Model test method and device based on measured data

Abstract

The invention discloses a model test method and device based on measured data. The method comprises the following steps: acquiring a measured data set; processing the measured data set to obtain a first data set; processing the first data set to obtain a second data set and a third data set; processing the second data set to obtain a fourth data set; and processing the third data set and the fourth data set to obtain model evaluation result information. The platform performance parameter data and the test data are obtained after singular value elimination, time alignment, space alignment and parameter sensitivity analysis processing are carried out on the obtained different platform actual measurement data, the platform performance parameter data and the test data are used for inspection and evaluation of a platform simulation model, and the fidelity of the simulation model is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of model simulation evaluation, and in particular to a model verification method and device based on measured data. Background Art

[0002] The fidelity of equipment simulation models directly impacts the credibility of equipment combat simulation results. Therefore, validating simulation models has become a key research topic. This is achieved by converting field-measured data into data that can be processed by the simulation model and injecting it into the model output. This data is then compared with the measured data to verify the model.

[0003] The verification, validation, and confirmation of simulation systems are fundamental to their reliability and are essential processes for every simulation system during its development phase. Currently, research in this area of simulation system reliability in my country is still in its early stages, lagging behind internationally advanced standards. Currently, the effective use of measured data to verify simulation models, achieve consistency verification between internal and external fields, and improve the fidelity of simulation models remains a pressing technical challenge. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a model verification method and device based on measured data, which effectively utilizes the measured data to verify the simulation model and realize the consistency verification of internal and external fields, thereby improving the realism of the simulation model, realizing the potential value of equipment test data, and deepening the connotation of equipment test identification.

[0005] In order to solve the above technical problems, a first aspect of an embodiment of the present invention discloses a model verification method based on measured data, the method comprising:

[0006] S1, obtain the measured data set;

[0007] S2, processing the measured data set to obtain a first data set;

[0008] S3, processing the first data set to obtain a second data set and a third data set;

[0009] S4, processing the second data set to obtain a fourth data set;

[0010] S5: Process the third data set and the fourth data set to obtain model evaluation result information.

[0011] As an optional implementation manner, in the first aspect of the embodiment of the present invention, processing the measured data set to obtain the first data set includes:

[0012] S21, using a data elimination model to process the measured data set to obtain a first preprocessed data set;

[0013] The data elimination model includes a first data elimination model and a second data elimination model;

[0014] S22, using a data verification model to process the first preprocessed data set to obtain a second preprocessed data set;

[0015] The data verification model includes a first data verification model and a second data verification model;

[0016] S23, performing inspection processing on the second preprocessed data set to obtain a third preprocessed data set;

[0017] S24, performing error processing on the third preprocessed data set to obtain a fourth preprocessed data set;

[0018] S25, performing time alignment processing on the fourth preprocessed data set to obtain a fifth preprocessed data set;

[0019] S26 , performing spatial alignment processing on the fifth pre-processed data set to obtain a first data set.

[0020] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the using of the data elimination model to process the measured data set to obtain the first preprocessed data set includes:

[0021] S211, obtaining a data sample value of the measured data set;

[0022] S212, determining whether the data sample value is greater than a first threshold, and obtaining a first determination result;

[0023] S213: When the first judgment result is yes, execute S224;

[0024] When the first judgment result is no, executing S1;

[0025] S214, determining whether the data sample value is less than a second threshold, and obtaining a second determination result;

[0026] When the second judgment result is yes, the measured data set is processed using the first data elimination model to obtain a first preprocessed data set;

[0027] The first data elimination model expression is:

[0028]

[0029] Wherein, n represents the data sample size of the measured data set; x i represents the i-th measured data in the measured data set; i represents the index of the measured data; represents the average value of the measured data set; S represents the standard deviation of the measured data;

[0030] When the second judgment result is no, the measured data set is processed using the second data elimination model to obtain a first preprocessed data set;

[0031] The second data elimination model expression is:

[0032]

[0033] Wherein, n represents the data sample size of the measured data set; x i represents the i-th measured data in the measured data set; i represents the index of the measured data; represents the mean value of the measured data set; α represents the significance level; k represents the first relationship coefficient; σ represents the standard deviation of the measured data set.

[0034] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the processing of the first preprocessed data set using the data verification model to obtain the second preprocessed data set includes:

[0035] S221, obtaining a data sample value of the first preprocessed data set;

[0036] S222, determining whether the data sample value is greater than a third threshold, and obtaining a third determination result;

[0037] S223, when the third judgment result is yes, execute S234;

[0038] When the third judgment result is no, executing S1;

[0039] S224, determining whether the data sample value is less than a fourth threshold, and obtaining a fourth determination result;

[0040] When the fourth judgment result is yes, the first preprocessed data set is processed using the first data verification model to obtain a second preprocessed data set;

[0041] The first data verification model expression is:

[0042]

[0043] Among them, X (1) ≤X (2) ≤...X(n) represents the sample order statistic of the first preprocessed data set; n represents the data sample size of the first preprocessed data set; a k W represents the significance level of the kth first pre-processed data; a represents the significance level quantile: k represents the first relationship coefficient:

[0044] When the fourth judgment result is no, processing the first preprocessed data set using the second data verification model to obtain a second preprocessed data set;

[0045] The second data verification model expression is:

[0046]

[0047] Among them, X (1) ≤X (2) ≤...X (n) represents the sample order statistic of the first preprocessed data set; n represents the data sample size of the first preprocessed data set; a k represents the significance level of the kth first pre-processed data; D a represents the rejection region of the second data check.

[0048] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the performing inspection processing on the second preprocessed data set to obtain a third preprocessed data set includes:

[0049] S231, performing autocorrelation processing on each element of the second preprocessed data set to obtain a correlated data set;

[0050] The autocorrelation processing expression is:

[0051]

[0052] Among them, x i represents the i-th second pre-processed data of the second pre-processed data set;

[0053] S232, performing estimation processing on each element of the related processing data set to obtain a related data estimation value set;

[0054] The estimation processing expression is:

[0055]

[0056] in, Expressed as the autocorrelation coefficient of white noise; x irepresents the i-th related data in the related data set; N represents the number of elements in the related data set;

[0057] S233: Perform judgment processing on the relevant data estimated value set to obtain a third preprocessed data set.

[0058] As an optional implementation manner, in the first aspect of the embodiments of the present invention, processing the first data set to obtain the second data set and the third data set includes:

[0059] S31, parsing the first data set to obtain a test parameter data set and a test result data set;

[0060] S32, using a sensitivity analysis model, processing the test parameter data set and the test result data set to obtain a second data set and a third data set;

[0061] The sensitivity analysis model expression is:

[0062]

[0063] R (x，y) =[1-e -2I(x，y) ] 1 / 2 ;

[0064] Wherein, U(x, y) represents the first mutual information value; R(x, y) represents the second mutual information value; x represents; y represents; i represents; n represents; X represents any element value of the second data set; Y represents any element value of the third data set; p(x i ) indicates that the random event X is x i The probability of p(y i ) indicates that the random event Y is y i The probability of random events X and Y.

[0065] As an optional implementation manner, in the first aspect of the embodiments of the present invention, processing the second data set to obtain a fourth data set includes:

[0066] S41, processing the second data set to obtain a second optimized data set;

[0067] S42, using a parameter control model, iteratively processing the second optimized data set to obtain a fourth data set;

[0068] The parameter control model expression is:

[0069]

[0070]

[0071] in, Represents the parameter θ at the i-th iteration j The value of Indicates the parameter θ at the i+1th iteration j The value of ; μ represents the learning rate; represents the prediction function; Represents the prediction function with respect to parameter θ j The partial derivative at the i-th iteration; θ i represents the i-th parameter update step; μ represents the learning rate; L(θ) represents the loss function; Represents the loss function The gradient of the parameters at iteration i.

[0072] A second aspect of an embodiment of the present invention discloses a model verification device based on measured data, the device comprising:

[0073] Data acquisition module, used to obtain measured data sets;

[0074] A first processing module, configured to process the measured data set to obtain a first data set;

[0075] a second processing module, configured to process the first data set to obtain a second data set and a third data set;

[0076] a third processing module, configured to process the second data set to obtain a fourth data set;

[0077] The fourth processing module is used to process the third data set and the fourth data set to obtain model evaluation result information.

[0078] A third aspect of the present invention discloses a model verification device based on measured data, the device comprising:

[0079] a memory storing executable program code;

[0080] a processor coupled to the memory;

[0081] The processor calls the executable program code stored in the memory to execute part or all of the steps in the model verification method based on measured data disclosed in the first aspect of the embodiment of the present invention.

[0082] The fourth aspect of the present invention discloses a computer-readable storage medium, which stores computer instructions. When the computer instructions are called, they execute some or all of the steps in the model verification method based on measured data disclosed in the first aspect of the embodiment of the present invention.

[0083] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0084] In an embodiment of the present invention, the obtained measured data from different platforms are subjected to singular value removal, time alignment, spatial alignment, and parameter sensitivity analysis to obtain platform performance parameter data and measured data, which are used for testing and evaluation of the platform simulation model, thereby improving the realism of the simulation model. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0086] Figure 1 This is a schematic diagram of a scenario of a simulation system provided by an embodiment of the present invention;

[0087] Figure 2 This is a flow chart of a model verification method based on measured data disclosed in an embodiment of the present invention;

[0088] Figure 3 Schematic diagram of a model verification device based on measured data disclosed in an embodiment of the present invention;

[0089] Figure 4 This is a schematic diagram of another model verification device based on measured data disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0090] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0091] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different objects, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or device.

[0092] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0093] In this application, the word "exemplary" is used to mean "serving as an example, illustration, or illustration." Any embodiment described in this application as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is given to enable any person skilled in the art to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that one of ordinary skill in the art can recognize that the present application can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present application with unnecessary details. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in this application.

[0094] It should be noted that since the method of the embodiment of the present application is executed in a computer device, the processing objects of each computer device exist in the form of data or information. For example, time is actually time information. It can be understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, the corresponding data exist for the computer device to process. The details will not be repeated here.

[0095] It should be noted that the artificial intelligence related technologies that may be involved in this application are briefly described. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that machines have the functions of perception, reasoning and decision-making.

[0096] Artificial intelligence (AI) technology is a comprehensive discipline encompassing a wide range of fields, encompassing both hardware and software technologies. Foundational AI technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0097] Computer vision (CV) is the science of making machines "see." Specifically, it refers to machine vision, where cameras and computers replace the human eye in identifying and measuring objects, performing further image processing to create images more suitable for human observation or transmission to instrumentation. As a scientific discipline, computer vision studies related theories and technologies, aiming to build artificial intelligence systems capable of extracting information from images or multidimensional data. Computer vision technologies typically include image processing, image recognition, image semantic understanding, image retrieval, optical character recognition (OCR), video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping, and common biometric recognition technologies such as facial recognition and fingerprint recognition.

[0098] Unimodal information is data consisting of only one type, such as text, images, audio, video, or electromagnetic signals. Multimodal information is data that includes at least two types of unimodal information. Furthermore, multimodal information is suitable for complex tasks that require integrating multiple information sources, such as sentiment analysis, robot interaction, and autonomous driving. By integrating information from multiple modalities, higher performance and accuracy can often be achieved on the task.

[0099] A large model refers to an artificial neural network model with a very large number of parameters. In the field of artificial intelligence, a large model generally refers to a model with hundreds of millions to trillions of parameters. Models usually need to be trained on large-scale data sets and require a large amount of computing resources to be optimized and adjusted. Large models are generally used to solve complex tasks such as natural language processing, computer vision, and speech recognition. Generative AI is an AI that can create new content and ideas, including conversations, stories, images, videos, and music. In the embodiment of the present application, the large model can be ChatGPT, BERT, XLNet, Zhipu model, Claude, Moonshot AI model, ChatGLM model, Qianyi Tongwen model, MiniMax model, Spark model, Llama model, 360GPT model, Qwen model, Baichuan model, Skylark model, vivoLM model, Wenxin Yiyan and other large-scale language models, which are not limited in the embodiment of the present application.

[0100] The embodiments of the present application provide a model verification method, system, apparatus, computer equipment, and computer-readable storage medium based on measured data, which are described in detail below.

[0101] See also Figure 1 , Figure 1 This is a schematic diagram of a simulation system provided in an embodiment of the present application. The system may include a computer device 100, in which a model verification device based on measured data is integrated, such as Figure 1 Computer equipment in.

[0102] In the embodiments of the present application, the computer device 100 may be an independent server, or a server network or server cluster composed of servers. For example, the computer device 100 described in the embodiments of the present application includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. A cloud server is composed of a large number of computers or network servers based on cloud computing.

[0103] It is understood that the computer device 100 used in the embodiments of the present application can be a device that includes both receiving and transmitting hardware, that is, a device that has receiving and transmitting hardware capable of performing two-way communication over a two-way communication link. Such a device may include: a cellular or other communication device that has a single-line display, a multi-line display, or a cellular or other communication device without a multi-line display. The specific computer device 100 can be a desktop terminal or a mobile terminal. The computer device 100 can also be a mobile phone, a tablet computer, a laptop computer, etc.

[0104] Those skilled in the art will understand that Figure 1 The application environment shown in the figure is only one application scenario of the present application solution and does not constitute a limitation on the application scenario of the present application solution. Other application environments may also include Figure 1 More or fewer computer devices as shown in Figure 1 Only one computer device is shown in the figure. It can be understood that the system can also include one or more other services, which are not limited here.

[0105] In addition, if Figure 1 As shown, the simulation system may further include a memory 200 for storing processing result data and remote sensing image sample data, such as evaluation result data.

[0106] It should be noted that Figure 1The scenario diagram of the simulation system shown is only an example. The simulation system and scenario described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided by the embodiment of the present application. Ordinary technicians in this field can know that with the evolution of the simulation system and the emergence of new business scenarios, the technical solution provided by the embodiment of the present application is also applicable to similar technical problems.

[0107] This invention discloses a model verification method and device based on measured data. This method, which performs singular value removal, temporal alignment, spatial alignment, and parameter sensitivity analysis on measured data from different platforms, generates platform performance parameter data for verification and evaluation of platform simulation models, thereby improving the fidelity of the simulation models. These methods are described in detail below.

[0108] Example 1

[0109] See also Figure 2 , Figure 2 This is a flow chart of a model verification method based on measured data disclosed in an embodiment of the present invention. Figure 2 The model verification method based on measured data is applied to a simulation system, such as a local server or a cloud server for the simulation system, and the embodiment of the present invention does not limit this. Figure 1 As shown, the model verification method based on measured data may include the following operations:

[0110] S1, obtain the measured data set;

[0111] It should be noted that the measured data set refers to measured data from different platforms, which is used to test the simulation model;

[0112] S2, processing the measured data set to obtain a first data set;

[0113] It should be noted that the measured data set needs to be pre-processed by singular value removal, normality test, independence test, error processing, time alignment and space conversion to obtain a first data set that is consistent with the simulation data format, unit and coordinate system;

[0114] S3, processing the first data set to obtain a second data set and a third data set;

[0115] S4, processing the second data set to obtain a fourth data set;

[0116] S5: Process the third data set and the fourth data set to obtain model evaluation result information.

[0117] It can be seen that by implementing the model verification method based on measured data described in the embodiment of the present invention, the measured data obtained from different platforms are subjected to singular value elimination, time alignment, spatial alignment, and parameter sensitivity analysis to obtain the third data set including platform performance parameter data and the fourth data set of measured results. The platform simulation model is verified and evaluated using the third data set and the fourth data set, thereby improving the realism of the simulation model.

[0118] Optionally, in step S2 above, processing the measured data set to obtain a first data set includes:

[0119] S21, using a data elimination model to process the measured data set to obtain a first preprocessed data set;

[0120] The data elimination model includes a first data elimination model and a second data elimination model;

[0121] S22, using a data verification model to process the first preprocessed data set to obtain a second preprocessed data set;

[0122] The data verification model includes a first data verification model and a second data verification model;

[0123] S23, performing inspection processing on the second preprocessed data set to obtain a third preprocessed data set;

[0124] S24, performing error processing on the third preprocessed data set to obtain a fourth preprocessed data set;

[0125] It should be noted that the error processing refers to the use of outlier processing, missing value processing, standardization and normalization processing, data cleaning processing and data smoothing processing to reduce random errors or eliminate systematic errors and improve the quality and reliability of data, which is not limited in this embodiment;

[0126] S25, performing time alignment processing on the fourth preprocessed data set to obtain a fifth preprocessed data set;

[0127] S26, performing spatial alignment processing on the fifth pre-processed data set to obtain a first data set;

[0128] It should be noted that the spatial alignment processing refers to unifying the fifth pre-processed data set of the multi-frequency device data into a coordinate system with the fusion center platform as the coordinate origin as a reference coordinate system through coordinate transformation. The coordinate systems involved include polar coordinate systems, rectangular coordinate systems, geodetic coordinate systems, and grid coordinate systems, which are not limited in this embodiment.

[0129] It should be noted that the measured data sets originate from different platforms and are different from the simulation data formats, units, coordinate systems, etc. required by the target model. Data preprocessing such as format conversion, coordinate conversion, interpolation and extrapolation, and spatiotemporal consistency solution must be performed.

[0130] It can be seen that by implementing the model verification method based on measured data described in the embodiment of the present invention, the obtained measured data of different platforms are subjected to singular value elimination, verification, inspection, time alignment, and spatial alignment preprocessing to obtain platform performance parameter data, which is used for verification and evaluation of the platform simulation model, thereby improving the realism of the simulation model.

[0131] Optionally, in the above step S21, the use of the data elimination model to process the measured data set to obtain a first preprocessed data set includes:

[0132] S211, obtaining a data sample value of the measured data set;

[0133] S212, determining whether the data sample value is greater than a first threshold, and obtaining a first determination result;

[0134] S213: When the first judgment result is yes, execute S224;

[0135] When the first judgment result is no, executing S1;

[0136] S214, determining whether the data sample value is less than a second threshold, and obtaining a second determination result;

[0137] When the second judgment result is yes, the measured data set is processed using the first data elimination model to obtain a first preprocessed data set;

[0138] The first data elimination model expression is:

[0139]

[0140] Wherein, n represents the data sample size of the measured data set; x i represents the i-th measured data in the measured data set; i represents the index of the measured data; represents the average value of the measured data set; S represents the standard deviation of the measured data;

[0141] It should be noted that when Then x l It is a singular value and is removed;

[0142] When the second judgment result is no, the measured data set is processed using the second data elimination model to obtain a first preprocessed data set;

[0143] The second data elimination model expression is:

[0144]

[0145] Wherein, n represents the data sample size of the measured data set; x i represents the i-th measured data in the measured data set; i represents the index of the measured data; represents the mean value of the measured data set; α represents the significance level; k represents the first relationship coefficient; σ represents the standard deviation of the measured data set;

[0146] It should be noted that, in this embodiment, the significance level α is set to 0.05;

[0147] The first relationship coefficient k is obtained by referring to the Grubbs test critical value table based on α and n;

[0148] It can be seen that the model verification method based on measured data described in the embodiment of the present invention is implemented to eliminate singular values of the measured data obtained from different platforms, providing data support for the verification and evaluation of subsequent platform simulation models, thereby improving the realism of the simulation model.

[0149] Optionally, in step S22, the step of processing the first preprocessed data set using a data verification model to obtain a second preprocessed data set includes:

[0150] S221, obtaining a data sample value of the first preprocessed data set;

[0151] S222, determining whether the data sample value is greater than a third threshold, and obtaining a third determination result;

[0152] S223, when the third judgment result is yes, execute S234;

[0153] When the third judgment result is no, executing S1;

[0154] S224, determining whether the data sample value is less than a fourth threshold, and obtaining a fourth determination result;

[0155] When the fourth judgment result is yes, the first preprocessed data set is processed using the first data verification model to obtain a second preprocessed data set;

[0156] The first data verification model expression is:

[0157]

[0158] Among them, X (1) ≤X (2)≤...X (n) represents the sample order statistic of the first preprocessed data set; n represents the data sample size of the first preprocessed data set; a k W represents the significance level of the kth first pre-processed data; a represents the significance level quantile; k represents the first relationship coefficient;

[0159] It should be noted that the significance level quantile W a Based on a k Obtained by consulting the critical value table of Grubbs test;

[0160] It should be noted that the significance level a of the first pre-processed data is k Obtained by consulting the critical value table of Grubbs test;

[0161] When the fourth judgment result is no, processing the first preprocessed data set using the second data verification model to obtain a second preprocessed data set;

[0162] The second data verification model expression is:

[0163]

[0164] Among them, X (1) ≤X (2) ≤...X (n) represents the sample order statistic of the first preprocessed data set; n represents the data sample size of the first preprocessed data set; a k represents the significance level of the kth first pre-processed data; D a represents the rejection region of the second data check;

[0165] It should be noted that the rejection region D of the second data verification a Obtained by consulting the Grubbs test critical value table from α.

[0166] It can be seen that the model verification method based on measured data described in the embodiment of the present invention is implemented, and the measured data obtained from different platforms are verified on the basis of singular value elimination to obtain a second preprocessed data set after verification, which provides data support for the subsequent verification and evaluation of the platform simulation model and improves the realism of the simulation model.

[0167] Optionally, in step S23, the step of performing verification processing on the second preprocessed data set to obtain a third preprocessed data set includes:

[0168] S231, obtaining the second preprocessed data set;

[0169] S232, performing autocorrelation processing on each element of the second preprocessed data set to obtain a correlated data set;

[0170] The autocorrelation processing expression is:

[0171]

[0172] Among them, x i represents the i-th second pre-processed data of the second pre-processed data set;

[0173] S233, performing estimation processing on each element of the related processing data set to obtain a related data estimation value set;

[0174] The processing expression is:

[0175]

[0176] in, Expressed as the autocorrelation coefficient of white noise; x i represents the i-th related data in the related data set; N represents the number of elements in the related data set;

[0177] S234: Perform judgment processing on the related data estimated value set to obtain a third preprocessed data set.

[0178] It can be seen that the model verification method based on measured data described in the embodiment of the present invention is implemented to verify the measured data obtained from different platforms on the basis of singular value elimination and verification processing, providing data support for the verification and evaluation of subsequent platform simulation models, thereby improving the realism of the simulation model.

[0179] Optionally, in step S25, performing time alignment on the fourth preprocessed dataset to obtain a fifth preprocessed dataset includes:

[0180] S251, performing parsing processing on the fourth preprocessed data set to obtain a radar measurement data set and a preprocessed data set;

[0181] It should be noted that the parsing process means determining, based on the data type, whether any piece of the fourth preprocessed data in the fourth preprocessed data set is radar measurement data; when the fourth preprocessed data is radar measurement data, extracting the fourth preprocessed data to obtain radar measurement data; and removing all of the radar measurement data from the fourth preprocessed data set to obtain a preprocessed data set;

[0182] S252, incrementally sorting the radar measurement data set to obtain a preprocessed radar measurement data set;

[0183] It should be noted that the incremental sorting refers to incremental sorting based on measurement accuracy;

[0184] S253, using a data precision adjustment model to process the preprocessed radar measurement data in the preprocessed radar measurement data set to obtain a radar preprocessed data set;

[0185] Optionally, the data precision adjustment model expression is:

[0186]

[0187] Among them, hn represents the high-precision time index; lm represents the low-precision time index; Indicates the coordinates of x, y, and z at the hnth moment; Indicates the speed in the x, y, and z directions at the hnth moment; T lm represents the lmth interpolation moment; T hn represents the hnth high-precision moment corresponding to the interpolation moment; T lm -T hn Indicates the T lm To T hn The time difference between moments; The target coordinates after hn high-precision alignment to lm low-precision alignment, i.e., radar pre-processing data;

[0188] Optionally, the data precision adjustment model expression is:

[0189]

[0190] Among them, X k-1 Indicates t k-1 Radar measurement data at the moment; X k Indicates t k Radar measurement data at the moment; X k+1 Indicates t k+1 Radar measurement data at the moment; X i Indicates t i Radar measurement data at the moment, i.e. radar pre-processing data;

[0191] S254, fusing the preprocessed dataset and the radar preprocessed dataset to obtain a fifth preprocessed dataset;

[0192] It should be noted that the fusion processing means sorting the pre-processed data set and the radar pre-processed data set in chronological order.

[0193] It can be seen that the model verification method based on measured data described in the embodiment of the present invention is implemented, and time alignment processing is performed on the measured data obtained from different platforms on the basis of singular value processing, verification processing and inspection processing, which provides data support for the inspection and evaluation of subsequent platform simulation models and improves the realism of the simulation model.

[0194] Optionally, in step S3 above, processing the first data set to obtain the second data set and the third data set includes:

[0195] S31, parsing the first data set to obtain a test parameter data set and a test result data set;

[0196] S32, using a sensitivity analysis model, processing the test parameter data set and the test result data set to obtain a second data set and a third data set;

[0197] The sensitivity analysis model expression is:

[0198]

[0199] R(x,y)=[1-e -2I(x，y) ] 1 / 2 ;

[0200] Wherein, U(x, y) represents the first mutual information value; R(x, y) represents the second mutual information value; x represents; y represents; i represents; n represents; X represents any element value of the second data set; Y represents any element value of the third data set; p(x i ) indicates that the random event X is x i The probability of p(y i ) indicates that the random event Y is y i The probability of random events X and Y.

[0201] It can be seen that the model verification method based on measured data described in the embodiment of the present invention is implemented to process the preprocessed first data set to obtain the second data set and the third data set, which provides data support for the subsequent verification and evaluation of the platform simulation model and improves the realism of the simulation model.

[0202] Optionally, in step S4 above, processing the second data set to obtain a fourth data set includes:

[0203] S41, processing the second data set to obtain a second optimized data set;

[0204] S42, using a parameter control model, iteratively processing the second optimized data set to obtain a fourth data set;

[0205] The parameter control model expression is:

[0206]

[0207]

[0208] in, Represents the parameter θ at the i-th iteration j The value of Indicates the parameter θ at the i+1th iteration j The value of ; μ represents the learning rate; represents the prediction function; Represents the prediction function with respect to parameter θ j The partial derivative at the i-th iteration; θ i represents the i-th parameter update step; L(θ) represents the loss function; Represents the loss function About the gradient of the parameters at the i-th iteration;

[0209] It should be noted that, in this embodiment, the number of iterations is set to 200; the learning rate μ is set to 0.05;

[0210] It can be seen that the model verification method based on measured data described in the embodiment of the present invention is implemented to process the second data set to obtain the fourth data set, which provides data support for the subsequent verification and evaluation of the platform simulation model and improves the realism of the simulation model.

[0211] Optionally, in step S5 above, the processing of the third data set and the fourth data set to obtain model evaluation result information includes:

[0212] S51, obtaining a target model;

[0213] It should be noted that the target model represents the user model used for evaluation;

[0214] It should be noted that the model evaluation result information is used to evaluate simulation tests. By constructing a model fidelity evaluation index system and importing the model fidelity evaluation algorithm into the system, the model test data and measured data of radar, communication, radar interference, communication interference and other models are compared and analyzed. The final evaluation results are presented in the form of text, tables, and graphics. The optimized parameter set needs to be re-bound to the simulation system, and simulation experiments are carried out under given combat conditions to confirm the consistency with the measured data again. The credibility and usability of the model are evaluated by comparing the consistency between the simulation model experiment and the field test output under the same input conditions and operating environment. Finally, the final state of the model parameters is confirmed and solidified to obtain a model that is highly close to the actual equipment.

[0215] S52, inputting the third data set into the target model, and obtaining a simulation result data set after being processed by the target model;

[0216] Optionally, use confidence interval methods to evaluate the model, including:

[0217] Step 1: Set the decision criteria for the simulation output results based on the interval [a, b], including the frequency threshold f0 and the confidence level 1-a0 of the parameter estimate;

[0218] Step 2: Calculate the confidence intervals of all simulation output samples [a i , b i ], and satisfies 1-a i ≥1-a0, i=1, 2,...,N;

[0219] Step 3: Count events A = [a i , b i ]∈[a,b] N (A), get the simulation result data set;

[0220] Optionally, a fuzzy comprehensive evaluation method is used to evaluate the model, including:

[0221] 1) Establish the evaluation factor set U = {u1, u2, u3, ..., u n The evaluation factors are various attributes or performances of the object, which are also called parameter indicators or quality indicators in different occasions. They can comprehensively reflect the quality of the object, and thus the object can be evaluated by these factors;

[0222] It should be noted that n is a positive integer, indicating the number of evaluation factors;

[0223] 2) Establish the evaluation result set V = {v1, v2, v3, ..., v m};

[0224] It should be noted that the evaluation result set includes the evaluation results of m evaluation object factors; m is a positive integer representing the number of the evaluation results;

[0225] It should be noted that the evaluation result set is a set of evaluation levels, which represents a set of adaptability levels;

[0226] Exemplarily, the evaluation result indicates excellent, medium, or poor training results;

[0227] 3) Using the fuzzy mapping model, the evaluation result set and the evaluation object factor set are processed to obtain the factor evaluation matrix:

[0228] The fuzzy mapping model expression is:

[0229]

[0230] Where R represents a single factor evaluation matrix; n represents the number of evaluation object factors; m represents the number of evaluation results of the evaluation object factors; i represents the index of the evaluation object factor; j represents the index of the evaluation result; r ij Indicates the adaptability value of the jth evaluation result of the i-th evaluation object factor; u i represents the i-th evaluation object factor; U represents the evaluation object factor set;

[0231] 4) Assign different weights to each of the evaluation object factors to obtain the factor weight set

[0232] Among them, a q represents the weight value of the qth evaluation object factor; p represents the number of factor weights; q represents the index of the factor weight;

[0233] 5) Processing the factor evaluation matrix and the factor weight set using a comprehensive evaluation model to obtain a simulation result data set;

[0234] The comprehensive evaluation model expression is:

[0235]

[0236] Where S=(S1,S2,…,S n ) represents a fuzzy subset of the evaluation result set; represents the fuzzy composition operator;

[0237] S53, performing evaluation processing on the simulation result data set and the fourth data set to obtain model evaluation result information;

[0238] It should be noted that when the probability of an event occurring is greater than the set threshold, the result of the simulation test is recognized; otherwise, the result of the simulation test is not recognized;

[0239] Or S=(S1,S2,…,S n ) is the model evaluation result information;

[0240] It should be noted that the evaluation process refers to comparing the consistency of the simulation result dataset and the fourth dataset to evaluate the credibility and usefulness of the target model;

[0241] It should be noted that at the end of the system performance evaluation task, the model evaluation result information is intuitively displayed in various forms such as text, tables, curves, and graphics.

[0242] It can be seen that by implementing the model verification method based on measured data described in the embodiment of the present invention, the third data set and the fourth data set are processed to obtain model evaluation result information, thereby improving the fidelity of the simulation model.

[0243] Example 2

[0244] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of a model verification device based on measured data disclosed in an embodiment of the present invention. Figure 3 The described device can be applied to a simulation system, such as a local server or a cloud server for a simulation system, and the embodiment of the present invention does not limit this. Figure 3 As shown, the device may include:

[0245] Data acquisition module 101, used to acquire measured data sets;

[0246] A first processing module 102 is configured to process the measured data set to obtain a first data set;

[0247] A second processing module 103 is configured to process the first data set to obtain a second data set and a third data set;

[0248] A third processing module 104 is configured to process the second data set to obtain a fourth data set;

[0249] The fourth processing module 105 is configured to process the third data set and the fourth data set to obtain model evaluation result information.

[0250] Example 3

[0251] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of a model verification device based on measured data disclosed in an embodiment of the present invention. Figure 4 The described device can be applied to a simulation system, such as a local server or a cloud server for a simulation system, and the embodiment of the present invention does not limit this. Figure 4 As shown, the device may include:

[0252] A memory 201 storing executable program code;

[0253] a processor 202 coupled to the memory 201;

[0254] The processor 202 calls the executable program code stored in the memory 201 to execute the steps of the model verification method based on measured data described in the first embodiment.

[0255] Example 4

[0256] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the model verification method based on measured data described in the first embodiment.

[0257] Example 5

[0258] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the model verification method based on measured data described in the first embodiment.

[0259] The device embodiments described above are merely illustrative. Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0260] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by means of hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, the storage medium including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0261] Finally, it should be noted that the model verification method, system and device based on measured data disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A model verification method based on measured data, characterized in that: The method comprises: S1, obtain the measured data set; S2, processing the measured data set to obtain a first data set; S3, processing the first data set to obtain a second data set and a third data set; S4, processing the second data set to obtain a fourth data set; S5: Process the third data set and the fourth data set to obtain model evaluation result information.

2. The model verification method based on measured data according to claim 1, characterized in that: The processing of the measured data set to obtain a first data set includes: S21, using a data elimination model to process the measured data set to obtain a first preprocessed data set; The data elimination model includes a first data elimination model and a second data elimination model; S22, using a data verification model to process the first preprocessed data set to obtain a second preprocessed data set; The data verification model includes a first data verification model and a second data verification model; S23, performing inspection processing on the second preprocessed data set to obtain a third preprocessed data set; S24, performing error processing on the third preprocessed data set to obtain a fourth preprocessed data set; S25, performing time alignment processing on the fourth preprocessed data set to obtain a fifth preprocessed data set; S26 , performing spatial alignment processing on the fifth pre-processed data set to obtain a first data set.

3. The model verification method based on measured data according to claim 1, characterized in that: The method of processing the measured data set by using the data elimination model to obtain a first preprocessed data set includes: S211, obtaining a data sample value of the measured data set; S212, determining whether the data sample value is greater than a first threshold, and obtaining a first determination result; S213: When the first judgment result is yes, execute S224; When the first judgment result is no, executing S1; S214, determining whether the data sample value is less than a second threshold, and obtaining a second determination result; When the second judgment result is yes, the measured data set is processed using the first data elimination model to obtain a first preprocessed data set; The first data elimination model expression is: Wherein, n represents the data sample size of the measured data set; x i represents the i-th measured data in the measured data set; i represents the index of the measured data; represents the average value of the measured data set; S represents the standard deviation of the measured data; When the second judgment result is no, the measured data set is processed using the second data elimination model to obtain a first preprocessed data set; The second data elimination model expression is: Wherein, n represents the data sample size of the measured data set; x i represents the i-th measured data in the measured data set; i represents the index of the measured data; represents the mean value of the measured data set; α represents the significance level; k represents the first relationship coefficient; σ represents the standard deviation of the measured data set.

4. The model verification method based on measured data according to claim 2, characterized in that: The method of processing the first preprocessed data set using a data verification model to obtain a second preprocessed data set includes: S221, obtaining a data sample value of the first preprocessed data set; S222, determining whether the data sample value is greater than a third threshold, and obtaining a third determination result; S223, when the third judgment result is yes, execute S234; When the third judgment result is no, executing S1; S224, determining whether the data sample value is less than a fourth threshold, and obtaining a fourth determination result; When the fourth judgment result is yes, the first preprocessed data set is processed using the first data verification model to obtain a second preprocessed data set; The first data verification model expression is: Among them, X (1) ≤X (2) ≤...X (n) represents the sample order statistic of the first preprocessed data set; n represents the data sample size of the first preprocessed data set; a k W represents the significance level of the kth first pre-processed data; a represents the significance level quantile; k represents the first relationship coefficient; When the fourth judgment result is no, processing the first preprocessed data set using the second data verification model to obtain a second preprocessed data set; The second data verification model expression is: Among them, X (1) ≤X (2) ≤...X (n) represents the sample order statistic of the first preprocessed data set; n represents the data sample size of the first preprocessed data set; a k represents the significance level of the kth first pre-processed data; D a represents the rejection region of the second data check.

5. The model verification method based on measured data according to claim 2, characterized in that: The performing inspection processing on the second preprocessed data set to obtain a third preprocessed data set includes: S231, performing autocorrelation processing on each element of the second preprocessed data set to obtain a correlated data set; The autocorrelation processing expression is: Among them, x i represents the i-th second pre-processed data of the second pre-processed data set; S232, performing estimation processing on each element of the related processing data set to obtain a related data estimation value set; The estimation processing expression is: in, Expressed as the autocorrelation coefficient of white noise; x i represents the i-th related data in the related data set; N represents the number of elements in the related data set; S233: Perform judgment processing on the relevant data estimated value set to obtain a third preprocessed data set.

6. The model verification method based on measured data according to claim 1, characterized in that: The processing of the first data set to obtain the second data set and the third data set includes: S31, parsing the first data set to obtain a test parameter data set and a test result data set; S32, using a sensitivity analysis model, processing the test parameter data set and the test result data set to obtain a second data set and a third data set; The sensitivity analysis model expression is: R(x,y)=[1-e -2I(x，y) ] 1 / 2 ; Wherein, U(x, y) represents the first mutual information value; R(x, y) represents the second mutual information value; x represents; y represents; i represents; n represents; X represents any element value of the second data set; Y represents any element value of the third data set; p(x i ) indicates that the random event X is x i The probability of p(y i ) indicates that the random event Y is y i The probability of random events X and Y.

7. The model verification method based on measured data according to claim 1, characterized in that: The processing of the second data set to obtain a fourth data set includes: S41, processing the second data set to obtain a second optimized data set; S42, using a parameter control model, iteratively processing the second optimized data set to obtain a fourth data set; The parameter control model expression is: in, Represents the parameter θ at the i-th iteration j The value of Indicates the parameter θ at the i+1th iteration j The value of ; μ represents the learning rate; represents the prediction function; Represents the prediction function with respect to parameter θ j The partial derivative at the i-th iteration; θ i represents the i-th parameter update step; μ represents the learning rate; L(θ) represents the loss function; Represents the loss function The gradient of the parameters at iteration i.

8. A model verification device based on measured data, characterized in that: The device comprises: Data acquisition module, used to obtain measured data sets; A first processing module, configured to process the measured data set to obtain a first data set; a second processing module, configured to process the first data set to obtain a second data set and a third data set; a third processing module, configured to process the second data set to obtain a fourth data set; The fourth processing module is used to process the third data set and the fourth data set to obtain model evaluation result information.

9. A model verification device based on measured data, characterized in that: The device comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the model verification method based on measured data according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the model verification method based on measured data according to any one of claims 1 to 7.

Images