include: adjusting the data publishing rate, adjusting the internal message buffer size of the DDS Agent proxy end, and modifying at least one of the quality of service (QoS) policies of DDS.

[0036] Among them, the key performance indicators (KPIs) include: end-to-end delay L, packet loss rate P, delay jitter J, and effective throughput T eff and the occupancy rate B of the proxy end buffer occ .

[0037] Specifically, step S4 includes: Step S4.2 includes: Normalize the key performance indicators (KPIs), and calculate the normalized scores of the key performance indicators respectively; specifically, Calculate the delay score : Set the maximum delay and the ideal delay ; The scoring function is designed to be 1 when the delay score is , and 0 when the delay score is , with a linear decrease in between:

[0038] Calculate the packet loss score : Set the maximum tolerable packet loss rate ; The scoring function is designed to be 1 when the packet loss score is , and 0 when the packet loss score is :

[0039] Calculate the jitter score : Set the maximum jitter and the ideal jitter , and the scoring function is designed to be that the jitter score is is 1 when the jitter score is is 0 when the jitter score is

[0040] Calculate the throughput score : Set the minimum throughput required for the current test task , and the scoring function is designed such that the throughput score is is 1 when the throughput score is

[0041] Calculate the buffer score : Set the warning threshold and critical threshold of the buffer occupancy rate and critical threshold , and the scoring function is designed such that the buffer score is is 1 when the buffer score is is 0 when the buffer score is

[0042] In the above functions, min(·) represents calculating the minimum value, and max(·) represents calculating the maximum value; Step S4.3 includes: calculating the Q value; specifically, Set the weight coefficients , and make the weight coefficients satisfy ; then the Q value is

[0043] where correspond to the weight coefficients of the KPIs respectively; the selection of the weight coefficients is based on the importance of the key performance indicators.

[0044] Step S4.5 includes: selecting the distribution strategy of the hierarchical data according to the interval where the Q value is located, and correspondingly adjusting at least one of the data publishing rate, the internal message cache of the DDS Agent proxy, and modifying the quality of service of DDS; specifically, When , it indicates that the current network link state is excellent, and the adjustment strategy is: lift or relax the restriction on the data publishing rate, reduce the cache occupancy, set the maximum data transmission throughput, and minimize the end-to-end communication delay; When , it indicates that the quality of the current network link has decreased to a certain extent, and the adjustment strategy is: take preventive measures, reduce the publishing frequency of non-critical or high-delay-tolerant data, moderately increase the cache, improve the QoS service quality, actively relieve the network pressure, and give priority to ensuring the transmission quality of important data; When When it indicates that the current network link quality has severely deteriorated, the adjustment strategy is as follows: adopt the most conservative transmission strategy, reserve the transmission channel for the data with the highest priority and ensure its priority transmission, expand its internal message buffer capacity to the preset maximum allowable value, and ensure the reliable transmission of the core instructions and key safety status data with the highest priority.

[0045] Specifically, step S5 includes: Step S5.1: The test platform receives and analyzes the real-time test data. If abnormal real-time test data is analyzed, it proceeds to step S5.2. If normal real-time test data is analyzed, it continues to receive data; Step S5.2: The test platform extracts the time series data features and static data features from the abnormal real-time test data; Step S5.3: Input the time series data features into the time series processing branch (including the long short-term memory network LSTM) in the pre-trained machine learning model for processing to obtain the time series processing result; Step S5.4: Input the static data features into the static data processing branch (including at least one fully connected layer) in the pre-trained machine learning model for processing to obtain the static processing result; Step S5.5: Fuse the time series processing result and the static processing result; Step S5.6: According to the fused result, output the prediction of the cause of the fault. At the same time, in combination with the real-time test data, the test platform simulates the actual situation of the wing to form a digital twin model, locates the fault position on the digital twin model, and performs highlighting and annotation. In a preferred embodiment, the normal wing parameter range can be set, and the digital twin model is compared with the normal wing parameter range in real time. The position where the digital twin model is not within the normal parameter range is marked as the fault position. At the same time, a fault library is set up, and according to the analysis of the part exceeding the parameter range, the corresponding fault is matched in the fault library, and the cause of the fault is speculated.

[0046] The present invention also provides an aircraft wing section test system based on DDS. The aircraft wing section test system based on DDS can be implemented by executing the process steps of the aircraft wing section test method based on DDS, that is, those skilled in the art can understand the aircraft wing section test method based on DDS as the preferred implementation manner of the aircraft wing section test system based on DDS.

[0047] An aircraft wing segment test system based on DDS, comprising: a test platform, a DDS Agent proxy, and one or more hardware test modules, which are sequentially connected through a data communication link established by DDS between the test platform, the DDS Agent proxy, and the hardware test modules; Test platform: The test platform is built based on digital twin, used to load and run the digital twin model of the wing segment, receive and parse the real-time test data fed back by the hardware test module through the internal test platform DDS communication module, and realize the real-time mapping between the physical hardware state and the virtual model state of the wing; used to monitor the test data and perform visual alarm; integrated with intelligent fault diagnosis ability, used to automatically track and visually locate the fault chain by using machine learning; used to manage real-time test data; also used to send test instructions; DDS Agent proxy: Connected to the test platform and the hardware test module, based on the DDS topic, used to forward test instructions and real-time data bidirectionally; set the communication quality evaluation Q value, used to evaluate the network communication quality in real time, and dynamically adjust the data distribution strategy according to the Q value to ensure the reliability of data transmission; Hardware test module: Configured at specific positions of the wing, used to actually measure or control specific parameters of the aircraft wing according to the test instructions issued by the test platform, and feed back the real-time test data to the test platform through DDS.

[0048] Specifically, the test platform includes: Test platform DDS communication module: Used to create DDS publishers and subscribers, associated with the DDS Agent proxy through the DDS topic, and perform data transceiver and parsing based on the predefined standardized instruction frame format; Wing twin model module: Used to load, manage and run the three-dimensional digital twin model of the wing segment, and update the model state according to the real-time test data received by the test platform DDS communication module, realizing the synchronization of the wing physical test and the virtual wing segment test state; Monitoring and alarm module: Used to verify according to the real-time test data and data range fed back by the operation of the hardware test module, and trigger a visual alarm when an abnormality is found; Intelligent fault diagnosis module: Based on machine learning technology, used to establish the mapping relationship between the fault mode and the data characteristics by cleaning historical data and training the model; when the monitoring and alarm module detects an abnormality, automatically extract the abnormal data characteristics, input them into the pre-trained model for calculation, predict the cause of the fault, trace its propagation path, highlight the fault source and associated components on the visualization interface of the wing twin model module, and output diagnostic suggestions; Test management module: Used for the configuration, import, saving, and execution control of test cases, and responsible for collecting test process data, alarm records, and diagnostic results.

[0049] Specifically, the intelligent fault diagnosis module includes: a pre-trained fault diagnosis model sub-module: a fault classification model trained based on historical time-series test data, static test data, and their corresponding known fault cause labels through a hybrid input neural network model architecture; the core function of the fault classification model is to establish a mapping relationship between the input data features and specific fault cause categories, and give predicted fault causes for abnormal test data; a test data extraction sub-module: used to obtain the currently monitored abnormal test data from the monitoring and alerting module in real time during the test, and perform feature engineering processing, including calculating statistical features and performing normalization processing; a fault location sub-module: used to receive the fault category prediction result output by the pre-trained fault diagnosis model for the current test data feature vector; when the prediction result indicates a specific fault, it is used to parse and map this fault category information to specific components or three-dimensional spatial positions in the digital twin model of the aircraft wing section, trigger the wing twin model module, and highlight and label the located components or areas on the visualization interface.

[0050] Specifically, the hardware test module includes: a hardware test DDS communication module: used to handle the connection with DDS and data transceiver, and send data in a predefined standard format; according to the test instruction, it is used to identify whether a specific field is relevant to itself. If it is relevant, the test is executed; if it is not relevant, the message is discarded; a physical measurement and control module: including sensors and actuators, used to directly interact with the aircraft wing section, perform measurement or control operations, and feedback the real-time measurement data; a data preprocessing module: filter and calibrate the raw data from the physical measurement and control module locally, and then send it through the hardware test DDS communication module; it also includes multiple test channels, each test channel corresponding to a different control word, used to execute different test operations.

[0051] Specifically, the DDS Agent proxy side includes: a data forwarding module: used to forward the test platform and hardware test module instructions and real-time test data bidirectionally, and is in the same DDS domain as the test platform and hardware test module; the same type of hardware test module and the DDS Agent proxy side are associated with the same topic. When the DDS Agent proxy side receives the test instruction from the test platform, it is used to forward the data to all hardware test modules associated with the topic at the same time; a Q value real-time calculation module: used to quantitatively evaluate the communication quality, by continuously monitoring the key performance indicators of the communication link, including end-to-end delay L, packet loss rate P, delay jitter J, etc., used to normalize the key performance indicators; and used to calculate the communication quality evaluation index Q value; a communication strategy dynamic adjustment module: according to the preset Q value threshold interval, used to automatically execute the corresponding adjustment and distribution strategy, and the adjusted content includes: adjusting the data publishing rate, adjusting the internal message cache size of the Agent, and dynamically modifying the QoS service quality of DDS.

[0052] Example 1 As shown in the figure Figures 2 - 3 a DDS-based aircraft wing test system 1 is provided, including: a test platform 10 deployed on an industrial control computer, a DDS Agent proxy, and a hardware test module 30. The test platform 10 is the core control and analysis unit of this system, and its specific composition is also referred to Figure 3 As shown in the figure, it is used for receiving and parsing instruction data, updating the virtual wing twin model, monitoring test data, intelligently diagnosing the causes of test failures, and test management, corresponding to the test platform DDS communication module 101, the wing twin model module 102, the monitoring and alarm module 103, the intelligent fault diagnosis module 104, and the test management module 105 respectively. Among them, the test management module 105 includes use case configuration reading, which is used for serializing and deserializing use case configurations, and can flexibly modify the original use cases according to specific requirements, improving the reusability of test cases and further reducing the test time consumption; in a preferred embodiment, a test report can also be generated. The test report mainly includes the test time, the test executor, the test items carried out, the test conclusion, and the specific problems found in the test, etc., and specifically displays the test report; the functions of importing and exporting test cases.

[0053] According to the above embodiment, relying on the test management module 105, corresponding test cases can be selected according to the test request, thereby improving the test efficiency. And through visual operation, the addition and modification of test cases can be realized, improving the expandability and maintainability of test cases.

[0054] The DDS Agent proxy and the test platform are in the same DDS Domain to ensure the establishment of a communication connection. In the test process, the data forwarding module 201 is relied on to forward the instructions and data between the test platform and the hardware test module bidirectionally. The Q-value real-time calculation module 203 and the communication strategy dynamic adjustment module 202 adjust the data distribution strategy in real time according to the network communication status. The hardware test module 30 establishes a communication connection with the DDS Agent proxy through the internal hardware test DDS communication module, receives and executes the relevant instructions of the test platform, and uploads the test measurement results through the DDS Agent proxy. The hardware test module 30 also includes a data preprocessing module 302, which is used for filtering and calibrating the raw data from the internal physical measurement and control module and then sending it through the hardware test DDS communication module. Further, in a preferred embodiment, the communication format 40 between the test platform and the hardware test module meets the specified string format, such as Figure 4As shown below, a specific embodiment is as follows: The control protocol frame header is 55, and the frame tail is AA. After removing the frame header and frame tail, the first 2 bits are the test category. The test category field is shifted 2 bits to the right to obtain the hexadecimal test module number, supporting up to 256 test modules. The test module number is shifted 2 bits to the right to obtain the specific operation control word.

[0055] The heartbeat protocol frame header is 66, and the frame tail is AA. After removing the frame header and frame tail, the first 2 bits are the test category. The test category field is shifted 2 bits to the right to obtain the hexadecimal test module number, supporting up to 256 test modules. The test module number field is shifted 2 bits to the right to obtain the online status. Regarding the functions of the specific system modules: An industrial control computer deploys a test platform, which is used to send and receive hardware test instructions, synchronize the status of the wing twin model, perform intelligent fault diagnosis, monitor and alarm test data, and manage test cases and test reports. The hardware test module contains a physical measurement and control module inside, which is used to accurately measure and control the wing rotation angle, cable continuity, fuel tank oil temperature, etc. The DDS Agent proxy is in the same DDS domain as the DDS communication module of the test platform, and is used to forward the instructions and data between the test platform and the hardware test module bidirectionally.

[0056] The DDS-based aircraft wing section test system provided according to the above technical points includes an industrial control computer, a DDS Agent proxy, and a hardware test module. On the industrial control computer, a test platform is deployed. The test platform internally includes a test platform DDS communication module, a wing twin model module, a monitoring and alarm module, an intelligent fault diagnosis module, and a test management module. The DDS Agent proxy can be deployed on the industrial control computer or other supported hardware devices, proxying all test data of the hardware test module, and at the same time associating with the corresponding Topic topic of the test platform to ensure real-time instruction data exchange between the test platform and the hardware test module. The hardware test module monitors or measures the status of the aircraft wing, uploads the status and values of the measured items to the test platform in a specified format and executes the test platform instructions. The instructions can include abnormal working conditions and boundary scenarios to meet the test requirements of functional integrity and status consistency in different scenarios and improve the reliability of test results. Moreover, by integrating the test platform DDS communication module in the test platform, the visualization interface can automatically complete various data operation logics such as instruction generation, instruction sending, and parsing verification, greatly reducing the consumption of test man-hours. Furthermore, through the combined storage and import use of test cases, manual repetitive operations by testers are avoided, thereby improving the test efficiency.

[0057] Furthermore, the test platform also includes a wing twin model module. The wing twin synchronizes with the actual hardware test module according to the parsed hardware data. After receiving the test module data through DDS, it parses the data and updates the state of the twin in the rendering scene in real time according to the parsed status or measurement value, enabling testers to intuitively discover abnormal situations during the test. The DDS communication module of the test platform embedded in the test platform needs to be integrated with the data processing method for easy invocation.

[0058] According to the above technical means, hardware test modules of the same category are associated with the same Topic. When the DDS Agent proxy end receives the test platform instruction, it will forward the data to all test modules associated with the Topic at the same time. The hardware test module identifies whether it is relevant to itself according to the test module field in the instruction data. If it is relevant, it will proceed to the next step; if it is not relevant, it will discard the message. When the hardware test module needs to forward the test data to the test platform, it still follows the above protocol format.

[0059] According to the above technical means, the aircraft wing section test system can configure and automatically execute test cases, parse data, and update the state of the aircraft twin in the scene in real time according to the specific test scenario, improving the test efficiency.

[0060] There is also provided a DDS-based aircraft wing section test method. The wing section test method includes: First, establish a data communication link between the test platform 10 (through its test platform DDS communication module 101), the DDS Agent proxy end 20, and one or more hardware test modules 30 (through their hardware test DDS communication modules 301) through DDS. During the test, the test platform 10 (initiated by the test management module 105 and through the internal test platform DDS communication module) sends a test instruction, which is efficiently forwarded by the DDS Agent proxy end 20 (mainly through its data forwarding module 201) to the hardware test module 30; the hardware test module 30 (its physical measurement and control module 303) performs the wing test operation and obtains real-time test data. The obtained real-time data is then reliably fed back from the hardware test module 30 to the test platform 10 through the DDS Agent proxy end 20. During the entire instruction and data interaction process, the DDS Agent proxy end 20 (through its Q-value real-time calculation module 203 and communication strategy dynamic adjustment module 202) continuously evaluates and optimizes the DDS communication quality and data distribution strategy. Finally, the test platform 10 receives and analyzes the feedback real-time test data (performed by the monitoring and warning module 103, etc.), executes the machine learning-based fault diagnosis provided by the intelligent fault diagnosis module 104 to determine the cause of the fault, and synchronously updates the diagnosis result and real-time status to the digital twin model managed by the wing twin model module 102 to achieve visual positioning of the fault.

[0061] Further, in a preferred embodiment, the steps for the test platform to construct instructions in a specified format according to the visual operations of the testers include: determining the first four specified digits according to the selected test category and test module; splicing the specified operation control word according to the specific test requirements and operations, and calling the DDS communication module interface of the test platform to send messages; finally, saving or deleting the test cases for this operation according to the test needs.

[0062] Further, saving the test cases includes normal scenario test cases and abnormal scenario test cases, which are used to more comprehensively cover the test requirements and improve the test coverage rate and test reliability.

[0063] Embodiment 2 In a preferred embodiment, the data distribution process of the dynamic data distribution service is specifically as follows: Data forwarding: Bidirectionally forward the instructions and test data between the test platform and the hardware test module, and the test platform, the hardware test module are in the same DDS domain. Based on the DDS Topic, bidirectionally forward the instructions and data between the test platform and the hardware test module. The hardware test modules of the same category are associated with the same Topic by the DDS Agent proxy. When the DDS Agent proxy receives the test platform instructions, it will forward the data to all the hardware test modules associated with the Topic at the same time. The hardware test module identifies whether it is relevant to itself according to the specific fields in the instructions. If it is relevant, it will execute the test. If it is not relevant, it will discard the message.

[0064] Real-time Q value calculation: This is used to quantitatively evaluate the communication quality. By continuously monitoring the key performance indicators (KPIs) of the communication link, including end-to-end delay (L), packet loss rate (P), delay jitter (J), etc., and normalizing these indicators, according to the preset weights perform weighted summation to calculate the real-time communication quality evaluation index , where is the score of the key performance indicator after normalization; Dynamic adjustment of communication strategy: Receive the Q value output by the real-time Q value calculation module and dynamically optimize the communication, which is another innovation point of the present invention. According to the preset Q value threshold interval, automatically execute the corresponding adjustment strategies, including: adjusting the data publishing rate, adjusting the internal message cache size of the Agent, dynamically modifying the QoS strategy of DDS, to ensure the data transmission reliability of the wing section test.

[0065] The main steps are as follows: 1. Select and measure the key performance indicators To comprehensively evaluate the communication quality, select the following KPIs that have a significant impact on the test data interaction of the aircraft wing for real-time monitoring: End-to-end delay (L): It reflects the transmission time of instructions or data from the sender to the receiver, with the unit of millisecond (ms). For wing control instructions or high-frequency status feedback, low delay is crucial. L is measured through the timestamp mechanism built into DDS.

[0066] Packet loss rate (P): It indicates the proportion of lost data packets during transmission and is a core indicator for measuring connection reliability. It is accurately calculated through the confirmation mechanism provided by DDS's RELIABLE QoS or statistically counted and compared with the serial numbers of the test platform and hardware test module under BEST_EFFORT QoS. P is a dimensionless ratio, and P ∈ [0,1].

[0067] Delay jitter (J): That is, the variation of the end-to-end delay, which is measured using the standard deviation of the end-to-end delay L, with the unit of millisecond (ms).

[0068] Effective throughput ( T eff ): It represents the amount of effective data successfully transmitted per unit time, with the unit of Mbps. It can determine whether the current test transmission rate meets the test requirements and is obtained by monitoring the actual test data traffic.

[0069] Proxy-side buffer occupancy rate ( B occ ): It indicates the current filling degree of the buffer queue used for sending and receiving DDS messages inside the DDS Agent proxy side, expressed as a proportion (0 - 1). High occupancy rate is a direct manifestation of network congestion and is obtained in real time by the internal monitoring mechanism of the Agent.

[0070] 2. Normalize key performance indicators Since the dimensions, value ranges, and evaluation directions (the larger the value, the better / the smaller the value, the better) of each KPI are different, it is necessary to uniformly map them to a dimensionless scoring range of [0, 1], where 1 represents the best communication quality and 0 represents the worst communication quality. The following normalization function is adopted , and set the threshold in combination with the specific requirements of aircraft wing testing: Delay score ( ): Set the maximum acceptable delay and the ideal delay . The scoring function is designed to be 1 when , 0 when , and linearly decreasing in between:

[0071] Packet loss score ( ): Set the maximum tolerable packet loss rate . The scoring function is designed to be at is 1 at and 0 at

[0072] Jitter score ( ): Similar to the latency, set the maximum acceptable jitter and the ideal jitter :

[0073] Throughput score ( ): Set the minimum throughput required for the current test task . The scoring function is 1 at and decreases proportionally when below the requirement:

[0074] Buffer score ( ): Set the warning threshold and the critical threshold of the buffer occupancy rate. The scoring function is 1 at and 0 at

[0075] In the above functions, min(·) represents calculating the minimum value, and max(·) represents calculating the maximum value. L, P, J, T, B OCC respectively represent the currently measured latency, packet loss rate, jitter, throughput, and buffer value sizes.

[0076] 3. Weighted fusion to calculate the comprehensive Q value Sum the above-normalized KPI scores according to their relative importance to communication reliability in the aircraft wing section test scenario to obtain the final comprehensive communication quality evaluation index . The weight coefficient ( ) is set by domain experts and satisfies , is the normalized score of the corresponding KPI.

[0077]

[0078] In the aircraft wing test, low latency ( ) and zero packet loss ( ) of control commands have the highest priority. Therefore, and are given higher weights (for example, ); For sensor data that requires precise time synchronization, the weight of jitter ( ) also needs to be considered (e.g., ); The importance of throughput ( ) depends on the current amount of data being transmitted. During data-intensive transmission phases it should be increased (e.g., ); The buffer occupancy rate ( ), as an early indicator of congestion, also has a certain weight (e.g., ). This value ( ) is calculated and updated in real time by the value real-time calculation module and provided to the communication policy dynamic adjustment module.

[0079] 4. Dynamic adjustment of communication policy Receive in real time the communication quality evaluation indicators output from the Q-value real-time calculation module , and compare this value with the pre-set high-quality threshold and low-quality threshold . According to the interval in which the value is located, automatically trigger and execute the corresponding hierarchical communication resource management and service quality guarantee policies. These policies aim to dynamically optimize the data publication rate, internal resource allocation of the DDSAgent proxy, and service quality (QoS) parameter configuration of the DDS communication protocol. The ultimate goal is to prioritize the real-time, integrity, and high reliability of critical data transmission in the aircraft wing section test under various network conditions. The specific adjustment strategies to be executed include but are not limited to the following three main levels: Level 1: High-quality communication policy ( ) When the Q value output by the Q-value real-time calculation module reaches or exceeds the pre-set high-quality threshold , it indicates that the current network link state is excellent, with characteristics of high bandwidth, low latency, low packet loss, and low jitter. At this time, the policy goal is: on the premise of ensuring basic communication reliability, maximize the data transmission throughput, minimize the end-to-end communication latency, and make full use of good network resources.

[0080] Specific adjustment actions: Optimization of data publication rate: Remove or relax the restrictions on the data publication rate. Allow the test platform (or when forwarded by the Agent proxy) to publish test instructions and data at the maximum nominal rate according to its application layer requirements or hardware capabilities.

[0081] Internal Cache Resource Management: Maintain the cache space within the DDS Agent proxy for temporarily storing DDS messages to be forwarded or processed at a preset standard or minimum baseline level, reducing unnecessary memory occupancy and avoiding additional processing latency that may be introduced by an overly large cache.

[0082] DDS QoS Policy Configuration: For most non-absolutely critical data streams, it is preferable to adopt a best-effort quality of service level (RELIABILITY QoS = BEST EFFORT). Under this configuration, the DDS middleware minimizes protocol overhead (no need to send acknowledgment messages, no need for retransmission), which helps reduce end-to-end latency. Only for core control instructions or security-related data streams that are explicitly required by the application layer to ensure delivery, retain or configure them with a reliable transmission quality of service level (RELIABILITY QoS = RELIABLE).

[0083] Tier 2: Medium-Quality Communication Strategy ( ) When the Q value output by the Q value real-time calculation module is between the low-quality threshold and the high-quality threshold it indicates that the current network link quality has declined to a certain extent. At this time, the policy objective is: Take preventive measures to actively relieve network pressure, enhance the system's tolerance to network fluctuations, prioritize ensuring the transmission quality of important data, and prevent the communication quality from deteriorating further to a low level.

[0084] Specific adjustment actions: Selective Data Rate Adjustment: Activate a rate control mechanism based on data priority or type. According to the preset data importance level (distinguished by DDS Topic), reduce the publication frequency of non-critical or high-latency-tolerant data to free up network bandwidth and processing resources for critical data.

[0085] Internal Cache Dynamic Expansion: Appropriately increase the internal message cache capacity of the DDS Agent proxy. The increased cache space can more effectively absorb the disorder of packet arrival timing or temporary backlog caused by network jitter or instantaneous congestion, thereby reducing the risk of actively discarding data due to internal cache overflow in the Agent.

[0086] Moderate Enhancement of DDS QoS Policy: According to the data criticality assessment, selectively upgrade the quality of service levels of some important data streams. For example, for the Topic of relatively important test instructions, dynamically adjust the RELIABILITY QoS policy of its publisher from BEST_EFFORT to RELIABLE, enabling the data confirmation and retransmission mechanism at the DDS level to improve its delivery guarantee.

[0087] Level 3: Low-quality communication strategy ( ) when The output of the real-time calculation module Values ​​below the preset low quality threshold , indicating that the current network link quality has seriously deteriorated, with a significant increase in latency, high packet loss rate, high jitter or severe congestion. At this time, the strategy adjustment goal is: in an extremely harsh network environment, adopt the most conservative transmission strategy, sacrifice the overall system throughput and the real-time performance of non-critical data, and strive to ensure the reliable transmission of the highest priority core instructions and key security status data, to ensure the basic controllability and security of the test system.

[0088] Specific adjustment actions: Strict rate control and priority guarantee: Implement enhanced, priority-based traffic scheduling and rate limiting. Reserve transmission channels for the highest priority data and ensure that they are sent first. At the same time, significantly reduce the sending rate of medium priority data and temporarily suspend the transmission of all low priority data until network quality is restored.

[0089] Maximize the use of internal cache: within the memory hardware resource range of the DDS Agent, expand its internal message cache capacity to the preset maximum allowable value, to maximize the buffering of data backlogs caused by severe network congestion, and provide space for subsequent DDS retransmission or data transmission after network recovery.

[0090] Mandatory enablement of high reliability DDS QoS: Mandatory setting of the RELIABILITY QoS policy to RELIABLE for all publishers of data streams identified as critical or important. At the same time, set the HISTORY QoS to KEEP_ALL to ensure that all historical samples are stored for retransmission, and adjust the RESOURCE_LIMITS QoS policy to increase the memory resources used to store samples. These adjustments sacrifice transmission efficiency and increase latency in exchange for the highest possibility of data delivery.

[0091] Example 3 In a preferred embodiment, the fault cause determination and fault location process is as follows: S100: Build a data set based on historical test data and fault data analysis; load the digital twin model of the aircraft wing section into the test platform and configure test cases.

[0092] S101: Divide the historical test data of the wing section into sequential test data and static test data.

[0093] Timing test data represents the preset time window W (Include TMeasure the specified physical quantity that changes continuously within a time step. For example, the sequence of wing rotation angles , the sequence of fuel tank oil temperature , etc. These data form a time series feature matrix , where is the number of time series features, that is, the number of test types. represents the set of real numbers.

[0094] Static test values refer to discrete states or values that remain unchanged within the same time window W or are measured only at specific moments. For example, the on / off state of the preset channel cable , the initial oil temperature at the start of the test , etc. These data form a static feature vector , where is the number of static features.

[0095] S102: Extract data segments from historical test logs and fault analysis data.

[0096] Each data segment consists of time series data within the corresponding time window and static data . Determine the label for each historical sample through the fault analysis data, representing the system state (normal or specific fault cause category) within this time window. Suppose there are a total of K categories (1 normal category + K - 1 fault categories).

[0097] S103: Perform dataset construction and preprocessing.

[0098] Combine all the labeled data segment samples to form a training dataset , where N is the total number of samples. Subsequently, perform normalization. Map the values in X ts and to the interval [0, 1] using min - max scaling, that is . If there are missing values in the data, fill them with the mean of adjacent bits.

[0099] S200: Build a hybrid input neural network model architecture According to the characteristics of time series test data and static test data, adopt a neural network architecture with two independent input branches.

[0100] S201: Build a time series processing branch The input is the normalized time series data matrix: . The core layer uses the existing Long Short-Term Memory (LSTM) network to construct the temporal dependencies in the data, which includes a forget gate , an input gate , and an output gate , a cell state . The core calculation process of state update is as follows: Forget gate : Determines the information to be discarded from the cell state at the previous time step.

[0101]

[0102] Input gate : Determines which new information will be stored in the cell state . It consists of two parts: one is that determines which values to update, and the other is to create a candidate value vector .

[0103]

[0104]

[0105] Cell state : Combines the results of the forget gate and the input gate to update the cell state .

[0106]

[0107] Output gate : Determines which parts of the current cell state will be output as the hidden state .

[0108]

[0109]

[0110] Among them, is the input feature vector at time step , is the hidden state at the current time step, is the hidden state vector at the previous time step ( initialized as a zero vector), is the cell state vector at the previous time step ( initialized as a zero vector), is the size of the LSTM hidden layer. and They are the weight matrices and bias vectors corresponding to the forget gate, input gate, cell state, and output gate respectively. represents the Sigmoid activation function (the output range is (0, 1), ⊙ represents element-wise multiplication, and tanh is the hyperbolic tangent activation function.

[0111] Output: After time steps of processing, the sequential processing branch outputs a vector that can represent the entire input sequence information . That is, the hidden state at the last time step , that is . The vector encapsulates the key dynamic features extracted from the sequential data.

[0112] S202: Build the static data processing branch The input is the normalized static feature vector . To perform feature space transformation and extract more abstract feature representations, is input into two fully connected layers, using the ReLU activation function ( ):

[0113]

[0114]

[0115]

[0116] where and are the weight matrix and bias vector of the two fully connected layers respectively. is the linear calculation result, is the output after the first layer is activated. The final output of this branch is a vector , representing the processed static information, where is the output dimension of the second fully connected layer, is the set of real numbers.

[0117] S203: Fuse the features of sequential data and static data Concatenate the output vector of the sequential processing branch with the output vector of the static data processing branch to obtain a combined feature vector that fuses the information of the two types of data ([;] represents vector concatenation):

[0118] S204: Construct the prediction output of the hybrid model Input the fused feature vectors into the fully connected layer for the final fault classification. The fully connected layer has output neurons ( is the total number of categories, including the normal category and categories of fault causes). Input its output into the Softmax function to convert it into the probability distribution for the corresponding categories. The conversion method is:

[0119] where represents the probability that the model predicts the current input sample belongs to category , is the j th element of the output of the fully connected layer, and satisfies , and exp represents the exponential function.

[0120] S300: Train the hybrid neural network model By learning on the labeled training data set , adjust all the trainable parameters of the entire hybrid neural network model (including the weight matrices and bias vectors ) of all LSTM layers and fully connected layers, so that the prediction results of the model for the training samples are as consistent as possible with the true fault labels. At the same time, select the categorical cross-entropy as the loss function. For example, for a mini-batch of data containing samples and K categories, the formula for its average loss is as follows:

[0121] where is the true label of the th sample (the true category corresponds to , and the rest are 0), is the probability that the model predicts the th sample as category (i.e., the th element of the Softmax output). Use the Adam (Adaptive Moment Estimation) optimizer and combine the backpropagation algorithm to calculate the gradient of the loss function with respect to the model parameters , and update the model parameters , to minimize the loss function . The model training process will iterate through the training dataset for multiple epochs to monitor the training process, adjust hyperparameters, and prevent the model from overfitting. After training is completed, a hybrid neural network model with optimal parameters Θ trained is obtained h(X ts ,X static ; Θ trained ) , and it is deployed into the intelligent fault diagnosis module within the test platform.

[0122] Those skilled in the art know that in addition to implementing the system and its various devices, modules, and units provided by the present invention in the form of pure computer-readable program code, the method steps can be logically programmed to enable the system and its various devices, modules, and units provided by the present invention to be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers, etc., to achieve the same functions. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a kind of hardware component, and the devices, modules, and units included therein for implementing various functions can also be regarded as the structures within the hardware component; the devices, modules, and units for implementing various functions can also be regarded as either software modules for implementing the method or structures within the hardware component.

[0123] The methods, devices, systems, etc. in the embodiments disclosed herein can also be implemented in other forms. For example, the module division of the device is only a logical function division. In actual applications, different division methods can be adopted according to requirements. For example, multiple modules can be combined or integrated into another system, and some features can be omitted or not executed. In addition, the coupling or communication between modules can be direct or can be indirectly implemented through interfaces, devices, or intermediate modules, and the connection form can be electrical, mechanical, or other methods. The separation or combination of modules can be physical or logical, that is, the modules can be centrally deployed or distributed on multiple network nodes.

[0124] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functions, and operations of systems, methods, and computer program products according to embodiments of the present disclosure. Each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code, and these parts may include one or more executable instructions for implementing logical functions. In certain implementations, the functions in the flowchart or block diagram may be executed in an order different from that shown in the accompanying drawings. For example, two consecutive blocks may be executed in parallel, or in the reverse order. Such adjustments can be determined according to actual functional requirements. Each block or a combination of blocks in the block diagram or flowchart may be implemented by a dedicated hardware system, or by a combination of dedicated hardware and computer instructions to perform the specified functions or operations.

[0125] The specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. An aircraft wing section testing method based on DDS, characterized in that, Including: Step S1: Establish a data communication link between the test platform, the DDS Agent proxy and one or more hardware test modules through DDS. Step S2: Cause the test platform to send test instructions, and the test instructions are forwarded to one or more of the hardware test modules via the DDS Agent proxy; at the same time, cause the hardware test modules to perform wing test operations to obtain real-time test data. Step S3: The hardware test module feeds back the real-time test data to the test platform through DDS. Step S4: During the process of sending test instructions and feeding back real-time test data, cause the DDS Agent proxy to calculate the communication quality Q value and dynamically adjust the distribution strategy according to the Q value. Step S5: Based on the adjusted distribution strategy, the test platform receives and analyzes the real-time test data, simultaneously performs fault diagnosis, determines the cause of the fault, and locates the fault position on the digital twin model in the test platform.

2. The method for testing an aircraft wing section based on DDS according to claim 1, characterized in that, The step S1 includes: Step S1.1: Configure the test platform, the DDS Agent proxy and all hardware test modules within the same DDS domain; where the hardware test modules are one or more and are configured at specific positions on the wing as needed. Step S1.2: Cause a data communication link to be established between the test platform, the DDS Agent proxy and the hardware test modules through DDS in sequence; specifically, between the test platform and the DDS Agent proxy, and between the DDS Agent proxy and one or more hardware test modules, a data communication link with a publish-subscribe relationship based on a predefined DDS topic is established for forwarding test instructions and real-time test data; where the real-time test data includes timing test data and static test data.

3. The DDS-based aircraft wing section testing method according to claim 1, characterized in that The step S4 includes: Step S4.1: The DDS Agent proxy monitors the key performance indicators (KPIs) of the data communication link in real time. Step S4.2: Normalize the monitored key performance indicators (KPIs) to obtain a normalized key performance indicator score. Step S4.3: Preset a weight coefficient, perform weighted summation on the normalized key performance indicator score, and calculate the communication quality Q value. Step S4.4: Set the high-quality threshold Q high and the low-quality threshold Q low , and determine the threshold interval where the Q value is located; Step S4.5: According to the interval where the Q value is located, perform adjustment of the distribution strategy for preset hierarchical data. Among them, the key performance indicators KPIs include: end-to-end delay L, packet loss rate P, delay jitter J, and effective throughput T eff and the proxy buffer occupancy rate B occ .

4. The DDS-based aircraft wing section testing method according to claim 3, wherein Step S4 includes: Step S4.2 includes: Normalize the key performance indicators (KPIs) and calculate the normalized scores of the key performance indicators respectively; specifically, Calculation of latency score : Set the maximum latency and the ideal latency ; The scoring function is designed to be 1 when the latency score is and 0 when the latency score is , with a linear decrease in between: Calculate Packet Loss Score : Set the maximum tolerable packet loss rate ; The scoring function is designed such that the packet loss score is 1 when the packet loss score is and 0 when the packet loss score is : Calculate Jitter Score : Set the maximum jitter and the ideal jitter , and the scoring function is designed such that the jitter score is 1 when the jitter score is at , and the jitter score is 0 when the jitter score is at , with a linear decrease in between: Calculate throughput score : Set the minimum throughput required for the current test task , and the scoring function is designed such that the throughput score is 1 when , and it decreases proportionally when the throughput score is lower than the minimum throughput: Calculate buffer score : Set the warning threshold and critical threshold of buffer occupancy rate and critical threshold , the scoring function is designed such that the buffer score is 1 when and 0 when the buffer score is , with a linear decrease in between: In the above function, min(·) represents calculating the minimum value, and max(·) represents calculating the maximum value. Step S4.3 includes: Calculate the Q value; specifically, Set weight coefficients , and make the weight coefficients satisfy ; then the Q value is Among them, correspond to the weight coefficients of the KPIs respectively; Step S4.5 includes: Select the distribution strategy for hierarchical data according to the interval where the Q value is located, and correspondingly adjust at least one of the data publishing rate, the internal message cache of the DDS Agent proxy, and modify the quality of service of DDS; specifically, When indicates that the current network link state is excellent, the adjustment strategy is as follows: lift or relax the restrictions on the data publishing rate, reduce the cache occupancy, set the maximum data transmission throughput, and minimize the end-to-end communication delay; When indicates that the current network link quality has decreased to a certain extent, the adjustment strategy is as follows: take preventive measures, reduce the data publishing frequency of non-critical or high latency tolerance data, moderately increase the cache, improve the QoS service quality, actively relieve network pressure, and give priority to ensuring the transmission quality of important data; When indicates that the current network link quality has severely deteriorated, the adjustment strategy is as follows: adopt the most conservative transmission strategy, reserve the transmission channel for the data with the highest priority and ensure its priority transmission, expand its internal message buffer capacity to the preset maximum allowable value, and ensure the reliable transmission of the core instructions and key safety status data with the highest priority.

5. The DDS-based aircraft wing section testing method according to claim 1, wherein The step S5 includes: Step S5.1: The test platform receives and analyzes real-time test data. If abnormal real-time test data is analyzed, it proceeds to Step S5.

2. If normal real-time test data is analyzed, it continues to receive data. Step S5.2: The test platform extracts the time-series data features and static data features from the abnormal real-time test data. Step S5.3: The time-series data features are input into the time-series processing branch of the pre-trained machine learning model for processing to obtain a time-series processing result. Step S5.4: The static data features are input into the static data processing branch of the pre-trained machine learning model for processing to obtain a static processing result. Step S5.5: The time-series processing result and the static processing result are fused. Step S5.6: Based on the fused result, the prediction of the fault cause is output. At the same time, in combination with the real-time test data, the test platform simulates the actual situation of the wing to form a digital twin model, locates the fault position on the digital twin model, and performs highlighting and annotation.

6. An aircraft wing section test system based on DDS, characterized in that, The system is used to implement the DDS-based aircraft wing section test method described in Claim 1, including: A test platform, a DDS Agent proxy, and one or more hardware test modules. The test platform, the DDS Agent proxy, and the hardware test modules are sequentially connected through a data communication link established by DDS. Test platform: The test platform is built based on digital twins and is used to load and run the digital twin model of the wing section. It receives and analyzes the real-time test data fed back by the hardware test module through the internal test platform DDS communication module to achieve real-time mapping of the physical hardware state and the virtual model state of the wing. It is used to monitor test data and perform visual alarms. It integrates intelligent fault diagnosis capabilities and is used to automatically track and visually locate the fault chain using machine learning. It is used to manage real-time test data. It is also used to send test instructions. DDS Agent proxy: Connected to the test platform and the hardware test module, based on the DDS topic, it is used to forward test instructions and real-time data bidirectionally. It sets the communication quality evaluation Q value to evaluate the network communication quality in real time and dynamically adjusts the data distribution strategy according to the Q value to ensure the reliability of data transmission. Hardware test module: Configured at specific positions on the wing, it is used to actually measure or control specific parameters of the aircraft wing according to the test instructions issued by the test platform and feedback the real-time test data to the test platform through DDS.

7. The DDS-based aircraft wing section test system according to claim 6, wherein The test platform includes: Test platform DDS communication module: Used to create a DDS publisher and subscriber, associated with the DDS Agent proxy through the DDS topic, and perform data sending, receiving, and parsing based on a predefined standardized instruction frame format. Wing twin model module: Used to load, manage, and run the three-dimensional digital twin model of the wing section, and update the model state according to the real-time test data received by the test platform DDS communication module to achieve synchronization of the wing physical test and the virtual wing section test state. Monitoring and Alarm Module: It is used to verify according to the real-time test data fed back by the Hardware Test Module and the preset data range, and trigger visual alarms when abnormalities are found; Intelligent Fault Diagnosis Module: Based on machine learning technology, it is used to clean historical data and train models to establish the mapping relationship between fault modes and data characteristics; when the Monitoring and Alarm Module detects an abnormality, it automatically extracts the abnormal data characteristics, inputs them into the pre-trained model for calculation, predicts the cause of the fault, traces its propagation path, highlights the fault source and related components on the visualization interface of the Wing Twin Model Module, and outputs diagnostic suggestions; Test Management Module: It is used for the configuration, import, saving, and execution control of test cases, and is responsible for collecting test process data, alarm records, and diagnostic results.

8. The DDS-based aircraft wing segment test system according to claim 7, wherein The Intelligent Fault Diagnosis Module includes: Pre-trained Fault Diagnosis Model Sub-module: Based on historical time-series test data, static test data, and their corresponding known fault cause labels, it is a fault classification model trained through a hybrid input neural network model architecture; the core function of the fault classification model is to establish the mapping relationship between input data characteristics and specific fault cause categories, and give predicted fault causes for abnormal test data; Test Data Extraction Sub-module: It is used to obtain the currently monitored abnormal test data from the Monitoring and Alarm Module in real time during the test, and perform feature engineering processing, including calculating statistical features and performing normalization processing; Fault Location Sub-module: It is used to receive the fault category prediction result output by the pre-trained fault diagnosis model for the current test data feature vector; when the prediction result indicates a specific fault, it is used to parse and map this fault category information to specific components or three-dimensional spatial positions in the digital twin model of the aircraft wing section, trigger the Wing Twin Model Module, and highlight and label the located components or areas on the visualization interface.

9. The DDS-based aircraft wing section test system according to claim 6, characterized in that The Hardware Test Module includes: Hardware Test DDS Communication Module: It is used to handle the connection with DDS and data transceiver, and send data in a predefined standard format; according to the test instructions, it is used to identify whether a specific field is relevant to itself. If it is relevant, it performs the test. If it is not relevant, it discards the message; Physical Measurement and Control Module: It includes sensors and actuators, which are used to directly interact with the aircraft wing section, perform measurement or control operations, and feedback the real-time measurement data; Data Preprocessing Module: After filtering and calibrating the raw data from the Physical Measurement and Control Module locally, it is sent through the Hardware Test DDS Communication Module; It also includes multiple test channels, each test channel corresponding to a different control word for performing different test operations.

10. The DDS-based aircraft wing section test system according to claim 6, characterized in that, The DDS Agent includes: Data forwarding module: It is used to forward the instructions and real-time test data between the test platform and the hardware test module bidirectionally, and is in the same DDS domain as the test platform and the hardware test module; Hardware test modules of the same category are associated with the same topic by the DDS Agent proxy. When the DDS Agent proxy receives the test instructions from the test platform, it is used to forward the data to all hardware test modules associated with the topic simultaneously. Q-value real-time calculation module: It is used to calculate the communication quality evaluation index Q-value; It is used to quantitatively evaluate the communication quality. By continuously monitoring the key performance indicators of the communication link, it is used to normalize the key performance indicators. Communication strategy dynamic adjustment module: According to the preset Q-value threshold interval, it is used to automatically execute the corresponding adjustment and distribution strategy. The adjusted content includes: adjusting the data publishing rate, adjusting the internal message cache size of the Agent, and dynamically modifying the QoS service quality of DDS.

Images