CN112084574A - Ship additional mass and additional moment of inertia determining method based on neural network - Google Patents
Ship additional mass and additional moment of inertia determining method based on neural network Download PDFInfo
- Publication number
- CN112084574A CN112084574A CN202010800265.5A CN202010800265A CN112084574A CN 112084574 A CN112084574 A CN 112084574A CN 202010800265 A CN202010800265 A CN 202010800265A CN 112084574 A CN112084574 A CN 112084574A
- Authority
- CN
- China
- Prior art keywords
- ship
- additional
- inertia
- mass
- model
- 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 72
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 21
- 238000012360 testing method Methods 0.000 claims abstract description 56
- 239000011159 matrix material Substances 0.000 claims abstract description 29
- 238000004088 simulation Methods 0.000 claims abstract description 23
- 230000008569 process Effects 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 13
- 230000010355 oscillation Effects 0.000 claims description 43
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000006073 displacement reaction Methods 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 11
- 238000013016 damping Methods 0.000 claims description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 7
- 230000001133 acceleration Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 238000010998 test method Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 12
- 238000002474 experimental method Methods 0.000 description 5
- 238000013459 approach Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003534 oscillatory effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010561 standard procedure Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Mathematical Analysis (AREA)
- Aviation & Aerospace Engineering (AREA)
- Automation & Control Theory (AREA)
- Biomedical Technology (AREA)
- Aerodynamic Tests, Hydrodynamic Tests, Wind Tunnels, And Water Tanks (AREA)
- Mathematical Optimization (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Mathematics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
Abstract
The invention provides a method for determining additional mass and additional moment of inertia of a ship based on a neural network, which comprises the steps of firstly, solving the additional mass of the same test ship by using different methods, and determining a parameter interval and an experimental group number of the test ship; then establishing a motion model of the test ship and obtaining a target function and a constraint condition; then, a simulation model for testing the ship dynamic positioning system is built in the MATLAB, testing is carried out according to the determined group number of the weight matrix, and an optimal parameter scheme is obtained; and repeating the process to calculate the optimal parameter scheme of a plurality of ships with different ship types as a training sample of the neural network, and calculating the additional mass and the additional moment of inertia of any ship by using the obtained basic probability distribution. The invention has self-learning ability and better universality and generalization, and can meet the requirement of determining additional mass of different types of ships.
Description
Technical Field
The invention relates to the field of ships, in particular to a method for determining additional mass and additional moment of inertia of any ship by using simulation test data of various ship types as training samples of a neural network.
Background
One of the key problems to accurately predict the motion performance of a ship in waves is to accurately determine the additional mass and the damping coefficient of the ship. The additional mass when the vessel is in motion is closely related to the damping and fluid flow characteristics around the vessel. At present, there are many theoretical methods for forecasting the motion performance of a ship in waves, including a slice theory, an elongated body theory, a three-dimensional frequency domain theory, various improving methods thereof, and the like. Basically, the theoretical methods are established based on the linear potential flow theory, but due to the limitation of the linear potential flow theory, the influence of viscosity and nonlinearity is difficult to consider, and if no correction is carried out, the forecasting precision of the ship motion is poor.
At present, the experimental method of the additional mass and the damping of the ship mainly comprises the following steps: firstly, in a free attenuation experiment of ship swing, the experimental result can only give the additional mass and damping of the ship at the resonance frequency, and the frequency correlation is lacked; secondly, although the forced oscillatory motion experiment of the ship can give additional mass and damping under a plurality of frequencies, the analysis of the experiment result is still limited by sub samples, and in addition, the forced oscillatory motion of the ship model has higher requirements on experimental equipment and a test system.
And the additional masses obtained by various methods have errors of different degrees, but the standard methods are lacked as references, so that the accuracy of the additional mass values obtained by the various methods is difficult to evaluate, and further, the optimal additional mass cannot be selected as a parameter for controlling the motion of the ship.
Disclosure of Invention
The invention aims to provide a method for determining additional mass and additional moment of inertia of any ship by using simulation test data of various ship types as a training sample of a neural network.
Specifically, the invention provides a method for determining additional mass and additional moment of inertia of a ship based on a neural network, which comprises the following steps:
200, firstly establishing a motion model of a test ship, then converting the motion model into a linear form, then carrying out discretization treatment, carrying out optimization target design on the motion of the test ship to obtain a target function, and establishing constraint conditions according to the constraint configuration of a propeller of the test ship;
step 400, repeating step 100-300, calculating optimal parameter schemes of a plurality of ships with different ship types, then taking all the optimal parameter schemes as training samples of the neural network to obtain basic probability distribution values of target elements, and calculating additional mass and additional moment of inertia of any ship based on the basic probability distribution values.
In one embodiment of the present invention, the different methods in step 100 include regression equations, oscillation tests and geometric methods.
In one embodiment of the present invention, the regression formula method finds the formula of the additional mass as follows:
the formula for solving the additional moment of inertia by the regression formula method is as follows:
in the formula, m is the quality of the ship to be measured; m isx、myFor additional masses of surging, swaying, JzIs an additional moment of inertia.
In one embodiment of the present invention, the step of determining the additional mass value by the oscillation test method is as follows:
step 111, enabling the ship model-connecting rod to do longitudinal undamped oscillation, and determining an oscillation period calculation formula according to the relation between the oscillation circle frequency of the undamped oscillation coefficient and the elastic coefficient C and the mass m;
In one embodiment of the present invention, the geometric method finds the formula of the additional mass and the additional moment of inertia as follows:
and step 121, correcting the additional moment of inertia by using a subcritical ratio correction formula according to the difference between the ship body and the elliptic revolution body due to the asymmetrical head and tail shapes, and finally obtaining the corrected additional moment of inertia.
In one embodiment of the present invention, in the step 200, the process of establishing the motion model is as follows:
firstly, establishing a nonlinear ship motion model, which is expressed as follows:
converting the non-linear motion model into the form of a vector function:
wherein M represents a system inertia matrix, D represents a hydrodynamic linear damping coefficient matrix, v represents a velocity matrix,
representing an acceleration matrix, representing control force by tau, representing a matrix caused by environmental disturbance force by omega, converting the established motion model into a motion model
Can be expressed as:
and expanding the established motion model at the reference state point to be in a linear form:
in the formula, vrTo the desired speed of flight, τrIs the desired thrust.
In one embodiment of the present invention, in the step 200, the discretization process is implemented by a Forward-Euler method, which comprises the following specific steps:
assuming T as a sampling period, the rate of change of the acceleration deviation at time k can be obtained as follows:
by substituting formula (19) for
It is simplified as follows:
setting the prediction time domain of the control system as NPControl time domain as NcThe state of the control system at the future moment is expressed in a matrix form as:
in the formula, YkA matrix of motion states representing the vessel at a future time,
representing a speed deviation matrix, τ(k)Representing a control force matrix.
In one embodiment of the present invention, the constraint condition is expressed by the following formula for a control amount limit constraint and a control increment constraint in the control process, corresponding to a thrust and thrust moment constraint and a constraint of a thrust and thrust moment change rate:
in one embodiment of the present invention, in the step 300, the process of calculating the deviation between the actual path and the planned path in each set of tests is as follows:
firstly, the deviation is quantized and represented, and the quantization parameters comprise:
(1) correlation: the evaluation of the correlation is quantified by using a correlation coefficient R;
in the formula, xiRepresenting the displacement of the actual motion trajectory in one of the three degrees of freedom, pitch, yaw and yaw, yiRepresenting the displacement of the planned trajectory in this degree of freedom,
represents the average value of the displacement of the actual motion trajectory,
representing the displacement average value of the planning track on the degree of freedom, wherein n represents the number of data in simulation time, namely the cycle number;
(2) standard deviation of deviation S;
(3) the mean value of the deviation σ;
(4) maximum value of deviation: sigmamax：
And quantitatively judging the consistency between the actual track and the target track of the ship under different additional masses and additional moments of inertia through the obtained quantitative parameters, and selecting a correlation coefficient R, a standard deviation S of the deviation, an average deviation sigma and the corresponding additional mass and the corresponding additional moment of inertia when the average deviation sigma is minimum, namely the optimal additional mass scheme.
In one embodiment of the present invention, in step 400, the formula for calculating the additional mass and the additional moment of inertia of any ship is as follows:
Mx＝A1X·mx1+A2X·mx2+A3X·mx3 (29)
My＝B1Y·my1+B2Y·my3+B3X·my3 (30)
jz＝c1z*jz1+c2z*jz2+c3z*jz3 (31)
where Mx and My are the final determined additional masses and Jz is the additional moment of inertia.
The method obtains simulation test data under the optimal parameter scheme of various ship types as a training sample of the neural network, obtains a basic probability distribution value representing any ship after being processed by the neural network method, and can obtain the minimum additional mass and the minimum additional moment of inertia of any ship error rate through the basic probability distribution value. The invention also has self-learning ability, better universality and generalization and can meet the requirement of determining additional mass coefficients of different types of ships.
Drawings
FIG. 1 is a flow diagram of a validation method in accordance with one embodiment of the present invention;
FIG. 2 is a schematic flow chart of the calculation of additional mass values using the oscillation test method;
FIG. 3 is a schematic flow chart of the method for obtaining additional quality values using geometric methods;
FIG. 4 is a graph of the added mass and the added moment of inertia coefficients of an elliptical solid of revolution;
FIG. 5 is a block flow diagram of a MATLAB simulation model building process in accordance with one embodiment of the present invention;
FIG. 6 is a diagram illustrating the effect of the output of the simulation test according to an embodiment of the present invention.
Detailed Description
In recent years, with rapid progress in computer technology and computing technology, Computational Fluid Dynamics (CFD) has been developed. The numerical simulation in the aspect of ship water movement based on the CFD theory has the advantages of low cost, non-contact flow field measurement, no scale effect, capability of eliminating the influence of factors such as sensor size and model deformation on a flow field in a physical model experiment, capability of obtaining more detailed flow field information and the like, and is widely concerned, so that the scheme fully utilizes the CFD to correct the calculation errors of the additional mass and the additional moment of inertia of the ship.
The detailed structure and implementation process of the present solution are described in detail below with reference to specific embodiments and the accompanying drawings.
As shown in fig. 1, in one embodiment of the present invention, a method for determining an additional mass and an additional moment of inertia of a ship based on a neural network is disclosed, which comprises the following steps:
different methods selected by the embodiment include a regression formula method, an oscillation test method and a geometric method.
(1) The formula for solving the additional mass of the regression formula method is shown as follows:
the formula for solving the additional moment of inertia by the regression formula method is as follows:
in the formula, m is the quality of the ship to be measured; m isx、myFor additional masses of surging, swaying, JzIs an additional moment of inertia.
(2) The steps of the oscillation test method for obtaining the additional mass are as follows:
the link here indicates both the link and the device that drives the link.
Step 111, enabling the ship model-connecting rod to do longitudinal undamped oscillation, and determining an oscillation period calculation formula according to the relation between the oscillation circle frequency of the undamped oscillation coefficient and the elastic coefficient C and the mass m;
the relation among the oscillation circle frequency of the undamped oscillation coefficient, the elastic coefficient C and the mass m is as follows:
and the oscillation period calculation formula is as follows:
step 112 set the mass of the connecting rod to m0Measured oscillation period of T0(ii) a The mass of the ship model is m after the ship model is connected with the connecting rod0+ m, oscillation period measured in air, T1(ii) a Carrying out oscillation test on the ship model and the connecting rod in water, wherein the total mass of the ship model and the connecting rod is m0+m+mxMeasured oscillation period of T2；
The method comprises the following steps: t is0、T1、T2The calculation formula is as follows:
M in this stepxThe formula for the additional mass calculation is:
m obtainedyThe formula for the additional mass calculation is:
m obtainedyThe formula for the additional mass calculation is:
(3) the geometric method finds the formula of the additional mass and the additional moment of inertia as follows:
the calculation formula is as follows:
mx＝kxm (12)
in the formula, kx、kyAnd kzAs determined by fig. 4, the major axis is 2a and the minor axis is 2b as determined by fig. 4.
And step 121, correcting the additional moment of inertia by using a subcritical ratio correction formula according to the difference between the ship body and the elliptic revolution body due to the asymmetrical head and tail shapes, and finally obtaining the corrected additional moment of inertia.
The following equation is given for the correction of the additional moment of inertia:
(4) the way to determine the parameter intervals and experimental groups is as follows:
three groups of additional masses are determined by the three methods, and are respectively as follows:
| method of producing a composite material | Additional mass |
| Regression formula | (mx1,my1) |
| Shaking test | (mx2,my2) |
| Geometric method | (mx3,my3) |
Taking three groups of additional masses mxMinimum and maximum values of, and myIs determined as the interval of the parameter scheme is mxmin,mxmax]And [ m ]ymin,mymax](ii) a The experimental groups were further divided, and when the number of the experimental groups was X, the parameters of each experimental group are shown in the following table.
| Experimental group | Experimental group 1 | Experimental group 2 | Experimental group 3 | Experimental group 4 | Experimental group 5 | .... |
| mx | ||||||
| my |
Wherein the additional mass data of each experimental group is filled according to the experimental results.
200, firstly establishing a motion model of a test ship, then converting the motion model into a linear form, then carrying out discretization treatment, carrying out optimization target design on the motion of the test ship to obtain a target function, and establishing constraint conditions according to the constraint configuration of a propeller of the test ship;
(1) the process of building a motion model according to the particular test vessel under study is as follows:
firstly, establishing a nonlinear ship motion model, which is expressed as follows:
the nonlinear motion model is written in the form of a vector function, and since the nonlinear model of the ship motion is converted into a linear model in the modeling process, and the linear model is also used in the subsequent steps, the linear motion model of the ship is directly given here.
Wherein M represents a system inertia matrix, D represents a hydrodynamic linear damping coefficient matrix, v represents a velocity matrix,
representing an acceleration matrix, representing control force by tau, representing a matrix caused by environmental disturbance force by omega, converting the established motion model into a motion model
Can be expressed as:
and (3) expanding the established motion model at the reference state point (the expected speed and the heading) into a linear form:
in the formula, vrTo the desired speed of flight, τrIs the desired thrust (in a state satisfying the desired speed, heading, there should be the desired thrust corresponding to that state).
(2) Discretization is carried out by a Forward-Euler method, T is a sampling period, and the change rate of the acceleration deviation at the k moment can be obtained as follows:
by substituting formula (18) into
It is simplified as follows:
setting the prediction time domain of the control system as NPControl time domain as NcThe state of the system at the future time is expressed in the form of a matrix:
in the formula, YkA matrix of motion states representing the vessel at a future time,
representing a speed deviation matrix, τ(k)Representing a control force matrix.
(3) The process of obtaining the objective function is as follows:
the control law is obtained by quadratic programming, and in the control of the ship motion, the optimization target is as follows:
1) the current spatial position is converged to a reference value as soon as possible (the position and heading of the ship are enabled to be as fast as possible to approach the expected position and heading, even if the deviation of the position and heading approaches zero as soon as possible);
2) the current motion state is converged to a reference value as soon as possible (the speed and the heading of the ship are enabled to be as fast as possible to approach to an expected position and heading, even if the deviation of the speed and the heading approaches zero as soon as possible);
3) the control amount is minimum (the thrust is minimum, and the deviation between the thrust and 0 is minimum);
the bias is generally considered as a sum of squares, and to account for the contribution of each part, so considered as a weighted sum of squares, can be expressed as follows:
min(η-ηr)TQ(η-ηr)+(v-vr)TR(v-vr)+τTPτ (24)
the constraint conditions mainly consider control quantity limit constraints and control increment constraints in the control process, namely thrust and thrust moment constraints and thrust moment change rate constraints, and can be expressed in the following form:
the built simulation model is as shown in fig. 5, the planned path is input into the simulation model, and the simulation model works to output the actual track of the ship.
The effect graph of the simulation test output is shown in fig. 6, in which graph (a) is a comparison between the planned path and the simulated trajectory in the surging direction, the solid line represents the planned path, and the dotted line represents the actual trajectory; FIG. b is a comparison of the planned path and the simulated trajectory in the sway direction, with the solid line representing the planned path and the dashed line representing the actual trajectory; fig. c is a comparison of the planned path and the simulated trajectory in the heading direction, the solid line representing the planned path and the dotted line representing the actual trajectory.
The process of selecting the optimal parameter scheme is as follows:
correlation: the evaluation of the correlation is quantified by using a correlation coefficient R;
in the formula, xiRepresenting the displacement of the actual motion trajectory in one of the three degrees of freedom, pitch, yaw and yaw, yiRepresenting the displacement of the planned trajectory in this degree of freedom, x representing the displacement average of the actual movement trajectory,
the displacement average value of the planning track in the degree of freedom is shown, and n represents the number of data in simulation time, namely the cycle number.
Standard deviation of deviation S;
the mean deviation σ;
maximum value of deviation: sigmamax。
The obtained three quantitative parameters can quantitatively judge the consistency between the actual track and the target track of the ship under different additional masses and additional moments of inertia, and a correlation coefficient R, a standard deviation S of deviation, an average deviation sigma, and the corresponding additional mass and the corresponding additional moment of inertia when the average deviation sigma is minimum are selected, so that the optimal additional mass scheme is obtained.
Step 400, repeating step 100-300, calculating optimal parameter schemes of a plurality of ships with different ship types, then taking all the optimal parameter schemes as training samples of the neural network to obtain basic probability distribution of target elements, and calculating additional mass and additional moment of inertia of any ship based on the basic probability distribution value.
The neural network training process is as follows:
the method comprises the steps of establishing a series of samples by utilizing data of various ship types, training a neural network, establishing a BP neural network by using an MATLAB tool box, limiting network output to a (0,1) interval by using a logsig function as an activation function under the condition that convergence precision and convergence speed are optimal, using a train function, using a learnpbm function as a learning function, and performing network training by taking a target error value as 0.001.
And after n times of training, the network tends to be stable, and the network training is finished. At this time, the sample set can be input into the neural network for identification to obtain decision output of the BP neural network, and the output result is normalized to obtain the basic probability distribution of the target element.
The additional mass and the additional moment of inertia of any ship are calculated as follows:
Mx＝A1X·mx1+A2X·mx2+A3X·mx3 (29)
My＝B1Y·my1+B2Y·my3+B3X·my3 (30)
jz＝c1z*jz1+c2z*jz2+c3z*jz3 (31)
in the formula, Mx and My are the finally determined additional mass and additional moment of inertia.
The embodiment acquires simulation test data under various ship type optimal parameter schemes, the simulation test data are used as training samples of the neural network, basic probability distribution values representing any ship are obtained after the simulation test data are processed by the neural network method, and the additional mass and the additional moment of inertia with the minimum error rate of any ship can be obtained through the basic probability distribution values. The invention also has self-learning ability, better universality and generalization and can meet the requirement of determining additional mass coefficients of different types of ships.
Thus, it should be appreciated by those skilled in the art that while a number of exemplary embodiments of the invention have been illustrated and described in detail herein, many other variations or modifications consistent with the principles of the invention may be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Accordingly, the scope of the invention should be understood and interpreted to cover all such other variations or modifications.
Claims (10)
1. A ship additional mass and additional moment of inertia determining method based on a neural network is characterized by comprising the following steps:
step 100, solving the additional mass and the additional moment of inertia of the same test ship by using different methods, and determining the parameter interval and the experimental group number of the additional mass and the additional moment of inertia according to the additional mass and the additional moment of inertia;
200, firstly establishing a motion model of a test ship, then converting the motion model into a linear form, then carrying out discretization treatment, carrying out optimization target design on the motion of the test ship to obtain a target function, and establishing constraint conditions according to the constraint configuration of a propeller of the test ship;
step 300, building a simulation model of a test ship dynamic positioning system in MATLAB according to a motion model, an objective function and constraint conditions, testing the simulation model in a corresponding quantity according to the number of groups of determined weight matrixes to calculate the deviation between an actual path and a planned path in each group of tests, and then selecting an optimal parameter scheme of the test ship;
step 400, repeating step 100-300, calculating optimal parameter schemes of a plurality of ships with different ship types, then taking all the optimal parameter schemes as training samples of the neural network to obtain basic probability distribution values of target elements, and calculating additional mass and additional moment of inertia of any ship based on the basic probability distribution values.
2. The determination method according to claim 1,
the different methods in step 100 include regression equations, oscillation tests and geometric methods.
3. The determination method according to claim 2,
the formula for solving the additional mass by the regression formula method is as follows:
the formula for solving the additional moment of inertia by the regression formula method is as follows:
in the formula, m is the quality of the ship to be measured; m isx、myFor additional masses of surging, swaying, JzIs an additional moment of inertia.
4. The determination method according to claim 2,
the steps of the oscillation test method for obtaining the additional quality value are as follows:
step 110, placing a ship model with mass m in a water tank, wherein the front end of the ship model is connected with a flat spring with elastic coefficient C through a connecting rod, and the rear end of the ship model is rigidly fixed on a test bed;
step 111, enabling the ship model-connecting rod to do longitudinal undamped oscillation, and determining an oscillation period calculation formula according to the relation between the oscillation circle frequency of the undamped oscillation coefficient and the elastic coefficient C and the mass m;
step 112, setting the mass of the connecting rod as m0Measured oscillation period of T0(ii) a The mass of the ship model is m after the ship model is connected with the connecting rod0+ m, oscillation period measured in air, T1(ii) a Carrying out oscillation test on the ship model and the connecting rod in water, wherein the total mass of the ship model and the connecting rod is m0+m+mxMeasured oscillation period of T2；
Step 113, according to the oscillation period calculation formula, eliminating the mass m of the connecting rod0And the elastic coefficient C is used for obtaining the additional mass m of the ship modelx(ii) a The step 110 and 113 are repeated, only the ship model-connecting rod is changed to do transverse undamped oscillation, so that the additional mass m can be obtainedy(ii) a Repeat step 110-113 by changing only the ship model-connecting rodWithout damping oscillation of the bow, so that an additional moment of inertia J can be obtainedZ。
5. The determination method according to claim 2,
the formula for the geometric method to find the additional mass and the additional moment of inertia is as follows:
step 120, regarding the test ship as an elliptical revolving body, taking the ship length as the major axis and twice the draft as the minor axis, and calculating the correction additional mass of the test ship through a subcritical ratio correction formula according to the difference between the shape of the ship body and the elliptical revolving body;
and step 121, correcting the additional moment of inertia by using a subcritical ratio correction formula according to the difference between the ship body and the elliptic revolution body due to the asymmetrical head and tail shapes, and finally obtaining the corrected additional moment of inertia.
6. The determination method according to claim 1,
in step 200, the process of establishing the motion model is as follows:
firstly, establishing a nonlinear ship motion model, which is expressed as follows:
converting the non-linear motion model into the form of a vector function:
wherein M represents a system inertia matrix, D represents a hydrodynamic linear damping coefficient matrix, v represents a velocity matrix,
representing an acceleration matrix, representing control force by tau, representing a matrix caused by environmental disturbance force by omega, converting the established motion model into a motion model
Can be expressed as:
and expanding the established motion model at the reference state point to be in a linear form:
in the formula, vrTo the desired speed of flight, τrIs the desired thrust.
7. The determination method according to claim 1,
in the step 200, the discretization is realized by a Forward-Euler method, and the specific process is as follows:
assuming T as a sampling period, the rate of change of the acceleration deviation at time k can be obtained as follows:
by substituting formula (19) for
It is simplified as follows:
setting the prediction time domain of the control system as NPControl time domain as NcThe state of the control system at the future moment is expressed in a matrix form as:
in the formula, YkA matrix of motion states representing the vessel at a future time,
representing a speed deviation matrix, τ(k)Representing a control force matrix.
8. The determination method according to claim 1,
the constraint conditions are expressed by the following formula aiming at the control quantity limit constraint and the control increment constraint in the control process, corresponding to the thrust and thrust moment constraint and the constraint of the thrust and thrust moment change rate:
9. the determination method according to claim 1,
in step 300, the process of calculating the deviation between the actual path and the planned path in each set of tests is as follows:
firstly, the deviation is quantized and represented, and the quantization parameters comprise:
(1) correlation: the evaluation of the correlation is quantified by using a correlation coefficient R;
in the formula, xiRepresenting the displacement of the actual motion trajectory in one of the three degrees of freedom, pitch, yaw and yaw, yiRepresenting the displacement of the planned trajectory in this degree of freedom,
represents the average value of the displacement of the actual motion trajectory,
representing the displacement average value of the planning track on the degree of freedom, wherein n represents the number of data in simulation time, namely the cycle number;
(2) standard deviation of deviation S;
(3) the mean value of the deviation σ;
(4) maximum value of deviation: sigmamax：
And quantitatively judging the consistency between the actual track and the target track of the ship under different additional masses and additional moments of inertia through the obtained quantitative parameters, and selecting a correlation coefficient R, a standard deviation S of the deviation, an average deviation sigma and the corresponding additional mass and the corresponding additional moment of inertia when the average deviation sigma is minimum, namely the optimal additional mass scheme.
10. The determination method according to claim 1,
in step 400, the formula for calculating the additional mass and the additional moment of inertia of any ship is as follows:
Mx＝A1X·mx1+A2X·mx2+A3X·mx3 (29)
My＝B1Y·my1+B2Y·my3+B3X·my3 (30)
jz＝c1z*jz1+c2z*jz2+c3z*jz3 (31)
where Mx and My are the final determined additional masses and Jz is the additional moment of inertia.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010800265.5A CN112084574B (en) | 2020-08-11 | 2020-08-11 | Ship additional mass and additional moment of inertia determining method based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010800265.5A CN112084574B (en) | 2020-08-11 | 2020-08-11 | Ship additional mass and additional moment of inertia determining method based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112084574A true CN112084574A (en) | 2020-12-15 |
| CN112084574B CN112084574B (en) | 2024-04-19 |
Family
ID=73734937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010800265.5A Active CN112084574B (en) | 2020-08-11 | 2020-08-11 | Ship additional mass and additional moment of inertia determining method based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112084574B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101859147A (en) * | 2010-06-11 | 2010-10-13 | 哈尔滨工程大学 | Ship course intelligent coordination control method |
| CN108846207A (en) * | 2018-06-15 | 2018-11-20 | 哈尔滨工程大学 | A kind of ship movement prediction device and its forecasting procedure based on Non-linear Model Identification |
| KR20180126730A (en) * | 2017-05-18 | 2018-11-28 | (주)세이프텍리서치 | Autonomous navigation system using ship dynamics model |
| CN109656143A (en) * | 2019-02-25 | 2019-04-19 | 曲阜师范大学 | A kind of sea drives the adaptive tracking control method and system of ship entirely |
| CN110647041A (en) * | 2019-10-11 | 2020-01-03 | 大连海事大学 | Unmanned ship model full-coefficient accurate identification method |
| CN110737986A (en) * | 2019-10-15 | 2020-01-31 | 大连海事大学 | unmanned ship energy efficiency intelligent optimization simulation system and method |
-
2020
- 2020-08-11 CN CN202010800265.5A patent/CN112084574B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101859147A (en) * | 2010-06-11 | 2010-10-13 | 哈尔滨工程大学 | Ship course intelligent coordination control method |
| KR20180126730A (en) * | 2017-05-18 | 2018-11-28 | (주)세이프텍리서치 | Autonomous navigation system using ship dynamics model |
| CN108846207A (en) * | 2018-06-15 | 2018-11-20 | 哈尔滨工程大学 | A kind of ship movement prediction device and its forecasting procedure based on Non-linear Model Identification |
| CN109656143A (en) * | 2019-02-25 | 2019-04-19 | 曲阜师范大学 | A kind of sea drives the adaptive tracking control method and system of ship entirely |
| CN110647041A (en) * | 2019-10-11 | 2020-01-03 | 大连海事大学 | Unmanned ship model full-coefficient accurate identification method |
| CN110737986A (en) * | 2019-10-15 | 2020-01-31 | 大连海事大学 | unmanned ship energy efficiency intelligent optimization simulation system and method |
Non-Patent Citations (2)
| Title |
|---|
| MINHO LEE, HYEUNG-SIK CHOI: "A robust neural controller for underwater robot manipulators", IEEE TRANSACTIONS ON NEURAL NETWORKS, vol. 11, no. 6, XP011039544 * |
| 仇明;张贺;金博文;曾骥;: "基于RBF神经网络的船舶路径跟踪控制建模及仿真", 海洋工程装备与技术, no. 05 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112084574B (en) | 2024-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114117840B (en) | Structural performance prediction method based on simulation and test data hybrid drive | |
| CN110631792B (en) | Seismic hybrid test model updating method based on convolutional neural network | |
| CN106568647B (en) | A kind of Strength Forecast of Concrete method neural network based | |
| CN106446424A (en) | Unsteady aerodynamic model parameter prediction method | |
| CN106597852A (en) | MEMS gyroscope temperature compensation method based on RBF neural network | |
| CN114510887B (en) | Method for rapidly predicting liquid level of large container under ocean condition based on proxy model | |
| CN104899642B (en) | Large deformation flexible body dynamic stress compensation method based on hybrid production style | |
| CN114611416A (en) | LS-SVM modeling method for nonlinear unsteady aerodynamic characteristics of missile | |
| CN116933400B (en) | Method for constructing aerodynamic moment model of coupling uncertainty | |
| CN112084574B (en) | Ship additional mass and additional moment of inertia determining method based on neural network | |
| CN117708985A (en) | Machine learning-based high-speed double-spin unsteady aerodynamic prediction method | |
| CN114030008B (en) | Industrial robot practical training energy consumption measurement method based on data driving | |
| Milovanović et al. | Adaptive control of nonlinear MIMO system with orthogonal endocrine intelligent controller | |
| CN113158297B (en) | Hydraulic arc steel gate parameter load identification method | |
| CN115033977B (en) | Ground actually-measured pulsating pressure parameter identification method based on neural network technology | |
| CN112327666A (en) | Method for determining target function weight matrix of power cruise system control model | |
| Ghosh Roy et al. | Longitudinal aircraft parameter estimation using neuro-fuzzy and genetic algorithm based method | |
| Gubarev et al. | Identification in cognitive maps in the impulse processes mode with full information | |
| Simsek et al. | System Identification and Handling Quality Analysis of a UAV from Flight Test Data | |
| Nguyen | Machine learning in the calibration process of discrete particle model | |
| CN115081318B (en) | Artificial bata ray based on antagonistic neural network method for predicting experimental data of aircraft | |
| Chen et al. | Intelligent prediction method for linear wave load based on deep neural network | |
| Othman et al. | Surrogate model of aerodynamic model toward efficient digital flight | |
| Su | Design and Research on Modification Method of Finite Element Dynamic Model of Concrete Beam Based on Convolutional Neural Network | |
| Dichev et al. | Models for analysis of dynamic error for instruments, measuring parameters of moving objects |
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 |