CN116620492B - Deformable unmanned ship and deformation method - Google Patents
Deformable unmanned ship and deformation method Download PDFInfo
- Publication number
- CN116620492B CN116620492B CN202310911453.9A CN202310911453A CN116620492B CN 116620492 B CN116620492 B CN 116620492B CN 202310911453 A CN202310911453 A CN 202310911453A CN 116620492 B CN116620492 B CN 116620492B
- Authority
- CN
- China
- Prior art keywords
- ship
- speed
- wing
- tail
- wings
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012549 training Methods 0.000 claims description 19
- 238000012360 testing method Methods 0.000 claims description 15
- 239000013598 vector Substances 0.000 claims description 9
- 230000000737 periodic effect Effects 0.000 claims description 7
- 238000007476 Maximum Likelihood Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 5
- 241000764238 Isis Species 0.000 claims description 3
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING
- B63B35/00—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING
- B63B3/00—Hulls characterised by their structure or component parts
- B63B3/14—Hull parts
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63H—MARINE PROPULSION OR STEERING
- B63H5/00—Arrangements on vessels of propulsion elements directly acting on water
- B63H5/07—Arrangements on vessels of propulsion elements directly acting on water of propellers
- B63H5/08—Arrangements on vessels of propulsion elements directly acting on water of propellers of more than one propeller
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63H—MARINE PROPULSION OR STEERING
- B63H5/00—Arrangements on vessels of propulsion elements directly acting on water
- B63H5/07—Arrangements on vessels of propulsion elements directly acting on water of propellers
- B63H5/125—Arrangements on vessels of propulsion elements directly acting on water of propellers movably mounted with respect to hull, e.g. adjustable in direction, e.g. podded azimuthing thrusters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING
- B63B35/00—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for
- B63B2035/006—Unmanned surface vessels, e.g. remotely controlled
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Abstract
The invention discloses a deformable unmanned ship and a deformation method, which relate to the technical field of unmanned ships and comprise a ship body, ship wings, a tail wing and deformation components, wherein a controller, a speed collector and a main propeller are arranged on the ship body, the two sides of the ship body are connected with the ship wings through the deformation components, the tail of the ship body is connected with the tail wing through an electric telescopic rod, the deformation components comprise universal components and electric push rods, one end of each electric push rod is connected with the side surface of the ship body through the universal components, and the other end of each electric push rod is connected with the middle part of the side surface of the ship side wing. And predicting the speed change through a Gaussian process regression prediction model, clustering the predicted speed data through an improved self-adaptive k-means algorithm, and controlling the deformation of the unmanned ship by the controller according to the speed type. According to the invention, the ship body can be correspondingly deformed according to the state of the ship, and the lifting force provided by the ship wings and the tail wings can provide power for the navigation of the unmanned ship, so that the consumption of energy sources is greatly saved, and a certain contribution is made to solving the problem of the cruising of the unmanned ship.
Description
Technical Field
The invention relates to the technical field of unmanned ships, in particular to a deformable unmanned ship and a deformation method.
Background
Along with the continuous progress of scientific technology, the rapid development of unmanned ship field has greatly liberated manpower and materials in aspects such as marine observation, water quality monitoring and treatment, is applicable to a great deal of water work content such as water quality sampling, submarine topography survey, surface garbage clearance. In practical application, the operation is flexible, and unmanned ship can replace manpower to finish the detection, sampling and other works of dangerous environment. However, most of the existing unmanned ships adopt fixed navigational speed to complete tasks, for example, the Chinese patent application number is CN202011437750.7, and discloses an unmanned ship navigational speed control method and an unmanned ship.
Disclosure of Invention
In order to overcome the problems in the prior art, the invention provides a deformable unmanned ship and a deformation method.
The technical scheme adopted for solving the technical problems is as follows: the utility model provides a flexible unmanned ship, includes hull, ship flank, fin, deformation part, install controller, speed collector, main propulsion ware on the hull, the ship flank is connected through deformation part to the hull both sides, the hull afterbody is connected with the fin through electric telescopic handle, deformation part includes universal component and electric putter, electric putter one end is connected with the hull side through universal component, and the other end is connected with ship side flank middle part through universal component, speed collector, electric putter, electric telescopic handle, ship flank, fin all with controller electric connection.
The deformable unmanned ship comprises the universal component, wherein the universal component comprises an inner ball head and an annular clamp, the inner ball head is arranged on the side surface of the ship body, and the annular clamp is clamped on the inner ball head.
The deformable unmanned ship comprises a ship side wing body, a ship side wing driver and a ship side wing propeller, wherein the driver is arranged on the bottom surface of the wing body, an output shaft of the driver is connected with the propeller, and the driver is electrically connected with the controller; the tail wing comprises a tail wing body, a tail wing driver and a tail wing screw propeller, wherein the middle part of the tail wing body is fixedly connected with one end of an electric telescopic rod, the tail wing body is of a T-shaped structure, the head part of the tail wing body is arc-shaped, the tail wing driver is arranged at the tail part of the tail wing body, and the output end of the tail wing driver is fixedly connected with the tail wing screw propeller.
The deformation method of the deformable unmanned ship comprises the following steps of:
step 1, training a Gaussian process regression prediction model according to navigational speed data acquired by an unmanned ship in real time, and predicting navigational speed change trend of the unmanned ship at future time;
step 2, clustering the navigational speed data predicted by the Gaussian process regression prediction model by adopting an improved self-adaptive k-means algorithm, wherein the navigational speed data is in three categories of low speed, medium speed and high speed, the speed is lower than 3m/s and is low speed, the speed is medium speed between 3 and 9m/s, and the speed is higher than 9m/s and is high speed;
step 3, the controller completes the deformation of the object ship body according to the type of the predicted navigational speed, when the ship body runs at a low speed, the ship side wings and the tail wing are close to the ship body, and the ship body provides power by the main propeller; when the speed of the ship body reaches 3-9m/s, the electric push rod pushes the ship side wings out, the driver of the ship side wings rotates to drive the ship side wing propellers to rotate, and the main propeller and the ship side wing propellers simultaneously provide power for the ship body; when the speed of the ship body is greater than 9m/s, the electric telescopic rod pushes the tail wing out, the tail wing driver rotates to drive the tail wing screw propeller to rotate, and the main propeller, the ship side wing screw propeller and the tail wing screw propeller simultaneously provide power for the ship body.
The deformation method of the deformable unmanned ship specifically comprises the following steps:
step 1.1, the gaussian process f (x) can be fully described by a mean function m (x) and a covariance function k (x, x'): f (x) to GP (m (x), k (x, x')
Step 1.2, the navigational speed information collected by the ship body speed collector is a training set of a Gaussian process regression prediction model:
wherein ,xi Is the ith input data, y i Is the ith output data;
step 1.3, the mapping relation between input and output in Gaussian process regression is as follows:
y＝f(x)+ξ
wherein ζ is 0 subject to mean and covariance isIs a gaussian distributed noise independent of (1);
the joint probability distribution of the multidimensional gaussian distribution is:
wherein the mean function μ of the training samples x Given a priori as 0, f (x * ) Represents the output of the test sample, N represents the Gaussian distribution, K (x * X) represents the mixed kernel function between the test sample and the training sample, K (X, X) represents the mixed kernel function between the training samples, K (X) * ，x * ) Representing a mixed kernel function between test samples,representing the covariance of noise, I n Representing the identity matrix;
step 1.4, deriving by a Shuerbu formula:
wherein m (f (x) * ) Representing the mean function of the test sample output, i.e. predicted unmanned ship speed, cov(f(x * ) A) represents a covariance function, i.e. a predicted uncertainty of the unmanned ship's speed, y represents the output of the training samples;
and 1.5, outputting the navigational speed prediction information to an improved self-adaptive k-means algorithm module to cluster navigational speeds.
In the deformation method of the deformable unmanned ship, the mixed kernel function in the step 1.4 adopts a mixed kernel function of a square index kernel function and a periodic kernel function, and the specific formula is as follows:
wherein, alpha and beta are weights of square index function and periodic kernel function, and the magnitude of the weights, sigma, is adaptively adjusted according to the ocean sampling environment 2 Is the super parameter of the kernel function, the super parameter is selected by optimizing the maximum likelihood boundary function, and the mathematical formula is as follows:
wherein ,gaussian distributed noise representing zero mean value, θ being a super-parametric vector, L representing the order;
in order to calculate the maximum likelihood boundary function, the bias derivative of equation (1) in step 1.4 is:
where λ represents a vector.
The deformation method of the deformable unmanned ship specifically comprises the following step 2:
step 2.1, the input data is a navigational speed data set predicted by mixed kernel Gaussian process regression: y= { x 1 ，x 2 ，，...x m }，Where u is the x-axis heave velocity, v is the y-axis heave velocity, z-axis velocity is negligible, and the output data is the cluster division c= { c 1 ，c 2 ，c 3 }；
Step 2.2, 3 are specified from the dataset Y as initial 3 centroid vectors: { mu 1 ，μ 2 ，μ 3 }，
Designating the initialization adaptive centroid as:
wherein , is the length Froude number, L WL The waterline length of the ship, g is the gravity acceleration;
step 2.3, initializing cluster partition C to step 2.1t＝1，2，3；
Step 2.4, calculating the distance between the sample and the adaptive centroid in step 2.2:one-to-one grouping of sample points to clusters closest to the centroid, and recalculating new sample points for all sample points in each clusterA centroid;
and 2.5, if all centroids are unchanged, outputting cluster division C to a controller, and if the centroids are changed, repeating the step 2.4 according to the new centroids.
The step 2.1 is to specify the cluster according to the speed classification criterion:
c 1 ＜3m＝/s
3m/s≤c 2 ＜9m/s
c 3 ≥9m/s。
the beneficial effects of the invention are as follows: the deformable unmanned ship disclosed by the invention has the advantages that the navigational speed is generally slower in a region with a narrow and obstacle in a water area, the area of the ship body is reduced by deforming and shrinking the ship side wings through the ship body, and the power provided by the main propeller only passes through the region with the narrow and obstacle at a low speed; in a region with a wider working range and no obstacle, the navigational speed is generally faster, the ship wings are unfolded through the deformation of the ship body by predicting the navigational speed, and the three propellers are linked and the lifting force provided by the ship wings and the hydrofoils provides power for the unmanned ship to navigate; the ship body can be correspondingly deformed according to the state of the ship, and the lifting force provided by the ship wings and the tail wings can provide power for the navigation of the unmanned ship, so that the consumption of energy sources is greatly saved, and a certain contribution is made for solving the problem of the cruising of the unmanned ship.
Drawings
The invention will be further described with reference to the drawings and examples.
FIG. 1 is a schematic illustration of an unmanned ship in a high speed condition according to the present invention;
FIG. 2 is a schematic illustration of the unmanned ship in a low speed condition according to the present invention;
fig. 3 is a schematic view of the unmanned ship in the medium speed state according to the present invention.
In the figure, a ship body 1, ship wings 2, ship side wing propellers 3, electric telescopic rods 4, tail wings 5 and electric push rods 6.
Detailed Description
The present invention will be described in detail below with reference to the drawings and detailed description to enable those skilled in the art to better understand the technical scheme of the present invention.
As shown in fig. 1-3, this embodiment discloses a deformable unmanned ship, including hull 1, ship side wing 2, fin 5, deformation part, install controller, speed collector, main propulsion ware on the hull, hull both sides are connected ship flank 2 through deformation part, hull 1 afterbody is connected with fin 5 through electric telescopic handle 4, deformation part includes universal component and electric putter 6, electric putter 6 one end is connected with the hull side through universal component, the other end is connected with ship side wing side middle part through universal component, speed collector, electric putter, electric telescopic handle, ship flank, fin all with controller electric connection.
In this embodiment, the universal component includes interior bulb and annular clamp, and interior bulb is installed in hull side, annular clamp joint is on the interior bulb.
As shown in fig. 1, the ship side wing comprises a wing body, a ship side wing driver and a ship side wing propeller 3, wherein the driver is arranged on the bottom surface of the wing body, an output shaft of the driver is connected with the propeller, and the driver is electrically connected with the controller. The fin includes the fin wing body, fin driver, fin screw, fin wing body middle part and electric telescopic handle 4 one end fixed connection, and the fin wing body is T type structure, and the head is convex, fin wing body afterbody installation fin driver, fin driver output and fin screw fixed connection.
Based on the deformable unmanned ship, the specific deformation method comprises the following steps:
step 1, training a Gaussian process regression prediction model according to navigational speed data acquired by an unmanned ship in real time, and predicting navigational speed change trend of the unmanned ship at future time;
the step 1 specifically comprises the following steps:
step 1.1, the gaussian process f (x) can be fully described by a mean function m (x) and a covariance function k (x, x'): f (x) to GP (m (x), k (x, x'));
step 1.2, the navigational speed information collected by the ship body speed collector is a training set of a Gaussian process regression prediction model:
wherein ,xi Is the ith input data, y i Is the ith output data;
step 1.3, the mapping relation between input and output in Gaussian process regression is as follows:
y＝f(x)+ξ
wherein ζ is 0 subject to mean and covariance isIs a gaussian distributed noise independent of (1);
the joint probability distribution of the multidimensional gaussian distribution is:
wherein the mean function μ of the training samples x Given a priori as 0, f (x * ) Represents the output of the test sample, N represents the Gaussian distribution, K (x * X) represents the mixed kernel function between the test sample and the training sample, K (X, X) represents the mixed kernel function between the training samples, K (X) * ，x * ) Representing a mixed kernel function between test samples,representing the covariance of noise, I n Representing the identity matrix;
step 1.4, deriving by a Shuerbu formula:
wherein m (f (x) * ) Represents a mean function, i.e. a predicted unmanned ship speed, cov (f (x) * ) A covariance function, i.e. the predicted uncertainty of the unmanned ship's speed,y represents the output of the training sample;
the mixed kernel function adopts a mixed kernel function of a square index kernel function and a periodic kernel function, and the specific formula is as follows:
wherein, alpha and beta are weights of square index function and periodic kernel function, and the size of the weights is adaptively adjusted according to the ocean sampling environment. For example, when the navigation data of the unmanned ship is a standard z-shaped test or a standard circumference test, the data samples show high regularity, so that the weight of the periodic kernel function can be increased, and alpha is set to be 0.3, and beta is set to be 0.7. Sigma (sigma) 2 Is the super parameter of the kernel function, the super parameter is selected by optimizing the maximum likelihood boundary function, and the mathematical formula is as follows:
wherein ,gaussian distributed noise representing zero mean value, θ being a super-parametric vector, L representing the order;
in order to calculate the maximum likelihood boundary function, the bias derivative of equation (1) in step 1.4 is:
wherein λ represents a vector;
and 1.5, outputting the navigational speed prediction information to an improved self-adaptive k-means algorithm module to cluster navigational speeds.
Step 2, clustering the navigational speed data predicted by the Gaussian process regression prediction model by adopting an improved self-adaptive k-means algorithm, wherein the navigational speed data is in three categories of low speed, medium speed and high speed, the speed is lower than 3m/s and is low speed, the speed is medium speed between 3 and 9m/s, and the speed is higher than 9m/s and is high speed;
the step 2 specifically comprises the following steps:
step 2.1, the input data is a navigational speed data set predicted by mixed kernel Gaussian process regression: y= { x 1 ，x 2 ，，...x m }，Where u is the x-axis heave velocity, v is the y-axis heave velocity, z-axis velocity is negligible, and the output data is cluster division c= (C) 1 ，c 2 ，c 3 }；
The clusters are specified according to a speed classification criterion:
c 1 ＜3m/s
3m/s≤c 2 ＜9m/s
c 3 ≥9m/s。
step 2.2, 3 are specified from the dataset Y as initial 3 centroid vectors: { mu 1 ，μ 2 ，μ 3 }，
Designating the initialization adaptive centroid as:
wherein , is the length Froude number, L WL The waterline length of the ship, g is the gravity acceleration;
step 2.3, initializing cluster partition C to step 2.1t＝1，2，3；
Step 2.4, calculating the distance between the sample and the adaptive centroid in step 2.2:one by one grouping the sample points into clusters closest to the centroid,
re-computing a new centroid for all sample points in each cluster;
and 2.5, if all centroids are unchanged, outputting cluster division C to a controller, and if the centroids are changed, repeating the step 2.4 according to the new centroids.
Step 3, the controller completes the deformation of the object ship body according to the type of the predicted navigational speed, as shown in fig. 2, when the ship body runs at a low speed, both the ship side wings and the tail wing are close to the ship body, and the ship body provides power by the main propeller; as shown in fig. 3, the ship runs at a medium speed when the speed of the ship reaches 3-9m/s, the electric push rod pushes out the ship side wings, the driver of the ship side wings rotates to drive the ship side wing propellers to rotate, and the main propeller and the ship side wing propellers simultaneously provide power for the ship; as shown in figure 1, the ship runs at a high speed when the speed of the ship is greater than 9m/s, the electric telescopic rod pushes the tail wing out, the tail wing driver rotates to drive the tail wing screw propeller to rotate, and the main propeller, the ship side wing screw propeller and the tail wing screw propeller simultaneously provide power for the ship.
The above embodiments are only exemplary embodiments of the present invention and are not intended to limit the present invention, the scope of which is defined by the claims. Various modifications and equivalent arrangements of this invention will occur to those skilled in the art, and are intended to be within the spirit and scope of the invention.
Claims (2)
1. The deformation method of the deformable unmanned ship is characterized in that the deformable unmanned ship specifically comprises a ship body, ship wings, tail wings and deformation components, wherein a controller, a speed collector and a main propeller are arranged on the ship body, the two sides of the ship body are connected with the ship wings through the deformation components, the tail parts of the ship body are connected with the tail wings through electric telescopic rods, the deformation components comprise universal components and electric push rods, one end of each electric push rod is connected with the side surface of the ship body through the universal components, the other end of each electric push rod is connected with the middle part of the side wing surface of the ship side through the universal components, and the speed collector, the electric push rods, the electric telescopic rods, the ship wings and the tail wings are electrically connected with the controller;
the ship side wing comprises a wing body, a ship side wing driver and a ship side wing propeller, wherein the ship side wing driver is arranged on the bottom surface of the wing body, an output shaft of the ship side wing driver is connected with the ship side wing propeller, and the ship side wing driver is electrically connected with the controller; the tail wing comprises a tail wing body, a tail wing driver and a tail wing screw propeller, the middle part of the tail wing body is fixedly connected with one end of the electric telescopic rod, the tail wing body is of a T-shaped structure, the head part of the tail wing body is arc-shaped, the tail wing driver is arranged at the tail part of the tail wing body, and the output end of the tail wing driver is fixedly connected with the tail wing screw propeller;
the deformation method of the deformable unmanned ship specifically comprises the following steps:
step 1, training a Gaussian process regression prediction model according to navigational speed data acquired by an unmanned ship in real time, and predicting navigational speed change trend of the unmanned ship at future time;
step 2, clustering the navigational speed data predicted by the Gaussian process regression prediction model by adopting an improved self-adaptive k-means algorithm, wherein the navigational speed data is in three categories of low speed, medium speed and high speed, the speed is lower than 3m/s and is lower than 9m/s, the speed is higher than 3m/s and is lower than 9m/s and is middle speed, and the speed is higher than 9m/s and is high speed;
step 3, the controller completes the deformation of the object ship body according to the type of the predicted navigational speed, when the ship body runs at a low speed, the ship side wings and the tail wing are close to the ship body, and the ship body provides power by the main propeller; when the speed of the ship body is greater than or equal to 3m/s and smaller than 9m/s, the electric push rod pushes the ship side wings out, the driver of the ship side wings rotates to drive the ship side wing propellers to rotate, and the main propeller and the ship side wing propellers simultaneously provide power for the ship body; when the speed of the ship body is greater than or equal to 9m/s, the electric telescopic rod pushes the tail wing out, the tail wing driver rotates to drive the tail wing screw propeller to rotate, and the main propeller, the ship side wing screw propeller and the tail wing screw propeller simultaneously provide power for the ship body;
the step 1 specifically includes:
step 1.1, gaussian process f (x) is described by mean function m (x) and covariance function k (x, x'):
f(x)～GP(m(x)，k(x，x′))
step 1.2, the navigational speed information collected by the speed collector is a training set of a Gaussian process regression prediction model:
wherein ,xi Is the ith input data, y i Is the ith output data;
step 1.3, the mapping relation between input and output in Gaussian process regression is as follows:
y＝f(x)+ξ
wherein ζ is 0 subject to mean and covariance isIs a gaussian distributed noise independent of (1);
the joint probability distribution of the multidimensional gaussian distribution is:
wherein the mean function μ of the training samples x Given a priori as 0, f (x * ) Represents the output of the test sample, N represents the Gaussian distribution, K (x * X) represents the mixed kernel function between the test sample and the training sample, K (X, X) represents the mixed kernel function between the training samples, K (X) * ，x * ) Representing a mixed kernel function between test samples,representing the covariance of noise, I n Representing the identity matrix, k (X,x * ) Representing a mixed kernel function between the training sample and the test sample;
step 1.4, deriving by a Shuerbu formula:
wherein m (f (x) * ) Represents the mean function of the test sample output, i.e. the predicted unmanned ship speed, cov (f (x) * ) A covariance function of the test sample output, i.e., the predicted uncertainty of the unmanned ship speed, y represents the output of the training sample;
step 1.5, outputting the navigational speed prediction information to an improved self-adaptive k-means algorithm module to cluster navigational speeds;
the mixed kernel function in the step 1.4 adopts a mixed kernel function of a square index kernel function and a periodic kernel function, and the specific formula is as follows:
wherein, alpha and beta are weights of square index kernel function and periodic kernel function, and the size of the weights, sigma, is adaptively adjusted according to the ocean sampling environment 2 Is the super parameter of the kernel function, the super parameter is selected by optimizing the maximum likelihood boundary function, and the mathematical formula is as follows:
wherein ,gaussian distributed noise representing zero mean value, θ being a super-parametric vector, L representing the order;
in order to calculate the maximum likelihood boundary function, the bias derivative of equation (1) in step 1.4 is:
wherein λ represents a vector;
the step 2 specifically includes:
step 2.1, the input data is a navigational speed data set predicted by mixed kernel function Gaussian process regression: y= { x 1 ，x 2 ，，...x m }，Where u is the x-axis heave velocity, v is the y-axis heave velocity, z-axis velocity is negligible, and the output data is cluster division c= { C 1 ，c 2 ，c 3 }；
Step 2.2, 3 are specified from the dataset Y as initial 3 centroid vectors: { mu 1 ，μ 2 ，μ 3 -assigning an initialized adaptive centroid as:
wherein ,is the length Froude number, L WL The waterline length of the ship, g is the gravity acceleration;
step 2.3, initializing cluster partition C to step 2.1
Step 2.4, calculating the distance between the sample in the data set Y and the adaptive centroid in step 2.2:the sample points in the data sets Y are grouped into clusters closest to the centroid one by one, and new centroids are recalculated for the sample points in all the data sets Y in each cluster;
step 2.5, if all centroids are not changed, outputting cluster division C to a controller, and if the centroids are changed, repeating step 2.4 according to the new centroids;
step 2.1, designating clusters according to a speed classification criterion:
c 1 ＜3m/s
3m/s≤c 2 ＜9m/s
c 3 ≥9m/s。
2. the method of claim 1, wherein the universal component comprises an inner ball and an annular clip, the inner ball is mounted on a side of the hull, and the annular clip is clamped on the inner ball.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310911453.9A CN116620492B (en) | 2023-07-25 | 2023-07-25 | Deformable unmanned ship and deformation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310911453.9A CN116620492B (en) | 2023-07-25 | 2023-07-25 | Deformable unmanned ship and deformation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116620492A CN116620492A (en) | 2023-08-22 |
| CN116620492B true CN116620492B (en) | 2023-10-24 |
Family
ID=87603043
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310911453.9A Active CN116620492B (en) | 2023-07-25 | 2023-07-25 | Deformable unmanned ship and deformation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116620492B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1393372A (en) * | 2001-06-29 | 2003-01-29 | 三菱重工业株式会社 | Shipping propelling equipment |
| CN1433926A (en) * | 2002-01-22 | 2003-08-06 | 三菱重工业株式会社 | Ship and use method thereof |
| CN203142973U (en) * | 2013-01-15 | 2013-08-21 | 柏森 | Maritime three-body high-speed gliding boat |
| RU2012132893A (en) * | 2012-08-01 | 2014-02-20 | Нелли Алексеевна Седова | METHOD FOR AUTOMATIC COURT MANAGEMENT BY COURSE AND INTELLECTUAL SYSTEM FOR IMPLEMENTING THE METHOD |
| CN203780788U (en) * | 2013-10-22 | 2014-08-20 | 刘宗蒲 | Side-wing ship |
| WO2015102216A1 (en) * | 2013-12-31 | 2015-07-09 | 울산대학교 산학협력단 | Ship provided with wings |
| CN104773280A (en) * | 2014-01-10 | 2015-07-15 | 森元信吉 | Vessel equipped with main propeller and additional propeller and hybrid navigation method thereof |
| KR200490972Y1 (en) * | 2018-10-18 | 2020-01-30 | 서동구 | Water board having hydrofoil |
| CN112124489A (en) * | 2020-09-03 | 2020-12-25 | 武汉理工大学 | Unmanned ground effect wing ship based on folding wings |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SE545371C2 (en) * | 2021-05-06 | 2023-07-18 | Candela Tech Ab | Method and controller unit for controlling motion of a hydrofoil watercraft |
-
2023
- 2023-07-25 CN CN202310911453.9A patent/CN116620492B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1393372A (en) * | 2001-06-29 | 2003-01-29 | 三菱重工业株式会社 | Shipping propelling equipment |
| CN1433926A (en) * | 2002-01-22 | 2003-08-06 | 三菱重工业株式会社 | Ship and use method thereof |
| RU2012132893A (en) * | 2012-08-01 | 2014-02-20 | Нелли Алексеевна Седова | METHOD FOR AUTOMATIC COURT MANAGEMENT BY COURSE AND INTELLECTUAL SYSTEM FOR IMPLEMENTING THE METHOD |
| CN203142973U (en) * | 2013-01-15 | 2013-08-21 | 柏森 | Maritime three-body high-speed gliding boat |
| CN203780788U (en) * | 2013-10-22 | 2014-08-20 | 刘宗蒲 | Side-wing ship |
| WO2015102216A1 (en) * | 2013-12-31 | 2015-07-09 | 울산대학교 산학협력단 | Ship provided with wings |
| CN104773280A (en) * | 2014-01-10 | 2015-07-15 | 森元信吉 | Vessel equipped with main propeller and additional propeller and hybrid navigation method thereof |
| KR200490972Y1 (en) * | 2018-10-18 | 2020-01-30 | 서동구 | Water board having hydrofoil |
| CN112124489A (en) * | 2020-09-03 | 2020-12-25 | 武汉理工大学 | Unmanned ground effect wing ship based on folding wings |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116620492A (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Parametric geometric model and hydrodynamic shape optimization of a flying-wing structure underwater glider | |
| Huang et al. | Hydrodynamic analysis and motion simulation of fin and propeller driven manta ray robot | |
| US5551369A (en) | Dualcavitating hydrofoil structures | |
| CN116620492B (en) | Deformable unmanned ship and deformation method | |
| CN110316340A (en) | A kind of high stability Underwater Vehicle Hydrodynamic layout of low-speed motion | |
| Zhang et al. | Experimental study on the control form of fin stabilizer at zero speed | |
| Wang et al. | A numerical and experimental study on the hull-propeller interaction of a long range autonomous underwater vehicle | |
| Wang et al. | Analysis of the hydrodynamic performance of a water-air amphibious trans-medium hexacopter | |
| Savitsky et al. | Hydrodynamic development of a high speed planing hull for rough water | |
| CN110398961B (en) | Hovercraft track keeping rudder propeller cooperative control and distribution method | |
| CN113741433A (en) | Distributed formation method for unmanned surface ship | |
| Hoffmann et al. | Biologically inspired optimization of underwater vehicles hull geometries and fin propulsion | |
| Desai et al. | Augmenting maneuverability of UUVs with cycloidal propellers | |
| Ahmed et al. | Dynamic Modeling and Maneuvering of REMUS 100 AUV: The Impact of Added Mass Coefficients | |
| Zou et al. | Design and implementation of a gliding cross-domain vehicle | |
| Yuan et al. | The underwater towed system behavior during Ship turning maneuvers | |
| Liu et al. | Influence of the camber trailing-edge wings on the motion performance of underwater gliders | |
| Oladele | Dynamics of an Autonomous Underwater Vehicle (AUV) towing another AUV | |
| CN115562271B (en) | Open loop control method suitable for high-speed water inlet | |
| Liu et al. | Seal-Inspired Underwater Glider With a Rigid-Flexible Composite Hull | |
| Yamaguchi et al. | Study on hydrodynamic performance of a blended wing body for an underwater glider based on numerical analysis | |
| Zhao et al. | Simulation study of plane motion of air cushion vehicle | |
| ZHANG | Research on Key Technologies of Small Underwater Robots | |
| Dantas et al. | Experimental research on AUV manoeuvrability | |
| Gao et al. | Underwater Feature Comparison of a Fan-Wing, a Propeller and a Fixed-Wing |
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 |