Abnormal state detection method of space target based on micro motion and multivariate Gaussian distribution
Through detection methods based on micro-movement and multivariate Gaussian distribution, abnormal state detection is carried out on spatial targets, which solves the monitoring problems in the existing technology, real-time dynamic detection and abnormal state recognition of spatial targets are achieved, and monitoring accuracy and efficiency are improved. .
Patent Information
- Application Number
- CN202111396470.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-11-23
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2041-11-23
AI Technical Summary
There is a gap in research on the detection of abnormal states of space targets in the prior art, and it is difficult to effectively monitor and early warning of abnormal motion states of satellites and space debris, resulting in potential collision risks.
Using detection methods based on micro-movement and multivariate Gaussian distribution, a multi-dimensional micro-movement feature library is constructed by pre-processing the radar multi-dimensional micro-movement feature, and the multi-dimensional joint probability density function is determined using the maximum likelihood estimation algorithm, and the threshold judgment is made based on the probability density function. The status of the sample to be tested.
Real-time dynamic abnormal state detection of space targets is achieved, monitoring accuracy and efficiency is improved, false alarm rate is reduced, and information situation guarantee needs of aerospace activities are met.
Smart Images

Figure CN114239643B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of space target radar signal processing, and in particular to a method for detecting abnormal state of space targets based on micro-motion and multivariate Gaussian distribution. Background Art
[0002] As the development and utilization of global space resources deepens, countries are stepping up efforts to seize space resources. The outer space of the earth is gradually becoming crowded and becoming a new competitive field. So far, more than 36,000 man-made targets have been sent into space. Therefore, the detection and identification of space targets is becoming increasingly important. The period of geosynchronous orbit satellites is the same as the rotation period of the earth. They play an important role in communication, broadcasting, reconnaissance, surveying, meteorology and relay. However, due to the influence of factors such as the gravity of the sun and the moon, the slight deviation between the gravity of the earth and the centrifugal force, the synchronous satellite will produce complex position drift and deviate from its balance point, which may lead to the loss of the target or potential collision risk. The hypervelocity impact of space targets poses a huge potential threat to the safety of spacecraft and the lives of astronauts. As of 2017, the International Space Station has carried out 24 maneuvers to avoid collisions with space targets. In February 2009, the artificial satellites "Iridium 33" and "Cosmos 2251" of the United States and Russia had their first satellite collision over Siberia. The space debris generated by the collision posed a great threat to adjacent orbital targets. Therefore, it is extremely necessary to monitor the motion status of space targets such as satellites and space debris, especially abnormal status, in real time.
[0003] At present, the monitoring methods of space targets such as artificial satellites and space debris mainly include optical observation and active and passive radar observation. Optical observation is affected by day and night and weather, and the monitoring period is limited. Radar observation is a necessary means for continuous monitoring of targets. Radar characteristic signals are the basis for radar target identification. By analyzing, processing and transforming radar characteristic signals, the relevant characteristics of the target can be obtained, so as to detect and identify the target.
[0004] Anomaly detection is a difficult and hot issue in the field of monitoring space targets such as artificial satellites and space debris. By detecting the abnormal motion state of the target, the fault information of the target can be timely and effectively warned to avoid the risks of target disintegration and collision between targets. However, there is still a certain research gap in anomaly detection of space targets such as satellites and space debris. Summary of the invention
[0005] The present application aims to solve one of the technical problems in the related art at least to some extent.
[0006] To this end, the first purpose of this application is to propose a method for detecting abnormal states of space targets based on micro-motion and multivariate Gaussian distribution, so as to solve the technical problem that there is a research gap in the current broadband radar space target abnormal state detection.
[0007] The second objective of the present application is to propose a device for detecting abnormal states of space targets based on micro-motion and multivariate Gaussian distribution.
[0008] The third objective of the present application is to provide a terminal.
[0009] A fourth object of the present application is to provide a non-transitory computer-readable storage medium.
[0010] To achieve the above-mentioned purpose, a method for detecting abnormal state of a space target based on micro-motion and multivariate Gaussian distribution is proposed in the first aspect of the present application, including:
[0011] Preprocess the samples to be tested to obtain samples to be tested that obey a one-dimensional Gaussian distribution;
[0012] Determine the probability density function value of the sample to be tested that obeys the one-dimensional Gaussian distribution in the multidimensional joint probability density function;
[0013] Based on a probability density function threshold, the state of the sample to be tested is determined according to the probability density function value.
[0014] Optionally, in one embodiment of the present application, before determining the probability density function value of the sample to be tested that obeys the one-dimensional Gaussian distribution in the multidimensional joint probability density function, the method further includes:
[0015] According to the normal state of space targets, the accumulated radar multi-dimensional micro-motion features are extracted and the target multi-dimensional micro-motion feature library is constructed;
[0016] Preprocessing each dimensional feature vector in the target multi-dimensional micro-motion feature library to obtain a preprocessed target multi-dimensional micro-motion feature library, wherein each dimensional feature vector in the preprocessed target multi-dimensional micro-motion feature library obeys a one-dimensional Gaussian distribution;
[0017] Multivariate Gaussian distribution fitting is performed on all feature vectors in the preprocessed target multidimensional micro-motion feature library to obtain a target multidimensional joint probability density function.
[0018] Optionally, in one embodiment of the present application, performing multivariate Gaussian distribution fitting on all feature vectors in the preprocessed target multidimensional micro-motion feature library to obtain a target multidimensional joint probability density function includes:
[0019] Determine the sample mean and covariance matrix of the preprocessed target multi-dimensional micro-motion feature library based on the maximum likelihood estimation algorithm;
[0020] Based on the sample mean and the covariance matrix, a target multidimensional joint probability density function is determined.
[0021] Optionally, in one embodiment of the present application, performing multivariate Gaussian distribution fitting on all feature vectors in the preprocessed target multidimensional micro-motion feature library to obtain a target multidimensional joint probability density function includes:
[0022] Determine the sample mean and covariance matrix of the preprocessed target multi-dimensional micro-motion feature library based on the maximum likelihood estimation algorithm;
[0023] Based on the sample mean and the covariance matrix, a target multidimensional joint probability density function is determined.
[0024] Optionally, in one embodiment of the present application, determining a target multidimensional joint probability density function based on the sample mean and the covariance matrix includes:
[0025] The sample mean is determined according to the following formula:
[0026]
[0027] in, is the sample mean, is the M-dimensional random vector corresponding to the preprocessed target multi-dimensional micro-motion feature library;
[0028] The covariance matrix is determined according to the following formula:
[0029]
[0030]
[0031] in, is the covariance matrix, S is the dispersion matrix;
[0032] The covariance matrix is modified, and an unbiased estimator of the covariance matrix is determined according to the following formula;
[0033]
[0034] in, is the unbiased estimator of the covariance matrix, S is the deviation matrix;
[0035] The target multidimensional joint probability density function is determined according to the unbiased estimator of the covariance matrix and the sample mean, and the target multidimensional joint probability density function is determined according to the following formula:
[0036]
[0037] Among them, det(·) represents the operation of finding the matrix determinant, (·) T Represents the transpose operator.
[0038] Optionally, in one embodiment of the present application, before determining the state of the sample to be tested according to the probability density function value based on the probability density function threshold, the method further includes:
[0039] Determining a confidence region based on a confidence level of the target multidimensional joint probability density function;
[0040] A probability density function threshold corresponding to a boundary of the confidence region is determined.
[0041] Optionally, in one embodiment of the present application, the determining the state of the sample to be tested according to the probability density function value based on the probability density function threshold includes:
[0042] Based on the confidence region, determine the initial decision criterion;
[0043] Based on the Neyman-Pearson criterion, the decision criterion is determined according to the initial decision criterion and the probability density function threshold;
[0044] Based on the decision criterion, the state of the sample to be tested is determined according to the probability density function value.
[0045] Optionally, in one embodiment of the present application, determining the state of the sample to be tested according to the probability density function value based on the decision criterion includes:
[0046] If the probability density function value is less than the probability density function threshold, the sample to be tested is in a normal state;
[0047] If the probability density function value is not less than the probability density function threshold, the sample to be tested is in an abnormal state.
[0048] In summary, the method proposed in the embodiment of the first aspect of the present application obtains a sample to be tested that obeys a one-dimensional Gaussian distribution by preprocessing the sample to be tested; determines the probability density function value of the sample to be tested that obeys the one-dimensional Gaussian distribution in a multidimensional joint probability density function; and determines the state of the sample to be tested according to the probability density function value based on a probability density function threshold. The present application introduces a multidimensional joint probability density function to perform real-time dynamic detection of the abnormal motion state of a space target, providing technical support for the field of space target monitoring, especially the field of anomaly detection.
[0049] To achieve the above-mentioned purpose, a second aspect of the present application proposes a space target abnormal state detection device based on micro-motion and multivariate Gaussian distribution, comprising:
[0050] The sample processing module is used to pre-process the samples to be tested to obtain the samples to be tested that obey the one-dimensional Gaussian distribution;
[0051] A function determination module, used to determine the probability density function value of the sample to be tested that obeys the one-dimensional Gaussian distribution in the multidimensional joint probability density function;
[0052] The state determination module is used to determine the state of the sample to be tested according to the probability density function value based on the probability density function threshold.
[0053] In summary, the device proposed in the second aspect of the embodiment of the present application pre-processes the sample to be tested through the sample processing module to obtain the sample to be tested that obeys the one-dimensional Gaussian distribution; the function determination module determines the probability density function value of the sample to be tested that obeys the one-dimensional Gaussian distribution in the multidimensional joint probability density function; the state determination module determines the state of the sample to be tested according to the probability density function value based on the probability density function threshold. This application introduces a multidimensional joint probability density function to perform real-time dynamic detection of the abnormal motion state of space targets, providing technical support for the field of space target monitoring, especially the field of anomaly detection.
[0054] To achieve the above-mentioned purpose, the third aspect of the present application provides a terminal, including:
[0055] at least one processor; and
[0056] a memory communicatively connected to the at least one processor; wherein,
[0057] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any one of the methods described in the above aspect.
[0058] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present application proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute any one of the methods described in the preceding aspect.
[0059] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:
[0061] Figure 1 A flowchart of a method for detecting abnormal state of a space target based on micro-motion and multivariate Gaussian distribution provided in an embodiment of the present application;
[0062] Figure 2 A schematic diagram of a model of a simulated satellite provided in an embodiment of the present application;
[0063] Figure 3 A flowchart of abnormal state detection of a simulated satellite provided in an embodiment of the present application;
[0064] Figure 4 A schematic diagram of some characteristic value samples provided in the embodiments of the present application;
[0065] Figure 5 A schematic diagram of a statistical histogram of the preprocessed entropy value and variance and a fitted one-dimensional Gaussian probability density curve provided in an embodiment of the present application;
[0066] Figure 6 A schematic diagram of the distribution of feature value sample points after preprocessing of the training set provided in an embodiment of the present application;
[0067] Figure 7 A schematic diagram of the probability density function of the binary Gaussian distribution provided in the embodiment of the present application;
[0068] Figure 8 A schematic diagram of an anomaly detector provided in an embodiment of the present application;
[0069] Fig. 9 A schematic diagram of abnormal state detection results of the test set data provided in an embodiment of the present application;
[0070] Fig.10 A schematic diagram of the structure of a space target abnormal state detection device based on micro-motion and multivariate Gaussian distribution provided in an embodiment of the present application.
[0071] Fig.11 is a schematic diagram of the structure of a terminal provided in an embodiment of the present application;
[0072] Fig.12 It is a schematic diagram of the structure of the operating system and user space provided in the embodiment of the present application;
[0073] Fig.13 yes Fig.12 The architecture diagram of the Android operating system;
[0074] Fig.14 yes Fig.12 Architecture diagram of the IOS operating system. DETAILED DESCRIPTION
[0075] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be construed as limiting the present application. On the contrary, the embodiments of the present application include all changes, modifications and equivalents that fall within the spirit and connotation of the appended claims.
[0076] It should be noted that micro-Doppler describes the fine features of target motion and is one of the useful features for radar target identification, which helps to improve radar target detection, identification and state perception capabilities. The abnormality of a space target is a situation in which its working and operating state is significantly different from the normal state, mainly manifested in abnormal rotation, swinging or overall tumbling of components. When the target has typical abnormal micro-motion behaviors such as abnormal rotation of components such as solar panels and abnormal tumbling of attitude, the micro-motion characteristics of the target radar echo signal will change significantly. Therefore, the abnormal state of the target can be detected and perceived by extracting the target micro-motion features.
[0077] At present, there are few studies on anomaly detection methods in the field of space target monitoring such as artificial satellites and space debris. One of them is an attitude anomaly detection method based on the space target Radar Cross Section (RCS) sequence and one-class Support Vector Machine (OCSVM). This method is mainly aimed at narrow-band radars with low range resolution. It has a good detection effect when the three-axis stable space target has an unstable rotation attitude anomaly, but it is difficult to detect the abnormal motion behavior of the target components.
[0078] Gaussian distribution has beautiful mathematical properties and powerful modeling capabilities. According to the central limit theorem, the means of a large number of independent and identically distributed random variables will converge to Gaussian distribution according to the distribution after proper standardization. There are two types of Gaussian models: single Gaussian model and multivariate Gaussian model. The multivariate Gaussian distribution model has good universality in data distribution fitting. Therefore, by introducing multivariate Gaussian distribution as the prior distribution of space target radar micro-motion characteristics, the space target abnormal state detection technology based on radar micro-motion characteristics and multivariate Gaussian distribution can be studied.
[0079] The present application is described in detail below with reference to specific embodiments.
[0080] Figure 1 A flowchart of a method for detecting abnormal state of a space target based on micro-motion and multivariate Gaussian distribution provided in an embodiment of the present application.
[0081] like Figure 1As shown, an embodiment of the present application provides a method for detecting abnormal state of a space target based on micro-motion and multivariate Gaussian distribution, comprising the following steps:
[0082] Step 101, preprocessing the sample to be tested to obtain the sample to be tested that obeys a one-dimensional Gaussian distribution;
[0083] Step 102, determining the probability density function value of the sample to be tested that obeys the one-dimensional Gaussian distribution in the multi-dimensional joint probability density function;
[0084] Step 103: Based on the probability density function threshold, determine the state of the sample to be tested according to the probability density function value.
[0085] In the embodiment of the present application, before determining the probability density function value of the sample to be tested that obeys the one-dimensional Gaussian distribution in the multidimensional joint probability density function, it also includes:
[0086] According to the normal state of space targets, the accumulated radar multi-dimensional micro-motion features are extracted and the target multi-dimensional micro-motion feature library is constructed;
[0087] Preprocessing each dimensional feature vector in the target multi-dimensional micro-motion feature library to obtain a preprocessed target multi-dimensional micro-motion feature library, wherein each dimensional feature vector in the preprocessed target multi-dimensional micro-motion feature library obeys a one-dimensional Gaussian distribution;
[0088] All feature vectors in the preprocessed target multidimensional micro-motion feature library are fitted with multivariate Gaussian distribution to obtain the target multidimensional joint probability density function.
[0089] Specifically, Y=[Y1,Y2,…,Y M ] N×M It represents the radar multi-dimensional micro-motion feature matrix extracted and accumulated in the normal state of the space target, where M is the dimension of the radar multi-dimensional micro-motion feature, N is the number of samples of the radar multi-dimensional micro-motion feature, and Y i (i=1,…,M) is the i-th eigenvalue sample vector, Y i =[Y i [1],Y i [2],…,Y i [N]] T , where Y i [1], i [2],…,Y i [N] is the N observations of the i-th eigenvalue sample vector.
[0090] Specifically, in order to make the distribution of elements in the radar multi-dimensional micro-motion feature matrix obey the one-dimensional Gaussian distribution, the size of the eigenvalue sample vector in the radar multi-dimensional micro-motion feature matrix is preprocessed according to a set scale, for example, the eigenvalue sample vector can be scaled, the eigenvalue sample vector can be raised to a power, or the eigenvalue sample vector can be lowered to a power. The preprocessed eigenvalue sample vector obeys the one-dimensional Gaussian distribution.
[0091] Furthermore, the preprocessing process is denoted as f i (·), then X i =f i (Y i ), where X i is the i-th eigenvalue sample vector after preprocessing. Let X=[X1,X2,…,X M ] T represents the radar multi-dimensional micro-motion feature matrix after preprocessing,
[0092] In the embodiment of the present application, all feature vectors in the preprocessed target multidimensional micro-motion feature library are fitted with multivariate Gaussian distribution to obtain the target multidimensional joint probability density function, including:
[0093] Determine the sample mean and covariance matrix of the preprocessed target multi-dimensional micro-motion feature library based on the maximum likelihood estimation algorithm;
[0094] Based on the sample mean and covariance matrix, the target multidimensional joint probability density function is determined.
[0095] In the embodiment of the present application, all feature vectors in the preprocessed target multidimensional micro-motion feature library are fitted with multivariate Gaussian distribution to obtain the target multidimensional joint probability density function, including:
[0096] Based on the Maximum Likelihood Estimation (MLE) algorithm, the sample mean and covariance matrix of the preprocessed target multi-dimensional micro-motion feature library are determined;
[0097] Based on the sample mean and covariance matrix, the target multidimensional joint probability density function is determined.
[0098] In an embodiment of the present application, based on the sample mean and the covariance matrix, a target multidimensional joint probability density function is determined, including:
[0099] The sample mean is determined by the following formula:
[0100]
[0101] in, is the sample mean, is the M-dimensional random vector corresponding to the preprocessed target multi-dimensional micro-motion feature library;
[0102] The covariance matrix is determined as follows:
[0103]
[0104]
[0105] in, is the covariance matrix, S is the dispersion matrix;
[0106] The covariance matrix is modified and the unbiased estimator of the covariance matrix is determined according to the following formula;
[0107]
[0108] in, is the unbiased estimator of the covariance matrix, S is the deviation matrix;
[0109] The target multidimensional joint probability density function is determined according to the unbiased estimator of the covariance matrix and the sample mean, and the target multidimensional joint probability density function is determined according to the following formula:
[0110]
[0111] Among them, det(·) represents the operation of finding the matrix determinant, (·) T Represents the transpose operator.
[0112] Specifically, since the covariance matrix is not an unbiased estimate, it is necessary to correct the covariance matrix to obtain an unbiased estimator of the covariance matrix. Convert to
[0113] In the embodiment of the present application, before determining the state of the sample to be tested according to the probability density function value based on the probability density function threshold, the method further includes:
[0114] Determine the confidence region based on the confidence level of the target multi-dimensional joint probability density function;
[0115] Determine the probability density function threshold corresponding to the boundaries of the confidence region.
[0116] Specifically, when the multidimensional micro-motion feature of the radar is two-dimensional, that is, M=2, the multidimensional joint probability density function of the target is p(x1,x2), and the relationship between the confidence level and the confidence region and the multidimensional joint probability density function of the target is determined according to the following formula:
[0117]
[0118] Where p is the confidence level, Ωp (x1,x2) is the confidence region.
[0119] Furthermore, for the bivariate Gaussian distribution, Ω p (x1,x2) is an elliptical area, and the boundary of the elliptical area is an elliptic curve. The expression of this elliptic curve is: Based on the statistical theory of bivariate Gaussian distribution, we can determine Therefore, the confidence region is determined according to the following formula:
[0120]
[0121] Furthermore, a probability density function threshold ε=p(x1,x2) corresponding to the boundary of the confidence region is determined.
[0122] In the embodiment of the present application, based on the probability density function threshold, the state of the sample to be tested is determined according to the probability density function value, including:
[0123] Based on the confidence region, determine the initial decision criterion;
[0124] Based on the Neyman-Pearson criterion, the decision criterion is determined according to the initial decision criterion and the probability density function threshold;
[0125] Based on the decision criterion, the state of the sample to be tested is determined according to the probability density function value.
[0126] In the embodiment of the present application, based on the decision criterion, the state of the sample to be tested is determined according to the probability density function value, including:
[0127] If the probability density function value is less than the probability density function threshold, the sample to be tested is in a normal state;
[0128] If the probability density function value is not less than the probability density function threshold, the sample to be tested is in an abnormal state.
[0129] Specifically, in the initial decision criterion, if z∈Ω p (x1,x2,…,x M ), the sample to be tested is in normal state, recorded as H0; if Then the sample to be tested is in an abnormal state, denoted as H1. Where z=(z1,z2,…,z M ) T Represents the radar multi-dimensional micro-motion feature matrix after preprocessing.
[0130] Specifically, according to the Neyman-Pearson criterion, under a certain detection false alarm rate P FA The detection probability P under the condition D The higher the detection probability, the better the detection result. D=P(H1|H1); False alarm rate of the first type of detection P FA =P(H1|H0). Therefore, the decision criterion is determined according to the following formula:
[0131]
[0132] Where ε is the probability density function threshold. According to the decision criteria, the probability density function value p(z1,z2,…,z M ) is less than ε, H1 is established, that is, the sample to be tested is considered to be in an abnormal state; otherwise, H0 is established, that is, the sample to be tested is considered to be in a normal state.
[0133] Taking a scenario as an example, the embodiment of the present application uses a simulated satellite as a space target, and the model of the simulated satellite is shown as follows: Figure 2 As shown in Figure 2, the process of abnormal state detection of simulated satellite is as follows Figure 3 As shown, the method specifically includes the following steps:
[0134] Step 201, determine the normal state micro-motion feature value samples of the training set, and construct a target multi-dimensional micro-motion feature library. All micro-motion feature value samples are generated by the normal and abnormal rotation of the solar panel components of the simulated satellite model. Let the dimension of the target multi-dimensional micro-motion feature library be 2, that is, M = 2, and each feature vector contains two feature values: time-frequency spectrum entropy value and variance. The normal state micro-motion feature value samples of the training set consist of 1000 groups of normal state samples, that is, the number of samples N = 1000. Some feature value samples are as follows Figure 4 shown.
[0135] Step 202, preprocess the entropy value Y1 and variance Y2 of the normal state micro-motion characteristic value samples of the training set respectively, so that the preprocessed entropy value and variance obey the one-dimensional Gaussian distribution. The preprocessed entropy value and variance are determined according to the following formula:
[0136]
[0137] Among them, X1 is the entropy value after preprocessing, and X2 is the variance after preprocessing. The statistical histogram of the entropy value and variance after preprocessing and the fitted one-dimensional Gaussian probability density curve are as follows: Figure 5 As shown, Figure 5 (a) is the entropy value after preprocessing, Figure 5 (b) is the variance after preprocessing. The distribution of eigenvalue sample points after preprocessing of the training set is shown in Figure 6 shown.
[0138] Step 203, fitting the probability density function of the multidimensional radar micro-motion feature based on the multivariate Gaussian distribution. Combine the pre-processed eigenvalues X1 and X2, perform the maximum likelihood estimation of the bivariate Gaussian distribution parameters on them, and determine the sample mean Covariance matrix Then the probability density function of the bivariate Gaussian distribution is determined according to the following formula:
[0139]
[0140] Among them, the probability density function of the bivariate Gaussian distribution is as follows Figure 7 As shown, Figure 7 (a) is the three-dimensional probability density diagram of the bivariate Gaussian distribution. Figure 7 (b) is the probability density contour diagram of the bivariate Gaussian distribution.
[0141] Step 204: Determine the confidence region Ω according to the confidence level p. p (x1,x2). To achieve better anomaly detection results, the confidence level p is set to 0.999999, and the ellipse equation of the confidence region boundary is obtained as follows: The corresponding ε value is 0.0148. Based on the confidence region and decision criteria, the anomaly detector is determined, such as Figure 8 shown.
[0142] Step 205, abnormal state detection is performed using the test set data. The test set micromotion feature value samples consist of 500 groups of normal state samples and 100 groups of abnormal state samples. The test set micromotion feature value samples are preprocessed in the same way as the training set normal state micromotion feature value samples, and the preprocessed test set micromotion feature value samples are input into the anomaly detector to perform abnormal state detection on the test set data. The test results are shown in the attached figure. Fig. 9 As shown, the circles are normal samples of the test set, and the stars are abnormal samples of the test set. The test abnormality detection rate is 96%, and the test false alarm rate is 5.2%. It shows that the method provided by the embodiment of the present application has a good detection effect in the abnormal state detection of space targets such as artificial satellites and space debris, and can obtain a higher abnormality detection rate under the condition of a lower false alarm rate, which can meet the actual application needs and provide space target information situation guarantee for my country's space activities.
[0143] In summary, the method proposed in the embodiment of the present application obtains a sample to be tested that obeys a one-dimensional Gaussian distribution by preprocessing the sample to be tested; determines the probability density function value of the sample to be tested that obeys a one-dimensional Gaussian distribution in a multidimensional joint probability density function; and determines the state of the sample to be tested according to the probability density function value based on a probability density function threshold. The present application introduces a multidimensional joint probability density function to perform real-time dynamic detection of the abnormal motion state of a space target, providing technical support for the field of space target monitoring, especially the field of anomaly detection.
[0144] In order to implement the above-mentioned embodiments, the present application also proposes a device for detecting abnormal state of a space target based on micro-motion and multivariate Gaussian distribution.
[0145] Fig.10 A schematic diagram of the structure of a space target abnormal state detection device based on micro-motion and multivariate Gaussian distribution provided in an embodiment of the present application.
[0146] like Fig.10 As shown, a space target abnormal state detection device based on micro-motion and multivariate Gaussian distribution includes:
[0147] The sample processing module 1010 is used to pre-process the sample to be tested to obtain the sample to be tested that obeys the one-dimensional Gaussian distribution;
[0148] A function determination module 1020 is used to determine the probability density function value of the sample to be tested that obeys the one-dimensional Gaussian distribution in the multi-dimensional joint probability density function;
[0149] The state determination module 1030 is used to determine the state of the sample to be tested according to the probability density function value based on the probability density function threshold.
[0150] In summary, the device proposed in the embodiment of the present application pre-processes the sample to be tested through the sample processing module to obtain the sample to be tested that obeys the one-dimensional Gaussian distribution; the function determination module determines the probability density function value of the sample to be tested that obeys the one-dimensional Gaussian distribution in the multidimensional joint probability density function; the state determination module determines the state of the sample to be tested according to the probability density function value based on the probability density function threshold. This application introduces a multidimensional joint probability density function to perform real-time dynamic detection of the abnormal motion state of space targets, providing technical support for the field of space target monitoring, especially the field of anomaly detection.
[0151] The present application also provides a computer storage medium that can store multiple instructions, which are suitable for being loaded and executed by a processor as described above. Figure 1-Figure 9 The method for detecting abnormal state of space target based on micro-motion and multivariate Gaussian distribution in the embodiment shown in the figure can be found in the specific execution process. Figure 1-Figure 9 The specific description of the illustrated embodiment will not be repeated here.
[0152] Please refer to Fig.11 , which shows a block diagram of the structure of a terminal provided by an exemplary embodiment of the present application. The terminal in the present application may include one or more of the following components: a processor 110, a memory 120, an input device 130, an output device 140, and a bus 150. The processor 110, the memory 120, the input device 130, and the output device 140 may be connected via the bus 150. The processor loads and executes the above Figure 3-Figure 9 The network connection method of the embodiment shown in the figure can be specifically executed by referring to Figure 3-Figure 9 The specific description of the illustrated embodiment will not be repeated here.
[0153] The processor 110 may include one or more processing cores. The processor 110 uses various interfaces and lines to connect various parts of the entire terminal, and executes various functions and processes data of the terminal 100 by running or executing instructions, programs, code sets or instruction sets stored in the memory 120, and calling data stored in the memory 120. Optionally, the processor 110 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 110 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 110, but may be implemented separately through a communication chip.
[0154] The memory 120 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 120 includes a non-transitory computer-readable storage medium. The memory 120 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 120 may include a storage program area and a storage data area, wherein the storage program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc. The operating system may be an Android system, including a system deeply developed based on the Android system, an IOS system developed by Apple, including a system deeply developed based on the IOS system or other systems. The storage data area may also store data created by the terminal during use, such as a phone book, audio and video data, chat record data, etc.
[0155] See also Fig.12As shown, the memory 120 can be divided into an operating system space and a user space. The operating system runs in the operating system space, and native and third-party applications run in the user space. In order to ensure that different third-party applications can achieve good operating results, the operating system allocates corresponding system resources to different third-party applications. However, different application scenarios in the same third-party application also have different requirements for system resources. For example, in the local resource loading scenario, the third-party application has higher requirements for disk reading speed; in the animation rendering scenario, the third-party application has higher requirements for GPU performance. The operating system and third-party applications are independent of each other, and the operating system often cannot perceive the current application scenario of the third-party application in a timely manner, resulting in the operating system being unable to perform targeted system resource adaptation according to the specific application scenario of the third-party application.
[0156] In order for the operating system to distinguish the specific application scenarios of third-party applications, it is necessary to open up data communication between third-party applications and the operating system so that the operating system can obtain the current scenario information of third-party applications at any time, and then perform targeted system resource adaptation based on the current scenario.
[0157] Taking the Android operating system as an example, the programs and data stored in the memory 120 are as follows: Fig.13As shown, the memory 120 may store a Linux kernel layer 320, a system runtime library layer 340, an application framework layer 360, and an application layer 380, wherein the Linux kernel layer 320, the system runtime library layer 340, and the application framework layer 360 belong to the operating system space, and the application layer 380 belongs to the user space. The Linux kernel layer 320 provides underlying drivers for various hardware of the terminal, such as display drivers, audio drivers, camera drivers, Bluetooth drivers, Wi-Fi drivers, power management, etc. The system runtime library layer 340 provides the main feature support for the Android system through some C / C++ libraries. For example, the SQLite library provides database support, the OpenGL / ES library provides 3D drawing support, and the Webkit library provides browser kernel support, etc. The Android runtime library (Android runtime) is also provided in the system runtime library layer 340, which mainly provides some core libraries that allow developers to use the Java language to write Android applications. The application framework layer 360 provides various APIs that may be used when building applications. Developers can also use these APIs to build their own applications, such as activity management, window management, view management, notification management, content provider, package management, call management, resource management, and location management. At least one application runs in the application layer 380. These applications can be native applications that come with the operating system, such as contact applications, text messaging applications, clock applications, camera applications, etc.; they can also be third-party applications developed by third-party developers, such as game applications, instant messaging applications, photo beautification applications, network connection applications, etc.
[0158] Taking the operating system as an IOS system as an example, the programs and data stored in the memory 120 are as follows: Fig.13As shown, the IOS system includes: a core operating system layer 420 (Core OS layer), a core service layer 440 (Core Services layer), a media layer 460 (Media layer), and a touchable layer 480 (Cocoa Touch Layer). The core operating system layer 420 includes the operating system kernel, drivers, and underlying program frameworks, which provide functions closer to the hardware for use by the program framework located in the core service layer 440. The core service layer 440 provides system services and / or program frameworks required by the application, such as the foundation framework, account framework, advertising framework, data storage framework, network connection framework, geographic location framework, motion framework, etc. The media layer 460 provides audio-visual interfaces for the application, such as graphics and image related interfaces, audio technology related interfaces, video technology related interfaces, and wireless playback (AirPlay) interfaces for audio and video transmission technologies. The touchable layer 480 provides various commonly used interface-related frameworks for application development, and the touchable layer 480 is responsible for the user's touch interaction operations on the terminal. For example, local notification service, remote push service, advertising framework, game tool framework, message user interface (UI) framework, user interface UIKit framework, map framework, etc.
[0159] exist Fig.14 Among the frameworks shown, the frameworks related to most applications include but are not limited to: the basic framework in the core service layer 440 and the UIKit framework in the touchable layer 480. The basic framework provides many basic object classes and data types, provides the most basic system services for all applications, and has nothing to do with UI. The classes provided by the UIKit framework are basic UI class libraries for creating touch-based user interfaces. iOS applications can provide UIs based on the UIKit framework, so it provides the basic architecture of applications for building user interfaces, drawing, processing and user interaction events, responding to gestures, etc.
[0160] Among them, the method and principle of implementing data communication between third-party applications and the operating system in the IOS system can be referred to the Android system, and this application will not go into details here.
[0161] Among them, the input device 130 is used to receive input instructions or data, and the input device 130 includes but is not limited to a keyboard, a mouse, a camera, a microphone or a touch device. The output device 140 is used to output instructions or data, and the output device 140 includes but is not limited to a display device and a speaker. In one example, the input device 130 and the output device 140 can be combined, and the input device 130 and the output device 140 are a touch display screen, which is used to receive touch operations on or near it by a user using any suitable object such as a finger or a touch pen, and to display the user interface of each application. The touch display screen is usually set on the front panel of the terminal. The touch display screen can be designed as a full screen, a curved screen or a special-shaped screen. The touch display screen can also be designed as a combination of a full screen and a curved screen, or a combination of a special-shaped screen and a curved screen, which is not limited in the embodiments of the present application.
[0162] In addition, those skilled in the art will appreciate that the structure of the terminal shown in the above drawings does not constitute a limitation on the terminal, and the terminal may include more or fewer components than shown, or combine certain components, or arrange the components differently. For example, the terminal also includes a radio frequency circuit, an input unit, a sensor, an audio circuit, a wireless fidelity (WiFi) module, a power supply, a Bluetooth module, and other components, which will not be described in detail here.
[0163] In the embodiment of the present application, the execution subject of each step may be the terminal described above. Optionally, the execution subject of each step is the operating system of the terminal. The operating system may be an Android system, an IOS system, or other operating systems, which is not limited in the embodiment of the present application.
[0164] The terminal of the embodiment of the present application may also be equipped with a display device, which may be any device capable of realizing a display function, such as a cathode ray tube display (CR), a light-emitting diode display (LED), an electronic ink screen, a liquid crystal display (LCD), a plasma display panel (PDP), etc. The user may use the display device on the terminal 100 to view displayed text, images, videos and other information. The terminal may be a smart phone, a tablet computer, a gaming device, an AR (Augmented Reality) device, a car, a data storage device, an audio playback device, a video playback device, a notebook, a desktop computing device, a wearable device such as an electronic watch, an electronic glasses, an electronic helmet, an electronic bracelet, an electronic necklace, electronic clothing and other devices.
[0165] Those skilled in the art can clearly understand that the technical solution of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (FPGA), an integrated circuit (IC), etc.
[0166] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.
[0167] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0168] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0169] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0170] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0171] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program code.
[0172] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct the relevant hardware. The program may be stored in a computer-readable memory, and the memory may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.
[0173] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.
Claims
1. A method for detecting abnormal state of space targets based on micro-motion and multivariate Gaussian distribution, characterized in that: The method comprises: Preprocess the samples to be tested to obtain samples to be tested that obey a one-dimensional Gaussian distribution; Determine the probability density function value of the sample to be tested that obeys the one-dimensional Gaussian distribution in the multidimensional joint probability density function; Based on a probability density function threshold, determining the state of the sample to be tested according to the probability density function value; Before determining the probability density function value of the sample to be tested that obeys the one-dimensional Gaussian distribution in the multidimensional joint probability density function, the method further includes: According to the normal state of space targets, the accumulated radar multi-dimensional micro-motion features are extracted and the target multi-dimensional micro-motion feature library is constructed; Preprocessing each dimensional feature vector in the target multi-dimensional micro-motion feature library to obtain a preprocessed target multi-dimensional micro-motion feature library, wherein each dimensional feature vector in the preprocessed target multi-dimensional micro-motion feature library obeys a one-dimensional Gaussian distribution; Multivariate Gaussian distribution fitting is performed on all feature vectors in the preprocessed target multidimensional micro-motion feature library to obtain a target multidimensional joint probability density function.
2. The method according to claim 1, characterized in that The multi-dimensional Gaussian distribution fitting is performed on all feature vectors in the pre-processed target multi-dimensional micro-motion feature library to obtain the target multi-dimensional joint probability density function, including: Determine the sample mean and covariance matrix of the preprocessed target multi-dimensional micro-motion feature library based on the maximum likelihood estimation algorithm; Based on the sample mean and the covariance matrix, a target multidimensional joint probability density function is determined.
3. The method according to claim 2, characterized in that The step of determining a target multidimensional joint probability density function based on the sample mean and the covariance matrix includes: The sample mean is determined according to the following formula: in, is the sample mean, is the M-dimensional random vector corresponding to the preprocessed target multi-dimensional micro-motion feature library; The covariance matrix is determined according to the following formula: in, is the covariance matrix, S is the dispersion matrix; The covariance matrix is modified, and an unbiased estimator of the covariance matrix is determined according to the following formula; in, is the unbiased estimator of the covariance matrix, S is the deviation matrix; The target multidimensional joint probability density function is determined according to the unbiased estimator of the covariance matrix and the sample mean, and the target multidimensional joint probability density function is determined according to the following formula: Among them, det(·) represents the operation of finding the matrix determinant, (·) T Represents the transpose operator.
4. The method according to claim 1, characterized in that Before determining the state of the sample to be tested according to the probability density function value based on the probability density function threshold, the method further includes: Determining a confidence region based on a confidence level of the target multidimensional joint probability density function; A probability density function threshold corresponding to a boundary of the confidence region is determined.
5. The method according to claim 4, characterized in that The determining the state of the sample to be tested according to the probability density function value based on the probability density function threshold value includes: Based on the confidence region, determine the initial decision criterion; Based on the Neyman-Pearson criterion, the decision criterion is determined according to the initial decision criterion and the probability density function threshold; Based on the decision criterion, the state of the sample to be tested is determined according to the probability density function value.
6. The method according to claim 5, characterized in that The determining the state of the sample to be tested according to the probability density function value based on the decision criterion includes: If the probability density function value is less than the probability density function threshold, the sample to be tested is in a normal state; If the probability density function value is not less than the probability density function threshold, the sample to be tested is in an abnormal state.
7. A device for detecting abnormal state of space targets based on micro-motion and multivariate Gaussian distribution, characterized in that: The device comprises: The sample processing module is used to pre-process the samples to be tested to obtain the samples to be tested that obey the one-dimensional Gaussian distribution; A function determination module is used to determine the probability density function value of the sample to be tested that obeys the one-dimensional Gaussian distribution in the multidimensional joint probability density function, wherein the accumulated radar multidimensional micro-motion features are extracted according to the normal state of the space target, a target multidimensional micro-motion feature library is constructed, each dimensional feature vector in the target multidimensional micro-motion feature library is preprocessed to obtain the preprocessed target multidimensional micro-motion feature library, each dimensional feature vector in the preprocessed target multidimensional micro-motion feature library obeys the one-dimensional Gaussian distribution, and all feature vectors in the preprocessed target multidimensional micro-motion feature library are fitted with multivariate Gaussian distribution to obtain the target multidimensional joint probability density function; The state determination module is used to determine the state of the sample to be tested according to the probability density function value based on the probability density function threshold.
8. A terminal, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.
9. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.
