CN113361649A - Autonomous ship navigation scene clustering method for improving fuzzy C-means algorithm - Google Patents
Autonomous ship navigation scene clustering method for improving fuzzy C-means algorithm Download PDFInfo
- Publication number
- CN113361649A CN113361649A CN202110771266.6A CN202110771266A CN113361649A CN 113361649 A CN113361649 A CN 113361649A CN 202110771266 A CN202110771266 A CN 202110771266A CN 113361649 A CN113361649 A CN 113361649A
- Authority
- CN
- China
- Prior art keywords
- clustering
- autonomous
- scene
- ship navigation
- scenes
- 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 37
- 230000008569 process Effects 0.000 claims abstract description 15
- 230000008859 change Effects 0.000 claims abstract description 11
- 238000007621 cluster analysis Methods 0.000 claims abstract description 11
- 238000011156 evaluation Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 14
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 238000011160 research Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Traffic Control Systems (AREA)
Abstract
An autonomous ship navigation scene clustering method for improving a fuzzy C-means algorithm is characterized by establishing an autonomous ship navigation scene clustering model, establishing coordinate axes by using dynamic factors, and forming a coordinate system by using parameter values of various attributes; forming elements in a coordinate system by using parameters which change in navigation according to the coordinate system, and acquiring a scene library; in a scene library, selecting parameter values of different attributes in a coordinate system to carry out random combination, and enumerating all scenes encountered in the autonomous ship navigation process; extracting feature points under each scene, and performing cluster analysis on the feature points so as to perform cluster analysis on the scenes corresponding to the autonomous ships; a fuzzy C-means algorithm based on distance evaluation is fused to construct an autonomous ship navigation scene clustering model; and clustering autonomous ship navigation scenes through MATLAB.
Description
Technical Field
The invention belongs to the technical field of autonomous ship scenes, and particularly relates to an autonomous ship navigation scene clustering method for improving a fuzzy C-means algorithm.
Background
During the navigation process of the autonomous ship, the autonomous ship senses the surrounding environment by means of various sensors, controllers and other devices which are arranged on the ship and comprise a channel navigation mark, channel change, weather change, surrounding dynamic and static barriers, other ships and the like, and the control of the ship is autonomously completed by a control system of the ship. In the system, the design parameters and the running state of the ship, the ship navigation environment and the control attributes are changed mutually to form an intricate driving scene, and the autonomous ship can accurately identify the current traffic scene and make appropriate driving decisions on the corresponding scene, so that the safe navigation of the autonomous ship can be ensured. How to accurately and quickly identify a scene needs to be designed urgently.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides an autonomous ship navigation scene clustering method for improving a fuzzy C-means algorithm, and provides a theoretical framework for autonomous ship navigation scene clustering. And the fuzzy C-means algorithm is improved aiming at the clustering algorithm in the framework. And finally, clustering the autonomous ship navigation scene through MATLAB programming.
The invention provides an autonomous ship navigation scene clustering method for improving a fuzzy C-means algorithm, which comprises the following steps of,
s1, establishing an autonomous ship navigation scene clustering model, constructing coordinate axes by dynamic factors in ship attributes, environment attributes and control attributes, and forming a coordinate system by parameter values of various attributes;
step S2, forming elements in the coordinate system according to the parameters which change in the navigation process, thereby obtaining a scene library;
step S3, selecting parameter values of different attributes in a coordinate system to carry out random combination in a scene library, thereby enumerating all scenes encountered in the autonomous ship navigation process; in a database of ship navigation scenes, extracting characteristic points under each scene, and performing cluster analysis on the characteristic points, so that the scenes corresponding to autonomous ships are subjected to cluster analysis;
s4, fusing a fuzzy C-means algorithm based on distance evaluation to construct an autonomous ship navigation scene clustering model;
and step S5, clustering autonomous ship navigation scenes through MATLAB.
As a further technical solution of the present invention, in step S1, the dynamic factors of the coordinate system include the wind and wave current, the channel width, the surplus water depth and the operation state of the ship during the sailing process, and the operation state of the ship includes the speed, the heading, and the traffic density and interference of other ships in the traffic environment.
Further, in step S1, the autonomous ship navigation scenario includes an operation state of the ship and an autonomous ship navigation scenario in a navigation environment during the navigation of the autonomous ship.
Further, in step S3, the autonomous ship navigation scene clustering analysis is to extract feature points in different scenes by recording the channel, environment, traffic condition information and operating state information of the autonomous ship in each scene in the autonomous ship navigation scene database, and perform clustering analysis on the feature points, so as to perform clustering analysis on the navigation scene corresponding to the autonomous ship.
Further, in step S4, specifically,
step S41, standardizing the data set, initializing the membership degree matrix U and enabling the membership degree matrix U to meet the requirements
step S42, providing an iteration standard epsilon larger than 0, setting the clustering number C to be 2, setting the maximum iteration number of the traditional fuzzy C-means algorithm to be 1, and then carrying out initialization clustering by using the maximum and minimum distance algorithm to further obtain an initial partitioning result;
step S43 according to
And the center vector of the total sample
Updating the clustering center and the membership degree, and calculating
A cost function of (a);
step S44, comparing V with a matrix norm | | · | |(k+1)And V(k)If V | |(k+1)-V(k)If | | is less than or equal to epsilon, stopping iteration, otherwise, setting k equal to k +1, and turning to the third step;
step S45, calculating L (c), if c > 2 and c < n, if L (c-1) > L (c-2) and L (c-1) > L (c), the clustering process is ended, otherwise, c ═ c +1 is set, and the process goes to step S43.
Further, in step S5, importing a scene attribute data set, running an improved fuzzy C-means algorithm code in matlab software, and obtaining an optimal clustering number of the scene attribute data set after the operation is finished; and (4) verifying the algorithm through a sample membership degree matrix graph and a target function change value.
The method has the advantages that the method can screen typical characteristic attributes to conduct clustering analysis research on autonomous ship navigation scenes by utilizing the related data of the existing ships. The autonomous ship navigation scene clustering method based on the improved fuzzy C-means algorithm can practically and effectively perform clustering analysis on autonomous ship navigation scenes, can give the optimal clustering number in a self-adaptive mode by using the fuzzy C-means algorithm based on distance evaluation, and can quickly achieve the purpose of optimal clustering.
Drawings
FIG. 1 is a flow chart of an autonomous ship navigation scene cluster analysis of the present invention;
FIG. 2 is a sample membership degree matrix diagram, which is an effect judgment diagram of the autonomous ship navigation scene clustering method of the present invention;
FIG. 3 is a schematic diagram of an effect judgment diagram-objective function change value of the autonomous ship navigation scene clustering method of the present invention.
Detailed Description
Referring to fig. 1, the embodiment provides an autonomous ship navigation scene clustering method for improving a fuzzy C-means algorithm, including the following steps,
s1: establishing autonomous ship navigation scene clustering model
From the perspective of a coordinate system, a coordinate axis is constructed by dynamic change factors in ship attributes, environment attributes and control attributes, and parameter values of various attributes form the coordinate system.
In the coordinate system, dynamic parameter values which may change during navigation, such as wind wave flow, channel width, surplus water depth, running states of the ship, such as navigation speed, course, traffic density in a traffic environment, interference of other ships and the like, form mutually independent elements in the coordinate system.
S2: autonomous ship navigation scene composition
During the navigation process of the autonomous ship, the running state of the autonomous ship and various parameters of the navigation environment, such as wind waves, channel width and surplus water depth encountered by the autonomous ship during the navigation process, the running state of the ship, such as navigation speed, course, traffic density in the traffic environment, interference of other ships and the like, constitute mutually independent elements in a coordinate axis, and various element parameters are combined to form an intricate autonomous ship navigation scene; and selecting each combination on the coordinate axes to carry out random matching, so that all possible autonomous ship navigation scenes can be enumerated.
S3: autonomous ship navigation scene cluster analysis
In the autonomous ship navigation scene database, by recording the information of the navigation channels, the environment and the traffic condition under different autonomous ship navigation scenes and the running state information of the autonomous ship, the characteristic points under different scenes are extracted, and the characteristic points are subjected to cluster analysis so as to perform cluster analysis on the navigation scene corresponding to the autonomous ship.
The data obtained by combining all parameter elements is too huge, so that clustering of the parameter elements is difficult to realize, the research significance is not large, and in addition, the autonomous ship is still in a development research stage, characteristic attribute data related to autonomous ship navigation risks are difficult to obtain, and by combining with research water area characteristics and consulting expert opinions, some typical characteristic attributes are determined to be screened out for autonomous ship navigation scene clustering analysis research.
Screening the following parameter elements for cluster analysis: speed, visibility, surplus water depth, channel traffic density, fault maintenance timeliness, communication equipment fault rate, human error rate, power plant stability and remote operation reliability.
S4: construction of improved fuzzy C-means algorithm for constructing autonomous ship navigation scene clustering model
According to the autonomous ship navigation scene clustering method for improving the fuzzy C-means algorithm, the number of clustering centers does not need to be specified in advance, the clustering centers are initialized by using a maximum-minimum distance method, then the clustering numbers are determined by using a clustering adaptive function, and finally iteration is performed by using the fuzzy C-means.
Standardizing a data set, initializing a membership matrix U, and enabling the membership matrix U to meet an optimization model of Bezdek clustering:
wherein, assuming the sample set as X ═ { X ═ X1,x2,...,xNAnd the clustering center matrix is V ═ V1,v2,...,vC}，vkRepresented is a feature vector for each cluster center, where sample xj(j ═ 1, 2.., N) for the clustering center vi(i ═ 1, 2.., C) with a degree of membership of uijAnd u in hard clusteringijThe difference is that u in the fuzzy C-means algorithm is only 0 or 1ij∈[0,1]M represents the fuzzy weight index, dij＝||xj-viAnd | | l represents the Euclidean distance between the jth sample and the ith clustering center, and J (U, V) represents the weighted value from each type of sample to the clustering center.
Giving an iteration standard epsilon larger than 0, setting the clustering number C to be 2, setting the maximum iteration number of the traditional fuzzy C-means algorithm to be 1, and then carrying out initialization clustering by using a maximum-minimum distance algorithm to further obtain an initial partitioning result;
③ according to
And the center vector of the total sample
Updating the clustering center and the membership degree, and calculating
A cost function of (a);
comparing V with a matrix norm | | · | |(k+1)And V(k)If V | |(k+1)-V(k)If | | is less than or equal to epsilon, stopping iteration, otherwise, setting k equal to k +1, and turning to the third step;
and (6) calculating L (c), if c is more than 2 and c is less than n, if L (c-1) > L (c-2) and L (c-1) > L (c), ending the clustering process, otherwise, setting c to be c +1, and turning to (c).
S5: clustering of autonomous ship navigation scene based on MATLAB
After the autonomous ship navigation scene clustering model is constructed, a large amount of sample data is required to interact with the model to really realize scene clustering.
Importing a scene attribute data set, running an improved fuzzy C-means algorithm code in matlab software, and obtaining the optimal clustering number of the scene attribute data set after running is finished;
in the embodiment of the present invention, the parameters in the code are set as follows:
maximum number of iterations, max _ iter 1000;
minimum improvement, i.e. error criterion for iteration stop, min _ impro ═ 1 e-4;
the initial clustering value c is 2;
the maximum cluster number, clu _ max, is 10.
And importing the collected autonomous ship navigation scene attribute data set into a programmed program, operating an algorithm code of an autonomous ship navigation scene clustering method for improving the fuzzy C-means algorithm by using matlab software, obtaining the optimal clustering number of the autonomous ship navigation scene attribute data set as 3 classes after the operation is finished, wherein the classification result is consistent with the selected data characteristics, and further, the clustering algorithm is feasible.
Because the data set contains more index attributes and has larger dimensionality, a visualized cluster map cannot be obtained, and the effect of the algorithm can be verified by sampling the membership matrix map of fig. 2 and the target function change value of fig. 3.
The autonomous ship navigation scene clustering method for improving the fuzzy C-means algorithm provided by the invention designs an autonomous ship navigation scene clustering model, and the autonomous ship can identify the navigation scene faster by clustering the navigation scene so as to guide the autonomous ship to make a correct driving decision better and faster in the navigation process, thereby ensuring the navigation safety of the autonomous ship. Meanwhile, the clustering algorithm is not only suitable for navigation of independent ships in open water areas, but also suitable for navigation of independent ships in limited water areas.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are intended to further illustrate the principles of the invention, and that various changes and modifications may be made without departing from the spirit and scope of the invention, which is intended to be protected by the appended claims. The scope of the invention is defined by the claims and their equivalents.
Claims (6)
1. An autonomous ship navigation scene clustering method for improving a fuzzy C-means algorithm is characterized by comprising the following steps,
s1, establishing an autonomous ship navigation scene clustering model, constructing coordinate axes by dynamic factors in ship attributes, environment attributes and control attributes, and forming a coordinate system by parameter values of various attributes;
step S2, forming elements in the coordinate system according to the parameters which change in the navigation process, thereby obtaining a scene library;
step S3, selecting parameter values of different attributes in a coordinate system to carry out random combination in a scene library, thereby enumerating all scenes encountered in the autonomous ship navigation process; in a database of ship navigation scenes, extracting characteristic points under each scene, and performing cluster analysis on the characteristic points, so that the scenes corresponding to autonomous ships are subjected to cluster analysis;
s4, fusing a fuzzy C-means algorithm based on distance evaluation to construct an autonomous ship navigation scene clustering model;
and step S5, clustering autonomous ship navigation scenes through MATLAB.
2. The method for clustering autonomous ship navigation scenes by using an improved fuzzy C-means algorithm as claimed in claim 1, wherein in step S1, the dynamic factors of the coordinate system include the wave current, the channel width, the surplus water depth and the running state of the ship during the navigation of the ship, and the running state of the ship includes the speed, the heading and the traffic density in the traffic environment and interference of other ships.
3. The method for clustering autonomous ship navigation scenes based on the improved fuzzy C-means algorithm of claim 1, wherein in step S1, the autonomous ship navigation scenes comprise the running state of the ship and the autonomous ship navigation scenes in the navigation environment during the navigation of the autonomous ship.
4. The method for clustering autonomous ship navigation scenes according to claim 1, wherein in step S3, the clustering analysis of autonomous ship navigation scenes is performed by recording information of channels, environments, traffic conditions, and operating states of autonomous ships in each scene in a database of autonomous ship navigation scenes, extracting feature points in different scenes, and performing clustering analysis on the feature points, so as to perform clustering analysis on the navigation scenes corresponding to the autonomous ships.
5. The method for clustering autonomous ship navigation scenes based on the improved fuzzy C-means algorithm as claimed in claim 1, wherein said step S4 is specifically,
step S41, standardizing the data set, initializing the membership degree matrix U and enabling the membership degree matrix U to meet the requirements
step S42, providing an iteration standard epsilon larger than 0, setting the clustering number C to be 2, setting the maximum iteration number of the traditional fuzzy C-means algorithm to be 1, and then carrying out initialization clustering by using the maximum and minimum distance algorithm to further obtain an initial partitioning result;
step S43 according to
And the center vector of the total sample
Updating the clustering center and the membership degree, and calculating
step S44, comparing V with a matrix norm | | · | |(k+1)And V(k)If V | |(k+1)-V(k)If | | is less than or equal to epsilon, stopping iteration, otherwise, setting k equal to k +1, and turning to the third step;
step S45, calculating L (c), if c > 2 and c < n, if L (c-1) > L (c-2) and L (c-1) > L (c), the clustering process is ended, otherwise, c ═ c +1 is set, and the process goes to step S43.
6. The method for clustering autonomous ship navigation scenes by using an improved fuzzy C-means algorithm according to claim 1, wherein in step S5, a scene attribute data set is imported, the improved fuzzy C-means algorithm code is run in matlab software, and the optimal clustering number of the scene attribute data set is obtained after the operation is finished; and (4) verifying the algorithm through a sample membership degree matrix graph and a target function change value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110771266.6A CN113361649B (en) | 2021-07-08 | 2021-07-08 | Autonomous ship navigation scene clustering method for improving fuzzy C-means algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110771266.6A CN113361649B (en) | 2021-07-08 | 2021-07-08 | Autonomous ship navigation scene clustering method for improving fuzzy C-means algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113361649A true CN113361649A (en) | 2021-09-07 |
| CN113361649B CN113361649B (en) | 2024-04-02 |
Family
ID=77538904
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110771266.6A Active CN113361649B (en) | 2021-07-08 | 2021-07-08 | Autonomous ship navigation scene clustering method for improving fuzzy C-means algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113361649B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114550121A (en) * | 2022-02-28 | 2022-05-27 | 重庆长安汽车股份有限公司 | Clustering-based automatic driving lane change scene classification method and recognition method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107153846A (en) * | 2017-05-26 | 2017-09-12 | 南京邮电大学 | A kind of road traffic state modeling method based on Fuzzy C-Means Cluster Algorithm |
| US20170262695A1 (en) * | 2016-03-09 | 2017-09-14 | International Business Machines Corporation | Face detection, representation, and recognition |
| CN108830289A (en) * | 2018-04-28 | 2018-11-16 | 河南师范大学 | A kind of image clustering method and device based on improved fuzzy C-means clustering |
| CN109298712A (en) * | 2018-10-19 | 2019-02-01 | 大连海事大学 | A kind of autonomous Decision of Collision Avoidance method of unmanned ship based on the study of adaptive sailing situation |
| CN111144015A (en) * | 2019-12-30 | 2020-05-12 | 吉林大学 | Method for constructing virtual scene library of automatic driving automobile |
-
2021
- 2021-07-08 CN CN202110771266.6A patent/CN113361649B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170262695A1 (en) * | 2016-03-09 | 2017-09-14 | International Business Machines Corporation | Face detection, representation, and recognition |
| CN107153846A (en) * | 2017-05-26 | 2017-09-12 | 南京邮电大学 | A kind of road traffic state modeling method based on Fuzzy C-Means Cluster Algorithm |
| CN108830289A (en) * | 2018-04-28 | 2018-11-16 | 河南师范大学 | A kind of image clustering method and device based on improved fuzzy C-means clustering |
| CN109298712A (en) * | 2018-10-19 | 2019-02-01 | 大连海事大学 | A kind of autonomous Decision of Collision Avoidance method of unmanned ship based on the study of adaptive sailing situation |
| CN111144015A (en) * | 2019-12-30 | 2020-05-12 | 吉林大学 | Method for constructing virtual scene library of automatic driving automobile |
Non-Patent Citations (1)
| Title |
|---|
| JAMESC BEZDEK ET AL.: "Convergence theory for fuzzy c-means Counterexamples and repairs", 《IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS》, vol. 17, no. 5, pages 873 - 877, XP008115441 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114550121A (en) * | 2022-02-28 | 2022-05-27 | 重庆长安汽车股份有限公司 | Clustering-based automatic driving lane change scene classification method and recognition method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113361649B (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109000645A (en) | Complex environment target classics track extracting method | |
| Bhanu et al. | Genetic learning for adaptive image segmentation | |
| CN105975913B (en) | Road network extraction method based on adaptive cluster learning | |
| Ren et al. | A novel hybrid method of lithology identification based on k-means++ algorithm and fuzzy decision tree | |
| CN114970321A (en) | Scene flow digital twinning method and system based on dynamic trajectory flow | |
| CN107016464B (en) | threat estimation method based on dynamic Bayesian network | |
| CN111540193A (en) | Traffic data restoration method for generating countermeasure network based on graph convolution time sequence | |
| CN111832615A (en) | Sample expansion method and system based on foreground and background feature fusion | |
| CN115829171B (en) | Pedestrian track prediction method combining space-time information and social interaction characteristics | |
| CN111582380A (en) | Ship track density clustering method and device based on space-time characteristics | |
| CN110263709A (en) | Driving Decision-making method for digging and device | |
| CN115457414B (en) | Unmanned aerial vehicle abnormal behavior identification method based on improved residual error network | |
| CN112084240B (en) | Intelligent identification and linkage treatment method and system for group renting | |
| CN116739176A (en) | Tunnel mechanized construction risk prediction method based on deep belief network | |
| CN114037871A (en) | Image classification interpretable method based on neural support decision tree | |
| CN115619963A (en) | City building entity modeling method based on content perception | |
| CN113361649B (en) | Autonomous ship navigation scene clustering method for improving fuzzy C-means algorithm | |
| CN112380945B (en) | Method and system for identifying potential hazards of power transmission channel environment based on satellite remote sensing image | |
| CN116975781A (en) | Automatic driving vehicle behavior decision system and method | |
| Martínez et al. | Engine health monitoring for engine fleets using fuzzy radviz | |
| CN112465253B (en) | Method and device for predicting links in urban road network | |
| Lin et al. | Connectivity guaranteed multi-robot navigation via deep reinforcement learning | |
| CN113761699A (en) | Crack model construction method and device, electronic equipment and medium | |
| Zhao et al. | Application of data fusion based on clustering-neural network for ETC gantry flow capacity correction | |
| CN113269278B (en) | Robot cruising target identification method and system based on field overturning |
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 |