AI and digital twinning combined aircraft operating environment simulation method and verification platform

Abstract

The invention relates to the technical field of artificial intelligence and digital twinning, in particular to an AI and digital twinning combined aircraft operation environment simulation method and verification platform, and provides more accurate and practical technical support for research and practice in the aviation field through intelligent data processing and precise analogue simulation. Specifically, detection data recorded in the air are acquired and processed, the AI technology is used for data analysis, and the digital twinning technology is combined to simulate the air operation environment of the aircraft, so that the atmospheric meteorological state during actual flight is accurately simulated. Therefore, not only is the data processing efficiency improved, but also the authenticity and accuracy of flight environment simulation are remarkably improved, and powerful technical guarantee is provided for safety and performance optimization in the aviation field.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence and digital twin technology, and in particular to an aircraft operating environment simulation method and verification platform combining AI and digital twin. Background Art

[0002] In the aviation field, accurate simulation of the flight environment has always been the goal pursued by researchers and engineers. With the advancement of science and technology, especially the rapid development of AI technology and digital twin technology, new possibilities have been provided for the simulation and analysis of the flight environment. However, traditional flight environment simulation methods are often limited by the efficiency of data processing and the authenticity of simulation. Especially when processing large amounts of complex airborne meteorological detection data, traditional methods often find it difficult to achieve accurate matching and efficient analysis. Summary of the invention

[0003] In order to improve the above problems, the present application provides an aircraft operating environment simulation method and verification platform combining AI and digital twins.

[0004] The embodiment of the present application provides an aircraft operating environment simulation method combining AI and digital twins, which is applied to an AI verification platform. The method includes:

[0005] Acquire the airborne meteorological detection data to be processed and acquire the airborne meteorological simulation data of X atmospheric meteorological state tags, wherein each atmospheric meteorological state tag matches one or more airborne meteorological simulation data, and the airborne meteorological simulation data of the X atmospheric meteorological state tags are recorded in an airborne meteorological simulation data pool, where X is not less than 1;

[0006] Determine a simulation matching weight between the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state tags;

[0007] On the basis that the simulation matching weights of the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state labels are both less than the first threshold, and the simulation matching weights of all airborne meteorological simulation data of the first atmospheric meteorological state label and the airborne meteorological detection data to be processed are not less than the second threshold, obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, and the first atmospheric meteorological state label belongs to one of the X atmospheric meteorological state labels;

[0008] On the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, the airborne meteorological detection data to be processed is divided into the airborne meteorological simulation data pool, wherein the airborne meteorological detection data to be processed divided into the airborne meteorological simulation data pool is used as an airborne meteorological simulation data of the first atmospheric meteorological state label, and is used to perform flight environment simulation analysis based on the first atmospheric meteorological state label on the real-time meteorological detection data under the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed.

[0009] Optionally, after obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, the process further includes:

[0010] On the basis that the number of airborne meteorological simulation data of the first atmospheric meteorological state label is not less than the airborne meteorological simulation data number threshold, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the same as the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label, obtaining the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed;

[0011] On the basis that the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed is greater than the meteorological detection signal-to-noise weight of the airborne meteorological simulation data with the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed and having the first atmospheric meteorological state label, the airborne meteorological simulation data with the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed and having the first atmospheric meteorological state label in the airborne meteorological simulation data pool is updated to the airborne meteorological detection data to be processed;

[0012] On the basis that the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed is not greater than the meteorological detection signal-to-noise weight of the airborne meteorological simulation data of the first atmospheric meteorological state label with the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed, the airborne meteorological simulation data of the first atmospheric meteorological state label in the airborne meteorological simulation data pool is not corrected.

[0013] Optionally, updating the airborne meteorological simulation data having the same digital twin experiment configuration parameters of the first atmospheric meteorological state tag as the airborne meteorological detection data to be processed in the airborne meteorological simulation data pool to the airborne meteorological detection data to be processed includes:

[0014] Determine the timeliness coefficient of all airborne meteorological simulation data of the first atmospheric meteorological state tag having the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed in the airborne meteorological simulation data pool;

[0015] The airborne meteorological simulation data with the largest timeliness coefficient of the first atmospheric meteorological state label having the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed in the airborne meteorological simulation data pool is updated as the airborne meteorological detection data to be processed.

[0016] Optionally, the airborne meteorological simulation data pool includes an airborne meteorological simulation information set of a first experimental configuration parameter and an airborne meteorological simulation information set of a second experimental configuration parameter;

[0017] The method further comprises dividing the airborne meteorological detection data to be processed into the airborne meteorological simulation data pool on the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, including:

[0018] On the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the first experiment configuration parameters, the airborne meteorological detection data to be processed are divided into the airborne meteorological simulation information set of the first experiment configuration parameters, and the airborne meteorological detection data to be processed are used to perform flight environment simulation analysis based on the first atmospheric meteorological state label on the real-time meteorological detection data under the first experiment configuration parameters;

[0019] On the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the second experiment configuration parameters, the airborne meteorological detection data to be processed are divided into the airborne meteorological simulation information set of the second experiment configuration parameters, and the airborne meteorological detection data to be processed are used to perform flight environment simulation analysis based on the first atmospheric meteorological state label on the real-time meteorological detection data under the second experiment configuration parameters.

[0020] Optionally, the airborne meteorological simulation information set of the second experiment configuration parameter includes a first airborne meteorological simulation information set and a second airborne meteorological simulation information set;

[0021] The digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are divided into the airborne meteorological simulation information set of the second experiment configuration parameters on the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the second experiment configuration parameters, including:

[0022] The airborne meteorological detection data to be processed is classified into the first airborne meteorological simulation information set on the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are second experiment configuration parameters, and the simulation influence weight of the airborne meteorological detection data to be processed is less than the simulation influence weight threshold;

[0023] The airborne meteorological detection data to be processed is divided into the second airborne meteorological simulation information set on the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the second experiment configuration parameters, and the simulation influence weight of the airborne meteorological detection data to be processed is not less than the simulation influence weight threshold.

[0024] Optionally, after obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, the process further includes:

[0025] The airborne meteorological detection data to be processed is divided into the first airborne meteorological simulation information set on the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed and the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label are both second experiment configuration parameters, and the simulation influence weight of the airborne meteorological simulation data of the first atmospheric meteorological state label whose digital twin experiment configuration parameters are the second experiment configuration parameters is not less than the simulation influence weight threshold, and the simulation influence weight of the airborne meteorological detection data to be processed is less than the simulation influence weight threshold;

[0026] The airborne meteorological detection data to be processed is divided into the second airborne meteorological simulation information set on the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed and the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label are both second experiment configuration parameters, and the simulation influence weight of the airborne meteorological simulation data of the first atmospheric meteorological state label whose digital twin experiment configuration parameters are the second experiment configuration parameters is less than the simulation influence weight threshold, and the simulation influence weight of the airborne meteorological detection data to be processed is not less than the simulation influence weight threshold.

[0027] Optionally, after obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, the process further includes:

[0028] On the basis that the number of airborne meteorological simulation data of the first atmospheric meteorological state label is less than the airborne meteorological simulation data number threshold, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the same as the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label, obtaining the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed;

[0029] On the basis that the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed is greater than the meteorological detection signal-to-noise weight of the airborne meteorological simulation data having the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed and having the first atmospheric meteorological state label, the airborne meteorological detection data to be processed is divided into the airborne meteorological simulation data pool;

[0030] On the basis that the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed is not greater than the meteorological detection signal-to-noise weight of the airborne meteorological simulation data of the first atmospheric meteorological state label with the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed, the airborne meteorological simulation data of the first atmospheric meteorological state label in the airborne meteorological simulation data pool is not corrected.

[0031] Optionally, after obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, the process further includes:

[0032] On the basis that the number of airborne meteorological simulation data of the first atmospheric meteorological state label is less than the airborne meteorological simulation data number threshold, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the same as the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label, obtaining the meteorological state signal-to-noise evaluation vector of the airborne meteorological detection data to be processed;

[0033] On the basis that the simulation matching weight of the meteorological state signal-noise evaluation vector of the airborne meteorological simulation data of the first atmospheric meteorological state label having the same digital twin experiment configuration parameters as the meteorological state signal-noise evaluation vector of the airborne meteorological detection data to be processed is less than the simulation matching weight threshold, the airborne meteorological detection data to be processed is divided into the airborne meteorological simulation data pool;

[0034] On the basis that the simulation matching weight of the meteorological state signal-noise evaluation vector of the airborne meteorological detection data to be processed and the meteorological state signal-noise evaluation vector of the airborne meteorological simulation data of the first atmospheric meteorological state label having the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed is not less than the simulation matching weight threshold, the airborne meteorological simulation data pool is not corrected.

[0035] Optionally, after determining the simulation matching weights of the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state tags, the method further includes:

[0036] On the basis that the simulation matching weights of the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state labels are both less than a first threshold, and the simulation matching weights of all airborne meteorological simulation data of the first atmospheric meteorological state label and the airborne meteorological detection data to be processed are both not less than a second threshold, a first meteorological state simulation viewpoint is generated, wherein the first meteorological state simulation viewpoint is used to reflect that the atmospheric meteorological state label corresponding to the airborne meteorological detection data to be processed is the same as the first atmospheric meteorological state label.

[0037] Optionally, after determining the simulation matching weights of the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state tags, the method further includes:

[0038] On the basis that the simulation matching weight between the airborne meteorological detection data to be processed and any airborne meteorological simulation data of the second atmospheric meteorological state label is not less than the first threshold, a second meteorological state simulation viewpoint is generated, wherein the second meteorological state simulation viewpoint is used to reflect that the atmospheric meteorological state label corresponding to the airborne meteorological detection data to be processed is the same as the second atmospheric meteorological state label.

[0039] Optionally, the acquiring of airborne meteorological simulation data of X atmospheric meteorological state tags includes:

[0040] Acquire X airborne meteorological simulation data groups corresponding to X atmospheric meteorological state tags from an airborne meteorological simulation data pool, wherein the airborne meteorological simulation data groups include at least one batch of airborne meteorological simulation data;

[0041] From the X airborne meteorological simulation data groups, the airborne meteorological simulation data closest to the current meteorological detection period in each airborne meteorological simulation data group is determined to obtain airborne meteorological simulation data of X atmospheric meteorological state labels.

[0042] An embodiment of the present application provides an AI verification platform, comprising at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the above method.

[0043] An embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. The computer program implements the above method when running.

[0044] In the embodiments of the present application, more accurate and practical technical support is provided for research and practice in the aviation field through intelligent data processing and precise simulation. Specifically, by acquiring and processing the detection data recorded in the air, using AI technology for data analysis, and combining digital twin technology to simulate the environment in which the aircraft operates in the air, an accurate simulation of the atmospheric meteorological state during actual flight is achieved. In this way, not only the efficiency of data processing is improved, but also the authenticity and accuracy of flight environment simulation are significantly improved, providing a strong technical guarantee for safety and performance optimization in the aviation field. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flowchart of a method for simulating an aircraft operating environment combining AI and digital twins provided in an embodiment of the present application.

[0046] Figure 2 A schematic diagram of the structure of an AI verification platform provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to better understand the above technical scheme, the technical scheme of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0048] Figure 1 A method for simulating an aircraft operating environment combining AI and digital twins is shown, which is applied to an AI verification platform. The method includes the following steps 110 to 140.

[0049] In an exemplary overall application scenario, the AI ​​verification platform began to perform a critical task: processing and classifying new airborne meteorological detection data. Airborne meteorological detection data are crucial for simulation analysis of the flight environment because they can provide real-time and accurate meteorological information to ensure flight safety.

[0050] First, the AI ​​verification platform obtained a batch of unprocessed airborne meteorological detection data from the data source. These unprocessed airborne meteorological detection data contain rich meteorological information, such as temperature, humidity, wind speed, etc., which are an important basis for analyzing the flight environment. At the same time, the AI ​​verification platform also obtained airborne meteorological simulation data with multiple atmospheric meteorological state labels from the airborne meteorological simulation data pool. The airborne meteorological simulation data has been classified according to different meteorological states (such as sunny, cloudy, rainy, etc.), and each label corresponds to one or more groups of simulation data.

[0051] Next, the AI ​​verification platform begins to determine the simulation matching weights between the airborne meteorological detection data to be processed and the airborne meteorological simulation data of each atmospheric meteorological state label. This step is completed through a complex algorithm that takes into account multiple factors, including the similarity between the data, the distribution of historical data, etc. The calculation of the matching weight is the key to ensuring the accuracy of subsequent classification.

[0052] After calculating the simulation matching weights, the AI ​​verification platform checks whether these weights meet specific conditions. Specifically, if the simulation matching weights of all tags are lower than a preset first threshold value, and the simulation matching weights of all airborne meteorological simulation data and the data to be processed for a specific atmospheric meteorological state tag (such as the "clear sky" tag) are not lower than another preset second threshold value, then the AI ​​verification platform proceeds to the next step.

[0053] At this point, the AI ​​verification platform obtains the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed. These parameters describe how to simulate and reproduce actual meteorological conditions in the digital twin environment. If these parameters are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data under the "Sunny Day" label, the AI ​​verification platform divides the data to be processed into the airborne meteorological simulation data pool and classifies it as an airborne meteorological simulation data under the "Sunny Day" label.

[0054] Finally, these data will be used to simulate and analyze the flight environment based on the "clear sky" label of the real-time meteorological detection data under the configuration parameters of the digital twin experiment. In this way, the AI ​​verification platform can continuously enrich and improve its airborne meteorological simulation data pool, improve the accuracy and reliability of flight environment simulation analysis, and thus provide stronger protection for flight safety.

[0055] It can be seen that the AI ​​verification platform ensures the accurate classification and effective utilization of airborne meteorological detection data through precise algorithms and rigorous logical judgments, which not only improves the efficiency of data processing, but also provides a high-quality data foundation for subsequent flight environment simulation analysis.

[0056] Step 110: obtain the airborne meteorological detection data to be processed and obtain the airborne meteorological simulation data of X atmospheric meteorological state tags, wherein each atmospheric meteorological state tag matches one or more airborne meteorological simulation data, and the airborne meteorological simulation data of the X atmospheric meteorological state tags are recorded in an airborne meteorological simulation data pool, and X is not less than 1.

[0057] In step 110, the airborne meteorological detection data to be processed refers to the raw meteorological data obtained from the airborne meteorological detection equipment, which has not been classified or processed. These data may include various meteorological parameters such as temperature, humidity, wind speed, wind direction, and air pressure, and are an important basis for analyzing the current flight environment conditions. These data need to be classified and processed by the AI ​​verification platform to more accurately reflect the meteorological conditions during the flight.

[0058] Atmospheric meteorological state labels refer to labels used to describe and classify different meteorological states, such as "sunny", "cloudy", "rainy", etc. Each label represents a specific meteorological state and is used to classify airborne meteorological detection data. These labels help the AI ​​verification platform understand and analyze meteorological data more accurately, thereby improving the accuracy of flight environment simulation analysis.

[0059] Airborne meteorological simulation data: These data are based on actual meteorological detection data, which are processed and optimized to simulate and emulate specific meteorological conditions. They are similar to actual detection data, but may have been adjusted to better suit the needs of digital twin experiments or flight environment simulation analysis. These data are critical to verifying the performance and safety of aircraft.

[0060] The airborne weather simulation data pool is a database or data warehouse that stores and manages airborne weather simulation data. It contains a large amount of classified and labeled weather simulation data, which can be retrieved and used as needed. The data pool not only stores historical data, but can also be continuously updated and expanded to meet the ever-changing flight environment simulation needs.

[0061] It can be understood that step 110 is the starting step for the AI ​​verification platform to process airborne meteorological detection data, which mainly involves data acquisition and preparation. First, the AI ​​verification platform obtains the airborne meteorological detection data to be processed from the data source. These data are the latest collected, unprocessed raw meteorological information, containing rich real-time meteorological parameters such as temperature, humidity, wind speed, etc. The accuracy and real-time nature of these data are crucial for subsequent flight environment simulation analysis. At the same time, in this step, the AI ​​verification platform will also obtain airborne meteorological simulation data with X atmospheric meteorological state labels from the airborne meteorological simulation data pool. These data are historical simulation data that are classified and labeled according to different meteorological states (such as sunny, cloudy, rainy, etc.), and each label corresponds to one or more groups of processed simulation data. These data will be used as a reference for comparison and analysis with the airborne meteorological detection data to be processed. X represents the number of atmospheric meteorological state labels, which is an integer not less than 1. This means that in each processing process, the AI ​​verification platform will consider the simulation data of at least one meteorological state label. In fact, depending on the specific needs and the richness of the data, the value of X may be larger, thereby covering more meteorological states. Through this step, the AI ​​verification platform has laid a solid foundation for subsequent data processing and analysis. The combined use of onboard meteorological detection data to be processed and onboard meteorological simulation data will help to more accurately classify new meteorological data and improve the accuracy and reliability of flight environment simulation analysis.

[0062] Step 120: Determine the simulation matching weight between the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state tags.

[0063] In step 120, the simulation matching weight is an indicator used to quantify the similarity between the airborne meteorological detection data to be processed and the airborne meteorological simulation data of each atmospheric meteorological state label. Simply put, it represents the degree of match between the new detection data and the existing simulation data. The calculation of the simulation matching weight can be based on complex algorithms that comprehensively consider multiple dimensions of the data, such as the similarity and distribution characteristics of meteorological parameters such as temperature, humidity, and wind speed. The higher the weight value, the more similar the new detection data is to the simulation data under a certain label, which helps the AI ​​verification platform to more accurately classify and archive new meteorological detection data. By calculating the simulation matching weight, the AI ​​verification platform can more effectively utilize historical data resources and improve the accuracy and efficiency of data processing.

[0064] It can be understood that step 120 is a key link for the AI ​​verification platform to process airborne meteorological detection data, and its main purpose is to determine the simulation matching weight between the airborne meteorological detection data to be processed and the existing airborne meteorological simulation data. In this step, the AI ​​verification platform uses advanced algorithms to conduct in-depth comparison and analysis of the airborne meteorological detection data to be processed and the airborne meteorological simulation data under X atmospheric meteorological state labels. This comparison process not only involves the comparison of a single meteorological parameter, but also comprehensively considers the correlation and overall distribution characteristics between multiple parameters. Through complex calculations, the AI ​​verification platform generates a simulation matching weight value for each set of data comparison. This weight value is actually a quantitative similarity index, which reflects the degree of match between the new detection data and the simulation data under each label. The higher the weight value, the more similar the new data is to the simulation data of a certain label. The importance of this step is that it provides a key decision-making basis for subsequent data classification and archiving. Through the calculation of the simulation matching weight, the AI ​​verification platform can more accurately determine which meteorological state label the new meteorological detection data should be classified under, thereby ensuring the accuracy and completeness of the data pool. This not only helps to improve the efficiency of data processing, but also provides a more reliable data basis for simulation analysis of the flight environment.

[0065] Step 130: On the basis that the simulation matching weights of the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state labels are both less than the first threshold, and the simulation matching weights of all airborne meteorological simulation data of the first atmospheric meteorological state label and the airborne meteorological detection data to be processed are not less than the second threshold, the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are obtained, and the first atmospheric meteorological state label belongs to one of the X atmospheric meteorological state labels.

[0066] In step 130, the digital twin experiment configuration parameters refer to the detailed setting information required when conducting simulation experiments in the digital twin environment. These parameters define how to simulate actual meteorological conditions in a virtual environment, including but not limited to the initial values ​​and changing trends of meteorological elements such as temperature, humidity, wind speed, and wind direction. The setting of these parameters is crucial to ensuring the accuracy and realism of the simulation experiment because they directly affect the meteorological conditions and behavior patterns in the simulation environment. By carefully configuring these parameters, researchers can reproduce specific meteorological conditions in the digital twin environment, thereby gaining a deeper understanding of the performance and safety of the aircraft under different meteorological conditions.

[0067] It can be understood that step 130 is a key decision point in the AI ​​verification platform in the process of processing airborne meteorological detection data. In this step, the AI ​​verification platform makes further data processing decisions based on the previously calculated simulation matching weights. First, the AI ​​verification platform checks the simulation matching weights between the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state labels. If these weights are all lower than a preset first threshold value, this means that the new detection data does not match all existing simulation data very well and is not clearly classified under any existing meteorological state label. Next, the AI ​​verification platform pays special attention to a specific atmospheric meteorological state label (referred to as the "first atmospheric meteorological state label") and checks the simulation matching weights of all airborne meteorological simulation data under this label and the data to be processed. If these weights are not lower than another preset second threshold value, this indicates that the new detection data has a high degree of similarity with the simulation data under this specific label. On the basis of meeting the above two conditions, the AI ​​verification platform further obtains the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed. These parameters are set to reproduce and simulate actual meteorological conditions in a digital twin environment, and they are crucial for subsequent flight environment simulation analysis. The purpose of this step is to provide the necessary configuration information for further data processing and simulation analysis after determining the relationship between the new detection data and the existing data. In this way, the AI ​​verification platform can ensure that subsequent simulation experiments are closer to actual meteorological conditions, thereby improving the accuracy and reliability of simulation results.

[0068] Step 140: On the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, the airborne meteorological detection data to be processed is divided into the airborne meteorological simulation data pool, wherein the airborne meteorological detection data to be processed divided into the airborne meteorological simulation data pool is used as an airborne meteorological simulation data of the first atmospheric meteorological state label, and is used to perform flight environment simulation analysis based on the first atmospheric meteorological state label on the real-time meteorological detection data under the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed.

[0069] In step 140, the digital twin experiment configuration parameters refer to a series of configuration settings required when conducting experiments in a digital twin environment. A digital twin is a virtual model that can simulate entities and their behaviors in the real world. In the field of meteorology, these configuration parameters may include meteorological conditions such as wind speed, wind direction, temperature, humidity, air pressure, as well as the time range and spatial resolution of the simulation. The setting of these parameters is crucial to ensure the accuracy and fidelity of the simulation experiment. They define how to reproduce or predict actual meteorological conditions in a virtual environment.

[0070] Flight environment simulation analysis is a method that uses digital twin technology to simulate and analyze the flight environment of an aircraft under specific meteorological conditions. By inputting a series of meteorological data and flight parameters, the AI ​​verification platform can simulate various meteorological conditions that an aircraft may encounter in actual flight, such as turbulence, wind shear, etc., and analyze the impact of these factors on flight safety and comfort. This analysis helps to evaluate the performance of the aircraft, optimize flight paths and strategies, and improve flight safety and efficiency.

[0071] In detail, step 140 is an important part of the data processing process, which involves integrating the airborne meteorological detection data to be processed into the existing airborne meteorological simulation data pool and assigning a suitable meteorological state label to it. First, the AI ​​verification platform checks whether the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the same as the digital twin experiment configuration parameters of all airborne meteorological simulation data under the first atmospheric meteorological state label. If it is found that these parameters are all different, it means that the data to be processed has unique meteorological characteristics, which is different from the existing simulation data. Based on this finding, the AI ​​verification platform will divide the airborne meteorological detection data to be processed into the airborne meteorological simulation data pool. The advantage of this is that the data diversity in the data pool has been increased, so that different meteorological conditions can be more comprehensively reflected. At the same time, the newly added data will be marked as an airborne meteorological simulation data under the first atmospheric meteorological state label, which means that in subsequent analysis, it can be considered as part of the data under this label. More importantly, the newly added airborne meteorological detection data to be processed not only enriches the data pool, but will also be used for flight environment simulation analysis based on the first atmospheric meteorological state label. In this analysis, the AI ​​verification platform uses the digital twin experimental configuration parameters of these data to simulate the real-time meteorological detection environment and evaluate the performance and safety of the aircraft under such specific meteorological conditions. In this way, step 140 not only enhances the diversity and integrity of the airborne meteorological simulation data pool, but also provides a more accurate and comprehensive data foundation for subsequent flight environment simulation analysis.

[0072] The embodiment of the present application uses advanced AI technology and digital twin technology to build an efficient and accurate flight environment simulation analysis system. It can not only acquire and process the detection data recorded in the air in real time, but also accurately simulate the operating environment of the aircraft in the air based on these data through digital twin technology, and realize the simulation of the atmospheric meteorological state during actual flight. This innovative technology integration has brought many significant beneficial effects.

[0073] First, the ability to replay and analyze historical data enables researchers to gain an in-depth understanding of various meteorological conditions during flight, providing valuable data support for aircraft design and performance optimization. Second, algorithm verification ensures the accuracy and reliability of simulation results, further enhancing the ability to assess flight safety. In addition, it can also help to deeply explore the connotation of atmospheric detection data, providing strong technical support for meteorological research, flight path planning and other fields.

[0074] It is worth mentioning that when processing newly acquired airborne meteorological detection data, it can automatically classify it into the corresponding meteorological state label through intelligent matching and weight analysis, and update the airborne meteorological simulation data pool. This adaptive data integration capability not only enriches the content of the data pool, but also improves the efficiency of data use and the authenticity of simulation.

[0075] In summary, the embodiments of the present application provide strong technical support for research and practice in the aviation field through efficient data processing and precise simulation, significantly improve the accuracy and practicality of flight environment simulation, and are of great significance for ensuring flight safety and optimizing flight performance.

[0076] In some preferred embodiments, after obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, the method further includes: (1) obtaining the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed on the basis that the number of airborne meteorological simulation data of the first atmospheric meteorological state label is not less than the airborne meteorological simulation data number threshold, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the same as the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label; (2) obtaining the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed when the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed is greater than the digital twin experiment configuration parameters of the first atmospheric meteorological state label and the airborne meteorological detection data to be processed. Based on the meteorological detection signal-noise weight of the airborne meteorological simulation data with the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed, the airborne meteorological simulation data with the same digital twin experiment configuration parameters as the first atmospheric meteorological state label in the airborne meteorological simulation data pool is updated to the airborne meteorological detection data to be processed; (3) based on the meteorological detection signal-noise weight of the airborne meteorological simulation data with the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed being not greater than the meteorological detection signal-noise weight of the airborne meteorological simulation data with the same digital twin experiment configuration parameters as the first atmospheric meteorological state label, the airborne meteorological simulation data with the first atmospheric meteorological state label in the airborne meteorological simulation data pool is not corrected.

[0077] In an embodiment of the present application, when the AI ​​verification platform executes airborne meteorological detection data processing, after obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, it will perform a series of refined processing steps.

[0078] First, the AI ​​verification platform will check the number of airborne meteorological simulation data under the first atmospheric meteorological state label. If this number reaches the preset threshold of airborne meteorological simulation data, it means that the data under this label is relatively abundant and can be used for more in-depth comparative analysis.

[0079] Next, the AI ​​verification platform will compare the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed with the corresponding parameters of each airborne meteorological simulation data under the first atmospheric meteorological state label. If it is found that the configuration parameters of the data to be processed are exactly the same as the configuration parameters of a certain simulation data, the platform will further obtain the meteorological detection signal-to-noise weight of the two. The meteorological detection signal-to-noise weight is an important indicator for measuring data quality. It reflects the ratio of signal to noise in the data during the detection process. A high signal-to-noise weight means that the data is more accurate and the noise interference is less.

[0080] After comparing the signal-to-noise weights of the data to be processed and the simulation data with the same configuration parameters, the AI ​​verification platform will make different processing decisions based on the comparison results. If the signal-to-noise weight of the data to be processed is higher than that of the simulation data, it means that the quality of the data to be processed is higher. Therefore, the platform will replace the simulation data with the same configuration parameters as the data to be processed in the airborne meteorological simulation data pool with the data to be processed, thereby optimizing the data quality in the data pool.

[0081] On the contrary, if the signal-to-noise weight of the data to be processed is not higher than that of the simulation data, the AI ​​verification platform will not correct the simulation data in the data pool to maintain the stability and reliability of the data pool.

[0082] Through this processing method, the AI ​​verification platform can not only continuously optimize the data quality in its airborne meteorological simulation data pool, but also ensure that the data in the data pool always reflects the most realistic and accurate meteorological detection conditions.

[0083] This design not only can intelligently identify and process a large amount of airborne meteorological detection data, but also can continuously optimize the data quality in its airborne meteorological simulation data pool through a refined comparison and correction mechanism. This capability is of vital importance to improving the accuracy of flight environment simulation, ensuring flight safety, and optimizing flight performance. At the same time, the intelligent and automated characteristics of the platform also greatly improve the efficiency and accuracy of data processing, providing strong technical support for research and practice in the aviation field.

[0084] In some optional embodiments, the updating of the airborne meteorological simulation data having the same digital twin experiment configuration parameters of the first atmospheric meteorological state label as the airborne meteorological detection data to be processed in the airborne meteorological simulation data pool to the airborne meteorological detection data to be processed includes: determining the timeliness coefficient of all airborne meteorological simulation data having the same digital twin experiment configuration parameters of the first atmospheric meteorological state label as the airborne meteorological detection data to be processed in the airborne meteorological simulation data pool; and updating the airborne meteorological simulation data having the largest timeliness coefficient of the first atmospheric meteorological state label having the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed in the airborne meteorological simulation data pool to the airborne meteorological detection data to be processed.

[0085] In detail, in the process of the AI ​​verification platform executing the airborne meteorological detection data processing task, when it is determined that the data in the airborne meteorological simulation data pool that has the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed needs to be updated, the AI ​​verification platform will take a series of refined operations.

[0086] First, the AI ​​verification platform will filter out all the airborne meteorological simulation data in the airborne meteorological simulation data pool that have the first atmospheric meteorological state label and whose digital twin experiment configuration parameters are completely consistent with the airborne meteorological detection data to be processed. This step is to ensure the accuracy of the update and avoid misoperation of other irrelevant data.

[0087] Next, the AI ​​verification platform will evaluate the timeliness of these selected airborne meteorological simulation data. The timeliness coefficient is an indicator to measure the freshness of data, which reflects the real-time nature or recent update of the data. Generally, data with a higher timeliness coefficient means that it is closer to the current time and therefore may contain more accurate and timely information.

[0088] In order to determine which data is most in need of updating, the AI ​​verification platform calculates the timeliness coefficient of each screened airborne meteorological simulation data. This process may involve multiple factors, such as the data collection time, the last update time, and the comparison with the current time. After calculating the timeliness coefficients of all relevant data, the platform will find the airborne meteorological simulation data with the largest timeliness coefficient. This means that this data is relatively old and may no longer reflect the latest meteorological conditions, so it is most in need of updating.

[0089] Finally, the AI ​​verification platform will replace the airborne meteorological simulation data with the most timely coefficient with the airborne meteorological detection data to be processed. This step ensures that the data in the data pool is always up-to-date and accurate, thereby improving the reliability of subsequent experiments or analyses based on this data.

[0090] For example, there are three copies of data with the first atmospheric meteorological state label in the airborne meteorological simulation data pool, and their digital twin experiment configuration parameters are the same as a new airborne meteorological detection data to be processed. The timeliness coefficients of these three copies of data are 0.8, 0.9, and 0.7, respectively. In this case, the AI ​​verification platform will identify that the data with a timeliness coefficient of 0.9 is the most in need of updating because it is older than the other two copies of data. Therefore, the platform will replace this data with the new airborne meteorological detection data to be processed.

[0091] Thus, it can be seen that the AI ​​verification platform adopts a refined screening and timeliness evaluation mechanism when updating the airborne meteorological simulation data pool. This method not only ensures the accuracy and pertinence of data updates, but also effectively maintains the timeliness and reliability of information in the data pool. This intelligent data processing method is of great significance to the fields of aviation, military, scientific research, etc. that rely on accurate meteorological data, and can significantly improve the accuracy and effectiveness of experiments and analysis based on simulation data. At the same time, through the automated and intelligent data processing process, the work efficiency and convenience of data management are also greatly improved.

[0092] In other optional embodiments, the airborne meteorological simulation data pool includes an airborne meteorological simulation information set of a first experimental configuration parameter and an airborne meteorological simulation information set of a second experimental configuration parameter; the airborne meteorological detection data to be processed is divided into the airborne meteorological simulation data pool on the basis that the digital twin experimental configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experimental configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, including: on the basis that the digital twin experimental configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experimental configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, and the digital twin experimental configuration parameters of the airborne meteorological detection data to be processed are the first experimental configuration parameters, The airborne meteorological simulation information set of the first experimental configuration parameters, the airborne meteorological detection data to be processed is used to perform a flight environment simulation analysis on the real-time meteorological detection data under the first experimental configuration parameters based on the first atmospheric meteorological state label; the digital twin experimental configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experimental configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, and on the basis that the digital twin experimental configuration parameters of the airborne meteorological detection data to be processed are the second experimental configuration parameters, the airborne meteorological detection data to be processed is divided into the airborne meteorological simulation information set of the second experimental configuration parameters, and the airborne meteorological detection data to be processed is used to perform a flight environment simulation analysis on the real-time meteorological detection data under the second experimental configuration parameters based on the first atmospheric meteorological state label.

[0093] During the operation of the AI ​​verification platform, the airborne meteorological simulation data pool is a key component, which contains airborne meteorological simulation information sets of multiple experimental configuration parameters. In this embodiment, two experimental configuration parameters are particularly concerned: the first experimental configuration parameter and the second experimental configuration parameter, which correspond to two different information sets in the airborne meteorological simulation data pool.

[0094] When the AI ​​verification platform receives a piece of airborne meteorological detection data to be processed, it will first check whether the digital twin experiment configuration parameters of this data are the same as the configuration parameters of all airborne meteorological simulation data under the first atmospheric meteorological state label. If they are different, the platform will further determine the configuration parameter type of the data to be processed.

[0095] For example, the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are identified as the first experiment configuration parameters, and the AI ​​verification platform will classify this data into the airborne meteorological simulation information set of the first experiment configuration parameters. This is done to ensure that data with the same configuration parameters are classified together to facilitate subsequent targeted flight environment simulation analysis. For example, if the first experiment configuration parameter represents a specific combination of flight altitude and speed, then all detection data with this configuration parameter will be classified into the same information set, so that the meteorological impact under this specific flight condition can be more accurately simulated and analyzed.

[0096] Similarly, if the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are identified as the second experiment configuration parameters, then this data will be divided into the airborne meteorological simulation information set of the second experiment configuration parameters. In this way, the AI ​​verification platform can construct multiple segmented data sets based on different experiment configuration parameters, each of which focuses on simulating and analyzing the meteorological environment under specific flight conditions.

[0097] For example, there is a piece of airborne meteorological detection data to be processed, and its digital twin experiment configuration parameters show that it was collected at a flight altitude of 10,000 meters and a flight speed of 800 kilometers per hour, which is different from all existing data under the first atmospheric meteorological state label. If this configuration parameter is defined as the first experimental configuration parameter, then this data will be added to the airborne meteorological simulation information set of the first experimental configuration parameter. Subsequently, when flight environment simulation analysis is required, the AI ​​verification platform can use the data in this information set to simulate and analyze the impact of meteorological conditions on flight at an altitude of 10,000 meters and a speed of 800 kilometers per hour.

[0098] In this way, we can see the efficiency and accuracy of the AI ​​verification platform in processing airborne meteorological detection data. By dividing the data of different experimental configuration parameters into corresponding information sets, the platform can establish a structured and segmented data pool, which not only improves the efficiency of data management, but also provides a more accurate data foundation for subsequent flight environment simulation analysis. This refined data classification method helps researchers, engineers, and pilots to more accurately understand and predict meteorological conditions under different flight conditions, thereby improving flight safety and performance optimization capabilities. At the same time, this data management method also provides a rich, high-quality data set for future data analysis and machine learning, which helps to promote technological progress and innovation in related fields.

[0099] In some exemplary embodiments, the airborne meteorological simulation information set of the second experimental configuration parameters includes a first airborne meteorological simulation information set and a second airborne meteorological simulation information set; the digital twin experimental configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experimental configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, and the digital twin experimental configuration parameters of the airborne meteorological detection data to be processed are divided into the airborne meteorological simulation information set of the second experimental configuration parameters on the basis of the second experimental configuration parameters, including: the digital twin experimental configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experimental configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, and The digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the second experiment configuration parameters, and on the basis that the simulation influence weight of the airborne meteorological detection data to be processed is less than the simulation influence weight threshold, the airborne meteorological detection data to be processed is divided into the first airborne meteorological simulation information set; the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the second experiment configuration parameters, and on the basis that the simulation influence weight of the airborne meteorological detection data to be processed is not less than the simulation influence weight threshold, the airborne meteorological detection data to be processed is divided into the second airborne meteorological simulation information set.

[0100] In the airborne meteorological simulation data management of the AI ​​verification platform, there is a more detailed division of data sets for different experimental configuration parameters. In this embodiment, the airborne meteorological simulation information set of the second experimental configuration parameter will be discussed in depth, and this set is further subdivided into the first airborne meteorological simulation information set and the second airborne meteorological simulation information set.

[0101] When the AI ​​verification platform receives a piece of airborne meteorological detection data to be processed, it will first check whether the digital twin experiment configuration parameters of the data are the same as the configuration parameters of the existing airborne meteorological simulation data under the first atmospheric meteorological state label. If they are different, and the configuration parameters of the data are identified as the second experiment configuration parameters, the platform will proceed to the next step of judgment.

[0102] At this point, the AI ​​verification platform will evaluate the simulation impact weight of the airborne meteorological detection data to be processed. The simulation impact weight is an important indicator used to measure the degree of influence of the data on the results in the simulation experiment. If this weight is less than the preset simulation impact weight threshold, it means that the impact of the data in the simulation is relatively small, and the platform will classify it into the first airborne meteorological simulation information set. The advantage of this is that when performing simulation analysis, more attention can be paid to data that has a significant impact on the experimental results.

[0103] For example, there is a piece of airborne meteorological detection data to be processed, whose digital twin experiment configuration parameters are different from all existing data and are identified as the second experiment configuration parameters. If the simulation impact weight of this data is 0.4, and the preset simulation impact weight threshold is 0.5, since 0.4 is less than 0.5, this data will be included in the first airborne meteorological simulation information set.

[0104] On the contrary, if the simulated impact weight of the airborne meteorological detection data to be processed is not less than the simulated impact weight threshold, it means that the data may have a greater influence in the simulation experiment. In this case, the AI ​​verification platform will classify it into the second airborne meteorological simulation information set. In this way, when performing flight environment simulation analysis, special attention can be paid to these data because they may have a significant impact on the experimental results.

[0105] Continuing with the above example, if the simulation impact weight of another set of airborne meteorological detection data to be processed is 0.6, since 0.6 is not less than 0.5, this data will be included in the second airborne meteorological simulation information set.

[0106] It can be seen that by subdividing the airborne meteorological simulation information set of the second experimental configuration parameters, the AI ​​verification platform can manage and utilize airborne meteorological detection data more effectively. This subdivision not only improves the efficiency of data use, but also makes the simulation experiment more accurate and targeted. By classifying data with less influence into the first airborne meteorological simulation information set and data with greater influence into the second airborne meteorological simulation information set, the platform can pay more attention to data that has a significant impact on the experimental results when conducting flight environment simulation analysis, thereby improving the accuracy and effectiveness of the simulation. This data management strategy helps scientific researchers, engineers, etc. to better understand and predict meteorological conditions in the flight environment, and provide strong support for flight safety and performance optimization.

[0107] In some further optional embodiments, after obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, it also includes: on the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed and the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label are both second experiment configuration parameters, and the digital twin experiment configuration parameters are the second experiment configuration parameters. The simulation influence weight of the airborne meteorological simulation data of the first atmospheric meteorological state label whose digital twin experiment configuration parameters are the second experiment configuration parameters is not less than the simulation influence weight threshold, and the simulation influence weight of the airborne meteorological detection data to be processed is less than the simulation influence weight threshold, the airborne meteorological detection data to be processed is processed. The airborne meteorological detection data to be processed is divided into the first airborne meteorological simulation information set; on the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed and the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label are both second experimental configuration parameters, and the simulation influence weight of the airborne meteorological simulation data of the first atmospheric meteorological state label whose digital twin experiment configuration parameters are the second experimental configuration parameters is less than the simulation influence weight threshold, and the simulation influence weight of the airborne meteorological detection data to be processed is not less than the simulation influence weight threshold, the airborne meteorological detection data to be processed is divided into the second airborne meteorological simulation information set.

[0108] In this embodiment, when processing the airborne meteorological detection data to be processed, the AI ​​verification platform pays special attention to its digital twin experiment configuration parameters and the simulation influence weight of the airborne meteorological simulation data related to the first atmospheric meteorological state label. This process is performed after obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed.

[0109] First, the AI ​​verification platform checks whether the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the same as the digital twin experiment configuration parameters of any airborne meteorological simulation data under the first atmospheric meteorological state label, and whether they are both the second experiment configuration parameters. This is a key prerequisite to ensure the accuracy and relevance of subsequent comparisons.

[0110] Next, the platform will evaluate the simulation impact weights of these airborne meteorological simulation data with the same second experimental configuration parameters. The simulation impact weight is an important indicator to measure the degree of influence of data on the results in the simulation experiment. If the simulation impact weight of the airborne meteorological simulation data with the second experimental configuration parameters under the first atmospheric meteorological state label is not less than the preset simulation impact weight threshold, and the simulation impact weight of the airborne meteorological detection data to be processed is less than this threshold, then the platform will classify the data to be processed into the first airborne meteorological simulation information set.

[0111] For example, the simulation impact weight threshold is set to 0.6. If the simulation impact weight of airborne meteorological simulation data under the first atmospheric meteorological state label (whose digital twin experiment configuration parameters are the same as the data to be processed, both of which are the second experiment configuration parameters) is 0.7, and the simulation impact weight of the airborne meteorological detection data to be processed is 0.5, then since 0.5 is less than 0.6 and 0.7 is not less than 0.6, the data to be processed will be classified into the first airborne meteorological simulation information set.

[0112] On the contrary, if under the first atmospheric meteorological state label, the simulation impact weight of the airborne meteorological simulation data with the digital twin experiment configuration parameters of the second experiment configuration parameters is less than the simulation impact weight threshold, and the simulation impact weight of the airborne meteorological detection data to be processed is not less than this threshold, then the platform will classify the data to be processed into the second airborne meteorological simulation information set.

[0113] Continuing with the above example, if the simulation impact weight of airborne meteorological simulation data under a first atmospheric meteorological state label is 0.5 (less than 0.6), and the simulation impact weight of the airborne meteorological detection data to be processed is 0.7 (not less than 0.6), then the data to be processed will be classified into the second airborne meteorological simulation information set.

[0114] In this way, by comprehensively considering the digital twin experiment configuration parameters and simulation impact weights, the AI ​​verification platform can more finely classify and manage airborne meteorological detection data. This classification method not only improves the efficiency of data use, but also makes the subsequent flight environment simulation analysis more accurate and targeted. Classifying data with less influence into the first airborne meteorological simulation information set and data with greater influence into the second airborne meteorological simulation information set will help researchers and engineers pay more attention to data that have a significant impact on the experimental results when conducting simulation experiments. This data management strategy improves the accuracy and effectiveness of simulation experiments and provides more reliable data support for flight safety and performance optimization.

[0115] Under some optional design ideas, after obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, it also includes: on the basis that the number of airborne meteorological simulation data of the first atmospheric meteorological state label is less than the airborne meteorological simulation data number threshold, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the same as the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label, obtaining the meteorological detection signal-noise weight of the airborne meteorological detection data to be processed; on the basis that the meteorological detection signal-noise weight of the airborne meteorological detection data to be processed is greater than the meteorological detection signal-noise weight of the airborne meteorological simulation data of the first atmospheric meteorological state label with the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed, dividing the airborne meteorological detection data to be processed into the airborne meteorological simulation data pool; on the basis that the meteorological detection signal-noise weight of the airborne meteorological detection data to be processed is not greater than the meteorological detection signal-noise weight of the airborne meteorological simulation data of the first atmospheric meteorological state label with the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed, not correcting the airborne meteorological simulation data of the first atmospheric meteorological state label in the airborne meteorological simulation data pool.

[0116] Under this design concept, after obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, the AI ​​verification platform will further process the data according to specific conditions. These conditions mainly involve the number of airborne meteorological simulation data under the first atmospheric meteorological state label and the meteorological detection signal-to-noise weight of the data to be processed.

[0117] First, the platform checks whether the number of airborne meteorological simulation data under the first atmospheric meteorological state label is less than the preset airborne meteorological simulation data number threshold. This threshold is set in advance to determine whether the data under this label is rich enough. If the number of data is less than this threshold, it means that the data under this label is relatively small, and more data may be needed to enrich the simulation model.

[0118] Next, if the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the same as the digital twin experiment configuration parameters of any airborne meteorological simulation data under the first atmospheric meteorological state label, the platform will further obtain the meteorological detection signal-to-noise weight of the data to be processed. The meteorological detection signal-to-noise weight is an important indicator for measuring data quality, which reflects the ratio of signal to noise in the data detection process.

[0119] For example, the threshold for the number of airborne meteorological simulation data is set to 100, but there are only 80 airborne meteorological simulation data under the first atmospheric meteorological state label, which is less than the threshold. At this time, if the digital twin experiment configuration parameters of a to-be-processed airborne meteorological detection data are the same as one of the 80 data, the platform will calculate the meteorological detection signal-to-noise weight of the to-be-processed data.

[0120] Then, the platform will compare the meteorological detection signal-noise weight of the data to be processed with the meteorological detection signal-noise weight of the airborne meteorological simulation data with the same digital twin experiment configuration parameters under the first atmospheric meteorological state label. If the meteorological detection signal-noise weight of the data to be processed is greater than the meteorological detection signal-noise weight of the existing data, it means that the quality of the data to be processed is higher and contains more useful signal information, so the platform will classify it into the airborne meteorological simulation data pool to enrich and optimize the simulation model.

[0121] On the contrary, if the meteorological detection signal-noise weight of the data to be processed is not greater than the meteorological detection signal-noise weight of the existing data, it means that its quality is not better than the existing data. Therefore, the platform will not correct the airborne meteorological simulation data under the first atmospheric meteorological state label in the airborne meteorological simulation data pool to maintain the data quality in the data pool.

[0122] Through the above design ideas, the AI ​​verification platform can more effectively screen and manage airborne meteorological detection data. When the airborne meteorological simulation data under the first atmospheric meteorological state label is insufficient, the platform will determine whether to include new data to be processed into the data pool based on the meteorological detection signal-to-noise weight, thereby ensuring that the data quality in the data pool is continuously improved. This data screening mechanism not only helps to enrich the data set of the simulation model, but also ensures the accuracy and reliability of the simulation experiment, providing a more solid data foundation for the prediction and optimization of the flight environment.

[0123] In some other exemplary technical schemes, after obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, it also includes: on the basis that the number of airborne meteorological simulation data of the first atmospheric meteorological state label is less than the airborne meteorological simulation data number threshold, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the same as the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label, obtaining the meteorological state signal-to-noise evaluation vector of the airborne meteorological detection data to be processed; comparing the meteorological state signal-to-noise evaluation vector of the airborne meteorological detection data to be processed with the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed; On the basis that the simulation matching weight of the meteorological state signal-noise evaluation vector of the airborne meteorological simulation data of the first atmospheric meteorological state label with the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed is less than the simulation matching weight threshold, the airborne meteorological detection data to be processed is divided into the airborne meteorological simulation data pool; on the basis that the simulation matching weight of the meteorological state signal-noise evaluation vector of the airborne meteorological simulation data of the first atmospheric meteorological state label with the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed is not less than the simulation matching weight threshold, the airborne meteorological simulation data pool is not corrected.

[0124] In these exemplary technical solutions, after obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, the AI ​​verification platform will perform a series of judgments and operations. This process mainly involves the amount of airborne meteorological simulation data, the matching of digital twin experiment configuration parameters, the acquisition of meteorological state signal-noise evaluation vectors, and the comparison of simulation matching weights.

[0125] First, the AI ​​verification platform checks whether the number of airborne meteorological simulation data under the first atmospheric meteorological state label is less than the preset airborne meteorological simulation data number threshold. This threshold is set according to actual needs to determine whether more data is needed to enhance the accuracy of the simulation model. If the number of data is indeed less than the threshold, the platform will further consider the airborne meteorological detection data to be processed.

[0126] Next, the platform will confirm whether the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the same as the digital twin experiment configuration parameters of any airborne meteorological simulation data under the first atmospheric meteorological state tag. If a match is found, the platform will continue processing; if not, the data to be processed may not be considered.

[0127] After confirming that the configuration parameters match, the AI ​​verification platform will obtain the meteorological state signal-to-noise evaluation vector of the airborne meteorological detection data to be processed. This vector is a multidimensional data used to quantify the signal-to-noise ratio of the evaluation data under different meteorological conditions, thereby reflecting the quality of the data.

[0128] Subsequently, the platform compares the simulation matching weight between the meteorological state signal-noise evaluation vector of the data to be processed and the meteorological state signal-noise evaluation vector of the airborne meteorological simulation data under the first atmospheric meteorological state label with the same digital twin experiment configuration parameters. The simulation matching weight is an indicator that measures the similarity between two vectors. The higher the value, the more similar the two are.

[0129] If the simulated matching weight of the meteorological state signal-noise evaluation vector of the data to be processed and the existing data is less than the preset simulation matching weight threshold, it means that the data to be processed provides new information that is different from the existing data. In this case, the AI ​​verification platform will add the airborne meteorological detection data to be processed to the airborne meteorological simulation data pool to enrich the diversity and coverage of the data set.

[0130] On the contrary, if the simulation matching weight is not less than the simulation matching weight threshold, it means that the data to be processed is highly similar to the existing data and no additional new information is provided. In this case, the platform will not correct the airborne meteorological simulation data pool to avoid data redundancy and duplication.

[0131] Through these technical solutions, the AI ​​verification platform can intelligently filter and integrate airborne meteorological detection data to ensure that the data in the data pool is both rich and diverse. By comparing the simulation matching weights of the meteorological state signal-to-noise evaluation vector, the platform can accurately identify data that brings new value to the simulation model and incorporate it into the data pool, thereby improving the accuracy and reliability of the simulation experiment. At the same time, avoiding the addition of duplicate data makes the data pool more streamlined and efficient. This data management method not only optimizes the use of data resources, but also provides a more solid data foundation for subsequent flight environment simulation analysis.

[0132] In a replaceable embodiment, after determining the simulation matching weights of the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state labels, it also includes: on the basis that the simulation matching weights of the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state labels are all less than a first threshold, and the simulation matching weights of all airborne meteorological simulation data of the first atmospheric meteorological state label and the airborne meteorological detection data to be processed are all not less than a second threshold, generating a first meteorological state simulation viewpoint, wherein the first meteorological state simulation viewpoint is used to reflect that the atmospheric meteorological state label corresponding to the airborne meteorological detection data to be processed is the same as the first atmospheric meteorological state label.

[0133] In this alternative embodiment, after determining the simulated matching weights of the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state labels, the AI ​​verification platform will perform a series of judgments and operations. These operations mainly revolve around the comparison of the simulated matching weights with the preset threshold values, and ultimately generate a viewpoint reflecting the meteorological state corresponding to the data to be processed.

[0134] Specifically, the AI ​​verification platform first checks the simulated matching weights of the airborne meteorological detection data to be processed and the airborne meteorological simulation data of X atmospheric meteorological state labels. If these weights are all less than the first threshold, it means that the data to be processed is not particularly matched with the simulation data of all existing meteorological state labels. This may be because the data to be processed represents a unique or rare meteorological state, or because the data itself has some special characteristics.

[0135] Next, the platform will pay special attention to the simulated matching weights of all airborne meteorological simulation data under the first atmospheric meteorological state label and the airborne meteorological detection data to be processed. If these weights are not less than the second threshold, it means that although the overall matching degree of the data to be processed is not high with the simulated data of all labels, it has a certain similarity with the data of the first atmospheric meteorological state label.

[0136] Based on the above two conditions, the AI ​​verification platform will generate a conclusion called "First Meteorological State Simulation Viewpoint". This viewpoint is actually an inference that the atmospheric meteorological state label corresponding to the airborne meteorological detection data to be processed is likely to be the same as the first atmospheric meteorological state label. In other words, although the data to be processed does not match the simulation data of all labels globally, it is closest to the data characteristics of the first atmospheric meteorological state label.

[0137] For example, there are four atmospheric weather state labels: clear, cloudy, rainy, and snowy. The simulated matching weights of the airborne meteorological detection data to be processed and the simulated data of these four labels are all low, below the first threshold. However, when compared with the simulated data under the "cloudy" label, it is found that their simulated matching weights are all higher than the second threshold. In this case, the AI ​​verification platform will generate a view that the data to be processed is likely to correspond to the meteorological state of "cloudy".

[0138] Through this implementation method, the AI ​​verification platform can still make reasonable inferences about the meteorological conditions corresponding to the onboard meteorological detection data to be processed even when the global matching degree is not high. This not only improves the flexibility and accuracy of data processing, but also helps to provide more accurate decision support for flight safety under complex and changeable meteorological conditions. At the same time, this method also enhances the depth and breadth of data analysis, making the AI ​​verification platform more advantageous when dealing with atypical or rare meteorological conditions.

[0139] In a preferred embodiment, after determining the simulation matching weights of the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state labels, it also includes: generating a second meteorological state simulation viewpoint on the basis that the simulation matching weight of the airborne meteorological detection data to be processed and any airborne meteorological simulation data of the second atmospheric meteorological state label is not less than a first threshold, wherein the second meteorological state simulation viewpoint is used to reflect that the atmospheric meteorological state label corresponding to the airborne meteorological detection data to be processed is the same as the second atmospheric meteorological state label.

[0140] In this preferred embodiment, after determining the simulation matching weights of the onboard meteorological detection data to be processed and the onboard meteorological simulation data of the X atmospheric meteorological state labels, the AI ​​verification platform will further perform specific judgments and operations based on these weights. The core of this process is to generate a viewpoint reflecting the meteorological state of the data to be processed by comparing the simulation matching weights with the preset first threshold.

[0141] Specifically, the AI ​​verification platform will examine the simulated matching weights of the airborne meteorological detection data to be processed and all airborne meteorological simulation data under the second atmospheric meteorological state label. If any of the weights is not less than the first threshold, it means that the data to be processed has a high degree of similarity with at least one simulation data of the second atmospheric meteorological state label.

[0142] Taking the actual meteorological state as an example, assuming that the second atmospheric meteorological state label represents "cloudy" weather, if the simulated matching weight of the airborne meteorological detection data to be processed and one or some simulated data under the "cloudy" label reaches the first threshold, the AI ​​verification platform will determine that this data is likely to also reflect the "cloudy" meteorological state.

[0143] Based on this judgment, the AI ​​verification platform will generate a "second weather state simulation view". This view clearly states that the atmospheric weather state label corresponding to the airborne weather detection data to be processed is the same as the second atmospheric weather state label (in this case, "cloudy"). The generation of this view provides an important basis for subsequent meteorological analysis, flight plan formulation or risk assessment.

[0144] In this way, the AI ​​verification platform can more accurately identify the meteorological conditions reflected by the onboard meteorological detection data to be processed. This precise recognition capability not only improves the accuracy of meteorological data analysis, but also provides a strong guarantee for the safety and efficiency of flight missions. For example, accurately judging meteorological conditions before flight can help pilots or autopilot systems choose more appropriate flight routes and flight altitudes, thereby avoiding potential meteorological risks. In addition, this method can also help improve the application value of meteorological data and provide more reliable data support for multiple fields such as aviation and climate research.

[0145] In another preferred embodiment, the obtaining of airborne meteorological simulation data of X atmospheric meteorological state tags comprises: obtaining X airborne meteorological simulation data groups corresponding to the X atmospheric meteorological state tags from an airborne meteorological simulation data pool, wherein the airborne meteorological simulation data groups comprise at least one batch of airborne meteorological simulation data; and determining, from the X airborne meteorological simulation data groups, the airborne meteorological simulation data closest to the current meteorological detection cycle in each airborne meteorological simulation data group, to obtain the airborne meteorological simulation data of the X atmospheric meteorological state tags.

[0146] In another preferred embodiment, the AI ​​verification platform adopts a more sophisticated and timely method when acquiring airborne meteorological simulation data of X atmospheric meteorological state tags. This process not only involves extracting data from the airborne meteorological simulation data pool, but also includes further screening and processing of these data to ensure that the acquired data is closest to the current meteorological detection cycle.

[0147] Specifically, the AI ​​verification platform will first obtain X airborne meteorological simulation data groups corresponding to X atmospheric meteorological state labels from the airborne meteorological simulation data pool. These data groups are classified according to different meteorological state labels (such as clear, cloudy, rainy, etc.), and each label corresponds to an airborne meteorological simulation data group. Each data group contains at least one airborne meteorological simulation data, which may be simulated or measured at different times and under different conditions.

[0148] Next, the AI ​​verification platform will determine the airborne meteorological simulation data closest to the current meteorological detection period from each airborne meteorological simulation data group. This step is crucial because it ensures that the selected data is highly relevant to the current actual meteorological conditions. For example, if it is a summer afternoon, the simulation data selected from the data group labeled "clear" should be the data that is most similar to the meteorological characteristics of that period.

[0149] Through this screening process, the AI ​​verification platform finally obtained airborne meteorological simulation data with X atmospheric meteorological state labels, which not only matched their respective meteorological state labels but were also highly correlated with the current meteorological detection cycle.

[0150] For example, the AI ​​verification platform needs to select data from the airborne meteorological simulation data sets with three labels: "clear", "cloudy" and "rainy". For the data set labeled "clear", the platform will select a simulation data with clear weather conditions and the meteorological characteristics that are closest to the current time (such as summer afternoon). Similarly, similar screening will be performed for the data sets labeled "cloudy" and "rainy".

[0151] In this way, the AI ​​verification platform can obtain airborne meteorological simulation data that is closest to the current meteorological detection cycle. These data are not only highly timely, but also more accurately reflect the current meteorological conditions. This is of great significance for subsequent meteorological analysis, forecasting, and flight plan formulation. At the same time, this method also improves the efficiency of data use and avoids analysis errors caused by data timeliness issues.

[0152] In some independent embodiments, the method also includes: utilizing the unprocessed airborne meteorological detection data divided into the airborne meteorological simulation data pool, and performing a flight environment simulation analysis based on the first atmospheric meteorological state label on the real-time meteorological detection data under the digital twin experimental configuration parameters of the unprocessed airborne meteorological detection data.

[0153] In some independent embodiments, the functionality of the AI ​​verification platform is further expanded. In these embodiments, the platform not only matches and analyzes meteorological data, but also uses this data to perform more in-depth flight environment simulation analysis.

[0154] Specifically, when the airborne meteorological detection data to be processed is divided into the airborne meteorological simulation data pool, these data do not just remain in the state of being classified and stored. On the contrary, the AI ​​verification platform will further utilize these data to perform flight environment simulation analysis on the real-time meteorological detection data corresponding to the airborne meteorological detection data to be processed under the digital twin experiment configuration parameters. This analysis is based on the first atmospheric meteorological state label. In other words, the platform will simulate the flight environment under the meteorological conditions based on the meteorological state represented by this label (for example, clear, cloudy, rainy, etc.). In this way, the AI ​​verification platform can more accurately predict and evaluate the meteorological conditions that may be encountered in actual flights.

[0155] For example, the airborne meteorological detection data to be processed is classified under the weather status label of "cloudy". In the digital twin experimental environment, the AI ​​verification platform simulates a cloudy weather condition and analyzes various possible flight conditions in this weather. This includes but is not limited to the thickness of the clouds, the speed of cloud movement, possible changes in wind direction and speed, etc. This flight environment simulation analysis based on real-time meteorological detection data is of great significance for flight mission planning, flight safety assessment, and flight efficiency improvement. It can help pilots or flight control systems understand the upcoming meteorological conditions more accurately, so as to make more reasonable flight decisions.

[0156] In this way, the AI ​​verification platform not only improves the depth and breadth of meteorological data processing, but also provides more accurate meteorological environment simulation analysis for the planning and execution of flight missions. This analysis can significantly improve the safety and efficiency of flight and reduce the risks caused by uncertain meteorological conditions. At the same time, it also provides pilots and flight control systems with richer decision support information, allowing flight missions to be completed more smoothly and efficiently.

[0157] It is worth mentioning that, using the to-be-processed airborne meteorological detection data divided into the airborne meteorological simulation data pool, the real-time meteorological detection data under the digital twin experiment configuration parameters of the to-be-processed airborne meteorological detection data is subjected to flight environment simulation analysis based on the first atmospheric meteorological state label, and the method includes:

[0158] Extract the to-be-processed airborne meteorological detection data corresponding to the first atmospheric meteorological state label from the airborne meteorological simulation data pool, and ensure that the extracted data can accurately reflect the environmental characteristics under the meteorological state;

[0159] According to the configuration parameters of the digital twin experiment, a virtual flight environment is constructed, which can simulate various meteorological conditions that may be encountered in actual flight, including but not limited to key meteorological elements such as temperature, humidity, wind speed, wind direction, and air pressure;

[0160] The extracted airborne meteorological detection data to be processed is used as input, and high-precision meteorological field reconstruction is performed in the virtual flight environment of the digital twin experiment through technical means such as data interpolation and model calculation to ensure the accuracy and authenticity of the simulation analysis;

[0161] Based on the reconstructed meteorological field, combined with the aircraft's performance parameters, route planning, and flight mission requirements, advanced simulation algorithms are used to simulate and analyze various possible situations during the flight, including but not limited to key indicators such as flight stability, fuel consumption rate, and flight path optimization;

[0162] Based on the simulation analysis results, a detailed flight environment assessment report is generated. The report should include flight performance predictions under various meteorological conditions, identification of potential risk points, and corresponding response strategy recommendations, providing scientific and comprehensive decision-making support for the planning and execution of flight missions.

[0163] In detail, when performing flight environment simulation analysis, the AI ​​verification platform takes a series of refined steps to ensure the accuracy and comprehensiveness of the analysis. This process starts with extracting data from the onboard meteorological simulation data pool and ends with generating a detailed flight environment assessment report.

[0164] First, the AI ​​verification platform extracts the pending airborne meteorological detection data corresponding to the first atmospheric meteorological state label from the airborne meteorological simulation data pool. These data are carefully selected to accurately reflect the environmental characteristics under specific meteorological conditions. For example, if the first atmospheric meteorological state label is "cloudy", the extracted data will contain key information such as temperature, humidity, and wind speed under cloudy weather.

[0165] Next, based on the configuration parameters of the digital twin experiment, the AI ​​verification platform will build a virtual flight environment. This environment can not only simulate various meteorological conditions that may be encountered in actual flight, but also be flexibly adjusted as needed. In this virtual environment, key meteorological elements such as temperature, humidity, wind speed, wind direction, and air pressure will be accurately simulated, providing a solid foundation for subsequent simulation analysis.

[0166] Then, the AI ​​verification platform will use the extracted airborne meteorological detection data to be processed as input, and reconstruct the meteorological field with high precision in the virtual flight environment of the digital twin experiment through technical means such as data interpolation and model calculation. This step is the key to ensuring the accuracy and authenticity of the simulation analysis. Through the detailed meteorological field reconstruction, the platform can more accurately simulate various meteorological conditions during the flight.

[0167] Based on the reconstructed meteorological field, the AI ​​verification platform will combine the performance parameters of the aircraft, route planning and flight mission requirements, and use advanced simulation algorithms to simulate and analyze various possible situations during the flight. This includes but is not limited to key indicators such as flight stability, fuel consumption rate, flight path optimization, etc. Through these analyses, the platform can comprehensively evaluate the performance of flight missions under various meteorological conditions.

[0168] Finally, based on the simulation analysis results, the AI ​​verification platform will generate a detailed flight environment assessment report. This report not only includes flight performance predictions under various meteorological conditions, but also identifies potential flight risk points and provides corresponding response strategy recommendations. This report provides scientific and comprehensive decision support for the planning and execution of flight missions, helping to ensure flight safety and improve flight efficiency.

[0169] In this way, the AI ​​verification platform can achieve comprehensive and high-precision simulation analysis of the flight environment. This not only helps to improve the safety and efficiency of flight missions, but also provides more accurate decision support information for pilots and flight control systems. Through sophisticated data extraction, construction of virtual flight environments, reconstruction of meteorological fields, and comprehensive simulation analysis, the platform can generate highly instructive flight environment assessment reports, thereby significantly improving flight safety and reliability.

[0170] Further, Figure 2This is a schematic diagram of the structure of an AI verification platform 200 provided in an embodiment of the present application. Figure 2 The AI ​​verification platform 200 shown includes a processor 210, which can call and run a computer program from a memory to implement the method in the embodiment of the present application.

[0171] Alternatively, if Figure 2 As shown, the AI ​​verification platform 200 may further include a memory 230. The processor 210 may call and run a computer program from the memory 230 to implement the method in the embodiment of the present application.

[0172] The memory 230 may be a separate device independent of the processor 210 , or may be integrated into the processor 210 .

[0173] Alternatively, if Figure 2 As shown, the AI ​​verification platform 200 may further include a transceiver 220, and the processor 210 may control the transceiver 220 to interact with other devices. Specifically, it may send information or data to other devices, or receive information or data sent by other devices.

[0174] Optionally, the AI ​​verification platform 200 can implement the corresponding processes corresponding to the storage engine or components in the storage engine (such as a processing module) or a device deployed with a storage engine in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0175] It should be understood that the processor of the embodiment of the present application may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment can be completed by the hardware integrated logic circuit or software instructions in the processor. The above processor can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor are combined and performed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0176] It can be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0177] It should be understood that the above-mentioned memory is exemplary but not restrictive. For example, the memory in the embodiments of the present application may also be static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM), etc. That is to say, the memory in the embodiments of the present application is intended to include but not limited to these and any other suitable types of memory.

[0178] Based on the above, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program implements the above method when running.

[0179] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations.

Claims

1. A method for simulating an aircraft operating environment combining AI and digital twins, characterized in that: Applied to an AI verification platform, the method includes: Acquire the airborne meteorological detection data to be processed and acquire the airborne meteorological simulation data of X atmospheric meteorological state tags, wherein each atmospheric meteorological state tag matches one or more airborne meteorological simulation data, and the airborne meteorological simulation data of the X atmospheric meteorological state tags are recorded in an airborne meteorological simulation data pool, where X is not less than 1; Determine a simulation matching weight between the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state tags; On the basis that the simulation matching weights of the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state labels are both less than the first threshold, and the simulation matching weights of all airborne meteorological simulation data of the first atmospheric meteorological state label and the airborne meteorological detection data to be processed are not less than the second threshold, obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, and the first atmospheric meteorological state label belongs to one of the X atmospheric meteorological state labels; On the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, the airborne meteorological detection data to be processed is divided into the airborne meteorological simulation data pool, wherein the airborne meteorological detection data to be processed divided into the airborne meteorological simulation data pool is used as an airborne meteorological simulation data of the first atmospheric meteorological state label, and is used to perform flight environment simulation analysis based on the first atmospheric meteorological state label on the real-time meteorological detection data under the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed.

2. The aircraft operating environment simulation method combining AI and digital twins according to claim 1, characterized in that: After obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, the method further includes: On the basis that the number of airborne meteorological simulation data of the first atmospheric meteorological state label is not less than the airborne meteorological simulation data number threshold, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the same as the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label, obtaining the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed; On the basis that the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed is greater than the meteorological detection signal-to-noise weight of the airborne meteorological simulation data with the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed and having the first atmospheric meteorological state label, the airborne meteorological simulation data with the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed and having the first atmospheric meteorological state label in the airborne meteorological simulation data pool is updated to the airborne meteorological detection data to be processed; On the basis that the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed is not greater than the meteorological detection signal-to-noise weight of the airborne meteorological simulation data of the first atmospheric meteorological state label with the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed, the airborne meteorological simulation data of the first atmospheric meteorological state label in the airborne meteorological simulation data pool is not corrected.

3. The aircraft operating environment simulation method combining AI and digital twins according to claim 2, characterized in that: The updating of the airborne meteorological simulation data having the same digital twin experiment configuration parameters of the first atmospheric meteorological state tag as the airborne meteorological detection data to be processed in the airborne meteorological simulation data pool to the airborne meteorological detection data to be processed includes: Determine the timeliness coefficient of all airborne meteorological simulation data of the first atmospheric meteorological state tag having the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed in the airborne meteorological simulation data pool; The airborne meteorological simulation data with the largest timeliness coefficient of the first atmospheric meteorological state label having the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed in the airborne meteorological simulation data pool is updated as the airborne meteorological detection data to be processed.

4. The aircraft operating environment simulation method combining AI and digital twins according to any one of claims 1 to 3, characterized in that: The airborne meteorological simulation data pool includes an airborne meteorological simulation information set of a first experimental configuration parameter and an airborne meteorological simulation information set of a second experimental configuration parameter; The method further comprises dividing the airborne meteorological detection data to be processed into the airborne meteorological simulation data pool on the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, including: On the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the first experiment configuration parameters, the airborne meteorological detection data to be processed are divided into the airborne meteorological simulation information set of the first experiment configuration parameters, and the airborne meteorological detection data to be processed are used to perform flight environment simulation analysis based on the first atmospheric meteorological state label on the real-time meteorological detection data under the first experiment configuration parameters; On the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are second experiment configuration parameters, the airborne meteorological detection data to be processed are divided into the airborne meteorological simulation information set of the second experiment configuration parameters, and the airborne meteorological detection data to be processed are used to perform flight environment simulation analysis based on the first atmospheric meteorological state label on the real-time meteorological detection data under the second experiment configuration parameters; The airborne meteorological simulation information set of the second experimental configuration parameters includes a first airborne meteorological simulation information set and a second airborne meteorological simulation information set; the digital twin experimental configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experimental configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, and the digital twin experimental configuration parameters of the airborne meteorological detection data to be processed are divided into the airborne meteorological simulation information set of the second experimental configuration parameters, including: the digital twin experimental configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experimental configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, and the digital twin experimental configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experimental configuration parameters of the airborne meteorological detection data to be processed The digital twin experiment configuration parameters of the airborne meteorological detection data are the second experiment configuration parameters, and on the basis that the simulation influence weight of the airborne meteorological detection data to be processed is less than the simulation influence weight threshold, the airborne meteorological detection data to be processed is divided into the first airborne meteorological simulation information set; the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are different from the digital twin experiment configuration parameters of all airborne meteorological simulation data of the first atmospheric meteorological state label, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the second experiment configuration parameters, and on the basis that the simulation influence weight of the airborne meteorological detection data to be processed is not less than the simulation influence weight threshold, the airborne meteorological detection data to be processed is divided into the second airborne meteorological simulation information set; After acquiring the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, it also includes: on the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed and the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label are both second experiment configuration parameters, and the simulation influence weight of the airborne meteorological simulation data of the first atmospheric meteorological state label whose digital twin experiment configuration parameters are the second experiment configuration parameters is not less than the simulation influence weight threshold, and the simulation influence weight of the airborne meteorological detection data to be processed is less than the simulation influence weight threshold, the airborne meteorological detection data to be processed is divided into the first airborne meteorological simulation information set; on the basis that the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed and the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label are both second experiment configuration parameters, and the simulation influence weight of the airborne meteorological simulation data of the first atmospheric meteorological state label whose digital twin experiment configuration parameters are the second experiment configuration parameters is less than the simulation influence weight threshold, and the simulation influence weight of the airborne meteorological detection data to be processed is not less than the simulation influence weight threshold, the airborne meteorological detection data to be processed is divided into the second airborne meteorological simulation information set.

5. The aircraft operating environment simulation method combining AI and digital twins according to claim 1, characterized in that: After obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, the method further includes: On the basis that the number of airborne meteorological simulation data of the first atmospheric meteorological state label is less than the airborne meteorological simulation data number threshold, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the same as the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label, obtaining the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed; On the basis that the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed is greater than the meteorological detection signal-to-noise weight of the airborne meteorological simulation data having the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed and having the first atmospheric meteorological state label, the airborne meteorological detection data to be processed is divided into the airborne meteorological simulation data pool; On the basis that the meteorological detection signal-to-noise weight of the airborne meteorological detection data to be processed is not greater than the meteorological detection signal-to-noise weight of the airborne meteorological simulation data of the first atmospheric meteorological state label with the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed, the airborne meteorological simulation data of the first atmospheric meteorological state label in the airborne meteorological simulation data pool is not corrected.

6. The aircraft operating environment simulation method combining AI and digital twins according to claim 1, characterized in that: After obtaining the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed, the method further includes: On the basis that the number of airborne meteorological simulation data of the first atmospheric meteorological state label is less than the airborne meteorological simulation data number threshold, and the digital twin experiment configuration parameters of the airborne meteorological detection data to be processed are the same as the digital twin experiment configuration parameters of any airborne meteorological simulation data of the first atmospheric meteorological state label, obtaining the meteorological state signal-to-noise evaluation vector of the airborne meteorological detection data to be processed; On the basis that the simulation matching weight of the meteorological state signal-noise evaluation vector of the airborne meteorological simulation data of the first atmospheric meteorological state label having the same digital twin experiment configuration parameters as the meteorological state signal-noise evaluation vector of the airborne meteorological detection data to be processed is less than the simulation matching weight threshold, the airborne meteorological detection data to be processed is divided into the airborne meteorological simulation data pool; On the basis that the simulation matching weight of the meteorological state signal-noise evaluation vector of the airborne meteorological detection data to be processed and the meteorological state signal-noise evaluation vector of the airborne meteorological simulation data of the first atmospheric meteorological state label having the same digital twin experiment configuration parameters as the airborne meteorological detection data to be processed is not less than the simulation matching weight threshold, the airborne meteorological simulation data pool is not corrected.

7. The aircraft operating environment simulation method combining AI and digital twins according to claim 1, characterized in that: After determining the simulation matching weights of the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state tags, the method further includes: On the basis that the simulation matching weights of the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state labels are both less than a first threshold, and the simulation matching weights of all airborne meteorological simulation data of the first atmospheric meteorological state label and the airborne meteorological detection data to be processed are both not less than a second threshold, a first meteorological state simulation viewpoint is generated, wherein the first meteorological state simulation viewpoint is used to reflect that the atmospheric meteorological state label corresponding to the airborne meteorological detection data to be processed is the same as the first atmospheric meteorological state label.

8. The aircraft operating environment simulation method combining AI and digital twins according to claim 1, characterized in that: After determining the simulation matching weights of the airborne meteorological detection data to be processed and the airborne meteorological simulation data of the X atmospheric meteorological state tags, the method further includes: On the basis that the simulation matching weight between the airborne meteorological detection data to be processed and any airborne meteorological simulation data of the second atmospheric meteorological state label is not less than the first threshold, a second meteorological state simulation viewpoint is generated, wherein the second meteorological state simulation viewpoint is used to reflect that the atmospheric meteorological state label corresponding to the airborne meteorological detection data to be processed is the same as the second atmospheric meteorological state label.

9. The aircraft operating environment simulation method combining AI and digital twins according to claim 1, characterized in that: The step of obtaining the airborne meteorological simulation data of X atmospheric meteorological state tags includes: Acquire X airborne meteorological simulation data groups corresponding to X atmospheric meteorological state tags from an airborne meteorological simulation data pool, wherein the airborne meteorological simulation data group includes at least one airborne meteorological simulation data; From the X airborne meteorological simulation data groups, the airborne meteorological simulation data closest to the current meteorological detection period in each airborne meteorological simulation data group is determined to obtain airborne meteorological simulation data of X atmospheric meteorological state labels.

10. An AI verification platform, characterized in that: The method comprises at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method according to any one of claims 1 to 9.

Images