Analog machine air-ground switch parameter correction method and device and storage medium

Abstract

The invention belongs to the technical field of simulated flight training, particularly relates to an analog machine air-to-ground switch parameter correction method and device and a storage medium, and aims to solve the problem of high-precision correction of analog machine air-to-ground switch state parameters. The method comprises the following steps: acquiring flight key parameters in analog machine QAR data; on the basis of the flight key parameters, using a multivariable decision tree model to obtain an air-ground switch value influence maximum parameter; constructing a single-variable single-layer decision tree based on the air-ground switch value influence maximum parameter, and determining an optimal threshold value of the air-ground switch value based on the single-variable single-layer decision tree; and based on the optimal threshold value of the air-to-ground switch value and the air-to-ground switch value influence maximum parameter, finishing correction of the air-to-ground switch parameter of the simulator. According to the method, the error state of the air-ground switch in the QAR parameters is corrected in an auxiliary mode through the decision tree, and the problem of high-precision correction of the state parameters of the air-ground switch of the analog machine is solved.

Description

Background Art

[0002] In recent years, with the rapid development of technologies such as the Internet of Things, communications, and avionics, more and more airlines have installed Quick Access Recorder (QAR) devices on their aircraft, making the collection of flight data more convenient. It has become an inevitable trend to better support the innovative development of the civil aviation industry through flight data analysis. At the same time, flight training is an important part of the civil aviation industry. Conducting flight training through simulators is of great significance for improving the skill level of pilots and their ability to deal with emergencies in the air. Many domestic airlines have their own simulator flight training bases. The QAR equipment built into the simulator can also complete the collection of multiple flight parameters in simulated flight training. These data include parameters such as the aircraft's attitude, speed, altitude, weight, front and rear landing gear status, and pilot operation information. By analyzing the above data, researchers can evaluate and judge various flight events, thereby improving the quality of flight training and flight safety. Among the various parameters of the simulator, the landing gear ground switch state parameter (ground_air) is an important parameter. It uses whether the landing gear is in a compressed state to reflect whether the aircraft is in the air or on the ground. When ground_air=0, it means that the aircraft is in the air. This parameter is crucial for determining the takeoff and landing time of the aircraft. However, due to the error or lag in the information collection of the simulator sensor, the air-to-ground switch parameter records will be abnormal, and the simulator may have taken off or landed, but the parameter has not changed, thus affecting the subsequent analysis and discussion. Therefore, it is necessary to take certain measures to correct this parameter based on other key parameters.

[0003] The following documents are technical background materials related to the present invention: The patent name is "A method for judging the air-ground status of an aircraft" (publication number CN113955086A), which includes: step 1, real-time acquisition of three independent air-ground status judgment information on the aircraft, including: wheel-mounted switch air-ground status judgment information, radio altitude air-ground status judgment information and calibrated airspeed air-ground status judgment information, and the output of each air-ground status judgment information is: valid "air", valid "ground" or invalid; step 2, according to the three independent air-ground status judgment information obtained, the pre-configured air-ground comprehensive logic is used to output the current air-ground status of the aircraft. However, it is not accurate enough to judge the air-ground status only by simple rules and modify the existing air-ground status parameters. Summary of the invention

[0004] In order to solve the above-mentioned problem in the prior art, namely, the problem of high-precision correction of the state parameters of the simulator air-ground switch, the present invention provides a simulator air-ground switch parameter correction method, device and storage medium, which uses a decision tree as an auxiliary to correct the erroneous state of the air-ground switch in the QAR parameters to solve the problem of high-precision correction of the state parameters of the simulator air-ground switch.

[0005] The first aspect of the present invention provides a method for correcting parameters of a simulator air-ground switch, comprising: Obtain key flight parameters from the simulator QAR data; Based on the key flight parameters and using a multivariate decision tree model, the parameter with the greatest impact on the value of the air-to-ground switch is obtained; Constructing a univariate single-layer decision tree based on the parameter with the greatest impact on the open space switch value, and determining an optimal threshold value for the open space switch value based on the univariate single-layer decision tree; The simulator open-ground switch parameters are modified based on the optimal threshold of the open-ground switch value and the parameter with the greatest impact on the open-ground switch value.

[0006] Preferably, the method of obtaining the parameter with the greatest impact on the air-to-ground switch value based on the key flight parameters and using a multivariate decision tree model includes: The importance of parameter features is calculated using the flight key parameters through the splitting process of the multivariate decision tree model; Based on the importance of the parameter characteristics, it is determined that the parameter with the greatest impact on the value of the air-to-ground switch is the radio altitude.

[0007] Preferably, the calculating the importance of parameter features using the flight key parameters through the splitting process of the multivariate decision tree model comprises: Selecting preset parameters of the splitting process of the multivariate decision tree model in sequence from the key flight parameters; Based on the splitting of the current decision tree in the process of building the multivariate decision tree model, in each splitting process, the selected preset parameters are used to sequentially calculate the information gain values ​​of different preset parameters relative to the current decision tree; Determining the importance of the parameter feature based on the ranking of different preset parameters relative to the information gain values ​​of the current decision tree; The sum of the information gain values ​​of the different preset parameters relative to the current decision tree is 1.

[0008] Preferably, the information gain values ​​of different preset parameters relative to the current decision tree are calculated in sequence using the selected preset parameters in each splitting process, including: The information entropy of the current decision tree is obtained by probability calculation based on the preset parameters and the value categories of the open space switch; An information gain value of the preset parameter relative to the current decision tree is obtained based on the preset parameter and the information entropy of the current decision tree.

[0009] Preferably, the information entropy of the current decision tree is obtained by probability calculation based on the preset parameters and the value category of the open space switch, and the formula is as follows:

[0010] in, represents the information entropy of the decision tree, It is the value category of open space switch The probability of the open space switch is 0. Indicates category 1, when the open space switch value is 1, Indicates category 2, Indicates that the preset parameters The number of value categories for upper ground switches.

[0011] Preferably, the information gain value of the preset parameter relative to the current decision tree is obtained by calculating the information entropy based on the preset parameter and the current decision tree, and the formula is as follows:

[0012] in, represents the information entropy of the decision tree, Indicates that the preset parameters The upper value is The sample subset size is represents the total number of samples, Indicates that the preset parameters The upper value is The information entropy of the sample subset is Indicates preset parameters Relative to the current decision tree The information gain value brought.

[0013] Preferably, constructing a univariate single-layer decision tree based on the parameter with the largest impact on the open space switch value, and determining the optimal threshold of the open space switch value based on the univariate single-layer decision tree includes: constructing the univariate single-layer decision tree using radio altitude; Selecting an optimal threshold using a decision tree algorithm based on the univariate single-layer decision tree: traversing all possible values ​​of the radio altitude, and selecting an optimal threshold by the information gain value of the radio altitude relative to the current decision tree; A decision node is created based on the optimal threshold, and all possible values ​​of the radio altitude are divided into two subsets based on the decision node, and the decision tree algorithm is recursively repeated for the two subsets respectively until the maximum tree depth is reached to obtain the optimal threshold of the open space switch value.

[0014] Preferably, the modification of the simulator open-ground switch parameters based on the optimal threshold of the open-ground switch value and the parameter with the greatest impact on the open-ground switch value includes: If the radio altitude is greater than the optimal threshold of the air-to-ground switch value, the simulator air-to-ground switch parameter value is 0; If the radio altitude is less than the optimal threshold of the air-to-ground switch value, the simulator air-to-ground switch parameter value is 1.

[0015] A second aspect of the present invention provides an electronic device, comprising: at least one processor; and a memory communicatively coupled to at least one of the processors; The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the above-mentioned simulator air-ground switch parameter correction method.

[0016] According to a third aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the above-mentioned simulator open-ground switch parameter correction method.

[0017] Beneficial effects of the present invention: (1) Improving the accuracy of air-ground switch parameter values: By introducing some QAR parameters and using the traditional machine learning model decision tree to screen parameter contributions and determine the optimal radio height threshold, the correct value of the air-ground switch in the QAR parameter can be determined more accurately, avoiding misjudgment of the air-ground switch status due to data recording delay or recording error; (2) Providing convenience for subsequent research: The research on many flight safety events cannot be separated from the key parameter of the air-ground switch. For example, flight events such as hard landing, tail strike, and runway overrun all require the value of the air-ground switch to determine the landing time. The correct value of the air-ground switch is determined with high precision, which is helpful for the subsequent analysis and research of such flight events. (3) Help correct other parameters: Provide reliable and feasible methods for reference to correct other erroneous parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 It is a flow chart of a method for correcting parameters of a simulator open-ground switch; Figure 2 is a flow chart for calculating the importance of parameter features; Figure 3 It is a flow chart for determining the optimal threshold value for the open space switch; Figure 4 It is a structural diagram of a computer system of a server for implementing the method, system, and device embodiments of the present application. DETAILED DESCRIPTION

[0019] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0020] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0021] The invention provides a simulator open-ground switch parameter correction method, which uses a decision tree as an auxiliary to correct the error state of the open-ground switch in the QAR parameter to solve the problem of high-precision correction of the simulator open-ground switch state parameters.

[0022] A simulator open-ground switch parameter correction method of the present invention comprises: Obtain key flight parameters from the simulator QAR data; Based on the key flight parameters and using a multivariate decision tree model, the parameter with the greatest impact on the value of the air-to-ground switch is obtained; Constructing a univariate single-layer decision tree based on the parameter with the greatest impact on the open space switch value, and determining an optimal threshold value for the open space switch value based on the univariate single-layer decision tree; The simulator open-ground switch parameters are modified based on the optimal threshold of the open-ground switch value and the parameter with the greatest impact on the open-ground switch value.

[0023] In order to more clearly explain the simulator open-ground switch parameter correction method of the present invention, the following is combined with Figure 1 Each step in the embodiment of the present invention is described in detail.

[0024] The simulator open-ground switch parameter correction method of the first embodiment of the present invention includes steps S101 to S104, each of which is described in detail as follows: Step S101, obtaining key flight parameters in the simulator QAR data; Specifically, the QAR parameters in the flight training simulator are decoded and parsed to obtain a CSV file. The relevant QAR parameters required to correct the air-ground switch are extracted, including radio altitude (ra), pitch angle (pitch), pitch change rate (pitch_rate), slope (roll), aircraft height on the runway (alt_agl), aircraft cabin altitude (alt_cabin), airspeed (airspeed), climb rate (climbrate), ground speed (groundspeed), and air-ground switch (ground_air). The last parameter, air-ground switch (ground_air), is the parameter that needs to be corrected.

[0025] The flight key parameters are obtained after data cleaning of the extracted relevant QAR parameters, and the cleaning process includes: 1) Abnormal data identification scope: If the flight segment information contained in the CSV file is incomplete, does not include the entire takeoff process, or the parameter value has a very large jump, etc., it will be regarded as abnormal data.

[0026] 2) Deletion operation: For the above-mentioned abnormal situations, they are regarded as invalid data and discarded.

[0027] The ground switch parameter ground_air in the QAR data is a discrete value, which only contains two values: 1 and 0, where 1 means the aircraft is on the ground and 0 means the aircraft is in the air. Through analysis, it is found that there is a strong correlation between different parameters of QAR, and the value of the ground switch can be inferred from other related parameters.

[0028] Step S102, based on the key flight parameters and using a multivariate decision tree model, obtaining the parameter with the greatest impact on the air-to-ground switch value; In other words, the multivariate decision tree of the machine learning model is used to analyze the importance of key flight parameters for the judgment of air-to-ground switch parameters, so as to obtain the parameters with the greatest impact on the value of the air-to-ground switch.

[0029] It should be noted that considering the huge amount of QAR data, manual analysis is very time-consuming and labor-intensive. Therefore, the present invention first extracts some key parameters from the QAR data, and then uses a multivariate decision tree model to find out the parameters that have the greatest impact on the open space switch value.

[0030] Step S103, constructing a univariate single-layer decision tree based on the parameter with the greatest impact on the value of the open space switch, and determining the optimal threshold value of the open space switch based on the univariate single-layer decision tree; Specifically, a univariate decision tree is used to select the optimal threshold of the parameter with the greatest influence on the value of the open space switch, and finally the threshold is used to judge the state of the open space switch.

[0031] Step S104, completing the modification of the simulator open-ground switch parameters based on the optimal threshold of the open-ground switch value and the parameter with the greatest impact on the open-ground switch value.

[0032] The technical solution of the present invention not only makes full use of the excellent performance of machine learning models such as decision trees, but also provides a specific judgment threshold, so that the model has the characteristics of simplicity and interpretability, and uses the decision tree as an auxiliary to correct the erroneous state of the air-ground switch in the QAR parameters, thereby solving the problem of high-precision correction of the simulator air-ground switch state parameters.

[0033] Although the various steps in the above embodiment are described in the above-mentioned order, those skilled in the art can understand that in order to achieve the effect of this embodiment, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple changes are within the scope of protection of the present invention.

[0034] Based on the above embodiment, the method of obtaining the parameter with the greatest impact on the value of the air-to-ground switch based on the key flight parameters and using a multivariate decision tree model includes: The importance of parameter features is calculated using the flight key parameters through the splitting process of the multivariate decision tree model; Based on the importance of the parameter characteristics, it is determined that the parameter with the greatest impact on the value of the air-to-ground switch is the radio altitude.

[0035] Specifically, during the construction of the multivariate decision tree model, the importance of parameter features is calculated based on the flight key parameters used in the decision tree splitting process. After calculation, the importance of each flight key parameter to the air-to-ground switch value is obtained. It is found that the radio altitude (RA) parameter has the greatest impact on the air-to-ground switch value. Therefore, the present invention further selects this parameter for subsequent analysis to determine the specific judgment threshold.

[0036] Based on the above embodiment, the importance of parameter features is calculated using the flight key parameters through the splitting process of the multivariate decision tree model, such as Figure 2 As shown, including: Step S201, selecting preset parameters of the splitting process of the multivariate decision tree model from the key flight parameters in sequence; Step S202, based on the splitting of the current decision tree in the process of building the multivariate decision tree model, in each splitting process, the selected preset parameters are used to sequentially calculate the information gain values ​​of different preset parameters relative to the current decision tree; Step S203, determining the importance of the parameter feature based on the ranking of the information gain values ​​of the different preset parameters relative to the current decision tree; wherein the sum of the information gain values ​​of the different preset parameters relative to the current decision tree is 1.

[0037] That is, in each split, the information gain brought by using a specific parameter for splitting is calculated. The higher the information gain of a parameter, the greater the impact of the parameter on the result. The sum of the information gain values ​​of all parameters is 1.

[0038] Based on the above embodiment, the information gain values ​​of different preset parameters relative to the current decision tree are calculated in sequence using the selected preset parameters in each splitting process, including: The information entropy of the current decision tree is obtained by probability calculation based on the preset parameters and the value categories of the open space switch; An information gain value of the preset parameter relative to the current decision tree is obtained based on the preset parameter and the information entropy of the current decision tree.

[0039] Specifically, the information entropy calculation formula of the decision tree is:

[0040] The calculation formula for the information gain value based on the information entropy of the decision tree is:

[0041] in, represents the information entropy of the decision tree, Is the category The probability of, in the present invention, the category refers to the two values ​​0 and 1 of the open-air switch, Indicated in the parameter The upper value is The sample subset size is represents the total number of samples, Indicates that the preset parameters The upper value is The information entropy of the sample subset is Representation parameters Relative to the current decision tree The information gain brought by it.

[0042] Based on the above embodiment, the information entropy of the current decision tree is obtained by the probability calculation based on the preset parameters and the value category of the open space switch, and the formula is as follows:

[0043] in, represents the information entropy of the decision tree, It is the value category of open space switch The probability of the open space switch is 0. Indicates category 1, when the open space switch value is 1, Indicates category 2, Indicates that the preset parameters The number of value categories for upper ground switches.

[0044] Based on the above embodiment, the information gain value of the preset parameter relative to the current decision tree is obtained by calculating the information entropy based on the preset parameter and the current decision tree, and the formula is as follows:

[0045] in, Indicates that the preset parameters The upper value is The sample subset size is represents the total number of samples, Indicates that the preset parameters The upper value is The information entropy of the sample subset is Indicates preset parameters Relative to the current decision tree The information gain value brought.

[0046] Based on the above embodiment, a univariate single-layer decision tree is constructed based on the parameter with the largest impact on the open space switch value, and the optimal threshold of the open space switch value is determined based on the univariate single-layer decision tree, such as Figure 3 As shown, including: Step S301, constructing the univariate single-layer decision tree using radio altitude; Step S302, selecting an optimal threshold value by using a decision tree algorithm based on the univariate single-layer decision tree: traversing all possible values ​​of the radio altitude, and selecting an optimal threshold value by using the information gain value of the radio altitude relative to the current decision tree; Step S303, creating a decision node based on the optimal threshold, and dividing all possible values ​​of the radio altitude into two subsets based on the decision node, and recursively repeating the decision tree algorithm for the two subsets respectively until the maximum tree depth is reached to obtain the optimal threshold of the open-air switch value.

[0047] Specifically, the radio altitude (RA) is used to construct a univariate single-layer decision tree to determine the optimal threshold affecting the change of the air-ground switch value.

[0048] A univariate single-layer decision tree is a single-layer decision tree with only one parameter, and the information gain is calculated based on the parameter to determine the optimal threshold.

[0049] The steps of the single-variable decision tree algorithm are as follows: 1. Select parameters and thresholds: Traverse all possible values of parameter ra, select the optimal threshold through information gain, and divide the air-ground switch data into two parts.

[0050] 2. Create nodes: Create a decision node according to the selected threshold. If the air-ground switch data can be effectively separated, divide the data into two subsets.

[0051] 3. Recursively repeat the above process for each subset until the maximum tree depth is reached.

[0052] Based on the above embodiments, the correction of the air-ground switch parameters of the simulator is completed based on the optimal threshold of the air-ground switch value and the parameter that is most affected by the air-ground switch value, including: If the radio altitude is greater than the optimal threshold of the air-ground switch value, the value of the air-ground switch parameter of the simulator is 0; If the radio altitude is less than the optimal threshold of the air-ground switch value, the value of the air-ground switch parameter of the simulator is 1.

[0053] Specifically, after the above decision tree algorithm is executed, the radio altitude threshold ra_thr for determining the air-ground switch value is obtained. For all data, if ra > ra_thr, it is determined that the aircraft is in the air at this time, and the value of the air-ground switch parameter is 0; if ra < ra_thr, it is determined that the aircraft is on the ground at this time, and the air-ground switch parameter is 1. Through this step, the correction of the air-ground switch parameter is completed.

[0054] An electronic device according to the second embodiment of the present invention includes: At least one processor; And a memory communicatively connected to at least one of the processors; Wherein, the memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the above method for correcting the air-ground switch parameters of the simulator.

[0055] A computer-readable storage medium according to the third embodiment of the present invention, the computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the above method for correcting the air-ground switch parameters of the simulator.

[0056] Those skilled in the art of the present technology can clearly understand that for the convenience and conciseness of description, the specific working processes and related descriptions of the above-described storage device and processing device can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0057] Those skilled in the art should be able to appreciate that the modules and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two, and the programs corresponding to the software modules and method steps can be placed in random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0058] Reference below Figure 4 , which shows a schematic diagram of the structure of a computer system of a server for implementing the method, system, and device embodiments of the present application. Figure 4 The server shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0059] like Figure 4 As shown, the computer system includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403. Various programs and data required for system operation are also stored in the RAM 403. The CPU 401, ROM 402 and RAM 403 are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0060] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0061] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, - but not limited to - a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus or a device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus or a device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0062] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0063] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0064] The terms "first", "second", etc. are used to distinguish similar objects rather than to describe or indicate a particular order or sequence.

[0065] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus / device.

[0066] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for correcting parameters of a simulator open-ground switch, characterized in that: The following steps are involved: Obtain key flight parameters from the simulator QAR data; Based on the key flight parameters and using a multivariate decision tree model, the parameter with the greatest impact on the value of the air-to-ground switch is obtained; Constructing a univariate single-layer decision tree based on the parameter with the greatest impact on the open space switch value, and determining an optimal threshold value for the open space switch value based on the univariate single-layer decision tree; The simulator open-ground switch parameters are modified based on the optimal threshold of the open-ground switch value and the parameter with the greatest impact on the open-ground switch value.

2. The simulator open-ground switch parameter correction method according to claim 1 is characterized in that: The method of obtaining the parameters with the greatest impact on the air-to-ground switch value based on the key flight parameters and using a multivariate decision tree model includes: The importance of parameter features is calculated using the flight key parameters through the splitting process of the multivariate decision tree model; Based on the importance of the parameter characteristics, it is determined that the parameter with the greatest impact on the value of the air-to-ground switch is the radio altitude.

3. The simulator open-ground switch parameter correction method according to claim 2 is characterized in that: The splitting process of the multivariate decision tree model using the flight key parameters to calculate the importance of parameter features includes: Selecting preset parameters of the splitting process of the multivariate decision tree model in sequence from the key flight parameters; Based on the splitting of the current decision tree in the process of building the multivariate decision tree model, in each splitting process, the selected preset parameters are used to sequentially calculate the information gain values ​​of different preset parameters relative to the current decision tree; Determining the importance of the parameter feature based on the ranking of different preset parameters relative to the information gain values ​​of the current decision tree; The sum of the information gain values ​​of the different preset parameters relative to the current decision tree is 1.

4. The simulator open-ground switch parameter correction method according to claim 3 is characterized in that: The information gain values ​​of different preset parameters relative to the current decision tree are calculated in sequence using the selected preset parameters in each splitting process, including: The information entropy of the current decision tree is obtained by probability calculation based on the preset parameters and the value categories of the open space switch; An information gain value of the preset parameter relative to the current decision tree is obtained based on the preset parameter and the information entropy of the current decision tree.

5. The simulator open-ground switch parameter correction method according to claim 4 is characterized in that: The information entropy of the current decision tree is obtained by probability calculation based on the preset parameters and the value category of the open space switch, and the formula is as follows: ； in, represents the information entropy of the decision tree, It is the value category of the open space switch The probability of the open space switch is 0. Indicates category 1, when the open space switch value is 1, Indicates category 2, Indicates that the preset parameters The number of value categories for upper ground switches.

6. The simulator open-ground switch parameter correction method according to claim 4 is characterized in that: The information gain value of the preset parameter relative to the current decision tree is obtained by calculating the information entropy based on the preset parameter and the current decision tree, and its formula is as follows: ； in, represents the information entropy of the decision tree, Indicates that the preset parameters The upper value is The sample subset size is represents the total number of samples, Indicates that the preset parameters The upper value is The information entropy of the sample subset is Indicates preset parameters Relative to the current decision tree The information gain value brought.

7. The simulator open-ground switch parameter correction method according to claim 2 is characterized in that: The step of constructing a univariate single-layer decision tree based on the parameter with the largest impact on the open space switch value, and determining an optimal threshold value of the open space switch value based on the univariate single-layer decision tree includes: constructing the univariate single-layer decision tree using radio altitude; Selecting an optimal threshold using a decision tree algorithm based on the univariate single-layer decision tree: traversing all possible values ​​of the radio altitude, and selecting an optimal threshold by the information gain value of the radio altitude relative to the current decision tree; A decision node is created based on the optimal threshold, and all possible values ​​of the radio altitude are divided into two subsets based on the decision node, and the decision tree algorithm is recursively repeated for the two subsets respectively until the maximum tree depth is reached to obtain the optimal threshold of the open space switch value.

8. The simulator open-ground switch parameter correction method according to claim 2 is characterized in that: The method of modifying the simulator open-ground switch parameters based on the optimal threshold of the open-ground switch value and the parameter with the greatest impact on the open-ground switch value includes: If the radio altitude is greater than the optimal threshold of the air-to-ground switch value, the simulator air-to-ground switch parameter value is 0; If the radio altitude is less than the optimal threshold of the air-to-ground switch value, the simulator air-to-ground switch parameter value is 1.

9. An electronic device, characterized in that: include: at least one processor; and a memory communicatively coupled to at least one of the processors; Wherein, the memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the simulator air-to-ground switch parameter correction method described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to be executed by the computer to implement the simulator air-ground switch parameter correction method described in any one of claims 1-8.

Images