Method and apparatus for identification and envelope analysis of ion electric propulsion key quality characteristics

Abstract

The application relates to a method and device for identifying and envelope analyzing key quality characteristics of ion electric propulsion. The method comprises the following steps: collecting quality data of ion electric propulsion quality characteristics; establishing an original characteristic data set of the ion electric propulsion quality characteristics according to the quality data; obtaining an original key quality characteristic set of the ion electric propulsion quality characteristics according to the original characteristic data set and a K-split-Lasso algorithm; constructing a key quality characteristic envelope model of the ion electric propulsion quality characteristics according to the original key quality characteristic set and a current key quality characteristic; and obtaining a cross-validation result of the ion electric propulsion quality characteristics according to the key quality characteristic envelope model and a z-fold cross-validation method. The application solves the problems of strong uncertainty in identifying key quality characteristics of ion electric propulsion, and difficulty in fine envelope analysis and discrimination control in the prior art.

Description

Technical Field

[0001] This invention relates to the field of space electric propulsion technology, and more specifically, to a method and apparatus for identifying and envelope analysis of key mass characteristics of ion electric propulsion. Background Technology

[0002] The ion thruster is the core component of the electric propulsion subsystem, consisting of key components such as the discharge cathode, discharge chamber, grid system, and neutralizer. The basic working principle of the ion thruster is that the main cathode emits primary electrons, which collide with neutral propellant atoms in the discharge chamber under the combined action of electric and magnetic fields. The ionized positive ions are focused, accelerated, and directed out by the grid assembly, generating thrust.

[0003] Currently, high-density launches and large-scale development in fields such as deep space exploration, space infrastructure construction, and internet constellations have become the new normal. As a core power technology, ion electric propulsion is facing a shift from customized to mass production under the aforementioned demand. This places higher demands on the consistency and reliability control of ion electric propulsion quality. Existing technologies urgently need to solve the problem of strong uncertainty in identifying key quality characteristics of ion electric propulsion, as well as the difficulty in refined envelope analysis and discrimination control caused by complex physical mechanisms, numerous coupling factors, and nonlinear stress. Summary of the Invention

[0004] This application provides a method and apparatus for identifying and envelope analyzing key mass characteristics of ion electric propulsion. To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its sole purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0005] In a first aspect, embodiments of this application provide a method for identifying and analyzing the key mass characteristics of ion electric propulsion, the method comprising:

[0006] Collect mass data on the mass characteristics of ion electric propulsion;

[0007] Based on the mass data, establish the original characteristic dataset of the ion electric propulsion mass characteristics;

[0008] Based on the original characteristic dataset and the K-split-Lasso algorithm, the original key mass characteristic set of the ion electric propulsion mass characteristics is obtained;

[0009] Based on the original set of key mass characteristics and the current key mass characteristics, a key mass characteristic envelope model of the ion electric propulsion mass characteristics is constructed.

[0010] Based on the envelope model of the key mass characteristics and the z-fold cross-validation method, the cross-validation results of the ion electric propulsion mass characteristics are obtained.

[0011] Optionally, the step of obtaining the original key mass characteristic set of the ion electric propulsion mass characteristics based on the original characteristic dataset and the K-split-Lasso algorithm includes:

[0012] The original characteristic dataset is divided into several original subsets of the ion electric propulsion mass characteristics;

[0013] Based on several original subsets and the K-split-Lasso algorithm, the original key mass characteristic set of the ion electric propulsion mass characteristics is obtained.

[0014] Optionally, the step of obtaining the original key mass characteristic set of the ion electric propulsion mass characteristics based on several original subsets and the K-split-Lasso algorithm includes:

[0015] Based on the Lasso feature selection algorithm, feature selection is performed on each of the original subsets to obtain several optimal original feature subsets of the ion electric propulsion mass characteristics;

[0016] Based on the optimal original feature subset and the risk priority index weighting method improved by the entropy weight method, the original key mass characteristic set of the ion electric propulsion mass characteristics is determined;

[0017] The Lasso feature selection algorithm and the entropy weight method improved risk priority index weighting method are used as the K-split-Lasso algorithm for the mass characteristics of ion electric propulsion.

[0018] Optionally, the step of constructing a key mass characteristic envelope model of the ion electric propulsion mass characteristics based on the original key mass characteristic set and the current key mass characteristics includes:

[0019] Based on the original key mass characteristic set and the Bootstrap method, several Bootstrap samples of the ion electric propulsion mass characteristics are obtained;

[0020] Based on the current key mass characteristics and the Bootstrap sample, a key mass characteristic envelope model for the ion electric propulsion mass characteristics is constructed.

[0021] Optionally, the step of constructing a key mass characteristic envelope model of the ion electric propulsion mass characteristics based on the current key mass characteristics and the Bootstrap sample includes:

[0022] If the characterization parameters of the current key mass characteristics are deterministic variables, then based on the deterministic variables and the Bootstrap sample, a deterministic variable key mass characteristic envelope model of the ion electric propulsion mass characteristics is constructed.

[0023] Optionally, the step of constructing the key mass characteristic envelope model of the ion electric propulsion mass characteristics based on the current key mass characteristics and the Bootstrap sample further includes:

[0024] If the characterization parameters of the current key quality characteristics are evolutionary variables, then a linear mixed-effects model of the evolutionary variables is established;

[0025] Based on the linear mixed effect model, an envelope model of the key mass characteristics of the evolutionary variables of the ion electric propulsion mass characteristics is constructed.

[0026] The deterministic variable key quality characteristic envelope model and the evolutionary variable key quality characteristic envelope model are used as the key quality characteristic envelope models for the ion electric propulsion quality characteristics.

[0027] Optionally, the quality data includes: performance test data, thermal vacuum test data, mechanical test data, and life test data.

[0028] Secondly, embodiments of this application provide a device for identifying and analyzing the key mass characteristics of ion electric propulsion, the device comprising:

[0029] The acquisition module is used to collect mass data on the mass characteristics of ion electric propulsion.

[0030] The dataset creation module is used to create a raw characteristic dataset of the ion electric propulsion mass characteristics based on the mass data.

[0031] The key mass characteristic acquisition module is used to obtain the original key mass characteristic set of the ion electric propulsion mass characteristics based on the original characteristic dataset and the K-split-Lasso algorithm.

[0032] The model building module is used to construct a key mass characteristic envelope model of the ion electric propulsion mass characteristics based on the original key mass characteristic set and the current key mass characteristics.

[0033] The verification module is used to obtain the cross-validation results of the ion electric propulsion mass characteristics based on the envelope model of the key mass characteristics and the z-fold cross-validation method.

[0034] Thirdly, embodiments of this application provide a computer storage medium storing multiple instructions adapted for loading and execution of the above-described method steps by a processor.

[0035] Fourthly, embodiments of this application provide a terminal that may include: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and executed by the above-described method steps.

[0036] The technical solutions provided in this application embodiment may include the following beneficial effects:

[0037] In this embodiment, a method and apparatus for identifying and analyzing the key mass characteristics of ion electric propulsion are described. First, mass data of the ion electric propulsion mass characteristics are collected. Based on this data, an original characteristic dataset of the ion electric propulsion mass characteristics is established. Then, based on the original characteristic dataset and the K-split-Lasso algorithm, an original set of key mass characteristics of the ion electric propulsion mass characteristics is obtained. Next, based on the original set of key mass characteristics and the current key mass characteristics, a key mass characteristic envelope model of the ion electric propulsion mass characteristics is constructed. Finally, based on the key mass characteristic envelope model and the z-fold cross-validation method, the cross-validation results of the ion electric propulsion mass characteristics are obtained. This method can systematically guide the consistency control of ion electric propulsion quality, greatly reducing the unexpected extension of the development cycle due to imperfect quality control and significantly reducing development costs. It solves the problems in the prior art where the identification of key mass characteristics of ion electric propulsion is highly uncertain, and refined envelope analysis and discrimination control are difficult due to complex physical mechanisms, numerous coupling factors, and nonlinear stress.

[0038] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0039] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0040] Figure 1 This is a flowchart illustrating a method for identifying and analyzing the key mass characteristics of ion electric propulsion according to an embodiment of this application.

[0041] Figure 2 This is another flowchart illustrating a method for identifying and analyzing the key mass characteristics of ion electric propulsion provided in an embodiment of this application;

[0042] Figure 3 This is a schematic diagram of an ion electric thruster for identifying and analyzing key mass characteristics of ion electric propulsion according to an embodiment of this application.

[0043] Figure 4This is a schematic diagram of a device for identifying and analyzing the key mass characteristics of ion electric propulsion, as provided in an embodiment of this application.

[0044] Figure 5 This is a schematic diagram of a terminal provided in an embodiment of this application. Detailed Implementation

[0045] The following description and accompanying drawings fully illustrate specific embodiments of the invention to enable those skilled in the art to practice them.

[0046] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0047] In the following description, when referring to the accompanying drawings, the same numbers in different drawings denote the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of systems and methods consistent with some aspects of the invention as detailed in the appended claims.

[0048] In the description of this invention, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of these terms in this invention based on the specific circumstances. Furthermore, in the description of this invention, unless otherwise stated, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0049] The following will be combined with the appendix Figure 1 -Appendix Figure 3 This paper provides a detailed description of a method for identifying and analyzing the key mass characteristics of ion electric propulsion, as provided in the embodiments of this application.

[0050] Please see Figures 1-3 This is a flowchart illustrating a method for identifying and analyzing the key mass characteristics of ion electric propulsion, as provided in this application embodiment. Figures 1-3 As shown, the method in this application embodiment may include the following steps:

[0051] Figure 1This is a schematic diagram of an ion thruster, which generates thrust through the combined action of components such as a discharge cathode, a discharge chamber, a grid system, and a neutralizer. The discharge cathode is the main cathode, and the grid system includes a screen grid, an accelerating grid, and a decelerating grid. Xenon atoms entering the discharge chamber ionize into electrons and positive ions.

[0052] This application presents a study on the identification and envelope analysis methods for key quality characteristics of ion electric propulsion, providing systematic guidance for consistent quality control in ion electric propulsion. This significantly reduces the unexpected extension of the development cycle due to imperfect quality control and substantially lowers development costs. It solves the problems in existing technologies where the identification of key quality characteristics of ion electric propulsion is highly uncertain, and refined envelope analysis and discrimination control are difficult due to complex physical mechanisms, numerous coupling factors, and nonlinear stresses.

[0053] In the embodiments of this application, S100 and S200 are mainly used for data research and data processing.

[0054] S100 collects mass data on the mass characteristics of ion electric propulsion.

[0055] In this embodiment of the application, existing ion electric propulsion design and development and 1:1 ground test data can be systematically investigated through methods such as on-site test data, archived data surveys and consultations, so as to fully obtain prior data such as performance test data, thermal vacuum test data, mechanical test data and life test data; the quality data includes: performance test data, thermal vacuum test data, mechanical test data and life test data.

[0056] S200, Based on the mass data, establish the original characteristic dataset of the ion electric propulsion mass characteristics.

[0057] In this embodiment of the application, a data dictionary can be constructed using the quality data, the data context can be summarized, the input variables X such as electrical parameters and component status values, and the output variables Y such as thruster performance parameters can be sorted out, and data processing work such as data consistency checks and handling of invalid and missing values ​​can be carried out to establish an original dataset of ion electric propulsion quality characteristics as the data basis for identifying key quality characteristics of ion electric propulsion.

[0058] The original dataset contains a well-organized data context with input variables X and output variables Y. Input variables X include electrical parameters such as grid voltage, anode current, and propellant flow rate; component status values ​​include key component inspection dimensions, grid spacing, and assembly dimensions, where key component inspection dimensions can be grid aperture, and assembly dimensions can be feature point magnetic field dimensions. Output variables Y include thrust, specific impulse, and power, among other thrust performance parameters.

[0059] S300, based on the original characteristic dataset and the K-split-Lasso algorithm, obtain the original key mass characteristic set of the ion electric propulsion mass characteristics. Step S300 includes:

[0060] S310, the original characteristic dataset is divided into several original subsets of the ion electric propulsion mass characteristics.

[0061] In this embodiment, S310 is mainly used for the preliminary sorting and classification of the mass characteristics of ion electric propulsion. Based on the functional attributes of the components such as the original electron emission module, plasma generation module, beam extraction and acceleration module, the mass characteristics of ion electric propulsion are initially sorted, and the original characteristic dataset is divided into several original subsets to reduce the feature dimensionality. This achieves preliminary dimensionality reduction of the ion electric propulsion mass characteristics, reducing the interference of model complexity on the accuracy of the identification results in this embodiment.

[0062] The aforementioned primary electron emission module quality characteristics include ignition time, ignition success rate, main contact voltage, main contact current, and heating wire resistance. The plasma generation module includes anode voltage, anode current, grid current, and characteristic point magnetic field. The beam extraction and acceleration module includes grid spacing, neutrality, acceleration grid voltage, grid voltage, grid current, and acceleration grid interception current.

[0063] For example, the original characteristic dataset may include n ion electric propulsion samples, each ion electric propulsion sample corresponding to m mass characteristics, and the m mass characteristics can be divided into K mass characteristic sets (i.e. K original subsets) according to their functional attributes.

[0064] S320, based on several of the original subsets and the K-split-Lasso algorithm, obtain the original key mass characteristic set of the ion electric propulsion mass characteristics. Step S320 includes:

[0065] Based on the Lasso feature selection algorithm, feature selection is performed on each of the original subsets to obtain several optimal original feature subsets of the ion electric propulsion mass characteristics; according to the optimal original feature subsets and the entropy weight method improved risk priority index weighting method, the original key mass characteristic set of the ion electric propulsion mass characteristics is determined; the Lasso feature selection algorithm and the entropy weight method improved risk priority index weighting method are used as the K-split-Lasso algorithm for the ion electric propulsion mass characteristics.

[0066] In this embodiment, S320 performs Lasso feature selection on each quality feature set (i.e. each original subset) based on the Lasso feature selection algorithm to obtain the optimal original feature subset of each functional module (each optimal original feature subset is a key feature in the corresponding quality feature set). Then, the optimal original feature subset is weighted by the risk priority index weighting method improved by the entropy weight method. Based on the weighting result, the final original key quality feature set is obtained on the basis of determining the priority index weight.

[0067] When performing Lasso feature selection using the Lasso method for each original subset, the parameter tuning constraints are as follows:

[0068]

[0069] Where n represents the sample data size, l represents the feature dimension, and y i Let x represent the response variable value of the i-th variable. ij β represents the observed variable value (independent variable value). j Let represent the regression coefficient of the j-th variable, i≥0, t represent the constraint harmonic parameter, and λ represent the specified function of the Lasso constraint harmonic parameter t.

[0070] In the process of improving the risk priority index weighting using the entropy weight method, we first assume there are p evaluation objects, each with q evaluation indicators. After normalizing the evaluation results, we can obtain a standard evaluation matrix:

[0071]

[0072] Where, r ij This represents the normalized value of the j-th evaluation index for the i-th evaluation object.

[0073] Then calculate the information entropy H for each evaluation indicator. j :

[0074]

[0075] In the formula, k = 1 / lnp.

[0076] Next, calculate the entropy weight for each evaluation indicator:

[0077]

[0078] Finally, the risk priority index RPN was improved using the entropy weight method to obtain the final set of original critical mass characteristics for ion electric propulsion. Specifically, as follows:

[0079] In the embodiments of this application, the criticality of each functional component is characterized by the Risk Priority Index (RPN), which is closely related to three risk factors: occurrence, severity, and detection.

[0080] Each risk factor is weighted using the entropy weighting method, which is...

[0081]

[0082] Where O represents occurrence, S represents severity, and D represents detection. wO Entropy weight representing the degree of occurrence, w S Entropy weights representing severity, w D Entropy weights represent the detection rate.

[0083] This yields the importance ranking of the K optimal original feature subsets, and ultimately the final set of original key quality characteristics.

[0084] S400, based on the original set of key mass characteristics and the current key mass characteristics, construct a key mass characteristic envelope model for the ion electric propulsion mass characteristics. Step S400 includes:

[0085] S410: Based on the original set of critical mass characteristics and the Bootstrap method, several Bootstrap samples of the ion electric propulsion mass characteristics are obtained. Step S410 is virtual augmented sampling of critical mass characteristics based on the Bootstrap method. In this embodiment, the Bootstrap method can be used for random sampling with replacement to obtain multiple Bootstrap samples with critical mass characteristics from the original set of critical mass characteristics. The value of B during the sampling process is determined through multiple simulations, and the convergence criterion is the coverage of the confidence interval.

[0086] For example, in this embodiment of the application, a Bootstrap random sampling can be performed from an original sample (i.e., the original set of critical mass characteristics) S0 of an ion electric propulsion sample that follows a completely uncertain distribution P. Let l be the sampling length, and repeat the above process B times to obtain B Bootstrap samples with a sample size of l.

[0087] S420, based on the current critical mass characteristics and the Bootstrap sample, construct the critical mass characteristic envelope model of the ion electric propulsion mass characteristics. Step S420 includes:

[0088] If the characterization parameters of the current key mass characteristics are deterministic variables, then based on the deterministic variables and the Bootstrap sample, a deterministic variable key mass characteristic envelope model of the ion electric propulsion mass characteristics is constructed.

[0089] In this embodiment, if the characterization parameter of the current key quality characteristic is a variable whose final value can be determined once the ion electric propulsion is developed, then the characterization parameter of the current key quality characteristic is a deterministic variable. The original key quality characteristic set and the Bootstrap sample can be directly combined to construct a deterministic variable key quality characteristic envelope model of the current key quality characteristic. The maximum likelihood estimation method (MLE) is used to take the deterministic variable key quality characteristic envelope model of the current key quality characteristic as the deterministic variable key quality characteristic envelope model of the ion electric propulsion quality characteristic.

[0090] If the characterization parameters of the current key mass characteristics are evolutionary variables, then a linear mixed effect model of the evolutionary variables is established; based on the linear mixed effect model, an envelope model of the key mass characteristics of the evolutionary variables of the ion electric propulsion mass characteristics is constructed.

[0091] In this embodiment, if the characterization parameters of the current critical quality characteristics change during service and exhibit individual differences and linear non-homogeneous variance, then the characterization parameters of the current critical quality characteristics are evolutionary variables. A linear mixed-effect model of this variable with service time and service environment needs to be established. Based on the established linear mixed-effect model, an evolutionary variable envelope model of the critical quality characteristics for the predicted parameters at a specified mission time point is constructed. The service environment includes stress parameters such as grid voltage, accelerating grid voltage, anode current, holding current, and gas supply rate. The specified mission time point can be the midpoint or end of the design life. The predicted parameters can be parameters not included in the currently acquired original design parameters, occurring later than the acquisition time, and requiring curve fitting using a linear mixed-effect model for prediction.

[0092] Because the increase in repeated measurement data in ion electric propulsion leads to heteroscedasticity, and the functional coupling between components leads to autocorrelation, this application embodiment needs to first consider using a specified kernel function to adjust the heteroscedasticity structure when constructing a linear mixed-effect model in combination with the special data field of electric propulsion. Then, it uses a matrix model ARMA(1,1) combining first-order autoregression and moving average models to adjust the autocorrelation. Finally, it uses a combination of Newton's iteration algorithm and EM algorithm to solve the parameters of the linear mixed-effect model, thereby determining the linear mixed-effect model of the ion electric propulsion mass characteristics.

[0093] The structure of a linear mixed-effects model can be:

[0094] u i =v i α+z i d i +ε i

[0095]

[0096] ε i ~N(0, R) i )

[0097] R i =σ 2 V i ×Γ i ×V i

[0098] Among them, u i v represents the value of the i-th key quality characteristic that satisfies the evolutionary trait. i With V i All represent the value of the i-th variable of the influencing factors, α represents the coefficient matrix of the mixed-effects model, and z i This represents the design matrix related to evolution time, where N represents a normal distribution, and d i This indicates that the mean is 0 and the covariance is... The coefficients of the multivariate joint normal distribution, ε i R represents the measurement error of the i-th variable. i s i The covariance matrix, σ 2 Γ represents the sample variance. i This represents the parameter vector of the i-th variable.

[0099] The embodiments of this application construct the linear mixed-effects model based on the individual differences, autocorrelation, and linear non-homogeneous variance characteristics of evolutionary variables, thereby improving the accuracy of the model. This makes the method described in the embodiments of this application more scientifically realize the refined judgment and analysis of the reliability of ion electric propulsion quality under a specified mission duration, and has higher application value.

[0100] The aforementioned envelope model of key quality characteristics for deterministic variables and the envelope model of key quality characteristics for evolutionary variables are used as the envelope model of key quality characteristics.

[0101] S500, based on the key mass characteristic envelope model and z-fold cross-validation method, the cross-validation results of the ion electric propulsion mass characteristics are obtained.

[0102] In this embodiment, the discrimination and analysis of the key quality characteristic envelope model according to the classification of deterministic variables and evolutionary variables are as follows:

[0103] The Z-fold cross-validation method is used to perform hypothesis testing on the parameters of the envelope model of key mass characteristics of evolutionary variables, and the cross-validation results are obtained. Then, the cross-validation results are used to guide the judgment and control of mass consistency and service reliability of ion electric propulsion.

[0104] What is the specific process of hypothesis testing? What are the results of cross-validation? How do the results of cross-validation guide the judgment and control of ion electric propulsion mass consistency and service reliability?

[0105] Z-fold cross-validation is used to assess the generalization ability of the envelope model for deterministic key quality characteristics. For example, the entire sample consisting of the original sample and the bootstrap sample is divided into Z groups. One sub-sample is selected sequentially as the validation set, and the remaining Z-1 sub-samples are used as the training set. Cross-validation is repeated Z times. The distribution parameters and confidence intervals of the envelope model for deterministic key quality characteristics are calculated for each validation iteration, thus obtaining the cross-validation results and providing a basis for optimizing the envelope model.

[0106] In this embodiment, cross-validation yields Z batches of different distribution parameters and their confidence intervals, consisting of the validation set and the training set. The cross-validation result is as follows: the distribution parameters obtained Z times are either stably within or outside the confidence interval. If the distribution parameters are stably within the confidence interval, it indicates that the solution of the distribution parameters is less affected by the samples, and the envelope model of the deterministic variable key quality characteristics is stable. Otherwise, the distribution parameters and their confidence intervals are solved again. Repeating cross-validation Z times allows for the solution of the distribution parameters and their confidence intervals Z times. The fact that the distribution parameters are stably within the confidence interval once or multiple times in the cross-validation results can guide the subsequent optimization of the envelope model of the deterministic variable key quality characteristics.

[0107] In summary, the embodiments of this application perform feature selection on each of the original subsets based on the Lasso feature selection algorithm to obtain the optimal original feature subsets of several ion electric propulsion mass characteristics. Based on the optimal original feature subsets and the risk priority index weighting method improved by the entropy weight method, the original key mass characteristic set (i.e. the final key mass characteristics) of the ion electric propulsion mass characteristics is determined. This avoids the interference of high dimensionality on model accuracy, and the quantization weighting coefficients weaken the impact of empirical errors on the model.

[0108] This application embodiment identifies the original key mass characteristic set of ion electric propulsion mass characteristics based on several original subsets and the K-split-Lasso feature selection algorithm. It then uses the Bootstrap method to virtually augment samples, constructing envelope models for both deterministic and evolutionary key mass characteristics based on the division of deterministic and evolutionary variables. This scientifically guides the judgment and control of consistency and reliability of ion electric propulsion mass, shortening the development cycle and reducing development costs. Furthermore, this application embodiment overcomes the influence of small sample size and unbalanced data features on the confidence of the envelope model by implementing virtual augmented samples through the Bootstrap method. The generalization ability of the envelope model is verified through Z-fold cross-validation, improving the robustness of the model.

[0109] The embodiments of this application fully consider the high-dimensionality, small sample size, and non-equilibrium characteristics of ion electric propulsion mass characteristic data, making them more targeted. Based on these characteristics, appropriate modeling methods are selected, making the modeling results more in line with the actual needs of ion electric propulsion engineering. This can guide the comparative analysis and judgment of the consistency of ion electric propulsion product quality and actual service reliability during the model development process, and has good application value.

[0110] The following are embodiments of the apparatus of the present invention, which can be used to execute embodiments of the method of the present invention. For details not disclosed in the embodiments of the apparatus of the present invention, please refer to the embodiments of the method of the present invention.

[0111] Please see Figure 4 The diagram illustrates a structural schematic of an ion electric propulsion key mass characteristic identification and envelope analysis device according to an exemplary embodiment of the present invention. The device includes: a data acquisition module 10, a dataset establishment module 20, a key mass characteristic acquisition module 30, a model building module 40, and a verification module 50.

[0112] Acquisition module 10 is used to acquire mass data of the mass characteristics of ion electric propulsion;

[0113] The dataset creation module 20 is used to create a raw characteristic dataset of the ion electric propulsion mass characteristics based on the mass data.

[0114] The key mass characteristic acquisition module 30 is used to obtain the original key mass characteristic set of the ion electric propulsion mass characteristics based on the original characteristic dataset and the K-split-Lasso algorithm.

[0115] The model building module 40 is used to construct a key mass characteristic envelope model of the ion electric propulsion mass characteristics based on the original key mass characteristic set and the current key mass characteristics.

[0116] The verification module 50 is used to obtain the cross-validation results of the ion electric propulsion mass characteristics based on the envelope model of the key mass characteristics and the z-fold cross-validation method.

[0117] It should be noted that the ion electric propulsion key mass characteristic identification and envelope analysis device provided in the above embodiments is only illustrated by the division of the above functional modules when executing the ion electric propulsion key mass characteristic identification and envelope analysis method. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the ion electric propulsion key mass characteristic identification and envelope analysis device and the ion electric propulsion key mass characteristic identification and envelope analysis method embodiments provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.

[0118] The device described above identifies and analyzes the key mass characteristics of ion electric propulsion. First, it collects mass data of the ion electric propulsion mass characteristics and establishes an original characteristic dataset based on this data. Then, using the original characteristic dataset and the K-split-Lasso algorithm, it obtains an original set of key mass characteristics. Next, based on the original set of key mass characteristics and the current key mass characteristics, it constructs a key mass characteristic envelope model for the ion electric propulsion mass characteristics. Finally, using the key mass characteristic envelope model and the z-fold cross-validation method, it obtains the cross-validation results of the ion electric propulsion mass characteristics. This device can systematically guide the consistency control of ion electric propulsion quality, greatly reducing the unexpected extension of the development cycle due to imperfect quality control and significantly lowering development costs. It solves the problems in existing technologies where the identification of key mass characteristics of ion electric propulsion is highly uncertain, and refined envelope analysis and discrimination control are difficult due to complex physical mechanisms, numerous coupling factors, and nonlinear stress.

[0119] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0120] The present invention also provides a computer-readable medium having program instructions stored thereon, which, when executed by a processor, implement the methods for identifying and envelope analyzing key mass characteristics of ion electric propulsion provided in the above-described method embodiments.

[0121] The present invention also provides a computer program product containing instructions that, when run on a computer, causes the computer to execute the method for identifying and envelope analysis of key mass characteristics of ion electric propulsion in the above-described method embodiments.

[0122] Please see Figure 5This is a schematic diagram of the structure of a terminal provided in an embodiment of this application. Figure 5 As shown, terminal 1000 may include: at least one processor 1001, at least one network interface 1004, user interface 1003, memory 1005, and at least one communication bus 1002.

[0123] The communication bus 1002 is used to realize the connection and communication between these components.

[0124] The user interface 1003 may include a display screen and a camera. Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0125] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0126] The processor 1001 may include one or more processing cores. The processor 1001 connects to various parts within the electronic device 1000 using various interfaces and lines. It executes various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling data stored in the memory 1005. Optionally, the processor 1001 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 1001 may integrate one or more of the following: a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip without being integrated into the processor 1001.

[0127] The memory 1005 may include random access memory (RAM) or read-only memory. Optionally, the memory 1005 may include a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1005 may also be at least one storage device located remotely from the aforementioned processor 1001. Figure 5 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for identifying and analyzing the key mass characteristics of ion electric propulsion.

[0128] exist Figure 5 In the terminal 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and to acquire user input data; while the processor 1001 can be used to call the application program for the identification and envelope analysis of key mass characteristics of ion electric propulsion stored in the memory 1005, and specifically perform the following operations:

[0129] Collect mass data on the mass characteristics of ion electric propulsion; the mass data includes: performance test data, thermal vacuum test data, mechanical test data, and life test data;

[0130] Based on the mass data, establish the original characteristic dataset of the ion electric propulsion mass characteristics;

[0131] Based on the original characteristic dataset and the K-split-Lasso algorithm, the original key mass characteristic set of the ion electric propulsion mass characteristics is obtained;

[0132] Based on the original set of key mass characteristics and the current key mass characteristics, a key mass characteristic envelope model of the ion electric propulsion mass characteristics is constructed.

[0133] Based on the envelope model of the key mass characteristics and the z-fold cross-validation method, the cross-validation results of the ion electric propulsion mass characteristics are obtained.

[0134] In one embodiment, when processor 1001 executes the process of obtaining the original key mass characteristic set of the ion electric propulsion mass characteristics based on the original characteristic dataset and the K-split-Lasso algorithm, it specifically performs the following operations:

[0135] The original characteristic dataset is divided into several original subsets of the ion electric propulsion mass characteristics;

[0136] Based on the Lasso feature selection algorithm, feature selection is performed on each of the original subsets to obtain several optimal original feature subsets of the ion electric propulsion mass characteristics;

[0137] Based on the optimal original feature subset and the risk priority index weighting method improved by the entropy weight method, the original key mass characteristic set of the ion electric propulsion mass characteristics is determined;

[0138] The Lasso feature selection algorithm and the entropy weight method improved risk priority index weighting method are used as the K-split-Lasso algorithm for the mass characteristics of ion electric propulsion.

[0139] In one embodiment, when processor 1001 executes the step of constructing a key mass characteristic envelope model of the ion electric propulsion mass characteristics based on the original key mass characteristic set and the current key mass characteristics, it specifically performs the following operations:

[0140] Based on the original key mass characteristic set and the Bootstrap method, several Bootstrap samples of the ion electric propulsion mass characteristics are obtained;

[0141] If the characterization parameters of the current key mass characteristics are deterministic variables, then based on the deterministic variables and the Bootstrap sample, construct a deterministic variable key mass characteristic envelope model for the ion electric propulsion mass characteristics.

[0142] If the characterization parameters of the current key quality characteristics are evolutionary variables, then a linear mixed-effects model of the evolutionary variables is established;

[0143] Based on the linear mixed effect model, an envelope model of the key mass characteristics of the evolutionary variables of the ion electric propulsion mass characteristics is constructed.

[0144] The deterministic variable key quality characteristic envelope model and the evolutionary variable key quality characteristic envelope model are used as the key quality characteristic envelope models for the ion electric propulsion quality characteristics.

[0145] The method and apparatus for identifying and analyzing the key mass characteristics of ion electric propulsion are described. First, mass data of the ion electric propulsion mass characteristics are collected. Based on this data, an original characteristic dataset of the ion electric propulsion mass characteristics is established. Then, based on the original characteristic dataset and the K-split-Lasso algorithm, an original set of key mass characteristics of the ion electric propulsion mass characteristics is obtained. Next, based on the original set of key mass characteristics and the current key mass characteristics, a key mass characteristic envelope model of the ion electric propulsion mass characteristics is constructed. Finally, based on the key mass characteristic envelope model and the z-fold cross-validation method, the cross-validation results of the ion electric propulsion mass characteristics are obtained. This method can systematically guide the consistency control of ion electric propulsion quality, greatly reducing the unexpected extension of the development cycle due to imperfect quality control and significantly reducing development costs. It solves the problems in existing technologies where the identification of key mass characteristics of ion electric propulsion is highly uncertain, and refined envelope analysis and discrimination control are difficult due to complex physical mechanisms, numerous coupling factors, and nonlinear stress.

[0146] Those skilled in the art will understand that implementing all or part of the processes in the above embodiments can be accomplished by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory, or random access memory, etc.

[0147] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A method for identifying and envelope analyzing key mass characteristics of ion electric propulsion, characterized in that, Includes the following steps: Collect mass data on the mass characteristics of ion electric propulsion; Based on the mass data, establish the original characteristic dataset of the ion electric propulsion mass characteristics; Based on the original characteristic dataset and the K-split-Lasso algorithm, the original key mass characteristic set of the ion electric propulsion mass characteristics is obtained, including: The original characteristic dataset is divided into several original subsets of the ion electric propulsion mass characteristics; Based on several original subsets and the K-split-Lasso algorithm, the original key mass characteristic set of the ion electric propulsion mass characteristics is obtained; Based on the original set of critical mass characteristics and the current critical mass characteristics, a critical mass characteristic envelope model for the ion electric propulsion mass characteristics is constructed, including: Based on the original key mass characteristic set and the Bootstrap method, several Bootstrap samples of the ion electric propulsion mass characteristics are obtained; Based on the current key mass characteristics and the Bootstrap sample, a key mass characteristic envelope model for the ion electric propulsion mass characteristics is constructed, including: If the characterization parameters of the current key quality characteristics are deterministic variables, that is, the final values ​​of the characterization parameters can be determined once the ion electric propulsion is developed, then based on the deterministic variables and the Bootstrap sample, a key quality characteristic envelope model of the deterministic variables of the ion electric propulsion quality characteristics is constructed. If the characterization parameters of the current key quality characteristics are evolutionary variables, that is, the characterization parameters change with the service process and have individual differences and linear non-homogeneous variance characteristics, then a linear mixed effect model of the evolutionary variable is established. Based on the linear mixed effect model, an envelope model of the key mass characteristics of the evolutionary variables of the ion electric propulsion mass characteristics is constructed. The envelope model of the key quality characteristics of the deterministic variables and the envelope model of the key quality characteristics of the evolutionary variables are used as the envelope model of the key quality characteristics of the ion electric propulsion quality characteristics. Based on the key mass characteristic envelope model and the z-fold cross-validation method, the distribution parameters of the key mass characteristic envelope model and its confidence interval for each validation are obtained, thus yielding the cross-validation results of the ion electric propulsion mass characteristics.

2. The identification and envelope analysis method according to claim 1, characterized in that, The original key mass characteristic set of the ion electric propulsion mass characteristics is obtained based on several original subsets and the K-split-Lasso algorithm, including: Based on the Lasso feature selection algorithm, feature selection is performed on each of the original subsets to obtain several optimal original feature subsets of the ion electric propulsion mass characteristics; Based on the optimal original feature subset and the risk priority index weighting method improved by the entropy weight method, the original key mass characteristic set of the ion electric propulsion mass characteristics is determined; The Lasso feature selection algorithm and the entropy weight method improved risk priority index weighting method are used as the K-split-Lasso algorithm for the mass characteristics of ion electric propulsion.

3. The identification and envelope analysis method according to claim 1, characterized in that, The quality data includes: performance test data, thermal vacuum test data, mechanical test data, and life test data.

4. A device for identifying and analyzing the key mass characteristics of ion electric propulsion, characterized in that, include: The acquisition module is used to collect mass data on the mass characteristics of ion electric propulsion. The dataset creation module is used to create a raw characteristic dataset of the ion electric propulsion mass characteristics based on the mass data. The key mass characteristic acquisition module is used to obtain the original key mass characteristic set of the ion electric propulsion mass characteristics based on the original characteristic dataset and the K-split-Lasso algorithm. The original characteristic dataset is divided into several original subsets of the ion electric propulsion mass characteristics; Based on several original subsets and the K-split-Lasso algorithm, the original key mass characteristic set of the ion electric propulsion mass characteristics is obtained; The model building module is used to construct a key mass characteristic envelope model of the ion electric propulsion mass characteristics based on the original key mass characteristic set and the current key mass characteristics. Based on the original key mass characteristic set and the Bootstrap method, several Bootstrap samples of the ion electric propulsion mass characteristics are obtained; Based on the current key mass characteristics and the Bootstrap sample, a key mass characteristic envelope model for the ion electric propulsion mass characteristics is constructed, including: If the characterization parameters of the current key quality characteristics are deterministic variables, that is, the final values ​​of the characterization parameters can be determined once the ion electric propulsion is developed, then based on the deterministic variables and the Bootstrap sample, a key quality characteristic envelope model of the deterministic variables of the ion electric propulsion quality characteristics is constructed. If the characterization parameters of the current key quality characteristics are evolutionary variables, that is, the characterization parameters change with the service process and have individual differences and linear non-homogeneous variance characteristics, then a linear mixed effect model of the evolutionary variable is established. Based on the linear mixed effect model, an envelope model of the key mass characteristics of the evolutionary variables of the ion electric propulsion mass characteristics is constructed. The envelope model of the key quality characteristics of the deterministic variables and the envelope model of the key quality characteristics of the evolutionary variables are used as the envelope model of the key quality characteristics of the ion electric propulsion quality characteristics. The verification module is used to obtain the distribution parameters of the key mass characteristic envelope model and its confidence interval for each verification based on the key mass characteristic envelope model and the z-fold cross-validation method, so as to obtain the cross-validation results of the ion electric propulsion mass characteristics.

5. A computer storage medium, characterized in that, The computer storage medium stores a plurality of instructions adapted for loading by a processor and executing the method steps as claimed in any one of claims 1-3.

6. A terminal, characterized in that, include: A processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to execute the method steps as claimed in any one of claims 1-3.

Images