CN110703764A - Method for planning optimal position of movable guide star of adaptive optical system in real time - Google Patents
Method for planning optimal position of movable guide star of adaptive optical system in real time Download PDFInfo
- Publication number
- CN110703764A CN110703764A CN201911072944.9A CN201911072944A CN110703764A CN 110703764 A CN110703764 A CN 110703764A CN 201911072944 A CN201911072944 A CN 201911072944A CN 110703764 A CN110703764 A CN 110703764A
- Authority
- CN
- China
- Prior art keywords
- turbulence
- data
- guide star
- movable guide
- optimal position
- 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 27
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 21
- 230000003287 optical effect Effects 0.000 title claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 29
- 238000005457 optimization Methods 0.000 claims abstract description 15
- 238000010801 machine learning Methods 0.000 claims abstract description 10
- 238000000342 Monte Carlo simulation Methods 0.000 claims abstract description 5
- 238000013507 mapping Methods 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 9
- 238000005259 measurement Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 230000002068 genetic effect Effects 0.000 claims description 4
- 238000013041 optical simulation Methods 0.000 claims description 4
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000003064 k means clustering Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 abstract description 10
- 238000009825 accumulation Methods 0.000 abstract description 2
- 238000007621 cluster analysis Methods 0.000 abstract description 2
- 238000002474 experimental method Methods 0.000 description 5
- 238000007476 Maximum Likelihood Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- DGAQECJNVWCQMB-PUAWFVPOSA-M Ilexoside XXIX Chemical compound C[C@@H]1CC[C@@]2(CC[C@@]3(C(=CC[C@H]4[C@]3(CC[C@@H]5[C@@]4(CC[C@@H](C5(C)C)OS(=O)(=O)[O-])C)C)[C@@H]2[C@]1(C)O)C)C(=O)O[C@H]6[C@@H]([C@H]([C@@H]([C@H](O6)CO)O)O)O.[Na+] DGAQECJNVWCQMB-PUAWFVPOSA-M 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- SQNZJJAZBFDUTD-UHFFFAOYSA-N durene Chemical compound CC1=CC(C)=C(C)C=C1C SQNZJJAZBFDUTD-UHFFFAOYSA-N 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 229910052708 sodium Inorganic materials 0.000 description 1
- 239000011734 sodium Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Telescopes (AREA)
- Optical Couplings Of Light Guides (AREA)
Abstract
The invention relates to the field of movable guide star optimal position planning. The method for planning the optimal position of the movable guide star of the adaptive optical system in real time obtains the statistical distribution characteristics of the profile through cluster analysis on the basis of the accumulation of sufficient actually-measured atmospheric turbulence profile data; on the basis of analyzing statistical distribution characteristics, Monte Carlo simulation and optimization algorithms are utilized to obtain the positions of the guide stars corresponding to the profiles of different categories, and further the mapping relation between the profiles of different turbulences and the optimized positions of the movable guide stars is obtained through a machine learning method. The corresponding movable guide star optimal position can be rapidly calculated according to actually measured turbulence data in practical application.
Description
Technical Field
The invention relates to the field of movable guide star optimal position planning.
Background
During the observation of the spatial target, the propagation of the light wave is randomly disturbed by atmospheric turbulence which changes with time, so that the image quality observed by the ground telescope is degraded. The adaptive optics technology can achieve the purpose of improving the imaging quality of the telescope by measuring and correcting disturbance introduced by atmospheric turbulence in real time. However, atmospheric turbulence is extremely non-isoplanatic and the disturbances experienced by closely spaced targets are generally different. For this reason, modern adaptive optics systems often use multiple steering stars to sample turbulence within a certain field of view. However, since the atmospheric turbulence changes continuously with time, the profile of the atmospheric turbulence distributed with different heights also changes with time, and therefore, the calculation of the optimal position of the guide star by combining the atmospheric turbulence profile changing in real time is crucial to further improve the performance of the adaptive optical system.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: according to the mass data of the actually measured atmospheric turbulence profile and the working requirements of the adaptive optical system, how to obtain the optimal movable guide star position distribution aiming at the actually measured turbulence profile.
The technical scheme adopted by the invention is as follows: the method for planning the optimal position of the movable guide star of the adaptive optical system in real time comprises the following steps
Step one, preprocessing acquired mass real turbulence profile data, enabling the turbulence data to be equivalent to different layers, then taking common logarithm for the turbulence data, normalizing the result to an interval [0,1] according to a 0-1 standardized mode, and adding 1 to all turbulence data and then carrying out logarithm taking operation to prevent computing overflow caused by zero-filling data;
step two, clustering the turbulence data processed in the step one, and classifying the turbulence profile data according to a clustering result;
thirdly, simulating a self-adaptive optical system by adopting a Monte Carlo method, and establishing a physical model relation between the atmospheric turbulence profile and the position of the movable guide star in atmospheric optics;
randomly selecting partial data from the turbulence profile data of different types as representative profiles according to actual requirements, taking the performance of the simulated adaptive optical system as a target function under the turbulence profile data of different types, and calculating the optimal position of the guide star by using a related optimization algorithm;
step five, taking the representative profile and the optimal position of the corresponding guide star in the step four as training data, and obtaining a space mapping relation between the turbulent flow profile and the optimal position of the movable guide star by adopting a machine learning method;
and step six, substituting real-time measurement data of the atmospheric turbulence profile into machine learning to quickly give the optimal position of the movable guide star.
The clustering method adopted in the second step is one of Gaussian mixture model GMM, K-Means clustering algorithm K-Means, hierarchical clustering and K nearest neighbor algorithm knn.
In the third step, the self-adaptive optical system adopts GLAO or MCAO, and the movable guide star is selected from a nano laser guide star.
And in the fourth step, after the representative profile is selected, the performance of the adaptive optical simulation system is taken as a target function, the position coordinate of the laser guide star is taken as a target value, the target value is optimized by adopting a relevant optimization algorithm, and finally, the coordinate with high fitness is selected as the optimal position of the laser guide star.
The related optimization algorithm is one of a genetic optimization algorithm, a particle population algorithm and a differential evolution algorithm.
And the machine learning method in the step five is one of a neural network, a decision tree and a random forest.
The invention has the beneficial effects that: acquiring statistical distribution characteristics of the profile through cluster analysis on the basis of sufficient accumulation of actually measured atmosphere turbulence profile data; on the basis of analyzing statistical distribution characteristics, Monte Carlo simulation and optimization algorithms are utilized to obtain the positions of the guide stars corresponding to the profiles of different categories, and further the mapping relation between the profiles of different turbulences and the optimized positions of the movable guide stars is obtained through a machine learning method. The corresponding movable guide star optimal position can be rapidly calculated according to actually measured turbulence data in practical application.
Detailed Description
This example will be described in detail with respect to the mobile position of 5 laser-guided stars in a GLAO (near-ground layer adaptive optics) using acquired turbulence data at the chile parralanol observation site. The present embodiment includes the following steps:
the first step is as follows: preprocessing the acquired mass real turbulence profile data, and equating the turbulence data to different layer numbers. Specifically, we can equate to a thin phase screen of 1 layer every 150 meters height, and to 100 layers at most at the maximum measurement height, according to the characteristics of the measuring instrument. Thereafter, the turbulence data was normalized 0-1: firstly, logarithm log10 is taken for turbulence intensity data, in order to prevent the problem of calculation overflow caused by zero-filled data, 1 is added to all turbulence data, then logarithm operation is carried out, and finally, the result after the operation is normalized to an interval [0,1] according to a 0-1 standardization mode.
The second step is that: and clustering the preprocessed turbulent flow data by adopting a clustering method including but not limited to GMM (Gaussian mixture model), K-Means (K-Means clustering algorithm) and other clustering algorithms, and a data clustering method considering data characteristics and influence thereof on the guide star, such as a hierarchical clustering method considering influence of the guide star on the near-ground layer. Now, taking GMM as an example for simple introduction, GMM precisely quantizes an object by using a gaussian probability density function, and decomposes the object into a plurality of models formed based on the gaussian probability density function. The experiment utilizes the algorithm to gather turbulence data into different categories according to different Gaussian distributions of a single sample. First, AIC (information of Chi pool) criterion, which is a criterion for balancing the complexity of the estimation model and the superiority of the fitting data, is adopted. It is a weighted function of fitting accuracy and number of parameters: AIC =2 × k-2ln (L), where k is the number of parameters of the model, the experiment is the number of gaussian distributions in the GMM, L is the maximum likelihood function of the model, and the experiment is the maximum likelihood function of all turbulence data samples. In practical application, all turbulence profile data samples are used for training and classifying different GMM models, and the optimal number N of Gaussian distribution models of GMM under all turbulence profile data samples is determined by minimizing AIC. And then, assuming that the probability of each turbulence sample from a certain Gaussian distribution (m, s) is p, iteratively determining the parameters m, s and p repeatedly through the idea of a maximum likelihood estimation method until the likelihood function value of the sample is converged, and finally dividing each turbulence data sample into a class of Gaussian distributions with the maximum probability value p.
The third step: the adaptive optics system is simulated by adopting a Monte Carlo method, wherein the adaptive optics system comprises but is not limited to GLAO and MCAO. A GLAO near-ground layer self-adaptive optical system is selected for the experiment, and a nano laser guide star is selected as the movable guide star. The position arrangement of the movable guide star mainly influences the measurement of the atmospheric turbulence of the ground layer and the wave front reconstruction result, so the relation between the movable guide star and the ground layer is mainly researched by establishing a model relation between the multilayer simulation phase screen and the wave front measurement. In practical use, we will utilize adaptive optics system monte carlo simulation software, and we use dapp (adaptive optics system simulation platform of university of duren) to build the software including: the Monte Carlo model comprises a sodium laser guide star, a multilayer atmosphere turbulence thin phase screen, a telescope primary mirror, a telescope secondary mirror, a wavefront detector, a focal plane camera and other photoelectric instruments. The device parameters are configured into corresponding parameters matched with an actual system, the position of the laser guide star is changed, and the corresponding performance of the ground-near layer self-adaptive optical system can be obtained by operating the self-adaptive optical system under the configuration when the laser guide star is located at the position.
The fourth step: under a given turbulence profile, the performance of the adaptive optical simulation system is taken as an objective function, the position coordinates of the laser guide star are taken as a target value, and the target value is optimized by adopting a related optimization algorithm, wherein the optimization algorithm comprises but is not limited to a genetic optimization algorithm, a particle population algorithm, a differential evolution algorithm and the like. The experiment is briefly described by taking a genetic algorithm as an example, the algorithm starts an evolution process with a random initial value, and establishes an area matrix Field according to the coordinates of the guide stars and the boundary range of the coordinates, for example, 10 position coordinates corresponding to 5 guide stars are a group, and the coordinates are sequentially marked as x1, y1,.., x5 and y5, wherein the boundary range of x is the range [0,420] of the laser guide star at the Field angle, the unit is angular seconds, and the range of y is the range [0,360] of the laser guide star at the circumferential angle. And in the evolution process, the fitness is determined according to the performance evaluation of the adaptive optical simulation system, the coordinate optimization is carried out according to the modes of recombination, variation and intersection, and finally the coordinate with high fitness is selected as the optimal position of the laser guide star.
The fifth step: and saving different turbulence profiles and the positions of the corresponding laser guide stars in the fourth step as training data, and obtaining the spatial mapping relation of the turbulence profiles on the laser guide stars by adopting a machine learning method, wherein the machine learning method comprises but is not limited to a neural network, a decision tree, a random forest and the like, the neural network is taken as an example, RNN in a pytorch is adopted, the structure is LSTM (long short term memory network), 3 layers of LSTM network layers are adopted, and the number of the hidden units in each layer of the hidden layers is 200. The input data being turbulence profile data, e.g. we need only consider variations in turbulence height
(atmospheric refractive index structure constants) on the system, the data is a vector of 100 x1, and the input dimension is 100 x 1. The output data are 10 values of 5 laser guide stars in polar coordinates, i.e. the output dimension is 10 x 1.
And a sixth step: training a neural network under the configuration environment of a linux system pytore, selecting a dynamic adjustment learning rate and an AdaGrad optimizer as an optimization method in the training process, and training the network by taking the square of the difference value between the predicted value and the true value of the movable guide star coordinate in the training process, namely the mean square error as a loss function; in addition, dropout is added in the middle layer to prevent overfitting, and the full-connection layer adopts a nonlinear activation function Relu to enhance the expression capability of the network and prevent gradient disappearance. The smaller the error between the predicted value and the true value in the training result is, the better the measurement result of the network to the optimal position of the movable guide satellite is, otherwise, the worse the measurement result is. After 2000 epochs are trained, a neural network algorithm model for calculating the position of the movable guide star under the corresponding turbulence profile can be obtained.
Claims (6)
1. The method for planning the optimal position of the movable guide star of the adaptive optical system in real time is characterized by comprising the following steps: the method comprises the following steps
Step one, preprocessing acquired mass real turbulence profile data, enabling the turbulence data to be equivalent to different layers, then taking common logarithm for the turbulence data, normalizing the result to an interval [0,1] according to a 0-1 standardized mode, and adding 1 to all turbulence data and then carrying out logarithm taking operation to prevent computing overflow caused by zero-filling data;
step two, clustering the turbulence data processed in the step one, and classifying the turbulence profile data according to a clustering result;
thirdly, simulating a self-adaptive optical system by adopting a Monte Carlo method, and establishing a physical model relation between the atmospheric turbulence profile and the position of the movable guide star in atmospheric optics;
randomly selecting partial data from the turbulence profile data of different types as representative profiles according to actual requirements, taking the performance of the simulated adaptive optical system as a target function under the turbulence profile data of different types, and calculating the optimal position of the guide star by using a related optimization algorithm;
step five, taking the representative profile and the optimal position of the corresponding guide star in the step four as training data, and obtaining a space mapping relation between the turbulent flow profile and the optimal position of the movable guide star by adopting a machine learning method;
and step six, substituting real-time measurement data of the atmospheric turbulence profile into machine learning to quickly give the optimal position of the movable guide star.
2. The method of claim 1, wherein the method comprises the steps of: the clustering method adopted in the second step is one of Gaussian mixture model GMM, K-Means clustering algorithm K-Means, hierarchical clustering and K nearest neighbor algorithm knn.
3. The method of claim 1, wherein the method comprises the steps of: in the third step, the self-adaptive optical system adopts GLAO or MCAO, and the movable guide star is selected from a nano laser guide star.
4. The method of claim 3, wherein the method comprises the steps of: and in the fourth step, after the representative profile is selected, the performance of the adaptive optical simulation system is taken as a target function, the position coordinate of the laser guide star is taken as a target value, the target value is optimized by adopting a relevant optimization algorithm, and finally, the coordinate with high fitness is selected as the optimal position of the laser guide star.
5. The method of claim 4, wherein the adaptive optics system comprises a mobile guidance satellite and a mobile guidance satellite, and the method further comprises: the related optimization algorithm is one of a genetic optimization algorithm, a particle population algorithm and a differential evolution algorithm.
6. The method of claim 1, wherein the method comprises the steps of: and the machine learning method in the step five is one of a neural network, a decision tree and a random forest.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911072944.9A CN110703764B (en) | 2019-11-05 | 2019-11-05 | Method for planning optimal position of movable guide star of adaptive optical system in real time |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911072944.9A CN110703764B (en) | 2019-11-05 | 2019-11-05 | Method for planning optimal position of movable guide star of adaptive optical system in real time |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110703764A true CN110703764A (en) | 2020-01-17 |
| CN110703764B CN110703764B (en) | 2022-08-16 |
Family
ID=69205223
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911072944.9A Active CN110703764B (en) | 2019-11-05 | 2019-11-05 | Method for planning optimal position of movable guide star of adaptive optical system in real time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110703764B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112583480A (en) * | 2020-12-24 | 2021-03-30 | 微感科技(南通)有限公司 | Method for realizing high-precision wireless optical communication link |
| CN112948352A (en) * | 2021-02-04 | 2021-06-11 | 中国科学院合肥物质科学研究院 | Method for constructing atmospheric optical turbulence space-time characteristics and probabilistic database |
| CN113312848A (en) * | 2021-06-10 | 2021-08-27 | 太原理工大学 | Intelligent design method of optical system with adaptive target information extraction algorithm as target |
-
2019
- 2019-11-05 CN CN201911072944.9A patent/CN110703764B/en active Active
Non-Patent Citations (6)
| Title |
|---|
| BRICE LE ROUX 等: "Optimal control law for classical and multiconjugate adaptive optics", 《JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A》 * |
| JING SUN 等: "An Efficient Guide Stars Classification Algorithm via Support Vector Machines", 《IEEE》 * |
| PENG JIA 等: "Modelling synthetic atmospheric turbulence profiles with temporal variation using Gaussian mixture model", 《MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY》 * |
| 杨慧珍等: "自适应光学系统几种随机并行优化控制算法比较", 《强激光与粒子束》 * |
| 江伦等: "基于瑞利激光导星的大气湍流廓线测量仪设计", 《激光与红外》 * |
| 程知等: "改进的差分光柱像运动激光雷达的湍流廓线反演方法", 《光学学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112583480A (en) * | 2020-12-24 | 2021-03-30 | 微感科技(南通)有限公司 | Method for realizing high-precision wireless optical communication link |
| CN112948352A (en) * | 2021-02-04 | 2021-06-11 | 中国科学院合肥物质科学研究院 | Method for constructing atmospheric optical turbulence space-time characteristics and probabilistic database |
| CN113312848A (en) * | 2021-06-10 | 2021-08-27 | 太原理工大学 | Intelligent design method of optical system with adaptive target information extraction algorithm as target |
| CN113312848B (en) * | 2021-06-10 | 2022-10-04 | 太原理工大学 | Intelligent design method of optical system with adaptive target information extraction algorithm as target |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110703764B (en) | 2022-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110703764B (en) | Method for planning optimal position of movable guide star of adaptive optical system in real time | |
| CN110889324A (en) | Thermal infrared image target identification method based on YOLO V3 terminal-oriented guidance | |
| CN110866887A (en) | Target situation fusion sensing method and system based on multiple sensors | |
| CN112101278A (en) | Hotel point cloud classification method based on k nearest neighbor feature extraction and deep learning | |
| Wlodarczyk–Sielicka et al. | Clustering bathymetric data for electronic navigational charts | |
| JP7403690B2 (en) | System and method for measuring high-speed wind flow with LiDAR in complex terrain | |
| CN112050832B (en) | Atmospheric refraction error correction method for aviation star sensor | |
| CN112949466B (en) | Video AI smoke pollution source identification and positioning method | |
| CN112131731B (en) | Urban growth cellular simulation method based on spatial feature vector filtering | |
| CN116563466A (en) | Deep learning-based three-dimensional Shan Mudian cloud completion method | |
| Tian et al. | Performance evaluation of deception against synthetic aperture radar based on multifeature fusion | |
| CN110033043B (en) | Radar one-dimensional range profile rejection method based on condition generation type countermeasure network | |
| JP7351029B2 (en) | System and method for measuring wind flow turbulence with LiDAR in complex terrain | |
| CN114690790A (en) | GRU-based rapid identification method for guidance law of intercepted aircraft | |
| Duan et al. | An anchor box setting technique based on differences between categories for object detection | |
| CN109977797A (en) | The optimization method of single order object detector based on sequence loss function | |
| CN114035536A (en) | Flight control system robustness assessment method based on Monte Carlo method | |
| CN113553708A (en) | Method and device for tracing key influence factors of simulation model | |
| Ma et al. | A Single Aircraft Intelligent Passive Location Processing Algorithm for Slow Moving Emitter | |
| CN107480709A (en) | A kind of big data clustering method | |
| CN115797814B (en) | Real-time evaluation and calculation method for hidden danger of power transmission line tree obstacle based on unmanned aerial vehicle | |
| CN116993832B (en) | CNN-based position prediction method and device for flight target | |
| Stephan et al. | Artificial Neural Networks for Individual Tracking and Characterization of Wake Vortices in LIDAR Measurements | |
| Tang et al. | Visibility Prediction Based On XGBoost And Markov Chain Combined Model | |
| González-Gutiérrez et al. | Atmospheric Tomography Using Convolutional Neural Networks |
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 |