Test case generation method and platform for aircraft performance test

Abstract

The invention belongs to the technical field of software testing, and discloses a test case generation method and platform for aircraft performance testing. The method comprises the following steps: determining a first input parameter set, and generating a first test case by utilizing global random search; using the first test case to drive the flight management module to perform simulation test, and receiving first flight state data output after the flight management module performs the simulation test; determining a second input parameter set based on the first flight state information, and generating a second test case by using local random search; driving the flight management module to perform a simulation test by using the second test case, and receiving second flight state data output by the flight management module after the simulation test; an out-of-control input parameter is determined based on the second flight state data. Generation and execution of the test cases are optimized through an intelligent algorithm, the generation efficiency of the test cases is improved, the test cost is reduced, meanwhile, the more comprehensive test coverage rate is ensured, and the test reliability is improved.

Description

Technical Field

[0001] This application relates to the technical field of software testing, and particularly to a test case generation method and a generation platform for aircraft performance testing. Background Art

[0002] The Vehicle Management System (VMS) is a comprehensive system that encompasses key subsystems such as the Flight Management System (FMS) and the Propulsion Utility Management System (UMS) to ensure the safe flight of the aircraft. The core advantage of VMS lies in its comprehensive management ability. Through the integrated design concept, multiple functions and subsystems are coordinated as a whole. As the core control system of aircraft such as unmanned aerial vehicles, the performance and stability of the Flight Management System are directly related to the flight effect and safety of the aircraft. To ensure the high performance and stability of this critical system, it must be strictly tested and evaluated. However, traditional testing methods mainly rely on manual operations, including writing test cases and manually executing tests. This method is not only inefficient but also has limited test coverage, making it difficult to meet the high requirements for testing modern aircraft. Summary of the Invention

[0003] For this reason, the embodiments of this application provide a test case generation method and a generation platform for aircraft performance testing, which can improve the generation efficiency of test cases and effectively increase the test coverage at the same time.

[0004] In the first aspect, this application provides a test case generation method for aircraft performance testing.

[0005] This application is achieved through the following technical solutions:

[0006] A test case generation method for aircraft performance testing includes:

[0007] Determine a first set of input parameters, and generate a first test case using global random search based on the first set of input parameters;

[0008] Send the first test case to the flight management module, drive the flight management module to perform a simulation test, and receive the first flight state data output after the flight management module performs the simulation test;

[0009] Determine a second set of input parameters based on the first flight state information, and generate a second test case using local random search based on the second set of input parameters;

[0010] Send the second test case to the flight management module, drive the flight management module to perform a simulation test, and receive the second flight state data output after the flight management module performs the simulation test;

[0011] Determine the out-of-control input parameters based on the second flight state data.

[0012] In a preferred example of the present application, it can be further set that the determining the first input parameter set and generating the first test case by using global random search based on the first input parameter set includes:

[0013] Determine multiple input parameters of the aircraft to be tested in each flight mission phase and the value range corresponding to each input parameter, where the flight mission phases include the takeoff phase, the flight phase, and the landing phase;

[0014] Randomly select two random values within the value range of each input parameter, where the two random values are respectively located in the first half and the second half of the value range;

[0015] Combine all input parameters, corresponding random values with different flight mission phases to generate the first test case.

[0016] In a preferred example of the present application, it can be further set that the flight management module includes a simulation unit, a flight management calculation unit, and a flight simulation calculation unit. Send the first test case to the flight management module to drive the flight management module to perform a simulation test, including:

[0017] Use the first test case to drive multiple simulation systems in the simulation unit to perform a simulation test to obtain the first simulation result;

[0018] The flight management calculation unit adjusts the flight characteristic parameters based on the first simulation result and sends the adjusted flight characteristic parameters to the flight simulation calculation unit;

[0019] The flight simulation calculation unit comprehensively calculates the adjusted flight characteristic parameters and the first simulation result to obtain the first flight state data.

[0020] In a preferred example of the present application, it can be further set that the second input parameter set is determined based on the first flight state information, and the second test case is generated by using local random search based on the second input parameter set, including:

[0021] Compare the first flight state data with the reference flight state data, and determine the potential fault input parameters, potential fault flight phases, and potential fault value ranges where the flight of the aircraft to be tested is abnormal according to the comparison result;

[0022] Sub-divide the potential fault flight phases, where the takeoff phase is sub-divided into the takeoff off-the-ground phase and the climbing phase, the flight phase is sub-divided into the leveling-off phase, the cruise phase, and the circling phase, and the landing phase is sub-divided into the approach phase and the landing phase;

[0023] Divide the potential failure value range into four sub - ranges, and randomly determine a random input value in each sub - range;

[0024] Combine the potential failure input parameters, the potential failure flight phase, and the random input value to generate a second test case.

[0025] In a preferred example of the present application, it can be further set that,

[0026] The flight management module includes a simulation unit, a flight management calculation unit, and a flight simulation calculation unit. Send the second test case to the flight management module to drive the flight management module to perform a simulation test, including:

[0027] Use the second test case to drive multiple simulation systems in the simulation unit to perform a simulation test to obtain a second simulation result;

[0028] The flight management calculation unit adjusts the flight characteristic parameters based on the second simulation result, and sends the adjusted flight characteristic parameters to the flight simulation calculation unit;

[0029] The flight simulation calculation unit performs a comprehensive calculation on the adjusted flight characteristic parameters and the second simulation result to obtain second flight state data.

[0030] In a preferred example of the present application, it can be further set that after generating the first test case, it further includes: performing a sensitivity analysis on the first test case;

[0031] Use the gradient method to analyze the influence degree of each input parameter in the first test case on the output result;

[0032] Based on the influence degree, determine the logical relationship between each input parameter, where the logical relationship includes AND, OR, NOT, and subordination;

[0033] Based on the logical relationship, identify the redundant test cases in the first test case and delete the redundant test cases.

[0034] In a preferred example of the present application, it can be further set that after generating the second test case, it further includes:

[0035] Used to perform dimensionality reduction processing on the second test case using the trained random forest model.

[0036] In a second aspect, the present application provides a test case generation platform for aircraft performance testing.

[0037] The present application is achieved through the following technical solutions:

[0038] A test case generation platform for aircraft performance testing, which executes the test case generation platform method described in the first aspect above, includes:

[0039] A test environment module, a data exchange module, and a flight management module;

[0040] The test environment module includes a first generation unit and a second generation unit. The first generation unit is used to determine a first set of input parameters, generate a first test case using global random search based on the first set of input parameters, send the first test case to the flight management module for simulation testing, and receive the first flight status data of the flight management module; the second generation unit is used to determine a second set of input parameters based on the first flight status data, generate a second test case using local random search based on the second set of input parameters, send the second test case to the flight management module for simulation testing, receive the second flight status data of the flight management module, and determine out-of-control input parameters based on the second flight status data;

[0041] The data exchange module is used to cache the interaction data between the test environment module and the flight management module. The interaction data includes the first test case, the first flight status data, the second test case, and the second flight status data;

[0042] The flight management module is used to receive the first test case, perform simulation testing based on the first test case to obtain the first flight status data; receive the second test case, and perform simulation testing based on the second test case to obtain the second flight status data.

[0043] In a preferred example of the present application, it can be further set as

[0044] The test environment module further includes a first sensitivity analysis unit and a second sensitivity analysis unit;

[0045] The first sensitivity analysis unit is used to analyze the influence degree of each input parameter in the first test case on the output result using the gradient method, determine the logical relationship between each input parameter based on the influence degree, where the logical relationship includes AND, OR, NOT, and subordination, and identify and delete the redundant test cases in the first test case based on the logical relationship;

[0046] The second sensitivity analysis unit is used to perform dimensionality reduction processing on the second test case using the trained random forest model.

[0047] In the third aspect, the present application is achieved through the following technical solutions:

[0048] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the above test case generation methods for aircraft performance testing are implemented.

[0049] In summary, compared with the prior art, the beneficial effects brought by the technical solutions provided in the embodiments of the present application at least include:

[0050] The test case generation method of the present application determines a first input parameter set, generates a first test case using global random search based on the first input parameter set; sends the first test case to the flight management module, drives the flight management module to perform a simulation test, and receives the first flight state data output by the flight management module after the simulation test; determines a second input parameter set based on the first flight state information, generates a second test case using local random search based on the second input parameter set; sends the second test case to the flight management module, drives the flight management module to perform a simulation test, and receives the second flight state data output by the flight management module after the simulation test; determines the out-of-control input parameters based on the second flight state data. By optimizing the generation and execution of test cases through intelligent algorithms, the generation efficiency of test cases is improved, the test cost is reduced, and at the same time, a more comprehensive test coverage is ensured, and the reliability of the test is improved. Description of the Drawings

[0051] Figure 1 It is a schematic structural diagram of a test case generation platform for aircraft performance testing provided by an embodiment of the present application;

[0052] Figure 2 It is a schematic structural diagram of a test case generation platform for aircraft performance testing provided by another embodiment of the present application;

[0053] Figure 3 It is a schematic structural diagram of a test case generation platform for aircraft performance testing provided by another embodiment of the present application;

[0054] Figure 4 It is a schematic flowchart of a test case generation method for aircraft performance testing provided by an embodiment of the present application;

[0055] Description of the Reference Numerals:

[0056] Test environment module 1, first generation unit 11, second generation unit 12, data exchange module 2, flight management module 3, simulation unit 31, flight management calculation unit 32, flight simulation calculation unit 33, first sensitivity analysis unit 13, second sensitivity analysis unit 14. Detailed Embodiments

[0057] This specific embodiment is only an interpretation of the present application and does not limit the present application. After reading this specification, those skilled in the art can make modifications to this embodiment that do not contribute creatively, but as long as they are within the scope of the claims of the present application, they are protected by the patent law.

[0058] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0059] In addition, the term "and / or" in the present application is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present application generally represents an "or" relationship between the associated objects before and after, unless otherwise specified.

[0060] The terms "first", "second", etc. in the present application are used to distinguish between identical or similar items with basically the same functions and effects. It should be understood that there is no logical or chronological dependency between "first", "second", and "nth", nor are the quantity and execution order limited.

[0061] In the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, using words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner.

[0062] When testing the performance of an aircraft, the design of test cases needs to consider different test scenarios and test purposes, such as tests for attitude control, position control, navigation control, flight mode switching, etc. At the same time, when designing test cases, representative test cases need to be designed according to different functional modules of the aircraft management system to cover as many functional points and test requirements of the aircraft management system as possible. Different test parameters and test environments also need to be considered to ensure the reliability and effectiveness of test results.

[0063] Test cases are designed to simulate the complete flight scenario of an unmanned aerial vehicle from takeoff to landing, in which some components will fail in specific flight scenarios, such as the landing gear failing during takeoff or landing or the operator continuously pulling the joystick, etc.

[0064] The data information of the test cases is divided into input information and output information, which is used to comprehensively evaluate the flight function and stability of the UAV. Among them, the input data includes the modules and related data that need to be tested for the test equipment and the aircraft itself, specifically including:

[0065] (1) Inertial Navigation System (INS) and its data: Provide inertial navigation data at frequencies of 100Hz and 400Hz, and provide information such as the acceleration and angular velocity of the aircraft;

[0066] (2) GPS and DGPS and their data: GPS-1, GPS-2, GPS-3, and DGPS (Differential GPS), a total of 4 modules, are used to provide accurate position information;

[0067] (3) Atmospheric Computer and its data: Two identical atmospheric computer devices are respectively provided for redundant measurement. Both device A and device B are used to measure atmospheric parameters, such as atmospheric data such as temperature, pressure, and wind speed;

[0068] (4) Front-wheel control equipment and its data: Two identical front-wheel control equipment are respectively provided for redundant control. Device A and device B respectively control the direction and position of the front wheel;

[0069] (5) Power control equipment and its data: Two identical power control equipment are respectively provided for redundant control. Device A and device B are respectively responsible for the management and control of the UAV power system;

[0070] (6) Brake control equipment and its data: Two identical brake control equipment are respectively provided for redundant control. Device A and device B respectively control the braking system of the UAV;

[0071] (7) Main and standby channels of the controller and its data: Each direction of the controller has main and standby channels to ensure that the standby channel can take over control when the main channel fails;

[0072] (8) Fiber optic attitude sensor and its data: Fiber optic attitude data at frequencies of 100Hz and 400Hz, providing aircraft attitude information;

[0073] (9) Pilot instructions and their data: Pull and push the throttle lever, rudder control, etc.

[0074] The output data are the key parameters generated during the flight of the UAV, which are mainly used to evaluate the flight stability and control performance. The output data generally includes:

[0075] (1) Flight attitude: Such as pitch angle, roll angle, heading angle, etc.

[0076] (2) Flight data: including speed, altitude, climb rate, etc.

[0077] (3) Position coordinates: real-time position information provided by GPS and DGPS, used to track the flight path.

[0078] (4) Track and heading information: used to record and analyze the flight route of the UAV.

[0079] The embodiments of the present application will be further described in detail below with reference to the accompanying drawings of the specification.

[0080] Refer to Figure 1 which is a test case generation platform for aircraft performance testing provided by an exemplary embodiment of the present application, and includes:

[0081] A test environment module 1, a data exchange module 2, and a flight management module 3;

[0082] Among them, the test environment module 1 includes a first generation unit 11 and a second generation unit 12; the test environment module 1 can automatically generate test cases according to the input parameter set, and drive the flight management module 3 to perform a simulation test according to the test cases, and then screen out the test cases whose operation results exceed the preset output quantity reference range according to the simulation results of the flight management module 3 and the preset output quantity reference range. The test cases include multiple input parameter sets.

[0083] Specifically, the first generation unit 11 is used to determine the first input parameter set, generate the first test case using global random search based on the first input parameter set, send the first test case to the flight management module 3 for simulation testing, and receive the first flight state data of the flight management module 3. It should be noted that the test environment module 1 transmits the first test case generated by the first generation unit 11 to the data exchange module 2 in a specific format, and the data exchange module 2 outputs it to the flight management module 3; after the flight management module 3 performs the simulation test, the obtained first flight state data is transmitted to the data exchange module 2, and the data exchange module 2 outputs it to the test environment module 1.

[0084] Among them, the second generation unit 12 is used to determine a second set of input parameters based on the first flight state data, generate a second test case by using local random search based on the second set of input parameters, send the second test case to the flight management module 3 for simulation testing, receive the second flight state data of the flight management module 3, and determine out-of-control input parameters based on the second flight state data. It should be noted that the test environment module 1 transmits the second test case generated by the second generation unit 12 to the data exchange module 2 in a specific format, and the data exchange module 2 outputs it to the flight management module 3; after the flight management module 3 conducts simulation testing, the obtained second flight state data is transmitted to the data exchange module 2, and the data exchange module 2 outputs it to the test environment module 1.

[0085] The data exchange module 2 is used to cache the interaction data between the test environment module 1 and the flight management module 3. The interaction data includes the first test case, the first flight state data, the second test case, and the second flight state data.

[0086] The flight management module 3 is used to receive the first test case, conduct simulation testing based on the first test case to obtain the first flight state data; receive the second test case, and conduct simulation testing based on the second test case to obtain the second flight state data.

[0087] It should be noted that the data exchange module 2, as the connection module between the test environment module 1 and the flight management module 3, is used to cache a large amount of the first test case and the second test case transmitted from the test environment module 1 to the flight management module 3, as well as the first flight state data and the second flight state data transmitted from the flight management module 3 to the test environment module 1. In order to facilitate better storage of a large amount of interaction data, the data exchange module 2 stores the data in a specific format.

[0088] Specifically, the data exchange module 2 stores input parameters in xml format, including variable name, upper and lower bounds, data type (continuous / discrete), number of bits, default value, data scaling ratio, and address; stores discriminant variables in xml format, including variable name, upper and lower bounds, data type (continuous / discrete); stores the relationships between variables in xml format, which are mainly divided into AND, OR, NOT, and subordination, and each two variables in the main category are grouped to reflect their relationships; uses the MAC and inp file formats to record test cases, and each test case is stored in a file, which is convenient for management and modification. Compared with the traditional method of directly adjusting input variables manually through reflective memory, the improved method records test cases in the MAC and inp file formats, realizes independent storage and automated management of test cases, improves efficiency and traceability, and is convenient for management and reuse of test cases.

[0089] In a preferred embodiment, the test environment module 1 and the flight management module 3 are deployed on a computing simulation server. The test environment module 1 uses multi-process technology to start or stop multiple flight management system software in the flight management module 3. The data exchange module is deployed on a data storage server. The simulation server and the data storage server are connected through a network protocol. Specifically, through one of the network protocols FC, iSCSI, NFS, CIFS, HTTP, FTP. In view of the problems commonly existing in test case generation, such as large computational volume, difficult variable management, and difficult management of a large amount of data, the present application proposes to use distributed computing and a software and hardware architecture driven by variable management to complete the generation of the use case environment and achieve an efficient solution to this complex problem.

[0090] Reference Figure 2 Shown is a test case generation platform for aircraft performance testing. The flight management module 3 includes a simulation unit 31, a flight management calculation unit 32, and a flight simulation calculation unit 33.

[0091] Among them, the simulation unit 31 includes multiple simulation systems, which are used to receive the first test case from the data exchange module 2, drive the multiple simulation systems to perform simulation tests using the first test case, and obtain the first simulation result; and are used to receive from the data exchange module, drive the multiple simulation systems to perform simulation tests using the second test case, and obtain the second simulation result. It should be noted that the simulation systems include a ground station simulation system, a servo simulation system, a sensor simulation system, a cross-link simulation system, a mission simulation system, etc. The simulation unit 31 is not limited to the simulation systems mentioned above.

[0092] The flight management calculation unit 32 is used to adjust the flight characteristic parameters based on the simulation results and send the adjusted flight characteristic parameters to the flight simulation calculation unit 33, where the simulation results include the first simulation result and the second simulation result. Specifically, the flight management calculation unit 32 receives the first simulation result from the simulation unit 31, makes a first adjustment to the flight characteristic parameters based on the first simulation result, and sends the adjusted flight characteristic parameters to the flight simulation calculation unit 33; the flight management calculation unit 32 receives the second simulation result from the simulation unit 31, makes a second adjustment to the flight characteristic parameters based on the second simulation result, and sends the adjusted flight characteristic parameters to the flight simulation calculation unit 33. Among them, the flight characteristic parameters include flight parameters and component parameters.

[0093] A flight simulation calculation unit 33 is configured to comprehensively calculate the adjusted flight characteristic parameters and simulation results to obtain flight state data, where the flight state data includes first flight state data and second flight state data. Specifically, the flight simulation calculation unit 33 comprehensively calculates the flight characteristic parameters after the first adjustment and the first simulation result to obtain the current first flight state data of the aircraft under test. In addition, the flight simulation calculation unit 33 comprehensively calculates the flight characteristic parameters after the second adjustment and the second simulation result to obtain the current second flight state data of the aircraft under test.

[0094] In some embodiments, when the first generation unit 11 determines the first input parameter set and generates the first test case using global search based on the first input parameter set, it is specifically configured to:

[0095] Determine a plurality of input parameters of the aircraft under test in different flight mission phases and the value range corresponding to each input parameter, where the flight mission phases include a takeoff phase, a flight phase, and a landing phase;

[0096] Randomly select two random values within the value range of each input parameter, where the two random values are respectively located in the first half and the second half of the value range;

[0097] Combine all input parameters, the corresponding random values, and different flight mission phases to form the first test case.

[0098] It should be noted that when determining the random values of all input parameters and performing combinations, the following constraint conditions are also required:

[0099] (a) Under the condition of taking only one fault, three flight mission phases are required for combined changes, and at the same time, consider the restoration of the fault in the next phase. In this case, there are 2n*(3 + 3) possibilities, where 2n is a random value, one 3 is for the non-restoration of the next phase after the fault occurs, and the other 3 is for the occurrence of the fault and the restoration in the next phase;

[0100] (b) Under the condition of taking two faults, three flight mission phases are required for combined changes, and at the same time, consider the restoration of the faults in the next phase, including the restoration of both faults in the next phase, the non-restoration of both faults in the next phase, and the restoration of only one of the faults in the next phase.

[0101] In the global random search, each iteration is independent and not affected by the previous iteration. The value of each input variable is randomly selected within its value range, and all variables are combined into a test case. In the global random search process, the test case is generated only once to roughly locate the part where problems may occur.

[0102] In some embodiments, when the second generating unit 12 determines the second input parameter set based on the first flight status data and generates the second test case based on the second input parameter set by using local random search, it is specifically used to:

[0103] The first flight status data is compared with the reference flight status data, and the potential fault input parameters, potential fault flight phase and potential fault value range of the abnormal flight of the aircraft under test are determined according to the comparison result; wherein the reference flight status data is used to indicate normal data.

[0104] The potential failure flight phase is subdivided. If the potential failure flight phase belongs to the take-off phase, the take-off phase is subdivided into the take-off phase and the climb phase. If the potential failure flight phase belongs to the flight phase, the flight phase is subdivided into the leveling phase, the cruising phase and the circling phase. If the potential failure flight phase belongs to the landing phase, the landing phase is subdivided into the approach phase and the landing phase.

[0105] The potential fault value interval is divided into four sub-intervals, and a random value is randomly determined in each sub-interval;

[0106] The potential fault input parameters, potential fault flight phase and random values ​​are combined to generate a second test case.

[0107] In some preferred embodiments, the second generation unit 12 iterates the local random search process twice to accurately locate the part with the problem. Local random search adds an iterative optimization function on the basis of global random search. The candidate solution of each iteration depends on the result of the previous iteration, and the search is concentrated near the area with potential faults previously found. This method can adjust the parameters more finely and converge to the parameter area with better performance more quickly.

[0108] In some preferred embodiments, in order to reduce the data size while ensuring the coverage of test cases, refer to Figure 3 , the test environment module 1 also includes a first sensitivity analysis unit 13;

[0109] Specifically, the first sensitivity analysis unit 13 is used to use the gradient method to analyze the degree of influence of each input parameter in the first test case on the output result; determine the logical relationship between each input parameter based on the degree of influence, where the logical relationship includes AND, OR, NOT and subordination; based on the logical relationship, identify redundant test cases in the first test case and delete the redundant test cases.

[0110] The gradient method calculates the partial derivatives of the objective function with respect to each input parameter to obtain the change in the output when each input parameter changes. By observing whether a certain quantity of the flight state exceeds the limit after the observation component enters the simulation test, the sensitivity analysis of the input parameters and output parameters is completed to assist in determining whether the positioned area is accurate; if two input parameters cause the output parameter to change, their AND / OR dependency relationship is considered.

[0111] After determining the logical relationship between each input parameter, redundant test cases are determined according to the following rules:

[0112] Through the AND relationship, the values of multiple input parameters can be combined together, and it is not necessary to consider all possible values of each input parameter separately. Only combine them into one test case, and the rest are used as redundant test cases, thus reducing the number of independently generated test cases.

[0113] When considering test cases, the number of combinations that must be considered can be reduced. As long as one of the conditions is met, it is not necessary to meet both conditions at the same time, so the number of test cases can be significantly reduced.

[0114] By clarifying which combinations do not need to be considered, after excluding certain value combinations, the scale of the test cases is reduced, and the range of generated test cases can be further narrowed. By reducing the options for free combinations, the dependency relationship can greatly reduce the number of test cases that need to be generated. By capturing the dependencies between input parameters, invalid or impossible combinations can be avoided, thus reducing redundancy.

[0115] In some preferred embodiments, with continued reference to Figure 3 , the test environment module 1 further includes a second sensitivity analysis unit 14; the second sensitivity analysis unit 14 is used to perform dimensionality reduction processing on the second test case by using the trained random forest model. Specifically, the random forest classifier in the sklearn.ensemble toolkit is used to train the simulation data after local random search. The random forest classifier has a built-in feature importance scoring mechanism, and the importance scores of each input parameter can be obtained through the feature_importances_ attribute; further, according to the importance scores of the features, the top N most important features are selected as the new input features, and the unimportant features are removed to complete the dimensionality reduction. N is selected as 75% of the more important values among all variable values.

[0116] In a preferred embodiment, when the first generation unit sends the first test case to the flight management module for simulation testing, it is specifically used for:

[0117] Set the preset simulation time for multiple flight mission phases, and generate test cases for each flight mission phase according to the preset simulation time; send the test cases for each flight mission phase to the flight management module in a multi-process manner to drive the flight management module to complete the simulation test of the entire process.

[0118] The test case generation platform of this application supports a massive-scale test environment, featuring a large quantity and comprehensive coverage. Compared with traditional manual case generation, it can ensure the comprehensiveness of test cases and improve the generation efficiency; the test environment module provides an optimization search algorithm from the global to the local, avoiding the problem that traditional grid search algorithms are prone to missing unqualified cases; through sensitivity analysis, the relationships between components and between components and flight states in the flight management module are improved. On the premise of ensuring coverage, the scale of test case generation is effectively reduced, and efficient testing is carried out for related components, enhancing the pertinence and efficiency of testing.

[0119] In another embodiment of this application, a test case generation method for aircraft performance testing is also provided. Referring to Figure 4 as shown, this method includes:

[0120] S1: Determine the first input parameter set, and generate the first test case using global random search based on the first input parameter set;

[0121] S2: Send the first test case to the flight management module, drive the flight management module to conduct a simulation test, and receive the first flight state data output after the flight management module conducts the simulation test;

[0122] S3: Determine the second input parameter set based on the first flight state information, and generate the second test case using local random search based on the second input parameter set;

[0123] S4: Send the second test case to the flight management module, drive the flight management module to conduct a simulation test, and receive the second flight state data output after the flight management module conducts the simulation test;

[0124] S5: Determine the out-of-control input parameters based on the second flight state data.

[0125] Among them, step S1 specifically includes:

[0126] S11: Determine multiple input parameters of the aircraft under test in each flight mission phase and the value range corresponding to each input parameter, where the flight mission phases include the takeoff phase, the flight phase, and the landing phase;

[0127] S12: Randomly select two random values within the value range of each input parameter, where the two random values are respectively located in the first half and the second half of the value range;

[0128] S13: Combine all input parameters, corresponding random values ​​and different flight mission phases to form a first test case.

[0129] The flight management module includes a simulation unit, a flight management calculation unit and a flight simulation calculation unit. In step S2, the first test case is sent to the flight management module to drive the flight management module to perform a simulation test, which specifically includes:

[0130] S21: using a first test case to drive multiple simulation systems in a simulation unit to perform simulation testing, and obtaining a first simulation result;

[0131] S22: The flight management calculation unit adjusts the flight characteristic parameters based on the first simulation result, and sends the adjusted flight characteristic parameters to the flight simulation calculation unit;

[0132] S23: The flight simulation calculation unit performs comprehensive calculation on the adjusted flight characteristic parameters and the first simulation result to obtain first flight status data.

[0133] Wherein, in step S3, determining a second input parameter set based on the first flight state information, and generating a second test case based on the second input parameter set by using local random search, include:

[0134] S31: comparing the first flight state data with the reference flight state data, and determining potential fault input parameters, potential fault flight stages, and potential fault value intervals of abnormal flight of the aircraft under test according to the comparison result;

[0135] S32: The potential failure flight phases are subdivided into the take-off phase and the climb phase, the flight phase is subdivided into the leveling phase, the cruising phase and the circling phase, and the landing phase is subdivided into the approach phase and the landing phase;

[0136] S33: Divide the potential fault value interval into four sub-intervals, and randomly determine a random input value in each sub-interval;

[0137] The potential fault input parameters, potential fault flight phases and random input values ​​are combined to generate a second test case.

[0138] The flight management module includes a simulation unit, a flight management calculation unit and a flight simulation calculation unit. In step S4, the second test case is sent to the flight management module to drive the flight management module to perform a simulation test, including:

[0139] S41: using a second test case to drive multiple simulation systems in the simulation unit to perform simulation testing to obtain a second simulation result;

[0140] S42: The flight management computing unit adjusts the flight characteristic parameters based on the second simulation result and sends the adjusted flight characteristic parameters to the flight simulation computing unit;

[0141] S43: The flight simulation computing unit comprehensively calculates the adjusted flight characteristic parameters and the second simulation result to obtain the second flight state data.

[0142] In some embodiments, after step S1, it further includes:

[0143] Conduct a sensitivity analysis on the first test case;

[0144] Use the gradient method to analyze the influence degree of each input parameter on the output result in the first test case;

[0145] Determine the logical relationship between each input parameter based on the influence degree, where the logical relationship includes AND, OR, NOT, and subordination;

[0146] Based on the logical relationship, identify the redundant test cases in the first test case and delete the redundant test cases.

[0147] In some embodiments, after step S4, it further includes: using the trained random forest model to perform dimensionality reduction processing on the second test case.

[0148] The embodiments of the present application provide a computer device, which may include a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the processor executes the steps of the test case generation method for aircraft performance testing as described in any of the above embodiments.

[0149] For the working process, working details, and technical effects of the computer device provided in this embodiment, reference may be made to the embodiments of the test case generation method for aircraft performance testing described above, and details are not repeated here.

[0150] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in this application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0151] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0152] Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the system described in this application is divided into different functional units or modules to complete all or part of the functions described above.

Claims

1. A test case generation method for aircraft performance testing, characterized in that, Including: Determine a first set of input parameters, and generate a first test case using global random search based on the first set of input parameters; Send the first test case to the flight management module, drive the flight management module to perform a simulation test, and receive the first flight state data output after the flight management module performs the simulation test; Determine a second set of input parameters based on the first flight state information, and generate a second test case using local random search based on the second set of input parameters; Send the second test case to the flight management module, drive the flight management module to perform a simulation test, and receive the second flight state data output after the flight management module performs the simulation test; Determine the out-of-control input parameters based on the second flight state data.

2. The test case generation method for aircraft performance testing according to claim 1, wherein, The determining the first set of input parameters and generating the first test case using global random search based on the first set of input parameters includes: Determine multiple input parameters of the aircraft under test in each flight mission phase and the corresponding value range of each input parameter, where the flight mission phases include the takeoff phase, the flight phase, and the landing phase; Randomly select two random values within the value range of each input parameter, where the two random values are respectively located in the first half and the second half of the value range; Combine all input parameters, the corresponding random values, and different flight mission phases to generate a first test case.

3. The test case generation method for aircraft performance testing according to claim 1, characterized in that, The flight management module includes a simulation unit, a flight management calculation unit, and a flight simulation calculation unit. Sending the first test case to the flight management module and driving the flight management module to perform a simulation test includes: Use the first test case to drive multiple simulation systems in the simulation unit to perform a simulation test to obtain a first simulation result; The flight management calculation unit adjusts the flight characteristic parameters based on the first simulation result, and sends the adjusted flight characteristic parameters to the flight simulation calculation unit; The flight simulation calculation unit performs comprehensive calculations on the adjusted flight characteristic parameters and the first simulation result to obtain the first flight state data.

4. The test case generation method for aircraft performance testing according to claim 1, wherein, Determine a second set of input parameters based on the first flight state information, and generate a second test case using local random search based on the second set of input parameters, including: Compare the first flight state data with the reference flight state data, and determine the potential fault input parameters, the potential fault flight phase, and the potential fault value range where the flight of the aircraft under test is abnormal according to the comparison result; Sub-divide the potential fault flight phase, where the takeoff phase is sub-divided into the takeoff-off-the-ground phase and the climb phase, the flight phase is sub-divided into the leveling-off phase, the cruise phase, and the circling phase, and the landing phase is sub-divided into the approach phase and the landing phase; Divide the potential fault value range into four sub-ranges on average, and randomly determine a random input value in each sub-range; Combine the potential fault input parameters, the potential fault flight phase, and the random input value to generate a second test case.

5. The test case generation method for aircraft performance testing according to claim 1, wherein The flight management module includes a simulation unit, a flight management calculation unit, and a flight simulation calculation unit. Sending the second test case to the flight management module and driving the flight management module to perform a simulation test includes: Use the second test case to drive multiple simulation systems in the simulation unit to perform simulation tests, and obtain the second simulation result; The flight management calculation unit adjusts the flight characteristic parameters based on the second simulation result, and sends the adjusted flight characteristic parameters to the flight simulation calculation unit; The flight simulation calculation unit performs comprehensive calculations on the adjusted flight characteristic parameters and the second simulation result to obtain the second flight state data.

6. The test case generation method for aircraft performance testing according to claim 2, wherein After generating the first test case, it further includes: performing sensitivity analysis on the first test case; Use the gradient method to analyze the influence degree of each input parameter in the first test case on the output result; Based on the influence degree, determine the logical relationship between each input parameter, where the logical relationship includes AND, OR, NOT, and subordination; Based on the logical relationship, identify the redundant test cases in the first test case and delete the redundant test cases.

7. The test case generation method for aircraft performance testing according to claim 6, wherein, After generating the second test case, it further includes: Used to perform dimensionality reduction processing on the second test case using the trained random forest model.

8. A test case generation platform for aircraft performance testing, characterized in that, Used to execute the method according to any one of claims 1 to 7, including: A test environment module, a data exchange module, and a flight management module; The test environment module includes a first generation unit and a second generation unit. The first generation unit is used to determine the first input parameter set, generate the first test case using global random search based on the first input parameter set, send the first test case to the flight management module for simulation testing, and receive the first flight state data of the flight management module; the second generation unit is used to determine the second input parameter set based on the first flight state data, generate the second test case using local random search based on the second input parameter set, send the second test case to the flight management module for simulation testing, receive the second flight state data of the flight management module, and determine the out-of-control input parameter based on the second flight state data; The data exchange module is used to cache the interaction data between the test environment module and the flight management module, and the interaction data includes the first test case, the first flight state data, the second test case, and the second flight state data; The flight management module is used to receive the first test case, perform simulation testing based on the first test case to obtain the first flight state data; receive the second test case, and perform simulation testing based on the second test case to obtain the second flight state data.

9. The test case generation platform for aircraft performance testing according to claim 8, characterized in that, The test environment module further includes a first sensitivity analysis unit and a second sensitivity analysis unit; The first sensitivity analysis unit is used to use the gradient method to analyze the influence degree of each input parameter in the first test case on the output result, determine the logical relationship between each input parameter based on the influence degree, where the logical relationship includes AND, OR, NOT, and subordination, and based on the logical relationship, identify the redundant test cases in the first test case and delete the redundant test cases; The second sensitivity analysis unit is used to perform dimensionality reduction processing on the second test case using the trained random forest model.

10. A computer device, characterized in that, Comprising a memory, a processor, and a computer program stored in the memory, the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

Images