CN114911159A - Simulated bat aircraft depth control method based on T-S fuzzy neural network - Google Patents
Simulated bat aircraft depth control method based on T-S fuzzy neural network Download PDFInfo
- Publication number
- CN114911159A CN114911159A CN202210466842.0A CN202210466842A CN114911159A CN 114911159 A CN114911159 A CN 114911159A CN 202210466842 A CN202210466842 A CN 202210466842A CN 114911159 A CN114911159 A CN 114911159A
- Authority
- CN
- China
- Prior art keywords
- layer
- neural network
- fuzzy
- aircraft
- depth
- 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.)
- Pending
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 33
- 241001471424 Manta birostris Species 0.000 claims abstract description 24
- 241001331491 Myliobatis californica Species 0.000 claims abstract description 17
- 238000012360 testing method Methods 0.000 claims abstract description 15
- 230000008569 process Effects 0.000 claims abstract description 11
- 230000009182 swimming Effects 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000011478 gradient descent method Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000005192 partition Methods 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 abstract description 6
- 230000008859 change Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000011664 nicotinic acid Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention relates to a depth control method of a simulated manta ray aircraft based on a T-S fuzzy neural network, which is characterized in that depth deviation and depth change rate in the navigation process of the aircraft are collected as input of neural network training, and corresponding tail fin angles are used as output of the neural network training; then, a T-S type fuzzy neural network is established, the neural network is trained by utilizing a training set, and then the trained neural network is tested by utilizing a testing set; and finally, the tested T-S neural network controller is used for controlling the tail fin angle of the simulated bat ray aircraft in the swimming process, so that the tail fin angle of the aircraft is adjusted in real time according to a control value, and the purpose of depth control of the aircraft is finally achieved. Experiments show that the method for controlling the depth of the simulated manta ray aircraft based on the T-S fuzzy neural network has high accuracy and reliability, and the method has practical value in the aspect of aircraft depth control.
Description
Technical Field
The invention belongs to the field of underwater vehicle motion control, relates to a method for controlling the depth of a simulated bat ray vehicle, and particularly relates to a method for controlling the depth of the simulated bat ray vehicle based on a T-S fuzzy neural network.
Background
The underwater unmanned vehicle plays an important role in a plurality of fields such as military, civil use, science and technology and the like as an indispensable part in ocean science and technology. Traditional underwater vehicles mainly adopt propellers for propulsion, but in the face of increasingly complex task demands, the traditional underwater vehicles adopting propellers for propulsion have the defects of large energy consumption, large volume, low efficiency and the like.
Bionic scientific research provides a new idea for developing a novel underwater vehicle and solving the problems of the traditional vehicle. The simulated bat ray aircraft is a novel bionic aircraft which adopts a central fin/opposite fin mode to propel, and has the advantages of small volume, small noise, high maneuverability and the like.
The depth control of the simulated bat ray navigation device has important significance for underwater operation of the navigation device. Existing methods for depth control of underwater vehicles are also primarily directed to conventional vehicles that employ propellers for propulsion. However, due to the differences of the simulated bat ray aircraft and the traditional aircraft in structure and propulsion mechanism, the depth control method applicable to the traditional aircraft is difficult to be directly used for the depth control of the simulated bat ray aircraft.
The depth control method of the underwater vehicle mentioned in the patent CN113050666A depends on the dynamic model of the underwater vehicle. However, since the simulated bat ray aircraft is a complex system with strong nonlinearity and strong coupling, and the establishment of a dynamic model is very difficult, the method is not suitable for depth control of the simulated bat ray aircraft.
Disclosure of Invention
Technical problem to be solved
In order to avoid the defects of the prior art, the invention provides a simulated manta ray aircraft depth control method based on a T-S fuzzy neural network, and solves the problem of depth control of the manta ray aircraft.
Because the change of the tail fin deflection angle and the direction of the simulated manta ray aircraft can change the magnitude and the direction of the pitching moment acting on the simulated manta ray aircraft, and the depth control of the simulated manta ray aircraft can be realized by utilizing the pitching moment, the depth control is realized by changing the tail fin angle of the simulated manta ray aircraft.
Technical scheme
A depth control method of an simulated bat ray aircraft based on a T-S fuzzy neural network is characterized by comprising the following steps:
step 1: depth deviation e of simulated bat ray aircraft at different moments in swimming process d The depth deviation rate ec d And corresponding tail fin angle gamma, constructing a training set and a test set for training the T-S fuzzy neural network;
step 2: the T-S fuzzy neural network comprises an input layer, a fuzzy inference layer, a regression layer and an output layer;
the first layer is an input layer and is connected with an input vector, and an input value is transmitted to nodes, wherein the number of the nodes of the layer is equal to the dimension of the input vector;
the second layer is a fuzzy layer, wherein each node represents a fuzzy language variable value, and the membership degree of each input which belongs to each language variable value fuzzy set is calculated through a membership function;
the membership function:
wherein n is the input number; m is i Is x i The number of fuzzy partitions of (1); c. C ij Is the central value of the membership function; sigma ij Is the width of the membership function, c ij And σ ij Are all adjustable parameters;
the third layer is a fuzzy inference layer, wherein each node represents a fuzzy rule, and the fitness of each rule is calculated; weight α of each rule j By usingProduct method:
wherein i 1 ∈{1,2,…,m 1 },i 2 ∈{1,2,…,m 2 },…,i n ∈{1,2,…,m n }；j＝1,2,…,m；
And calculating an output value y of the fuzzy model by adopting a weighted average method:
in the formula alpha i Represents the weight, y, which is the proportion of the weight of the ith rule in the total output i The output of the ith rule is shown;
the fourth layer is a layer, wherein each node is correspondingly connected with the node of the third layer, and the number of the nodes is the same as that of the third layer, so that normalization calculation is carried out;
the fifth layer is an input layer, wherein each node represents a sharpening output to carry out sharpening calculation;
and step 3: performing learning training on the T-S neural network by using the training set in the step 1, and continuously updating the central value c of the membership function in the second layer during the learning training ij Width value σ ij And the connection weight sum ω in the fifth layer i The method comprises the following steps:
firstly, taking an error cost function as follows:
in the formula, y di Indicating the desired output, y i Representing the actual output;
then according to the gradient descent method, the parameters are modified as follows:
wherein, beta is more than 0 as learning rate;
and 4, step 4: testing the trained T-S neural network by using the constructed test set, and using the tested T-S-based fuzzy neural network as a depth controller for controlling the tail fin angle of the simulated manta ray aircraft; the depth deviation and the depth deviation rate collected by a sensor in the swimming process of the simulated manta ray aircraft are used as input, the tail fin angle is used as output, a steering engine rotates by a corresponding angle according to the output tail fin angle, the pitching moment of the aircraft is changed, and the depth control of the simulated manta ray aircraft is realized.
Advantageous effects
The invention provides a simulated bat aircraft depth control method based on a T-S fuzzy neural network, which comprises the steps of firstly collecting depth deviation and depth change rate in the navigation process of an aircraft as input of neural network training, and taking the corresponding tail fin angle as output of the neural network training so as to construct a training set and a test set for the T-S fuzzy network training; then, a T-S type fuzzy neural network is established, the neural network is trained by utilizing a training set, and then the trained neural network is tested by utilizing a testing set; and finally, the tested T-S neural network controller is used for controlling the tail fin angle of the simulated bat ray aircraft in the swimming process, so that the tail fin angle of the aircraft is adjusted in real time according to a control value, and the purpose of depth control of the aircraft is finally achieved. Experiments show that the method for controlling the depth of the simulated manta ray aircraft based on the T-S fuzzy neural network has high accuracy and reliability, and the method has practical value in the aspect of aircraft depth control.
The invention has the following beneficial effects:
1. the simulated manta ray aircraft depth control method based on the T-S fuzzy neural network provides an effective method for depth control of the manta ray aircraft.
2. The method provided by the invention realizes the depth control of the aircraft by establishing the T-S fuzzy neural network to calculate the control angle of the tail fin, has higher efficiency and prediction precision, and improves the stability and reliability of the depth control of the simulated manta ray aircraft.
3. The simulated manta ray depth control system utilizes a prototype to carry out experiments, realizes effective control on the depth of the simulated manta ray aircraft, and obtains a fixed depth curve graph of the aircraft. The feasibility and the authenticity of the method provided by the invention in a real working environment are verified.
Drawings
FIG. 1 is a control block diagram of the present invention;
FIG. 2 is a block diagram of a T-S fuzzy neural network of the present invention;
FIG. 3 is a graph of the experimental aircraft depthkeeping;
Detailed Description
The invention will now be further described with reference to the following examples and drawings:
the method comprises the following concrete implementation steps:
depth deviation e collected when simulated manta ray aircraft swims in a pool d Degree of depth deviation ec d As a training input for the model, and the corresponding skeg angle γ as a training output for the model. Thus, the present invention has two input level nodes and one output level node. The T-S fuzzy neural network has five layers as shown in FIG. 2.
The specific steps of adopting the T-S fuzzy neural network to carry out the depth control of the simulated manta ray aircraft are as follows:
1. and establishing a training set.
Performing a pool swimming experiment by using a simulated bat ray navigation device, and acquiring navigation device swimming by using a sensor carried by the navigation deviceDepth deviation e at different moments in the process d The depth deviation rate ec d And a corresponding skeg angle γ. Wherein the experimentally obtained depth deviation e d The depth deviation rate ec d Form X ═ e d ，ec d ]As the network input, the tail fin angle γ is taken as the network desired output y di . Thus, a training set and a test set for training the T-S fuzzy neural network are constructed.
2. And establishing a T-S fuzzy neural network and training and testing.
(1) Selecting membership function and calculating weight
Suppose there is an input of X ═ X 1 ,x 2 ,...,x n ]Firstly, the membership degree of each input variable is calculated according to a membership degree function
The membership function of the invention adopts a Gaussian function, and is shown as the following formula:
wherein n is the input number; m is a unit of i Is x i The number of fuzzy partitions of (1); c. C ij Is the central value of the membership function; sigma ij Is the width of the membership function, c ij And σ ij Are all adjustable parameters.
Weight of each rule α j The calculation is performed by the product method, as shown in the following formula:
wherein i 1 ∈{1,2,…,m 1 },i 2 ∈{1,2,…,m 2 },…,i n ∈{1,2,…,m n }；j＝1,2,…,m；
And calculating an output value y of the fuzzy model by adopting a weighted average method:
in the formula of alpha i Represents the proportion (weight) of the component of the ith rule in the total output, y i Indicating the output of the ith rule.
(2) T-S fuzzy neural network construction
A T-S neural network constructed according to the T-S fuzzy algorithm is shown in FIG. 2. The T-S fuzzy neural network has 5 layers including: input layer, fuzzy inference layer, regression layer and output layer
The first layer is an input layer directly connected to the input vector and has the effect of transferring the input value to the nodes, the number of nodes of the layer being equal to the dimension of the input vector.
The second layer is a fuzzy layer, each node of the layer represents a fuzzy linguistic variable value, and the function of the fuzzy linguistic variable value fuzzy layer is to calculate the membership degree of each input belonging to each fuzzy set of linguistic variable values through a membership function.
The third layer is a fuzzy inference layer, each node represents a fuzzy rule, and the layer is used for calculating the fitness of each rule.
The fourth layer is a normalization layer, each node of the layer is correspondingly connected with the node of the third layer, and the number of the nodes is the same as that of the nodes of the third layer. The effect is to perform a normalization calculation.
The fifth layer is the input layer, and each node represents a sharpening output. Its function is to perform a sharpening calculation.
(3) Learning algorithm selection
Because the fuzzy segmentation number of the input value in the T-S fuzzy neural network is predetermined, only the central value c of the membership function in the second layer needs to be continuously updated in the training process ij Width value σ ij And the connection weight sum ω in the fifth layer i . The invention determines the parameters of the neural network by the gradient descent method to obtain the ideal mapping relation of input and outputThe method comprises the following specific steps.
Firstly, taking an error cost function as:
in the formula, y di Representing the desired output, y i Representing the actual output.
Then according to the gradient descent method, the parameters are modified as follows:
wherein β > 0 is the learning rate.
(4) Training and testing of T-S fuzzy neural network
Firstly, training the T-S neural network by using the constructed training set, and then testing the trained T-S neural network by using the constructed testing set to verify the effectiveness of the T-S neural network.
The T-S fuzzy neural network training mainly comprises the following steps:
(a) initializing basic parameters of the neural network, including the number of nodes of the input layer, the output layer and the middle layer of the network, the maximum iteration times of the algorithm, the learning rate beta and the central value c of the membership function ij Sum width value σ ij 。
(b) Calculating corresponding actual output y for each group of input parameters in the training set through a neural network i 。
(c) According to the actual output y i And the desired output y di Updating the central value c of the membership function in the second layer ij Width value σ ij And the connection weight sum ω in the fifth layer i 。
(d) Judging an end condition, and finishing training if the iteration times reach the set maximum algorithm iteration times; otherwise, returning to the step (b) to continue training.
And verifying the T-S neural network obtained after training by using a test set to determine the effectiveness of the obtained T-S neural network.
3. And (3) applying the tested depth controller based on the T-S fuzzy neural network to the simulated manta ray aircraft to control the tail fin angle. And (4) utilizing the finally obtained controller based on the T-S fuzzy neural network to carry out depth control on the simulated bat aircraft. The sensor collects the depth data of the simulated bat ray aircraft in the swimming process of the aircraft, the lower computer calculates the depth deviation and the depth deviation rate, and the depth deviation rate are used as the input of the controller to obtain the corresponding tail fin angle control value. And sending the control value to a tail fin steering engine to enable the steering engine to rotate by a corresponding angle so as to control the depth of the simulated bat ray aircraft.
A prototype is used for carrying out experiments in a water pool to verify the depth control method of the simulated bat aircraft based on the T-S neural network. The depth profile shown in fig. 3 was obtained by experiment. The experimental result shows that the depth of the simulated manta ray aircraft can be effectively controlled by the controller of the fuzzy neural network based on the T-S.
Claims (1)
1. A depth control method of an simulated bat ray aircraft based on a T-S fuzzy neural network is characterized by comprising the following steps:
step 1: depth deviation e of simulated bat ray aircraft at different moments in swimming process d The depth deviation rate ec d And corresponding tail fin angle gamma, constructing a training set and a test set for training the T-S fuzzy neural network;
step 2: the T-S fuzzy neural network comprises an input layer, a fuzzy inference layer, a regression layer and an output layer;
the first layer is an input layer and is connected with an input vector, and an input value is transmitted to nodes, wherein the number of the nodes of the layer is equal to the dimension of the input vector;
the second layer is a fuzzy layer, wherein each node represents a fuzzy linguistic variable value, and the membership degree of each input belonging to each fuzzy set of linguistic variable values is calculated through a membership function;
the membership function:
wherein n is the input number; m is i Is x i The number of fuzzy partitions of (1); c. C ij Is the central value of the membership function; sigma ij Is the width of the membership function, c ij And σ ij Are all adjustable parameters;
the third layer is a fuzzy inference layer, wherein each node represents a fuzzy rule, and the fitness of each rule is calculated;
weight α of each rule j Adopting a product method:
wherein i 1 ∈{1,2,…,m 1 },i 2 ∈{1,2,…,m 2 },…，i n ∈{1,2,…,m n }；j＝1,2,…,m；
And calculating an output value y of the fuzzy model by adopting a weighted average method:
in the formula of alpha i Represents the weight, y, which is the proportion of the weight of the ith rule in the total output i The output of the ith rule is shown;
the fourth layer is a layer, wherein each node is correspondingly connected with the node of the third layer, and the number of the nodes is the same as that of the third layer, so that normalization calculation is carried out;
the fifth layer is an input layer, wherein each node represents a sharpening output to carry out sharpening calculation;
and step 3: performing learning training on the T-S neural network by using the training set in the step 1, and continuously updating the central value c of the membership function in the second layer during the learning training ij Width value σ ij And the connection weight sum ω in the fifth layer i The method comprises the following steps:
firstly, taking an error cost function as:
in the formula, y di Indicating the desired output, y i Representing the actual output;
then according to the gradient descent method, the parameters are modified as follows:
wherein, beta is more than 0 as learning rate;
and 4, step 4: testing the trained T-S neural network by using the constructed test set, and using the tested T-S-based fuzzy neural network as a depth controller for controlling the tail fin angle of the simulated manta ray aircraft; the depth deviation and the depth deviation rate collected by a sensor in the swimming process of the simulated manta ray aircraft are used as input, the tail fin angle is used as output, a steering engine rotates by a corresponding angle according to the output tail fin angle, the pitching moment of the aircraft is changed, and the depth control of the simulated manta ray aircraft is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210466842.0A CN114911159A (en) | 2022-04-26 | 2022-04-26 | Simulated bat aircraft depth control method based on T-S fuzzy neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210466842.0A CN114911159A (en) | 2022-04-26 | 2022-04-26 | Simulated bat aircraft depth control method based on T-S fuzzy neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114911159A true CN114911159A (en) | 2022-08-16 |
Family
ID=82765644
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210466842.0A Pending CN114911159A (en) | 2022-04-26 | 2022-04-26 | Simulated bat aircraft depth control method based on T-S fuzzy neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114911159A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103606006A (en) * | 2013-11-12 | 2014-02-26 | 北京工业大学 | Sludge volume index (SVI) soft measuring method based on self-organized T-S fuzzy nerve network |
| CN111952962A (en) * | 2020-07-30 | 2020-11-17 | 国网江苏省电力有限公司南京供电分公司 | Power distribution network low voltage prediction method based on T-S fuzzy neural network |
| CN113342011A (en) * | 2021-06-08 | 2021-09-03 | 西北工业大学 | Gliding course control method of simulated bat aircraft based on rolling mechanism |
| CN113341974A (en) * | 2021-06-08 | 2021-09-03 | 西北工业大学 | Gliding course control method of simulated manta ray underwater vehicle based on flapping wing bias |
-
2022
- 2022-04-26 CN CN202210466842.0A patent/CN114911159A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103606006A (en) * | 2013-11-12 | 2014-02-26 | 北京工业大学 | Sludge volume index (SVI) soft measuring method based on self-organized T-S fuzzy nerve network |
| CN111952962A (en) * | 2020-07-30 | 2020-11-17 | 国网江苏省电力有限公司南京供电分公司 | Power distribution network low voltage prediction method based on T-S fuzzy neural network |
| CN113342011A (en) * | 2021-06-08 | 2021-09-03 | 西北工业大学 | Gliding course control method of simulated bat aircraft based on rolling mechanism |
| CN113341974A (en) * | 2021-06-08 | 2021-09-03 | 西北工业大学 | Gliding course control method of simulated manta ray underwater vehicle based on flapping wing bias |
Non-Patent Citations (1)
| Title |
|---|
| 梁霄等: "水下机器人T-S 型模糊神经网络控制" * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | An optimization method for control parameters of underwater gliders considering energy consumption and motion accuracy | |
| CN111506970B (en) | Ship hydrodynamic performance evaluation method | |
| CN108319293B (en) | UUV real-time collision avoidance planning method based on LSTM network | |
| CN108334677B (en) | UUV real-time collision avoidance planning method based on GRU network | |
| CN111506969B (en) | Ship type optimization method based on multi-target particle swarm algorithm | |
| CN114218875A (en) | Acceleration method and device for flow field prediction | |
| US7831418B1 (en) | Autonomous experimental design optimization | |
| CN114065663B (en) | Bionic fish hydrodynamic prediction method based on CFD and MLP | |
| CN111445498A (en) | Target tracking method adopting Bi-L STM neural network | |
| CN115577436B (en) | Combined deep learning method for solving wind-induced vibration response of uncertain structure | |
| CN109800517B (en) | Improved reverse modeling method for magnetorheological damper | |
| CN112462792A (en) | Underwater robot motion control method based on Actor-Critic algorithm | |
| CN114077258A (en) | Unmanned ship pose control method based on reinforcement learning PPO2 algorithm | |
| CN114967713B (en) | Underwater vehicle buoyancy discrete change control method based on reinforcement learning | |
| Yan et al. | Real-world learning control for autonomous exploration of a biomimetic robotic shark | |
| Peng et al. | Multi-fidelity nonlinear unsteady aerodynamic modeling and uncertainty estimation based on Hierarchical Kriging | |
| CN113419424A (en) | Modeling reinforcement learning robot control method and system capable of reducing over-estimation | |
| Lei et al. | Gliding hydrodynamic modeling and identification of underwater glider based on differential evolution algorithm | |
| CN114895653A (en) | Water jet propulsion device closed-loop control system fault detection method based on CAE and SVDD | |
| CN114911159A (en) | Simulated bat aircraft depth control method based on T-S fuzzy neural network | |
| CN112800690A (en) | Underwater folding and unfolding mechanism parameter optimization method based on group intelligent optimization algorithm | |
| CN117150881A (en) | Reinforced learning training loop method and device for bionic robot fish navigation task | |
| CN116227073A (en) | Method for researching development and collapse of shoulder cavitation of underwater launching navigation body | |
| CN112140098B (en) | Underwater snake-shaped robot high-speed gait generation method based on near-end strategy optimization | |
| CN115061485A (en) | Unmanned aerial vehicle guidance instruction generation method and system based on neural network |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220816 |
|
| RJ01 | Rejection of invention patent application after publication |