Spacecraft attitude determination state detection method based on attitude regression model construction

By constructing an attitude regression model based on the decision tree model, the problem of difficult detection of attitude anomalies in spacecraft and poor model universality is solved, and the accuracy and universality of posture state detection for different spacecraft are improved.

CN119066628AActive Publication Date: 2024-12-03CHINA XIAN SATELLITE CONTROL CENT
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411555794.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-04
Publication Date
2024-12-03
Estimated Expiration
2044-11-04

AI Technical Summary

Technical Problem

It is difficult to establish a general spacecraft attitude adjustment/maneuvering mechanism model in the prior art, which makes it difficult to detect spacecraft attitude abnormalities and the model is not very versatile.

Method used

By constructing an attitude regression model based on the decision tree model, the spacecraft's attitude control actuator and attitude control measurement historical parameters are used for data preprocessing and training, and an adaptive attitude regression model is generated to detect the attitude of the spacecraft. state.

Benefits of technology

It improves the accuracy and versatility of spacecraft attitude state detection, making it suitable for different attitude control actuators and stand-alone spacecraft with attitude control measurement, enhancing the accuracy of detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066628A_ABST
    Figure CN119066628A_ABST
Patent Text Reader

Abstract

The invention relates to a spacecraft attitude determination state detection method based on attitude regression model construction. The method comprises the following steps: determining an attitude control execution mechanism and an attitude control measurement single machine of a spacecraft, and obtaining corresponding to-be-detected parameters and historical parameters; generating set data through normalization processing; splitting the set data into a training set and training according to the decision tree model, verifying the training result by the test set, and taking the trained decision tree model as a posture regression model corresponding to the spacecraft; generating to-be-detected data through normalization processing; and substituting to-be-detected data into the attitude regression model and detecting the attitude determination state of the spacecraft. According to the method, the parameters of the spacecraft are preprocessed, and the adaptive attitude regression model is constructed in a targeted manner, so that the detection of the attitude determination state can be applicable to spacecrafts adopting different attitude control execution mechanisms and attitude control measurement single machines; and the universality of the detection of the attitude determination state is improved on the basis of high accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of data processing in spacecraft measurement and control management, and in particular to a method for detecting the attitude state of a spacecraft based on building an attitude regression model. Background Art

[0002] When a spacecraft enters a predetermined orbit and operates, it sometimes needs to make attitude adjustments to achieve the pointing requirements of the payload. When the satellite attitude is adjusted in a small range, it is called satellite attitude adjustment, and when the satellite attitude is maneuvered in a large range, it is called satellite attitude maneuvering. However, whether it is attitude adjustment or attitude maneuvering, it reflects the correspondence between the control quantity applied to the attitude control actuator and the output value of the control result. This correspondence is mainly related to the execution capability of the actuator and the attitude dynamics of the satellite in the space environment. However, attitude adjustment / maneuvering is a complex mechanism process, which requires the integration of the telemetry data of the current spacecraft's space attitude sensors, controllers, actuators and other control quantities, and after a series of calculations, the data of the attitude control units such as the star sensor, the time sensor, and the gyroscope on the satellite are obtained.

[0003] Regarding the above technical solution, the inventors found that there are at least the following technical problems: It is difficult to detect spacecraft attitude anomalies by building a model of attitude adjustment / maneuvering mechanism, because the model of the mechanism is not universal due to the different design mechanisms of spacecraft.

[0004] Therefore, it is necessary to improve one or more problems existing in the above-mentioned related technical solutions.

[0005] It should be noted that this section is intended to provide background or context for the technical solutions of the present invention stated in the claims. The description herein is not admitted to be prior art by inclusion in this section. Summary of the invention

[0006] The object of the present invention is to provide a method for detecting the attitude state of a spacecraft based on constructing an attitude regression model, thereby solving one or more problems caused by the limitations and defects of the relevant technology at least to a certain extent.

[0007] The present invention provides a method for detecting the attitude state of a spacecraft based on constructing an attitude regression model, comprising: Determine the attitude control actuator and attitude control measurement unit of the spacecraft, and obtain the corresponding parameters to be tested and historical parameters; Taking the historical parameters of the attitude control actuator as input and the historical parameters of the attitude control measurement unit as output, generating aggregate data through normalization processing; Splitting part of the set data as a training set and training according to a decision tree model, then splitting another part of the set data as a test set to verify the training result, and using the trained decision tree model as an attitude regression model corresponding to the spacecraft; Taking the parameters to be detected of the attitude control actuator as input and the parameters to be detected of the attitude control measurement unit as output, and generating the data to be detected through normalization processing; Substitute the data to be detected into the attitude regression model and detect the attitude state of the spacecraft.

[0008] Optionally, the step of taking the historical parameters of the attitude control actuator as input and the historical parameters of the attitude control measurement unit as output, and generating the set data through normalization processing includes: The input historical parameters and the output historical parameters are used as sample data in a one-to-one correspondence. The data is eliminated according to the sample standard deviation and the sample mean. The sample data after elimination is normalized to generate set data.

[0009] Optionally, the step of splitting part of the set data as a training set and training according to a decision tree model includes: The loss function is defined by the mean square error, and the training data is updated according to the gradient of the loss function. The updated training data is substituted into the decision tree model for training, where the mean value of the sample is used as the initial value.

[0010] Optionally, the step of splitting another part of the set data as a test set to verify the training result includes: The test set is used to evaluate the model accuracy of the trained decision tree model and calculate the determination coefficient of the decision tree model; if the determination coefficient is less than a preset threshold, retraining is performed; if the determination coefficient is greater than or equal to the preset threshold, the trained decision tree model is used as the attitude regression model corresponding to the spacecraft.

[0011] Optionally, the step of splitting part of the set data as a training set and training according to a decision tree model, and then using another part of the set data as a test set to verify the training result, and using the trained decision tree model as the attitude regression model corresponding to the spacecraft includes: The set data is split into the training set and the test set in a ratio of 7:3.

[0012] Optionally, the step of splitting part of the set data as a training set and training according to a decision tree model, and then using another part of the set data as a test set to verify the training result, and using the trained decision tree model as the attitude regression model corresponding to the spacecraft includes: Splitting the set data into the training set, the test set and the validation set in a ratio of 6:2:2; In the training based on the decision tree model, each time the training is completed, the loss function threshold is verified according to the verification set, and the training is completed when the loss function is less than the verification threshold.

[0013] Optionally, the step of substituting the data to be detected into the attitude regression model and detecting the attitude state of the spacecraft includes: Set the detection threshold and detection step size; Inputting the input data of the data to be detected into the posture regression model to generate prediction data; Comparing the output data of the data to be detected with the predicted data; When the comparison result exceeds the detection threshold and meets the detection step length, it is judged as posture abnormality.

[0014] Optionally, the step of substituting the data to be detected into the attitude regression model and detecting the attitude state of the spacecraft includes: If continuous If the points to be detected satisfy the following formula, it is judged as abnormal posture: in, Generate prediction data for the posture regression model The kth component of ; The output data of the data to be detected The kth component of is the characteristic dimension of the output data; is the detection threshold; is the detection step length.

[0015] Optionally, the step of substituting the data to be detected into the attitude regression model and detecting the attitude state of the spacecraft includes: The detection accuracy of the attitude model is evaluated by the data to be detected and the predicted data; the attitude model is a model for controlling the attitude state of the spacecraft.

[0016] Optionally, the step of determining the attitude control actuator and attitude control measurement unit of the spacecraft and obtaining the corresponding parameters to be detected and historical parameters includes: The parameters of the attitude control actuator are at least one of the following: parameters of a reaction flywheel, a magnetic torquer, a thruster, a balance wheel, a track control subsystem, on-board time or an orbit; The parameters of the attitude control measurement unit are at least one of the following: parameters of a thermosensitive meter, a star sensitive meter, a gyroscope or a magnetometer.

[0017] The technical solution provided by the present invention may include the following beneficial effects: In the present invention, by preprocessing the parameters of the spacecraft and constructing an adaptive attitude regression model in a targeted manner, the detection of the attitude state can be applicable to spacecraft using different attitude control actuators and attitude control measurement units; the detection of the attitude state has improved versatility on the basis of high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present invention, and together with the specification are used to explain the principles of the present invention. Obviously, the accompanying drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0019] Figure 1 A schematic flow chart showing a method for detecting a spacecraft attitude state based on constructing an attitude regression model in an exemplary embodiment of the present invention; Figure 2 A schematic diagram showing the judgment logic of a method for detecting a spacecraft attitude state based on building an attitude regression model in an exemplary embodiment of the present invention is shown; Figure 3 A schematic diagram showing the results of star-sensing quaternion anomaly detection in an exemplary embodiment of the present invention is shown. DETAILED DESCRIPTION

[0020] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present invention will be more comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0021] In addition, the accompanying drawings are only schematic illustrations of embodiments of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and their repeated descriptions will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities.

[0022] The present invention provides a method for detecting the attitude state of a spacecraft based on constructing an attitude regression model. Figure 1 As shown in , the following steps are included: Step S100: Determine the attitude control actuator and attitude control measurement unit of the spacecraft, and obtain the corresponding parameters to be detected and historical parameters.

[0023] Step S200: taking the historical parameters of the attitude control actuator as input and the historical parameters of the attitude control measurement unit as output, and generating aggregate data through normalization processing.

[0024] Step S300: split part of the set data as a training set and train it according to the decision tree model, then use the split part of the set data as a test set to verify the training result, and use the trained decision tree model as the attitude regression model corresponding to the spacecraft.

[0025] Step S400: taking the parameters to be detected of the attitude control actuator as input and the parameters to be detected of the attitude control measurement unit as output, and generating data to be detected through normalization processing.

[0026] Step S500: Substitute the data to be detected into the attitude regression model and detect the attitude state of the spacecraft.

[0027] It is important to understand that, from the perspective of data analysis, according to the characteristics of actual data, a mathematical model of attitude regression based on a general process is established. Through data-driven training, a model of attitude determination mechanism is fitted, which can provide technical support for spacecraft attitude anomaly detection, and has important practical significance for ensuring the normal operation of spacecraft in orbit.

[0028] It should also be understood that the normalization process of the data to be detected is the same as the processing process of the set data.

[0029] It is also necessary to understand that the parameters to be detected and the historical parameters corresponding to the attitude control measurement unit refer to the relevant measurement values ​​and their incremental values ​​of the attitude control measurement unit.

[0030] It is also necessary to understand that after determining the input data and output data, the input data and output data need to be preprocessed to generate set data. The data preprocessing includes data selection, data culling, data normalization, and training, validation, and test data division.

[0031] It is also important to understand that after the calculation is completed, the input and output parameters are restored to their original ranges. The denormalization method for the input data is ; The processing of output data is similar. Input parameters ,in Represents the telemetry value of the i-th parameter in the input at time t, output sample ,in, Represents the telemetry value of the jth parameter in the output at time t. After the input and output data are inversely normalized, the inversely normalized data (that is, the data restored to the original scale range of the parameter) is compared with the data to be detected to further perform anomaly detection. N, R, M, and T in each sample of this application represent the total number in the corresponding sample.

[0032] By adopting the above-mentioned method for detecting the attitude state of a spacecraft based on constructing an attitude regression model, the spacecraft parameters are preprocessed and an adaptive attitude regression model is specifically constructed, so that the detection of the attitude state can be applicable to spacecraft using different attitude control actuators and attitude control measurement units; the detection of the attitude state has improved versatility on the basis of high accuracy.

[0033] Next, we will refer to Figure 1 to Figure 2 The various steps of the above-mentioned method for detecting the attitude state of a spacecraft based on constructing an attitude regression model in this example embodiment are described in more detail.

[0034] In some embodiments, reference Figure 2 As shown in , step S100 includes: The parameters of the attitude control actuator are at least one of the following: parameters of a reaction flywheel, a magnetic torquer, a thruster, a balance wheel, a track control subsystem, on-board time or an orbit; The parameters of the attitude control measurement unit are at least one of the following: parameters of a thermosensitive meter, a star sensitive meter, a gyroscope or a magnetometer.

[0035] It should be understood that when training and applying the attitude regression model, the main parameters applied to the attitude control actuator, including reaction flywheel, magnetic torquer, thruster, balance wheel, orbit control subsystem, on-board time, orbit and other parameters are used as the input of the attitude regression model; the output of the attitude regression model is the relevant measurement value and its incremental value of the attitude control measurement unit, including the time sensitivity, star sensitivity, gyroscope, magnetometer, etc. The input and output data used to train the attitude regression model should be selected from the data in the normal state. The above input and output parameter types can be adapted and selected according to the actual situation.

[0036] In some embodiments, reference Figure 2 As shown in , step S200 includes: The input historical parameters and the output historical parameters are used as sample data in a one-to-one correspondence. The data is eliminated according to the sample standard deviation and the sample mean. The sample data after elimination is normalized to generate set data.

[0037] It should be understood that the input parameters and output parameters are selected under normal conditions of the spacecraft attitude maneuver; the input parameters ,in Represents the telemetry value of the i-th parameter in the input at time t, output sample ,in Represents the telemetry value of the jth parameter in the output at time t.

[0038] Data de-wilding, using Eliminate the wild, among which is the sample standard deviation, is a positive integer, usually Perform culling, that is, remove the Data outside the region, is the sample mean, and is padded with the mean of the two points before and after the adjacent area.

[0039] Normalize the input and output data to between [0,1]. The normalization method for input data is: , is the column feature vector of all input samples, For parameters The minimum value of For parameters The maximum value of the output data is processed in a similar way. After the calculation is completed, it is restored to the original range. The inverse normalization method of the input data is ; The processing of output data is similar. is the row feature vector of all input samples, max( )for The maximum value, min( )for The minimum value of .

[0040] In some embodiments, reference Figure 2 As shown in , step S300 includes: The loss function is defined by the mean square error, and the training data is updated according to the gradient of the loss function. The updated training data is substituted into the decision tree model for training, where the mean value of the sample is used as the initial value.

[0041] It is important to understand that for the training set samples ,The posture regression model construction process is as follows: (1) Initialize weak learners , For the prediction sample The mean of .

[0042] (2) For sample i, the loss function of the posture regression model on sample i is defined as , is the predicted value of the posture regression model in sample i, is the true value of the training set samples.

[0043] (3) Obtain new training data based on the gradient of the loss function , and use the new training data to get the decision tree model .

[0044] (4) Update the decision tree model to obtain , where the parameters Indicates the strength of decision tree model update. The calculation formula is: .in, The initial value of the decision tree model update strength. Specifically, it can be =0.01.

[0045] (5) Repeat the above steps (3) and (4) to obtain the decision tree model update formula The decision tree The training data is ;in, .

[0046] The depth m of the gradient boosting decision tree is selected, that is, m decision trees are used in the decision tree model. The decision tree model can be expressed as: The loss function is defined as mean square error: .

[0047] An initial posture regression model and parameters of the posture regression model are obtained.

[0048] In some embodiments, reference Figure 2 As shown in , step S300 includes: The test set is used to evaluate the model accuracy of the trained decision tree model and calculate the determination coefficient of the decision tree model; if the determination coefficient is less than a preset threshold, retraining is performed; if the determination coefficient is greater than or equal to the preset threshold, the trained decision tree model is used as the attitude regression model corresponding to the spacecraft.

[0049] It should be understood that the model obtained after training the decision tree model is a pending posture regression model. It is necessary to introduce test data for testing, calculate the error between the output value of the test data and the predicted value of the pending posture regression model, and if the mean value of the loss function L of all test data is greater than or equal to the threshold (for example, the threshold is equal to 0.001), the output is the final posture regression model, and the loss function L value of the posture regression model for each test sample is counted; otherwise, return to retraining. If the determination coefficient is greater than or equal to the preset threshold, the posture regression model and the parameters of the posture regression model are output. The posture regression model parameters, weights, thresholds and other data are stored for detection applications.

[0050] In some embodiments, reference Figure 2 As shown in , step S300 includes: The set data is split into the training set and the test set in a ratio of 7:3.

[0051] It should be understood that the processed data is split into training sets in a ratio of 7:3. and test set , where the training data is used to train the posture regression model, and the test data is used to verify the accuracy of the posture regression model.

[0052] In some embodiments, reference Figure 2 As shown in , step S300 includes: The set data is split into the training set, the test set and the validation set in a ratio of 6:2:2.

[0053] In the training based on the decision tree model, each time the training is completed, the loss function threshold is verified according to the verification set, and the training is completed when the loss function is less than the verification threshold.

[0054] It is important to understand that the processed set data is split into training data , Verify data And test data , T, D, and R are the number of samples of three categories, respectively, and the ratio is 6:2:2, and M=T+D+R. The training data is used to train the posture regression model, the validation data is used to prevent overfitting, and the test data is used to verify the accuracy of the posture regression model.

[0055] After each training with training data, verification data is used for verification. If the value of the loss function L is less than the threshold (for example, 0.001), in order to prevent overfitting, the algorithm iteration is terminated, and the trained network is the pending posture regression model; at the same time, the maximum number of iterations is set to 100 times. When the maximum number is reached, the iteration is also terminated, and the pending posture regression model is output.

[0056] In some embodiments, reference Figure 2 As shown in , step S500 includes: Set the detection threshold and detection step size.

[0057] The input data of the data to be detected is input into the posture regression model to generate prediction data.

[0058] The output data of the data to be detected is compared with the predicted data.

[0059] When the comparison result exceeds the detection threshold and meets the detection step length, it is judged as posture abnormality.

[0060] It should be understood that the detection rule setting is based on the output loss function L value set , set the detection threshold = 0.001 and detection step size , i.e. continuous The number of points to be detected exceeds the threshold It is judged as abnormal; in order to improve the detection sensitivity, Get Collection The upper quartile of .

[0061] In some embodiments, reference Figure 2 As shown in , step S500 includes: If continuous If the points to be detected satisfy the following formula, it is judged as abnormal posture: in, Generate prediction data for the posture regression model The kth component of ; The output data of the data to be detected The kth component of is the characteristic dimension of the output data; is the detection threshold; is the detection step length.

[0062] It should be understood that the predicted data generated by the posture regression model is the data after the output data is inversely normalized, that is, the data restored to the original scale range of the parameters after the posture regression model is generated. Substitute the input data of the data to be detected into the above formula one by one for calculation. If the continuous If the points to be detected satisfy the above formula, it is judged to be abnormal posture.

[0063] In some embodiments, reference Figure 2 As shown in , step S500 includes: The detection accuracy of the attitude model is evaluated by the data to be detected and the predicted data; the attitude model is a model for controlling the attitude state of the spacecraft.

[0064] It is important to understand that the detection accuracy is evaluated. , is the total number of sequences, and the output sequence of the posture regression model is , the following calculation formula is used to evaluate the accuracy of the pose model detection: in, for The mean of the j-th component. The value range is 0~1. The better the pose model is, the larger the value is. It should be understood that the output sequence of the pose regression model is also the data after the data is inverse normalized.

[0065] Combination Figure 3 The above embodiments will be described below by means of specific examples.

[0066] Step 1: Determine the input and output parameters of the attitude regression model. When training and applying the attitude regression model, the parameters applied to the attitude control actuator, including reaction flywheel, magnetic torquer, thruster, balance wheel, orbit control subsystem, on-board time, orbit, etc., are mainly used as the input of the attitude regression model; the output of the attitude regression model is the relevant measurement values ​​and their incremental values ​​of the attitude control measurement unit, including the time sensitivity, star sensitivity, gyroscope, magnetometer, etc. Step 2: Divide the given set data into input samples , output sample , M and N are the corresponding sample numbers.

[0067] Step 3: Preprocess the input and output parameters, including data culling, normalization, data alignment and padding; Step 4: Data pruning, using Eliminate the wild, among which is the sample standard deviation, is a positive integer, using Perform culling, that is, remove the Data outside the region, is the sample mean, and is filled with the mean of the two points before and after the adjacent area; Step 5: Normalization processing, normalize the data to between [0,1]. The normalization method of input data is , is the column feature vector of all input samples in step 1; after calculation, it is restored to the original range. The inverse normalization method of the input data is ; The processing of output data is similar; Step 6: Data alignment and filling: align the data by time point in units of days. In addition, delete the time points with large sparseness in the data, and fill the small sparseness with sliding average; Step 7: Split the processed data into training data , Verify data And test data , T, D, and R are the number of samples of three categories, respectively, and the ratio is 6:2:2, and M=T+D+R. The training data is used to train the posture regression model, the validation data is used to prevent overfitting, and the test data is used to verify the accuracy of the posture regression model; Step 8: Select the random forest algorithm to build an initial posture regression model; Step 9: using the training data to train the initial posture regression model to obtain the trained initial posture regression model, and verifying the trained posture regression model using the verification data to obtain a posture regression model verification index (determination coefficient); Step 10: If the determination coefficient is greater than the threshold, output the posture regression model and loss function L; Step 11: Prepare the data to be tested. According to steps 1 to 6, prepare the input and output of the data to be tested. Step 12: Import the posture regression model, import the posture regression model output in step 10; Step 13: Detection rule setting, based on the loss function L value set output in step 10 , set the detection threshold = 0.001 and detection step size , i.e. continuous The number of points to be detected exceeds the threshold It is judged as abnormal; in order to improve the detection sensitivity, Get Collection The upper quartile of Step 14: Bring the input of the data to be detected into the posture regression model one by one for calculation. If the points to be detected satisfy the following formula, it is judged as abnormal posture: In the above formula, , are respectively the predicted value vectors of the posture regression model , the true value vector of the data to be tested The weight, is the feature dimension of the output data.

[0068] Step 15: Detection accuracy evaluation. For the sequence to be detected , is the total number of sequences, and the output sequence of the posture regression model is , the following calculation formula is used to evaluate the accuracy of the pose model detection: for The mean of the j-th component. The value range is 0~1. The better the model effect, the larger the value.

[0069] refer to Figure 3 As shown, Figure 3 The yellow line in the middle is the real value of telemetry, the green line is the predicted value of the attitude regression model, and the orange dotted arrow is the abnormal moment detected by the attitude regression model. It can be seen that at the abnormal moment detected in the figure, the real curve deviates significantly, and the real fault case verifies the accuracy of the detection method.

[0070] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification.

[0071] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the appended claims.

Claims

1. A method for detecting the attitude state of a spacecraft based on constructing an attitude regression model, characterized in that: include: Determine the attitude control actuator and attitude control measurement unit of the spacecraft, and obtain the corresponding parameters to be tested and historical parameters; Taking the historical parameters of the attitude control actuator as input and the historical parameters of the attitude control measurement unit as output, generating aggregate data through normalization processing; Splitting part of the set data as a training set and training according to a decision tree model, then splitting another part of the set data as a test set to verify the training result, and using the trained decision tree model as an attitude regression model corresponding to the spacecraft; Taking the parameters to be detected of the attitude control actuator as input and the parameters to be detected of the attitude control measurement unit as output, and generating the data to be detected through normalization processing; Substitute the data to be detected into the attitude regression model and detect the attitude state of the spacecraft.

2. The method for detecting the attitude state of a spacecraft based on constructing an attitude regression model according to claim 1, characterized in that: The step of taking the historical parameters of the attitude control actuator as input and the historical parameters of the attitude control measurement unit as output, and generating the set data through normalization processing comprises: The input historical parameters and the output historical parameters are used as sample data in a one-to-one correspondence. The data is eliminated according to the sample standard deviation and the sample mean. The sample data after elimination is normalized to generate set data.

3. The method for detecting the attitude state of a spacecraft based on constructing an attitude regression model according to claim 2, characterized in that: The step of splitting part of the set data as a training set and training according to the decision tree model comprises: The loss function is defined by the mean square error, and the training data is updated according to the gradient of the loss function. The updated training data is substituted into the decision tree model for training, where the mean value of the sample is used as the initial value.

4. The method for detecting the attitude state of a spacecraft based on constructing an attitude regression model according to claim 3, characterized in that: The step of splitting another part of the set data as a test set to verify the training result comprises: The test set is used to evaluate the model accuracy of the trained decision tree model and calculate the determination coefficient of the decision tree model; if the determination coefficient is less than a preset threshold, retraining is performed; if the determination coefficient is greater than or equal to the preset threshold, the trained decision tree model is used as the attitude regression model corresponding to the spacecraft.

5. The method for detecting the attitude state of a spacecraft based on constructing an attitude regression model according to claim 4, characterized in that: The steps of splitting part of the data of the set data as a training set and training according to a decision tree model, and then using another part of the data of the set data as a test set to verify the training result, and using the trained decision tree model as the attitude regression model corresponding to the spacecraft include: The set data is split into the training set and the test set in a ratio of 7:

3.

6. The method for detecting the attitude state of a spacecraft based on constructing an attitude regression model according to claim 4, characterized in that: The steps of splitting part of the data of the set data as a training set and training according to a decision tree model, and then using another part of the data of the set data as a test set to verify the training result, and using the trained decision tree model as the attitude regression model corresponding to the spacecraft include: Splitting the set data into the training set, the test set and the validation set in a ratio of 6:2:2; In the training based on the decision tree model, each time the training is completed, the loss function threshold is verified according to the verification set, and the training is completed when the loss function is less than the verification threshold.

7. The method for detecting the attitude state of a spacecraft based on constructing an attitude regression model according to claim 1, characterized in that: The step of substituting the data to be detected into the attitude regression model and detecting the attitude state of the spacecraft comprises: Set the detection threshold and detection step size; Inputting the input data of the data to be detected into the posture regression model to generate prediction data; Comparing the output data of the data to be detected with the predicted data; When the comparison result exceeds the detection threshold and meets the detection step length, it is judged as posture abnormality.

8. The method for detecting the attitude state of a spacecraft based on constructing an attitude regression model according to claim 7, characterized in that: The step of substituting the data to be detected into the attitude regression model and detecting the attitude state of the spacecraft comprises: If continuous If the points to be detected satisfy the following formula, it is judged as abnormal posture: in, Generate prediction data for the posture regression model The kth component of ; The output data of the data to be detected The kth component of is the characteristic dimension of the output data; is the detection threshold; is the detection step length.

9. The method for detecting the attitude state of a spacecraft based on constructing an attitude regression model according to claim 8, characterized in that: The step of substituting the data to be detected into the attitude regression model and detecting the attitude state of the spacecraft comprises: The detection accuracy of the attitude model is evaluated by the data to be detected and the predicted data; the attitude model is a model for controlling the attitude state of the spacecraft.

10. The method for detecting the attitude state of a spacecraft based on constructing an attitude regression model according to any one of claims 1 to 9, characterized in that: The steps of determining the attitude control actuator and attitude control measurement unit of the spacecraft and obtaining the corresponding parameters to be detected and historical parameters include: The parameters of the attitude control actuator are at least one of the following: parameters of a reaction flywheel, a magnetic torquer, a thruster, a balance wheel, a track control subsystem, on-board time or an orbit; The parameters of the attitude control measurement unit are at least one of the following: parameters of a thermosensitive meter, a star sensitive meter, a gyroscope or a magnetometer.

Citation Information

Patent Citations

  • Attitude and orbit control data analysis method based on decision tree

    CN105573329A

  • Construction method of attitude determination regression model based on deep neural network

    CN115563571A

  • Abnormal positioning method and device for spacecraft attitude control system

    CN115617023A

  • Machining posture operation optimization method and system based on numerical control machining and medium

    CN117095247A

  • Space reconstruction based method for predicting key performance parameters of transition state acceleration process of aircraft engine

    WO2020000248A1