Satellite test data analysis method and system

Abstract

This application provides a satellite test data analysis method and system. First, it acquires a raw data set containing multiple types of observation data units collected during the satellite test. Then, it performs feature transformation processing on the raw data set to obtain an analysis feature set containing temporal and spatial features. Next, it calls a pre-trained satellite test state assessment model to perform multi-dimensional state assessment and generate test state assessment results. Based on the assessment results, it determines the anomaly type and impact range information. Finally, based on this information, it generates test optimization instructions containing anomaly location identifiers and feeds them back to the satellite control terminal. This can promptly resolve satellite test problems, improve test success rate and efficiency, and reduce risk costs.

Description

Technical Field

[0001] This application relates to the field of aerospace computer technology, and more specifically, to a satellite test data analysis method and system. Background Technology

[0002] In the aerospace field, satellite testing is a crucial step in ensuring the stable performance and normal functioning of satellites during launch and operation. Satellite testing generates a large amount of observational data from different test modules, covering all subsystems and functional modules of the satellite. Current satellite test data analysis methods primarily rely on manual inspection and analysis of each data point. This approach is not only inefficient but also prone to overlooking critical information due to human error. Furthermore, existing analysis methods often only allow for isolated analysis of data from individual test modules, failing to comprehensively and deeply explore the relationships between different test modules and accurately assess the overall status of the satellite test. When anomalies are detected, it is difficult to quickly and accurately determine the type of anomaly and its impact range, leading to untimely and inaccurate adjustments to test parameters. This increases the risks and costs of satellite testing and may even affect the satellite's final performance and on-orbit operational effectiveness. Summary of the Invention

[0003] In view of this, the purpose of this application is to provide a method and system for analyzing satellite test data.

[0004] In conjunction with the first aspect of this application, a satellite test data analysis method is provided, applied to a satellite test data analysis system, the method comprising:

[0005] Acquire the raw data set collected during the satellite experiment, the raw data set containing multiple types of observation data units generated by different experimental modules within a continuous time period;

[0006] The original dataset is subjected to data feature transformation processing to obtain an analytical feature set for experimental state analysis. The analytical feature set includes temporal features reflecting the operating state of the experimental modules and spatial features reflecting the correlation between modules.

[0007] The pre-trained satellite test state evaluation model is invoked to perform multi-dimensional state evaluation processing on the analysis feature set, generating test state evaluation results of the satellite test process. The test state evaluation results include descriptions of the operational stability of each test module and descriptions of the parameter correlation between modules.

[0008] Based on the test status assessment results, the types of anomalies existing during the satellite test and the corresponding impact range information of the anomaly types are determined. The impact range information includes the action boundary of the anomaly module and the affected area of ​​the associated module.

[0009] Based on the anomaly type and the scope of impact information, a test optimization instruction containing an anomaly location identifier is generated, and the test optimization instruction is fed back to the satellite control terminal to trigger the test parameter adjustment operation.

[0010] In conjunction with the second aspect of this application, a satellite test data analysis system is provided, the satellite test data analysis system including a machine-readable storage medium and a processor, the machine-readable storage medium storing machine-executable instructions, and the satellite test data analysis system implementing the aforementioned satellite test data analysis method when the processor executes the machine-executable instructions.

[0011] In conjunction with a third aspect of this application, a computer-readable storage medium is provided, wherein computer-executable instructions are stored therein, and when the computer-executable instructions are executed, the aforementioned satellite test data analysis method is implemented.

[0012] Combining any of the above aspects, by acquiring the raw data set containing multiple types of observation data units collected during satellite experiments, and performing data feature transformation processing on the raw data set, an analytical feature set containing temporal and spatial features is obtained. This set can reflect the operational status of the experimental modules and the inter-module relationships from both temporal and spatial dimensions. This allows for the invocation of a pre-trained satellite experiment status assessment model to perform multi-dimensional status assessment processing on the analytical feature set, generating experimental status assessment results that include descriptions of the operational stability of each experimental module and descriptions of the parameter correlations between modules. This achieves accurate assessment of the satellite experiment process. Based on the experimental status assessment results, the anomaly type and impact range information are determined, enabling rapid and accurate anomaly location and clarification of its impact range. Based on this information, experimental optimization instructions containing anomaly location identifiers are generated and fed back to the satellite control terminal, triggering experimental parameter adjustment operations. This allows for timely and effective resolution of problems encountered during satellite experiments, improving the success rate and efficiency of satellite experiments, and reducing experimental risks and costs. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained in conjunction with these drawings without creative effort.

[0014] Figure 1 A flowchart illustrating the satellite test data analysis method provided in this application embodiment. Detailed Implementation

[0015] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0016] It should be understood that the terms "system," "unit," and / or "module" used herein are a method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0017] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0018] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0019] Figure 1 The diagram illustrates a flowchart of a satellite test data analysis method provided in this application. It should be understood that in other embodiments, the order of some steps in the satellite test data analysis method of this embodiment can be shared based on actual needs, or some steps can be omitted or maintained. The detailed components of this satellite test data analysis method are as follows:

[0020] Step S110: Obtain the raw data set collected during the satellite experiment, wherein the raw data set contains multiple types of observation data units generated by different experimental modules within a continuous time period.

[0021] During satellite testing, continuous data acquisition is required from multiple test modules to gain a comprehensive understanding of the satellite's operational status. These test modules encompass different functional systems of the satellite, such as the attitude control module, power supply module, and communication transmission module. Each test module is equipped with corresponding sensors and monitoring equipment to collect various relevant physical quantities and operational parameters in real time.

[0022] The attitude control module is primarily responsible for adjusting the satellite's attitude to maintain it in a predetermined orbit and orientation. To monitor its operational status, it collects data such as angular velocity measured by gyroscopes and acceleration measured by accelerometers. The power supply module provides power to the satellite's various systems; related observational data includes the output voltage and current of the solar panels, as well as the charging and discharging status of the batteries. The communication transmission module is responsible for information exchange between the satellite and ground stations or other satellites; its collected data includes signal strength, communication error rate, and data transmission rate.

[0023] These different types of observation data units are continuously collected over consecutive time periods. For example, the angular velocity data from the attitude control module may be recorded every few seconds, forming a continuous time series. Similarly, data from the energy supply module and the communication transmission module are also collected at certain time intervals, thus forming the raw dataset. The data in this raw dataset is diverse and temporal, containing various types of data generated by different experimental modules and reflecting the changes in these data over continuous time periods.

[0024] Step S120: Perform data feature transformation processing on the original data set to obtain an analysis feature set for experimental state analysis. The analysis feature set includes temporal features reflecting the operating state of the experimental modules and spatial features reflecting the correlation between modules.

[0025] Because the data in the original dataset may contain noise, missing values, etc., and its original form may not be directly usable for analyzing the state of satellite experiments, data feature transformation processing is required.

[0026] Step S121: Perform data cleaning on the original data set to remove noise interference information in the data units and fill in missing data fragments to generate a cleaned data set.

[0027] In actual data acquisition, due to factors such as sensor accuracy limitations, external environmental interference, and equipment malfunctions, data units in the raw dataset may be contaminated by noise, and data may also be missing. To improve data quality, raw data cleaning is necessary.

[0028] Step S1211: Identify the noise distribution pattern of the data units in the original data set, and use an adaptive filtering algorithm to suppress noise in the data units according to the noise distribution pattern to obtain the denoised data units.

[0029] Different types of noise have different distribution patterns. Common noise types include Gaussian noise and impulse noise. Gaussian noise is characterized by data errors following a Gaussian distribution, meaning the noise probability density function exhibits a bell-shaped curve. Impulse noise, on the other hand, manifests as sudden, large noise spikes, typically caused by sudden external interference or momentary equipment malfunctions.

[0030] To identify noise distribution patterns, statistical analysis methods can be used. For example, statistical characteristics such as the mean, variance, skewness, and kurtosis of the data can be calculated to determine the type of noise. If the skewness of the data is close to 0 and the kurtosis is close to 3, Gaussian noise may be present; if there are significant outliers in the data, impulse noise may be present.

[0031] Based on the identified noise distribution pattern, a suitable adaptive filtering algorithm is selected for noise suppression. For Gaussian noise, the mean filtering algorithm can be used. The principle of mean filtering is to perform local averaging on the data, that is, to take the average of all data within a certain range around the data point as the new value of that data point. This can effectively smooth the data and reduce the influence of Gaussian noise. For impulse noise, the median filtering algorithm is more suitable. Median filtering sorts the data within a certain range around the data point and takes the median as the new value of that data point, thereby effectively removing the spikes of impulse noise.

[0032] In practical applications, the parameters of the filtering algorithm can be dynamically adjusted according to the specific characteristics of the data. For example, for mean filtering, the range of local averages can be adjusted; for median filtering, the range of sorted data can be adjusted. Through this adaptive approach, data with different noise distribution patterns can be better adapted, improving the noise suppression effect and obtaining denoised data units.

[0033] Step S1212: Detect the missing data position in the denoised data unit, and extract the complete data unit before and after the missing position as the reference data unit.

[0034] Even after denoising, data gaps may still exist in the data units. To detect the location of missing data, the entire data sequence can be traversed to find data points with empty values ​​or values ​​outside the normal range. For example, if a sensor's data should be within a specific interval, but values ​​outside that interval or no data are recorded, then that data point can be considered missing.

[0035] Once the positions of the missing data are determined, it is necessary to extract the complete data units in consecutive time periods before and after the missing positions as reference data units. These reference data units contain the normal data information before and after the missing data and can be used for subsequent interpolation and filling processes. For example, if a data point is missing at time t, then several consecutive data points before and after time t can be extracted as reference data units, and the number of these data points can be determined according to specific circumstances.

[0036] Step S1213: Perform interpolation and filling processing on the missing data positions based on the data change trend of the reference data units to generate a cleaned data set containing a complete data sequence.

[0037] After obtaining the reference data units, interpolation and filling can be performed on the missing data positions according to their data change trends. Common interpolation methods include linear interpolation, polynomial interpolation, etc.

[0038] Linear interpolation is a simple and commonly used interpolation method, which assumes that the data changes linearly between two adjacent data points. If the missing data point is located between two known data points, then the value of the missing data point can be calculated through a linear relationship based on the numerical values and time intervals of these two known data points. For example, given that the numerical values corresponding to times t1 and t2 are y1 and y2 respectively, the time of the missing data point is t, and t1 < t < t2, then the value y of the missing data point can be calculated through the linear interpolation formula:

[0039] y = y1 + (y2 - y1) * (t - t1) / (t2 - t1)

[0040] Polynomial interpolation can handle more complex data change trends. It approximates the data change of the reference data units by fitting a polynomial function and then uses this polynomial function to calculate the values of the missing data points. The order of the polynomial can be selected according to the number of reference data units and the complexity of the data.

[0041] Through interpolation and filling processing, the missing data points are supplemented to complete, thus generating a cleaned data set containing a complete data sequence. The data in this cleaned data set has undergone noise suppression and missing value filling, and the quality has been significantly improved.

[0042] Step S122: Perform feature extraction processing on the cleaned data set, extract the change rule features of each test module in consecutive time periods as time series features, and extract the association pattern features between the data units of different test modules as spatial features.

[0043] Although the cleaned dataset has removed noise and filled in missing values, it is still raw observation data and cannot directly reflect the state of the satellite experiment. Therefore, it is necessary to extract useful features from this data, including temporal features reflecting the operational status of the experimental modules and spatial features reflecting the relationships between the modules.

[0044] Step S1221: For each test module's cleaned data unit, calculate the change in data values ​​between adjacent time periods and statistically analyze the consistency of the change direction within consecutive time periods to generate a change pattern feature that reflects the stability of module operation as the time series feature.

[0045] For each cleaned data unit of the test module, the change in data values ​​between adjacent time periods is first calculated. Taking the angular velocity data of the attitude control module as an example, assuming that the angular velocities collected at times t and t+1 are ω(t) and ω(t+1) respectively, the change between adjacent time periods is Δω(t) = ω(t+1) - ω(t). By calculating the change between each adjacent time period, a sequence of changes can be obtained.

[0046] Next, the consistency of the direction of change over a continuous period is statistically analyzed. The consistency of the direction of change reflects whether the data continuously increases, continuously decreases, or fluctuates over a period of time. This can be achieved by defining a direction indicator. If Δω(t) > 0, it indicates a positive direction of change; if Δω(t) < 0, it indicates a negative direction of change; and if Δω(t) = 0, it indicates that the data has not changed.

[0047] By counting the number of times the direction of change is the same within a continuous period, we can obtain a statistic on the consistency of the direction of change. For example, if the direction of change is consistently positive within a continuous period, it indicates that the data from the experimental module shows a continuous increasing trend during this time, which may indicate that the module's operating status is relatively stable. Conversely, if the direction of change changes frequently, it suggests that the module's operating status may be fluctuating.

[0048] By comprehensively considering the consistency of the amount and direction of change in data values ​​between adjacent time periods, we can generate change patterns that reflect the stability of module operation. These change patterns constitute time-series characteristics. Time-series characteristics can reflect the changes in the operating status of the test module over continuous time periods.

[0049] Step S1222: For any two test modules, after cleaning the data units, analyze the degree of synchronous change and the frequency of asynchronous change of data values ​​within the same time period, and generate the association pattern features that reflect the collaborative relationship between modules as the spatial features.

[0050] To analyze the correlation between different experimental modules, it is necessary to study the cleaned data units of any two experimental modules. The degree of synchronous change of data values ​​within the same time period reflects whether the data changes of the two experimental modules are consistent at the same point in time. The frequency of asynchronous change, on the other hand, indicates the degree of temporal difference in the data changes of the two experimental modules.

[0051] The degree of synchronous change in data values ​​within the same time period can be calculated using the correlation coefficient method. The correlation coefficient is a value between -1 and 1, used to measure the degree of linear correlation between two variables. For the cleaned data units of two experimental modules, let them be x(t) and y(t), where t represents time. The degree of synchronous change can be assessed by calculating their correlation coefficient ρ(x, y). The formula for calculating the correlation coefficient is:

[0052] ρ(x,y)=cov(x,y) / (σ(x)*σ(y))

[0053] Where cov(x, y) is the covariance of x and y, and σ(x) and σ(y) are the standard deviations of x and y, respectively. If the correlation coefficient is close to 1, it indicates that the data of the two experimental modules have a strong synchronous trend within the same time period; if the correlation coefficient is close to -1, it indicates that their trends are opposite; if the correlation coefficient is close to 0, it indicates that there is no obvious synchronous relationship between the data of the two experimental modules.

[0054] The frequency of asynchronous changes can be calculated by statistically analyzing the time difference between the data changes of two experimental modules. For example, record the time points when x(t) and y(t) change significantly, and calculate the difference between these time points. If the time difference is small, it indicates that the data changes of the two experimental modules are relatively synchronous; if the time difference is large, it indicates that their changes are asynchronous.

[0055] By analyzing the degree of synchronous change and the frequency of asynchronous change of data values ​​within the same time period, correlation pattern features reflecting the collaborative relationships between modules can be generated. These features constitute spatial features. Spatial features can reveal the interrelationships between different experimental modules, which is of great significance for understanding the overall operational status of the satellite system.

[0056] Step S123: Perform feature association processing on the temporal features and the spatial features to establish a mapping relationship between features of different experimental modules within the same time period, and generate a set of associated features with temporal-spatial coupling characteristics as the set of analytical features.

[0057] Temporal and spatial characteristics reflect the operational status of satellite test modules and the interrelationships between modules from different perspectives, but they are independent features. To analyze the satellite test status more comprehensively, it is necessary to correlate these features and establish a mapping relationship between them.

[0058] Step S1231: Mark each time period with a time identifier, and perform time dimension alignment processing on the temporal features of each experimental module within the time period with the corresponding spatial features to obtain a feature alignment set with consistent time identifiers.

[0059] Before performing feature association processing, it is necessary to first assign a time identifier to each time period. This time identifier can be a specific timestamp or a relative time sequence number. By assigning a unique time identifier to each time period, the time position corresponding to each data point and feature can be clearly identified.

[0060] Then, the temporal characteristics of each test module within each time period are aligned with their corresponding spatial characteristics in terms of time dimension. For example, for a specific time point t, the temporal characteristics of the attitude control module (such as the change in angular velocity and the consistency of its direction of change) are matched with its spatial characteristics (such as correlation coefficient and asynchronous change frequency) and those of other test modules (such as the energy supply module and the communication transmission module). This ensures that all characteristics correspond to the same time point, thus obtaining a feature alignment set with consistent time signatures.

[0061] Time-dimensional alignment is the foundation of feature association processing, enabling different types of features to be compared and analyzed on the same time scale.

[0062] Step S1232: Perform cross-correlation analysis on the temporal and spatial features in the feature alignment set, and extract the influence weight of temporal feature changes on spatial features and the feedback strength of spatial feature changes on temporal features.

[0063] After obtaining the feature alignment set with consistent time signatures, cross-correlation analysis needs to be performed on the temporal and spatial features. The purpose of cross-correlation analysis is to study the mutual influence between temporal and spatial features, that is, how changes in temporal features affect spatial features, and how changes in spatial features are fed back to temporal features.

[0064] To extract the weights of the influence of temporal feature changes on spatial features, regression analysis can be used. Taking the temporal features of the attitude control module (such as the change in angular velocity) and its spatial features with those of the communication transmission module (such as the correlation coefficient of signal strength) as an example, a regression model is established, with the temporal features as the independent variable and the spatial features as the dependent variable. By fitting a large amount of data, regression coefficients can be obtained, which can then be used as the weights of the influence of temporal feature changes on spatial features.

[0065] Similarly, a similar regression analysis method can be used to extract the feedback strength of spatial feature changes on temporal features. Spatial features are used as independent variables, and temporal features as dependent variables to establish a regression model and calculate the regression coefficients. These regression coefficients reflect the feedback strength of spatial feature changes on temporal features.

[0066] Cross-correlation analysis can reveal the mutual influence between temporal and spatial features, and these relationships are quantified using influence weights and feedback strengths.

[0067] Step S1233: Construct a feature correlation matrix based on the influence weight and feedback intensity, and use the feature combination with significant correlation in the feature correlation matrix as the correlation feature set.

[0068] Based on the weights of the impact of extracted temporal feature changes on spatial features and the feedback strength of spatial feature changes on temporal features, a feature correlation matrix can be constructed. The feature correlation matrix is ​​a two-dimensional matrix where each element represents the degree of correlation between different features.

[0069] The rows and columns of a feature correlation matrix correspond to different features; for example, rows represent time-series features, and columns represent spatial features. The value of each element in the feature correlation matrix is ​​the corresponding influence weight or feedback strength. By analyzing the elements in the feature correlation matrix, it is possible to determine whether the correlation between different features is significant.

[0070] A threshold can be set; when the element values ​​in the feature correlation matrix exceed this threshold, the corresponding features are considered to have a significant correlation. Features with significant correlations are extracted to form a correlation feature set. This correlation feature set has temporal-spatial coupling characteristics, integrating information from both temporal and spatial features, and can more comprehensively reflect the state of the satellite experiment. Therefore, it can be used as an analytical feature set for experiment state analysis.

[0071] Step S130: Call the pre-trained satellite test state evaluation model to perform multi-dimensional state evaluation processing on the analysis feature set, and generate the test state evaluation results of the satellite test process. The test state evaluation results include the operational stability description of each test module and the parameter correlation description between modules.

[0072] The pre-trained satellite test state assessment model is an artificial intelligence model trained on a large amount of data. It can perform multi-dimensional state assessments on the set of analytical features, thereby generating detailed assessment results about the satellite test process.

[0073] Step S131: Input the set of analytical features into the state stability assessment module of the satellite test state assessment model, analyze the fluctuation range and fluctuation frequency of the time series characteristics of each test module, and generate a state stability description that reflects the operational reliability of the module.

[0074] The state stability assessment module focuses on the timing characteristics of each test module, and evaluates the operational reliability of the module by analyzing the fluctuation range and frequency of these characteristics.

[0075] Step S1311: Extract the temporal features of each experimental module in the analysis feature set, and calculate the maximum, minimum and average values ​​of each temporal feature within a preset time window.

[0076] The temporal characteristics of each experimental module are extracted from the feature set. These temporal characteristics reflect the changes in the operational status of the experimental module over a continuous period. To analyze the fluctuations of these characteristics, a preset time window needs to be set. The preset time window can be determined according to specific analytical needs and data characteristics. For example, a shorter time window can be selected to capture short-term fluctuations, while a longer time window can be selected to observe long-term trends.

[0077] Within a preset time window, the maximum, minimum, and average values ​​of each timing characteristic are statistically analyzed. Taking the angular velocity change of the attitude control module as an example, within a specific time window, the maximum and minimum values ​​of all angular velocity changes are identified, and their average value is calculated. These statistics can reflect the approximate range and average level of the test module's operating status within that time window.

[0078] Step S1312: Calculate the difference between the maximum and minimum values ​​as the fluctuation range parameter, and count the number of times the fluctuation range parameter exceeds a preset threshold as the fluctuation frequency parameter.

[0079] Based on the statistically obtained maximum and minimum values, the difference between them is calculated; this difference is the fluctuation range parameter. The fluctuation range parameter reflects the magnitude of change of the timing characteristics within a preset time window. For example, if the maximum value of the angular velocity change of the attitude control module within a time window is 10 and the minimum value is 2, then the fluctuation range parameter is 10 - 2 = 8.

[0080] The preset threshold is a pre-defined standard value used to determine whether the fluctuation range is too large. By counting the number of times the fluctuation range parameter exceeds the preset threshold, the fluctuation frequency parameter can be obtained. The fluctuation frequency parameter reflects the frequency of fluctuations in the time series characteristics over a period of time. If the fluctuation frequency parameter is high, it indicates that the operating state of the test module is unstable and there may be a significant risk of fluctuation.

[0081] Step S1313: Based on the fluctuation range parameter and the fluctuation frequency parameter, construct a module to run a reliability assessment function, and generate a state stability description containing reliability level and fluctuation risk point through the module running the reliability assessment function.

[0082] To comprehensively evaluate the operational reliability of the test module, a module operational reliability evaluation function needs to be constructed based on the fluctuation range parameter and the fluctuation frequency parameter. The evaluation function can be a complex mathematical model that takes the fluctuation range parameter and the fluctuation frequency parameter as input and outputs a numerical value representing the operational reliability of the module.

[0083] For example, the evaluation function can use a weighted summation method, multiplying the fluctuation range parameter and the fluctuation frequency parameter by different weights, and then summing them to obtain a comprehensive evaluation value. The choice of weights can be adjusted according to the actual situation to reflect the different degrees of impact of fluctuation range and fluctuation frequency on the reliability of module operation.

[0084] Based on the output value of the evaluation function, the operational reliability of the module can be classified into different reliability levels, such as high reliability, medium reliability, and low reliability. Furthermore, by analyzing the specific time points when the fluctuation range parameter exceeds a preset threshold, fluctuation risk points can be identified. These fluctuation risk points indicate at which time points or on which data characteristics there is a significant fluctuation risk, which is crucial for timely detection and resolution of problems.

[0085] The state stability description generated by the evaluation function includes the reliability level and fluctuation risk points, which can help operators quickly understand the operational reliability of each test module.

[0086] Step S132: Input the set of analytical features into the parameter correlation evaluation module of the satellite test state evaluation model, analyze the degree of correlation and rate of change of spatial features of different test modules, and generate a parameter correlation description that reflects the effectiveness of module collaboration.

[0087] After the set of analytical features is input into the parameter correlation assessment module of the satellite test state assessment model, the module will conduct an in-depth analysis of the spatial characteristics of different test modules, mainly focusing on the degree of correlation and the rate of correlation change, in order to generate a parameter correlation description that reflects the effectiveness of module collaboration.

[0088] Spatial characteristics reflect the correlation between different experimental modules, and the strength of this correlation is an important indicator of its strength. For any two experimental modules, the spatial characteristics need to be analyzed from multiple perspectives. For example, the spatial characteristics of the communication module and the power module may involve the correlation between communication signal strength and the thrust of the power system. The strength of the correlation can be assessed by calculating the correlation index between the two. Correlation indices can be calculated using various methods, such as the Pearson correlation coefficient. When calculating the Pearson correlation coefficient, the covariance and standard deviation of the two variables can be considered. The covariance reflects whether the trends of the two variables are consistent; a positive covariance indicates that the trends of the two variables are the same, while a negative covariance indicates that the trends are opposite. The standard deviation measures the dispersion of the variables. By comprehensively considering the covariance and standard deviation, a correlation coefficient between -1 and 1 can be obtained. The closer the coefficient is to 1 or -1, the stronger the correlation between the spatial characteristics of the two experimental modules; the closer it is to 0, the weaker the correlation.

[0089] Besides correlation indicators, other factors can be considered to assess the degree of correlation. For example, the synchronicity of the spatial characteristics of two experimental modules over time can be observed. If the spatial characteristics of both modules change simultaneously at most time points, their correlation can be considered high. The causal relationship between spatial characteristics can also be analyzed, i.e., whether a change in the spatial characteristics of one experimental module leads to a corresponding change in the spatial characteristics of the other. A comprehensive analysis of these factors can yield a complete assessment of the degree of correlation.

[0090] The rate of change of correlation reflects how the correlation between the spatial features of different test modules changes over time. When analyzing the rate of change of correlation, it is first necessary to record the degree of correlation at different time points. The degree of correlation between the spatial features of every two test modules can be calculated and recorded at regular time intervals. For example, the degree of correlation between the spatial features of the communication module and the power module can be calculated every hour.

[0091] Then, by comparing the degree of correlation between adjacent time points, the change in the degree of correlation can be obtained. For example, if the degree of correlation between the spatial characteristics of the communication module and the power module is calculated as C1 and C2 at times t1 and t2 respectively, then the change in the degree of correlation is C2-C1. Dividing this change by the time interval (t2-t1) yields the rate of correlation change. The rate of correlation change reflects whether the collaborative relationship between different test modules is stable. If the rate of correlation change is large, it indicates that the correlation between the test modules has changed significantly in a short period of time, which may indicate that the collaborative work between the modules has become unstable; if the rate of correlation change is small, it indicates that the correlation is relatively stable.

[0092] When analyzing the rate of change of correlations, the trend of change should also be considered. For example, is the rate of change of correlation continuously increasing, continuously decreasing, or fluctuating? If the rate of change of correlations is continuously increasing, it may indicate that the synergy between modules is gradually deteriorating; if it is continuously decreasing, it may indicate that the synergy is gradually improving. By analyzing the rate of change of correlations and its trend, a deeper understanding of the collaborative work between different experimental modules can be obtained.

[0093] Based on the analysis of the correlation strength and rate of change of spatial features of different experimental modules, a parameter correlation description reflecting the effectiveness of module collaboration is generated. The parameter correlation description comprehensively considers both the correlation strength and the rate of change of correlation. For example, if the spatial features of two experimental modules are highly correlated and the rate of change of correlation is small, it indicates that the collaboration between the two experimental modules is relatively effective, which can be reflected in the parameter correlation description as "close and stable correlation, high collaborative effectiveness".

[0094] If the correlation is weak and the rate of change in the correlation is high, it indicates a potential problem with the collaboration between modules. In the parameter correlation description, this can be reflected as "weak and unstable correlation, low collaborative effectiveness." Furthermore, the parameter correlation description can specify the correlation between which experimental modules, and at which time points or time periods significant changes in the correlation occurred.

[0095] Step S133: Perform a comprehensive evaluation of the state stability description and the parameter correlation description to generate an experimental state evaluation result that includes module-level evaluation conclusions and system-level evaluation conclusions.

[0096] After obtaining the state stability description and parameter correlation description, these two descriptions need to be comprehensively evaluated to generate a more comprehensive experimental state assessment result. The experimental state assessment result includes module-level assessment conclusions and system-level assessment conclusions.

[0097] State stability descriptions reflect the operational reliability of each test module, while parameter correlation descriptions reflect the effectiveness of collaboration between different test modules. In comprehensive evaluation, both aspects need to be considered. For example, if a test module's state stability description shows high operational reliability, but its parameter correlation descriptions with other test modules show low collaborative effectiveness, then the impact of this situation on the overall satellite test status needs to be considered in the comprehensive evaluation.

[0098] A weighted approach can be used to synthesize the state stability description and the parameter correlation description. Different weights are assigned to the state stability description and the parameter correlation description, with the weight determined by their importance to the satellite test state. For example, if the operational reliability of a module is considered more important to the overall satellite test state, a higher weight can be assigned to the state stability description; if the collaborative work between modules is considered to have a greater impact on the satellite test state, a higher weight can be assigned to the parameter correlation description. Then, a comprehensive evaluation value is obtained by calculating based on the respective evaluation results and weights.

[0099] Based on the comprehensive evaluation results, module-level evaluation conclusions are generated. These conclusions provide specific assessments for each test module. For each module, the evaluation considers both its state stability description and its parameter correlation descriptions with other modules. For example, for the communication module, the evaluation conclusions might indicate its operational reliability, its effectiveness in coordinating with other modules such as the power module and detection module, and whether there are any potential problems affecting the overall satellite test status. Module-level evaluation conclusions can provide a basis for adjusting and optimizing individual test modules.

[0100] When generating module-level evaluation conclusions, test modules can also be categorized. For example, test modules with high operational reliability and high collaborative effectiveness can be grouped into one category, while test modules with low operational reliability or low collaborative effectiveness can be grouped into another. This categorization can more clearly demonstrate the status of each test module, facilitating subsequent management and processing.

[0101] In addition to module-level evaluation conclusions, system-level evaluation conclusions also need to be generated. System-level evaluation conclusions take the perspective of the entire satellite test system, comprehensively considering the state stability of all test modules and the parameter correlations between modules. The system-level evaluation conclusions will provide an overall assessment of the operational status of the entire satellite test system, such as whether the system is stable and whether there are any potential risks.

[0102] When generating system-level evaluation conclusions, the interactions between various test modules should be considered. If the coordination effectiveness between multiple test modules is low, it may significantly impact the performance of the entire satellite test system; this situation should be explicitly stated in the system-level evaluation conclusions. Simultaneously, the system-level evaluation conclusions can also propose overall improvement suggestions, such as whether adjustments to certain test modules are needed or whether the coordination relationships between modules need optimization. By combining module-level and system-level evaluation conclusions, a comprehensive and in-depth understanding of the satellite test status can be achieved.

[0103] Step S140: Based on the test status assessment results, determine the types of anomalies that exist during the satellite test and the impact range information corresponding to the anomaly types. The impact range information includes the action boundary of the anomaly module and the affected area of ​​the associated module.

[0104] Step S141: Analyze the module-level evaluation conclusions and system-level evaluation conclusions in the test state evaluation results, and identify abnormal modules that deviate from the normal state in the evaluation conclusions.

[0105] The module-level and system-level evaluation conclusions in the test state assessment results contain a wealth of information. When interpreting these conclusions, the focus should be on identifying anomalous modules that deviate from normal conditions. For module-level evaluation conclusions, the operational reliability of each test module and its effectiveness in coordinating with other modules can be described in detail. If a test module has low operational reliability (e.g., the state stability description shows many points of fluctuation risk) or poor effectiveness in coordinating with other modules (e.g., the parameter correlation description shows weak and unstable correlation), then this test module can be considered an anomalous module.

[0106] System-level evaluations provide a holistic assessment of the satellite test system. If a system-level evaluation indicates that problems with certain test modules significantly impact the overall system performance, these modules may be considered anomalous. A comprehensive analysis of module-level and system-level evaluations allows for the accurate identification of anomalous modules.

[0107] Step S142: Based on the state stability description and parameter correlation description of the abnormal module, determine the abnormal manifestation form and match the preset abnormal type classification rules to generate the abnormal type.

[0108] After identifying the abnormal module, it is necessary to determine the abnormal behavior based on its state stability description and parameter correlation description. Abnormal behavior can include module instability, poor coordination with other modules, etc. For example, if the state stability description of the abnormal module shows high fluctuation range and frequency parameters, it indicates that the module is unstable and may exhibit frequent fluctuations as an abnormal behavior. If the parameter correlation description shows low correlation with other modules and a large rate of correlation change, it indicates poor coordination with other modules and may exhibit coordination disorder as an abnormal behavior.

[0109] The preset exception type classification rules are summarized based on a large amount of historical data and experience. These rules map different exception manifestations to different exception types. For example, an exception manifestation of module instability may correspond to the "operational failure" exception type; an exception manifestation of poor module coordination may correspond to the "coordination failure" exception type. By matching the exception manifestation with the preset exception type classification rules, exception types can be generated.

[0110] Step S143: Extract information about other modules associated with the spatial features of the abnormal module, analyze the trend of parameter correlation description of the associated modules, determine the degree of influence and scope of influence of the abnormal module on the associated modules, and generate the influence scope information.

[0111] The spatial characteristics of an abnormal module contain information about its relationships with other modules. By extracting this information, other modules associated with the abnormal module can be identified. Then, the changing trends of the parameter correlation descriptions of these associated modules are analyzed. For example, the degree of correlation and the rate of change of the correlation between the associated modules and the abnormal module can be observed before and after the abnormal module experiences a problem.

[0112] If the correlation between the associated module and the abnormal module decreases significantly after the abnormal module encounters a problem, and the rate of change in the correlation increases, it indicates that the abnormal module has a significant impact on the associated module. By analyzing the changing trends of the parameter correlation descriptions of the associated modules, the degree of influence of the abnormal module on the associated module can be determined.

[0113] The influence scope boundary refers to the area affected by the abnormal module. It can be determined based on changes in the parameter correlation descriptions of related modules. For example, if the parameter correlation description of one related module changes significantly after the abnormal module malfunctions, while the parameter correlation description of another related module remains unaffected, then the area containing the affected related module can be defined as the influence scope boundary. By determining the degree of impact and the influence scope boundary, influence scope information is generated. This information includes the operational boundary of the abnormal module and the affected area of ​​related modules.

[0114] Step S150: Generate a test optimization instruction containing an anomaly location identifier based on the anomaly type and the scope of influence information, and feed the test optimization instruction back to the satellite control terminal to trigger the test parameter adjustment operation.

[0115] After determining the anomaly type and its affected area, test optimization instructions need to be generated to address problems encountered during satellite testing. These instructions include anomaly location markers to accurately pinpoint the location and extent of the problem.

[0116] Step S151: Based on the anomaly type, match the preset optimization strategy library and extract the parameter adjustment direction and adjustment range suggestions corresponding to the anomaly type.

[0117] The pre-defined optimization strategy library is built upon different anomaly types and extensive historical experience. When generating test optimization instructions, the appropriate optimization strategy needs to be matched from the library based on the anomaly type. For example, if the anomaly type is "operational failure," the optimization strategy library may contain suggestions on the direction and magnitude of parameter adjustments for operational failures, such as adjusting the operating parameters of the test module to improve operational stability.

[0118] For different anomaly types, the parameter adjustment direction and magnitude suggestions in the optimization strategy library will differ. The parameter adjustment direction can include increasing or decreasing the values ​​of certain parameters, while the magnitude suggestion will specify the degree of adjustment. By matching the optimization strategy library, you can accurately obtain the parameter adjustment direction and magnitude suggestions corresponding to the anomaly type.

[0119] Step S152: Based on the influence range boundary in the influence range information, extract the identification information of the abnormal module and its associated modules as the abnormal location identifier.

[0120] The impact scope information clearly defines the range of the abnormal module and its associated modules. Based on this range, the identification information of the abnormal module and its associated modules, such as the module number and name, is extracted as anomaly location markers. These anomaly location markers can accurately pinpoint the location of the problem, facilitating subsequent adjustments to experimental parameters.

[0121] Step S153: Perform information fusion processing on the parameter adjustment direction and adjustment range suggestions and the abnormal positioning identifier to generate a test optimization instruction containing module identifier, adjustment direction and adjustment range.

[0122] The parameter adjustment direction and magnitude suggestions obtained from the optimization strategy library are fused with anomaly location markers. This information fusion process integrates all the information to form a complete experimental optimization instruction. The experimental optimization instruction clearly indicates which experimental modules require parameter adjustments, the direction of the adjustments, and the magnitude of the adjustments.

[0123] For example, a test optimization instruction can be expressed as "For the communication module (number 123), increase the operating parameter A by a certain percentage; for the power module (number 456), decrease the operating parameter B by a certain percentage." These test optimization instructions can accurately guide the satellite control terminal in adjusting test parameters.

[0124] Step S154: Feed back the test optimization command to the satellite control terminal to trigger the test parameter adjustment operation.

[0125] The generated test optimization instructions are fed back to the satellite control terminal. Upon receiving the instructions, the satellite control terminal can adjust the parameters of the corresponding test modules based on the information provided. Adjusting the test parameters can resolve problems encountered during satellite testing, improving the performance and reliability of the satellite tests. Furthermore, after adjusting the test parameters, data from the satellite test process can be acquired again, and the aforementioned data analysis and evaluation process can be repeated to verify the effectiveness of the adjustments and ensure the smooth conduct of the satellite tests.

[0126] This specification provides one or more embodiments of a computer program product, which includes a computer program that, when executed by a processor, implements the satellite test data analysis method described above.

[0127] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0128] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0129] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the flow and sequence of layers in this specification. Although various examples have been discussed in the foregoing disclosure of some embodiments that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the substance and scope of the embodiments in this specification. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0130] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0131] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and are considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for analyzing satellite test data, characterized in that, The method includes: Acquire the raw data set collected during the satellite experiment, the raw data set containing multiple types of observation data units generated by different experimental modules within a continuous time period; The original dataset is subjected to data feature transformation processing to obtain an analytical feature set for experimental state analysis. The analytical feature set includes temporal features reflecting the operating state of the experimental modules and spatial features reflecting the correlation between modules. The pre-trained satellite test state evaluation model is invoked to perform multi-dimensional state evaluation processing on the analysis feature set, generating test state evaluation results of the satellite test process. The test state evaluation results include descriptions of the operational stability of each test module and descriptions of the parameter correlation between modules. Based on the test status assessment results, the types of anomalies existing during the satellite test and the corresponding impact range information of the anomaly types are determined. The impact range information includes the action boundary of the anomaly module and the affected area of ​​the associated module. Based on the anomaly type and the scope of impact information, a test optimization instruction containing an anomaly location identifier is generated, and the test optimization instruction is fed back to the satellite control terminal to trigger the test parameter adjustment operation; The process of calling the pre-trained satellite test state assessment model to perform multi-dimensional state assessment processing on the analysis feature set, generating test state assessment results for the satellite test process, including: The set of analytical features is input into the state stability assessment module of the satellite test state assessment model to analyze the fluctuation range and frequency of the time series characteristics of each test module and generate a state stability description that reflects the operational reliability of the module. The set of analytical features is input into the parameter correlation evaluation module of the satellite test state evaluation model to analyze the degree of correlation and rate of change of spatial features of different test modules, and generate a parameter correlation description that reflects the effectiveness of module collaboration. The state stability description and the parameter correlation description are comprehensively evaluated to generate an experimental state evaluation result that includes module-level evaluation conclusions and system-level evaluation conclusions. The step of determining the types of anomalies present during the satellite test and the corresponding impact range information based on the test status assessment results includes: Analyze the module-level and system-level evaluation conclusions in the test status evaluation results to identify abnormal modules that deviate from the normal state in the evaluation conclusions; Based on the state stability description and parameter correlation description of the abnormal module, the abnormal manifestation form is determined and matched with the preset abnormal type classification rules to generate the abnormal type; Extract information about other modules associated with the abnormal module from its spatial features, analyze the trend of parameter correlation description of the associated modules, determine the degree and scope of influence of the abnormal module on the associated modules, and generate the scope of influence information.

2. The satellite test data analysis method according to claim 1, characterized in that, The process of performing data feature transformation on the original data set to obtain an analytical feature set for experimental state analysis includes: The original dataset is cleaned to remove noise and interference from data units and fill in missing data segments, resulting in a cleaned dataset. The cleaned dataset is subjected to feature extraction processing. The variation pattern features of each experimental module in a continuous time period are extracted as time-series features, and the correlation pattern features between data units of different experimental modules are extracted as spatial features. The temporal and spatial features are subjected to feature association processing to establish a mapping relationship between features of different experimental modules within the same time period, and a set of associated features with temporal-spatial coupling characteristics is generated as the set of analytical features.

3. The satellite test data analysis method according to claim 2, characterized in that, The step of cleaning the original dataset to remove noise and interference from data units and fill in missing data segments to generate a cleaned dataset includes: Identify the noise distribution pattern of data units in the original dataset, and use an adaptive filtering algorithm to suppress noise in the data units based on the noise distribution pattern to obtain denoised data units; Detect the missing data position in the denoised data unit, and extract the complete data unit before and after the missing position as the reference data unit; Based on the data change trend of the reference data unit, interpolation is performed on the missing data positions to generate a cleaned data set containing a complete data sequence.

4. The satellite test data analysis method according to claim 2, characterized in that, The step of performing feature extraction processing on the cleaned data set, extracting the variation pattern features of each experimental module within a continuous time period as temporal features, and extracting the correlation pattern features between data units of different experimental modules as spatial features, includes: For each test module's cleaned data unit, the change in data values ​​between adjacent time periods is calculated, and the consistency of the change direction within consecutive time periods is statistically analyzed to generate a change pattern feature that reflects the stability of module operation as the time series feature. For any two test modules, after cleaning the data units, analyze the degree of synchronous change and the frequency of asynchronous change of data values ​​within the same time period, and generate association pattern features that reflect the collaborative relationship between modules as the spatial features.

5. The satellite test data analysis method according to claim 2, characterized in that, The step of performing feature association processing on the temporal and spatial features to establish a mapping relationship between features of different experimental modules within the same time period, and generating a set of associated features with temporal-spatial coupling characteristics as the analysis feature set, includes: Each time period is marked with a time identifier. The temporal features of each experimental module within that time period are aligned with the corresponding spatial features in terms of time dimension to obtain a feature alignment set with consistent time identifiers. Cross-correlation analysis is performed on the temporal and spatial features in the feature alignment set to extract the influence weight of temporal feature changes on spatial features and the feedback strength of spatial feature changes on temporal features; Based on the influence weights and feedback strengths, a feature correlation matrix is ​​constructed, and the feature combinations with significant correlations in the feature correlation matrix are used as the correlation feature set.

6. The satellite test data analysis method according to claim 1, characterized in that, The step involves inputting the set of analytical features into the state stability assessment module of the satellite test state assessment model, analyzing the fluctuation range and frequency of the time-series characteristics of each test module, and generating a state stability description reflecting the operational reliability of the module, including: Extract the temporal features of each experimental module from the set of analytical features, and calculate the maximum, minimum and average values ​​of each temporal feature within a preset time window; The difference between the maximum and minimum values ​​is calculated as the fluctuation range parameter, and the number of times the fluctuation range parameter exceeds a preset threshold is counted as the fluctuation frequency parameter. Based on the fluctuation range parameter and the fluctuation frequency parameter, the module runs a reliability assessment function, and generates a state stability description containing reliability level and fluctuation risk points through the reliability assessment function.

7. The satellite test data analysis method according to claim 1, characterized in that, The step of generating test optimization instructions containing anomaly location identifiers based on the anomaly type and the scope of impact information includes: Based on the anomaly type, a preset optimization strategy library is matched, and suggestions for parameter adjustment direction and adjustment range corresponding to the anomaly type are extracted; Based on the influence range boundary in the influence range information, extract the identification information of the abnormal module and its associated modules as the abnormal location identifier; The suggested adjustment direction and range of the parameters are fused with the abnormal location identifier to generate a test optimization instruction that includes the module identifier, adjustment direction, and adjustment range.

8. A satellite test data analysis system, characterized in that, The method includes a processor and a computer-readable storage medium storing machine-executable instructions that, when executed by a computer, implement the satellite test data analysis method according to any one of claims 1-7.

Images