CN116825215B - Fluid circulation reaction control system and method for lithium hexafluorophosphate preparation - Google Patents
Fluid circulation reaction control system and method for lithium hexafluorophosphate preparation Download PDFInfo
- Publication number
- CN116825215B CN116825215B CN202310178520.0A CN202310178520A CN116825215B CN 116825215 B CN116825215 B CN 116825215B CN 202310178520 A CN202310178520 A CN 202310178520A CN 116825215 B CN116825215 B CN 116825215B
- Authority
- CN
- China
- Prior art keywords
- flow velocity
- vector
- time sequence
- feature vector
- liquid flow
- 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.)
- Active
Links
- -1 lithium hexafluorophosphate Chemical compound 0.000 title claims abstract description 74
- 238000006243 chemical reaction Methods 0.000 title claims abstract description 67
- 238000002360 preparation method Methods 0.000 title claims abstract description 61
- 239000012530 fluid Substances 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000013598 vector Substances 0.000 claims description 440
- 239000007789 gas Substances 0.000 claims description 191
- 239000007788 liquid Substances 0.000 claims description 176
- 239000011159 matrix material Substances 0.000 claims description 50
- 238000009826 distribution Methods 0.000 claims description 34
- 230000004927 fusion Effects 0.000 claims description 25
- 230000004044 response Effects 0.000 claims description 24
- 238000005457 optimization Methods 0.000 claims description 15
- 230000003247 decreasing effect Effects 0.000 claims description 12
- 230000004043 responsiveness Effects 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 239000000463 material Substances 0.000 abstract description 12
- PQXKHYXIUOZZFA-UHFFFAOYSA-M lithium fluoride Chemical compound [Li+].[F-] PQXKHYXIUOZZFA-UHFFFAOYSA-M 0.000 description 58
- 230000008859 change Effects 0.000 description 13
- 238000013135 deep learning Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 11
- 238000003860 storage Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 9
- 238000000889 atomisation Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 5
- 230000002195 synergetic effect Effects 0.000 description 5
- 238000003786 synthesis reaction Methods 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000001788 irregular Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- OBCUTHMOOONNBS-UHFFFAOYSA-N phosphorus pentafluoride Chemical compound FP(F)(F)(F)F OBCUTHMOOONNBS-UHFFFAOYSA-N 0.000 description 3
- 239000002904 solvent Substances 0.000 description 3
- KRHYYFGTRYWZRS-UHFFFAOYSA-N Fluorane Chemical compound F KRHYYFGTRYWZRS-UHFFFAOYSA-N 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 229910000040 hydrogen fluoride Inorganic materials 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 229910013870 LiPF 6 Inorganic materials 0.000 description 1
- 101150058243 Lipf gene Proteins 0.000 description 1
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000002425 crystallisation Methods 0.000 description 1
- 230000008025 crystallization Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000011049 filling Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000007791 liquid phase Substances 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000012452 mother liquor Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000012071 phase Substances 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- C—CHEMISTRY; METALLURGY
- C01—INORGANIC CHEMISTRY
- C01D—COMPOUNDS OF ALKALI METALS, i.e. LITHIUM, SODIUM, POTASSIUM, RUBIDIUM, CAESIUM, OR FRANCIUM
- C01D15/00—Lithium compounds
- C01D15/005—Lithium hexafluorophosphate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/10—Analysis or design of chemical reactions, syntheses or processes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Materials Engineering (AREA)
- General Physics & Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Organic Chemistry (AREA)
- Computing Systems (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Crystallography & Structural Chemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Inorganic Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Feedback Control In General (AREA)
Abstract
The application relates to the field of intelligent preparation of lithium hexafluorophosphate, and particularly discloses a fluid circulation reaction control system and a method for preparing lithium hexafluorophosphate. In this way, the flow rate value of the LiF-HF solution is controlled in real time and adaptively based on the cooperative correlation between the flow rate value of the LiF-HF solution and the inflow flow rate value of the PF 5 gas, so that the LiF-HF solution and the PF 5 gas react more fully, and the lithium hexafluorophosphate preparation efficiency and the material utilization rate are improved.
Description
Technical Field
The application relates to the field of intelligent preparation of lithium hexafluorophosphate, and in particular relates to a fluid circulation reaction control system and a method for preparing lithium hexafluorophosphate.
Background
Lithium hexafluorophosphate (LiPF 6) is a key raw material of lithium ion battery electrolyte, and is a preferred raw material of a high-performance battery due to a plurality of excellent characteristics, and is widely applied to the fields of 3C, power batteries, energy storage and the like.
The most widely-used industrial preparation method of lithium hexafluorophosphate at present is a solvent method. The existing solvent method is to dissolve lithium fluoride in anhydrous hydrogen fluoride to form LiF-HF solution, introduce high-purity phosphorus pentafluoride gas for reaction, and obtain lithium hexafluorophosphate products through the procedures of low-temperature crystallization, solid-liquid separation, drying and the like of mother liquor. Although the solvent method produces a high-purity product with low cost, the synthesis reaction PF 5 (gas) +lif (liquid dissolved in anhydrous hydrogen fluoride) →lipf 6 belongs to a multiphase reaction, and the reaction efficiency is affected by the mass transfer rate and the reaction rate of phosphorus pentafluoride in the gas phase, the gas-liquid interface and the liquid phase, so that the reaction efficiency and the material utilization rate are limited, the reaction between PF 5 and LiF in unit time is too slow, part of LiF is not fully reacted, and unreacted LiF is entrained into the product, so that the purity of lithium hexafluorophosphate is affected.
The liquid circulation atomization synthesis technology provides a method for solving the technical problems, which atomizes LiF and HF solution through an atomization nozzle to form very small liquid drops similar to gas; meanwhile, liF and HF solution is always in a high-speed flowing state, the contact reaction surface between the LiF and PF 5 (gas) is enlarged, the phenomenon of reaction dead zone is avoided, and the reaction is more complete in a full flow field state. In the actual process of preparing lithium hexafluorophosphate by adopting the liquid circulation atomization synthesis technology, the abrasion and faults of an atomization nozzle or the change of the supply quantity of LiF and HF solution can cause the change of the flow rate of the LiF and HF solution passing through the atomization nozzle, so that the flowing state of the LiF and HF solution is also changed, and meanwhile, the flowing flow rate value of the PF 5 gas is also changed along with the change of the performance of gas flowing equipment and the supply quantity of gas, namely, the synergism of the LiF and HF solution and the PF 5 gas in the process of preparing lithium hexafluorophosphate is ignored in the actual process, thereby reducing the reaction filling degree of the LiF and HF solution and PF 5 gas and reducing the preparation efficiency and the material utilization rate of lithium hexafluorophosphate.
Thus, an optimized fluid circulation reaction control scheme for lithium hexafluorophosphate production is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides a fluid circulation reaction control system and a method for preparing lithium hexafluorophosphate, which adopt an artificial intelligent detection technology based on deep learning to excavate time sequence high-dimensional implicit correlation characteristic distribution of flow velocity values of LiF and HF solution and flow velocity values of PF 5 gas through a time sequence encoder, and establish cooperative correlation between the two to carry out classification treatment. In this way, the flow rate value of the LiF-HF solution is controlled in real time and adaptively based on the cooperative correlation between the flow rate value of the LiF-HF solution and the inflow flow rate value of the PF 5 gas, so that the LiF-HF solution and the PF 5 gas react more fully, and the lithium hexafluorophosphate preparation efficiency and the material utilization rate are improved.
Accordingly, in accordance with one aspect of the present application, there is provided a fluid circulation reaction control system for lithium hexafluorophosphate preparation, comprising: the sensor data receiving module is used for obtaining flow velocity values of LiF and HF solutions at a plurality of preset time points in a preset time period and the inlet flow velocity values of PF 5 gas at the preset time points; the sensor data structuring module is used for respectively arranging the flow velocity values of LiF and HF solutions at a plurality of preset time points and the inlet flow velocity values of PF 5 gases at a plurality of preset time points into a liquid flow velocity input vector and a gas flow velocity input vector according to a time dimension; the flow velocity time sequence feature extraction module is used for respectively inputting the liquid flow velocity input vector and the gas flow velocity input vector into a time sequence encoder comprising a full-connection layer and a one-dimensional convolution layer to obtain a liquid flow velocity time sequence feature vector and a gas flow velocity time sequence feature vector; the Gaussian correlation module is used for fusing the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector by using a Gaussian density chart to obtain a cooperative feature matrix; the query module is used for taking the liquid flow velocity time sequence feature vector as a query feature vector, and calculating the product between the liquid flow velocity time sequence feature vector and the cooperative feature matrix to obtain a classification feature vector; the responsiveness optimization module is used for carrying out characteristic response optimization on the classification characteristic vector based on the liquid flow velocity time sequence characteristic vector so as to obtain an optimized classification characteristic vector; and the control result generation module is used for enabling the optimized classification feature vector to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating that the flow velocity value of LiF-HF solution at the current time point is increased or decreased.
In the above-mentioned fluid circulation reaction control system for lithium hexafluorophosphate preparation, the flow rate time sequence feature extraction module comprises: the full-connection coding unit is used for respectively carrying out full-connection coding on the liquid flow velocity input vector and the gas flow velocity input vector by using the full-connection layer of the time sequence coder according to the following formula to respectively extract high-dimensional implicit characteristics of characteristic values of all positions in the liquid flow velocity input vector and the gas flow velocity input vector, wherein the formula is as follows: Wherein/> is the liquid flow rate input vector or the gas flow rate input vector,/> is the output vector,/> is the weight matrix,/> is the bias vector,/> represents the matrix multiplication; and a one-dimensional convolution encoding unit, configured to perform one-dimensional convolution encoding on the liquid flow velocity input vector and the gas flow velocity input vector by using a one-dimensional convolution layer of the timing encoder to extract high-dimensional implicit correlation features between feature values of each position in the liquid flow velocity input vector and the gas flow velocity input vector, where the formula is:
Where a is the width of the convolution kernel in the x direction, is the vector of the convolution kernel parameters,/> is the local vector matrix calculated with the convolution kernel function, w is the size of the convolution kernel,/> represents the liquid flow rate input vector or the gas flow rate input vector, and/> represents one-dimensional convolution encoding of the liquid flow rate input vector or the gas flow rate input vector.
In the above fluid circulation reaction control system for lithium hexafluorophosphate preparation, the gaussian correlation module comprises: the Gaussian fusion unit is used for calculating a fusion Gaussian density chart between the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector, wherein the mean value vector of the fusion Gaussian density chart is a per-position mean value vector between the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector, and the covariance matrix of the fusion Gaussian density chart is a variance between feature values of corresponding two positions in the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector; and the Gaussian discretization unit is used for carrying out Gaussian discretization on the Gaussian distribution of each position in the fused Gaussian density map so as to obtain the collaborative feature matrix.
In the above fluid circulation reaction control system for lithium hexafluorophosphate preparation, the gaussian fusion unit is further configured to: calculating a fused gaussian density map between the liquid flow velocity time series feature vector and the gas flow velocity time series feature vector in the following formula; wherein, the formula is: ,
Wherein represents a per-position mean vector between the liquid flow velocity timing feature vector and the gas flow velocity timing feature vector, and the value per position/> represents the variance between the feature values for each position in the liquid flow velocity timing feature vector and the gas flow velocity timing feature vector,/> represents the fused gaussian density map.
In the above fluid circulation reaction control system for lithium hexafluorophosphate preparation, the responsiveness optimization module is further configured to calculate, based on the classification feature vector and the liquid flow velocity timing feature vector, incoherent sparse response fusion features of the classification feature vector and the liquid flow velocity timing feature vector according to the following formula to optimize the classification feature vector to obtain the optimized classification feature vector; wherein, the formula is:
Wherein represents the classification feature vector,/> represents the liquid flow velocity timing feature vector,/> and represent the first and second norms of the vector,/> is the length of the vector,/> and/> represent the vector product and vector dot product, respectively, and all vectors are in the form of row vectors,/> represents the optimized classification feature vector.
In the above-mentioned fluid circulation reaction control system for lithium hexafluorophosphate preparation, the control result generation module comprises: the probability unit is used for inputting the optimized classification feature vector into a Softmax classification function of the classifier to obtain a probability value of the optimized classification feature vector belonging to each classification label; and the classification result generation unit is used for determining the classification label corresponding to the maximum probability value as the classification result.
According to another aspect of the present application, there is also provided a fluid circulation reaction control method for lithium hexafluorophosphate preparation, comprising: acquiring flow velocity values of LiF and HF solutions at a plurality of preset time points in a preset time period and flow velocity values of PF 5 gas flowing in at the preset time points; arranging the flow velocity values of LiF and HF solutions at a plurality of preset time points and the inflow flow velocity values of PF 5 gas at a plurality of preset time points into a liquid flow velocity input vector and a gas flow velocity input vector according to a time dimension respectively; respectively inputting the liquid flow velocity input vector and the gas flow velocity input vector into a time sequence encoder comprising a full-connection layer and a one-dimensional convolution layer to obtain a liquid flow velocity time sequence characteristic vector and a gas flow velocity time sequence characteristic vector; fusing the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector by using a Gaussian density chart to obtain a cooperative feature matrix; taking the liquid flow velocity time sequence feature vector as a query feature vector, and calculating the product between the query feature vector and the cooperative feature matrix to obtain a classification feature vector; based on the liquid flow velocity time sequence feature vector, carrying out feature response optimization on the classification feature vector to obtain an optimized classification feature vector; and passing the optimized classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for representing that the flow rate value of LiF-HF solution at the current time point is increased or decreased.
According to still another aspect of the present application, there is provided an electronic apparatus including: a processor; and a memory having stored therein computer program instructions that, when executed by the processor, cause the processor to perform the fluid circulation reaction control method for lithium hexafluorophosphate preparation as described above.
According to yet another aspect of the present application, there is provided a computer readable medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the fluid circulation reaction control method for lithium hexafluorophosphate preparation as described above.
Compared with the prior art, the fluid circulation reaction control system and the method for preparing lithium hexafluorophosphate, provided by the application, adopt an artificial intelligent detection technology based on deep learning to excavate the time sequence high-dimensional implicit association characteristic distribution of the flow velocity value of LiF/HF solution and the flow velocity value of the inlet flow velocity value of PF 5 gas through a time sequence encoder, and establish cooperative association between the two to carry out classification treatment. In this way, the flow rate value of the LiF-HF solution is controlled in real time and adaptively based on the cooperative correlation between the flow rate value of the LiF-HF solution and the inflow flow rate value of the PF 5 gas, so that the LiF-HF solution and the PF 5 gas react more fully, and the lithium hexafluorophosphate preparation efficiency and the material utilization rate are improved.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is an application scenario diagram of a fluid circulation reaction control system for lithium hexafluorophosphate preparation according to an embodiment of the present application.
Fig. 2 is a block diagram of a fluid circulation reaction control system for lithium hexafluorophosphate preparation according to an embodiment of the present application.
Fig. 3 is a schematic diagram of the architecture of a fluid circulation reaction control system for lithium hexafluorophosphate preparation according to an embodiment of the present application.
Fig. 4 is a flow chart of a fluid circulation reaction control method for lithium hexafluorophosphate preparation according to an embodiment of the present application.
Fig. 5 is a block diagram of an electronic device according to an embodiment of the application.
Detailed Description
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Summary of the application: accordingly, in order to reduce the influence of insufficient reaction caused by the change of the flow rate of the LiF-HF solution and the change of the inlet rate of the PF 5 gas in the actual preparation process of the lithium hexafluorophosphate, the flow rate of the LiF-HF solution can be controlled in real time and adaptively based on the cooperative correlation between the flow rate of the LiF-HF solution and the inlet flow rate of the PF 5 gas, so that the LiF-HF solution and the PF 5 gas react more fully, and the preparation efficiency and the material utilization rate of the lithium hexafluorophosphate are improved. However, since the flow rate of LiF-HF solution and the gas inlet rate of PF 5 have a hidden association relationship in the time dimension, it is difficult to capture the variation pattern of the flow rate of LiF-HF solution and the gas inlet rate of PF 5 deeply, that is, in this process, the difficulty is how to excavate the time sequence hidden association relationship of the flow rate of LiF-HF solution and the gas inlet rate of PF 5, and to establish a cooperative association between the two, so as to improve the adaptive degree of the adaptive control of the flow rate value of LiF-HF solution, thereby improving the reaction sufficiency of LiF-HF solution and the gas of PF 5, the preparation efficiency of lithium hexafluorophosphate and the material utilization rate.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. In addition, deep learning and neural networks have also shown levels approaching and even exceeding humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like.
The development of deep learning and neural networks provides a new solution for constructing a liquid circulation atomization synthesis control scheme for lithium hexafluorophosphate preparation.
Specifically, in the technical scheme of the application, firstly, the flow rate values of LiF & HF solution at a plurality of preset time points in a preset time period and the flow rate values of PF 5 gas flowing in at the preset time points are obtained. In one specific example of the present application, a flow rate sensor may be used to obtain the data described above.
And then, arranging the flow rate values of the LiF & HF solution at a plurality of preset time points and the inflow flow rate values of the PF 5 gas at a plurality of preset time points into a liquid flow rate input vector and a gas flow rate input vector according to a time dimension so as to integrate time sequence discrete distribution of the flow rate values of the LiF & HF solution and time sequence discrete distribution of the inflow flow rate values of the PF 5 gas, and constructing the structured liquid flow rate input vector and the structured gas flow rate input vector for reading and recognition by a computer.
Considering that the liquid flow velocity input vector and the gas flow velocity input vector respectively contain high-dimensional implicit correlation characteristics of flow velocity values of LiF & HF solution and flow velocity values of PF 5 gas in time sequence, in the technical scheme of the application, the liquid flow velocity input vector and the gas flow velocity input vector are respectively input into a time sequence encoder comprising a full-connection layer and a one-dimensional convolution layer to obtain a liquid flow velocity time sequence characteristic vector and a gas flow velocity time sequence characteristic vector. It should be understood that the one-dimensional convolution layer can extract local liquid flow rate and gas flow rate associated feature information and lack global context semantic information, the full connection layer can establish global associated information among all positions and lack the capability of extracting local features, and the combination of the two can mutually compensate the limitation of the data characteristics of respective models, so that feature extraction of flow rate values of LiF and HF solution and the flow rate values of the introduction of PF 5 gas is optimized.
And then, fusing the liquid flow velocity time sequence characteristic vector and the gas flow velocity time sequence characteristic vector by using a Gaussian density chart to express the synergy condition between the time sequence change characteristic of the flow velocity of LiF-HF solution and the time sequence change characteristic of the inlet flow velocity of PF 5 gas, thereby obtaining a synergy characteristic matrix.
In particular, in the technical solution of the present application, considering that the liquid flow velocity time series feature vector and the gas flow velocity time series feature vector correspond to one feature distribution manifold in a high-dimensional feature space, and these feature distribution manifolds are due to their irregular shapes and scattering positions, if a gas global feature representation is obtained by simply concatenating the liquid flow velocity time series feature vector and the gas flow velocity time series feature vector, it would be equivalent to simply superimposing these feature distribution manifolds in original positions and shapes, so that the boundaries of newly obtained feature distribution manifolds become very irregular and complex.
Based on this, the applicant of the present application has considered that gaussian density maps are widely used in deep learning for a priori based estimation of the objective posterior and can therefore be used to correct the data distribution, thus achieving the above objective. Specifically, in the technical scheme of the application, the liquid flow velocity time sequence characteristic vector and the gas flow velocity time sequence characteristic vector are fused based on a Gaussian density chart to obtain a collaborative representation between the liquid flow velocity and the gas flow velocity.
Specifically, firstly, constructing a fused Gaussian density map of the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector, wherein the mean vector of the fused Gaussian density map is a position-based mean vector between the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector, and the value of each position in a covariance matrix of the fused Gaussian density map is the variance between the characteristic values of the corresponding positions between the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector. Further, the gaussian distribution at each position in the fused gaussian density map is subjected to gaussian discretization to obtain a synergistic characteristic matrix for representing a synergistic representation between the liquid flow rate and the gas flow rate.
And then, taking the liquid flow velocity time sequence feature vector as a query feature vector, calculating the product between the query feature vector and the cooperative feature matrix to obtain a classification feature vector so as to map cooperative correlation feature information between the liquid flow velocity and the gas flow velocity expressed by the cooperative feature matrix into a liquid flow velocity time sequence feature domain expressed by the liquid flow velocity time sequence feature vector, and extracting time sequence dynamic change feature information about the flow velocity value of the LiF-HF solution, which takes the cooperative correlation feature information between the liquid flow velocity and the gas flow velocity as constraint, thereby obtaining the classification feature vector.
After the classification feature vector is obtained, it is passed through a classifier to obtain a classification result, and the flow rate value of the LiF-HF solution used for representing the current time point should be increased or decreased. That is, in the technical solution of the present application, the classification label of the classifier includes that the flow rate value of LiF-HF solution at the current time point should be increased (first label) and that the flow rate value of LiF-HF solution at the current time point should be decreased (second label), wherein the classifier determines to which classification label the classification feature vector belongs by a soft maximum function. It should be understood that the classification label of the classifier is a flow rate value control strategy label of LiF-HF solution, so after the classification result is obtained, the flow rate value of the LiF-HF solution can be adaptively adjusted based on the classification result, thereby achieving the purpose of improving the reaction sufficiency of the LiF-HF solution and the PF 5 gas, and further improving the lithium hexafluorophosphate preparation efficiency and the material utilization rate.
In particular, in the technical scheme of the application, when the liquid flow velocity time sequence feature vector is used as a query feature vector and the product between the query feature vector and the cooperative feature matrix is calculated to obtain a classification feature vector, the Gaussian density correlation feature of the time sequence distribution of the solution flow velocity value and the gas flow velocity value expressed by the cooperative feature matrix is mapped into the one-dimensional time sequence correlation feature space of the solution flow velocity value expressed by the liquid flow velocity time sequence feature vector. Therefore, the liquid flow velocity time series feature vector can be regarded as a source vector, and the classification feature vector can be regarded as a response feature vector of a source vector based on the feature domain of the correlation feature matrix of the solution flow velocity-gas flow velocity, and therefore, in this case, if the degree of feature fusion between feature vectors having a response relationship can be improved, it is apparent that the expression effect of the classification feature vector can be further improved.
Accordingly, the applicant of the present application further calculates its incoherent sparse response fusion features based on the classification feature vector and the liquid flow rate timing feature vector/> to optimize the classification feature vector/> , expressed as:
Where and/> represent the first and second norms of the vector,/> is the length of the vector,/> and/> represent vector product and vector dot product, respectively, and all vectors are in the form of row vectors.
Here, in the case where the incoherent sparse response is fused with the one-dimensional time-series correlation feature of the solution flow velocity value expressed by the liquid flow velocity time-series feature vector to be the authenticity distribution (group-truth distribution) of the feature inter-domain response, the incoherent sparse fusion representation between vectors is obtained by the ambiguity bit distribution responsiveness of the vector difference represented by a norm and the true difference embedding responsiveness based on the modulo constraint of the differential vector, so as to improve the probability distribution descriptive degree after the feature vectors with the response relationship are fused, thereby improving the fusion degree of the classification feature vector to the feature probability distribution of the liquid flow velocity time-series feature vector. In this way, the accuracy of the obtained classification result can be improved by passing the optimized classification feature vector/> through the classifier.
Fig. 1 is an application scenario diagram of a fluid circulation reaction control system for lithium hexafluorophosphate preparation according to an embodiment of the present application. As shown in fig. 1, in this application scenario, first, flow rate values of LiF-HF solution (e.g., L as illustrated in fig. 1) at a plurality of predetermined time points within a predetermined period and inflow flow rate values of PF 5 gas (e.g., G as illustrated in fig. 1) at the plurality of predetermined time points are acquired by a flow rate sensor (e.g., se as illustrated in fig. 1), respectively. Further, the flow rate values of LiF-HF solution at the plurality of predetermined time points and the flow rate value of PF 5 gas at the plurality of predetermined time points are input to a server (e.g., S as illustrated in fig. 1) in which a fluid circulation reaction control algorithm for lithium hexafluorophosphate production is deployed, wherein the server is capable of processing the flow rate values of LiF-HF solution at the plurality of predetermined time points and the flow rate value of PF 5 gas at the plurality of predetermined time points based on the fluid circulation reaction control algorithm for lithium hexafluorophosphate production to obtain a classification result indicating that the flow rate value of LiF-HF solution at the current time point should be increased or decreased.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Exemplary System: fig. 2 is a block diagram of a fluid circulation reaction control system for lithium hexafluorophosphate preparation according to an embodiment of the present application. As shown in fig. 2, a fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation according to an embodiment of the present application includes: a sensor data receiving module 110, configured to obtain flow rate values of LiF-HF solution at a plurality of predetermined time points in a predetermined time period and flow rate values of PF 5 gas flowing in at the plurality of predetermined time points; a sensor data structuring module 120, configured to arrange the flow rate values of LiF-HF solution at the plurality of predetermined time points and the inflow flow rate values of PF 5 gas at the plurality of predetermined time points into a liquid flow rate input vector and a gas flow rate input vector according to a time dimension, respectively; a flow velocity time sequence feature extraction module 130, configured to input the liquid flow velocity input vector and the gas flow velocity input vector into a time sequence encoder including a full-connection layer and a one-dimensional convolution layer respectively to obtain a liquid flow velocity time sequence feature vector and a gas flow velocity time sequence feature vector; a gaussian correlation module 140 for fusing the liquid flow velocity timing feature vector and the gas flow velocity timing feature vector using a gaussian density map to obtain a collaborative feature matrix; the query module 150 is configured to calculate a product between the liquid flow velocity time sequence feature vector and the collaborative feature matrix to obtain a classification feature vector by using the liquid flow velocity time sequence feature vector as a query feature vector; a responsiveness optimization module 160, configured to perform feature response optimization on the classification feature vector based on the liquid flow velocity time sequence feature vector to obtain an optimized classification feature vector; and a control result generating module 170, configured to pass the optimized classification feature vector through a classifier to obtain a classification result, where the classification result is used to indicate that the flow rate value of the LiF-HF solution at the current time point should be increased or decreased.
Fig. 3 is a schematic diagram of the architecture of a fluid circulation reaction control system for lithium hexafluorophosphate preparation according to an embodiment of the present application. As shown in fig. 3, first, flow velocity values of LiF-HF solution at a plurality of predetermined time points in a predetermined period of time and inflow flow velocity values of PF 5 gas at the plurality of predetermined time points are obtained; then, arranging the flow velocity values of the LiF & HF solution at the preset time points and the inflow flow velocity values of the PF 5 gas at the preset time points into a liquid flow velocity input vector and a gas flow velocity input vector according to the time dimension respectively; then, respectively inputting the liquid flow velocity input vector and the gas flow velocity input vector into a time sequence encoder comprising a full-connection layer and a one-dimensional convolution layer to obtain a liquid flow velocity time sequence characteristic vector and a gas flow velocity time sequence characteristic vector; then, fusing the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector by using a Gaussian density chart to obtain a cooperative feature matrix; then, taking the liquid flow velocity time sequence feature vector as a query feature vector, and calculating the product between the query feature vector and the cooperative feature matrix to obtain a classification feature vector; based on the liquid flow velocity time sequence feature vector, carrying out feature response optimization on the classification feature vector to obtain an optimized classification feature vector; finally, the optimized classification feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for representing that the flow velocity value of LiF & HF solution at the current time point is increased or decreased.
Accordingly, in order to reduce the influence of insufficient reaction caused by the change of the flow rate of the LiF-HF solution and the change of the inlet rate of the PF 5 gas in the actual preparation process of the lithium hexafluorophosphate, the flow rate of the LiF-HF solution can be controlled in real time and adaptively based on the cooperative correlation between the flow rate of the LiF-HF solution and the inlet flow rate of the PF 5 gas, so that the LiF-HF solution and the PF 5 gas react more fully, and the preparation efficiency and the material utilization rate of the lithium hexafluorophosphate are improved. However, since the flow rate of LiF-HF solution and the gas inlet rate of PF 5 have a hidden association relationship in the time dimension, it is difficult to capture the variation pattern of the flow rate of LiF-HF solution and the gas inlet rate of PF 5 deeply, that is, in this process, the difficulty is how to excavate the time sequence hidden association relationship of the flow rate of LiF-HF solution and the gas inlet rate of PF 5, and to establish a cooperative association between the two, so as to improve the adaptive degree of the adaptive control of the flow rate value of LiF-HF solution, thereby improving the reaction sufficiency of LiF-HF solution and the gas of PF 5, the preparation efficiency of lithium hexafluorophosphate and the material utilization rate.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. In addition, deep learning and neural networks have also shown levels approaching and even exceeding humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like.
The development of deep learning and neural networks provides a new solution for constructing a liquid circulation atomization synthesis control scheme for lithium hexafluorophosphate preparation.
In the above-mentioned fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation, the sensor data receiving module 110 is configured to obtain flow rate values of LiF-HF solution at a plurality of predetermined time points in a predetermined period of time and inflow flow rate values of PF5 gas at the plurality of predetermined time points. In one specific example of the present application, a flow rate sensor may be used to obtain the data described above.
In the above-mentioned fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation, the sensor data structuring module 120 is configured to arrange the flow rate values of LiF-HF solution at the plurality of predetermined time points and the inflow flow rate values of PF 5 gas at the plurality of predetermined time points into a liquid flow rate input vector and a gas flow rate input vector according to a time dimension, respectively. That is, the time-series discrete distribution of flow rate values of the LiF-HF solution and the time-series discrete distribution of flow rate values of the gas of PF 5 are integrated and structured as the structured liquid flow rate input vector and the gas flow rate input vector for computer reading and recognition.
In the above-mentioned fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation, the flow velocity time sequence feature extraction module 130 is configured to input the liquid flow velocity input vector and the gas flow velocity input vector into a time sequence encoder comprising a fully-connected layer and a one-dimensional convolution layer, respectively, so as to obtain a liquid flow velocity time sequence feature vector and a gas flow velocity time sequence feature vector. Considering that the liquid flow velocity input vector and the gas flow velocity input vector respectively contain high-dimensional implicit correlation characteristics of flow velocity values of LiF & HF solution and flow velocity values of PF 5 gas in time sequence, in the technical scheme of the application, the liquid flow velocity input vector and the gas flow velocity input vector are respectively input into a time sequence encoder comprising a full-connection layer and a one-dimensional convolution layer to obtain a liquid flow velocity time sequence characteristic vector and a gas flow velocity time sequence characteristic vector. It should be understood that the one-dimensional convolution layer can extract local liquid flow rate and gas flow rate associated feature information and lack global context semantic information, the full connection layer can establish global associated information among all positions and lack the capability of extracting local features, and the combination of the two can mutually compensate the limitation of the data characteristics of respective models, so that feature extraction of flow rate values of LiF and HF solution and the flow rate values of the introduction of PF 5 gas is optimized.
Specifically, in the embodiment of the present application, the flow rate timing feature extraction module 130 includes: the full-connection coding unit is used for respectively carrying out full-connection coding on the liquid flow velocity input vector and the gas flow velocity input vector by using the full-connection layer of the time sequence coder according to the following formula to respectively extract high-dimensional implicit characteristics of characteristic values of all positions in the liquid flow velocity input vector and the gas flow velocity input vector, wherein the formula is as follows: Wherein/> is the liquid flow rate input vector or the gas flow rate input vector,/> is the output vector,/> is the weight matrix, is the bias vector,/> represents the matrix multiplication; and a one-dimensional convolution encoding unit, configured to perform one-dimensional convolution encoding on the liquid flow velocity input vector and the gas flow velocity input vector by using a one-dimensional convolution layer of the timing encoder to extract high-dimensional implicit correlation features between feature values of each position in the liquid flow velocity input vector and the gas flow velocity input vector, where the formula is:
Where a is the width of the convolution kernel in the x direction, is the vector of the convolution kernel parameters,/> is the local vector matrix calculated with the convolution kernel function, w is the size of the convolution kernel,/> represents the liquid flow rate input vector or the gas flow rate input vector, and/> represents one-dimensional convolution encoding of the liquid flow rate input vector or the gas flow rate input vector.
In a specific example of the present application, the full-connection layer and the one-dimensional convolution layer in the timing encoder are in a parallel structure, the liquid flow velocity timing characteristic vector is obtained by fusing the output of the last layer of the full-connection layer and the output of the last layer of the one-dimensional convolution layer, and similarly, the gas flow velocity timing characteristic vector is obtained by fusing the output of the last layer of the full-connection layer and the output of the last layer of the one-dimensional convolution layer.
In the above-mentioned fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation, the gaussian correlation module 140 is configured to use a gaussian density chart to fuse the liquid flow velocity time series eigenvector and the gas flow velocity time series eigenvector to obtain a synergistic eigenvector. That is, the synergy between the time-series change characteristic of the flow rate of the LiF-HF solution and the time-series change characteristic of the flow rate of the PF 5 gas is expressed by the synergy characteristic matrix.
In particular, in the technical solution of the present application, considering that the liquid flow velocity time series feature vector and the gas flow velocity time series feature vector correspond to one feature distribution manifold in a high-dimensional feature space, and these feature distribution manifolds are due to their irregular shapes and scattering positions, if a gas global feature representation is obtained by simply concatenating the liquid flow velocity time series feature vector and the gas flow velocity time series feature vector, it would be equivalent to simply superimposing these feature distribution manifolds in original positions and shapes, so that the boundaries of newly obtained feature distribution manifolds become very irregular and complex.
Based on this, the applicant of the present application has considered that gaussian density maps are widely used in deep learning for a priori based estimation of the objective posterior and can therefore be used to correct the data distribution, thus achieving the above objective. Specifically, in the technical scheme of the application, the liquid flow velocity time sequence characteristic vector and the gas flow velocity time sequence characteristic vector are fused based on a Gaussian density chart to obtain a collaborative representation between the liquid flow velocity and the gas flow velocity.
Specifically, firstly, constructing a fused Gaussian density map of the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector, wherein the mean vector of the fused Gaussian density map is a position-based mean vector between the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector, and the value of each position in a covariance matrix of the fused Gaussian density map is the variance between the characteristic values of the corresponding positions between the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector. Further, the gaussian distribution at each position in the fused gaussian density map is subjected to gaussian discretization to obtain a synergistic characteristic matrix for representing a synergistic representation between the liquid flow rate and the gas flow rate.
Specifically, in the embodiment of the present application, the gaussian fusion unit is further configured to: calculating a fused gaussian density map between the liquid flow velocity time series feature vector and the gas flow velocity time series feature vector in the following formula; wherein, the formula is: Wherein/> represents a per-position mean vector between the liquid flow velocity timing feature vector and the gas flow velocity timing feature vector, and the value of each position/> represents the variance between the feature values of each position in the liquid flow velocity timing feature vector and the gas flow velocity timing feature vector,/> represents the fused gaussian density map.
In the above-mentioned fluid circulation reaction control system 100 for preparing lithium hexafluorophosphate, the query module 150 is configured to calculate a product between the liquid flow velocity time sequence feature vector and the collaborative feature matrix to obtain a classification feature vector by using the liquid flow velocity time sequence feature vector as a query feature vector. That is, the cooperative correlation characteristic information between the liquid flow rate and the gas flow rate expressed by the cooperative characteristic matrix is mapped into the liquid flow rate time sequence characteristic domain expressed by the liquid flow rate time sequence characteristic vector, so that the time sequence dynamic change characteristic information about the flow rate value of the LiF-HF solution taking the cooperative correlation characteristic information between the liquid flow rate and the gas flow rate as constraint is extracted, and the classification characteristic vector is obtained.
In the above-mentioned fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation, the responsiveness optimization module 160 is configured to perform feature response optimization on the classification feature vector based on the liquid flow velocity time sequence feature vector to obtain an optimized classification feature vector. In particular, in the technical scheme of the application, when the liquid flow velocity time sequence feature vector is used as a query feature vector and the product between the query feature vector and the cooperative feature matrix is calculated to obtain a classification feature vector, the Gaussian density correlation feature of the time sequence distribution of the solution flow velocity value and the gas flow velocity value expressed by the cooperative feature matrix is mapped into the one-dimensional time sequence correlation feature space of the solution flow velocity value expressed by the liquid flow velocity time sequence feature vector. Therefore, the liquid flow velocity time series feature vector can be regarded as a source vector, and the classification feature vector can be regarded as a response feature vector of a source vector based on the feature domain of the correlation feature matrix of the solution flow velocity-gas flow velocity, and therefore, in this case, if the degree of feature fusion between feature vectors having a response relationship can be improved, it is apparent that the expression effect of the classification feature vector can be further improved.
Accordingly, the applicant of the present application further calculates its incoherent sparse response fusion features based on the classification feature vector and the liquid flow rate timing feature vector/> to optimize the classification feature vector/> , expressed as:
wherein represents the classification feature vector,/> represents the liquid flow velocity timing feature vector,/> and represent the first and second norms of the vector,/> is the length of the vector,/> and/> represent the vector product and vector dot product, respectively, and all vectors are in the form of row vectors,/> represents the optimized classification feature vector.
Here, in the case where the incoherent sparse response is fused with the one-dimensional time-series correlation feature of the solution flow velocity value expressed by the liquid flow velocity time-series feature vector to be the authenticity distribution (group-truth distribution) of the feature inter-domain response, the incoherent sparse fusion representation between vectors is obtained by the ambiguity bit distribution responsiveness of the vector difference represented by a norm and the true difference embedding responsiveness based on the modulo constraint of the differential vector, so as to improve the probability distribution descriptive degree after the feature vectors with the response relationship are fused, thereby improving the fusion degree of the classification feature vector to the feature probability distribution of the liquid flow velocity time-series feature vector. In this way, the accuracy of the obtained classification result can be improved by passing the optimized classification feature vector/> through the classifier.
In the above-mentioned fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation, the control result generation module 170 is configured to pass the optimized classification feature vector through a classifier to obtain a classification result, where the classification result is used to indicate that the flow rate value of lif·hf solution at the current time point should be increased or decreased. That is, in the technical solution of the present application, the classification label of the classifier includes that the flow rate value of LiF-HF solution at the current time point should be increased (first label) and that the flow rate value of LiF-HF solution at the current time point should be decreased (second label), wherein the classifier determines to which classification label the classification feature vector belongs by a soft maximum function. It should be understood that the classification label of the classifier is a flow rate value control strategy label of LiF-HF solution, so after the classification result is obtained, the flow rate value of the LiF-HF solution can be adaptively adjusted based on the classification result, thereby achieving the purpose of improving the reaction sufficiency of the LiF-HF solution and the PF 5 gas, and further improving the lithium hexafluorophosphate preparation efficiency and the material utilization rate.
Specifically, in the embodiment of the present application, the encoding process of the control result generating module 170 includes: firstly, inputting the optimized classification feature vector into a Softmax classification function of the classifier through a probability unit to obtain a probability value of the optimized classification feature vector belonging to each classification label; then, a classification label corresponding to the maximum probability value is determined as the classification result by a classification result generation unit.
In summary, a fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation according to an embodiment of the present application is illustrated, which adopts an artificial intelligence detection technique based on deep learning to mine a time-series high-dimensional implicit correlation characteristic distribution of flow velocity values of LiF-HF solution and flow velocity values of PF 5 gas to be introduced through a time-series encoder, and establishes a cooperative correlation between the two to perform a classification process. In this way, the flow rate value of the LiF-HF solution is controlled in real time and adaptively based on the cooperative correlation between the flow rate value of the LiF-HF solution and the inflow flow rate value of the PF 5 gas, so that the LiF-HF solution and the PF 5 gas react more fully, and the lithium hexafluorophosphate preparation efficiency and the material utilization rate are improved.
As described above, the fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation according to the embodiment of the present application may be implemented in various terminal devices, such as a server or the like for fluid circulation reaction control for lithium hexafluorophosphate preparation. In one example, the fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation according to embodiments of the present application may be integrated into the terminal device as one software module and/or hardware module. For example, the fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation can also be one of the numerous hardware modules of the terminal device.
Alternatively, in another example, the fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation and the terminal device may be separate devices, and the fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation may be connected to the terminal device through a wired and/or wireless network and transmit interactive information according to an agreed data format.
An exemplary method is: fig. 4 is a flow chart of a fluid circulation reaction control method for lithium hexafluorophosphate preparation according to an embodiment of the present application. As shown in fig. 4, a fluid circulation reaction control method for lithium hexafluorophosphate preparation according to an embodiment of the present application includes: s110, obtaining flow velocity values of LiF and HF solutions at a plurality of preset time points in a preset time period and the inlet flow velocity values of PF 5 gas at the preset time points; s120, arranging the flow velocity values of LiF & HF solution at a plurality of preset time points and the inflow flow velocity values of PF 5 gas at a plurality of preset time points into a liquid flow velocity input vector and a gas flow velocity input vector according to a time dimension respectively; s130, respectively inputting the liquid flow velocity input vector and the gas flow velocity input vector into a time sequence encoder comprising a full-connection layer and a one-dimensional convolution layer to obtain a liquid flow velocity time sequence characteristic vector and a gas flow velocity time sequence characteristic vector; s140, fusing the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector by using a Gaussian density chart to obtain a cooperative feature matrix; s150, taking the liquid flow velocity time sequence feature vector as a query feature vector, and calculating the product between the query feature vector and the cooperative feature matrix to obtain a classification feature vector; s160, carrying out characteristic response optimization on the classification characteristic vector based on the liquid flow velocity time sequence characteristic vector so as to obtain an optimized classification characteristic vector; and S170, passing the optimized classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the flow rate value of LiF-HF solution at the current time point is increased or decreased.
Here, it will be understood by those skilled in the art that the respective steps and operations in the above-described fluid circulation reaction control method for lithium hexafluorophosphate preparation have been described in detail in the above description of the fluid circulation reaction control system 100 for lithium hexafluorophosphate preparation with reference to fig. 1 to 3, and thus, repetitive descriptions thereof will be omitted.
Exemplary electronic device: next, an electronic device according to an embodiment of the present application is described with reference to fig. 5. Fig. 5 is a block diagram of an electronic device according to an embodiment of the application. As shown in fig. 5, the electronic device 10 includes one or more processors 11 and a memory 12.
The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer readable storage medium that can be executed by the processor 11 to implement the functions in the fluid circulation reaction control method for lithium hexafluorophosphate preparation and/or other desired functions of the various embodiments of the present application described above. Various contents such as a flow rate value of LiF HF solution and an inflow flow rate value of PF 5 gas may also be stored in the computer-readable storage medium.
In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown).
The input means 13 may comprise, for example, a keyboard, a mouse, etc.
The output device 14 may output various information including the classification result and the like to the outside. The output means 14 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.
Of course, only some of the components of the electronic device 10 that are relevant to the present application are shown in fig. 5 for simplicity, components such as buses, input/output interfaces, etc. are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer readable storage Medium: in addition to the methods and apparatus described above, embodiments of the application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform steps in the functions of the fluid circulation reaction control method for lithium hexafluorophosphate preparation according to the various embodiments of the application described in the "exemplary methods" section of this specification.
The computer program product may write program code for performing operations of embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer-readable storage medium, having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform steps in the functions of the fluid circulation reaction control method for lithium hexafluorophosphate preparation according to the various embodiments of the present application described in the "exemplary methods" section of the present specification.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The basic principles of the present application have been described above in connection with specific embodiments, but it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not intended to be limiting, and these advantages, benefits, effects, etc. are not to be construed as necessarily possessed by the various embodiments of the application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not necessarily limited to practice with the above described specific details.
The block diagrams of the devices, apparatuses, devices, systems referred to in the present application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
Claims (3)
1. A fluid circulation reaction control system for lithium hexafluorophosphate preparation, comprising:
The sensor data receiving module is used for obtaining flow velocity values of LiF and HF solutions at a plurality of preset time points in a preset time period and the inlet flow velocity values of PF 5 gas at the preset time points;
The sensor data structuring module is used for respectively arranging the flow velocity values of LiF and HF solutions at a plurality of preset time points and the inlet flow velocity values of PF 5 gases at a plurality of preset time points into a liquid flow velocity input vector and a gas flow velocity input vector according to a time dimension;
The flow velocity time sequence feature extraction module is used for respectively inputting the liquid flow velocity input vector and the gas flow velocity input vector into a time sequence encoder comprising a full-connection layer and a one-dimensional convolution layer to obtain a liquid flow velocity time sequence feature vector and a gas flow velocity time sequence feature vector;
the Gaussian correlation module is used for fusing the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector by using a Gaussian density chart to obtain a cooperative feature matrix;
the query module is used for taking the liquid flow velocity time sequence feature vector as a query feature vector, and calculating the product between the liquid flow velocity time sequence feature vector and the cooperative feature matrix to obtain a classification feature vector;
The responsiveness optimization module is used for carrying out characteristic response optimization on the classification characteristic vector based on the liquid flow velocity time sequence characteristic vector so as to obtain an optimized classification characteristic vector; and
The control result generation module is used for enabling the optimized classification feature vector to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating that the flow velocity value of LiF-HF solution at the current time point should be increased or decreased;
Wherein, the flow velocity time sequence feature extraction module comprises:
The full-connection coding unit is used for respectively carrying out full-connection coding on the liquid flow velocity input vector and the gas flow velocity input vector by using the full-connection layer of the time sequence coder according to the following formula to respectively extract high-dimensional implicit characteristics of characteristic values of all positions in the liquid flow velocity input vector and the gas flow velocity input vector, wherein the formula is as follows: Wherein x is the liquid flow rate input vector or the gas flow rate input vector, Y is the output vector, W is the weight matrix, B is the bias vector,/> represents the matrix multiplication; and
The one-dimensional convolution coding unit is used for respectively carrying out one-dimensional convolution coding on the liquid flow velocity input vector and the gas flow velocity input vector by using a one-dimensional convolution layer of the time sequence coder so as to respectively extract high-dimensional implicit correlation features between feature values of each position in the liquid flow velocity input vector and the gas flow velocity input vector, wherein the formula is as follows:
Wherein a is the width of a convolution kernel in the X direction, F (a) is a convolution kernel parameter vector, G (X-a) is a local vector matrix calculated by a convolution kernel function, w is the size of the convolution kernel, X represents the liquid flow velocity input vector or the gas flow velocity input vector, and Cov (X) represents one-dimensional convolution encoding of the liquid flow velocity input vector or the gas flow velocity input vector;
Wherein, the Gaussian association module comprises:
The Gaussian fusion unit is used for calculating a fusion Gaussian density chart between the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector, wherein the mean value vector of the fusion Gaussian density chart is a per-position mean value vector between the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector, and the covariance matrix of the fusion Gaussian density chart is a variance between feature values of corresponding two positions in the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector; and
The Gaussian discretization unit is used for carrying out Gaussian discretization on the Gaussian distribution of each position in the fused Gaussian density map so as to obtain the collaborative feature matrix;
wherein, the Gaussian fusion unit is used for:
Calculating a fused gaussian density map between the liquid flow velocity time series feature vector and the gas flow velocity time series feature vector in the following formula;
Wherein, the formula is:
Wherein μ represents a per-position mean value vector between the liquid flow velocity timing feature vector and the gas flow velocity timing feature vector, and a value of each position of σ represents a variance between feature values of each position in the liquid flow velocity timing feature vector and the gas flow velocity timing feature vector, represents the fused gaussian density map;
Wherein, the responsiveness optimization module is used for: calculating incoherent sparse response fusion characteristics of the classification characteristic vector and the liquid flow velocity time sequence characteristic vector according to the following formula based on the classification characteristic vector and the liquid flow velocity time sequence characteristic vector so as to optimize the classification characteristic vector to obtain the optimized classification characteristic vector;
Wherein, the formula is:
Wherein V 1 represents the classification feature vector, V 2 represents the liquid flow rate timing feature vector, i i·i 1 and i·i 2 represent the first and second norms of the vector, L is the length of the vector, and i represent the vector product and vector dot product, respectively, and all vectors are in the form of line vectors, V 1' represents the optimized classification feature vector.
2. The fluid circulation reaction control system for lithium hexafluorophosphate preparation of claim 1, wherein the control result generation module comprises:
The probability unit is used for inputting the optimized classification feature vector into a Softmax classification function of the classifier to obtain a probability value of the optimized classification feature vector belonging to each classification label; and
And the classification result generation unit is used for determining the classification label corresponding to the maximum probability value as the classification result.
3. A fluid circulation reaction control method for lithium hexafluorophosphate preparation, comprising:
Acquiring flow velocity values of LiF and HF solutions at a plurality of preset time points in a preset time period and flow velocity values of PF 5 gas flowing in at the preset time points;
arranging the flow velocity values of LiF and HF solutions at a plurality of preset time points and the inflow flow velocity values of PF 5 gas at a plurality of preset time points into a liquid flow velocity input vector and a gas flow velocity input vector according to a time dimension respectively;
Respectively inputting the liquid flow velocity input vector and the gas flow velocity input vector into a time sequence encoder comprising a full-connection layer and a one-dimensional convolution layer to obtain a liquid flow velocity time sequence characteristic vector and a gas flow velocity time sequence characteristic vector;
Fusing the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector by using a Gaussian density chart to obtain a cooperative feature matrix;
taking the liquid flow velocity time sequence feature vector as a query feature vector, and calculating the product between the query feature vector and the cooperative feature matrix to obtain a classification feature vector;
based on the liquid flow velocity time sequence feature vector, carrying out feature response optimization on the classification feature vector to obtain an optimized classification feature vector; and
The optimized classification feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the flow velocity value of LiF-HF solution at the current time point should be increased or decreased;
the method for inputting the liquid flow velocity input vector and the gas flow velocity input vector into a time sequence encoder comprising a full-connection layer and a one-dimensional convolution layer respectively to obtain a liquid flow velocity time sequence characteristic vector and a gas flow velocity time sequence characteristic vector comprises the following steps:
And respectively performing full-connection coding on the liquid flow velocity input vector and the gas flow velocity input vector by using a full-connection layer of the time sequence coder to respectively extract high-dimensional implicit characteristics of characteristic values of all positions in the liquid flow velocity input vector and the gas flow velocity input vector, wherein the formula is as follows: Wherein X is the liquid flow rate input vector or the gas flow rate input vector, Y is the output vector, W is the weight matrix, B is the bias vector,/> represents the matrix multiplication; and
And respectively carrying out one-dimensional convolution coding on the liquid flow velocity input vector and the gas flow velocity input vector by using a one-dimensional convolution layer of the time sequence coder to respectively extract high-dimensional implicit correlation features between feature values of all positions in the liquid flow velocity input vector and the gas flow velocity input vector, wherein the formula is as follows:
Wherein a is the width of a convolution kernel in the X direction, F (a) is a convolution kernel parameter vector, G (X-a) is a local vector matrix calculated by a convolution kernel function, w is the size of the convolution kernel, X represents the liquid flow velocity input vector or the gas flow velocity input vector, and Cov (X) represents one-dimensional convolution encoding of the liquid flow velocity input vector or the gas flow velocity input vector;
wherein fusing the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector to obtain a cooperative feature matrix by using a Gaussian density chart comprises:
Calculating a fused Gaussian density map between the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector, wherein the mean vector of the fused Gaussian density map is a position-based mean vector between the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector, and the covariance matrix of the fused Gaussian density map is a variance between feature values of corresponding two positions in the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector; and
Performing Gaussian discretization on Gaussian distribution of each position in the fused Gaussian density map to obtain the collaborative feature matrix;
The method for calculating the fusion Gaussian density map between the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector, wherein the mean vector of the fusion Gaussian density map is a position-based mean vector between the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector, and the covariance matrix of the fusion Gaussian density map is a variance between feature values of corresponding two positions in the liquid flow velocity time sequence feature vector and the gas flow velocity time sequence feature vector, and the method comprises the following steps:
Calculating a fused gaussian density map between the liquid flow velocity time series feature vector and the gas flow velocity time series feature vector in the following formula;
Wherein, the formula is:
Wherein μ represents a per-position mean value vector between the liquid flow velocity timing feature vector and the gas flow velocity timing feature vector, and a value of each position of σ represents a variance between feature values of each position in the liquid flow velocity timing feature vector and the gas flow velocity timing feature vector, represents the fused gaussian density map;
Wherein, based on the liquid flow velocity time sequence feature vector, carrying out feature response optimization on the classification feature vector to obtain an optimized classification feature vector, comprising: calculating incoherent sparse response fusion characteristics of the classification characteristic vector and the liquid flow velocity time sequence characteristic vector according to the following formula based on the classification characteristic vector and the liquid flow velocity time sequence characteristic vector so as to optimize the classification characteristic vector to obtain the optimized classification characteristic vector;
Wherein, the formula is:
Wherein V 1 represents the classification feature vector, V 2 represents the liquid flow rate timing feature vector, i i·i 1 and i·i 2 represent the first and second norms of the vector, L is the length of the vector, and i represent the vector product and vector dot product, respectively, and all vectors are in the form of line vectors, V 1' represents the optimized classification feature vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310178520.0A CN116825215B (en) | 2023-02-28 | 2023-02-28 | Fluid circulation reaction control system and method for lithium hexafluorophosphate preparation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310178520.0A CN116825215B (en) | 2023-02-28 | 2023-02-28 | Fluid circulation reaction control system and method for lithium hexafluorophosphate preparation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116825215A CN116825215A (en) | 2023-09-29 |
| CN116825215B true CN116825215B (en) | 2024-04-16 |
Family
ID=88128182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310178520.0A Active CN116825215B (en) | 2023-02-28 | 2023-02-28 | Fluid circulation reaction control system and method for lithium hexafluorophosphate preparation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116825215B (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2239935A1 (en) * | 1997-06-06 | 1998-12-06 | Philippe Bonnet | Process for producing lithium hexafluorophosphate |
| FR2768426A1 (en) * | 1997-06-06 | 1999-03-19 | Atochem Elf Sa | New preparation of lithium hexa-fluoro-phosphate |
| CA2677304A1 (en) * | 2007-02-08 | 2008-08-14 | Stella Chemifa Corporation | Method of manufacturing phosphorous pentafluoride and hexafluorophosphate |
| CN102320588A (en) * | 2011-09-05 | 2012-01-18 | 贵州省化工研究院 | Lithium hexafluorophosphate synthesizer |
| CN202279694U (en) * | 2011-09-05 | 2012-06-20 | 贵州省化工研究院 | Lithium hexafluorophosphate synthesis device |
| RU2011146387A (en) * | 2011-11-15 | 2013-05-20 | Общество с ограниченной ответственностью "ПРОМСЕРВИС" | METHOD FOR PRODUCING LITHIUM HEXAFLUORPHOSPHATE AND INSTALLATION FOR ITS IMPLEMENTATION |
| CN110422891A (en) * | 2019-08-08 | 2019-11-08 | 中国科学院青海盐湖研究所 | A kind of method preparing nickel-cobalt-manganese ternary presoma, system and application |
| CN111439735A (en) * | 2020-03-31 | 2020-07-24 | 福建省龙德新能源股份有限公司 | Method for recycling phosphorus pentafluoride in lithium hexafluorophosphate synthesis tail gas by using amine and derivatives thereof |
| WO2021115316A1 (en) * | 2019-12-10 | 2021-06-17 | 中化蓝天集团有限公司 | Process and system for producing lipf6, and mixture crystal, composition, electrolyte solution and lithium battery containing lipf6 |
| CN113392278A (en) * | 2021-05-17 | 2021-09-14 | 杭州咏情科技有限公司 | Industrial internet-based equipment liquid pipeline flow detection method |
| CN114697272A (en) * | 2022-03-03 | 2022-07-01 | 安徽师范大学 | Traffic classification method, system and computer readable storage medium |
| CN115196654A (en) * | 2022-08-11 | 2022-10-18 | 胜华新能源科技(东营)有限公司 | Liquid lithium hexafluorophosphate synthesis device and application thereof |
| CN115314265A (en) * | 2022-07-27 | 2022-11-08 | 天津市国瑞数码安全系统股份有限公司 | Method and system for identifying TLS encryption application based on flow and time sequence |
| CN115309215A (en) * | 2022-08-05 | 2022-11-08 | 福建龙氟化工有限公司 | Automatic batching control system for preparing ammonium fluoride and control method thereof |
| CN115430344A (en) * | 2022-08-31 | 2022-12-06 | 福建省龙德新能源有限公司 | Automatic batching system for preparing lithium hexafluorophosphate and batching method thereof |
| CN115453990A (en) * | 2022-08-31 | 2022-12-09 | 福建天甫电子材料有限公司 | Production management control system for ammonium fluoride production and control method thereof |
| CN115586755A (en) * | 2022-10-28 | 2023-01-10 | 福建省龙德新能源有限公司 | Production management control system and method for preparing lithium hexafluorophosphate |
-
2023
- 2023-02-28 CN CN202310178520.0A patent/CN116825215B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2239935A1 (en) * | 1997-06-06 | 1998-12-06 | Philippe Bonnet | Process for producing lithium hexafluorophosphate |
| FR2768426A1 (en) * | 1997-06-06 | 1999-03-19 | Atochem Elf Sa | New preparation of lithium hexa-fluoro-phosphate |
| CA2677304A1 (en) * | 2007-02-08 | 2008-08-14 | Stella Chemifa Corporation | Method of manufacturing phosphorous pentafluoride and hexafluorophosphate |
| CN102320588A (en) * | 2011-09-05 | 2012-01-18 | 贵州省化工研究院 | Lithium hexafluorophosphate synthesizer |
| CN202279694U (en) * | 2011-09-05 | 2012-06-20 | 贵州省化工研究院 | Lithium hexafluorophosphate synthesis device |
| RU2011146387A (en) * | 2011-11-15 | 2013-05-20 | Общество с ограниченной ответственностью "ПРОМСЕРВИС" | METHOD FOR PRODUCING LITHIUM HEXAFLUORPHOSPHATE AND INSTALLATION FOR ITS IMPLEMENTATION |
| CN110422891A (en) * | 2019-08-08 | 2019-11-08 | 中国科学院青海盐湖研究所 | A kind of method preparing nickel-cobalt-manganese ternary presoma, system and application |
| WO2021115316A1 (en) * | 2019-12-10 | 2021-06-17 | 中化蓝天集团有限公司 | Process and system for producing lipf6, and mixture crystal, composition, electrolyte solution and lithium battery containing lipf6 |
| CN111439735A (en) * | 2020-03-31 | 2020-07-24 | 福建省龙德新能源股份有限公司 | Method for recycling phosphorus pentafluoride in lithium hexafluorophosphate synthesis tail gas by using amine and derivatives thereof |
| CN113392278A (en) * | 2021-05-17 | 2021-09-14 | 杭州咏情科技有限公司 | Industrial internet-based equipment liquid pipeline flow detection method |
| CN114697272A (en) * | 2022-03-03 | 2022-07-01 | 安徽师范大学 | Traffic classification method, system and computer readable storage medium |
| CN115314265A (en) * | 2022-07-27 | 2022-11-08 | 天津市国瑞数码安全系统股份有限公司 | Method and system for identifying TLS encryption application based on flow and time sequence |
| CN115309215A (en) * | 2022-08-05 | 2022-11-08 | 福建龙氟化工有限公司 | Automatic batching control system for preparing ammonium fluoride and control method thereof |
| CN115196654A (en) * | 2022-08-11 | 2022-10-18 | 胜华新能源科技(东营)有限公司 | Liquid lithium hexafluorophosphate synthesis device and application thereof |
| CN115430344A (en) * | 2022-08-31 | 2022-12-06 | 福建省龙德新能源有限公司 | Automatic batching system for preparing lithium hexafluorophosphate and batching method thereof |
| CN115453990A (en) * | 2022-08-31 | 2022-12-09 | 福建天甫电子材料有限公司 | Production management control system for ammonium fluoride production and control method thereof |
| CN115586755A (en) * | 2022-10-28 | 2023-01-10 | 福建省龙德新能源有限公司 | Production management control system and method for preparing lithium hexafluorophosphate |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116825215A (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115586755B (en) | Production management control system and method for lithium hexafluorophosphate preparation | |
| Lai et al. | Deep recurrent regression for facial landmark detection | |
| He et al. | Visual semantics allow for textual reasoning better in scene text recognition | |
| Zhang et al. | AdapNet: Adaptability decomposing encoder–decoder network for weakly supervised action recognition and localization | |
| Tu et al. | Spatial-temporal data augmentation based on LSTM autoencoder network for skeleton-based human action recognition | |
| CN116052050A (en) | Intelligent production system and method for detergent | |
| Jin et al. | Video-text as game players: Hierarchical banzhaf interaction for cross-modal representation learning | |
| CN115896817A (en) | Production method and system of fluorine-nitrogen mixed gas | |
| CN116149280B (en) | Intelligent production system of electronic-grade potassium hydroxide | |
| Zhang et al. | Improved locality preserving projections based on heat-kernel and cosine weights for fault classification in complex industrial processes | |
| Li et al. | One-class knowledge distillation for face presentation attack detection | |
| Sun et al. | Vicinity vision transformer | |
| CN116086133A (en) | Device and method for preparing high-purity oxygen by chemical chain air separation technology | |
| CN116308754A (en) | Bank credit risk early warning system and method thereof | |
| Xu et al. | UNTIE: Clustering analysis with disentanglement in multi-view information fusion | |
| CN116825215B (en) | Fluid circulation reaction control system and method for lithium hexafluorophosphate preparation | |
| Chen et al. | Knowledge-aware textual entailment with graph attention network | |
| Ou et al. | Cross-modal generation and pair correlation alignment hashing | |
| Bi et al. | HGR-Net: Hierarchical graph reasoning network for arbitrary shape scene text detection | |
| Zhang et al. | Feature selection method using BPSO-EA with ENN classifier | |
| CN116385733A (en) | High-precision positioning system and method for bucket wheel machine | |
| CN116127019A (en) | Dynamic parameter and visual model generation WEB 2D automatic modeling engine system | |
| Yuan et al. | Indirect point cloud registration: Aligning distance fields using a pseudo third point set | |
| Lopez et al. | GD-VAEs: Geometric dynamic variational autoencoders for learning nonlinear dynamics and dimension reductions | |
| CN116027874A (en) | Notebook computer power consumption control method and system thereof |
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 |