CN112182965A - Method for designing infrared phase change material based on deep learning - Google Patents
Method for designing infrared phase change material based on deep learning Download PDFInfo
- Publication number
- CN112182965A CN112182965A CN202011022757.2A CN202011022757A CN112182965A CN 112182965 A CN112182965 A CN 112182965A CN 202011022757 A CN202011022757 A CN 202011022757A CN 112182965 A CN112182965 A CN 112182965A
- Authority
- CN
- China
- Prior art keywords
- layer
- network
- designing
- deep learning
- phase change
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 239000012782 phase change material Substances 0.000 title claims abstract description 22
- 238000013135 deep learning Methods 0.000 title claims abstract description 20
- 239000000463 material Substances 0.000 claims abstract description 52
- 238000013461 design Methods 0.000 claims abstract description 27
- 238000001228 spectrum Methods 0.000 claims abstract description 20
- 230000004044 response Effects 0.000 claims abstract description 17
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 230000003595 spectral effect Effects 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000004519 manufacturing process Methods 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims abstract description 4
- 238000012546 transfer Methods 0.000 claims abstract description 4
- 239000002184 metal Substances 0.000 claims description 9
- 229910052751 metal Inorganic materials 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 8
- 238000004364 calculation method Methods 0.000 abstract description 5
- 230000002068 genetic effect Effects 0.000 abstract description 5
- 230000007547 defect Effects 0.000 abstract description 4
- 229910005900 GeTe Inorganic materials 0.000 description 19
- 238000005457 optimization Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000005094 computer simulation Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000002086 nanomaterial Substances 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- 239000011324 bead Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 210000000349 chromosome Anatomy 0.000 description 1
- 239000011258 core-shell material Substances 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000008303 genetic mechanism Effects 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 239000008204 material by function Substances 0.000 description 1
- 239000004005 microsphere Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 239000008188 pellet Substances 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Aiming, Guidance, Guns With A Light Source, Armor, Camouflage, And Targets (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
Abstract
The invention discloses a method for designing an infrared phase change material based on deep learning, which comprises the following steps: step a, determining the types of inner layer materials and outer layer materials, and determining the number of layers and the thickness range of the inner layer and the outer layer; b, respectively manufacturing data sets corresponding to different material combinations by using a Mie scattering transfer matrix algorithm, wherein the thickness of each layer of each material combination is randomly distributed; step c, determining DNN network hyperparameters, and carrying out DNN network training on the data set based on a GPU; d, determining a proper material for the next design according to the response characteristics of the spectrum in the classification result; e, training and optimizing a sub-network corresponding to the suitable material, and designing structural parameters according to the sub-network; and f, obtaining specific parameters of the material and the structure. The method for designing the infrared phase change material based on the deep learning can quickly design a structure according to the required spectral response at any time and overcome the defect of long iterative calculation process of a genetic algorithm.
Description
Technical Field
The invention relates to a method for designing an infrared phase change material based on deep learning, and belongs to the technical field of micro-nano optical structure design.
Background
In photonics, forward calculation from a structure to a spectrum can be well calculated and understood by Maxwell equations, but solving an inverse problem is often a complex problem because high-dimensional space mapping is usually involved in design, and it is difficult to plan a plurality of design parameters at one time. The design of the traditional micro-nano optical structure is that the simulation modeling is generally carried out on the nano structure, the material, the surrounding medium and the acting wave band by using finite element software, and whether the spectral response can achieve an ideal effect or not is transversely compared by changing a parameter.
In the prior art, a genetic algorithm is often used as an optimization algorithm for reverse design. The genetic algorithm is a calculation model of a biological evolution process for simulating natural selection and genetic mechanism of Darwinian biological evolution theory, and is a method for searching an optimal solution by simulating the natural evolution process. The algorithm converts the solving process of the problem into the processes of crossover, variation and the like of chromosome genes in the similar biological evolution by a mathematical mode and by utilizing computer simulation operation. When a complex combined optimization problem is solved, the speed advantage can still be embodied compared with some conventional optimization algorithms.
The genetic algorithm is used for solving the inverse design problem of a set of system, an objective function is determined for optimizing a structure, and a large amount of computing power and time are needed, wherein the time grows exponentially along with the complexity of parameters. In a colloquial way, if a multi-layer Ag-GeTe core-shell structure realizing super-scattering in 2000nm wave band is optimized, the thickness of each layer is regarded as a single design or as an individual, all groups are involved to form a population, and the adaptability of each individual in the population is evaluated, so that the possibility of the individual becoming a next generation parent can be obtained. When one structure is designed, the design time is longer and longer as the number of layers of the multilayer ball is larger according to the complexity of the structure, and if the number of the layers of the two-layer structure is 10 minutes, the number of the layers of the four-layer structure is about 30 minutes, so that the defect of long iterative calculation process exists.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a method for designing an infrared phase-change material based on deep learning, which can quickly design a structure according to the required spectral response at any time and overcome the defect of long iterative calculation process of a genetic algorithm.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a method for designing an infrared phase change material based on deep learning comprises the following steps:
step a, determining the types of the inner layer material and the outer layer material, and determining the number of layers and the thickness range of the inner layer and the outer layer. In the design of the micro-nano material, a material selection link is added, so that the embarrassment that the design cannot be continued due to the problem of material limitation can be avoided, and more possibilities can be provided for the design by selecting the material.
B, respectively manufacturing data sets corresponding to different material combinations by using a Mie scattering transfer matrix algorithm, wherein the thickness of each layer of each material combination is randomly distributed;
and c, determining DNN network hyperparameters, and carrying out DNN network training on the data set based on the GPU. The DNN network with deep learning can be designed more quickly without long design time like other optimization algorithms, and design efficiency is improved.
D, determining a proper material for the next design according to the response characteristics of the spectrum in the classification result;
e, training and optimizing a sub-network corresponding to the suitable material, and designing structural parameters according to the sub-network;
and f, obtaining specific parameters of the material and the structure.
In the step a, the inner layer and the outer layer are in a structure of 2 layers, 4 layers or 6 layers, and the thickness of each layer is defined to be 30-200 nm.
In the step b, two dielectric constants of the outer phase-change material at low temperature and high temperature are selected as data of the data set.
In step c, the DNN network input layer is discrete value points of a spectrum, the wave band is an infrared wave band of 1000-3000nm, every 5nm is used as an interval, 401 discrete points are totally arranged, and the output classification layers respectively represent different inner layer materials. The design waveband selection of the spectrum is flexible, the whole spectrum input can be used for predicting the structure, and the design can also be carried out through a target function.
In the step d, firstly, a classification network with spectral response as input and material as output is pre-trained, an output layer adopts a single hot coding mode, then after the network is obtained, a target spectral response is added into an input layer, and a most appropriate metal layer material after network screening is obtained on the output layer.
In step e, the subnetwork input is spectrum Y0The output is the thickness value of each layer, and the structure result predicted by the final network is introduced into the forward network to obtain the correct predicted spectrum Y1Then obtaining Y from the mean square error formula1And Y0The loss value of (2) is smaller than the loss value obtained by judging the structure parameters of the specific layers.
The invention has the beneficial effects that: according to the method for designing the infrared phase change material based on deep learning, a deep learning algorithm is adopted, although the previous network training is time-consuming, once the network is formed, the training speed is within a few seconds, and the speed is obviously improved compared with other optimization algorithms; the most suitable material can be automatically selected according to the target spectrum, the accuracy of the selection of the material is 83%, and even if the network prediction is not completely correct, the fact that various materials have applicability to the target spectrum is shown; the phase change material which can well generate ultra-scattering infrared wave band to low-scattering infrared wave band can regulate and control specific wave band; the network can relate to other functional materials according to a specific objective function, flexible design can be realized, and after the objective function is changed, the design can be still completed quickly within a few seconds.
Drawings
FIG. 1 is a schematic structural diagram of a multilayer micro-nano small sphere phase change material in the invention;
FIG. 2 is a schematic flow chart illustrating a method for designing an infrared phase change material based on deep learning according to the present invention;
FIG. 3 shows scattering spectra for different target peaks designed using two layers of Ag-GeTe particles.
Detailed Description
The present invention is further described with reference to the accompanying drawings, and the following examples are only for clearly illustrating the technical solutions of the present invention, and should not be taken as limiting the scope of the present invention.
As shown in fig. 2, the present invention provides a method for designing an infrared phase change material based on deep learning, comprising the following steps:
firstly, a process of manufacturing a data set is determined, which specific materials, such as inner layer materials of Ag, Al and Au, and outer layer materials of GeTe, and the layer number and thickness range of each layer, such as 2-layer, 4-layer or 6-layer structures, are determined, and each layer is defined to be about 30-200 nm. As GeTe is a phase-change material, two dielectric constants of GeTe at low temperature and high temperature are mainly adopted. The design of optical structures may not achieve the desired spectral response due to limitations in the properties of the individual materials, and no optimization of the structure in any way can achieve the desired result, since we only consider the combination of two materials during the design process, and no attempt is made to select combinations of multiple materials. The structure of the multi-layer micro-nano microsphere phase change material is shown in figure 2.
Step two, respectively manufacturing corresponding data sets of Ag-GeTe, Al-GeTe and Au-GeTe by using a Mie scattering transfer matrix algorithm, wherein the thickness of each layer of each group is randomly distributed, and after the data sets are manufactured, the data sets should be as follows:
2 layers (Metal layer-GeTe layer) | 4 layers (Metal layer-GeTe layer-Metal layer-GeTe layer) | |
Ag-GeTe | Data set 1-1 | Data set 1-2 |
Al-GeTe | Data set 2-1 | Data set 2-2 |
Au-GeTe | Data set 3-1 | Data set 3-2 |
And step three, determining DNN network hyperparameters, and carrying out DNN network training on the data set based on the GPU. All data sets are integrated (i.e. data sets 1-1 to 3-2) to establish a multi-layer perceptron for classifying materials, which is a deep learning mode and records a physical mode of spectral response corresponding to materials by using a fully connected layer, namely a Deep Neural Network (DNN). The reverse design method based on the deep learning algorithm is a multi-layer characterization learning technology, which can find and classify the required characterization from the original data, and enables the neural network to learn the mapping from a very complex structure to a response in a data-driven manner through the combination of a large number of cascaded nonlinear neurons.
The network input layer is a spectrum discrete value point, the optimized wave band is an infrared wave band of 1000-3000nm, every 5nm is used as an interval, there are 401 discrete points, and the output classification layers respectively represent three materials.
And step four, carrying in all data sets for classification training, and judging which material is used for the next design according to the response characteristics of the spectrum by the final classification result. The method specifically comprises the following steps: firstly, a spectral response (input) -material (output) classification network is pre-trained, and an output layer adopts a form of unique thermal coding (softmax), namely a form metal layer of the output layer 1-0-0 is Ag, a form metal layer of the output layer 0-1-0 is Al, and a form metal layer of the output layer 0-0-1 is Au, so that the accuracy of the classification network during training can be ensured. Then after obtaining the network, adding the target spectral response to the input layer, a most suitable metal layer material after network screening can be obtained at the output layer, and then each layer thickness of the multilayer particle can be designed in detail by using the data set of the material.
And fifthly, training and optimizing the sub-networks corresponding to the suitable materials, and designing structural parameters according to the sub-networks. After the material is determined, we train sub-networks of 2, 4-layer structure, respectively. The variables designed by the invention are the thickness of each of the Ag layer and the GeTe layer, whether the number of the layers is 2 layers or 4 layers or more, and the variables are closely related to the spectral response. For example, according to the spectral characteristics, the Ag-GeTe is determined to be selected for design according to the network, and then the next step is to train the Ag-GeTe multilayer network. The input of the network is a spectrum Y0, the output is the thickness value of each layer, the structure result predicted by the final network can be brought into a forward network to obtain a correct predicted spectrum Y1, then the loss values of Y1 and Y0 are obtained by a mean square error formula, and the fact that the structure parameters of the specific layers can obtain smaller loss is judged, namely a better result is obtained.
And step six, obtaining specific parameters of the material and the structure. Experiments prove that when the infrared phase change scattering material is designed, the Ag-GeTe multilayer pellet with a two-layer structure has an ideal effect, the loss value is 0.00532, and the material of the four layers is more than 1.
As shown in fig. 3, since the wavelength controllability is not large at a high temperature, the scattering rate of the beads is mainly designed at a low temperature. Specific scattering peak positions are defined in the near-infrared band, the network can select the structural parameters (namely the thickness of each layer) of each layer according to the positions, and the scattering spectrum designed by two layers of Ag-GeTe particles for different target peaks is shown in figure 3, so that an obvious regulation and control design effect can be seen.
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.
Claims (6)
1. A method for designing an infrared phase change material based on deep learning is characterized by comprising the following steps: the method comprises the following steps:
step a, determining the types of inner layer materials and outer layer materials, and determining the number of layers and the thickness range of the inner layer and the outer layer;
b, respectively manufacturing data sets corresponding to different material combinations by using a Mie scattering transfer matrix algorithm, wherein the thickness of each layer of each material combination is randomly distributed;
step c, determining DNN network hyperparameters, and carrying out DNN network training on the data set based on a GPU;
d, determining a proper material for the next design according to the response characteristics of the spectrum in the classification result;
e, training and optimizing a sub-network corresponding to the suitable material, and designing structural parameters according to the sub-network;
and f, obtaining specific parameters of the material and the structure.
2. The method for designing the infrared phase change material based on the deep learning as claimed in claim 1, wherein: in the step a, the inner layer and the outer layer are in a structure of 2 layers, 4 layers or 6 layers, and the thickness of each layer is defined to be 30-200 nm.
3. The method for designing the infrared phase change material based on the deep learning as claimed in claim 1, wherein: in the step b, two dielectric constants of the outer phase-change material at low temperature and high temperature are selected as data of the data set.
4. The method for designing the infrared phase change material based on the deep learning as claimed in claim 1, wherein: in step c, the DNN network input layer is discrete value points of a spectrum, the wave band is an infrared wave band of 1000-3000nm, every 5nm is used as an interval, 401 discrete points are totally arranged, and the output classification layers respectively represent different inner layer materials.
5. The method for designing the infrared phase change material based on the deep learning as claimed in claim 1, wherein: in the step d, firstly, a classification network with spectral response as input and material as output is pre-trained, an output layer adopts a single hot coding mode, then after the network is obtained, a target spectral response is added into an input layer, and a most appropriate metal layer material after network screening is obtained on the output layer.
6. The method for designing the infrared phase change material based on the deep learning as claimed in claim 1, wherein: in step e, the subnetwork input is spectrum Y0The output is the thickness value of each layer, and the structure result predicted by the final network is introduced into the forward network to obtain the correct predicted spectrum Y1Then obtaining Y from the mean square error formula1And Y0The loss value of (2) is smaller than the loss value obtained by judging the structure parameters of the specific layers.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011022757.2A CN112182965B (en) | 2020-09-25 | 2020-09-25 | Method for designing infrared phase change material based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011022757.2A CN112182965B (en) | 2020-09-25 | 2020-09-25 | Method for designing infrared phase change material based on deep learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112182965A true CN112182965A (en) | 2021-01-05 |
CN112182965B CN112182965B (en) | 2024-02-02 |
Family
ID=73944874
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011022757.2A Active CN112182965B (en) | 2020-09-25 | 2020-09-25 | Method for designing infrared phase change material based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112182965B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120265596A1 (en) * | 2007-09-06 | 2012-10-18 | Mazed Mohammad A | System and method for intelligent social commerce |
CN108872130A (en) * | 2018-06-25 | 2018-11-23 | 北京空间飞行器总体设计部 | Typical aircraft Facing material recognition methods neural network based |
CN109271700A (en) * | 2018-09-10 | 2019-01-25 | 柯瑞林 | Battery thermal management method and system based on the modeling of deep learning multitiered network |
US20190278880A1 (en) * | 2018-03-12 | 2019-09-12 | Exxonmobil Research And Engineering Company | Hybrid computational materials fabrication |
JP6624533B1 (en) * | 2018-11-08 | 2019-12-25 | ジャパンモード株式会社 | Material property estimation program, Material generation mechanism estimation program |
CN110826289A (en) * | 2019-10-29 | 2020-02-21 | 中国地质大学(武汉) | Deep learning-based nano structure design method |
CN111177976A (en) * | 2019-12-25 | 2020-05-19 | 广东省焊接技术研究所(广东省中乌研究院) | Arc welding seam forming accurate prediction method based on deep learning |
WO2020117348A2 (en) * | 2018-12-06 | 2020-06-11 | Western Digital Technologies, Inc. | Non-volatile memory die with deep learning neural network |
WO2020130513A1 (en) * | 2018-12-18 | 2020-06-25 | 주식회사 포스코 | System and method for predicting material properties using metal microstructure images based on deep learning |
-
2020
- 2020-09-25 CN CN202011022757.2A patent/CN112182965B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120265596A1 (en) * | 2007-09-06 | 2012-10-18 | Mazed Mohammad A | System and method for intelligent social commerce |
US20190278880A1 (en) * | 2018-03-12 | 2019-09-12 | Exxonmobil Research And Engineering Company | Hybrid computational materials fabrication |
CN108872130A (en) * | 2018-06-25 | 2018-11-23 | 北京空间飞行器总体设计部 | Typical aircraft Facing material recognition methods neural network based |
CN109271700A (en) * | 2018-09-10 | 2019-01-25 | 柯瑞林 | Battery thermal management method and system based on the modeling of deep learning multitiered network |
JP6624533B1 (en) * | 2018-11-08 | 2019-12-25 | ジャパンモード株式会社 | Material property estimation program, Material generation mechanism estimation program |
WO2020117348A2 (en) * | 2018-12-06 | 2020-06-11 | Western Digital Technologies, Inc. | Non-volatile memory die with deep learning neural network |
WO2020130513A1 (en) * | 2018-12-18 | 2020-06-25 | 주식회사 포스코 | System and method for predicting material properties using metal microstructure images based on deep learning |
CN110826289A (en) * | 2019-10-29 | 2020-02-21 | 中国地质大学(武汉) | Deep learning-based nano structure design method |
CN111177976A (en) * | 2019-12-25 | 2020-05-19 | 广东省焊接技术研究所(广东省中乌研究院) | Arc welding seam forming accurate prediction method based on deep learning |
Non-Patent Citations (2)
Title |
---|
KYUNGDOC KIM等: "Deep-learning-based inverse design model for intelligent discovery of organic molecules", 《COMPUTATIONAL MATERIALS》 * |
杨宇等: "一种基于深度学习的复合材料结构损伤导波监测方法", 《航空科学技术》 * |
Also Published As
Publication number | Publication date |
---|---|
CN112182965B (en) | 2024-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Jia et al. | A novel optimized GA–Elman neural network algorithm | |
CN113053115B (en) | Traffic prediction method based on multi-scale graph convolution network model | |
CN115099519B (en) | Oil well yield prediction method based on multi-machine learning model fusion | |
CN106355330A (en) | Multi-response parameter optimization method based on radial basis function neural network prediction model | |
CN108665070A (en) | Limit TS fuzzy reasoning methods based on extreme learning machine and system | |
CN112364913A (en) | Federal learning communication traffic optimization method and system based on core data set | |
CN111203887B (en) | Robot control system optimization method based on NSGA-II fuzzy logic reasoning | |
CN104050505A (en) | Multilayer-perceptron training method based on bee colony algorithm with learning factor | |
Jaddi et al. | Taguchi-based parameter designing of genetic algorithm for artificial neural network training | |
Oh et al. | Hybrid fuzzy set-based polynomial neural networks and their development with the aid of genetic optimization and information granulation | |
CN114118567A (en) | Power service bandwidth prediction method based on dual-channel fusion network | |
CN112182965B (en) | Method for designing infrared phase change material based on deep learning | |
Adra et al. | A hybrid multi-objective evolutionary algorithm using an inverse neural network for aircraft control system design | |
Wu et al. | Echo state network prediction based on backtracking search optimization algorithm | |
CN113113776B (en) | Terahertz composite metamaterial multi-band absorber and bidirectional design method | |
Sharma et al. | Multi-objective Service Composition Optimization in Smart Agriculture Using Fuzzy-Evolutionary Algorithm | |
CN114202063A (en) | Fuzzy neural network greenhouse temperature prediction method based on genetic algorithm optimization | |
Lin et al. | Applying Taguchi’s Method, Artificial Neural Network and Genetic Algorithm to Reduce the CoSi₂ Resistance Deviation of DRAM Products | |
Almeida et al. | An improved method for automatically searching near-optimal artificial neural networks | |
Yen et al. | Hierarchical rank density genetic algorithm for radial-basis function neural network design | |
Tsimenidis | Evolutionary algorithms for fuzzy cognitive maps | |
Yang et al. | ELM weighted hybrid modeling and its online modification | |
Takahama et al. | Structural learning of neural networks by coevolutionary genetic algorithm with degeneration | |
Xie et al. | Time Series Prediction of ESN Based on Chebyshev Mapping and Strongly Connected Topology | |
CN113946974A (en) | Self-organizing one-type hierarchical fuzzy prediction system based on multi-objective optimization |
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 |