CN110515930A - Critical, carbon dioxide and hydrogen mixture thermal physical property data library and construction method - Google Patents
Critical, carbon dioxide and hydrogen mixture thermal physical property data library and construction method Download PDFInfo
- Publication number
- CN110515930A CN110515930A CN201910828664.XA CN201910828664A CN110515930A CN 110515930 A CN110515930 A CN 110515930A CN 201910828664 A CN201910828664 A CN 201910828664A CN 110515930 A CN110515930 A CN 110515930A
- Authority
- CN
- China
- Prior art keywords
- physical property
- multiple groups
- property data
- thermal physical
- critical
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/211—Schema design and management
- G06F16/212—Schema design and management with details for data modelling support
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a kind of critical, carbon dioxide and hydrogen mixture thermal physical property data library and construction method, which includes: multiple groups simulation and the experiment thermal physical property data for obtaining the ternary mixture of critical, carbon dioxide and hydrogen;Hot physical property model is obtained by deep neural network training according to the multiple groups thermal physical property data;Data under multiple groups different temperatures, pressure and the molar ratio of the ternary mixture are provided, the multiple groups model prediction thermal physical property data of the ternary mixture is obtained according to the data correspondence under the multiple groups different temperatures, pressure and molar ratio;The thermal physical property data library of the ternary mixture is constructed according to multiple groups simulation and experiment thermal physical property data and the multiple groups model prediction thermal physical property data, and the query interface in the thermal physical property data library is provided.The present invention can provide the data basis of thermal cycle design, facilitate the development that water steams coal technology.
Description
Technical field
The present embodiments relate to Power Engineering and Engineering Thermophysics technical fields, and in particular to a kind of critical, dioxy
Change carbon and hydrogen mixture thermal physical property data library and construction method.
Background technique
The thermal physical property parameter of fluid can be used for the design of power generation cycle system, the calculating of energy transmission and conversion, heat chemistry
The analysis etc. of process.
It is mixed to lack accurate ternary such as NIST (National Institute of Standards and Technology) database for current database
Close object H2O-CO2-H2Thermal physical property parameter.The H that NIST is provided2O-CO2-H2The hot physical property of ternary mixture is usually by through customs examination
What connection formula calculated, precision is low.
The method for usually obtaining the hot physical property of fluid is directly to be measured by experiment, but test the cost of measurement
Height, and the data point generated is less.
H is obtained at present2O-CO2-H2The method of the hot physical property of ternary mixture can also be simulated by classical molecular dynamics and be obtained
.In the case where potential field selects reasonable situation, accurate hot physical property result usually can be obtained using classical molecular dynamics simulation.
Molecular dynamics simulation can generate more data with lower cost, but calculate time-consuming high.
Summary of the invention
For this purpose, the embodiment of the present invention provides the hot physical property model building of a kind of critical, carbon dioxide and hydrogen mixture
Method obtains ternary mixture H to solve the prior art2O-CO2-H2Hot physical property precision it is low and calculate time-consuming high problem.
To achieve the goals above, the embodiment of the present invention provides the following technical solutions:
In a first aspect, embodiment of the invention discloses the hot physical property of a kind of critical, carbon dioxide and hydrogen mixture
Model building method, comprising:
Obtain the multiple groups thermal physical property data of the ternary mixture of critical, carbon dioxide and hydrogen, the hot physical property of multiple groups
Data include multiple groups input condition and multiple groups output as a result, the multiple groups input condition and multiple groups output result one are a pair of
It answers, every group of input condition includes temperature, pressure and the molar ratio of the ternary mixture of critical, carbon dioxide and hydrogen;
Hot physical property model is obtained by deep neural network training according to the multiple groups thermal physical property data, the hot physical property model is used for root
According to the temperature of the ternary mixture of given critical, carbon dioxide and hydrogen, pressure and molar ratio heat outputting physical property result.
Further, the parameter optimization algorithm of the deep neural network is Adam algorithm, the deep neural network
Activation primitive is tanh Tanh, and the hidden layer of the deep neural network is affine Affine layers, the deep neural network
Loss function be mean square error MSE.
Further, the multiple groups thermal physical property data of the ternary mixture for obtaining critical, carbon dioxide and hydrogen, tool
Body includes: to carry out molecular dynamics simulation respectively according to the multiple groups output condition or test to obtain the multiple groups output result;
The multiple groups thermal physical property data is obtained according to the multiple groups output condition and multiple groups output result.
Further, batch normalization layer is provided between the full articulamentum and active coating of the deep neural network.
Further, the critical includes subcritical water and supercritical water.
Second aspect, embodiment of the invention discloses the hot physical property of a kind of critical, carbon dioxide and hydrogen mixture
Database, the thermal physical property data library are the structures by above-mentioned critical, carbon dioxide and hydrogen mixture thermal physical property data library
What construction method obtained.The present invention has the advantage that
Construct hot physical property model based on deep neural network, the model can rapidly and accurately according to given critical,
The input condition of the ternary mixture of carbon dioxide and hydrogen exports corresponding thermal physical property parameter.
Thermal physical property data provided by the present invention can be directly used for supercritical water and steam coal technology.Supercritical water steams coal technology will
Coal chemistry can be hydrogen chemical energy with the direct transform in order of middle low temperature heat energy, and gaseous state and particle contamination can be eradicated from source
The generation of object.After usually converting hydrogen for coal after chemical reaction, containing supercritical water, three kinds of works of carbon dioxide and hydrogen
Matter.Three kinds of working medium are transferred in thermodynamic cycle later and are generated electricity.Obtain supercritical water, carbon dioxide and hydrogen (H2O-CO2-
H2) ternary mixture thermophysical property be thermal cycle design basis and water steam coal technology be able to the foundation developed.
Detailed description of the invention
It, below will be to embodiment party in order to illustrate more clearly of embodiments of the present invention or technical solution in the prior art
Formula or attached drawing needed to be used in the description of the prior art are briefly described.It should be evident that the accompanying drawings in the following description is only
It is merely exemplary, it for those of ordinary skill in the art, without creative efforts, can also basis
The attached drawing of offer, which is extended, obtains other implementation attached drawings.
Structure depicted in this specification, ratio, size etc., only to cooperate the revealed content of specification, for
Those skilled in the art understands and reads, and is not intended to limit the invention enforceable qualifications, therefore does not have technical
Essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size are not influencing the function of the invention that can be generated
Under effect and the purpose that can reach, should all still it fall in the range of disclosed technology contents can cover.
Fig. 1 is the construction method of the critical of the embodiment of the present invention, carbon dioxide and hydrogen mixture thermal physical property data library
Flow chart;
Fig. 2 is the working principle of the hot physical property model of the critical of the embodiment of the present invention, carbon dioxide and hydrogen mixture
Figure;
Fig. 3 is to predict meto-super-critical H using deep neural network of the invention in an example2O-CO2-H2Ternary mixing
The result figure of object PVT property.
Specific embodiment
Embodiments of the present invention are illustrated by particular specific embodiment below, those skilled in the art can be by this explanation
Content disclosed by book is understood other advantages and efficacy of the present invention easily, it is clear that described embodiment is the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
In the description of the present invention, it is to be understood that, term " first " and " second " are used for description purposes only, and cannot
It is interpreted as indication or suggestion relative importance.
Fig. 1 is the construction method of the critical of the embodiment of the present invention, carbon dioxide and hydrogen mixture thermal physical property data library
Flow chart.As shown in Figure 1, the hot physical property model of the critical of the embodiment of the present invention, carbon dioxide and hydrogen mixture constructs
Method, comprising:
S1: multiple groups simulation and the experiment thermal physical property data of the ternary mixture of critical, carbon dioxide and hydrogen are obtained.Its
In, multiple groups thermal physical property data includes multiple groups input condition and multiple groups output as a result, multiple groups input condition and multiple groups output result one
One is corresponding.Every group of input condition includes temperature, pressure and the molar ratio of the ternary mixture of critical, carbon dioxide and hydrogen
Example.In an example of the invention, every group of output result includes volume, thermal conductivity, viscosity and diffusion coefficient.
In one embodiment of the invention, critical includes subcritical water and supercritical water.
In one embodiment of the invention, step S1 is specifically included:
S1-1: according to multiple groups output condition to H2O-CO2-H2Ternary mixture carry out respectively molecular dynamics simulation or
Experiment obtains multiple groups output result.
Specifically, select one group of input condition to H2O-CO2-H2Ternary mixture carry out molecular dynamics simulation or reality
It tests to obtain corresponding output result.
One group of input condition of reselection carries out molecular dynamics simulation or experiment obtains corresponding output as a result, until all
The input condition of group all carries out molecular dynamics simulation and obtains corresponding output result.
S1-2: multiple groups thermal physical property data is obtained according to multiple groups output condition and multiple groups output result.By multiple groups output condition
Storage corresponding with multiple groups output result obtains above-mentioned multiple groups thermal physical property data.
S2: simulating and tested according to multiple groups thermal physical property data by deep neural network training and obtain hot physical property model, heat
Physical property model is used for defeated according to the temperature for the ternary mixture for giving critical, carbon dioxide and hydrogen, pressure and molar ratio
Hot physical property result out.
Specifically, the result of molecular dynamics simulation is limited, and does not still know H in the region that do not simulate2O-CO2-H2
Ternary mixture thermal physical property parameter.Therefore, multiple groups thermal physical property data is divided into training set and test set, such as will be groups of
And the thermal physical property data of multiple groups thermal physical property data 95% is input in deep neural network as training set and is trained, and obtains one
The hot physical property mapping relations of the corresponding one group of output result of group input condition, i.e. initial mapping model.Then remaining thermal physical property data
(i.e. by groups of and multiple groups thermal physical property data 5% thermal physical property data) is input to initial mapping model as test set and surveys
Examination obtains test result, and test data carries out molecular dynamics simulation and obtains standard results, and then according to test result and mark
The parameter re -training of discrepancy adjustment initial mapping model between quasi- result, until the test result of re -training meets user
Until standard, using model when meeting user's specification as hot physical property model.
In one embodiment of the invention, batch normalizing is provided between the full articulamentum and active coating of deep neural network
Change layer, the learning efficiency of every layer of neuron can be effectively increased, inhibits over-fitting, and the study precision of neural network can be increased.
In one embodiment of the invention, the parameter optimization algorithm of deep neural network is Adam algorithm, depth nerve
The activation primitive of network is tanh Tanh, and hidden layer is Affine (affine layer), and the loss function of deep neural network is equal
Square error MSE.The number and total number of plies of every layer of neuron, user can flexible choices according to the actual situation.
Wherein, the parameter optimization algorithm of deep neural network is Adam algorithm, and the update of Adam is by using gradient
Operation mean value (running average) direct estimation at the first and second moment, but also corrected including a deviation
.
The activation primitive of deep neural network is tanh Tanh, and Tanh can allow neural network that can learn complexity
Decision boundary.
The hidden layer of deep neural network is affine layer.A full articulamentum in neural network.Affine layer is one layer of front
Each of neuron be all connected to each of current layer neuron.Affine layer be generally increased by convolutional neural networks or
Recognition with Recurrent Neural Network makes the top layer of the output before final prediction.The general type of affine layer is y=f (Wx+b), and wherein x is layer
Input, W is affine layer parameter, and b is a bias vector, and f is a nonlinear activation function.
The loss function of deep neural network is mean square error MSE.
Fig. 2 is the working principle of the hot physical property model of the critical of the embodiment of the present invention, carbon dioxide and hydrogen mixture
Figure.As shown in Fig. 2, P, T and X respectively represent H2O-CO2-H2Ternary mixture pressure, temperature and molar ratio.V represents body
Product, λ represent thermal conductivity, and μ represents viscosity, and D represents diffusion coefficient.
Batch Norm is commonly used accelerans network training in depth network, accelerates convergence rate and stability
Algorithm.Deep learning requires to normalize data on CV, because deep neural network mainly aims at study instruction
Practice the distribution of data, and reaches good extensive effect on test set.But if the data of each batch input have
There is different distributions, it is clear that can come to the training band of network difficult.On the other hand, data are after network query function layer by layer, number
Variation also is occurring according to distribution, difficulty can brought to next layer of e-learning.Batch Norm can solve this distribution
Variation issue.
It can be according to the H of input according to process shown in Fig. 22O-CO2-H2The pressure of ternary mixture, temperature and mole
Ratio obtains corresponding volume, thermal conductivity, viscosity and diffusion coefficient.
Fig. 3 is to predict meto-super-critical H using deep neural network algorithm of the invention in an example2O-CO2-H2Ternary
The result figure of mixture PVT property.As shown in figure 3, meto-super-critical H2O-CO2-H2The hot physical property of ternary mixture is at present mainly by passing through
Allusion quotation molecular dynamics simulation obtains, this partial data is also data used in deep neural network training.It is explained below point
The details parameter and setting of subdynamics simulation.Molecular dynamics simulation carries out under open source software packet LAMMPS environment.Simulation
When use 2500 molecules in total, boundary condition is periodic boundary condition, long range Coulomb interactions PPPM when simulation
Algorithm is integrated.Material calculation is set as 1 femtosecond.Nose-Hoover heating bath is used when temperature control.The potential function of water is selected as TIP4P,
The potential function of carbon dioxide is selected as EMP2, and the potential function of hydrogen is selected as two-site gesture.
From figure 3, it can be seen that deep neural network has carried out good study to the result of Molecular Dynamics Calculation, and
Accurate prediction result is given, general thermodynamical model is difficult to obtain so high precision.It is required in forecast period
Time is substantially in ms magnitude.The result confirm this software can high-precision and rapidly provide a user meto-super-critical H2O-CO2-
H2Ternary mixture thermal physical property parameter.
S3: providing the data under multiple groups different temperatures, pressure and the molar ratio of ternary mixture, according to multiple groups not equality of temperature
Degree, pressure and data under molar ratio and hot physical property model correspondence obtain the hot physical property number of multiple groups model prediction of ternary mixture
According to.
Specifically, after the completion of hot physical property model is established, H is provided2O-CO2-H2The multiple groups different temperatures of ternary mixture,
These data are input in hot physical property model by the data under pressure and molar ratio, more by the corresponding output of hot physical property model
Group model predicts thermal physical property data.Wherein, the H provided in step S32O-CO2-H2The data of ternary mixture answer it is enough, and
Temperature, pressure and the molar ratio condition that may be used comprising water-gas technology.
S4: simulating according to multiple groups and test thermal physical property data and multiple groups model prediction thermal physical property data constructs ternary mixture
Thermal physical property data library, and provide the query interface in thermal physical property data library.In this way, related personnel can pass through thermal physical property data library
Directly acquire H2O-CO2-H2The thermal physical property data of ternary mixture.
The present invention has the advantage that
Construct hot physical property model based on deep neural network, the model can rapidly and accurately according to given critical,
The input condition of the ternary mixture of carbon dioxide and hydrogen exports corresponding thermal physical property parameter.
Thermal physical property data provided by the present invention can be directly used for supercritical water and steam coal technology.Supercritical water steams coal technology will
Coal chemistry can be hydrogen chemical energy with the direct transform in order of middle low temperature heat energy, and gaseous state and particle contamination can be eradicated from source
The generation of object.After usually converting hydrogen for coal after chemical reaction, containing supercritical water, three kinds of works of carbon dioxide and hydrogen
Matter.Three kinds of working medium are transferred in thermodynamic cycle later and are generated electricity.Obtain supercritical water, carbon dioxide and hydrogen (H2O-CO2-
H2) ternary mixture thermophysical property be thermal cycle design basis and water steam coal technology be able to the foundation developed.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although above having used general explanation and specific embodiment, the present invention is described in detail, at this
On the basis of invention, it can be made some modifications or improvements, this will be apparent to those skilled in the art.Therefore,
These modifications or improvements without departing from theon the basis of the spirit of the present invention are fallen within the scope of the claimed invention.
Claims (6)
1. the construction method of a kind of critical, carbon dioxide and hydrogen mixture thermal physical property data library characterized by comprising
Obtain multiple groups simulation and the experiment thermal physical property data of the ternary mixture of critical, carbon dioxide and hydrogen, the multiple groups
Simulation and experiment thermal physical property data include multiple groups input condition and multiple groups output as a result, the multiple groups input condition and the multiple groups
It exports result to correspond, every group of input condition includes temperature, pressure and the molar ratio of the ternary mixture;
Thermal physical property data is simulated and tested according to the multiple groups, and hot physical property model, the heat are obtained by deep neural network training
Physical property model is used for according to temperature, pressure and the molar ratio heat outputting physical property result for giving the ternary mixture;
Data under multiple groups different temperatures, pressure and the molar ratio of the ternary mixture are provided, it is different according to the multiple groups
Data and the corresponding multiple groups model for obtaining the ternary mixture of the hot physical property model under temperature, pressure and molar ratio are pre-
Calorimetric physical data;
Thermal physical property data is simulated and tested according to the multiple groups and the multiple groups model prediction thermal physical property data constructs the ternary
The thermal physical property data library of mixture, and the query interface in the thermal physical property data library is provided.
2. the construction method of critical according to claim 1, carbon dioxide and hydrogen mixture thermal physical property data library,
It is characterized in that, the parameter optimization algorithm of the deep neural network is Adam algorithm, the activation primitive of the deep neural network
Hidden layer for tanh Tanh, the deep neural network is affine layer, and the loss function of the deep neural network is equal
Square error MSE.
3. the construction method of critical according to claim 1, carbon dioxide and hydrogen mixture thermal physical property data library,
It is characterized in that, the multiple groups thermal physical property data of the ternary mixture for obtaining critical, carbon dioxide and hydrogen specifically includes:
Molecular dynamics simulation is carried out respectively according to the multiple groups output condition or experiment obtains the multiple groups output result;
The multiple groups simulation and experiment thermal physical property data are obtained according to the multiple groups output condition and multiple groups output result.
4. the construction method of critical according to claim 1, carbon dioxide and hydrogen mixture thermal physical property data library,
It is characterized in that, batch normalization layer is provided between the full articulamentum and active coating of the deep neural network.
5. the construction method of critical according to claim 1, carbon dioxide and hydrogen mixture thermal physical property data library,
It is characterized in that, the critical includes subcritical water and supercritical water.
6. the thermal physical property data library of a kind of critical, carbon dioxide and hydrogen mixture, which is characterized in that the critical, two
The thermal physical property data library of carbonoxide and hydrogen mixture is by the described in any item criticals of claim 1-5, carbon dioxide
It is obtained with the construction method in hydrogen mixture thermal physical property data library.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910828664.XA CN110515930A (en) | 2019-09-03 | 2019-09-03 | Critical, carbon dioxide and hydrogen mixture thermal physical property data library and construction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910828664.XA CN110515930A (en) | 2019-09-03 | 2019-09-03 | Critical, carbon dioxide and hydrogen mixture thermal physical property data library and construction method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110515930A true CN110515930A (en) | 2019-11-29 |
Family
ID=68630583
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910828664.XA Pending CN110515930A (en) | 2019-09-03 | 2019-09-03 | Critical, carbon dioxide and hydrogen mixture thermal physical property data library and construction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110515930A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111899814A (en) * | 2020-06-12 | 2020-11-06 | 中国石油天然气股份有限公司 | Method, equipment and storage medium for calculating physical properties of single molecule and mixture |
CN113505540A (en) * | 2021-06-07 | 2021-10-15 | 中国船舶重工集团公司第七一九研究所 | Supercritical carbon dioxide PCHE multi-field coupling rapid prediction method, device and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040110193A1 (en) * | 2001-07-31 | 2004-06-10 | Gene Logic, Inc. | Methods for classification of biological data |
CN106874511A (en) * | 2017-03-06 | 2017-06-20 | 云南电网有限责任公司电力科学研究院 | A kind of database for corroding quantity of electric charge forecasting system based on insulator metal accessory |
US20180341866A1 (en) * | 2017-05-26 | 2018-11-29 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method of building a sorting model, and application method and apparatus based on the model |
CN109557126A (en) * | 2018-12-07 | 2019-04-02 | 东北大学 | A kind of measuring device of soil thermal property parameter and seepage parameters |
CN109708651A (en) * | 2017-10-25 | 2019-05-03 | 朱奕瑾 | Path adaptation and path planning algorithm based on GIS database |
-
2019
- 2019-09-03 CN CN201910828664.XA patent/CN110515930A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040110193A1 (en) * | 2001-07-31 | 2004-06-10 | Gene Logic, Inc. | Methods for classification of biological data |
CN106874511A (en) * | 2017-03-06 | 2017-06-20 | 云南电网有限责任公司电力科学研究院 | A kind of database for corroding quantity of electric charge forecasting system based on insulator metal accessory |
US20180341866A1 (en) * | 2017-05-26 | 2018-11-29 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method of building a sorting model, and application method and apparatus based on the model |
CN109708651A (en) * | 2017-10-25 | 2019-05-03 | 朱奕瑾 | Path adaptation and path planning algorithm based on GIS database |
CN109557126A (en) * | 2018-12-07 | 2019-04-02 | 东北大学 | A kind of measuring device of soil thermal property parameter and seepage parameters |
Non-Patent Citations (1)
Title |
---|
杨薛明等: "H_2O/H_2/CO_2混合工质PVT性质的分子动力学模拟研究", 《工程热物理学报》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111899814A (en) * | 2020-06-12 | 2020-11-06 | 中国石油天然气股份有限公司 | Method, equipment and storage medium for calculating physical properties of single molecule and mixture |
CN111899814B (en) * | 2020-06-12 | 2024-05-28 | 中国石油天然气股份有限公司 | Single molecule and mixture physical property calculation method, device and storage medium |
CN113505540A (en) * | 2021-06-07 | 2021-10-15 | 中国船舶重工集团公司第七一九研究所 | Supercritical carbon dioxide PCHE multi-field coupling rapid prediction method, device and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Bao et al. | A data-driven framework for error estimation and mesh-model optimization in system-level thermal-hydraulic simulation | |
Samadianfard | Gene expression programming analysis of implicit Colebrook–White equation in turbulent flow friction factor calculation | |
Duke et al. | Mean field ring polymer molecular dynamics for electronically nonadiabatic reaction rates | |
Wang et al. | College English Classroom Teaching Evaluation Based on Particle Swarm Optimization-Extreme Learning Machine Model. | |
CN102129259B (en) | Neural network proportion integration (PI)-based intelligent temperature control system and method for sand dust environment test wind tunnel | |
CN110222828A (en) | A kind of Unsteady Flow method for quick predicting based on interacting depth neural network | |
CN110515930A (en) | Critical, carbon dioxide and hydrogen mixture thermal physical property data library and construction method | |
Menin | Information measure approach for calculating model uncertainty of physical phenomena | |
CN105260786A (en) | Comprehensive optimization method of simulation credibility evaluation model of electric propulsion system | |
Li et al. | Deep learning for multifidelity aerodynamic distribution modeling from experimental and simulation data | |
CN110189800A (en) | Furnace oxygen content soft-measuring modeling method based on more granularities cascade Recognition with Recurrent Neural Network | |
Ranade et al. | Generalized joint probability density function formulation inturbulent combustion using deeponet | |
Frey et al. | Artificial Neural Network modelling of sorption chillers | |
Zhou et al. | Machine learning based heat release rate indicator of premixed methane/air flame under wide range of equivalence ratio | |
Bartel et al. | Force calibration using errors-in-variables regression and Monte Carlo uncertainty evaluation | |
Shao et al. | A method for evaluating and improving linear power flow models in system with large fluctuations | |
Ren et al. | Reduced description of complex dynamics in reactive systems | |
Vollant et al. | Optimal estimator and artificial neural network as efficient tools for the subgrid-scale scalar flux modeling | |
Mavris et al. | Relational Oriented Systems Engineering and Technology Tradeoff Analysis (ROSETTA) Environment | |
Cheng et al. | Exercise recommendation method combining neuralcd and neumf models | |
Chen et al. | Research on Cognitive Diagnostic Model Based on BP Neural Network | |
Yang et al. | Coal Mine Safety Evaluation with V-Fold Cross-Validation and BP Neural Network. | |
Zhou et al. | Multi-fault diagnosis of district heating system based on PCA_BP neural network | |
Zhou | Exploring application of machine learning to power system analysis | |
Brokarev et al. | Multi-criteria estimation of input parameters in natural gas quality analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191129 |