A development kit performance testing system and method based on data analysis

Abstract

The invention discloses a development kit performance test system and method based on data analysis, and relates to the field of performance test data processing. The invention tests the development kit to be tested from two perspectives: a single performance test and a comprehensive performance test, so that the test result more accurately and comprehensively reflects the performance of the development kit to be tested. First, a single performance test is performed on the development kit to be tested, in order to determine whether certain performances of the development kit to be tested meet the test requirements of a certain test sub-item individually. Then, by clustering the test parameter comprehensive data set matrix, test sub-items with similar test conditions and no conflict with each other are clustered into one category, and then the development kit to be tested is tested simultaneously using the multiple test sub-items clustered into one category, so that the comprehensive anti-interference ability of the development kit to be tested can be detected, and the performance detection is more precise, comprehensive and accurate.

Description

Technical Field

[0001] The present invention belongs to the field of performance test data processing, and in particular, relates to a development kit performance test system and method based on data analysis. Background Art

[0002] Before putting a development kit into use, it is necessary to conduct a variety of performance tests to detect whether the performance of the development kit meets the requirements; traditional development kit performance tests often focus on a single virtual environment or test project, which can only detect the performance of the development kit under a single test project; then in actual use, due to the complexity of the environment, multiple factors often interfere with the development kit at the same time; therefore, if only a single test project is performed each time, it is impossible to accurately detect the actual performance of the development kit, which may leave hidden dangers for actual use. Summary of the invention

[0003] In view of the problems in the related art, the present invention proposes a development kit performance testing system and method based on data analysis to overcome the above technical problems existing in the existing related art.

[0004] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0005] The present invention is a development kit performance testing method based on data analysis, comprising the following steps:

[0006] S1. Set test parameter types for multiple test sub-items and standard parameter types when the test requirements are met to obtain a test parameter type set matrix and a standard parameter type set matrix;

[0007] S2, collecting test parameter data and standard parameter data of corresponding test sub-items according to the test parameter type set matrix and the standard parameter type set matrix to perform a single performance test on the development kit to be tested, and collecting corresponding test result data to make an initial determination on whether the single performance of the development kit to be tested meets the requirements, and obtaining a first determination result;

[0008] S3, performing a clustering operation on the test parameter comprehensive data set matrix according to the first determination result to obtain a test parameter comprehensive data set classification matrix set; performing a comprehensive performance test on the development kit to be tested according to the test parameter comprehensive data set classification matrix set to obtain a comprehensive test result parameter data set matrix;

[0009] S4, making an initial judgment on whether the comprehensive performance of the development kit to be tested meets the requirements according to the comprehensive test result parameter data set matrix, and performing a single performance test and a comprehensive performance test on the performance of the development kit to be tested in multiple time periods according to the test parameter data set matrix, to obtain a single real-time result parameter data matrix set and a comprehensive real-time result parameter data matrix set;

[0010] S5. making a final judgment on the single performance and the comprehensive performance of the development kit to be tested according to the single real-time result parameter data matrix set and the comprehensive real-time result parameter data matrix set;

[0011] By setting the test parameter types of multiple test sub-projects and the standard parameter types when the test requirements are met, a collection basis is provided for the subsequent collection of test parameter data and test result parameter data corresponding to each test sub-project; by collecting the test parameter data and standard parameter data of each sub-project, a setting basis is provided for the subsequent setting of test-related parameters when testing the development kit to be tested, as well as a judgment basis after the test is completed; a single performance test refers to the testing of only a single test sub-project in each test; in this solution, a single performance test is first performed on the development kit to be tested in order to determine whether certain performance of the development kit to be tested meets the test requirements of a certain test sub-project separately; however, in the actual use environment, due to complex external interference, the interference to the development kit to be tested is often multiple and simultaneous; based on this, in this solution, a comprehensive test is performed after a single performance test on the development kit to be tested. In the test, by clustering the test parameter comprehensive data set matrix, the test sub-items with similar test conditions and no conflicts are clustered into one category, and then the development kit to be tested is tested simultaneously using multiple test sub-items clustered into one category, so that the comprehensive anti-interference ability of the development kit to be tested can be detected, making the performance detection more refined, comprehensive and accurate, and more accurately simulating the interference conditions that may occur in the actual operating environment; since the performance of the development kit often changes with the extension of the normal use period, the performance of the development kit needs to meet the normal use for a certain period of time, and during this period of time, the performance of the development kit needs to always meet the requirements; based on the above, in this scheme, by performing single performance tests and comprehensive performance tests on the performance of the development kit to be tested in multiple time periods, it can be determined whether the performance of the development kit to be tested will continue to meet the requirements as the normal use period increases.

[0012] The development kit to be tested is preferably a SOM-A1000-01 development kit;

[0013] Preferably, the S1 comprises the following steps:

[0014] S11, setting the type of performance test to be performed on the development kit to obtain a performance test type set; setting multiple test sub-items for each performance test type in the performance test type set to obtain a performance test sub-item matrix;

[0015] Setting the test parameter type of each test sub-item in the performance test sub-item matrix to obtain a test parameter type set matrix;

[0016] S12, setting the standard parameter type corresponding to each performance test sub-item matrix in the performance test sub-item matrix when the test requirement is met, to obtain a standard parameter type set matrix;

[0017] The performance test sub-item matrix includes electrostatic discharge (ESD), electrical transient conduction immunity (CI) along the power line, electrical transient emission immunity (CI) coupled to non-power lines, conducted emission (CE), radiated emission (RE), radiated immunity (RS), large current injection (BCI), low temperature operation project, low temperature start-up project, high temperature operation project, high temperature endurance project, wet heat cycle project, salt spray test project, mechanical vibration project, mechanical shock project and free fall project, etc.;

[0018] The test parameter type set matrix includes electromagnetic compatibility test standards and specifications, such as the International Electrotechnical Commission (IEC) standards, military standards, etc.; required electromagnetic interference sources, test equipment, measuring instruments, etc.; test frequency range; electromagnetic field strength applied to the device under test; signal modulation methods during electromagnetic wave propagation, such as amplitude modulation, frequency modulation, etc.; considering interference sources, other electronic equipment, power lines, etc. When conducting electromagnetic compatibility tests, it is necessary to identify and control these interference sources to ensure the accuracy of the test results; set test frequency, field strength and other parameters;

[0019] The matrix of standard parameter type sets includes conducted emissions, radiated emissions, harmonic currents, voltage fluctuations and flicker, electrostatic discharge immunity, radiated radio frequency electromagnetic field immunity, electrical fast transient burst immunity, surge, conducted immunity, power frequency magnetic field immunity, and voltage dips / interruptions.

[0020] Preferably, S2 comprises the following steps:

[0021] S21, acquiring test parameter data and standard parameter data of each test sub-item of each performance test type according to the test parameter type set matrix and the standard parameter type set matrix, to obtain a test parameter data set matrix and a standard parameter data set matrix;

[0022] Combining the test parameter data set matrix with the test parameter type set matrix to obtain a test parameter comprehensive data set matrix; combining the standard parameter data set matrix with the standard parameter type set matrix to obtain a standard parameter comprehensive data set matrix;

[0023] S22, setting a development kit to be tested; performing a single performance test on the development kit to be tested according to the test parameter comprehensive data set matrix; when all test sub-items are completed, collecting test result parameter data of the development kit to be tested according to the standard parameter type set matrix to obtain a single test result parameter data set matrix;

[0024] S23, if the result parameter data in the single test result parameter data set matrix is ​​inconsistent with the corresponding standard parameter comprehensive data in the standard parameter comprehensive data set matrix, then there is a problem with the performance of the development kit to be tested; otherwise, the performance of the development kit to be tested meets the standard of the single test;

[0025] By combining the test parameter data set matrix with the test parameter type set matrix, the data is combined with the corresponding data type, so that when conducting subsequent comprehensive performance tests, test sub-items with similar test parameter data can be accurately matched, and accurate comparison can be performed to determine whether the development kit to be tested meets the test requirements.

[0026] Preferably, S3 comprises the following steps:

[0027] S31, when the performance of the development kit to be tested meets the standard of a single test, performing a clustering operation on the test parameter comprehensive data set matrix to obtain a test parameter comprehensive data set classification matrix set;

[0028] S32, simultaneously performing performance tests on the development kit to be tested for each test sub-item in each test parameter comprehensive data set classification matrix set in the test parameter comprehensive data set classification matrix; when all tests are completed, collecting test result parameter data of the development kit to be tested according to the standard parameter type set matrix to obtain a comprehensive test result parameter data set matrix;

[0029] By simultaneously performing performance tests on the development kit under test for each test sub-item in each test parameter comprehensive data set classification matrix, multiple test sub-items are superimposed together to jointly interfere with the development kit under test, thereby testing the comprehensive performance of the development kit under test when facing multiple interferences.

[0030] Preferably, the S31 comprises the following steps:

[0031] S311, constructing a test parameter clustering monarch butterfly population; setting the maximum number of iterations of the test parameter clustering monarch butterfly population to And the current number of iterations is , respectively recorded as the maximum iteration number of test parameter clustering and the current iteration number of test parameter clustering;

[0032] S312, randomly selecting a number of test parameter comprehensive data sets from the test parameter comprehensive data set matrix as the initial position matrix of each monarch butterfly in the test parameter clustering monarch butterfly population to obtain a first initial position matrix set;

[0033] S313, calculate each test parameter comprehensive data set in the test parameter comprehensive data set matrix to the test parameter clustering monarch butterfly population k The Euclidean distance between each row of data in the initial position matrix of the monarch butterfly is obtained to obtain the Euclidean distance matrix;

[0034] The test parameters are constructed based on the Euclidean distance matrix to cluster the monarch butterfly population. k The fitness function of a monarch butterfly;

[0035] S314, start iteration, before iteration, set the current iteration number of the test parameter clustering to 1; in the first round of iteration, use the test parameter clustering to cluster the monarch butterfly population. k The fitness function of each monarch butterfly calculates the fitness value of the initial position matrix of each monarch butterfly in the first initial position matrix set to obtain a first fitness value; the maximum fitness value among the first fitness values ​​and the corresponding initial position matrix of the monarch butterfly are respectively used as the first global optimal fitness and the first global optimal position; the initial position matrix of each monarch butterfly in the first initial position matrix set is updated according to the first global optimal fitness and the first global optimal position; after the update is completed, the current iteration number of the test parameter clustering is increased by 1 and the next iteration is entered;

[0036] In each other iteration, the test parameters are used to cluster the monarch butterfly population. k The fitness function of the monarch butterfly calculates the fitness value of the position matrix of each monarch butterfly in the test parameter clustering monarch butterfly population updated in the previous round of iteration to obtain a second fitness value; the maximum fitness value in the second fitness values ​​and the corresponding initial position matrix of the monarch butterfly are respectively used as the second global optimal fitness and the second global optimal position; the position matrix of each monarch butterfly in the test parameter clustering monarch butterfly population updated in the previous round of iteration is updated according to the second global optimal fitness and the second global optimal position; after the update is completed, the current iteration number of the test parameter clustering is increased by 1 and the next iteration is entered;

[0037] S315, when When , stop the iteration and get the first best global best position; otherwise, continue to iterate until until the time; classify the test parameter comprehensive data set matrix according to the first best global best position to obtain a test parameter comprehensive data set classification matrix set;

[0038] The monarch butterfly optimization algorithm integrates the social behavior and individual solving ability of butterfly groups, and has strong global convergence and fast convergence speed; it combines the cooperation and competition between monarch butterflies and other butterflies, and achieves the optimization goal through the interaction between leaders and groups. Therefore, it has good convergence performance and global search capabilities, and is suitable for solving complex optimization problems; it can adapt to different types of optimization problems, including nonlinear, non-convex, multimodal and other complex problems, and has strong adaptability and robustness; based on the above advantages, the monarch butterfly optimization algorithm is used in this scheme to perform multiple iterations on the multiple classification center data in the test parameter comprehensive data set matrix, and the overall discreteness of the test parameter comprehensive data set matrix is ​​used as the fitness function. As the iteration proceeds, the overall discreteness of the test parameter comprehensive data set matrix becomes smaller and smaller, indicating that the classification center data of each classification obtained in the current iteration is more accurate.

[0039] Preferably, S4 comprises the following steps:

[0040] S41. If there is no inconsistency between the comprehensive test result parameter data set in the comprehensive test result parameter data set matrix and the corresponding standard parameter comprehensive data in the standard parameter comprehensive data set matrix, then there is no problem with the performance of the development kit to be tested and the standard of the comprehensive test is met; otherwise, there is a problem with the performance of the development kit to be tested;

[0041] S42, when it is determined in S41 that there is no problem with the performance of the development kit to be tested, putting the development kit to be tested into use; setting a normal use cycle and setting multiple test time periods within the normal use cycle to obtain a test time period set;

[0042] Selecting a number of time periods from the test time period set as real-time test time periods, and using the remaining time periods as future time periods, to obtain a real-time test time period set and a future time period set;

[0043] S43, performing a single performance test and a comprehensive performance test on the development kit to be tested in each real-time test time period in the real-time test time period set according to the test parameter comprehensive data set matrix and the test parameter comprehensive data set classification matrix set, obtaining a single real-time result parameter data matrix set and a comprehensive real-time result parameter data matrix set;

[0044] By setting a normal use cycle and setting multiple test time periods within the normal use cycle, the test time is set for the subsequent single performance test and comprehensive performance test of the development kit to be tested; by performing a single performance test and a comprehensive performance test on the development kit to be tested in each real-time test time period set in the real-time test time period, data support is provided for the subsequent prediction of test result data at future times.

[0045] Preferably, the S5 comprises the following steps:

[0046] S51, constructing a single test data prediction model using the single real-time result parameter data matrix set and predicting the single result parameter data at a future time with the future time period set to obtain a single future result parameter data matrix set;

[0047] S52, using the comprehensive real-time result parameter data matrix set to construct a comprehensive test data prediction model and predicting the comprehensive result parameter data at future moments in conjunction with the future time period set to obtain a comprehensive future result parameter data matrix set;

[0048] S53, if there is no inconsistency between the result parameter data in the single future result parameter data matrix set and the comprehensive future result parameter data matrix set and the corresponding standard parameter comprehensive data in the standard parameter comprehensive data set matrix, then the performance of the development kit to be tested in the normal use cycle meets the requirements; otherwise, the performance of the development kit to be tested in the normal use cycle does not meet the requirements;

[0049] By predicting the single result parameter data and the comprehensive result parameter data at future moments, it is possible to determine whether the performance of the development kit to be tested always meets the requirements at future moments.

[0050] Preferably, the S51 comprises the following steps:

[0051] S511, constructing a first initial BP neural network model and setting a first training data ratio and a first test data ratio; dividing the single real-time result parameter data matrix set according to the first training data ratio and the first test data ratio to obtain a single real-time result parameter training data matrix set, a single real-time result parameter test data matrix set and a single real-time result parameter to-be-predicted data matrix set;

[0052] S512, setting a first training error threshold; inputting the single real-time result parameter training data matrix set into a first initial BP neural network model for training; during the training process, when the training error threshold is less than the first training error threshold, stopping the training to obtain a first trained BP neural network model; otherwise, continuing the training until the training error threshold is less than the first training error threshold;

[0053] S513, set a first test accuracy threshold; input the single real-time result parameter test data matrix set into the first trained BP neural network for testing; after the test is completed, obtain a first test accuracy; when the first test accuracy is greater than or equal to the first test accuracy, use the first trained BP neural network as a single test data prediction model; otherwise, return to S512 to continue training the first trained BP neural network until the first test accuracy is greater than or equal to the first test accuracy;

[0054] S514, inputting a single real-time result parameter to-be-predicted data matrix set into a single test data prediction model for prediction according to the future time period set, to obtain a single future result parameter data matrix set;

[0055] Preferably, the S52 comprises the following steps:

[0056] S521, constructing a second initial BP neural network model and setting a second training data ratio and a second test data ratio; dividing the comprehensive real-time result parameter data matrix set according to the second training data ratio and the second test data ratio to obtain a comprehensive real-time result parameter training data matrix set, a comprehensive real-time result parameter test data matrix set and a comprehensive real-time result parameter to-be-predicted data matrix set;

[0057] S522, setting a second training error threshold; inputting the comprehensive real-time result parameter training data matrix set into the second initial BP neural network model for training; during the training process, when the training error threshold is less than the second training error threshold, stopping the training to obtain a second trained BP neural network model; otherwise, continuing the training until the training error threshold is less than the second training error threshold;

[0058] S523, set a second test accuracy threshold; input the comprehensive real-time result parameter test data matrix set into the second trained BP neural network for testing; after the test is completed, obtain the second test accuracy; when the second test accuracy is greater than or equal to the second test accuracy, use the second trained BP neural network as the comprehensive test data prediction model; otherwise, return to S522 to continue training the second trained BP neural network until the second test accuracy is greater than or equal to the second test accuracy;

[0059] S524, inputting the comprehensive real-time result parameter to-be-predicted data matrix set into the comprehensive test data prediction model for prediction according to the future time period set, to obtain the comprehensive future result parameter data matrix set;

[0060] A development kit performance test system based on data analysis includes a test project type setting module, a project test standard parameter type setting module, a test parameter data collection module, a standard parameter data collection module, an initial single test module, an initial single performance determination module, a clustering module, an initial comprehensive test module, an initial comprehensive performance determination module, a real-time test result data collection module and a final performance determination module.

[0061] The present invention has the following beneficial effects:

[0062] 1. In the present invention, the development kit to be tested is tested from two perspectives: a single performance test and a comprehensive performance test, so that the test results reflect the performance of the development kit to be tested more accurately and comprehensively; first, a single performance test is performed on the development kit to be tested in order to determine whether certain performances of the development kit to be tested meet the test requirements of a certain test sub-item individually; then, by clustering the test parameter comprehensive data set matrix, test sub-items with similar test conditions and no conflict with each other are clustered into one category, and then the development kit to be tested is tested simultaneously using multiple test sub-items clustered into one category, so that the comprehensive anti-interference ability of the development kit to be tested can be detected, making the performance detection more refined, comprehensive and accurate.

[0063] 2. In the present invention, by setting up single performance tests and comprehensive performance tests for the development kit to be tested in multiple time periods, it is possible to determine whether the performance of the development kit to be tested continues to meet the requirements as the normal use time limit increases.

[0064] 3. In the present invention, the monarch butterfly optimization algorithm is used to perform multiple iterative optimizations on multiple classification center data in the test parameter comprehensive data set matrix, and the overall discreteness of the test parameter comprehensive data set matrix is ​​used as the fitness function. As the iteration proceeds, the overall discreteness of the test parameter comprehensive data set matrix becomes smaller and smaller, indicating that the classification center data of each classification obtained in the current iteration is more accurate.

[0065] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0067] Figure 1 The present invention is a flowchart of a development kit performance testing method based on data analysis. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the invention to clearly and completely describe the technical solutions in the embodiments of the invention. Obviously, the described embodiments are only part of the embodiments of the invention, not all of the embodiments. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the invention.

[0069] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0070] Embodiment 1

[0071] See also Figure 1 , this embodiment is a development kit performance testing method based on data analysis, comprising the following steps:

[0072] S1. Set test parameter types for multiple test sub-items and standard parameter types when the test requirements are met, and obtain a test parameter type set matrix and a standard parameter type set matrix;

[0073] The S1 comprises the following steps:

[0074] S11. Set the type of performance test for the development kit to obtain a performance test type set , a 1. a 2. a 3 represent electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test respectively; set multiple test sub-items of each performance test type in the performance test type set to obtain a performance test sub-item matrix ;as follows,

[0075] ;

[0076] in, , , Respectively represent the electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test. i Test sub-projects, , , Represents the total number of test sub-items of electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test respectively;

[0077] Set the test parameter type of each test sub-item in the performance test sub-item matrix to obtain a test parameter type set matrix ;as follows,

[0078] ;

[0079] in, , , Respectively represent the electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test. i A set of test parameter types for each test sub-project; , , , , , Respectively represent the electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test. i of the test subprojects j test parameter types, b 1i , b 2i , b 3i Respectively represent the electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test. i The total number of test parameter types for each test sub-item;

[0080] S12: Set the standard parameter type corresponding to each performance test sub-item matrix in the performance test sub-item matrix when the test requirements are met, and obtain a standard parameter type set matrix ;as follows,

[0081] ;

[0082] in, , , Respectively represent the electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test. i A set of standard parameter types for each test sub-project. , , ; , , Respectively represent the electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test. i of the test subprojects j standard parameter types;

[0083] S2, collecting test parameter data and standard parameter data of corresponding test sub-items according to the test parameter type set matrix and the standard parameter type set matrix to perform a single performance test on the development kit to be tested, and collecting corresponding test result data to make an initial determination on whether the single performance of the development kit to be tested meets the requirements, and obtaining a first determination result;

[0084] The S2 comprises the following steps:

[0085] S21, according to the test parameter type set matrix and the standard parameter type set matrix, obtain the test parameter data and the standard parameter data of each test sub-item of each performance test type, and obtain the test parameter data set matrix And the standard parameter data set matrix ; They are as follows,

[0086] ; ;

[0087] in, , , Respectively represent the electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test. i The test parameter data set corresponding to each test sub-project; , , ; , , Respectively represent the electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test. i The test sub-project corresponds to j Types of test parameter data; , , Respectively represent the electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test. i Standard parameter data sets corresponding to each test sub-item; , , ; , , Respectively represent the electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test. i The test sub-project corresponds to j types of standard parameter data;

[0088] The test parameter data set matrix is ​​combined with the test parameter type set matrix to obtain a test parameter comprehensive data set matrix c1; Combine the standard parameter data set matrix with the standard parameter type set matrix to obtain a standard parameter comprehensive data set matrix c 2; c 1. c 2 are as follows,

[0089] ; ;

[0090] in, c 11i , c 12i , c 13i Respectively represent the electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test. i The test parameter comprehensive data sets corresponding to the test sub-projects are as follows:

[0091] ;

[0092] ;

[0093] ;

[0094] c 21i , c 22i , c 23i Respectively represent the electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test. i The standard parameter comprehensive data sets corresponding to the test sub-items are as follows:

[0095] ;

[0096] ;

[0097] ;

[0098] S22, setting the development kit to be tested; performing a single performance test on the development kit to be tested according to the test parameter comprehensive data set matrix; when all test sub-items are completed, collecting the test result parameter data of the development kit to be tested according to the standard parameter type set matrix, and obtaining a single test result parameter data set matrix ;as follows,

[0099] ;

[0100] in, , , The first step of the electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test of the development kit to be tested is respectively i The test result parameter data sets of the test sub-projects are as follows:

[0101] ;

[0102] ;

[0103] ;

[0104] in, , They represent the first i of the test subprojects j Types of test result parameter data and corresponding parameter types; , They respectively represent the first step of the climate environment adaptability test for the development kit to be tested. i of the test subprojects j Types of test result parameter data and corresponding parameter types; , They represent the first i of the test subprojects j Types of test result parameter data and corresponding parameter types;

[0105] S23, if the result parameter data in the single test result parameter data set matrix is ​​inconsistent with the corresponding standard parameter comprehensive data in the standard parameter comprehensive data set matrix, then there is a problem with the performance of the development kit to be tested; otherwise, the performance of the development kit to be tested meets the standard of the single test;

[0106] S3, performing a clustering operation on the test parameter comprehensive data set matrix according to the first determination result to obtain a test parameter comprehensive data set classification matrix set; performing a comprehensive performance test on the development kit to be tested according to the test parameter comprehensive data set classification matrix set to obtain a comprehensive test result parameter data set matrix;

[0107] The S3 comprises the following steps:

[0108] S31. When the performance of the development kit to be tested meets the standard of a single test, a clustering operation is performed on the test parameter comprehensive data set matrix to obtain a test parameter comprehensive data set classification matrix set. , represents the clustering operation of the test parameter comprehensive data set matrix obtained by iThe test parameter comprehensive data set classification matrix, represents the total number of classification matrices of the test parameter comprehensive data set obtained by performing a clustering operation on the test parameter comprehensive data set matrix; as follows,

[0109] ;

[0110] in, , Respectively Middle j of the test subprojects k types of test parameter data and the types of corresponding test parameters, d ij express Middle j The total number of test parameter data for each test sub-item. express The total number of test sub-items assigned;

[0111] The S31 comprises the following steps:

[0112] S311. Constructing test parameters to cluster monarch butterfly populations , represents the test parameter clustering of the monarch butterfly population i A monarch butterfly, represents the size of the test parameter clustering monarch butterfly population; sets the maximum number of iterations of the test parameter clustering monarch butterfly population to And the current number of iterations is , respectively, are recorded as the maximum iteration number of test parameter clustering and the current iteration number of test parameter clustering; the search space dimension of the test parameter clustering monarch butterfly population is ;

[0113] S312, randomly selecting a number of test parameter comprehensive data sets from the test parameter comprehensive data set matrix as the initial position matrix of each monarch butterfly in the test parameter clustering monarch butterfly population to obtain a first initial position matrix set , Indicates the test parameter clustering monarch butterfly population k The initial position matrix of a monarch butterfly is as follows:

[0114] ;

[0115] in, , Respectively represent the test parameter clustering monarch butterfly population kThe initial position matrix of the monarch butterfly is in the first i The first j types of test parameter data and the corresponding components on the test parameter type dimension;

[0116] S313, calculate each test parameter comprehensive data set in the test parameter comprehensive data set matrix to the test parameter clustering monarch butterfly population k The Euclidean distance between each row of data in the initial position matrix of the monarch butterfly is obtained ;as follows,

[0117] ;

[0118] in, Indicates the test parameter comprehensive data set matrix i The test parameters of the integrated data set were clustered into the test parameters of the monarch butterfly population. k The initial position matrix of the monarch butterfly j Euclidean distance between rows of data;

[0119] According to the Euclidean distance matrix Constructing the test parameters to cluster the monarch butterfly population k Fitness function of a monarch butterfly ;as follows,

[0120] ;

[0121] S314, start iteration, before iteration, set the current iteration number of the test parameter clustering to 1; in the first round of iteration, use the test parameter clustering to cluster the monarch butterfly population. k Fitness function of a monarch butterfly Calculate the fitness value of the initial position matrix of each monarch butterfly in the first initial position matrix set to obtain a first fitness value; use the maximum fitness value among the first fitness values ​​and the corresponding initial position matrix of the monarch butterfly as the first global optimal fitness and the first global optimal position respectively; update the initial position matrix of each monarch butterfly in the first initial position matrix set according to the first global optimal fitness and the first global optimal position; after the update is completed, add 1 to the current iteration number of the test parameter clustering and enter the next round of iteration;

[0122] In each other iteration, the test parameters are used to cluster the monarch butterfly population. k Fitness function of a monarch butterfly Calculate the fitness value of the position matrix of each monarch butterfly in the test parameter clustering monarch butterfly population updated in the previous round of iteration to obtain a second fitness value; use the maximum fitness value of the second fitness values ​​and the corresponding initial position matrix of the monarch butterfly as the second global optimal fitness and the second global optimal position respectively; update the position matrix of each monarch butterfly in the test parameter clustering monarch butterfly population updated in the previous round of iteration according to the second global optimal fitness and the second global optimal position; after the update is completed, add 1 to the current iteration number of the test parameter clustering and enter the next round of iteration;

[0123] S315, when When , stop the iteration and get the first best global best position; otherwise, continue to iterate until until the time; classify the test parameter comprehensive data set matrix according to the first best global best position to obtain a test parameter comprehensive data set classification matrix set;

[0124] S32, simultaneously perform performance tests on the development kit to be tested for each test sub-item in each test parameter comprehensive data set classification matrix set in the test parameter comprehensive data set classification matrix; when all tests are completed, collect the test result parameter data of the development kit to be tested according to the standard parameter type set matrix to obtain a comprehensive test result parameter data set matrix ;as follows,

[0125] ;

[0126] in, , , They represent the first test of the electromagnetic compatibility test, climate environment adaptability test and mechanical protection adaptability test of the development kit under test using the test parameter comprehensive data set classification matrix set. i The test result parameter data sets of the test sub-projects are as follows:

[0127] ;

[0128] ;

[0129] ;

[0130] in, , They represent the first i of the test subprojects j Types of test result parameter data and corresponding parameter types; , They represent the first test of climate environment adaptability test of the development kit under test using the test parameter comprehensive data set classification matrix set. i of the test subprojects j Types of test result parameter data and corresponding parameter types; , They represent the first i of the test subprojects j Types of test result parameter data and corresponding parameter types;

[0131] S4, making an initial judgment on whether the comprehensive performance of the development kit to be tested meets the requirements according to the comprehensive test result parameter data set matrix, and performing a single performance test and a comprehensive performance test on the performance of the development kit to be tested in multiple time periods according to the test parameter data set matrix, to obtain a single real-time result parameter data matrix set and a comprehensive real-time result parameter data matrix set;

[0132] The S4 comprises the following steps:

[0133] S41. If there is no inconsistency between the comprehensive test result parameter data set in the comprehensive test result parameter data set matrix and the corresponding standard parameter comprehensive data in the standard parameter comprehensive data set matrix, then there is no problem with the performance of the development kit to be tested and the standard of the comprehensive test is met; otherwise, there is a problem with the performance of the development kit to be tested;

[0134] S42, when it is determined in S41 that there is no problem with the performance of the development kit to be tested, putting the development kit to be tested into use; setting a normal use cycle and setting multiple test time periods within the normal use cycle to obtain a test time period set , f 1i Indicates the first setting within the normal use cycle. i Test time period, Indicates the total number of test time periods set within the normal use cycle;

[0135] In the test time period set, several time periods are selected as real-time test time periods, and the remaining time periods are used as future time periods to obtain a real-time test time period set. and future time periods , f 2i , f 3i Respectively represent the selected i real-time test time periods and future time periods, Indicates the total number of selected real-time test time periods;

[0136] S43, performing a single performance test and a comprehensive performance test on the development kit to be tested in each real-time test time period in the real-time test time period set according to the test parameter comprehensive data set matrix and the test parameter comprehensive data set classification matrix set, obtaining a single real-time result parameter data matrix set and comprehensive real-time results parameter data matrix set ; , Respectively expressed in i The result parameter data matrix obtained by performing a single performance test and a comprehensive performance test on the development kit under test in a real-time test period is as follows:

[0137] ; ;

[0138] in, , , Respectively expressed in i The first test of the electromagnetic compatibility test, the climate environment adaptability test and the mechanical protection adaptability test in the single performance test of the development kit to be tested is performed within a real-time test period. j The test parameter data set corresponding to each test sub-project; , , , , , Respectively , , Middle k Types of test parameter data;

[0139] , , Respectively expressed in i The first test of the electromagnetic compatibility test, the climate environment adaptability test and the mechanical protection adaptability test in the comprehensive performance test of the development kit to be tested is performed within a real-time test period. j The test parameter data set corresponding to each test sub-project; , , , , , Respectively , , Middle k Types of test parameter data;

[0140] S5. making a final judgment on the single performance and the comprehensive performance of the development kit to be tested according to the single real-time result parameter data matrix set and the comprehensive real-time result parameter data matrix set;

[0141] The S5 comprises the following steps:

[0142] S51, constructing a single test data prediction model using the single real-time result parameter data matrix set and predicting the single result parameter data at a future time with the future time period set to obtain a single future result parameter data matrix set;

[0143] The S51 comprises the following steps:

[0144] S511, constructing a first initial BP neural network model and setting a first training data ratio and a first test data ratio; dividing the single real-time result parameter data matrix set according to the first training data ratio and the first test data ratio to obtain a single real-time result parameter training data matrix set, a single real-time result parameter test data matrix set and a single real-time result parameter to-be-predicted data matrix set;

[0145] S512, setting a first training error threshold; inputting the single real-time result parameter training data matrix set into a first initial BP neural network model for training; during the training process, when the training error threshold is less than the first training error threshold, stopping the training to obtain a first trained BP neural network model; otherwise, continuing the training until the training error threshold is less than the first training error threshold;

[0146] S513, set a first test accuracy threshold; input the single real-time result parameter test data matrix set into the first trained BP neural network for testing; after the test is completed, obtain a first test accuracy; when the first test accuracy is greater than or equal to the first test accuracy, use the first trained BP neural network as a single test data prediction model; otherwise, return to S512 to continue training the first trained BP neural network until the first test accuracy is greater than or equal to the first test accuracy;

[0147] S514, inputting a single real-time result parameter to-be-predicted data matrix set into a single test data prediction model for prediction according to the future time period set, to obtain a single future result parameter data matrix set;

[0148] S52, using the comprehensive real-time result parameter data matrix set to construct a comprehensive test data prediction model and predicting the comprehensive result parameter data at future moments in conjunction with the future time period set to obtain a comprehensive future result parameter data matrix set;

[0149] The S52 comprises the following steps:

[0150] S521, constructing a second initial BP neural network model and setting a second training data ratio and a second test data ratio; dividing the comprehensive real-time result parameter data matrix set according to the second training data ratio and the second test data ratio to obtain a comprehensive real-time result parameter training data matrix set, a comprehensive real-time result parameter test data matrix set and a comprehensive real-time result parameter to-be-predicted data matrix set;

[0151] S522, setting a second training error threshold; inputting the comprehensive real-time result parameter training data matrix set into the second initial BP neural network model for training; during the training process, when the training error threshold is less than the second training error threshold, stopping the training to obtain a second trained BP neural network model; otherwise, continuing the training until the training error threshold is less than the second training error threshold;

[0152] S523, set a second test accuracy threshold; input the comprehensive real-time result parameter test data matrix set into the second trained BP neural network for testing; after the test is completed, obtain the second test accuracy; when the second test accuracy is greater than or equal to the second test accuracy, use the second trained BP neural network as the comprehensive test data prediction model; otherwise, return to S522 to continue training the second trained BP neural network until the second test accuracy is greater than or equal to the second test accuracy;

[0153] S524, inputting the comprehensive real-time result parameter to-be-predicted data matrix set into the comprehensive test data prediction model for prediction according to the future time period set, to obtain the comprehensive future result parameter data matrix set;

[0154] S53. If there is no result parameter data in the single future result parameter data matrix set and the comprehensive future result parameter data matrix set that is inconsistent with the corresponding standard parameter comprehensive data in the standard parameter comprehensive data set matrix, then the performance of the development kit to be tested in the normal use cycle meets the requirements; otherwise, the performance of the development kit to be tested in the normal use cycle does not meet the requirements.

[0155] Embodiment 2

[0156] The present embodiment discloses a development kit performance testing system based on data analysis, the system can implement the method of the above embodiment, including a test project type setting module, a project test standard parameter type setting module, a test parameter data collection module, a standard parameter data collection module, an initial single test module, an initial single performance determination module, a clustering module, an initial comprehensive test module, an initial comprehensive performance determination module, a real-time test result data collection module and a final performance determination module;

[0157] The test item type setting module is used to set the test parameter types of multiple test sub-items to obtain a test parameter type set matrix;

[0158] The project test standard parameter type setting module is used to set the standard parameter types corresponding to multiple test sub-projects when the test requirements are met, and obtain a standard parameter type set matrix;

[0159] The test parameter data collection module is used to collect the test parameter data of the corresponding test sub-items according to the test parameter type set matrix to obtain a test parameter data set matrix;

[0160] The standard parameter data acquisition module is used to acquire the standard parameter data of the corresponding test sub-item when it meets the test requirements according to the standard parameter type set matrix to obtain a standard parameter data set matrix;

[0161] The initial single test module is used to perform a single performance test on the development kit to be tested according to the test parameter data set matrix and the standard parameter type set matrix and collect corresponding test result data to obtain a single test result parameter data set matrix;

[0162] The initial single performance determination module is used to compare the single test result parameter data set matrix with the standard parameter data set matrix, and make an initial determination on whether the single performance of the development kit to be tested meets the requirements according to the comparison result, to obtain a first determination result;

[0163] The clustering module is used to perform a clustering operation on the test parameter comprehensive data set matrix according to the first determination result to obtain a test parameter comprehensive data set classification matrix set;

[0164] The initial comprehensive test module is used to perform performance testing on the development kit to be tested simultaneously according to each test sub-item in each test parameter comprehensive data set classification matrix in the test parameter comprehensive data set classification matrix set, and obtain a comprehensive test result parameter data set matrix;

[0165] The initial comprehensive performance determination module is used to compare the comprehensive test result parameter data set matrix with the standard parameter data set matrix, and make an initial determination on whether the comprehensive performance of the development kit to be tested meets the requirements according to the comparison result, to obtain a second determination result;

[0166] The real-time test result data acquisition module is used to cooperate with the second determination result and perform single performance tests and comprehensive performance tests on the performance of the development kit to be tested in multiple time periods according to the test parameter data set matrix to obtain a single real-time result parameter data matrix set and a comprehensive real-time result parameter data matrix set;

[0167] The final performance determination module is used to compare the single real-time result parameter data matrix set and the comprehensive real-time result parameter data matrix set with the standard parameter data set matrix, and make a final determination on the single performance and comprehensive performance of the development kit to be tested based on the comparison results.

[0168] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0169] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A development kit performance testing method based on data analysis, characterized in that: The following steps are involved: S1. Set test parameter types for multiple test sub-items and standard parameter types when the test requirements are met, and obtain a test parameter type set matrix and a standard parameter type set matrix; S2, collecting test parameter data and standard parameter data of corresponding test sub-items according to the test parameter type set matrix and the standard parameter type set matrix to perform a single performance test on the development kit to be tested, and collecting corresponding test result data to make an initial determination on whether the single performance of the development kit to be tested meets the requirements, and obtaining a first determination result; S3, performing a clustering operation on the test parameter comprehensive data set matrix according to the first determination result to obtain a test parameter comprehensive data set classification matrix set; performing a comprehensive performance test on the development kit to be tested according to the test parameter comprehensive data set classification matrix set to obtain a comprehensive test result parameter data set matrix; S4, making an initial judgment on whether the comprehensive performance of the development kit to be tested meets the requirements according to the comprehensive test result parameter data set matrix, and performing a single performance test and a comprehensive performance test on the performance of the development kit to be tested in multiple time periods according to the test parameter data set matrix, to obtain a single real-time result parameter data matrix set and a comprehensive real-time result parameter data matrix set; S5. Make a final judgment on the single performance and the comprehensive performance of the development kit to be tested based on the single real-time result parameter data matrix set and the comprehensive real-time result parameter data matrix set.

2. The development kit performance testing method based on data analysis according to claim 1, characterized in that: The S1 comprises the following steps: S11, setting the type of performance test to be performed on the development kit to obtain a performance test type set; setting multiple test sub-items for each performance test type in the performance test type set to obtain a performance test sub-item matrix; setting the test parameter type of each test sub-item in the performance test sub-item matrix to obtain a test parameter type set matrix; S12, setting the standard parameter type corresponding to each performance test sub-item matrix in the performance test sub-item matrix when the test requirement is met, and obtaining a standard parameter type set matrix.

3. A development kit performance testing method based on data analysis according to claim 2, characterized in that: The S2 comprises the following steps: S21. According to the test parameter type set matrix and the standard parameter type set matrix, the test parameter data set matrix and the standard parameter data set matrix of each test sub-item of each performance test type are obtained to obtain a test parameter data set matrix and a standard parameter data set matrix; the test parameter data set matrix is ​​combined with the test parameter type set matrix to obtain a test parameter comprehensive data set matrix; the standard parameter data set matrix is ​​combined with the standard parameter type set matrix to obtain a standard parameter comprehensive data set matrix; S22, setting a development kit to be tested; performing a single performance test on the development kit to be tested according to the test parameter comprehensive data set matrix; when all test sub-items are completed, collecting test result parameter data of the development kit to be tested according to the standard parameter type set matrix to obtain a single test result parameter data set matrix; S23. If the result parameter data in the single test result parameter data set matrix is ​​inconsistent with the corresponding standard parameter comprehensive data in the standard parameter comprehensive data set matrix, there is a problem with the performance of the development kit to be tested; otherwise, the performance of the development kit to be tested meets the standard of a single test.

4. The development kit performance testing method based on data analysis according to claim 3 is characterized in that: The S3 comprises the following steps: S31, when the performance of the development kit to be tested meets the standard of a single test, performing a clustering operation on the test parameter comprehensive data set matrix to obtain a test parameter comprehensive data set classification matrix set; S32. Simultaneously perform performance testing on the development kit to be tested for each test sub-item in each test parameter comprehensive data set classification matrix set in the test parameter comprehensive data set classification matrix; when all tests are completed, collect the test result parameter data of the development kit to be tested according to the standard parameter type set matrix to obtain a comprehensive test result parameter data set matrix.

5. A development kit performance testing method based on data analysis according to claim 4, characterized in that: The S31 comprises the following steps: S311, constructing a test parameter clustering monarch butterfly population; setting the maximum number of iterations of the test parameter clustering monarch butterfly population to be and the current number of iterations to be, which are respectively recorded as the maximum number of iterations of the test parameter clustering and the current number of iterations of the test parameter clustering; S312, randomly selecting a number of test parameter comprehensive data sets from the test parameter comprehensive data set matrix as the initial position matrix of each monarch butterfly in the test parameter clustering monarch butterfly population to obtain a first initial position matrix set; S313, calculate each test parameter comprehensive data set in the test parameter comprehensive data set matrix to the test parameter clustering monarch butterfly population k The Euclidean distance between each row of data in the initial position matrix of each monarch butterfly is obtained to obtain a Euclidean distance matrix; a test parameter clustering method is constructed according to the Euclidean distance matrix. k The fitness function of a monarch butterfly; S314, start iteration, before iteration, set the current iteration number of the test parameter clustering to 1; in the first round of iteration, use the test parameter clustering to cluster the monarch butterfly population. k The fitness function of each monarch butterfly calculates the fitness value of the initial position matrix of each monarch butterfly in the first initial position matrix set and updates the initial position matrix of each monarch butterfly in the first initial position matrix set; after the update is completed, the current iteration number of the test parameter clustering is increased by 1 and the next round of iteration is entered; In each other iteration, the test parameters are used to cluster the monarch butterfly population. k The fitness function of each monarch butterfly calculates the fitness value of the position matrix of each monarch butterfly in the test parameter clustering monarch butterfly population updated in the previous iteration process and updates the position matrix of each monarch butterfly in the test parameter clustering monarch butterfly population updated in the previous iteration process; after the update is completed, the current iteration number of the test parameter clustering is increased by 1 and the next iteration is entered; S315, when When , stop the iteration and get the first best global best position; otherwise, continue to iterate until Until the time; classify the test parameter comprehensive data set matrix according to the first best global best position to obtain a test parameter comprehensive data set classification matrix set.

6. A development kit performance testing method based on data analysis according to claim 5, characterized in that: The S4 comprises the following steps: S41. If there is no inconsistency between the comprehensive test result parameter data set in the comprehensive test result parameter data set matrix and the corresponding standard parameter comprehensive data in the standard parameter comprehensive data set matrix, then there is no problem with the performance of the development kit to be tested and the standard of the comprehensive test is met; otherwise, there is a problem with the performance of the development kit to be tested; S42, when it is determined in S41 that there is no problem with the performance of the development kit to be tested, the development kit to be tested is put into use; a normal use cycle is set and multiple test time periods are set within the normal use cycle to obtain a test time period set; a number of time periods are selected from the test time period set as real-time test time periods, and the remaining time periods are used as future time periods to obtain a real-time test time period set and a future time period set; S43. Perform a single performance test and a comprehensive performance test on the development kit to be tested in each real-time test time period in the real-time test time period set according to the test parameter comprehensive data set matrix and the test parameter comprehensive data set classification matrix set, and obtain a single real-time result parameter data matrix set and a comprehensive real-time result parameter data matrix set.

7. A development kit performance testing method based on data analysis according to claim 6, characterized in that: The S5 comprises the following steps: S51, constructing a single test data prediction model using the single real-time result parameter data matrix set and predicting the single result parameter data at a future time with the future time period set to obtain a single future result parameter data matrix set; S52, using the comprehensive real-time result parameter data matrix set to construct a comprehensive test data prediction model and predicting the comprehensive result parameter data at future moments in conjunction with the future time period set to obtain a comprehensive future result parameter data matrix set; S53. If there is no result parameter data in the single future result parameter data matrix set and the comprehensive future result parameter data matrix set that is inconsistent with the corresponding standard parameter comprehensive data in the standard parameter comprehensive data set matrix, then the performance of the development kit to be tested in the normal use cycle meets the requirements; otherwise, the performance of the development kit to be tested in the normal use cycle does not meet the requirements.

8. A development kit performance testing method based on data analysis according to claim 7, characterized in that: The single test data prediction model described in S51 adopts a BP neural network model.

9. A development kit performance testing method based on data analysis according to claim 7, characterized in that: The comprehensive test data prediction model described in S52 adopts a BP neural network model.

10. A system for implementing a development kit performance testing method based on data analysis as described in any one of claims 1 to 9.

Images