CN113642105A - Multi-scale model construction method and device of ship power system and electronic equipment - Google Patents
Multi-scale model construction method and device of ship power system and electronic equipment Download PDFInfo
- Publication number
- CN113642105A CN113642105A CN202110887548.2A CN202110887548A CN113642105A CN 113642105 A CN113642105 A CN 113642105A CN 202110887548 A CN202110887548 A CN 202110887548A CN 113642105 A CN113642105 A CN 113642105A
- Authority
- CN
- China
- Prior art keywords
- dimensional simulation
- simulation
- model
- power system
- dimensional
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 38
- 238000004088 simulation Methods 0.000 claims abstract description 404
- 230000008878 coupling Effects 0.000 claims abstract description 74
- 238000010168 coupling process Methods 0.000 claims abstract description 74
- 238000005859 coupling reaction Methods 0.000 claims abstract description 74
- 239000013598 vector Substances 0.000 claims abstract description 57
- 238000000034 method Methods 0.000 claims abstract description 47
- 239000011159 matrix material Substances 0.000 claims abstract description 44
- 230000005540 biological transmission Effects 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 30
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 26
- 230000006870 function Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 238000013461 design Methods 0.000 claims description 8
- 239000012530 fluid Substances 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012546 transfer Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000009411 base construction Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000005577 local transmission Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a multi-scale model construction method and device of a ship power system and electronic equipment, wherein the multi-scale model construction method of the ship power system comprises the following steps: dividing a ship power system into a plurality of levels, and constructing a coupling simulation frame based on the plurality of levels; wherein, the coupling simulation framework includes: the transmission relation between a one-dimensional simulation model and a three-dimensional simulation reduced model of the ship power system; acquiring a three-dimensional simulation database of a corresponding local part or equipment of a ship power system, and acquiring a data matrix of a target parameter based on a coupling simulation frame and the three-dimensional simulation database; extracting a characteristic vector corresponding to the maximum characteristic value of the data matrix, constructing an intrinsic orthogonal decomposition basis vector of a target parameter based on the characteristic vector, and determining a basis coefficient to obtain a three-dimensional simulation reduced model; and obtaining a one-dimensional simulation model based on the coupling simulation framework. The method can improve the calculation efficiency of the simulation model and accurately reflect the real operation characteristics of the ship power system.
Description
Technical Field
The invention relates to the technical field of ship power, in particular to a multi-scale model construction method and device of a ship power system and electronic equipment.
Background
The power system is the heart of marine equipment such as ships and the like, provides energy sources such as propulsion power, electric power and the like for the marine equipment such as the ships and the like, directly determines comprehensive performances such as maneuverability, stealth, cruising ability and the like of the marine equipment such as the ships and the like, explores the energy and mass transfer mechanism of the ship power system, masters the operation rule of the power system, and has important significance in forming the optimal design method of the ship power system.
With the continuous development of computing power and models, numerical simulation becomes an important direction of ship power systems, and for complex systems such as ship power systems, the adoption of full-system three-dimensional unsteady numerical simulation has huge calculation amount, is difficult to converge and is difficult to realize at the present stage, so that the one-dimensional system simulation is usually adopted for large complex systems such as ship power systems at present. However, when local changes are severe, non-uniform characteristics are obvious or characteristics outside the component are not clear, real operation characteristics cannot be accurately reflected by adopting one-dimensional system simulation, and three-dimensional simulation research needs to be carried out.
Therefore, the existing one-dimensional-three-dimensional coupling simulation model of the ship power system is difficult to consider both high calculation efficiency and incapability of accurately reflecting the real operation characteristics of the ship power system.
Disclosure of Invention
The invention provides a multi-scale model construction method and device of a ship power system and electronic equipment, which are used for overcoming the defects that a simulation model of the ship power system in the prior art cannot give consideration to high calculation efficiency and cannot accurately reflect the real operating characteristics of the ship power system, and can improve the calculation efficiency of the simulation model and accurately reflect the real operating characteristics of the ship power system.
The invention provides a multi-scale model construction method of a ship power system, which comprises the following steps:
dividing a ship power system into a plurality of levels, and constructing a coupling simulation framework based on the plurality of levels; wherein the coupling simulation framework comprises: the transmission relation between the one-dimensional simulation model and the three-dimensional simulation reduced-order model of the ship power system;
acquiring a three-dimensional simulation database of the local part or equipment of the ship power system, and acquiring a data matrix of a target parameter based on the coupling simulation frame and the three-dimensional simulation database;
extracting a characteristic vector corresponding to the maximum characteristic value of the data matrix, constructing an intrinsic orthogonal decomposition base vector of the target parameter based on the characteristic vector, determining a base coefficient, and obtaining a three-dimensional simulation reduced model of the target parameter based on the base vector and the base coefficient;
and obtaining a one-dimensional simulation model coupled with the three-dimensional simulation reduced-order model based on the coupling simulation framework.
According to the multi-scale model construction method of the ship power system provided by the invention, the step of obtaining the three-dimensional simulation database of the corresponding local part or equipment of the ship power system comprises the following steps:
obtaining a three-dimensional simulation operation range and a parameter boundary based on the design and operation requirements of the ship power system;
determining a three-dimensional simulation calculation sample space based on the three-dimensional simulation operation range and the parameter boundary;
and carrying out three-dimensional numerical simulation on the three-dimensional simulation calculation sample space to obtain the three-dimensional simulation database.
The multi-scale model construction method of the ship power system provided by the invention further comprises the following steps:
under the target working condition of the ship power system, acquiring local or equipment three-dimensional simulation data of the ship power system;
and under the target working condition, comparing the output result of the three-dimensional simulation reduced-order model with local or equipment three-dimensional simulation data of the ship power system, and updating the three-dimensional simulation reduced-order model based on the comparison result.
According to the multi-scale model construction method of the ship power system, the one-dimensional simulation model coupled with the three-dimensional simulation reduced-order model is obtained based on the coupling simulation framework, and the method comprises the following steps:
obtaining a one-dimensional simulation function corresponding to the ship power system based on the coupling simulation framework;
constructing a theoretical model base based on the one-dimensional simulation function;
and performing model construction on the ship power system based on the theoretical model library to obtain the one-dimensional simulation model.
The multi-scale model construction method of the ship power system provided by the invention further comprises the following steps:
setting a simulation time step length and iteration precision for the one-dimensional simulation model;
sending the one-dimensional data to be transmitted to the three-dimensional simulation reduced order model to obtain an output result;
and sending the output result of the reduced-order model to the one-dimensional simulation model, and performing iterative updating on the one-dimensional simulation model.
The invention also provides a multi-scale model construction device of the ship power system, which comprises the following steps:
the framework construction module is used for dividing the ship power system into a plurality of levels and constructing a coupling simulation framework based on the plurality of levels; wherein the coupling simulation framework comprises: the transmission relation between the one-dimensional simulation model and the three-dimensional simulation reduced-order model of the ship power system;
the matrix construction module is used for acquiring a three-dimensional simulation database of a corresponding local part or equipment of the ship power system and obtaining a data matrix of a target parameter based on the coupling simulation frame and the three-dimensional simulation database;
the first model building module is used for extracting a characteristic vector corresponding to the maximum characteristic value of the data matrix, building an intrinsic orthogonal decomposition base vector of the target parameter based on the characteristic vector, determining a base coefficient, and obtaining a three-dimensional simulation reduced model of the transmission parameter based on the base vector and the base coefficient;
and the second model construction module is used for obtaining a one-dimensional simulation model coupled with the three-dimensional simulation reduced-order model based on the coupling simulation framework.
According to the multi-scale model construction device of the ship power system provided by the invention, a matrix construction module comprises:
the first calculation unit is used for obtaining a three-dimensional simulation operation range and a parameter boundary based on the design and operation requirements of the ship power system;
the second calculation unit is used for determining a three-dimensional simulation calculation sample space based on the three-dimensional simulation operation range and the parameter boundary;
and the third calculating unit is used for carrying out three-dimensional numerical simulation on the three-dimensional simulation calculation sample space to obtain the three-dimensional simulation database.
The multi-scale model construction device of the ship power system provided by the invention further comprises the following steps:
the simulation data acquisition module is used for acquiring local or equipment three-dimensional simulation data of the ship power system under the target working condition of the ship power system;
and the model updating module is used for comparing the output result of the three-dimensional simulation reduced-order model with local or equipment three-dimensional simulation data of the ship power system under the target working condition and updating the three-dimensional simulation reduced-order model based on the comparison result.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the multi-scale model construction method of the ship power system.
The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method of constructing a multi-scale model of a vessel power system according to any one of the preceding claims.
According to the multi-scale model construction method, device and electronic equipment of the ship power system, the ship power system is divided into a plurality of levels, and a coupling simulation frame is constructed based on the plurality of levels; wherein, the coupling simulation framework includes: the transmission relation between a one-dimensional simulation model and a three-dimensional simulation reduced model of the ship power system; acquiring a three-dimensional simulation database of a corresponding local part or equipment of a ship power system, and acquiring a data matrix based on a coupling simulation frame and the three-dimensional simulation database; extracting a characteristic vector of the data matrix, performing orthogonal decomposition on the characteristic vector to obtain a base vector, and determining a base coefficient to obtain a three-dimensional simulation reduced order model; and obtaining a one-dimensional simulation model coupled with the three-dimensional simulation reduced-order model based on the coupling simulation framework.
Compared with the prior art, when the ship power system is subjected to simulation analysis each time, a computational fluid dynamics numerical method is required to be called for computational iteration to obtain a corresponding three-dimensional data simulation result, however, when the computational fluid dynamics numerical method is called, a differential equation discrete form needs to be solved in a discrete space, iterative convergence processing needs to be continuously carried out in the solving process, and excessive time is consumed.
The method comprises the steps of obtaining a three-dimensional simulation database of a corresponding local part or equipment of a ship power system, and obtaining a data matrix based on a coupling simulation frame and the three-dimensional simulation database; the characteristic vectors of the data matrix are extracted, orthogonal decomposition is carried out on the characteristic vectors, and a three-dimensional simulation reduced-order model is obtained.
Therefore, the method can improve the calculation efficiency of the simulation model, and can accurately reflect the real operation characteristics of the ship power system through the three-dimensional simulation of the three-dimensional simulation reduced-order model.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is one of the flow diagrams of a multi-scale model construction method of a ship power system provided by the invention;
FIG. 2 is a schematic flow chart of the method for constructing a three-dimensional simulation reduced order model according to the present invention;
FIG. 3 is a schematic diagram of a one-dimensional-three-dimensional simulation model coupling calculation process provided by the present invention;
FIG. 4 is a second schematic flow chart of a multi-scale model building method for a ship power system according to the present invention;
FIG. 5 is a schematic block diagram of a multi-scale model building apparatus for a marine power system according to the present invention;
fig. 6 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The multi-scale model construction method, device and electronic equipment of the ship power system of the invention are described below with reference to fig. 1 to 6.
As shown in fig. 1, the multi-scale model construction method for a ship power system provided by the invention comprises the following steps:
It should be noted that, for the operation and energy transfer characteristics of the ship power system, the ship power system is further divided into different levels such as subsystems, devices and parts, and according to the flow characteristics and the actual requirements of the ship power system, devices or parts such as water pumps or valves with three-dimensional simulation requirements are determined.
Combing the composition relation of each layer of the ship power system and the coupling connection relation among the layers, such as the coupling connection relation among equipment and subsystems, and determining the transmission parameters and parameter setting interfaces of the one-dimensional-three-dimensional coupling simulation model, such as inlet and outlet pressure, flow, temperature or enthalpy value and the like; the three-dimensional simulation adopts a three-dimensional simulation reduced order model based on intrinsic orthogonal decomposition to realize high fidelity prediction.
It can be understood that the transmission parameters and the parameter setting interface of the one-dimensional-three-dimensional coupled simulation model are determined, that is, the coupled simulation frame is determined, the coupled simulation frame represents the transmission relationship between the one-dimensional simulation model and the three-dimensional simulation reduced-order model of the ship power system, the parameters corresponding to the transmission relationship between the one-dimensional simulation model and the three-dimensional simulation reduced-order model are the transmission parameters of the one-dimensional-three-dimensional coupled simulation model, and the types of the transmission parameters can be set through the parameter setting interface.
And 120, acquiring a three-dimensional simulation database of a corresponding local part or equipment of the ship power system, and acquiring a data matrix of the target parameter based on the coupling simulation frame and the three-dimensional simulation database.
It is understood that the three-dimensional simulation database corresponding to the part or the equipment of the ship power system can be a three-dimensional simulation database corresponding to a sub-hierarchy of the ship power system, such as a three-dimensional simulation database corresponding to the equipment of the ship power system or the part of the ship power system.
The data matrix is obtained based on the coupling simulation framework and the three-dimensional simulation database, and the data matrix of the corresponding target parameters is constructed one by one based on the transmission parameters in the coupling simulation framework and the three-dimensional simulation database.
And step 130, extracting a characteristic vector corresponding to the maximum characteristic value of the data matrix, constructing an intrinsic orthogonal decomposition basis vector of the target parameter based on the characteristic vector, determining a basis coefficient, and obtaining a three-dimensional simulation reduced-order model of the transmission parameter based on the basis vector and the basis coefficient.
It can be understood that the problem that a large amount of memory and machine time are consumed in the process of decomposing the data matrix can be avoided by adopting the Sirovich method to carry out orthogonal decomposition on the feature vectors.
It should be noted that the three-dimensional simulation reduced-order model is not used for three-dimensional simulation, but is used for direct three-dimensional simulation.
And 140, obtaining a one-dimensional simulation model coupled with the three-dimensional simulation reduced-order model based on the coupling simulation framework.
It should be noted that, the one-dimensional simulation model, that is, after receiving the setting data related to the ship power system, performs one-dimensional data simulation to obtain a corresponding one-dimensional data simulation result.
The one-dimensional simulation model is coupled with the three-dimensional simulation reduced model, that is, the output result of the three-dimensional simulation reduced model is sent to the one-dimensional simulation model, the one-dimensional simulation model carries out one-dimensional data simulation based on the output result of the three-dimensional simulation reduced model to obtain a one-dimensional data simulation result, and the one-dimensional data simulation result is sent to the three-dimensional simulation reduced model to be used as the input parameter of the three-dimensional simulation reduced model.
The one-dimensional simulation model and the three-dimensional simulation reduced-order model jointly form a simulation model of the ship power system.
In some embodiments, obtaining a three-dimensional simulation database of corresponding parts or equipment of a ship power system comprises:
obtaining a three-dimensional simulation operation range and a parameter boundary based on the design and operation requirements of a ship power system;
determining a three-dimensional simulation calculation sample space based on the three-dimensional simulation operation range and the parameter boundary;
and carrying out three-dimensional numerical simulation on the three-dimensional simulation calculation sample space to obtain a three-dimensional simulation database.
For sub-levels of a vessel power system, such as a plant or a part of a vessel power system, where a three-dimensional simulation is required. According to the design requirements of the ship power system, the operation range is determined, the parameter boundary is determined, the equipment or local three-dimensional simulation calculation sample space covering the parameter boundary is determined, three-dimensional numerical simulation in the sample space under a series of different working conditions is carried out, and a three-dimensional simulation database of the ship power system related sub-level is constructed.
In some embodiments, extracting the feature vector of the data matrix comprises:
and extracting the eigenvector corresponding to the maximum eigenvalue of the data matrix.
In some embodiments, performing orthogonal decomposition on the feature vector to obtain a three-dimensional simulation reduced order model, includes:
carrying out orthogonal decomposition on the feature vector to obtain a base vector and a base coefficient;
obtaining a three-dimensional simulation reduced model based on the basis of the basis vectors and the basis coefficients; the three-dimensional simulation reduced model can also set parameter types, the output parameters are one-dimensional data corresponding to the parameter types, and three-dimensional distribution of target parameters can be reconstructed through the three-dimensional simulation reduced model.
It can be understood that the feature vector corresponding to the maximum feature value is extracted, the intrinsic orthogonal decomposition basis vector corresponding to the target parameter is constructed, the basis coefficient is determined by adopting methods such as interpolation or machine learning, and the like, so that a three-dimensional simulation reduced-order model based on the intrinsic orthogonal decomposition of the corresponding device or local transmission parameter space is obtained, the input parameters of the model are boundary exchange parameters in a one-dimensional-three-dimensional coupling simulation frame, and the output parameters of the model are the corresponding external characteristics and the internal three-dimensional distribution of the target parameter.
In some embodiments, the multi-scale model construction method for a ship power system further comprises:
under the target working condition of the ship power system, acquiring local or equipment three-dimensional simulation data of the ship power system;
and under the target working condition, comparing the output result of the three-dimensional simulation reduced-order model with local or equipment three-dimensional simulation data of the ship power system, and updating the three-dimensional simulation reduced-order model based on the comparison result.
Comparing the output result of the three-dimensional simulation reduced model with the three-dimensional simulation data under the target working condition of the ship power system, evaluating the precision of the three-dimensional simulation reduced model, replenishing and constructing a three-dimensional simulation database again when the precision of the three-dimensional simulation reduced model does not meet the requirement, and updating the three-dimensional simulation reduced model until the precision of the three-dimensional simulation reduced model meets the requirement.
The process of constructing the three-dimensional simulation reduced-order model is shown in fig. 2, and it can be understood that a three-dimensional simulation database is constructed based on a computational fluid dynamics numerical method and the input working condition of the ship power system, and then the interested data is processed to obtain a data matrix after the interested data is screened from the three-dimensional simulation database according to the input interested variable and the interested region of the ship power system.
And carrying out orthogonal decomposition on the data matrix to obtain the base mode of the orthogonal decomposition, namely the base vector and the base coefficient. The orthogonal decomposition base mode data has multiple items, and partial data, such as the first ten items of data, can be selected from the multiple items of base mode data to form a three-dimensional simulation reduced order model.
And inputting new working condition data to the three-dimensional simulation reduced model to obtain an output result of the three-dimensional simulation reduced model, namely the prediction characteristic of the three-dimensional simulation reduced model. In addition, based on the method for calculating the fluid mechanics numerical value, the operation characteristics of the new working condition, namely the three-dimensional simulation data corresponding to the new working condition, are obtained by combining the input new working condition data.
And comparing the predicted characteristic of the three-dimensional simulation reduced-order model with the calculated new working condition operation characteristic, judging whether the predicted characteristic of the three-dimensional simulation reduced-order model meets the requirement, if not, supplementing the new working condition operation characteristic into a three-dimensional simulation database, repeating the process, and updating the three-dimensional simulation reduced-order model.
In some embodiments, obtaining a one-dimensional simulation model coupled with a three-dimensional simulation reduced-order model based on the coupled simulation framework includes:
obtaining a one-dimensional simulation function corresponding to a ship power system based on a coupling simulation framework;
constructing a theoretical model base based on a one-dimensional simulation function;
and (4) carrying out model construction on the ship power system based on a theoretical model library to obtain a one-dimensional simulation model.
It can be understood that according to the coupling relation of the coupling simulation framework and the ship power system, such as the system, the subsystem, the equipment, the parts and the like, based on the conservation equation, the empirical model and the like, the discrete format of the related equation is established, the basic theoretical model base is established based on the Modelica language, then the related parts and the equipment database are sequentially established from bottom to top through the combination of the basic theoretical model bases, the models of the subsystem, the system and the like are established through the dragging mode, the text compiling mode and the like, the dynamic simulation analysis capability of the one-dimensional system is provided, and the corresponding three-dimensional simulation analysis interface is reserved.
In some embodiments, the multi-scale model construction method for a ship power system further comprises:
setting simulation time step length and iteration precision for the one-dimensional simulation model;
sending the one-dimensional data to be transmitted to a three-dimensional simulation reduced order model to obtain an output result;
and sending the output result to the one-dimensional simulation model, and performing iterative updating on the one-dimensional simulation model.
It can be understood that, based on the above one-dimensional simulation model, three-dimensional simulation reduced-order model and coupling simulation framework, one-dimensional-three-dimensional coupling simulation is developed, and first, initial value setting and initialization are performed on one-dimensional system simulation, and simulation time step length, iteration precision and the like are set.
And sending a simulation starting instruction, starting the three-dimensional simulation reduced-order model, and transmitting parameters at the one-dimensional-three-dimensional coupling simulation interface to the three-dimensional simulation reduced-order model. Parameters at a one-dimensional-three-dimensional coupling simulation interface, namely one-dimensional data to be simulated, take a centrifugal pump as an example, and transmit parameters such as inlet flow, pressure, temperature, centrifugal pump rotating speed and the like to a three-dimensional simulation order-reducing model.
The three-dimensional simulation order-reducing model is provided with a three-dimensional simulation end used for carrying out three-dimensional data simulation and transmitting parameters at a one-dimensional-three-dimensional coupling simulation interface to the three-dimensional simulation end of the three-dimensional simulation order-reducing model.
After the three-dimensional simulation end receives data, the method is different from the traditional one-dimensional-three-dimensional coupling simulation method, and based on a three-dimensional simulation reduced-order model, the method can quickly calculate and obtain the macroscopic external characteristics of the ship power system, reconstruct an internal three-dimensional flow field, a pressure field or a temperature field and the like, and output the parameters at the outlet of the ship power system. Taking a centrifugal pump as an example, external characteristics such as lift and the like are obtained through a three-dimensional simulation reduced-order model, and parameters such as outlet pressure, flow and the like are output at an outlet of a ship power system and are used by a one-dimensional simulation model.
The iteration flow of the one-dimensional simulation model is as shown in fig. 3, after the one-dimensional simulation model starts simulation, the one-dimensional simulation model sends an instruction to the three-dimensional simulation reduced-order model, and the three-dimensional simulation reduced-order model is informed to start simulation.
The one-dimensional simulation model starts to solve a first step, simulation is carried out based on input one-dimensional data, after the simulation is started for a preset time, input parameters and inlet boundary parameters are sent to the three-dimensional simulation reduced-order model, the input parameters can be simulation time step lengths, and the inlet boundary parameters can be data such as fluid temperature and flow.
And after receiving the transmission parameters sent by the one-dimensional simulation model, the three-dimensional simulation reduced-order model starts a first step of resolving to obtain an output result, wherein the output result comprises output parameters and outlet boundary parameters, and the output result is sent to the one-dimensional simulation model.
The one-dimensional simulation model iterates to converge based on the output result of the three-dimensional simulation reduced-order model and the self one-dimensional data simulation result.
After the one-dimensional simulation end obtains the output data of the three-dimensional simulation end, iterating to convergence, advancing calculation, entering the next time step, and repeating the steps until the simulation is finished.
In some embodiments, the multi-scale model building method for the ship power system provided by the invention is shown in fig. 4, and comprises the following steps:
and step 410, dividing the ship power system into different levels of subsystems, equipment, parts and the like according to the running and energy and quality transmission characteristics of the ship power system, and determining a coupling simulation framework.
And step 420, constructing a three-dimensional simulation database, constructing a data matrix according to the transmission parameters, performing matrix decomposition by adopting a Sirovich method, extracting characteristic vectors, determining base coefficients, and obtaining a three-dimensional simulation reduced order model based on intrinsic orthogonal decomposition under the condition of meeting the precision.
And 430, establishing a basic theoretical equation set based on basic theories such as conservation equations, constructing a basic theoretical model base based on a Modelica language, and sequentially constructing one-dimensional simulation models such as parts, equipment, subsystems and systems from bottom to top.
And 440, starting the one-dimensional simulation model, carrying out initialization setting, carrying out one-dimensional simulation calculation, sending the transmission parameters to the three-dimensional simulation reduced-order model, sending the result to the one-dimensional simulation model by the three-dimensional simulation reduced-order model, and repeating iteration until the simulation is finished.
In summary, the multi-scale model construction method of the ship power system provided by the invention divides the ship power system into a plurality of levels, and constructs a coupling simulation frame based on the plurality of levels; wherein, the coupling simulation framework includes: the transmission relation between a one-dimensional simulation model and a three-dimensional simulation reduced model of the ship power system; acquiring a three-dimensional simulation database of a corresponding local part or equipment of a ship power system, and acquiring a data matrix based on a coupling simulation frame and the three-dimensional simulation database; extracting a characteristic vector of the data matrix, performing orthogonal decomposition on the characteristic vector to obtain a base vector, and determining a base coefficient to obtain a three-dimensional simulation reduced order model; and obtaining a one-dimensional simulation model coupled with the three-dimensional simulation reduced-order model based on the coupling simulation framework.
Compared with the prior art, when the ship power system is subjected to simulation analysis each time, a computational fluid dynamics numerical method is required to be called for computational iteration to obtain a corresponding three-dimensional data simulation result, however, when the computational fluid dynamics numerical method is called, a differential equation discrete form needs to be solved in a discrete space, iterative convergence processing needs to be continuously carried out in the solving process, and excessive time is consumed.
The method comprises the steps of obtaining a three-dimensional simulation database of a corresponding local part or equipment of a ship power system, and obtaining a data matrix based on a coupling simulation frame and the three-dimensional simulation database; the characteristic vectors of the data matrix are extracted, orthogonal decomposition is carried out on the characteristic vectors, and a three-dimensional simulation reduced-order model is obtained.
According to the method provided by the invention, at a three-dimensional simulation end, a three-dimensional simulation database covering all target working condition ranges is constructed, and a three-dimensional simulation order-reducing model based on intrinsic orthogonal decomposition is adopted, so that high-fidelity rapid prediction of three-dimensional detailed distribution of target parameters and macroscopic characteristics of equipment is realized; and the one-dimensional-three-dimensional coupling simulation of the ship power system is high-efficient and quick through data transmission between the one-dimensional simulation model and the three-dimensional simulation reduced-order model.
The method provided by the invention is used for carrying out simulation prediction on a typical ship power system, and under the condition that the parameter macroscopic characteristics are equivalent to the prediction precision of a computational fluid dynamics numerical method, the prediction speed of the three-dimensional simulation reduced order model is increased by more than 200 times, and the one-dimensional-three-dimensional coupling simulation speed is increased by more than 200 times, so that the one-dimensional-three-dimensional rapid and efficient coupling simulation is realized.
The multi-scale model building device of the ship power system provided by the invention is described below, and the multi-scale model building device of the ship power system described below and the multi-scale model building method of the ship power system described above can be referred to correspondingly.
As shown in fig. 5, the multi-scale model building apparatus 500 of a ship power system provided by the present invention includes: a framework building module 510, a matrix building module 520, a first model building module 530, and a second model building module 540.
The frame construction module 510 is configured to divide the ship power system into multiple levels, and construct a coupling simulation frame based on the multiple levels; wherein, the coupling simulation framework includes: and the transmission relation between the one-dimensional simulation model and the three-dimensional simulation reduced-order model of the ship power system.
The matrix construction module 520 is configured to obtain a three-dimensional simulation database of a local or device corresponding to the ship power system, and obtain a data matrix of the target parameter based on the coupling simulation frame and the three-dimensional simulation database.
The first model building module 530 extracts the eigenvector corresponding to the maximum eigenvalue of the data matrix, builds the eigen-orthogonal decomposition basis vector of the target parameter based on the eigenvector, determines the basis coefficient, and obtains the three-dimensional simulation reduced order model of the transfer parameter based on the basis of the basis vector and the basis coefficient.
The second model building module 540 is configured to obtain a one-dimensional simulation model coupled with the three-dimensional simulation reduced-order model based on the coupled simulation framework.
In some embodiments, matrix building module 520 includes: the device comprises a first calculation unit, a second calculation unit and a third calculation unit.
The first computing unit is used for obtaining a three-dimensional simulation operation range and parameter boundaries based on the design and operation requirements of the ship power system.
The second calculation unit is used for determining a three-dimensional simulation calculation sample space based on the three-dimensional simulation operation range and the parameter boundary.
The third calculating unit is used for carrying out three-dimensional numerical simulation on the three-dimensional simulation calculation sample space to obtain a three-dimensional simulation database.
In some embodiments, the multi-scale model building apparatus 500 for a ship power system further includes: the simulation system comprises a simulation data acquisition module and a model updating module.
The simulation data acquisition module is used for acquiring local or equipment three-dimensional simulation data of the ship power system under the target working condition of the ship power system.
And the model updating module is used for comparing the output result of the three-dimensional simulation reduced-order model with local or equipment three-dimensional simulation data of the ship power system under a target working condition and updating the three-dimensional simulation reduced-order model based on the comparison result.
In some embodiments, the second model building module 540 comprises: the device comprises a function obtaining unit, a model base constructing unit and a second model constructing unit.
The function obtaining unit is used for obtaining a one-dimensional simulation function corresponding to the ship power system based on the coupling simulation framework.
The model base construction unit is used for constructing a theoretical model base based on a one-dimensional simulation function.
And the second model construction unit is used for constructing a model of the ship power system based on the theoretical model library to obtain a one-dimensional simulation model.
In some embodiments, the multi-scale model building apparatus 500 for a ship power system further includes: the device comprises a parameter setting module, a first sending module and a second sending module.
The parameter setting module is used for setting simulation time step length and iteration precision for the one-dimensional simulation model.
The first sending module is used for sending the one-dimensional data to be transmitted to the three-dimensional simulation reduced order model to obtain an output result.
And the second sending module is used for sending the output result to the one-dimensional simulation model and carrying out iterative updating on the one-dimensional simulation model.
The electronic device and the storage medium provided by the present invention are described below, and the electronic device and the storage medium described below and the multi-scale model building method of the ship power system described above may be referred to in correspondence with each other.
Fig. 6 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 6: a processor (processor)610, a communication Interface (Communications Interface)620, a memory (memory)630 and a communication bus 640, wherein the processor 610, the communication Interface 620 and the memory 630 communicate with each other via the communication bus 640. The processor 610 may invoke logic instructions in the memory 630 to perform a method of multi-scale model building of a marine vessel power system, the method comprising:
and 140, obtaining a one-dimensional simulation model coupled with the three-dimensional simulation reduced-order model based on the coupling simulation framework.
In addition, the logic instructions in the memory 630 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the multi-scale model building method for a vessel power system provided by the above methods, the method comprising:
and 140, obtaining a one-dimensional simulation model coupled with the three-dimensional simulation reduced-order model based on the coupling simulation framework.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the method of constructing a multi-scale model of a marine vessel power system provided above, the method comprising:
and 140, obtaining a one-dimensional simulation model coupled with the three-dimensional simulation reduced-order model based on the coupling simulation framework.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A multi-scale model construction method of a ship power system is characterized by comprising the following steps:
dividing a ship power system into a plurality of levels, and constructing a coupling simulation framework based on the plurality of levels; wherein the coupling simulation framework comprises: the transmission relation between the one-dimensional simulation model and the three-dimensional simulation reduced-order model of the ship power system;
acquiring a three-dimensional simulation database of the local part or equipment of the ship power system, and acquiring a data matrix of a target parameter based on the coupling simulation frame and the three-dimensional simulation database;
extracting a characteristic vector corresponding to the maximum characteristic value of the data matrix, constructing an intrinsic orthogonal decomposition base vector of the target parameter based on the characteristic vector, determining a base coefficient, and obtaining a three-dimensional simulation reduced model of the target parameter based on the base vector and the base coefficient;
and obtaining a one-dimensional simulation model coupled with the three-dimensional simulation reduced-order model based on the coupling simulation framework.
2. The method for constructing the multi-scale model of the ship power system according to claim 1, wherein the obtaining of the three-dimensional simulation database of the corresponding part or equipment of the ship power system comprises:
obtaining a three-dimensional simulation operation range and a parameter boundary based on the design and operation requirements of the ship power system;
determining a three-dimensional simulation calculation sample space based on the three-dimensional simulation operation range and the parameter boundary;
and carrying out three-dimensional numerical simulation on the three-dimensional simulation calculation sample space to obtain the three-dimensional simulation database.
3. The method for constructing a multi-scale model of a marine vessel power system according to claim 1, further comprising:
under the target working condition of the ship power system, acquiring local or equipment three-dimensional simulation data of the ship power system;
and under the target working condition, comparing the output result of the three-dimensional simulation reduced-order model with local or equipment three-dimensional simulation data of the ship power system, and updating the three-dimensional simulation reduced-order model based on the comparison result.
4. The method for constructing a multi-scale model of a ship power system according to claim 1, wherein the obtaining of the one-dimensional simulation model coupled with the three-dimensional simulation reduced-order model based on the coupled simulation framework comprises:
obtaining a one-dimensional simulation function corresponding to the ship power system based on the coupling simulation framework;
constructing a theoretical model base based on the one-dimensional simulation function;
and performing model construction on the ship power system based on the theoretical model library to obtain the one-dimensional simulation model.
5. The multi-scale model construction method of a marine vessel power system according to any one of claims 1 to 4, further comprising:
setting a simulation time step length and iteration precision for the one-dimensional simulation model;
sending the one-dimensional data to be transmitted to the three-dimensional simulation reduced order model to obtain an output result;
and sending the output result of the reduced-order model to the one-dimensional simulation model, and performing iterative updating on the one-dimensional simulation model.
6. A multi-scale model building device of a ship power system is characterized by comprising:
the framework construction module is used for dividing the ship power system into a plurality of levels and constructing a coupling simulation framework based on the plurality of levels; wherein the coupling simulation framework comprises: the transmission relation between the one-dimensional simulation model and the three-dimensional simulation reduced-order model of the ship power system;
the matrix construction module is used for acquiring a three-dimensional simulation database of a corresponding local part or equipment of the ship power system and obtaining a data matrix of a target parameter based on the coupling simulation frame and the three-dimensional simulation database;
the first model building module is used for extracting a characteristic vector corresponding to the maximum characteristic value of the data matrix, building an intrinsic orthogonal decomposition base vector of the target parameter based on the characteristic vector, determining a base coefficient, and obtaining a three-dimensional simulation reduced model of the transmission parameter based on the base vector and the base coefficient;
and the second model construction module is used for obtaining a one-dimensional simulation model coupled with the three-dimensional simulation reduced-order model based on the coupling simulation framework.
7. The multi-scale model building apparatus of a marine vessel power system according to claim 6, wherein the matrix building module comprises:
the first calculation unit is used for obtaining a three-dimensional simulation operation range and a parameter boundary based on the design and operation requirements of the ship power system;
the second calculation unit is used for determining a three-dimensional simulation calculation sample space based on the three-dimensional simulation operation range and the parameter boundary;
and the third calculating unit is used for carrying out three-dimensional numerical simulation on the three-dimensional simulation calculation sample space to obtain the three-dimensional simulation database.
8. The multi-scale model building apparatus for a marine vessel power system according to claim 6, further comprising:
the simulation data acquisition module is used for acquiring local or equipment three-dimensional simulation data of the ship power system under the target working condition of the ship power system;
and the model updating module is used for comparing the output result of the three-dimensional simulation reduced-order model with local or equipment three-dimensional simulation data of the ship power system under the target working condition and updating the three-dimensional simulation reduced-order model based on the comparison result.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the method of multi-scale model construction of a marine vessel power system according to any of claims 1 to 5.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the steps of a method of constructing a multi-scale model of a marine vessel power system according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110887548.2A CN113642105B (en) | 2021-08-03 | 2021-08-03 | Multi-scale model construction method and device for ship power system and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110887548.2A CN113642105B (en) | 2021-08-03 | 2021-08-03 | Multi-scale model construction method and device for ship power system and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113642105A true CN113642105A (en) | 2021-11-12 |
| CN113642105B CN113642105B (en) | 2023-10-27 |
Family
ID=78419481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110887548.2A Active CN113642105B (en) | 2021-08-03 | 2021-08-03 | Multi-scale model construction method and device for ship power system and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642105B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115079592A (en) * | 2022-07-12 | 2022-09-20 | 哈尔滨工程大学 | Pipe network simulation method for thermodynamic system of ship nuclear power device |
| CN115146554A (en) * | 2022-05-31 | 2022-10-04 | 中国船舶重工集团公司第七一九研究所 | Method and device for determining characteristic parameters of pipeline pump |
| CN115358100A (en) * | 2022-10-21 | 2022-11-18 | 山东大学 | Multi-objective optimization method and device for ocean towing system |
| CN117216878A (en) * | 2023-09-27 | 2023-12-12 | 中国船舶集团有限公司第七一九研究所 | Ship power system-oriented rapid modeling method and device based on lumped parameter method |
| CN117709129A (en) * | 2024-02-05 | 2024-03-15 | 国家超级计算天津中心 | Multi-scale simulation method, device, equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170147722A1 (en) * | 2014-06-30 | 2017-05-25 | Evolving Machine Intelligence Pty Ltd | A System and Method for Modelling System Behaviour |
| KR102048243B1 (en) * | 2019-09-09 | 2019-11-25 | 주식회사 페이스 | Method for Building Reduced Order Model by Combining CAE Simulation and Measurement Data through Coupled-POD |
| CN111062145A (en) * | 2019-12-30 | 2020-04-24 | 浙江大学 | Three-layer partition and electrical distance-based power system electromagnetic transient simulation equivalence method |
| CN111104757A (en) * | 2018-10-09 | 2020-05-05 | 株洲中车时代电气股份有限公司 | Vibration response simulation method and vibration reduction optimization method of coupling power system |
| CN111353226A (en) * | 2020-02-27 | 2020-06-30 | 兰州大学 | Multidimensional control system model order reduction method and device |
| CN111353211A (en) * | 2018-12-21 | 2020-06-30 | 达索***公司 | Multi-instantiation simulation for large environments |
| CN111709090A (en) * | 2020-06-17 | 2020-09-25 | 上海船舶研究设计院（中国船舶工业集团公司第六0四研究院） | Model construction method and device, electronic equipment and computer readable storage medium |
| CN111797533A (en) * | 2020-07-09 | 2020-10-20 | 哈尔滨工程大学 | Nuclear power device operation parameter abnormity detection method and system |
| CN112632710A (en) * | 2021-01-02 | 2021-04-09 | 青岛海西电气有限公司 | Intelligent integrated simulation method for ship electric propulsion system |
| CN112836377A (en) * | 2021-02-07 | 2021-05-25 | 智慧航海（青岛）科技有限公司 | Ship simulation test system based on digital simulation |
-
2021
- 2021-08-03 CN CN202110887548.2A patent/CN113642105B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170147722A1 (en) * | 2014-06-30 | 2017-05-25 | Evolving Machine Intelligence Pty Ltd | A System and Method for Modelling System Behaviour |
| CN111104757A (en) * | 2018-10-09 | 2020-05-05 | 株洲中车时代电气股份有限公司 | Vibration response simulation method and vibration reduction optimization method of coupling power system |
| CN111353211A (en) * | 2018-12-21 | 2020-06-30 | 达索***公司 | Multi-instantiation simulation for large environments |
| KR102048243B1 (en) * | 2019-09-09 | 2019-11-25 | 주식회사 페이스 | Method for Building Reduced Order Model by Combining CAE Simulation and Measurement Data through Coupled-POD |
| CN111062145A (en) * | 2019-12-30 | 2020-04-24 | 浙江大学 | Three-layer partition and electrical distance-based power system electromagnetic transient simulation equivalence method |
| CN111353226A (en) * | 2020-02-27 | 2020-06-30 | 兰州大学 | Multidimensional control system model order reduction method and device |
| CN111709090A (en) * | 2020-06-17 | 2020-09-25 | 上海船舶研究设计院（中国船舶工业集团公司第六0四研究院） | Model construction method and device, electronic equipment and computer readable storage medium |
| CN111797533A (en) * | 2020-07-09 | 2020-10-20 | 哈尔滨工程大学 | Nuclear power device operation parameter abnormity detection method and system |
| CN112632710A (en) * | 2021-01-02 | 2021-04-09 | 青岛海西电气有限公司 | Intelligent integrated simulation method for ship electric propulsion system |
| CN112836377A (en) * | 2021-02-07 | 2021-05-25 | 智慧航海（青岛）科技有限公司 | Ship simulation test system based on digital simulation |
Non-Patent Citations (1)
| Title |
|---|
| 罗恒 等: "《基于层次分析法的动力***技术状态评估方法》", 《舰船科学技术》, vol. 39, no. 03, pages 79 - 82 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115146554A (en) * | 2022-05-31 | 2022-10-04 | 中国船舶重工集团公司第七一九研究所 | Method and device for determining characteristic parameters of pipeline pump |
| CN115079592A (en) * | 2022-07-12 | 2022-09-20 | 哈尔滨工程大学 | Pipe network simulation method for thermodynamic system of ship nuclear power device |
| CN115358100A (en) * | 2022-10-21 | 2022-11-18 | 山东大学 | Multi-objective optimization method and device for ocean towing system |
| CN117216878A (en) * | 2023-09-27 | 2023-12-12 | 中国船舶集团有限公司第七一九研究所 | Ship power system-oriented rapid modeling method and device based on lumped parameter method |
| CN117216878B (en) * | 2023-09-27 | 2024-02-13 | 中国船舶集团有限公司第七一九研究所 | Ship power system-oriented rapid modeling method and device based on lumped parameter method |
| CN117709129A (en) * | 2024-02-05 | 2024-03-15 | 国家超级计算天津中心 | Multi-scale simulation method, device, equipment and storage medium |
| CN117709129B (en) * | 2024-02-05 | 2024-05-14 | 国家超级计算天津中心 | Multi-scale simulation method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113642105B (en) | 2023-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113642105B (en) | Multi-scale model construction method and device for ship power system and electronic equipment | |
| Liu et al. | Hull form optimization based on calm-water wave drag with or without generating bulbous bow | |
| CN111783209B (en) | Self-adaptive structure reliability analysis method combining learning function and kriging model | |
| CN114818224A (en) | Structural grid generation method, device, equipment and storage medium | |
| Cordero-Gracia et al. | An interpolation tool for aerodynamic mesh deformation problems based on octree decomposition | |
| Zuo et al. | Fast sparse flow field prediction around airfoils via multi-head perceptron based deep learning architecture | |
| CN114385964B (en) | State space model calculation method, system and equipment of multi-element fractional order system | |
| CN112632874A (en) | Optimization method and system for numerical simulation of helicopter flow field | |
| Gagliardi et al. | A two–step radial basis function-based CFD mesh displacement tool | |
| Jiang et al. | Reparameterization of B-spline surface and its application in ship hull modeling | |
| CN113609585B (en) | Multi-level model construction method and device for ship power system and electronic equipment | |
| Zhu et al. | Fast electrothermal coupling calculation method for supporting digital twin construction of electrical equipment | |
| CN116822038B (en) | Abnormal-shape closed reinforcement topology optimization method based on data driving | |
| Pigounakis et al. | Fairing spatial B-spline curves | |
| CN113379103B (en) | Prediction method of pump equipment internal flow field based on reduced order model | |
| Kuleshov et al. | Cognitive technologies in adaptive models of complex plants | |
| CN115906987A (en) | Deep learning model training method, virtual image driving method and device | |
| CN114972695A (en) | Point cloud generation method and device, electronic equipment and storage medium | |
| Tsiakas et al. | Shape optimization of turbomachinery rows using a parametric blade modeller and the continuous adjoint method running on GPUs | |
| CN115270363A (en) | Centrifugal compressor blade optimization design method and device based on multi-agent model | |
| Yuqi et al. | Flow field reconstruction method based on array neural network | |
| CN116070310A (en) | Analysis method for dynamic response of marine structure | |
| US20230062268A1 (en) | System and method for fatigue response prediction | |
| Ivagnes et al. | A shape optimization pipeline for marine propellers by means of reduced order modeling techniques | |
| Xue et al. | An advanced rigid-flexible hybrid assembly deviation analysis method for aerostructures |
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 |