CN117170294A - Intelligent control method of satellite thermal control system based on space thermal environment prediction - Google Patents
Intelligent control method of satellite thermal control system based on space thermal environment prediction Download PDFInfo
- Publication number
- CN117170294A CN117170294A CN202311442494.4A CN202311442494A CN117170294A CN 117170294 A CN117170294 A CN 117170294A CN 202311442494 A CN202311442494 A CN 202311442494A CN 117170294 A CN117170294 A CN 117170294A
- Authority
- CN
- China
- Prior art keywords
- control parameter
- thermal environment
- historical
- target
- prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000004458 analytical method Methods 0.000 claims abstract description 47
- 238000004364 calculation method Methods 0.000 claims description 29
- 238000005457 optimization Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 10
- 238000012804 iterative process Methods 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims description 2
- 238000013075 data extraction Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 4
- 238000000605 extraction Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005486 microgravity Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Feedback Control In General (AREA)
Abstract
The disclosure provides an intelligent control method of a satellite thermal control system based on space thermal environment prediction, which relates to the technical field of thermal control system control, and comprises the following steps: collecting space thermal environment data and generating a historical thermal environment data set; constructing a thermal environment prediction network layer; carrying out working condition deviation analysis on the historical thermal environment data set to generate a plurality of control parameter deviation factors; data acquisition is carried out on the space thermal environment condition of the target satellite at the current moment, and target thermal environment data are generated; analyzing and predicting the target thermal environment data to generate a target working condition; optimizing control parameters to generate a target control parameter set; and the satellite thermal control system of the target satellite is intelligently controlled. According to the method and the device, the technical problem that in the prior art, the control efficiency of the satellite thermal control system is low due to low prediction accuracy of the satellite space thermal environment can be solved, the aim of improving the prediction accuracy of the space thermal environment is achieved, and the technical effect of improving the control efficiency of the thermal control system is achieved.
Description
Technical Field
The disclosure relates to the technical field of thermal control system control, in particular to an intelligent control method of a satellite thermal control system based on space thermal environment prediction.
Background
The space environment where the satellite is located is extremely complex and is influenced by vacuum environment, thermal environment, microgravity, space radiation and the like. The space thermal environment of the satellite is difficult to predict, firstly, the temperature difference is large, the temperature difference can reach 200 ℃, and the temperature difference is changed rapidly, so that a method is needed for thermal control in order to ensure that the satellite equipment is in a good working environment. However, in the prior art, the control efficiency of the satellite thermal control system is low due to the low prediction accuracy of the satellite space thermal environment.
Disclosure of Invention
The disclosure provides an intelligent control method of a satellite thermal control system based on space thermal environment prediction, which is used for solving the technical problem of low control efficiency of the satellite thermal control system caused by low accuracy of satellite space thermal environment prediction in the prior art.
According to a first aspect of the present disclosure, there is provided a satellite thermal control system intelligent control method based on spatial thermal environment prediction, including: collecting space thermal environment data of a target satellite in a preset history window, and generating a history thermal environment data set; performing feature analysis based on the historical thermal environment data set, and constructing a thermal environment prediction network layer; generating a plurality of control parameter deviation factors by carrying out working condition deviation analysis on a historical thermal environment data set, wherein the control parameter deviation factors correspond to a plurality of control parameters of a satellite thermal control system, each control parameter deviation factor has a direction mark, and the direction mark comprises a positive mark and a negative mark; the method comprises the steps that data acquisition is carried out on the space thermal environment condition of a target satellite at the current moment through an inversion environment parameter acquisition module, and target thermal environment data are generated; analyzing and predicting the target thermal environment data based on the thermal environment prediction network layer to generate a target working condition; performing control parameter optimization based on the target working condition, a plurality of current control parameters and a plurality of control parameter deviation factors to generate a target control parameter set, wherein the target control parameter set comprises a plurality of target control parameters; and utilizing the target control parameter set to intelligently control a satellite thermal control system of the target satellite.
According to a second aspect of the present disclosure, there is provided a satellite thermal control system intelligent control system based on spatial thermal environment prediction, comprising: the historical thermal environment data set acquisition module is used for acquiring the spatial thermal environment data of the target satellite in a preset historical window and generating a historical thermal environment data set; the thermal environment prediction network layer obtaining module is used for carrying out characteristic analysis based on the historical thermal environment data set to construct a thermal environment prediction network layer; the system comprises a plurality of control parameter deviation factor obtaining modules, a plurality of control parameter deviation factor determining module and a control parameter deviation factor determining module, wherein the plurality of control parameter deviation factor obtaining modules are used for generating a plurality of control parameter deviation factors through working condition deviation analysis on a historical thermal environment data set, the plurality of control parameter deviation factors correspond to a plurality of control parameters of a satellite thermal control system, each control parameter deviation factor has a direction mark, and the direction mark comprises a positive mark and a negative mark; the target thermal environment data acquisition module is used for acquiring data of the space thermal environment condition of the target satellite at the current moment through the inversion environment parameter acquisition module to generate target thermal environment data; the target working condition obtaining module is used for analyzing and predicting the target thermal environment data based on the thermal environment prediction network layer to generate a target working condition; the target control parameter set obtaining module is used for carrying out control parameter optimization based on the target working condition, a plurality of current control parameters and a plurality of control parameter deviation factors to generate a target control parameter set, wherein the target control parameter set comprises a plurality of target control parameters; and the intelligent control module is used for intelligently controlling the satellite thermal control system of the target satellite by utilizing the target control parameter set.
One or more technical solutions provided in the present disclosure have at least the following technical effects or advantages: according to the method, a historical thermal environment data set is generated by collecting the spatial thermal environment data of a target satellite in a preset historical window; performing feature analysis based on the historical thermal environment data set, and constructing a thermal environment prediction network layer; generating a plurality of control parameter deviation factors by carrying out working condition deviation analysis on a historical thermal environment data set, wherein the control parameter deviation factors correspond to a plurality of control parameters of a satellite thermal control system, each control parameter deviation factor has a direction mark, and the direction mark comprises a positive mark and a negative mark; the method comprises the steps that data acquisition is carried out on the space thermal environment condition of a target satellite at the current moment through an inversion environment parameter acquisition module, and target thermal environment data are generated; analyzing and predicting the target thermal environment data based on the thermal environment prediction network layer to generate a target working condition; performing control parameter optimization based on the target working condition, a plurality of current control parameters and a plurality of control parameter deviation factors to generate a target control parameter set, wherein the target control parameter set comprises a plurality of target control parameters; the satellite thermal control system of the target satellite is intelligently controlled by utilizing the target control parameter set, so that the technical problem of low control efficiency of the satellite thermal control system due to low prediction accuracy of the satellite space thermal environment in the prior art is solved, the target of improving the prediction accuracy of the space thermal environment is realized, and the technical effect of improving the control efficiency of the thermal control system is achieved.
It should be understood that the description of this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
For a clearer description of the present disclosure or of the prior art, the drawings used in the description of the embodiments or of the prior art will be briefly described, it being obvious that the drawings in the description below are only exemplary and that other drawings may be obtained, without inventive effort, by a person skilled in the art, from the provided drawings.
Fig. 1 is a schematic flow chart of an intelligent control method of a satellite thermal control system based on spatial thermal environment prediction according to an embodiment of the disclosure;
FIG. 2 is a schematic flow chart of generating a plurality of control parameter deviation factors in an intelligent control method of a satellite thermal control system based on spatial thermal environment prediction according to an embodiment of the disclosure;
fig. 3 is a schematic structural diagram of an intelligent control system of a satellite thermal control system based on spatial thermal environment prediction according to an embodiment of the disclosure.
Reference numerals illustrate: the system comprises a historical thermal environment data set obtaining module 11, a thermal environment prediction network layer obtaining module 12, a plurality of control parameter deviation factor obtaining modules 13, a target thermal environment data obtaining module 14, a target working condition obtaining module 15, a target control parameter set obtaining module 16 and an intelligent control module 17.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Example 1
The method for intelligently controlling a satellite thermal control system based on spatial thermal environment prediction according to the embodiment of the present disclosure is described with reference to fig. 1 and fig. 2, and the method includes:
the method provided by the embodiment of the disclosure comprises the following steps:
collecting space thermal environment data of a target satellite in a preset history window, and generating a history thermal environment data set;
specifically, the target satellite is a satellite to be intelligently controlled by the thermal control system. The preset history window is an intelligent control window of the thermal control system in a preset history time period. And collecting the space thermal environment data according to a preset history window, and generating a history thermal environment data set. Wherein the historical thermal environment data set includes, but is not limited to, thermal radiation from the satellite surface, and the like.
Performing feature analysis based on the historical thermal environment data set, and constructing a thermal environment prediction network layer;
specifically, feature extraction is performed according to a historical thermal environment data set, and a plurality of environment feature value sets are generated. And sequentially storing the historical thermal environment data sets into the prediction nodes, and identifying the prediction nodes by the corresponding plurality of environment characteristic value sets. And carrying out feature extraction on the historical thermal environment data set in the prediction node, and carrying out feature extraction on the historical thermal environment data set respectively to carry out similarity analysis, so as to generate a plurality of similarities. And adding the plurality of environment characteristic value sets into a plurality of prediction storage libraries according to the plurality of similarities, carrying out mean processing on the plurality of environment characteristic value sets, identifying a plurality of corresponding prediction nodes, and carrying out thermal environment prediction network layer construction according to the identified plurality of prediction nodes and the corresponding plurality of prediction storage libraries.
Generating a plurality of control parameter deviation factors by carrying out working condition deviation analysis on a historical thermal environment data set, wherein the control parameter deviation factors correspond to a plurality of control parameters of a satellite thermal control system, each control parameter deviation factor has a direction mark, and the direction mark comprises a positive mark and a negative mark;
Specifically, dense factors are obtained through dense analysis of a historical thermal environment data set, working condition deviation analysis is conducted on the dense factors, and a plurality of control parameter deviation factors are generated, wherein the plurality of control parameter deviation factors correspond to a plurality of control parameters of a satellite thermal control system, each control parameter deviation factor has a direction identifier, and the direction identifier comprises a positive identifier and a negative identifier. The positive marks indicate that the corresponding control parameter is larger than the normal control parameter value, and the satellite attitude can meet the space thermal environment requirement at the moment, and the negative marks indicate that the corresponding control parameter is smaller than the normal control parameter value.
The method comprises the steps that data acquisition is carried out on the space thermal environment condition of a target satellite at the current moment through an inversion environment parameter acquisition module, and target thermal environment data are generated;
specifically, the inversion environment parameter acquisition module is used for acquiring data of the space thermal environment condition of the target satellite at the current moment to generate target thermal environment data. The inversion environment parameter acquisition module is used for acquiring space thermal environment data of satellites and inverting the satellite thermal environment data through the orbit data and the satellite-borne accelerometer. For example, due to the action of atmospheric resistance, the actual orbit of the satellite can deviate from the expected orbit to reflect the stress condition of the satellite by utilizing the change of orbit parameters, and the atmospheric density is further inverted according to the resistance coefficient of a specific task.
Analyzing and predicting the target thermal environment data based on the thermal environment prediction network layer to generate a target working condition;
specifically, the collected target thermal environment data is input into a thermal environment prediction network layer, the target thermal environment data is analyzed and predicted based on the thermal environment prediction network layer, and the target working condition is output and generated.
Performing control parameter optimization based on the target working condition, a plurality of current control parameters and a plurality of control parameter deviation factors to generate a target control parameter set, wherein the target control parameter set comprises a plurality of target control parameters;
and utilizing the target control parameter set to intelligently control a satellite thermal control system of the target satellite.
Specifically, a step length is obtained for a plurality of current control parameters aiming at approaching a target working condition, a plurality of control parameter deviation factors are combined with the obtained step length, control parameter optimization is carried out, and a target control parameter set is generated, wherein the target control parameter set comprises a plurality of target control parameters. Further, the satellite thermal control system of the target satellite is intelligently controlled according to the target control parameter set.
The technical problem that in the prior art, the control efficiency of the satellite thermal control system is low due to low prediction accuracy of the satellite space thermal environment can be solved, the aim of improving the prediction accuracy of the space thermal environment is achieved, and the technical effect of improving the control efficiency of the thermal control system is achieved.
The method provided by the embodiment of the disclosure further comprises the following steps:
extracting features of the historical thermal environment data set to generate a plurality of environment feature value sets;
randomly selecting a first historical thermal environment data set from the historical thermal environment data sets, storing the first historical thermal environment data set to a first prediction node, and identifying the first prediction node by a first environment characteristic value set corresponding to the first historical thermal environment data set;
and traversing a plurality of environment characteristic value sets of the historical thermal environment data set and a first environment characteristic value set of the first prediction node to perform characteristic similarity analysis, generating a plurality of first characteristic similarities, judging whether the plurality of first characteristic similarities meet preset characteristic similarities, if yes, adding the first characteristic similarities into a first prediction storage library corresponding to the first prediction node, and if not, adding the first characteristic similarities into the first prediction set, wherein the first prediction storage library is a database for storing the historical thermal environment data, of which the similarity with the first prediction node meets the requirement, in the historical thermal environment data set.
In particular, features of the spatial thermal environment data are acquired. Such as density, temperature, and composition, etc. And extracting features of the historical thermal environment data set to generate a plurality of environment feature value sets. The plurality of environment characteristic value sets are parameter value results of characteristic extraction.
Further, a first historical thermal environment dataset is randomly selected from the historical thermal environment datasets. The first historical thermal environment data set is provided with a plurality of corresponding features in feature extraction, and an environment feature value set corresponding to the first historical thermal environment data set is obtained as a first environment feature value set according to the plurality of features extracted by the features. Further, a first historical thermal environment data set is stored to the first prediction node, and the first environmental feature set identifies the first prediction node based on the features. For example, the identification process assigns a value to the first historical thermal environment data set.
Further, a plurality of environment feature value sets of the historical thermal environment data set are sequentially accessed, feature similarity analysis is conducted on the plurality of environment feature value sets and the first environment feature value set of the first prediction node, and a plurality of first feature similarities are generated. And according to the plurality of characteristics, respectively calculating cosine values of vector included angles of data in the plurality of environment characteristic value sets and data in the first environment characteristic value set, wherein when the cosine values are smaller, the higher the first characteristic similarity between the corresponding environment characteristic value set and the first environment characteristic value set is, and otherwise, the lower the first characteristic similarity is.
Further, whether the plurality of first feature similarities meet the preset feature similarities is judged, if the plurality of first feature similarities meet the preset feature similarities, the corresponding plurality of environment feature value sets are indicated to be higher in similarity with the first environment feature value sets, and the corresponding plurality of environment feature value sets are added into a first prediction storage library corresponding to the first prediction nodes, wherein the first prediction storage library is a database for storing historical thermal environment data, the similarity between the historical thermal environment data set and the first prediction nodes meets the requirement. And if the plurality of first feature similarities do not meet the preset feature similarities, adding a plurality of corresponding environment feature value sets into the first prediction set. The preset feature similarity is set according to the historical thermal environment data set.
And performing feature analysis on the historical thermal environment data set, and comparing the feature similarity to improve the efficiency of obtaining the predicted network layer.
The method provided by the embodiment of the disclosure further comprises the following steps:
randomly selecting a second historical thermal environment data set from the historical thermal environment data sets, storing the second historical thermal environment data set to a second prediction node, and identifying the second prediction node by a second environment characteristic value set corresponding to the second historical thermal environment data set;
Traversing a plurality of environment characteristic value sets of the first prediction set and a second environment characteristic value set of the second prediction node to perform characteristic similarity analysis, generating a plurality of second characteristic similarities, judging whether the plurality of second characteristic similarities meet preset characteristic similarities, if yes, adding the second characteristic similarities into a second prediction storage library corresponding to the second prediction node, and if not, adding the second characteristic similarities into the second prediction set;
generating N prediction nodes and N prediction storage libraries through multiple feature similarity analysis, respectively carrying out mean value processing on a plurality of environment feature value sets in the N prediction storage libraries, and identifying the N prediction nodes according to processing results to generate N identification feature value sets;
and constructing a thermal environment prediction network layer based on the N prediction nodes and the N identification characteristic value sets.
Specifically, a second historical thermal environment data set is randomly selected from the historical thermal environment data sets, and a second environment characteristic value set corresponding to the second historical thermal environment data set is obtained. And storing the second historical thermal environment data set to a second prediction node, and identifying the second prediction node according to each feature by a second environment feature value set corresponding to the second historical thermal environment data set.
Further, a plurality of environment characteristic value sets of the first prediction set are sequentially accessed, characteristic similarity analysis is carried out on the plurality of environment characteristic value sets and a second environment characteristic value set of the second prediction node, and a plurality of second characteristic similarities are generated. And according to the plurality of characteristics, respectively calculating cosine values of vector included angles of data in the plurality of environment characteristic value sets and data in the second environment characteristic value set, wherein when the cosine values are smaller, the second characteristic similarity of the corresponding environment characteristic value set and the second environment characteristic value set is higher, and otherwise, the second characteristic similarity is lower.
Further, whether the plurality of second feature similarities meet the preset feature similarities is judged, if the plurality of second feature similarities meet the preset feature similarities, the corresponding plurality of environment feature value sets are indicated to be higher in similarity with the second environment feature value sets, and the corresponding plurality of environment feature value sets are added into a second prediction storage library corresponding to the second prediction nodes, wherein the second prediction storage library is a database for storing historical thermal environment data, the similarity between the historical thermal environment data set and the second prediction nodes meets the requirement. And if the plurality of second feature similarities do not meet the preset feature similarities, adding a plurality of corresponding environment feature value sets into the second prediction set.
Further, through extracting the historical thermal environment data set for a plurality of times, carrying out a plurality of feature similarity analyses, and respectively generating N prediction nodes and N prediction storage libraries. And respectively carrying out mean processing on a plurality of environment characteristic value sets in each prediction storage library of the N prediction storage libraries to obtain N mean results corresponding to the N prediction storage libraries. N average value result identifications are respectively carried out on N prediction nodes corresponding to the N prediction storage libraries, and N identification characteristic value sets are generated.
Further, according to the corresponding relation between the N prediction nodes and the N identification characteristic value sets, a thermal environment prediction network layer is built in a combined mode.
And performing feature analysis based on the historical thermal environment data set, and constructing a thermal environment prediction network layer by comparing the similarity so as to improve the prediction accuracy of the thermal environment prediction network layer.
The method provided by the embodiment of the disclosure further comprises the following steps:
matching a plurality of history working conditions of the target satellite based on the history thermal environment data set, and obtaining a plurality of history control parameter sets corresponding to the history working conditions, wherein each history control parameter set comprises a plurality of history control parameter sets;
performing dense analysis on the plurality of historical control parameter sets of the plurality of historical working conditions respectively to generate a plurality of control parameter dense data sets;
Taking the control parameter type as an index, and carrying out data extraction on the plurality of control parameter intensive data sets to obtain a plurality of control parameter data sets;
and respectively carrying out mode calculation on the plurality of control parameter data sets, comparing the difference value between the calculation result and the median value of the corresponding control parameter threshold value with the corresponding control parameter threshold value, and generating a plurality of control parameter deviation factors according to the calculation result.
Specifically, satellite working condition retrieval is performed based on big data, and a working condition set is obtained. And obtaining a plurality of historical working conditions of the target satellite in the working condition set based on the matching of the historical thermal environment data set, and performing cluster analysis on the plurality of historical working conditions to obtain a cluster analysis result. According to the clustering analysis results, unified working conditions conforming to each clustering analysis result are obtained, a plurality of historical thermal environment data conforming to the unified working conditions are determined, and a plurality of historical control parameter sets corresponding to the plurality of historical working conditions are obtained, wherein each historical control parameter set comprises a plurality of historical control parameter sets.
Further, dense analysis is performed on a plurality of historical control parameter sets in a plurality of historical control parameter sets of a plurality of historical working conditions respectively, so that a plurality of dense factors corresponding to the plurality of historical control parameter sets are obtained. The maximum value of the plurality of dense factors is used as a plurality of control parameter dense data sets.
Further, taking the control parameter type as an index, extracting data of the parameter type from the plurality of control parameter intensive data sets to obtain a plurality of control parameter data sets.
Further, mode calculation is performed on the plurality of control parameter data sets, respectively, to obtain a plurality of mode calculation results. And calculating the difference value of the median value of the mode calculation results and the corresponding control parameter threshold value, comparing the difference value with the corresponding control parameter threshold value, and generating a plurality of control parameter deviation factors according to the comparison calculation result. And obtaining the positive and negative of the deviation factors of the control parameters according to the positive and negative of the difference value.
The plurality of control parameter deviation factors are obtained through calculation after the plurality of dense factors are calculated, so that the data accuracy of obtaining the control parameter deviation factors is improved.
The method provided by the embodiment of the disclosure further comprises the following steps:
extracting one history working condition from the plurality of history working conditions, taking the history working condition as a first history working condition, and matching a first history control parameter set;
average value calculation is carried out on a plurality of historical control parameters in the first historical control parameter set, and average values of the plurality of historical control parameters are obtained;
respectively calculating the distance between the first historical control parameter set and the average value of the plurality of historical control parameters, and carrying out weighted calculation on the calculation result to obtain a plurality of dense factors, wherein each dense factor corresponds to one historical control parameter set in the first historical control parameter set, each historical control parameter set comprises a plurality of historical control parameters, and the dense factors reflect the approaching degree of the historical control parameter set and the average value of the historical control parameters;
Taking a historical control parameter set corresponding to the maximum value in the plurality of dense factors as a first control parameter dense data set;
and obtaining a plurality of dense data sets of the control parameters according to the plurality of historical working conditions and the plurality of historical control parameter sets.
Specifically, one history working condition is randomly extracted from a plurality of history working conditions and used as a first history working condition, and a first history control parameter set is obtained through matching, wherein the first history control parameter set comprises a plurality of history control parameter sets. And carrying out average value calculation on a plurality of historical control parameters of a plurality of historical control parameter sets in the first historical control parameter set to obtain a plurality of historical control parameter average values.
Further, distances of the plurality of history control parameter sets of the first history control parameter set from the plurality of history control parameter means are calculated, respectively, for example, euclidean distances are calculated. And carrying out weighted calculation on the plurality of distance calculation results to obtain a plurality of dense factors, wherein each dense factor corresponds to one historical control parameter set in the first historical control parameter set, each historical control parameter set comprises a plurality of historical control parameters, and the dense factors reflect the approaching degree of the historical control parameter set and the average value of the historical control parameters.
Further, a history control parameter set corresponding to a maximum value of a distance between the history control parameter set and a history control parameter mean value in the plurality of density factors is used as the first control parameter density data set. Further, a plurality of history control parameter sets of a plurality of history working conditions are obtained, and each history control parameter set is provided with
Further, a plurality of history control parameter sets of a plurality of history working conditions are obtained, average value calculation is carried out on a plurality of history control parameters in each history control parameter set, a plurality of history control parameter average values are obtained, distances between the plurality of history control parameter sets and the corresponding plurality of history control parameter average values are calculated respectively, weighting calculation is carried out on average value calculation results, a plurality of density factors are obtained, and a history control parameter set corresponding to the maximum value in the plurality of density factors is extracted to be used as a plurality of control parameter density data sets.
Wherein a plurality of dense data sets of control parameters are generated to improve the accuracy of obtaining the control parameter data.
The method provided by the embodiment of the disclosure further comprises the following steps:
the control parameters of the satellite thermal control system are called at the current moment to obtain a plurality of current control parameters;
performing parameter adjustment step length matching based on the target working condition to obtain a preset parameter adjustment step length;
Multiplying the preset parameter adjustment step length by a plurality of control parameter deviation factors to obtain a plurality of parameter adjustment step lengths, wherein the directions of the plurality of parameter adjustment step lengths are consistent with the directions of the plurality of control parameter deviation factors;
and performing iterative optimization based on the multiple parameter adjustment step sizes and the multiple current control parameters to generate a target control parameter set.
Specifically, the control parameters of the satellite thermal control system are called at the current moment, and a plurality of current control parameters are obtained. And carrying out parameter adjustment step length matching based on the target working condition to obtain a preset parameter adjustment step length. And adjusting the satellite attitude by a preset amplitude under the current space thermal environment, so as to obtain a preset parameter adjustment step length. Further, multiplying the preset parameter adjustment step length by a plurality of corresponding control parameter deviation factors to obtain a plurality of parameter adjustment step lengths, wherein the directions of the plurality of parameter adjustment step lengths are consistent with the directions of the plurality of control parameter deviation factors.
Further, iterative optimization is carried out on a plurality of current control parameters according to a plurality of corresponding parameter adjustment step sizes, so that an optimal solution is approximated gradually, and a target control parameter set is generated. And judging the value of the solution to be updated in each iterative optimization, and if the value of the current solution is poor, adjusting. If the value of the current solution is good, it remains unchanged.
The target control parameter set is generated through optimizing, so that the accuracy of obtaining the data of the target control parameter set is improved.
The method provided by the embodiment of the disclosure further comprises the following steps:
randomly adjusting a plurality of current control parameters for a plurality of times according to the plurality of parameter adjustment step sizes to generate a plurality of control parameter sets to be optimized;
traversing the plurality of control parameter sets to be optimized for fitness analysis to generate a plurality of fitness;
selecting a control parameter set to be optimized corresponding to the maximum value in the plurality of fitness as a stage control parameter set;
randomly adjusting the phase control parameter set according to a plurality of parameter adjustment step sizes to generate a plurality of phase control parameter sets to be optimized;
performing fitness analysis on the plurality of to-be-optimized stage control parameter sets, and selecting a to-be-optimized stage control parameter set corresponding to the maximum fitness value to update the stage control parameter set;
and (3) performing iterative optimization for a plurality of times, and taking a stage control parameter set corresponding to the maximum adaptation value in the iterative process as a target control parameter set.
Specifically, multiple current control parameters are randomly adjusted for multiple times according to multiple parameter adjustment step sizes, and multiple control parameter sets to be optimized are generated. And sequentially accessing a plurality of control parameter sets to be optimized for fitness analysis, and performing fitness training of the plurality of control parameter sets to be optimized through a neural network model to generate a plurality of fitness.
Further, selecting a control parameter set to be optimized corresponding to the maximum value in the plurality of fitness as a stage control parameter set. The selection method is obtained by carrying out serialization processing on a plurality of fitness according to the fitness.
Further, the phase control parameter set is randomly adjusted according to a plurality of parameter adjustment step sizes, and a plurality of phase control parameter sets to be optimized are generated. For example, the phase control parameter set is adjusted by half the step size of the plurality of parameter adjustment steps.
Further, fitness analysis is carried out on the plurality of to-be-optimized stage control parameter sets, fitness training is carried out on the plurality of to-be-optimized stage control parameter sets through a neural network model, and a plurality of stage fitness is generated. And selecting a to-be-optimized stage control parameter set corresponding to the stage fitness maximum value, and updating the stage control parameter set with the aim of meeting the to-be-optimized stage control parameter set. And performing multiple iterative optimization on the phase control parameter set according to multiple parameter adjustment step sizes, wherein the phase control parameter set corresponding to the phase fitness maximum value of the phase control parameter set to be optimized in the iterative process is used as a target control parameter set.
The target control parameter set is acquired to improve the accuracy of satellite control.
Example two
Based on the same inventive concept as the satellite thermal control system intelligent control method based on the spatial thermal environment prediction in the foregoing embodiment, and referring to fig. 3, the disclosure further provides a satellite thermal control system intelligent control system based on the spatial thermal environment prediction, where the system includes:
the historical thermal environment data set obtaining module 11 is used for collecting the spatial thermal environment data of the target satellite in the preset historical window and generating a historical thermal environment data set;
the thermal environment prediction network layer obtaining module 12, where the thermal environment prediction network layer obtaining module 12 is configured to perform feature analysis based on the historical thermal environment dataset to construct a thermal environment prediction network layer;
the system comprises a plurality of control parameter deviation factor obtaining modules 13, wherein the plurality of control parameter deviation factor obtaining modules 13 are used for generating a plurality of control parameter deviation factors by carrying out working condition deviation analysis on a historical thermal environment data set, the plurality of control parameter deviation factors correspond to a plurality of control parameters of a satellite thermal control system, each control parameter deviation factor has a direction mark, and the direction mark comprises a positive mark and a negative mark;
The target thermal environment data acquisition module 14 is used for acquiring data of the space thermal environment condition of the target satellite at the current moment through the inversion environment parameter acquisition module to generate target thermal environment data;
the target working condition obtaining module 15 is used for analyzing and predicting the target thermal environment data based on the thermal environment prediction network layer to generate a target working condition;
a target control parameter set obtaining module 16, where the target control parameter set obtaining module 16 is configured to perform control parameter optimization based on the target working condition, a plurality of current control parameters, and a plurality of control parameter deviation factors, and generate a target control parameter set, where the target control parameter set includes a plurality of target control parameters;
the intelligent control module 17, the intelligent control module 17 is configured to use the target control parameter set to intelligently control the satellite thermal control system of the target satellite.
Further, the system further comprises:
the plurality of environment characteristic value set obtaining modules are used for carrying out characteristic extraction on the historical thermal environment data set to generate a plurality of environment characteristic value sets;
The first historical thermal environment data set selection module is used for randomly selecting a first historical thermal environment data set from the historical thermal environment data set, storing the first historical thermal environment data set to a first prediction node, and identifying the first prediction node by a first environment characteristic value set corresponding to the first historical thermal environment data set;
the system comprises a plurality of first feature similarity obtaining modules, a plurality of first feature similarity obtaining modules and a first prediction node, wherein the plurality of first feature similarity obtaining modules are used for traversing a plurality of environment feature value sets of the historical thermal environment data set and the first environment feature value sets of the first prediction node to conduct feature similarity analysis, generating a plurality of first feature similarities, judging whether the plurality of first feature similarities meet preset feature similarities, if yes, adding the first feature similarities into a first prediction storage library corresponding to the first prediction node, and if not, adding the first prediction storage library into the first prediction set, wherein the first prediction storage library is a database for storing historical thermal environment data, wherein the similarity between the historical thermal environment data set and the first prediction node meets requirements.
Further, the system further comprises:
the second historical thermal environment data set selection module is used for randomly selecting a second historical thermal environment data set from the historical thermal environment data set, storing the second historical thermal environment data set to a second prediction node, and identifying the second prediction node by a second environment characteristic value set corresponding to the second historical thermal environment data set;
The second feature similarity obtaining module is used for traversing the plurality of environment feature value sets of the first prediction set and the second environment feature value set of the second prediction node to conduct feature similarity analysis, generating a plurality of second feature similarities, judging whether the plurality of second feature similarities meet preset feature similarities, if yes, adding the second feature similarities into a second prediction storage library corresponding to the second prediction node, and if not, adding the second feature similarities into the second prediction set;
the N identification characteristic value set obtaining modules are used for generating N prediction nodes and N prediction storage libraries through multiple characteristic similarity analysis, respectively carrying out mean value processing on the environment characteristic value sets in the N prediction storage libraries, and identifying the N prediction nodes according to the processing results to generate N identification characteristic value sets;
the thermal environment prediction network layer construction module is used for constructing a thermal environment prediction network layer based on N prediction nodes and N identification characteristic value sets.
Further, the system further comprises:
the historical control parameter set obtaining modules are used for matching a plurality of historical working conditions of the target satellite based on the historical thermal environment data set and obtaining a plurality of historical control parameter sets corresponding to the plurality of historical working conditions, and each historical control parameter set comprises a plurality of historical control parameter sets;
The system comprises a plurality of control parameter intensive data set acquisition modules, a plurality of control parameter intensive data set generation modules and a control parameter analysis module, wherein the plurality of control parameter intensive data set acquisition modules are used for respectively carrying out intensive analysis on a plurality of historical control parameter sets of a plurality of historical working conditions to generate a plurality of control parameter intensive data sets;
the control parameter data acquisition module is used for taking the control parameter type as an index, and extracting data from the control parameter intensive data sets to acquire a plurality of control parameter data sets;
the control parameter deviation factor obtaining module is used for respectively carrying out mode calculation on the plurality of control parameter data sets, comparing the difference value of the calculation result and the median value of the corresponding control parameter threshold value with the corresponding control parameter threshold value, and generating a plurality of control parameter deviation factors according to the calculation result.
Further, the system further comprises:
the first history working condition extraction module is used for extracting one history working condition from the plurality of history working conditions, serving as a first history working condition and matching a first history control parameter set;
the historical control parameter average value obtaining modules are used for carrying out average value calculation on the historical control parameters in the first historical control parameter set to obtain the historical control parameter average values;
The dense factor obtaining modules are used for respectively calculating the distances between the first historical control parameter set and the average value of the historical control parameters, weighting calculation is carried out on calculation results to obtain a plurality of dense factors, each dense factor corresponds to one historical control parameter set in the first historical control parameter set, each historical control parameter set comprises a plurality of historical control parameters, and the dense factors reflect the approaching degree of the historical control parameter set and the average value of the historical control parameters;
the first control parameter dense data set obtaining module is used for taking a historical control parameter set corresponding to the maximum value in the plurality of dense factors as a first control parameter dense data set;
the system comprises a plurality of control parameter intensive data set obtaining modules, a plurality of control parameter intensive data set obtaining modules and a control parameter intensive data set processing module, wherein the plurality of control parameter intensive data set obtaining modules are used for obtaining a plurality of control parameter intensive data sets according to a plurality of historical working conditions and a plurality of historical control parameter sets.
Further, the system further comprises:
the system comprises a plurality of current control parameter acquisition modules, a plurality of control parameter acquisition modules and a control module, wherein the plurality of current control parameter acquisition modules are used for acquiring control parameters of the satellite thermal control system at the current moment to acquire a plurality of current control parameters;
The preset parameter adjustment step length obtaining module is used for carrying out parameter adjustment step length matching based on the target working condition to obtain a preset parameter adjustment step length;
the parameter adjustment step length obtaining module is used for multiplying the preset parameter adjustment step length and a plurality of control parameter deviation factors to obtain a plurality of parameter adjustment step lengths, wherein the directions of the plurality of parameter adjustment step lengths are consistent with the directions of the plurality of control parameter deviation factors;
the target control parameter set obtaining module is used for carrying out iterative optimization based on the plurality of parameter adjustment step sizes and the plurality of current control parameters to generate a target control parameter set.
Further, the system further comprises:
the system comprises a plurality of control parameter set obtaining modules to be optimized, a plurality of control parameter setting module and a control parameter setting module, wherein the plurality of control parameter set obtaining modules to be optimized are used for carrying out random adjustment on a plurality of current control parameters for a plurality of times according to the plurality of parameter adjustment step sizes to generate a plurality of control parameter sets to be optimized;
the fitness obtaining modules are used for traversing the control parameter sets to be optimized to conduct fitness analysis and generate a plurality of fitness;
The phase control parameter set obtaining module is used for selecting a to-be-optimized control parameter set corresponding to the maximum value in the plurality of fitness as a phase control parameter set;
the system comprises a plurality of phase control parameter set acquisition modules to be optimized, a plurality of phase control parameter set optimization module and a phase control parameter set generation module, wherein the phase control parameter set acquisition modules to be optimized are used for randomly adjusting the phase control parameter set according to a plurality of parameter adjustment step sizes to generate a plurality of phase control parameter sets to be optimized;
the phase control parameter set updating module is used for carrying out adaptability analysis on the plurality of phase control parameter sets to be optimized, and selecting the phase control parameter set to be optimized corresponding to the maximum value of the adaptability to update the phase control parameter set;
the target control parameter set iteration obtaining module is used for selecting and optimizing through multiple iterations, and taking a stage control parameter set corresponding to the maximum adaptability value in the iteration process as a target control parameter set.
The specific example of the satellite thermal control system intelligent control method based on the spatial thermal environment prediction in the first embodiment is also applicable to the satellite thermal control system intelligent control system based on the spatial thermal environment prediction in this embodiment, and by the foregoing detailed description of the satellite thermal control system intelligent control method based on the spatial thermal environment prediction, those skilled in the art can clearly know the satellite thermal control system based on the spatial thermal environment prediction in this embodiment, so that the detailed description will not be repeated herein for the sake of brevity of the specification. The device disclosed in the embodiment corresponds to the method disclosed in the embodiment, so that the description is simpler, and the relevant points refer to the description of the method.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (8)
1. The intelligent control method of the satellite thermal control system based on the space thermal environment prediction is characterized by comprising the following steps:
collecting space thermal environment data of a target satellite in a preset history window, and generating a history thermal environment data set;
performing feature analysis based on the historical thermal environment data set, and constructing a thermal environment prediction network layer;
generating a plurality of control parameter deviation factors by carrying out working condition deviation analysis on a historical thermal environment data set, wherein the control parameter deviation factors correspond to a plurality of control parameters of a satellite thermal control system, each control parameter deviation factor has a direction mark, and the direction mark comprises a positive mark and a negative mark;
The method comprises the steps that data acquisition is carried out on the space thermal environment condition of a target satellite at the current moment through an inversion environment parameter acquisition module, and target thermal environment data are generated;
analyzing and predicting the target thermal environment data based on the thermal environment prediction network layer to generate a target working condition;
performing control parameter optimization based on the target working condition, a plurality of current control parameters and a plurality of control parameter deviation factors to generate a target control parameter set, wherein the target control parameter set comprises a plurality of target control parameters;
and utilizing the target control parameter set to intelligently control a satellite thermal control system of the target satellite.
2. The method of claim 1, wherein the method further comprises:
extracting features of the historical thermal environment data set to generate a plurality of environment feature value sets;
randomly selecting a first historical thermal environment data set from the historical thermal environment data sets, storing the first historical thermal environment data set to a first prediction node, and identifying the first prediction node by a first environment characteristic value set corresponding to the first historical thermal environment data set;
and traversing a plurality of environment characteristic value sets of the historical thermal environment data set and a first environment characteristic value set of the first prediction node to perform characteristic similarity analysis, generating a plurality of first characteristic similarities, judging whether the plurality of first characteristic similarities meet preset characteristic similarities, if yes, adding the first characteristic similarities into a first prediction storage library corresponding to the first prediction node, and if not, adding the first characteristic similarities into the first prediction set, wherein the first prediction storage library is a database for storing the historical thermal environment data, of which the similarity with the first prediction node meets the requirement, in the historical thermal environment data set.
3. The method of claim 2, wherein the method further comprises:
randomly selecting a second historical thermal environment data set from the historical thermal environment data sets, storing the second historical thermal environment data set to a second prediction node, and identifying the second prediction node by a second environment characteristic value set corresponding to the second historical thermal environment data set;
traversing a plurality of environment characteristic value sets of the first prediction set and a second environment characteristic value set of the second prediction node to perform characteristic similarity analysis, generating a plurality of second characteristic similarities, judging whether the plurality of second characteristic similarities meet preset characteristic similarities, if yes, adding the second characteristic similarities into a second prediction storage library corresponding to the second prediction node, and if not, adding the second characteristic similarities into the second prediction set;
generating N prediction nodes and N prediction storage libraries through multiple feature similarity analysis, respectively carrying out mean value processing on a plurality of environment feature value sets in the N prediction storage libraries, and identifying the N prediction nodes according to processing results to generate N identification feature value sets;
and constructing a thermal environment prediction network layer based on the N prediction nodes and the N identification characteristic value sets.
4. The method of claim 1, wherein the method further comprises:
Matching a plurality of history working conditions of the target satellite based on the history thermal environment data set, and obtaining a plurality of history control parameter sets corresponding to the history working conditions, wherein each history control parameter set comprises a plurality of history control parameter sets;
performing dense analysis on the plurality of historical control parameter sets of the plurality of historical working conditions respectively to generate a plurality of control parameter dense data sets;
taking the control parameter type as an index, and carrying out data extraction on the plurality of control parameter intensive data sets to obtain a plurality of control parameter data sets;
and respectively carrying out mode calculation on the plurality of control parameter data sets, comparing the difference value between the calculation result and the median value of the corresponding control parameter threshold value with the corresponding control parameter threshold value, and generating a plurality of control parameter deviation factors according to the calculation result.
5. The method of claim 4, wherein the method further comprises:
extracting one history working condition from the plurality of history working conditions, taking the history working condition as a first history working condition, and matching a first history control parameter set;
average value calculation is carried out on a plurality of historical control parameters in the first historical control parameter set, and average values of the plurality of historical control parameters are obtained;
Respectively calculating the distance between the first historical control parameter set and the average value of the plurality of historical control parameters, and carrying out weighted calculation on the calculation result to obtain a plurality of dense factors, wherein each dense factor corresponds to one historical control parameter set in the first historical control parameter set, each historical control parameter set comprises a plurality of historical control parameters, and the dense factors reflect the approaching degree of the historical control parameter set and the average value of the historical control parameters;
taking a historical control parameter set corresponding to the maximum value in the plurality of dense factors as a first control parameter dense data set;
and obtaining a plurality of dense data sets of the control parameters according to the plurality of historical working conditions and the plurality of historical control parameter sets.
6. The method of claim 1, wherein the method further comprises:
the control parameters of the satellite thermal control system are called at the current moment to obtain a plurality of current control parameters;
performing parameter adjustment step length matching based on the target working condition to obtain a preset parameter adjustment step length;
multiplying the preset parameter adjustment step length by a plurality of control parameter deviation factors to obtain a plurality of parameter adjustment step lengths, wherein the directions of the plurality of parameter adjustment step lengths are consistent with the directions of the plurality of control parameter deviation factors;
And performing iterative optimization based on the multiple parameter adjustment step sizes and the multiple current control parameters to generate a target control parameter set.
7. The method of claim 6, wherein the method further comprises:
randomly adjusting a plurality of current control parameters for a plurality of times according to the plurality of parameter adjustment step sizes to generate a plurality of control parameter sets to be optimized;
traversing the plurality of control parameter sets to be optimized for fitness analysis to generate a plurality of fitness;
selecting a control parameter set to be optimized corresponding to the maximum value in the plurality of fitness as a stage control parameter set;
randomly adjusting the phase control parameter set according to a plurality of parameter adjustment step sizes to generate a plurality of phase control parameter sets to be optimized;
performing fitness analysis on the plurality of to-be-optimized stage control parameter sets, and selecting a to-be-optimized stage control parameter set corresponding to the maximum fitness value to update the stage control parameter set;
and (3) performing iterative optimization for a plurality of times, and taking a stage control parameter set corresponding to the maximum adaptation value in the iterative process as a target control parameter set.
8. A satellite thermal control system intelligent control system based on space thermal environment prediction, which is used for implementing the satellite thermal control system intelligent control method based on space thermal environment prediction according to any one of claims 1-7, wherein the system comprises:
The historical thermal environment data set acquisition module is used for acquiring the spatial thermal environment data of the target satellite in a preset historical window and generating a historical thermal environment data set;
the thermal environment prediction network layer obtaining module is used for carrying out characteristic analysis based on the historical thermal environment data set to construct a thermal environment prediction network layer;
the system comprises a plurality of control parameter deviation factor obtaining modules, a plurality of control parameter deviation factor determining module and a control parameter deviation factor determining module, wherein the plurality of control parameter deviation factor obtaining modules are used for generating a plurality of control parameter deviation factors through working condition deviation analysis on a historical thermal environment data set, the plurality of control parameter deviation factors correspond to a plurality of control parameters of a satellite thermal control system, each control parameter deviation factor has a direction mark, and the direction mark comprises a positive mark and a negative mark;
the target thermal environment data acquisition module is used for acquiring data of the space thermal environment condition of the target satellite at the current moment through the inversion environment parameter acquisition module to generate target thermal environment data;
the target working condition obtaining module is used for analyzing and predicting the target thermal environment data based on the thermal environment prediction network layer to generate a target working condition;
The target control parameter set obtaining module is used for carrying out control parameter optimization based on the target working condition, a plurality of current control parameters and a plurality of control parameter deviation factors to generate a target control parameter set, wherein the target control parameter set comprises a plurality of target control parameters;
and the intelligent control module is used for intelligently controlling the satellite thermal control system of the target satellite by utilizing the target control parameter set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311442494.4A CN117170294B (en) | 2023-11-01 | 2023-11-01 | Intelligent control method of satellite thermal control system based on space thermal environment prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311442494.4A CN117170294B (en) | 2023-11-01 | 2023-11-01 | Intelligent control method of satellite thermal control system based on space thermal environment prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117170294A true CN117170294A (en) | 2023-12-05 |
| CN117170294B CN117170294B (en) | 2024-01-23 |
Family
ID=88941555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311442494.4A Active CN117170294B (en) | 2023-11-01 | 2023-11-01 | Intelligent control method of satellite thermal control system based on space thermal environment prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117170294B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117408572A (en) * | 2023-12-13 | 2024-01-16 | 南通纳科达聚氨酯科技有限公司 | Preparation optimization method and system of electrochromic elastic film |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0958600A (en) * | 1995-08-30 | 1997-03-04 | Nec Corp | Heat control system for artificial satellite |
| JPH11278398A (en) * | 1998-03-31 | 1999-10-12 | Nec Eng Ltd | Heat control system for artificial satellite |
| CN110377941A (en) * | 2019-06-10 | 2019-10-25 | 中国人民解放军军事科学院国防科技创新研究院 | Establish the method for penalizing golden agent model in blind likelihood gram of satellite temperature field |
| CN116595121A (en) * | 2023-07-19 | 2023-08-15 | 北京国遥新天地信息技术股份有限公司 | Data display monitoring system based on remote sensing technology |
| CN116629458A (en) * | 2023-07-24 | 2023-08-22 | 深圳康普盾科技股份有限公司 | Energy storage equipment operation optimization method and system based on data analysis |
-
2023
- 2023-11-01 CN CN202311442494.4A patent/CN117170294B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0958600A (en) * | 1995-08-30 | 1997-03-04 | Nec Corp | Heat control system for artificial satellite |
| JPH11278398A (en) * | 1998-03-31 | 1999-10-12 | Nec Eng Ltd | Heat control system for artificial satellite |
| CN110377941A (en) * | 2019-06-10 | 2019-10-25 | 中国人民解放军军事科学院国防科技创新研究院 | Establish the method for penalizing golden agent model in blind likelihood gram of satellite temperature field |
| CN116595121A (en) * | 2023-07-19 | 2023-08-15 | 北京国遥新天地信息技术股份有限公司 | Data display monitoring system based on remote sensing technology |
| CN116629458A (en) * | 2023-07-24 | 2023-08-22 | 深圳康普盾科技股份有限公司 | Energy storage equipment operation optimization method and system based on data analysis |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117408572A (en) * | 2023-12-13 | 2024-01-16 | 南通纳科达聚氨酯科技有限公司 | Preparation optimization method and system of electrochromic elastic film |
| CN117408572B (en) * | 2023-12-13 | 2024-04-19 | 南通纳科达聚氨酯科技有限公司 | Preparation optimization method and system of electrochromic elastic film |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117170294B (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110390396B (en) | Method, device and system for estimating causal relationship between observed variables | |
| JP6179598B2 (en) | Hierarchical hidden variable model estimation device | |
| Gramacy et al. | Parameter space exploration with Gaussian process trees | |
| CN117170294B (en) | Intelligent control method of satellite thermal control system based on space thermal environment prediction | |
| CN109063355A (en) | Near-optimal method based on particle group optimizing Yu Kriging model | |
| JP6525002B2 (en) | Maintenance time determination apparatus, deterioration prediction system, deterioration prediction method, and recording medium | |
| CN110969290A (en) | Runoff probability prediction method and system based on deep learning | |
| JP6451735B2 (en) | Energy amount estimation device, energy amount estimation method, and energy amount estimation program | |
| CN112417028A (en) | Wind speed time sequence characteristic mining method and short-term wind power prediction method | |
| CN113469426A (en) | Photovoltaic output power prediction method and system based on improved BP neural network | |
| CN115347571A (en) | Photovoltaic power generation power short-term prediction method and device based on transfer learning | |
| CN115906399A (en) | Improved method for predicting key process quality of product under small sample data | |
| CN113609763B (en) | Uncertainty-based satellite component layout temperature field prediction method | |
| CN116881676B (en) | Prediction method for water inflow of open pit | |
| CN116304213B (en) | RDF graph database sub-graph matching query optimization method based on graph neural network | |
| Huang et al. | Designing importance samplers to simulate machine learning predictors via optimization | |
| CN117154704A (en) | Photovoltaic power prediction method based on multiscale space-time diagram attention convolution network | |
| CN116822742A (en) | Power load prediction method based on dynamic decomposition-reconstruction integrated processing | |
| CN115829123A (en) | Natural gas demand prediction method and device based on grey model and neural network | |
| Pavithra et al. | Image matching using weighted graph matching algorithm | |
| CN117253209B (en) | Automatic driving point cloud detection method, device, communication equipment and storage medium | |
| Jain et al. | Simulation Model Calibration with Dynamic Stratification and Adaptive Sampling | |
| CN114428632A (en) | Software architecture recovery method based on self-adaptive grid division clustering | |
| CN117854650A (en) | Polymer material multi-target attribute prediction method based on Gaussian process regression | |
| CN116992315A (en) | Accurate line loss calculation method based on short-term load adjustment scene |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |