CN117094249A - Wave reduction method, model training method, device, electronic equipment and medium - Google Patents
Wave reduction method, model training method, device, electronic equipment and medium Download PDFInfo
- Publication number
- CN117094249A CN117094249A CN202311055830.XA CN202311055830A CN117094249A CN 117094249 A CN117094249 A CN 117094249A CN 202311055830 A CN202311055830 A CN 202311055830A CN 117094249 A CN117094249 A CN 117094249A
- Authority
- CN
- China
- Prior art keywords
- breakwater
- parameter
- control speed
- sample data
- parameters
- 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
- 238000000034 method Methods 0.000 title claims abstract description 75
- 230000009467 reduction Effects 0.000 title claims abstract description 70
- 238000012549 training Methods 0.000 title claims abstract description 53
- 230000007613 environmental effect Effects 0.000 claims abstract description 68
- 238000011156 evaluation Methods 0.000 claims description 81
- 230000006870 function Effects 0.000 claims description 58
- 239000007788 liquid Substances 0.000 claims description 38
- 230000009471 action Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 16
- 230000008859 change Effects 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 8
- 230000008901 benefit Effects 0.000 abstract description 8
- 230000000875 corresponding effect Effects 0.000 description 43
- 238000001514 detection method Methods 0.000 description 16
- 238000005070 sampling Methods 0.000 description 15
- 238000004088 simulation Methods 0.000 description 12
- 230000001276 controlling effect Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 8
- 239000012530 fluid Substances 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000001788 irregular Effects 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 238000009434 installation Methods 0.000 description 3
- 230000035699 permeability Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013016 damping Methods 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000000116 mitigating effect Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- BIIBYWQGRFWQKM-JVVROLKMSA-N (2S)-N-[4-(cyclopropylamino)-3,4-dioxo-1-[(3S)-2-oxopyrrolidin-3-yl]butan-2-yl]-2-[[(E)-3-(2,4-dichlorophenyl)prop-2-enoyl]amino]-4,4-dimethylpentanamide Chemical compound CC(C)(C)C[C@@H](C(NC(C[C@H](CCN1)C1=O)C(C(NC1CC1)=O)=O)=O)NC(/C=C/C(C=CC(Cl)=C1)=C1Cl)=O BIIBYWQGRFWQKM-JVVROLKMSA-N 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000013506 data mapping Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/11—Hard structures, e.g. dams, dykes or breakwaters
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Fluid Mechanics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computing Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Revetment (AREA)
Abstract
The disclosure relates to a wave reduction method, a model training method, a device, electronic equipment and a medium, wherein the environmental characteristic parameters and breakwater state parameters of a breakwater are obtained, the environmental characteristic parameters comprise wave characteristic parameters, the breakwater state parameters comprise breakwater kinematics parameters, the control speed parameters of the breakwater are determined based on the environmental characteristic parameters and the breakwater state parameters, and the breakwater is controlled to perform wave reduction based on the control speed parameters of the breakwater. Compared with the prior art, the embodiment of the disclosure has the following advantages: according to the embodiment of the disclosure, the breakwater can be controlled to conduct wave reduction more accurately according to the environmental characteristic parameters and the breakwater state parameters, so that incoming waves can be reduced more efficiently, the wave reduction and the utilization capacity of the breakwater can be improved, and the damage degree of waves to coastal structures and offshore operation platforms is reduced.
Description
Technical Field
The disclosure relates to the technical field of coastal engineering, in particular to a wave reduction method, a model training method, a device, electronic equipment and a medium.
Background
Continuous wave flapping is extremely prone to irrecoverable losses to coastal structures and offshore platforms. For example, sea waves may damage structures such as seawalls, lakes, wharfs, bridges, etc., and destroy their stability and raise safety hazards. As another example, sea waves may cause vibration and vibration of the offshore platform, increasing the risk to operators and possibly even causing equipment damage.
In order to reduce as much as possible the severe loss of sea waves to the coastal structure and the offshore platform, it is necessary to apply a breakwater to the structure. The breakwater is applied in consideration of not only the performance of the breakwater against wave reduction but also the water permeability, environmental friendliness and simplicity of installation and maintenance of the breakwater. In the prior art, a passive control strategy is generally adopted, and a passively-controlled undulating flat breakwater (passive control breakwater) is good in water permeability, environmental friendliness and simplicity in installation and maintenance, and is good in marine environmental parameters.
Because of a plurality of nonlinear factors existing in the interaction of the sea wave and the structure, and the moment of the sea wave changes, when the structure or the offshore operation platform is protected by adopting the passive control breakwater, the sea wave cannot be continuously and efficiently reduced, the problems of sea wave reduction and weaker utilization capacity of the breakwater exist, the problem that the wave reduction efficiency is low in practical application, and the coastal structure and the offshore operation platform are easily damaged is caused.
Disclosure of Invention
In order to solve the technical problems described above, or at least partially solve the technical problems described above, the present disclosure provides a wave reduction method, a model training method, a device, an electronic apparatus, and a medium.
In a first aspect, embodiments of the present disclosure provide a wave reduction method comprising:
acquiring environmental characteristic parameters and breakwater state parameters of the position of the breakwater, wherein the environmental characteristic parameters comprise wave characteristic parameters, and the breakwater state parameters comprise breakwater kinematics parameters;
determining a control speed parameter of the breakwater based on the environmental characteristic parameter and the breakwater state parameter;
and controlling the breakwater to perform wave reduction based on the control speed parameter of the breakwater.
In a second aspect, embodiments of the present disclosure provide a model training method, the method comprising:
acquiring a plurality of groups of sample data, wherein each group of sample data in the plurality of groups of sample data comprises a sample environment characteristic parameter and a sample breakwater state parameter;
training a control speed parameter determination model based on each group of sample data to obtain a control speed parameter of each group of sample data;
Acquiring a reward function evaluation parameter corresponding to the control speed parameter of each group of sample data;
updating model parameters of a control speed parameter determination model based on each group of sample data, a control speed parameter of each group of sample data and a corresponding reward function evaluation parameter;
and if the reward function evaluation parameter corresponding to the control speed parameter obtained by the updated control speed parameter determination model is the maximum value, obtaining a trained control speed parameter determination model.
In a third aspect, embodiments of the present disclosure provide a wave reduction device comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring environmental characteristic parameters and breakwater state parameters at the position of a breakwater, the environmental characteristic parameters comprise wave characteristic parameters, and the breakwater state parameters comprise breakwater kinematics parameters;
a determining module, configured to determine a control speed parameter of the breakwater based on the environmental characteristic parameter and the breakwater state parameter;
and the control module is used for controlling the breakwater to carry out wave reduction based on the control speed parameter of the breakwater.
In a fourth aspect, an embodiment of the present disclosure provides a model training apparatus, including:
The system comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for acquiring a plurality of groups of sample data, and each group of sample data in the plurality of groups of sample data comprises a sample environment characteristic parameter and a sample breakwater state parameter;
the first obtaining module is used for training the control speed parameter determining model based on each group of sample data to obtain the control speed parameter of each group of sample data;
the second acquisition module is used for acquiring the reward function evaluation parameters corresponding to the control speed parameters of each group of sample data;
the updating module is used for updating the model parameters of the control speed parameter determination model based on each group of sample data, the control speed parameter of each group of sample data and the corresponding reward function evaluation parameter;
and the second obtaining module is used for obtaining a trained control speed parameter determining model if the reward function evaluation parameter corresponding to the control speed parameter obtained by the updated control speed parameter determining model is the maximum value.
In a fifth aspect, embodiments of the present disclosure provide an electronic device, including:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method according to the first or second aspect.
In a sixth aspect, embodiments of the present disclosure provide a computer readable storage medium having stored thereon a computer program for execution by a processor to implement the method of the first or second aspects.
In a seventh aspect, the presently disclosed embodiments also provide a computer program product comprising a computer program or instructions which, when executed by a processor, implement the method according to the first or second aspect.
According to the wave reduction method, the model training method, the device, the electronic equipment and the medium, the environmental characteristic parameters and the breakwater state parameters of the position of the breakwater are obtained, the environmental characteristic parameters comprise wave characteristic parameters, the breakwater state parameters comprise breakwater kinematics parameters, the control speed parameters of the breakwater are determined based on the environmental characteristic parameters and the breakwater state parameters, and the breakwater is controlled to perform wave reduction based on the control speed parameters of the breakwater. Compared with the prior art, the embodiment of the disclosure has the following advantages: according to the embodiment of the disclosure, the breakwater can be controlled to conduct wave reduction more accurately according to the environmental characteristic parameters and the breakwater state parameters, so that incoming waves can be reduced more efficiently, the wave reduction and the utilization capacity of the breakwater can be improved, and the damage degree of waves to coastal structures and offshore operation platforms is reduced.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
In order to more clearly illustrate the embodiments of the present disclosure or the solutions in the prior art, the drawings that are required for the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a flow chart of a wave abatement method provided by an embodiment of the present disclosure;
FIG. 2 is a flow chart of a wave abatement method provided by another embodiment of the present disclosure;
FIG. 3 is a flow chart of a model training method provided by an embodiment of the present disclosure;
FIG. 4 is a flow chart of a model training method provided in another embodiment of the present disclosure;
FIG. 5 is a schematic view of a wave abatement device provided in an embodiment of the present disclosure;
FIG. 6 is a schematic structural diagram of a model training apparatus according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure.
Detailed Description
In order that the above objects, features and advantages of the present disclosure may be more clearly understood, a further description of aspects of the present disclosure will be provided below. It should be noted that, without conflict, the embodiments of the present disclosure and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced otherwise than as described herein; it will be apparent that the embodiments in the specification are only some, but not all, embodiments of the disclosure. The specific embodiments described herein are to be considered in an illustrative rather than a restrictive sense. All other embodiments, which are obtained by a person skilled in the art based on the described embodiments of the invention, fall within the scope of protection of the invention.
Because of a plurality of nonlinear factors existing in the interaction of the sea wave and the structure, and the moment of the sea wave changes, when the structure or the offshore operation platform is protected by adopting the passive control breakwater, the sea wave cannot be continuously and efficiently reduced, the problems of sea wave reduction and weaker utilization capacity of the breakwater exist, the problem that the wave reduction efficiency is low in practical application, and the coastal structure and the offshore operation platform are easily damaged is caused.
In response to this problem, embodiments of the present disclosure provide a wave abatement method, which is described below in connection with particular embodiments.
Fig. 1 is a flow chart of a wave reduction method provided by an embodiment of the present disclosure. The execution main body of the method is electronic equipment, and the electronic equipment can actively control the breakwater. The electronic equipment can be portable mobile equipment such as a notebook computer, a breakwater terminal, a Personal Digital Assistant (PDA), a staff wearable equipment and the like; the system can also be a fixed device such as a personal computer, an intelligent household appliance, a server and the like, wherein the server can be a single server, can be a server cluster, and can be a distributed cluster or a centralized cluster. The method can be applied to a scene of wave reduction, can more accurately control the breakwater to reduce waves according to environmental characteristic parameters and breakwater state parameters, further can more efficiently reduce incoming waves, can improve the wave reduction and the utilization capacity of the breakwater, can maximally exert the wave reduction performance of the breakwater under different sea conditions, and reduces the damage degree of waves to coastal structures and offshore operation platforms. It can be appreciated that the data fragment adjustment method provided by the embodiment of the present disclosure may also be applied in other scenarios.
The wave reduction method shown in fig. 1 is described below, and includes the following steps:
s101, acquiring environmental characteristic parameters and breakwater state parameters of the position of the breakwater, wherein the environmental characteristic parameters comprise wave characteristic parameters, and the breakwater state parameters comprise breakwater kinematics parameters.
In the embodiment of the disclosure, the breakwater may be a flat breakwater with a relief shape, or may be another type of breakwater, which is not limited herein. The electronic device obtains the environmental characteristic parameter of the position of the breakwater, which can be the actual environmental characteristic parameter of the position of the breakwater, or the environmental characteristic parameter obtained based on historical data or model simulation. For example, the breakwater is installed at an offshore structure or a deepwater work platform, and a wave data detection unit is arranged at the position, and the environmental characteristic parameter can be actual data observed. For another example, the environmental characteristic parameter may be more accurate numerical simulation data obtained by performing numerical simulation based on the model.
Optionally, the environmental characteristic parameter comprises a wave characteristic parameter. The wave characteristic parameter is a parameter for characterizing the wave characteristics of the sea state. The wave characteristic parameters include the wave height of the current incoming wave and the speed at which the wave height varies in the vertical direction. In some embodiments, the speed at which the wave height of the incoming wave varies in the vertical direction may be calculated based on the wave height of the current incoming wave.
In some embodiments of the present disclosure, the electronic device may calculate a speed at which the wave height of the incoming wave changes in the vertical direction through the wave height of the incoming wave collected by the wave data detection unit and the sampling time interval. Specifically, V can be used w =(H t -H t-1 )/t s Calculating the velocity V of the incoming wave with the wave height changing in the vertical direction w Wherein H is t For the wave height data collected at the current moment, H t-1 Representing wave height data collected at a previous time. The sampling time interval of each data is t s Representing, i.e., the sampling interval between two sets of data. Alternatively, the sampling interval may be narrowed to more precisely calculate the speed at which the wave height of the incoming wave changes in the vertical direction. It should be noted that the narrowing of the sampling interval is only for calculating a speed parameter of the wave height of the incoming wave that varies in the vertical direction, the sampling interval for the wave height of the incoming wave remains unchanged.
The breakwater state characteristic parameter may be an actual breakwater state characteristic parameter, or may be a breakwater state characteristic parameter obtained based on historical data or based on a simulation model. For example, the breakwater is provided with a movement state detection unit, and the characteristic parameter of the breakwater state may be detected actual data when the breakwater moves. For another example, the breakwater state characteristic parameter may be accurate breakwater state characteristic data detected in history or data obtained based on numerical simulation.
Optionally, the breakwater state characteristic parameter comprises a breakwater kinematics parameter. The breakwater kinematics parameter is a parameter for characterizing the current movement state of the breakwater. The breakwater kinematics parameters include a positional deviation parameter of the breakwater from an initial position and a movement speed parameter. In some embodiments, the movement speed parameter of the breakwater may be calculated based on the positional deviation parameter of the breakwater.
In some embodiments of the present disclosure, the electronic device may calculate the movement speed parameter of the breakwater through the breakwater position deviation parameter acquired by the movement state detection unit. In particular, V can be used b =(D t -D t-1 )/t s Calculating the movement speed parameter V of the breakwater b Wherein D is t For the position deviation parameter data of the breakwater in the vertical direction acquired at the current moment, D t-1 And the position deviation parameter data of the breakwater in the vertical direction, which is acquired at the last moment, is shown. The sampling time interval of each data is t s Meaning that the sampling time interval coincides with the sampling time interval of the wave data detection unit, i.e. the sampling interval between two sets of data. Alternatively, the sampling interval may be narrowed for more accurate calculation of the movement speed parameter of the breakwater. It should be noted that the narrowing of the sampling interval is only for calculating the movement speed parameter of the breakwater, and the sampling interval for the breakwater positional deviation parameter data is kept unchanged.
S102, determining a control speed parameter of the breakwater based on the environmental characteristic parameter and the breakwater state parameter.
In some alternative embodiments, the electronic device determines a control speed parameter of the breakwater based on the environmental characteristic parameter and the breakwater status parameter. For example, the control speed parameter of the breakwater may be determined based on an algorithm, or determined according to a correspondence of the control speed parameter with the environmental characteristic parameter and the breakwater state parameter.
In some embodiments, when wave reduction is performed on a specific incoming wave, the output of the control speed parameter should be performed based on the history of such specific incoming wave and the history action evaluation value in that case, or based on the history of incoming wave similar to such an incoming wave and the history data of the history action evaluation value in that case.
And S103, controlling the breakwater to reduce waves based on the control speed parameters of the breakwater.
The electronic equipment can control the breakwater to carry out wave reduction according to the control speed parameter of the breakwater. In embodiments of the present disclosure, the subject of active control is a breakwater, e.g., a heave plate breakwater. Specifically, an actively controlled undulating type single-plate breakwater with a power output unit connected below is to be used, for example, a control speed parameter of the breakwater is input into the power output unit, and a damping action corresponding to the control speed parameter is performed by the power output unit, so that wave damping is realized.
The breakwater in the embodiments of the present disclosure may be installed in different sea environments. For example, the device may be installed in a near-shore protection access structure, and may be installed near a deep-sea work platform to protect the work platform.
In specific application, the breakwater can be installed in a near-shore environment, and according to environmental incoming waves, the breakwater is controlled to adopt corresponding actions for maximizing wave-absorbing efficiency, so that the protection of offshore coasts, offshore structures and some deep sea operation platforms is realized. For example, the undulating flat breakwater has the characteristics of good water permeability, environmental friendliness, easiness in installation and the like. However, in practical situations, the passive undulating slab breakwater only can exert a better effect in a specific wave environment, so that the undulating slab breakwater needs to be actively controlled, and the wave-absorbing efficiency under various wave environments is maximized while the advantages of the undulating slab breakwater are ensured.
According to the embodiment of the disclosure, the environmental characteristic parameters and the breakwater state parameters of the position of the breakwater are obtained, the environmental characteristic parameters comprise wave characteristic parameters, the breakwater state parameters comprise breakwater kinematics parameters, the control speed parameters of the breakwater are determined based on the environmental characteristic parameters and the breakwater state parameters, and the breakwater is controlled to conduct wave reduction based on the control speed parameters of the breakwater. Compared with the prior art, the embodiment of the disclosure has the following advantages: according to the embodiment of the disclosure, the breakwater can be controlled to conduct wave reduction more accurately according to the environmental characteristic parameters and the breakwater state parameters, so that incoming waves can be reduced more efficiently, the wave reduction and the utilization capacity of the breakwater can be improved, and the damage degree of waves to coastal structures and offshore operation platforms is reduced.
Fig. 2 is a flow chart of a wave reduction method according to another embodiment of the present disclosure, as shown in fig. 2, the method includes the following steps:
s201, acquiring environmental characteristic parameters and breakwater state parameters of the position of the breakwater, wherein the environmental characteristic parameters comprise wave characteristic parameters, and the breakwater state parameters comprise breakwater kinematics parameters.
Specifically, the implementation process and principle of S201 and S101 are consistent, and will not be described herein.
S202, training the control speed parameter determination model to obtain a trained control speed parameter determination model.
In this embodiment, the electronic device constructs a control speed parameter determination model, and further trains the control speed parameter determination model to obtain a trained control speed parameter determination model.
In some embodiments, training sample data for some unknown sea states is obtained by numerical simulation of actual sea states. In this case, the active control speed parameter obtaining method may further include determining a sea state wave simulation model through an actual sea state wave parameter, and obtaining the sample environmental characteristic parameter through the sea state wave simulation model.
The sea state wave simulation model is a model for simulating environmental characteristic parameters at the position of the breakwater. The environmental characteristic parameter may be a model constructed based on computational fluid dynamics CFD (Computational Fluid Dynamics). The breakwater is placed in a numerical pool as an object to be controlled.
Specifically, a numerical pool is established through computational fluid dynamics software, wherein the numerical pool comprises a CFD calculation sub-module, a numerical wave generation sub-module, a numerical wave elimination sub-module and an active control sub-module.
In some embodiments of the present disclosure, the electronic device implements the CFD calculation sub-module by solving an incompressible stokes equation. Specifically, by the formula
The continuity equation, momentum equation and fluid volume transport equation over the time domain are calculated by the above equations. σ, ρ and f represent the cauchy stress, density and water body force tensor, respectively. Meanwhile, s= (u, v, w) is a time-averaged velocity field. F represents the transport volume of the fluid, water when f=1, air domain when f=0, and junction between the two domains when 0< F < 1.
In some embodiments of the present disclosure, the electronic device creates irregular waves that conform to the actual wave spectrum, simulating actual sea state wave conditions, through the velocity wave-making boundary. Specifically, by the formula
The irregular wave parameters based on the Pierson-Moskowitz (P-M) spectrum can be calculated by the above formula. Wherein N represents the number of constituent waves, ω max And omega min The frequencies representing the maximum and minimum component waves may be selected within a suitable range. Δω represents ω i+1 And omega i Difference between them. Will omega i Bringing into the spectrum equation to obtain S (f i ). Wherein H is s And f p Respectively representing the sense wave height and the spectral peak frequency. And calculating the wave parameters of the irregular wave through the P-M spectrum, and then generating the corresponding irregular wave through the speed inlet.
In some embodiments of the present disclosure, it should be noted that, to ensure accuracy of the model, a numerical wave cancellation sub-module needs to be provided at the tail of the numerical pool to ensure authenticity of the model simulation. Specifically, by the formula
The numerical clipping of the numerical pool can be realized through the formula. Where S and c represent the horizontal-vertical integration speed and the wave speed. c represents a ratio approximation to parameter c, a 0 、a 1 、b 1 Represents the adjustment parameters, and eta r ,η m And eta t The reflected wave height, the wave height measured at the wave-making boundary and the target free liquid level are indicated, respectively. By the method, wave elimination can be realized at the tail of the numerical pool, so that actual sea state waves can be better simulated.
It should be noted that, whether it is a CFD calculation sub-module, a numerical wave-making sub-module or a numerical wave-eliminating sub-module, the accuracy and the effectiveness of the numerical wave-making sub-module need to be verified before simulation is applied, so as to ensure that the simulation result meets the practical situation.
S203, inputting the environmental characteristic parameters and the breakwater state parameters into a trained control speed parameter determination model to obtain the control speed parameters of the breakwater.
After the trained control speed parameter determination model is obtained, the electronic equipment inputs the environmental characteristic parameters and the breakwater state parameters into the trained control speed parameter determination model, and the control speed parameters of the breakwater are output through the trained control speed parameter determination model.
In some embodiments of the disclosure, the control speed parameter determination model realizes the control of the breakwater through the active control submodule according to the control speed parameter obtained by the environmental characteristic parameter and the breakwater state parameter. And converting the output control speed parameter into the current position deviation parameter of the breakwater, and further converting the current position deviation parameter into a control signal of the power output unit, so as to realize active control of the breakwater.
In some embodiments, the control speed parameter determination model is a deep reinforcement learning model for obtaining the control speed parameter according to the wave characteristic parameter of the incoming wave and the kinetic parameter of the breakwater, so as to realize wave reduction maximization. In the embodiment of the disclosure, the control speed parameter determination model is trained based on a plurality of sets of sample data and reward function evaluation parameters. Each group of sample data comprises sample wave characteristic parameters and sample breakwater kinematics parameters, the reward function evaluation parameters are based on wave height related data detected by a wave data detection unit positioned behind the breakwater, the reward function evaluation parameters corresponding to the control speed parameters of each group of sample data are calculated based on the wave height related data, and the reward function evaluation parameters are used for representing the evaluation of the control speed parameters.
S204, calculating stroke parameters of the breakwater based on the control speed parameters of the breakwater.
In this step, the control speed parameter of the breakwater of the electronic device calculates the stroke parameter of the breakwater. For example, the control speed parameter is converted into a stroke parameter of the breakwater based on the current breakwater state.
Specifically, by the formulaCalculating a stroke parameter D of the power take-off unit t . Wherein D is t-1 Indicating the position of the breakwater at the previous moment, a and t s Respectively, the acceleration over the time interval and the time interval. The wave reduction performance of the breakwater is maximized by controlling the stroke parameters of the power output unit.
And S205, controlling the breakwater to execute the stroke action corresponding to the stroke parameter of the breakwater to perform wave reduction.
Further, the electronic device determines a stroke action corresponding to the stroke parameter of the breakwater, and controls the breakwater to execute the stroke action corresponding to the stroke parameter of the breakwater to perform wave reduction. Specifically, the motion stroke parameters are input into the power output unit, and the power output unit executes the stroke action corresponding to the motion stroke parameters, so that the active control of the breakwater is finished, and the wave reduction maximization is realized.
Compared with the prior art, the embodiment of the disclosure has the following advantages: the control speed parameter determination model is trained by acquiring environmental characteristic parameters and breakwater state parameters of the position of the breakwater, wherein the environmental characteristic parameters comprise wave characteristic parameters, the breakwater state parameters comprise breakwater kinematics parameters, and the trained control speed parameter determination model is obtained. Further, the environmental characteristic parameter and the breakwater state parameter are input into a trained control speed parameter determination model to obtain a control speed parameter of the breakwater, and the stroke parameter of the breakwater is calculated based on the control speed parameter of the breakwater. And further controlling the breakwater to execute the stroke action corresponding to the stroke parameter of the breakwater to reduce waves. According to the embodiment of the disclosure, the breakwater can be controlled to conduct wave reduction more accurately according to the environmental characteristic parameters and the breakwater state parameters, so that incoming waves can be reduced more efficiently, the wave reduction and the utilization capacity of the breakwater can be improved, and the damage degree of waves to coastal structures and offshore operation platforms is reduced.
Fig. 3 is a flowchart of a model training method according to an embodiment of the disclosure, as shown in fig. 3, where the method includes the following steps:
s301, acquiring a plurality of groups of sample data, wherein each group of sample data comprises a sample environment characteristic parameter and a sample breakwater state parameter.
The sets of sample data are training data for training a control speed parameter determination model. Each set of sample data includes a sample environmental characteristic parameter and a sample breakwater status characteristic parameter.
S302, training a control speed parameter determination model based on each group of sample data to obtain the control speed parameter of each group of sample data.
After the multiple sets of sample data are obtained, the electronic device can train the pre-constructed control speed parameter determination model by adopting the sample data to obtain the control speed parameter of each set of sample data.
Alternatively, the control speed parameter determination model may be various types of models, for example, deep-reinforcement learning models that have been widely used such as deep q-Networks (DQN), doubleDQN, proximalPolicyOptimization (PPO), twindelayeddpg (TD 3), and softactator-Critic (SAC).
S303, acquiring the reward function evaluation parameters corresponding to the control speed parameters of each group of sample data.
And the electronic equipment acquires the reward function evaluation parameters corresponding to the control speed parameters of each group of sample data. The evaluation parameter of the rewarding function is an evaluation value calculated based on the relevant data of the wave height detected behind the breakwater and the designed rewarding function after the breakwater executes corresponding reduction action according to the control speed parameter.
S304, updating model parameters of a control speed parameter determination model based on each group of sample data, the control speed parameter of each group of sample data and the corresponding reward function evaluation parameter.
And the electronic equipment updates the model parameters of the control speed parameter determination model according to each group of sample data, the control speed parameter of each group of sample data and the corresponding reward function evaluation parameter.
In the embodiment of the present disclosure, after each set of sample data, the control speed parameter of each set of sample data, and the corresponding bonus function evaluation parameter are obtained, the model parameters of the control speed parameter determination model may be updated using the following steps S3041-S3043.
Step S3041, training the action evaluation network.
In the embodiment of the disclosure, the action evaluation network is used for evaluating the score condition of the currently adopted control speed parameter under the premise of considering the future action. It should be noted that each training is based on a set of sample data of size, control speed parameters and bonus function evaluation parameters, the size can be any number, typically the size is typically 32, 64, 128 and 256, etc., as the performance of the algorithm allows. The formula can be constructed in specific applications Method of gradient descent to reduce motion estimation network Loss parameter Loss c For the purpose, the control speed parameter determination model is updated. Wherein,n is the number of sample data, control speed parameters and bonus function evaluation parameters in a training batch, S t At the current representation of sample data, a t Representing a control speed parameter, R t Represents the bonus function evaluation parameter, Q (x) represents the scoring parameter of the sample data-control speed parameter data pair x, and x represents the sample data-control speed parameter data pair. At the same time [ R t +εQ′ min (S t ,a t )] 2 Considered as a scoring parameter of the sample data-control speed parameter data versus x taking into account the entire control process. Therefore, loss c And may also be understood as the error between the predicted scoring parameters and the actual scoring parameters.
In the embodiment of the present disclosure, it is noted that there are four action evaluation networks for the whole control evaluation process, respectively: an evaluation network 1, an evaluation network 2, a final evaluation network 1 and a final evaluation network 2. The evaluation network is used for evaluating the temporary score of the current sample data-control speed parameter data pair in the current situation, and the final evaluation network is used for final scoring of the current sample data-control speed parameter data pair in consideration of the entire control process. In use, the minimum value of the two is selected, so that over-selection of parameters is avoided, and the local optimum value is trapped.
Step S3042, training a control speed parameter output network.
In the embodiment of the disclosure, the control speed parameter output network is used for outputting corresponding control speed parameters according to the currently input sample data. The formula can be constructed in specific applicationsLoss parameter Loss of output network based on control speed parameter by gradient descent method a And updating the control speed parameter determination model. Wherein N is the number of sample data, control speed parameters and bonus function evaluation parameters in a training batch, S t At the current representation of sample data, a t Representing a control speed parameter. Alpha is a weight used to adjust entropy. Q (Q) min (x) The minimum scoring parameter for the sample data-control speed parameter data pair x is represented.
And step S3043, realizing soft update on the final evaluation network.
In the embodiment of the disclosure, after a certain number of rounds of training are completed, the final evaluation network needs to be updated. In a specific application, the formula Q can be constructed i ′←τQ i ′+(1-τ)Q i I=1, 2 achieves soft update for the final evaluation network. Wherein Q is i ' represents the ith final evaluation network, Q i Representing the ith evaluation network, τ represents the soft update parameters. Through the formula, the final evaluation network is updated.
And S305, obtaining a trained control speed parameter determination model if the reward function evaluation parameter corresponding to the control speed parameter obtained by the updated control speed parameter determination model is the maximum value.
And if the reward function evaluation parameter corresponding to the control speed parameter obtained by the updated control speed parameter determination model is the maximum value, completing the training of the control speed parameter determination model, and obtaining a trained control speed parameter determination model.
Compared with the prior art, the embodiment of the disclosure has the following advantages: the control speed parameter determining model is trained through a plurality of groups of sample data, and further, based on each group of sample data, the control speed parameter of each group of sample data and the corresponding reward function evaluation parameter, the model parameter of the control speed parameter determining model is updated, if the reward function evaluation parameter corresponding to the control speed parameter obtained through the updated control speed parameter determining model is the maximum value, the trained control speed parameter determining model is obtained, and the accuracy of the control speed parameter determining model can be improved, so that the accuracy of the output control speed parameter is improved.
Fig. 4 is a flowchart of a model training method according to another embodiment of the present disclosure, as shown in fig. 4, the method includes the following steps:
s401, acquiring a plurality of groups of sample data, wherein each group of sample data comprises a sample environment characteristic parameter and a sample breakwater state parameter.
Specifically, the implementation process and principle of S401 and S301 are identical, and will not be described herein.
S402, carrying out normalization processing on each group of sample data to obtain each group of sample normalization data.
Normalizing each set of sample data may better eliminate training errors that may occur due to different scale data. The normalization of each group of sample data can accelerate the training of the model to a certain extent, and the final effect of the model training is improved.
After a large amount of sample data is obtained, the sample data can be subjected to data processing, so that the training performance of the control speed parameter determination model trained based on the sample data is enhanced. One available data processing method is to normalize the acquired sample data. By passing throughImplementing sample data mapping to [0,1 ]]Normalization of the interval ranges, calculated to normalized sample data +. >Where x is the sample data collected, x min Is the minimum value of preset corresponding parameters, x max Is the maximum value of preset corresponding parameters. In addition, byMapping of sample data to [ -1,1 can be achieved]Normalization processing of the interval, calculating to obtain normalized sample data +.>In practical application, the characteristic parameters of the sample environment are determined, and the wave data detection unit can be adopted for detection; the state parameters of the sample breakwater are determined, and the detection can be performed by adopting a motion state detection unit. Combining the sample environmental characteristic parameter and the sample breakwater state parameter into sample data, and performing sample dataAnd normalizing to obtain normalized sample data.
S403, training the control speed parameter determination model based on the sample normalization data of each group to obtain the control speed parameter of each group of sample data.
After obtaining the normalized data of each set of samples, the electronic device may train the pre-constructed control speed parameter determination model by using the normalized data of each set of samples, so as to obtain the control speed parameter of each set of sample data.
S404, acquiring wave height related data detected behind the breakwater after wave reduction according to the control speed parameter of each group of sample data.
Optionally, a wave height detection unit is arranged behind the breakwater, and the wave height detection unit behind the breakwater is used for detecting wave height related data, namely transmitted wave height parameter data, detected behind the breakwater, and the wave height related data is used for subsequently calculating the evaluation parameter of the reward function.
Optionally, the wave height related data detected behind the breakwater includes free liquid level data and a change speed of the free liquid level in a vertical direction.
In some embodiments, S404 includes, but is not limited to, S4041, S4042, S4043:
s4041, acquiring free liquid level data detected behind the breakwater after wave reduction according to the control speed parameter of each group of sample data.
The electronic equipment acquires free liquid level data detected behind the breakwater based on a wave height detection unit behind the breakwater, wherein the free liquid level data detected behind the breakwater are the free liquid level data acquired after wave reduction by using the control speed parameters of each group of sample data.
S4042, calculating the change speed of the free liquid level in the vertical direction based on the free liquid level data.
Can be represented by formula V w =(H t -H t-1 )/t s Calculating to obtain the change speed of the free liquid level height in the vertical directionDegree V w Wherein H is t For the free liquid level data collected at the current moment, H t-1 Representing free liquid level data collected at a previous time. The sampling time interval of each data is t s Representing, i.e., the sampling interval between two sets of data.
S4043, normalizing the free liquid level data and the change speed of the free liquid level in the vertical direction to obtain normalized wave height related data, wherein the normalized wave height related data comprises normalized free liquid level data and the change speed of the normalized free liquid level in the vertical direction.
And S405, calculating a reward function evaluation parameter corresponding to the control speed parameter of each group of sample data based on the wave height related data.
And the electronic equipment calculates a reward function evaluation parameter corresponding to the control speed parameter of each group of sample data according to the wave height related data detected behind the breakwater.
In some embodiments, S405 includes, but is not limited to, S4051, S4052, S4053, S4054:
s4051, calculating the height difference between the free liquid level height data and the sense wave height to obtain a direct evaluation parameter.
S4052, calculating the ratio of the breakwater position deviation parameter to the maximum position deviation parameter, and determining the ratio as a position deviation penalty term.
S4053, comparing the breakwater position deviation parameter with the maximum position deviation parameter, and determining a preset value as a serious position deviation punishment item if the breakwater position deviation parameter is larger than the maximum position deviation parameter.
S4054, linearly adding the direct evaluation parameter, the position offset penalty term and the serious position offset penalty term to obtain a reward function evaluation parameter.
In particular, a formula can be constructed
Calculating a reward function evaluation parameter R corresponding to transmitted wave reduction after the breakwater executes the control speed parameter t . Wherein the parameter gamma (m -1 ) And lambda are the sensitivity coefficient for the data of the square wave height detection unit behind the breakwater and the current offset position parameter Z of the breakwater respectively t From the maximum offset position Z m Sensitivity coefficient of the ratio. Psi and H s The threshold limiting coefficient and the sense wave height of the sea state wave environment are respectively represented. η (eta) t5 And | represents free liquid level data detected by a wave height detection unit behind the breakwater at the present moment. R is R t The evaluation of the control speed parameter is divided into two cases: 1) In z t <z m In the case of (2), gamma (ψHs-eta) t5 I) represents a direct evaluation parameter of the data of the breakwater post-wave height detection unit, and is used for representing the effect of the current control speed parameter on incoming wave reduction. When the current control speed parameter is positive, the current control speed parameter plays a positive role in reducing incoming waves; when it is negative, it means that the current control speed parameter has a negative effect on the reduction effect of the incoming wave, or, in other words, has an effect that is not within an ideal range.The degree of deflection of the breakwater is evaluated, which has only a negative value, and the evaluation of the current control speed parameter is more negative as it approaches the maximum deflection position. Combining the above gamma (ψHs- |eta) t5 I) item and->The items being co-formed at z t <z m Evaluation parameter R of reward function in case t . 2) In z t ≥z m When the current control speed parameter causes the position deviation of the breakwater to exceed the maximum position deviation, the bonus function evaluation parameter R t Being set to a preset value, for example-10, indicates that the current action is strictly prohibited.
S406, updating model parameters of a control speed parameter determination model based on each group of sample data, the control speed parameter of each group of sample data and the corresponding reward function evaluation parameter.
Specifically, the implementation process and principle of S406 and S305 are identical, and will not be described herein.
And S407, if the reward function evaluation parameter corresponding to the control speed parameter obtained by the updated control speed parameter determination model is the maximum value, obtaining a trained control speed parameter determination model.
Specifically, the implementation process and principle of S407 and S305 are consistent, and will not be described here again.
Compared with the prior art, the embodiment of the disclosure has the following advantages: and carrying out normalization processing on each group of sample data by acquiring a plurality of groups of sample data, wherein each group of sample data in the plurality of groups of sample data comprises a sample environment characteristic parameter and a sample breakwater state parameter, so as to obtain each group of sample normalized data, and training a control speed parameter determination model based on each group of sample normalized data, so as to obtain the control speed parameter of each group of sample data. Further, wave height related data detected behind the breakwater after wave reduction is carried out according to the control speed parameters of each group of sample data are obtained, and rewarding function evaluation parameters corresponding to the control speed parameters of each group of sample data are calculated based on the wave height related data. And updating the model parameters of the control speed parameter determination model based on each group of sample data, the control speed parameter of each group of sample data and the corresponding reward function evaluation parameter, if the reward function evaluation parameter corresponding to the control speed parameter obtained by the updated control speed parameter determination model is the maximum value, obtaining a trained control speed parameter determination model, improving the accuracy of the control speed parameter determination model, further improving the accuracy of the output control speed parameter, subsequently controlling the breakwater according to the control speed parameter to perform wave reduction, further efficiently reducing incoming waves, improving the utilization capacity of the wave reduction and the breakwater, and reducing the damage degree of waves to coastal structures and offshore operation platforms.
Fig. 5 is a schematic structural view of a wave reduction device provided in an embodiment of the present disclosure. The wave mitigation device may be an electronic apparatus as in the above embodiments, or the wave mitigation device may be a component or assembly in the electronic apparatus. The wave reduction device provided by the embodiments of the present disclosure may perform the process flow provided by the embodiments of the wave reduction method, as shown in fig. 5, the wave reduction device 50 includes: an acquisition module 51, a determination module 52, a control module 53; the acquiring module 51 is configured to acquire an environmental characteristic parameter and a breakwater state parameter at a location where the breakwater is located, where the environmental characteristic parameter includes a wave characteristic parameter, and the breakwater state parameter includes a breakwater kinematic parameter; a determining module 52 is configured to determine a control speed parameter of the breakwater based on the environmental characteristic parameter and the breakwater status parameter; the control module 53 is configured to control the breakwater to perform wave reduction based on a control speed parameter of the breakwater.
Optionally, when the determining module 52 determines the control speed parameter of the breakwater based on the environmental characteristic parameter and the breakwater state parameter, the determining module is specifically configured to: and inputting the environmental characteristic parameters and the breakwater state parameters into a trained control speed parameter determination model to obtain the control speed parameters of the breakwater.
Optionally, before the environmental characteristic parameter and the breakwater state parameter are input into the trained control speed parameter determination model, the determination module 52 is further configured to: and training the control speed parameter determining model to obtain a trained control speed parameter determining model.
Optionally, the control module 53 is specifically configured to, when controlling the breakwater to perform wave reduction based on the control speed parameter of the breakwater: calculating a stroke parameter of the breakwater based on the control speed parameter of the breakwater; and controlling the breakwater to execute the stroke action corresponding to the stroke parameter of the breakwater to reduce waves.
The wave reduction device of the embodiment shown in fig. 5 may be used to implement the technical solution of the above method embodiment, and its implementation principle and technical effects are similar, and will not be described here again.
Fig. 6 is a schematic structural diagram of a model training device according to an embodiment of the disclosure. The model training apparatus may be the electronic device of the above embodiment, or the model training apparatus may be a part or component in the electronic device. The model training apparatus provided in the embodiment of the present disclosure may execute the processing flow provided in the embodiment of the model training method, as shown in fig. 6, the model training apparatus 60 includes: a first acquisition module 61, a first obtaining module 62, a second acquisition module 63, an updating module 64, a second obtaining module 65; the first obtaining module 61 is configured to obtain a plurality of sets of sample data, where each set of sample data in the plurality of sets of sample data includes a sample environmental characteristic parameter and a sample breakwater state parameter; the first obtaining module 62 is configured to train the control speed parameter determination model based on the each set of sample data, so as to obtain a control speed parameter of each set of sample data; the second obtaining module 63 is configured to obtain a reward function evaluation parameter corresponding to the control speed parameter of each set of sample data; the updating module 64 is configured to update model parameters of the control speed parameter determination model based on each set of sample data, a control speed parameter of each set of sample data, and a corresponding bonus function evaluation parameter; the second obtaining module 65 is configured to obtain a trained control speed parameter determination model if the reward function evaluation parameter corresponding to the control speed parameter obtained by the updated control speed parameter determination model is the maximum value.
Optionally, before training the control speed parameter determining model based on the sample data of each set to obtain the control speed parameter of each sample data of each set, the model training device 60 further includes: a normalization module 66; the normalization module is used for carrying out normalization processing on each group of sample data to obtain each group of sample normalization data;
the first obtaining module 62 is specifically configured to, when training the control speed parameter determining model based on the sample data of each group to obtain the control speed parameter of each group of sample data: and training the control speed parameter determination model based on the normalized data of each group of samples to obtain the control speed parameter of each group of sample data.
Optionally, when the second obtaining module 63 obtains the reward function evaluation parameter corresponding to the control speed parameter of each set of sample data, the method is specifically used for: acquiring wave height related data detected behind the breakwater after wave reduction by using the control speed parameters of each group of sample data; and calculating a reward function evaluation parameter corresponding to the control speed parameter of each group of sample data based on the wave height related data.
Optionally, the wave height related data includes free liquid level data and a change speed of the free liquid level in a vertical direction;
The second obtaining module 63 is specifically configured to, when obtaining the wave height related data detected behind the breakwater after the wave is reduced according to the control speed parameter of each set of sample data: acquiring free liquid level height data detected behind the breakwater after wave reduction by using the control speed parameters of each group of sample data; calculating a change speed of the free liquid level in the vertical direction based on the free liquid level data; normalizing the free liquid level data and the change speed of the free liquid level in the vertical direction to obtain normalized wave height related data, wherein the normalized wave height related data comprises normalized free liquid level data and the change speed of the normalized free liquid level in the vertical direction.
Optionally, when the second obtaining module 63 calculates the bonus function evaluation parameter corresponding to the control speed parameter of each set of sample data based on the wave height related data, the method is specifically configured to: calculating the height difference between the free liquid level height data and the sense wave height to obtain a direct evaluation parameter; calculating the ratio of the breakwater position deviation parameter to the maximum position deviation parameter, and determining the ratio as a position deviation punishment item; comparing the breakwater position deviation parameter with the maximum position deviation parameter, and if the breakwater position deviation parameter is larger than the maximum position deviation parameter, determining a preset value as a serious position deviation punishment item; and linearly adding the direct evaluation parameter, the position offset penalty term and the serious position offset penalty term to obtain a reward function evaluation parameter.
The model training device of the embodiment shown in fig. 6 may be used to implement the technical solution of the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein again.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure. The electronic device may be an electronic device as described in the above embodiments. The electronic device provided in the embodiment of the present disclosure may execute the processing flow provided in the embodiment of the wave reduction method, as shown in fig. 7, the electronic device 70 includes: memory 71, processor 72, computer programs and communication interface 73; wherein a computer program is stored in the memory 71 and configured to be executed by the processor 72 for performing the wave reduction method as described above.
In addition, the embodiments of the present disclosure also provide a storage medium having stored thereon a computer program that is executed by a processor to implement the wave reduction method described in the above embodiments.
Furthermore, embodiments of the present disclosure provide a computer program product comprising a computer program or instructions which, when executed by a processor, implements a wave reduction method as described above.
It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
In some embodiments, the client, server, etc. may communicate using any currently known or future developed network protocol, such as HTTP (hypertext transfer protocol), etc., and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to:
acquiring environmental characteristic parameters and breakwater state parameters of the position of the breakwater, wherein the environmental characteristic parameters comprise wave characteristic parameters, and the breakwater state parameters comprise breakwater kinematics parameters;
determining a control speed parameter of the breakwater based on the environmental characteristic parameter and the breakwater state parameter;
And controlling the breakwater to perform wave reduction based on the control speed parameter of the breakwater.
In addition, the electronic device may also perform other steps in the wave reduction method as described above.
Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including, but not limited to, an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing is merely a specific embodiment of the disclosure to enable one skilled in the art to understand or practice the disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown and described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (13)
1. A method of wave abatement, comprising:
acquiring environmental characteristic parameters and breakwater state parameters of the position of the breakwater, wherein the environmental characteristic parameters comprise wave characteristic parameters, and the breakwater state parameters comprise breakwater kinematics parameters;
determining a control speed parameter of the breakwater based on the environmental characteristic parameter and the breakwater state parameter;
and controlling the breakwater to perform wave reduction based on the control speed parameter of the breakwater.
2. The method of claim 1, wherein the determining a control speed parameter of the breakwater based on the environmental characteristic parameter and the breakwater status parameter comprises:
and inputting the environmental characteristic parameters and the breakwater state parameters into a trained control speed parameter determination model to obtain the control speed parameters of the breakwater.
3. The method of claim 2, wherein prior to said inputting the environmental characteristic parameter and the breakwater status parameter into the trained control speed parameter determination model, the method further comprises:
And training the control speed parameter determining model to obtain a trained control speed parameter determining model.
4. The method of claim 1, wherein controlling the breakwater for wave abatement based on the control speed parameter of the breakwater comprises:
calculating a stroke parameter of the breakwater based on the control speed parameter of the breakwater;
and controlling the breakwater to execute the stroke action corresponding to the stroke parameter of the breakwater to reduce waves.
5. A method of model training, the method comprising:
acquiring a plurality of groups of sample data, wherein each group of sample data in the plurality of groups of sample data comprises a sample environment characteristic parameter and a sample breakwater state parameter;
training a control speed parameter determination model based on each group of sample data to obtain a control speed parameter of each group of sample data;
acquiring a reward function evaluation parameter corresponding to the control speed parameter of each group of sample data;
updating model parameters of a control speed parameter determination model based on each group of sample data, a control speed parameter of each group of sample data and a corresponding reward function evaluation parameter;
And if the reward function evaluation parameter corresponding to the control speed parameter obtained by the updated control speed parameter determination model is the maximum value, obtaining a trained control speed parameter determination model.
6. The method of claim 5, wherein the training the control speed parameter determination model based on each set of sample data further comprises, prior to obtaining the control speed parameter for each set of sample data:
carrying out normalization processing on each group of sample data to obtain each group of sample normalization data;
training the control speed parameter determination model based on each set of sample data to obtain the control speed parameter of each set of sample data, including:
and training the control speed parameter determination model based on the normalized data of each group of samples to obtain the control speed parameter of each group of sample data.
7. The method of claim 5, wherein obtaining the bonus function evaluation parameter corresponding to the control speed parameter of each set of sample data comprises:
acquiring wave height related data detected behind the breakwater after wave reduction by using the control speed parameters of each group of sample data;
And calculating a reward function evaluation parameter corresponding to the control speed parameter of each group of sample data based on the wave height related data.
8. The method of claim 7, wherein the wave height related data comprises free liquid level data and a rate of change of free liquid level in a vertical direction;
the acquiring the wave height related data detected behind the breakwater after wave reduction according to the control speed parameter of each group of sample data comprises the following steps:
acquiring free liquid level height data detected behind the breakwater after wave reduction by using the control speed parameters of each group of sample data;
calculating a change speed of the free liquid level in the vertical direction based on the free liquid level data;
normalizing the free liquid level data and the change speed of the free liquid level in the vertical direction to obtain normalized wave height related data, wherein the normalized wave height related data comprises normalized free liquid level data and the change speed of the normalized free liquid level in the vertical direction.
9. The method of claim 8, wherein calculating the bonus function evaluation parameter corresponding to the control speed parameter for each set of sample data based on the wave height related data comprises:
Calculating the height difference between the free liquid level height data and the sense wave height to obtain a direct evaluation parameter;
calculating the ratio of the breakwater position deviation parameter to the maximum position deviation parameter, and determining the ratio as a position deviation punishment item;
comparing the breakwater position deviation parameter with the maximum position deviation parameter, and if the breakwater position deviation parameter is larger than the maximum position deviation parameter, determining a preset value as a serious position deviation punishment item;
and linearly adding the direct evaluation parameter, the position offset penalty term and the serious position offset penalty term to obtain a reward function evaluation parameter.
10. A wave reduction device, comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring environmental characteristic parameters and breakwater state parameters at the position of a breakwater, the environmental characteristic parameters comprise wave characteristic parameters, and the breakwater state parameters comprise breakwater kinematics parameters;
a determining module, configured to determine a control speed parameter of the breakwater based on the environmental characteristic parameter and the breakwater state parameter;
and the control module is used for controlling the breakwater to carry out wave reduction based on the control speed parameter of the breakwater.
11. A model training device, comprising:
the system comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for acquiring a plurality of groups of sample data, and each group of sample data in the plurality of groups of sample data comprises a sample environment characteristic parameter and a sample breakwater state parameter;
the first obtaining module is used for training the control speed parameter determining model based on each group of sample data to obtain the control speed parameter of each group of sample data;
the second acquisition module is used for acquiring the reward function evaluation parameters corresponding to the control speed parameters of each group of sample data;
the updating module is used for updating the model parameters of the control speed parameter determination model based on each group of sample data, the control speed parameter of each group of sample data and the corresponding reward function evaluation parameter;
and the second obtaining module is used for obtaining a trained control speed parameter determining model if the reward function evaluation parameter corresponding to the control speed parameter obtained by the updated control speed parameter determining model is the maximum value.
12. An electronic device, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1-9.
13. A computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the method according to any of claims 1-9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311055830.XA CN117094249A (en) | 2023-08-21 | 2023-08-21 | Wave reduction method, model training method, device, electronic equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311055830.XA CN117094249A (en) | 2023-08-21 | 2023-08-21 | Wave reduction method, model training method, device, electronic equipment and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117094249A true CN117094249A (en) | 2023-11-21 |
Family
ID=88769354
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311055830.XA Pending CN117094249A (en) | 2023-08-21 | 2023-08-21 | Wave reduction method, model training method, device, electronic equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117094249A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118313162A (en) * | 2024-05-30 | 2024-07-09 | 广东海洋大学 | Ocean pasture wave-absorbing method and device |
-
2023
- 2023-08-21 CN CN202311055830.XA patent/CN117094249A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118313162A (en) * | 2024-05-30 | 2024-07-09 | 广东海洋大学 | Ocean pasture wave-absorbing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10197040B2 (en) | Optimal control of wave energy converters | |
CN117094249A (en) | Wave reduction method, model training method, device, electronic equipment and medium | |
CN108090614A (en) | A kind of space wind field prediction model method for building up based on related coefficient | |
Amann et al. | Model predictive control of a nonlinear 2-body point absorber wave energy converter with estimated state feedback | |
WO2023216946A1 (en) | Drift speed prediction method and apparatus, computing device, and storage medium | |
JP7156613B2 (en) | Tsunami prediction device, method and program | |
Zhang et al. | Improved Continuous Wavelet Transform for Modal Parameter Identification of Long‐Span Bridges | |
Shashank et al. | Impact of varying landfall time and cyclone intensity on storm surges in the Bay of Bengal using ADCIRC model | |
CN116863906B (en) | Building structure noise monitoring and sound insulation processing method | |
CN103699650A (en) | Message propagation prediction method and message propagation prediction device | |
CN117113798A (en) | Drift velocity prediction method, device, equipment and storage medium for floating object | |
Fouskitakis et al. | Functional series TARMA modelling and simulation of earthquake ground motion | |
CN110210152A (en) | A kind of ultra harmonics source modeling method | |
Gu et al. | Power maximising control of a heaving point absorber wave energy converter | |
Tulus et al. | Sea level prediction by using seasonal autoregressive integrated moving average model, case study in semarang, indonesia | |
CN117195672A (en) | Training method and device for wave-induced drift model, computing equipment and storage medium | |
CN110146276B (en) | Cable force and bending rigidity monitoring method and system based on wireless sensor | |
CN112100894B (en) | Method and system for recognizing impact load of flexible antenna structure | |
JP2007309785A (en) | Characteristic vibration mode extraction method, device, and program | |
Nevarez et al. | Feedback resonating control for a wave energy converter | |
CN111428342B (en) | Random dynamic load identification method based on frequency domain spectrum decomposition | |
KR102205175B1 (en) | Modular dynamic analysis system based on wireless communication using always vibration of structure | |
Sheng et al. | Short-term prediction of an artificial neural network in an oscillating water column | |
CN109635326B (en) | Mechanical structure and aviation hydraulic pipeline vibration failure sensitivity analysis method | |
CN109061652B (en) | Detection efficiency evaluation method of underwater acoustic networking detection system |
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 |