CN108059177A - A kind of method that hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake - Google Patents
A kind of method that hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake Download PDFInfo
- Publication number
- CN108059177A CN108059177A CN201711423361.7A CN201711423361A CN108059177A CN 108059177 A CN108059177 A CN 108059177A CN 201711423361 A CN201711423361 A CN 201711423361A CN 108059177 A CN108059177 A CN 108059177A
- Authority
- CN
- China
- Prior art keywords
- bittern
- mrow
- magnesium hydroxide
- pso
- salt lake
- 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.)
- Withdrawn
Links
Classifications
-
- C—CHEMISTRY; METALLURGY
- C01—INORGANIC CHEMISTRY
- C01F—COMPOUNDS OF THE METALS BERYLLIUM, MAGNESIUM, ALUMINIUM, CALCIUM, STRONTIUM, BARIUM, RADIUM, THORIUM, OR OF THE RARE-EARTH METALS
- C01F5/00—Compounds of magnesium
- C01F5/14—Magnesium hydroxide
- C01F5/22—Magnesium hydroxide from magnesium compounds with alkali hydroxides or alkaline- earth oxides or hydroxides
Landscapes
- Chemical & Material Sciences (AREA)
- Organic Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Inorganic Chemistry (AREA)
- Compounds Of Alkaline-Earth Elements, Aluminum Or Rare-Earth Metals (AREA)
Abstract
The invention discloses a kind of methods that hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake, include the following steps:By the BP neural network that multigroup experimental data that hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake is optimized for training through PSO, the experimental data includes preparation parameter and experimental result, and the group number of experimental data is more than or equal to 100 groups;The BP neural network through PSO optimizations after gained training can provide the preparation parameter of optimization, prediction hexagonal sheet magnesium hydroxide ratio with the physical and chemical properties change of bittern in salt lake;Using the preparation parameter of optimization, hexagonal sheet magnesium hydroxide is prepared.Experimental data is realized into digital intellectualization using PSO Optimized BP Neural Networks, hexagonal sheet magnesium hydroxide can be produced for bittern at any time and optimal experimental program and Accurate Prediction experimental result are provided, greatly reduce and substantial amounts of human and material resources and the wasting of resources are brought due to groping property is tested.
Description
Technical field
The present invention relates to technical field of preparation for inorganic material, and in particular, to a kind of to prepare six square pieces using bittern in salt lake
The method of shape magnesium hydroxide.
Background technology
Magnesium hydroxide is important magnesium salts functional material, with excellent mechanical property, corrosion-and high-temp-resistant, uniqueness
Enhancing, flame retardant property have important application value improving metal, plastics and ceramic and other composite material aspect of performance.These
Using the physicochemical properties for all deriving from crystal morphology, size and dispersion degree decision that magnesium hydroxide crystal possesses.Sheet
The magnesium hydroxide crystal of structure is due to having the characteristics that high-purity, uniform particle sizes, pattern rule and surface hydrophilic oleophobic, and machinery
Performance and good dispersion degree have both the function of filling and halogen-free flameproof in thermal plastic high polymer and fibrous material, moreover it is possible to improve high
The initial temperature of molecule burning, increases thermal stability.Therefore, sheet-like magnesium hydroxide crystal fire proofing is the heat studied at present
Point, it is current to prepare in high-quality fire retardant most one of direction of future to prepare flake magnesium hydroxide.
The current common method for preparing hexagonal sheet magnesium hydroxide has a sodium hydroxide magnesium sinking hydro-thermal method, and this method is sunk adding alkali
Gelatinous precipitate is formed since hydrate molecule cannot exclude in time during magnesium, so as to precipitation, filtering, washing lock out operation
It brings a lot of trouble.If by this method be applied to bittern in salt lake, whenever bittern physicochemical properties change once, will do
A large amount of numerous and diverse groping property test to adapt to new condition, expend substantial amounts of human and material resources, are not suitable for industrial mass production.
The content of the invention
The present invention provides a kind of utilization bittern in salt lake and prepares hexagonal flake hydrogen-oxygen to overcome the above-mentioned deficiency of the prior art
Change the method for magnesium.
To achieve these goals, the present invention is achieved by following scheme:
A kind of method that hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake, which is characterized in that include the following steps:
S1. multigroup experimental data that hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake is optimized for training through PSO
BP neural network, the experimental data includes preparation parameter and experimental result, and the group number of experimental data is more than or equal to 100 groups;
The mathematical model of the PSO is:
vij(t+1)=vij(t)+c1r1j(t)[pij(t)-xij(t)]+c2r2j(t)[gj(t)-xij(t)] (1)
xij(t+1)=xij(t)+vij(t+1) (2)
In formula (1) and formula (2), j is that the jth of particle is tieed up, and i is i-th of particle;t:Represent current evolutionary generation;vij(t) it is hidden
Containing i-th of node of layer to the weights between j-th of node;pij(t) particle i passes through the position of j;gij(t) population i is passed through
Cross the position of j;xij(t) current particle i is in the position of j;c1And c2All it is the restriction factor of change in displacement, is preset value;R be with
Machine function;
The PSO Optimized BP Neural Networks are that the J values in formula (3) are minimum, and J is mean square deviation index;
In formula (3), N is training sample sum, and M is the number of neuron,It is j-th of neurode of i-th of sample
Target output value, yj,iIt is the real output value of j-th of neurode of i-th of sample;
S2. gained training after through PSO optimization BP neural network can with the physical and chemical properties change of bittern in salt lake and
Provide preparation parameter, the prediction hexagonal sheet magnesium hydroxide ratio of optimization;Using the preparation parameter of optimization, six square pieces are prepared
Shape magnesium hydroxide.
c1And c2All it is the restriction factor of change in displacement, is preset value, usual value is 2.
The process of the BP neural network of training PSO optimizations is as shown in Figure 3.
Using bittern in salt lake prepare hexagonal sheet magnesium hydroxide preparation experimental implementation can refer to the prior art obtain and
Corresponding preparation parameter also can refer to the prior art and obtain.
BP (Back Propagation) neutral net is a kind of Multi-layered Feedforward Networks trained by Back Propagation Algorithm,
It is one of current most widely used neural network model, it can learn and store substantial amounts of input-output mode map relation,
The math equation of this mapping relations is described without disclosing in advance, there is stronger adaptivity, learning ability and extensive
Computation capability.But it is used alone that BP neural network sample size in need is big, convergence rate is slow, generalization ability is weak etc. no
Foot, for this purpose, being re-introduced into particle cluster algorithm (Particle Swarm Optimization, PSO) with Optimized BP Neural Network.PSO
It is a kind of new evolution algorithm developed in recent years, is the quality that solution is evaluated by fitness, has and realize easy, essence
The advantages that degree is high, convergence is fast, the BP neural network abbreviation PSO-BP neutral nets of PSO optimizations, PSO-BP neutral nets error is more
Small, accuracy higher.
Experimental data is realized into digital intellectualization using PSO Optimized BP Neural Networks, can be " from complicated and changeable at any time
Hexagonal sheet magnesium hydroxide is produced in bittern " problem solving is carried out, after experimental data intelligence, six sides can be produced for bittern at any time
Flake magnesium hydroxide provides optimal experimental program and Accurate Prediction experimental result, without expending substantial amounts of manpower and materials.
Preferably, the preparation parameter include bittern magnesium ion concentration, bittern volume, the concentration of NaOH, the volume of NaOH,
Reaction temperature and reaction time.
Preferably, the experimental result includes hexagonal sheet magnesium hydroxide ratio.
Preferably, the physicochemical property includes the magnesium ion concentration of bittern in salt lake, further include the acid-base value of bittern, viscosity,
The routine physicochemical property such as density.
Preferably, the algorithm flow of the BP neural network of the PSO optimizations is:Determine network topology structure, then initially
Then BP neural network weight threshold length obtains optimal power threshold value, then calculation error, then weight threshold updates, if
Meet termination condition, if then simulation and prediction is obtained as a result, termination condition is unsatisfactory for, back to calculation error, until meeting
Termination condition, final simulation and prediction obtain result;The acquisition best initial weights threshold value is obtained using cluster ion algorithm, the ion
The flow of group's algorithm is that ion and speed initialization, then particle fitness value calculation, then looks for individual extreme value and group pole
It is worth, then speed update and location updating, then ion fitness value calculation, then individual extreme value and group's extreme value, if full
Sufficient condition then obtains optimal power threshold value, if being unsatisfactory for condition, back to speed update and location updating, until meeting item
Part obtains best initial weights threshold value.
The data group number is more, and the prognostic experiment result of the BP neural network of PSO optimizations is more accurate.
BP neural network of the present invention for the first time by PSO optimizations is applied in the preparation method of hexagonal sheet magnesium hydroxide, because
The BP neural network of PSO optimizations answering in hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake is also claimed in this present invention
With.
Compared with prior art, the invention has the advantages that:
Experimental data is realized digital intellectualization by the present invention using PSO Optimized BP Neural Networks, can be produced at any time for bittern
Hexagonal sheet magnesium hydroxide provides optimal experimental program and Accurate Prediction experimental result, greatly reduces due to groping property is tested
Bring substantial amounts of human and material resources and the wasting of resources.
Description of the drawings
Fig. 1 is PSO Optimized BP Neural Network algorithm flow schematic diagrames.
Fig. 2 is the preparation parameter training PSO-BP neutral net signals that hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake
Figure.
Fig. 3 is the training process of PSO-BP neutral nets.
Specific embodiment
The present invention is made with reference to Figure of description and specific embodiment and further being elaborated, the embodiment
It is served only for explaining the present invention, is not intended to limit the scope of the present invention.Test method used in following embodiments is such as without spy
Different explanation, is conventional method;Used material, reagent etc., unless otherwise specified, for the reagent commercially obtained
And material.
(1) experiment problem solves explanation:
It is briefly described below by way of table 1.Table 1 gives 5 groups of experimental datas, wherein the I, the II, III group is the reality done
It tests and gives preparation parameter and experimental result, it is unknown that the IVth and V group, which has multiple parameters (or result), and unknown-value is equal
It is marked with question mark.After I, the II, III group of data is trained BP neural network, training data group is The more the better, and BP neural network is just
There is the artificial intelligence of " how to optimize the six side's shape magnesium hydroxide schemes that prepare and make the result optimal ", the IV, the V can be instructed
How group experiment should be done.For example, in the Vth group, it is known that bittern magnesium ion concentration be 3.2mol/L, volume 500.0mL,
The concentration of existing alkali is 2.0mol/L, it is assumed that prepare six side's shape magnesium hydroxides that ratio is 98%, may I ask other preparations
Parameter should be how manyAssume again after being tested by the parameter provided, as a result ratio only has 90%, what main cause isIt should
What kind of adjustment made to parameterAll these problems can all allow this intelligence " expert " of PSO-BP neutral nets to be answered.
Table 1PSO-BP Neural Networks Solution examples
(2) PSO-BP neural network algorithms flow in embodiment:As shown in Figure 1, the algorithm of the BP neural network of PSO optimizations
Flow is:It determines network topology structure, then initial BP neural network weight threshold length, then obtains optimal power threshold value, so
Calculation error afterwards, then weight threshold update, if meeting termination condition, if simulation and prediction is obtained as a result, being unsatisfactory for tying
Beam condition, then back to calculation error, until meeting termination condition, final simulation and prediction obtains result;Wherein obtain optimal power
Value threshold value is obtained using cluster ion algorithm, and the flow of the cluster ion algorithm is ion and speed initialization, and then particle adapts to
Angle value calculates, and then looks for individual extreme value and group's extreme value, then speed update and location updating, then ion fitness value meter
It calculates, then individual extreme value and group's extreme value, if meeting condition, obtain optimal power threshold value, if being unsatisfactory for condition, return
To speed update and location updating, until meeting condition, best initial weights threshold value is obtained.
(3) for hexagonal sheet magnesium hydroxide ratio using flying-spot microscope observation estimation, result is mass fraction in embodiment;
Confirm that the whisker being prepared is target product by XRD tests.
Embodiment
A kind of method that hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake, is included the following steps:
S1. hexagonal sheet magnesium hydroxide is prepared, and records data;
(1) Cha Er Han Salt Lake bittern 500mL is taken, filter and discards insoluble matter;Its magnesium ion concentration is measured as 2.46mol/
L;
(2) NaOH solution of 2.00mol/L is prepared;
(3) above-mentioned bittern solution 200mL is taken, is placed in the beaker of 1.00L, is then added dropwise to NaOH slowly under stirring
Solution 100mL, finishes, and mixed system is placed in the water-bath that water temperature is 110 DEG C and continues to be aged 30h;
(4) filter, while precipitation is washed with water and collects precipitation;(T=80 ± 3 DEG C, t=24h) drying is placed in baking oven,
Up to hexagonal sheet magnesium hydroxide, the hexagonal sheet magnesium hydroxide ratio in product that detects is 99%;
S2. the bittern magnesium ion concentration of change S1, bittern volume, the concentration of NaOH, the volume of NaOH, reaction temperature or anti-
One or more of between seasonable, hexagonal sheet magnesium hydroxide ratio is prepared, the above experiment of repetition 100 times obtains 100 groups of number
According to;
S3. PSO-BP neutral nets, training PSO-BP neutral nets and then by this 100 groups of data are inputted;
S4. when the magnesium ion concentration of bittern in salt lake changes, after inputting reaction condition data, PSO-BP neutral net energy
It enough predicts hexagonal sheet magnesium hydroxide ratio, most obtains taking an excellent data group at last, this group of data are exactly chemical technology
In it is optimal, in production afterwards Main Basiss this optimization data come enter produce, prepare hexagonal sheet magnesium hydroxide.
The data of PSO-BP neutral nets are trained in the present embodiment and the results are shown in Table 2, by hexagonal sheet magnesium hydroxide
The height digital representation of ratio represents that trained purpose is exactly to make reality output with number 1,2,3,4,5 respectively from low to high
Be worth it is infinite close to desired output (desired output be exactly actually test result), once achieve the goal, training knot
Beam.Desired output and real output value in contrast table 2, it is seen that the two is sufficiently close to, error very little.5 groups of numbers are only enumerated in table
According to other training datas are not shown in the table.
After completing training PSO-BP neutral nets, when the magnesium ion concentration of bittern in salt lake changes, input reaction
After condition data, PSO-BP neutral nets can predict hexagonal sheet magnesium hydroxide ratio, most obtain taking an excellent number at last
According to group, i.e., optimal preparation parameter is produced according to the preparation parameter, prepares hexagonal sheet magnesium hydroxide, can be subtracted significantly
It is few that substantial amounts of human and material resources and the wasting of resources are brought due to groping property is tested.
Table 2PSO-BP neural network predictions are trained
Obviously, the above embodiment of the present invention is only intended to clearly illustrate example of the present invention, and is not pair
The restriction of embodiments of the present invention.For those of ordinary skill in the art, may be used also on the basis of the above description
To make other variations or changes in different ways.There is no necessity and possibility to exhaust all the enbodiments.It is all this
All any modification, equivalent and improvement made within the spirit and principle of invention etc., should be included in the claims in the present invention
Protection domain within.
Claims (5)
- A kind of 1. method that hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake, which is characterized in that include the following steps:S1. the BP multigroup experimental data that hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake optimized for training through PSO Neutral net, the experimental data include preparation parameter and experimental result, and the group number of experimental data is more than or equal to 100 groups;The mathematical model of the PSO is:vij(t+1)=vij(t)+c1r1j(t)[pij(t)-xij(t)]+c2r2j(t)[gj(t)-xij(t)] (1)xij(t+1)=xij(t)+vij(t+1) (2)In formula (1) and formula (2), j is that the jth of particle is tieed up, and i is i-th of particle;t:Represent current evolutionary generation;vij(t) hidden layer I-th of node is to the weights between j-th of node;pij(t) particle i passes through the position of j;gij(t) population i passes through j Position;xij(t) current particle i is in the position of j;c1And c2All it is the restriction factor of change in displacement, is preset value;R is random Function;The PSO Optimized BP Neural Networks are that the J values in formula (3) are minimum, and J is mean square deviation index;<mrow> <mi>J</mi> <mo>=</mo> <mfrac> <mn>1</mn> <mi>N</mi> </mfrac> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>N</mi> </munderover> <munderover> <mo>&Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>M</mi> </munderover> <msup> <mrow> <mo>(</mo> <msubsup> <mi>y</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>i</mi> </mrow> <mi>d</mi> </msubsup> <mo>-</mo> <msub> <mi>y</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>i</mi> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>3</mn> <mo>)</mo> </mrow> </mrow>In formula (3), N is training sample sum, and M is the number of neuron,It is the mesh of j-th of neurode of i-th of sample Mark output valve, yj,iIt is the real output value of j-th of neurode of i-th of sample;S2. the BP neural network through PSO optimizations after gained training can be provided with the physical and chemical properties change of bittern in salt lake The preparation parameter of optimization, prediction hexagonal sheet magnesium hydroxide ratio;Using the preparation parameter of optimization, hexagonal flake hydrogen is prepared Magnesia.
- 2. according to the method described in claim 1, it is characterized in that, the preparation parameter includes bittern magnesium ion concentration, bittern Volume, the concentration of NaOH, the volume of NaOH, reaction temperature and reaction time.
- 3. according to the method described in claim 1, it is characterized in that, the experimental result includes hexagonal sheet magnesium hydroxide ratio Rate.
- 4. according to the method described in claim 1, it is characterized in that, magnesium ion of the physicochemical property including bittern in salt lake is dense Degree.
- Application of the BP neural network of 5.PSO optimizations in hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711423361.7A CN108059177A (en) | 2017-12-25 | 2017-12-25 | A kind of method that hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711423361.7A CN108059177A (en) | 2017-12-25 | 2017-12-25 | A kind of method that hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108059177A true CN108059177A (en) | 2018-05-22 |
Family
ID=62140123
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711423361.7A Withdrawn CN108059177A (en) | 2017-12-25 | 2017-12-25 | A kind of method that hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108059177A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113779887A (en) * | 2021-09-22 | 2021-12-10 | 上海上实龙创智能科技股份有限公司 | MF impregnating adhesive production process parameter optimization control method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020184569A1 (en) * | 2001-04-25 | 2002-12-05 | O'neill Michael | System and method for using neural nets for analyzing micro-arrays |
CN101172627A (en) * | 2007-10-11 | 2008-05-07 | 河北科技大学 | Method of producing magnesium hydroxide |
CN101177289A (en) * | 2007-11-05 | 2008-05-14 | 昆明理工大学 | Method for preparing fibrous nano magnesium hydrate |
CN104463343A (en) * | 2014-10-27 | 2015-03-25 | 中国石油大学(北京) | Method for predicting catalytic cracking light oil yield |
-
2017
- 2017-12-25 CN CN201711423361.7A patent/CN108059177A/en not_active Withdrawn
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020184569A1 (en) * | 2001-04-25 | 2002-12-05 | O'neill Michael | System and method for using neural nets for analyzing micro-arrays |
CN101172627A (en) * | 2007-10-11 | 2008-05-07 | 河北科技大学 | Method of producing magnesium hydroxide |
CN101177289A (en) * | 2007-11-05 | 2008-05-14 | 昆明理工大学 | Method for preparing fibrous nano magnesium hydrate |
CN104463343A (en) * | 2014-10-27 | 2015-03-25 | 中国石油大学(北京) | Method for predicting catalytic cracking light oil yield |
Non-Patent Citations (2)
Title |
---|
刘卫林,刘丽娜: "《基于智能计算技术的水资源配置系统预测》", 1 December 2015, 中国水利水电出版社 * |
吴健松 等: "徐闻盐场苦卤制备阻燃型氢氧化镁", 《无机盐工业》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113779887A (en) * | 2021-09-22 | 2021-12-10 | 上海上实龙创智能科技股份有限公司 | MF impregnating adhesive production process parameter optimization control method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108090658A (en) | Arc fault diagnostic method based on time domain charactreristic parameter fusion | |
CN109492287A (en) | A kind of solid electrolyte ionic conductivity prediction technique based on BP neural network | |
CN103971160B (en) | particle swarm optimization method based on complex network | |
CN109444832A (en) | Colony intelligence interfering well cluster method based on more jamming effectiveness values | |
CN109143872A (en) | A kind of continuous stirred tank reactor course control method for use based on event triggering GDHP | |
CN109376921A (en) | Based on hereditary artificial fish school optimization RBF neural short-term load forecasting method | |
CN109214503A (en) | Project of transmitting and converting electricity cost forecasting method based on KPCA-LA-RBM | |
CN108983177A (en) | A kind of radar sea clutter forecast system that parameter is optimal and method | |
CN108059177A (en) | A kind of method that hexagonal sheet magnesium hydroxide is prepared using bittern in salt lake | |
CN108460462A (en) | A kind of Interval neural networks learning method based on interval parameter optimization | |
CN108594793A (en) | A kind of improved RBF flight control systems fault diagnosis network training method | |
CN116318754A (en) | Multi-terminal collaborative dynamic security analysis method and system for distributed power supply | |
CN101893852B (en) | Multi-target modeling method for complex industrial process | |
CN108830035A (en) | A kind of novel water process coagulant dosage control method, computer, computer program | |
CN115310348A (en) | Stacking-based grouting amount integrated agent prediction model and prediction method | |
CN109726857A (en) | Cyanobacterial bloom prediction technique based on GA-Elman network | |
Ma et al. | Slope stability analysis based on leader dolphins herd algorithm and simplified Bishop method | |
CN103473599A (en) | Genetic algorithm and Kalman filtering based RBFN (Radial Basis Function Networks) combined training method | |
CN108073788A (en) | A kind of method that alkali formula magnesium borate crystal whisker is prepared using bittern in salt lake | |
Zhang et al. | The Markov model of bean optimization algorithm and its convergence analysis | |
CN108118396A (en) | A kind of method that alkali magnesium sulfate crystal whisker is prepared using bittern in salt lake | |
CN106126897A (en) | Multiple target transport path optimization method based on HIV Infectious Dynamics | |
He et al. | Greenhouse air temperature and humidity prediction based on improved BP neural network and genetic algorithm | |
Wang et al. | Rainfall-runoff simulation using simulated annealing wavelet bp neural networks | |
CN115618611A (en) | Method for establishing spatial multi-scale gradient lifting tree model and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180522 |