CN117101529B - Weighing type centrifugal batching method and batching device for fuel cell catalyst slurry - Google Patents
Weighing type centrifugal batching method and batching device for fuel cell catalyst slurry Download PDFInfo
- Publication number
- CN117101529B CN117101529B CN202311362678.XA CN202311362678A CN117101529B CN 117101529 B CN117101529 B CN 117101529B CN 202311362678 A CN202311362678 A CN 202311362678A CN 117101529 B CN117101529 B CN 117101529B
- Authority
- CN
- China
- Prior art keywords
- oxygen concentration
- stage
- slurry
- batching
- anaerobic
- 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
- 239000002002 slurry Substances 0.000 title claims abstract description 106
- 238000000034 method Methods 0.000 title claims abstract description 45
- 239000003054 catalyst Substances 0.000 title claims abstract description 40
- 239000000446 fuel Substances 0.000 title claims abstract description 31
- 238000005303 weighing Methods 0.000 title claims abstract description 22
- 239000001301 oxygen Substances 0.000 claims abstract description 229
- 229910052760 oxygen Inorganic materials 0.000 claims abstract description 229
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims abstract description 228
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims abstract description 71
- 239000002994 raw material Substances 0.000 claims abstract description 54
- 229910052757 nitrogen Inorganic materials 0.000 claims abstract description 36
- 239000004615 ingredient Substances 0.000 claims abstract description 17
- 238000001514 detection method Methods 0.000 claims abstract description 12
- 238000002156 mixing Methods 0.000 claims description 21
- 238000012360 testing method Methods 0.000 claims description 12
- 229910052751 metal Inorganic materials 0.000 claims description 10
- 239000002184 metal Substances 0.000 claims description 10
- 239000002904 solvent Substances 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 4
- 229920000554 ionomer Polymers 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000011068 loading method Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 230000035484 reaction time Effects 0.000 abstract description 7
- 238000005265 energy consumption Methods 0.000 abstract description 3
- 239000000306 component Substances 0.000 description 8
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- LYCAIKOWRPUZTN-UHFFFAOYSA-N Ethylene glycol Chemical compound OCCO LYCAIKOWRPUZTN-UHFFFAOYSA-N 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000012528 membrane Substances 0.000 description 3
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 2
- YCKRFDGAMUMZLT-UHFFFAOYSA-N Fluorine atom Chemical compound [F] YCKRFDGAMUMZLT-UHFFFAOYSA-N 0.000 description 2
- LRHPLDYGYMQRHN-UHFFFAOYSA-N N-Butanol Chemical compound CCCCO LRHPLDYGYMQRHN-UHFFFAOYSA-N 0.000 description 2
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 description 2
- KDLHZDBZIXYQEI-UHFFFAOYSA-N Palladium Chemical compound [Pd] KDLHZDBZIXYQEI-UHFFFAOYSA-N 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 239000011737 fluorine Substances 0.000 description 2
- 229910052731 fluorine Inorganic materials 0.000 description 2
- 150000002739 metals Chemical class 0.000 description 2
- BASFCYQUMIYNBI-UHFFFAOYSA-N platinum Chemical compound [Pt] BASFCYQUMIYNBI-UHFFFAOYSA-N 0.000 description 2
- 229920005989 resin Polymers 0.000 description 2
- 239000011347 resin Substances 0.000 description 2
- 238000003756 stirring Methods 0.000 description 2
- KJTLSVCANCCWHF-UHFFFAOYSA-N Ruthenium Chemical compound [Ru] KJTLSVCANCCWHF-UHFFFAOYSA-N 0.000 description 1
- 238000010923 batch production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 239000006229 carbon black Substances 0.000 description 1
- 239000002134 carbon nanofiber Substances 0.000 description 1
- 229910021393 carbon nanotube Inorganic materials 0.000 description 1
- 239000002041 carbon nanotube Substances 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 229910017052 cobalt Inorganic materials 0.000 description 1
- 239000010941 cobalt Substances 0.000 description 1
- GUTLYIVDDKVIGB-UHFFFAOYSA-N cobalt atom Chemical compound [Co] GUTLYIVDDKVIGB-UHFFFAOYSA-N 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 239000012153 distilled water Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000011049 filling Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 239000010439 graphite Substances 0.000 description 1
- 229910002804 graphite Inorganic materials 0.000 description 1
- -1 i.e. Substances 0.000 description 1
- 229910052741 iridium Inorganic materials 0.000 description 1
- GKOZUEZYRPOHIO-UHFFFAOYSA-N iridium atom Chemical compound [Ir] GKOZUEZYRPOHIO-UHFFFAOYSA-N 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010907 mechanical stirring Methods 0.000 description 1
- 229910001092 metal group alloy Inorganic materials 0.000 description 1
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 1
- 239000002070 nanowire Substances 0.000 description 1
- 229910052759 nickel Inorganic materials 0.000 description 1
- 229910052763 palladium Inorganic materials 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 229910052697 platinum Inorganic materials 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- BDERNNFJNOPAEC-UHFFFAOYSA-N propan-1-ol Chemical compound CCCO BDERNNFJNOPAEC-UHFFFAOYSA-N 0.000 description 1
- 229910052707 ruthenium Inorganic materials 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000004513 sizing Methods 0.000 description 1
- 238000001132 ultrasonic dispersion Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 229910052727 yttrium Inorganic materials 0.000 description 1
- VWQVUPCCIRVNHF-UHFFFAOYSA-N yttrium atom Chemical compound [Y] VWQVUPCCIRVNHF-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01F—MIXING, e.g. DISSOLVING, EMULSIFYING OR DISPERSING
- B01F35/00—Accessories for mixers; Auxiliary operations or auxiliary devices; Parts or details of general application
- B01F35/60—Safety arrangements
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01F—MIXING, e.g. DISSOLVING, EMULSIFYING OR DISPERSING
- B01F35/00—Accessories for mixers; Auxiliary operations or auxiliary devices; Parts or details of general application
- B01F35/60—Safety arrangements
- B01F35/605—Safety devices concerning the operation of the mixer
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01F—MIXING, e.g. DISSOLVING, EMULSIFYING OR DISPERSING
- B01F35/00—Accessories for mixers; Auxiliary operations or auxiliary devices; Parts or details of general application
- B01F35/80—Forming a predetermined ratio of the substances to be mixed
- B01F35/88—Forming a predetermined ratio of the substances to be mixed by feeding the materials batchwise
- B01F35/881—Forming a predetermined ratio of the substances to be mixed by feeding the materials batchwise by weighing, e.g. with automatic discharge
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01F—MIXING, e.g. DISSOLVING, EMULSIFYING OR DISPERSING
- B01F2101/00—Mixing characterised by the nature of the mixed materials or by the application field
- B01F2101/59—Mixing reaction ingredients for fuel cells
-
- 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
- Y02E60/30—Hydrogen technology
- Y02E60/50—Fuel cells
Landscapes
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Fuel Cell (AREA)
- Inert Electrodes (AREA)
Abstract
The invention relates to the technical field of fuel cells, in particular to a weighing type centrifugal batching method and a batching device for fuel cell catalyst slurry, wherein the batching method comprises the following steps: inputting raw materials into a batching assembly in an anaerobic cabin; the nitrogen supply assembly continuously introduces nitrogen into the anaerobic chamber body and discharges oxygen in the anaerobic chamber body; the oxygen detection assembly compares the real-time oxygen concentration with a preset oxygen concentration, and when the real-time oxygen concentration is smaller than or equal to the preset oxygen concentration, the batching assembly mixes and batching the raw materials to form catalyst slurry. According to the technical scheme, oxygen in the anaerobic cabin is discharged through the nitrogen supply assembly, and when the real-time oxygen concentration is judged to be smaller than or equal to the preset oxygen concentration, mixed ingredients can be prepared, so that an anaerobic safety environment is provided for the ingredients; in addition, divide different reaction time stages and set up corresponding oxygen concentration default according to the batching process, can reduce the power of supplying the nitrogen subassembly when oxygen concentration requirement is low, supply the nitrogen subassembly to need not whole full load operation, and the energy consumption reduces more accurately.
Description
Technical Field
The invention relates to the technical field of fuel cells, in particular to a weighing type centrifugal batching method and a batching device for fuel cell catalyst slurry.
Background
One of the core components of a single cell in a fuel cell is a proton exchange membrane, which plays a key role in cell performance. The slurry is an important component of the proton exchange membrane. The catalyst, i.e., slurry, uniformly coated on the proton exchange membrane has a cost that is a significant fraction of the fuel cell.
Chinese patent CN217511736U provides a fuel cell slurry mixing device, and fuel cell slurry mixing device includes the casing, be provided with agitating unit in the casing, the external evacuating device of casing, evacuating device is used for evacuating the casing inner chamber, the external ultrasonic generating device of casing, the external fluid-discharge tube of casing, be provided with filter equipment on the fluid-discharge tube. The patent further enhances the uniform dispersion of particles in the solvent by combining the mechanical stirring of the stirring device with the ultrasonic dispersion action of the ultrasonic generating device, and is favorable for forming the battery slurry with good consistency and strong stability. The raw material mixing and slurry preparation processes can be continuously carried out, the stirring time is short, the mixing efficiency is high, the controllability is strong, the device structure is simple, the operation is convenient, and the industrial application is easy to carry out. In this patent, the apparatus does not take any anaerobic measures to the raw material mixing environment, and during the slurry batching process, raw material mixing will react with oxygen, and then cause combustion or explosion.
In summary, in the slurry batching process, if oxygen exists during the mixing reaction of the raw materials, the raw materials react with the oxygen, and then combustion or explosion is initiated, and potential safety hazards exist in the batching environment.
Disclosure of Invention
The invention aims to provide a weighing type centrifugal batching method and a batching device for fuel cell catalyst slurry, and aims to solve the technical problem that potential safety hazards exist in the mixing batching environment of the existing fuel cell catalyst slurry, and the slurry can react with oxygen.
In order to achieve the above object, the present invention provides a weighing type centrifugal batching method of fuel cell catalyst slurry, the batching method comprising the steps of:
inputting raw materials into a batching assembly in an anaerobic cabin body, and weighing the raw materials;
the nitrogen supply assembly continuously introduces nitrogen into the anaerobic chamber body and discharges oxygen in the anaerobic chamber body;
the oxygen detection assembly compares the real-time oxygen concentration in the anaerobic cabin with the preset oxygen concentration, the weighing module compares the real-time weight and the preset weight of the raw materials, and when the real-time oxygen concentration is smaller than or equal to the preset oxygen concentration and the real-time weight is within a range value of the preset weight, the batching assembly mixes and doses the raw materials to form the catalyst slurry.
Further, the batching method further comprises the following steps:
before mixing ingredients, defining the oxygen concentration of the anaerobic tank body before the raw materials are input into the ingredients assembly as a first-stage oxygen concentration, defining the oxygen concentration of the anaerobic tank body during the raw materials are input into the ingredients assembly as a second-stage oxygen concentration, defining the oxygen concentration of the anaerobic tank body during the mixing ingredients of the raw materials in the ingredients tank as a third-stage oxygen concentration, and defining the oxygen concentration of the anaerobic tank body which stands after the raw materials are mixed as a fourth-stage oxygen concentration;
setting corresponding preset oxygen concentration values for the first-stage oxygen concentration, the second-stage oxygen concentration, the third-stage oxygen concentration and the fourth-stage oxygen concentration of the anaerobic cabin body;
in the raw material mixing and proportioning process, an oxygen detection component detects the first-stage oxygen concentration, the second-stage oxygen concentration, the third-stage oxygen concentration and the fourth-stage oxygen concentration of the anaerobic cabin in real time;
and respectively comparing the real-time oxygen concentration value of the first stage oxygen concentration, the second stage oxygen concentration, the third stage oxygen concentration and the fourth stage oxygen concentration with the corresponding preset oxygen concentration value, and if the real-time oxygen concentration value is higher than the corresponding preset oxygen concentration value, improving the air inlet flow of the nitrogen supply assembly by the regulating module.
Further, the batching method further comprises the following steps:
the raw materials comprise a carrier, catalyst metal, a solvent and an ionomer, and the preset oxygen concentration values of the first stage oxygen concentration, the second stage oxygen concentration, the third stage oxygen concentration and the fourth stage oxygen concentration are adjusted according to the types of the catalyst metal.
Further, the batching method further comprises the following steps:
the method comprises the steps that an acquisition module records first slurry, second slurry and the components and the quality of N slurry and corresponding preset oxygen concentration values of first-fourth stage oxygen concentrations, and a first slurry database, a second slurry database and the N slurry database are respectively generated;
the matching module detects the type of the current slurry and which stage is the first stage to the fourth stage, and invokes a slurry database which is the same as the current slurry;
the adjusting module compares the oxygen concentration of the current slurry in the stage with the preset oxygen concentration value of the corresponding stage in the slurry database according to the preset oxygen concentration values of the oxygen concentrations of the first stage to the fourth stage in the slurry database and the stage of the current slurry, and if the oxygen concentration of the current slurry in the stage is higher than the preset oxygen concentration value, the adjusting module improves the air inflow and the air inflow pressure of the nitrogen supply assembly.
Further, the batching method further comprises the following steps:
carrying out data normalization on a slurry database of the acquisition module, and dividing the slurry database into training data and test data;
based on an Xgboost algorithm, a model prediction module carries out model training on training data to obtain model parameters;
inputting Xgboost model parameters and test data, and predicting the stage where the slurry is and the corresponding preset oxygen concentration value;
and performing error evaluation on the Xgboost model prediction result to obtain prediction data of a preset oxygen concentration value and outputting the prediction data.
Further, the batching method further comprises the following steps:
collecting historical data of a slurry database to form a sample set for modeling;
preprocessing current raw material data, and determining input characteristic variables and output targets of a clustering model;
initializing model parameters, taking result data and intermediate environment feedback data as characteristic sample data, and loading N characteristic sample data sets;
initializing training times, calculating information of each input characteristic of preset oxygen concentration values of the oxygen concentration in the first stage to the fourth stage by using an extreme gradient lifting algorithm, and normalizing to adapt to the requirement of clustering analysis on data;
calling a training and parameter optimizing function XGBOOST in the XGBOOST model, and determining the maximum tree depth and the iteration times;
when the target times are not reached, obtaining a predicted value according to a forward propagation mode, calculating a gradient value l according to the difference between an actual value and the predicted value, updating a characteristic variable and an output target through a backward propagation mode, and adding 1 to the iteration times;
when the target times are reached, an output target function is obtained, then a test set is entered for testing, and if the training target is not met, the initial training times are returned until the training target is reached.
Further, the Xgboost prediction model expression is as follows:
wherein (1)>Representing the predicted value for i samples, +.>Within the F set->Representing the prediction of the ith sample by the kth tree;
training to obtain K trees, constructing a training objective function, and constructing an objective functionobjThe expression is as follows:
wherein,for the samplex i Training error of->A canonical term representing the kth tree,nis the total number of samples.
In order to achieve the above object, the present invention also provides a weighing type centrifugal batching device for fuel cell catalyst slurry, comprising:
an anaerobic cabin body, wherein a batching assembly is arranged in the anaerobic cabin body;
the anaerobic cabin body is provided with an air inlet and an air outlet, the nitrogen supply assembly is connected with the anaerobic cabin body through the air inlet, the oxygen detection assembly is connected with the anaerobic cabin body through the air outlet, and the nitrogen supply assembly is used for supplying nitrogen so as to form an anaerobic environment in the anaerobic cabin body; the oxygen detection assembly is used for detecting the oxygen concentration in the anaerobic cabin body.
Further, the batching subassembly includes the batching jar, the bottom of batching jar is connected with centrifugal flange, centrifugal flange's bottom is connected with the driving piece.
Further, the batching subassembly still includes the batching seat, the driving piece connect in the batching seat, centrifugal flange connect in the top of batching seat, the bottom of batching seat is provided with the electronic scale, the both sides of the bottom of batching seat still are provided with the promotion cylinder.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, the nitrogen supply assembly is used for discharging oxygen in the anaerobic cabin, and after the real-time oxygen concentration is judged to be smaller than or equal to the preset oxygen concentration and the real-time weight is judged to be within the range value of the preset weight, the mixing and proportioning can be carried out, so that the raw materials and the oxygen are prevented from reacting, and an anaerobic safety environment is provided for proportioning; meanwhile, the weighing control is carried out on the batching process, so that the dosage of each raw material is ensured to be matched with the dosage specified in a preset formula, the batching accuracy is improved, the product defect caused by the batching proportion error is avoided, and the economic loss caused by the slurry defect is reduced;
in addition, the invention divides different reaction time stages according to the batching process, and gives corresponding preset oxygen concentration values to the different reaction time stages, so that the power of the nitrogen supply assembly can be reduced in the reaction time period with low oxygen concentration requirement, and the nitrogen supply assembly does not need to run at full load, thereby accurately saving the energy consumption of gas supply.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the structures shown in these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of an embodiment of a weighted centrifugal dosing unit for fuel cell catalyst slurry of the present application;
FIG. 2 is a schematic diagram of an embodiment of a weighted centrifugal dosing unit for fuel cell catalyst slurry of the present application;
fig. 3 is a schematic diagram of a training flow of an embodiment of the model training module of the present application.
Wherein: the device comprises a 1-anaerobic cabin, a 2-batching tank, a 3-centrifugal flange, a 4-driving piece, a 5-electronic scale, a 6-lifting cylinder, a 7-nitrogen supply assembly, a 10-oxygen detection assembly, an 11-air outlet and a 12-air inlet.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that, if a directional indication (such as up, down, left, right, front, and rear … …) is involved in the embodiment of the present invention, the directional indication is merely used to explain the relative positional relationship, movement condition, etc. between the components in a specific posture, and if the specific posture is changed, the directional indication is correspondingly changed.
In addition, if there is a description of "first", "second", etc. in the embodiments of the present invention, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, if "and/or" and/or "are used throughout, the meaning includes three parallel schemes, for example," a and/or B "including a scheme, or B scheme, or a scheme where a and B are satisfied simultaneously. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present invention.
Referring to fig. 1-3, the present disclosure provides a weighted centrifugal batching apparatus for fuel cell catalyst slurry, in an embodiment of the weighted centrifugal batching apparatus for fuel cell catalyst slurry, the weighted centrifugal batching apparatus for fuel cell catalyst slurry includes:
the anaerobic cabin body 1 is internally provided with a batching assembly;
the oxygen supply assembly 7 and the oxygen detection assembly 10, the anaerobic chamber body 1 is provided with an air inlet 12 and an air outlet 11, the nitrogen supply assembly 7 is connected with the anaerobic chamber body 1 through the air inlet 12, the oxygen detection assembly 10 is connected with the anaerobic chamber body 1 through the air outlet 11, and the nitrogen supply assembly 7 is used for providing nitrogen so as to form an anaerobic environment in the anaerobic chamber body 1; the oxygen detecting component 10 is used for detecting the oxygen concentration in the anaerobic chamber body 1, and provides a detecting signal for judging the execution of the batching by the batching component.
Further, the batching subassembly includes batching jar 2, the bottom of batching jar 2 is connected with centrifugal flange 3, the bottom of centrifugal flange 3 is connected with driving piece 4, and driving piece 4 adopts pneumatic motor.
Further, the batching subassembly still includes the batching seat, the driving piece 4 connect in the batching seat, centrifugal flange 3 connect in the top of batching seat, the bottom of batching seat is provided with electronic scale 5, the both sides of the bottom of batching seat still are provided with promotion cylinder 6.
The weighing type centrifugal batching device for fuel cell catalyst slurry of the present embodiment discharges air in the anaerobic chamber 1 by using a nitrogen filling manner, and by installing an oxygen detecting assembly 10, the oxygen detecting assembly 10 includes an oxygen sensor, and batching is started under the condition that the oxygen sensor detects anaerobic condition, and in this process, the nitrogen continuously fills the discharged air, and an anaerobic environment is continuously provided for batching slurry. After weighing and proportioning are completed, the proportioning tank 2 is driven to centrifugally rotate under the action of the driving piece 4, and raw materials are promoted to be fully mixed and reacted. At the moment, the raw materials and oxygen can not react, and the raw materials can not burn or explode after being taken out for standby.
The technical scheme also provides a weighing type centrifugal batching method of the fuel cell catalyst slurry, which is based on the weighing type centrifugal batching device of the fuel cell catalyst slurry in the embodiment, and further comprises a weighing module, and in one embodiment of the batching method, the batching method comprises the following steps:
s1: inputting raw materials into a batching assembly in an anaerobic cabin body, and weighing the raw materials;
s2: the nitrogen supply assembly continuously introduces nitrogen into the anaerobic chamber body and discharges oxygen in the anaerobic chamber body;
s3: the oxygen detection assembly compares the real-time oxygen concentration in the anaerobic cabin with the preset oxygen concentration, the weighing module compares the real-time weight and the preset weight of the raw materials, and when the real-time oxygen concentration is smaller than or equal to the preset oxygen concentration and the real-time weight is within a range value of the preset weight, the batching assembly mixes and doses the raw materials to form the catalyst slurry.
In the embodiment, the nitrogen supply assembly is used for discharging oxygen in the anaerobic cabin, and after the real-time oxygen concentration is judged to be smaller than or equal to the preset oxygen concentration and the real-time weight is judged to be within the range value of the preset weight, the mixing and proportioning can be carried out, so that the raw materials and the oxygen are prevented from reacting, and an anaerobic safety environment is provided for proportioning; meanwhile, the weighing module is used for controlling the batching process, so that the dosage of each raw material is matched with the dosage specified in a preset formula, the batching accuracy is improved, poor products caused by wrong batching proportion are avoided, and economic losses caused by poor sizing agent can be reduced.
Further, in an embodiment, the weighted centrifugal dosing device of the fuel cell catalyst slurry further comprises a conditioning module, the dosing method further comprising the steps of:
a1: before mixing ingredients, defining the oxygen concentration of the anaerobic tank body before the raw materials are input into the ingredients assembly as a first-stage oxygen concentration, defining the oxygen concentration of the anaerobic tank body during the raw materials are input into the ingredients assembly as a second-stage oxygen concentration, defining the oxygen concentration of the anaerobic tank body during the mixing ingredients of the raw materials in the ingredients tank as a third-stage oxygen concentration, and defining the oxygen concentration of the anaerobic tank body which stands after the raw materials are mixed as a fourth-stage oxygen concentration;
a2: setting corresponding preset oxygen concentration values for the first-stage oxygen concentration, the second-stage oxygen concentration, the third-stage oxygen concentration and the fourth-stage oxygen concentration of the anaerobic cabin body;
a3: in the raw material mixing and proportioning process, an oxygen detection component detects the first-stage oxygen concentration, the second-stage oxygen concentration, the third-stage oxygen concentration and the fourth-stage oxygen concentration of the anaerobic cabin in real time;
a4: and respectively comparing the real-time oxygen concentration value of the first stage oxygen concentration, the second stage oxygen concentration, the third stage oxygen concentration and the fourth stage oxygen concentration with the corresponding preset oxygen concentration value, and if the real-time oxygen concentration value is higher than the corresponding preset oxygen concentration value, improving the air inlet flow of the nitrogen supply assembly by the regulating module.
Specifically, in the actual batching production process, the requirements on the oxygen concentration in different batching stages are different, and if the nitrogen supply assembly runs at full load before and after batching reaction, the nitrogen supply assembly excessively supplies nitrogen in the time period with low oxygen concentration requirement, so that the air supply energy source is wasted. Therefore, in the embodiment, different preset oxygen concentration values are set for different time periods of the anaerobic chamber according to the batching process. In this embodiment, the requirement of the batching system on the oxygen concentration of the anaerobic chamber body (i.e. the first-stage oxygen concentration) before the raw materials are input into the batching assembly and the oxygen concentration of the anaerobic chamber body (i.e. the fourth-stage oxygen concentration) after the raw materials are mixed and are kept still is low, and in the two time stages, the raw materials or the slurry are difficult to react with oxygen, so that the preset oxygen concentration values of the first-stage oxygen concentration and the fourth-stage oxygen concentration can be set to be 10%; the oxygen concentration (namely, the oxygen concentration of the second stage) of the anaerobic cabin in the process of inputting the raw materials into the batching assembly is required to be higher by the batching system, so that the preset oxygen concentration value of the oxygen concentration of the second stage can be set to be 2%; the batching system has the highest requirement on the oxygen concentration of the anaerobic cabin body (namely the oxygen concentration in the third stage) in the process of mixing and batching the raw materials in the batching tank, and the raw materials are easy to react with oxygen, so that the preset oxygen concentration value of the oxygen concentration in the third stage can be set to be 0.1%. The lower the oxygen concentration is, the higher the working power of the nitrogen supply assembly is, so that when the batch proportioning work is carried out, different reaction time stages are divided according to the proportioning process, corresponding oxygen concentration preset values are set for the different reaction time stages, the power of the nitrogen supply assembly can be reduced in the reaction time period with low oxygen concentration requirement, the nitrogen supply assembly does not need to run at full load, and therefore the air supply energy consumption is accurately saved.
Further, in one embodiment, the raw materials include a carrier, a catalyst metal, a solvent and an ionomer, wherein the catalyst metal adopts at least one or more metal alloys from the group of platinum, iridium, ruthenium, palladium, nickel, cobalt and yttrium; the carrier adopts one of graphite, activated carbon, carbon black, carbon nano tube, carbon nano fiber, carbon nano wire and the combination thereof; the solvent is one of distilled water, ethanol, propanol, butanol, ethylene glycol and a combination thereof; the ionomer employs at least one of the group of fluorine-based resins, non-fluorine-based resins, and combinations thereof. In this embodiment, since the activities of the catalyst metals are different and the reaction sensitivity degree with oxygen is different, the batching method adjusts the preset oxygen concentration values of the first stage oxygen concentration, the second stage oxygen concentration, the third stage oxygen concentration and the fourth stage oxygen concentration according to the types of the catalyst metals after setting the corresponding preset oxygen concentration values of the first stage oxygen concentration, the second stage oxygen concentration, the third stage oxygen concentration and the fourth stage oxygen concentration of the anaerobic chamber body. If the activity of the catalyst metal selected for a certain batch is stronger, the preset oxygen concentration value of the oxygen concentration in the second stage or the oxygen concentration in the third stage of the batch process is reduced, so that the reaction of the catalyst metal and oxygen is further avoided.
Further, in an embodiment, the weighing type centrifugal batching device of the fuel cell catalyst slurry further comprises a collecting module and a matching module, and the batching method further comprises the following steps:
b1: the method comprises the steps that an acquisition module records first slurry, second slurry and the components and the quality of N slurry and corresponding preset oxygen concentration values of first-fourth stage oxygen concentrations, and a first slurry database, a second slurry database and the N slurry database are respectively generated;
b2: the matching module detects the type of the current slurry and which stage is the first stage to the fourth stage, and invokes a slurry database which is the same as the current slurry;
b3: the adjusting module compares the oxygen concentration of the current slurry in the stage with the preset oxygen concentration value of the corresponding stage in the slurry database according to the preset oxygen concentration values of the oxygen concentrations of the first stage to the fourth stage in the slurry database and the stage of the current slurry, and if the oxygen concentration of the current slurry in the stage is higher than the preset oxygen concentration value, the adjusting module improves the air inflow and the air inflow pressure of the nitrogen supply assembly.
According to the embodiment, the data characteristics of the slurry are recorded through the acquisition module, so that a slurry database which can be called at any time is formed, when the system detects that the slurry database has the same data as the type of the current slurry, the preset oxygen concentration of the slurry is automatically called, program automation is realized, and the operation convenience is improved.
Further, in an embodiment, the weighted centrifugal dosing device of the fuel cell catalyst slurry further comprises a model prediction module, and the dosing method further comprises the steps of:
c1: carrying out data normalization on a slurry database of the acquisition module, and dividing the slurry database into training data and test data;
c2: based on an Xgboost algorithm, a model prediction module carries out model training on training data to obtain model parameters;
and C3: inputting Xgboost model parameters and test data, and predicting the stage where the slurry is and the corresponding preset oxygen concentration value;
and C4: and performing error evaluation on the Xgboost model prediction result to obtain prediction data of a preset oxygen concentration value and outputting the prediction data.
Specifically, in step C3, xgboost model parameters are input, the input data are processed by adopting time window step parameters, the first n preset oxygen concentration value data are input into the trained Xgboost model, and the next preset oxygen concentration value data prediction result, namely n+1 preset oxygen concentration values, is generated; in step C4, a trained Xgboost model is used to predict a preset oxygen concentration value, error calculation is performed on the predicted data and the actual data, and a Mean Square Error (MSE) and a Root Mean Square Error (RMSE) are used as evaluation indexes for error calculation:
mean square error:
root Mean Square Error (RMSE):
wherein: n is the number of data sets and,representing predictive data,/->Representing real data.
Based on the trained Xgboost model, the model prediction module inputs the type and quality of the slurry, and can predict and output the preset oxygen concentration values of the oxygen concentrations in the first stage to the fourth stage for the new slurry which does not exist in the slurry database, so that manual writing of a user is not needed, program automation is further realized, and operation convenience is further improved.
Further, in an embodiment, the weighted centrifugal dosing device of the fuel cell catalyst slurry further comprises a model training module, and the dosing method further comprises the steps of:
d1: collecting historical data of a slurry database to form a sample set for modeling;
d2: preprocessing current raw material data, and determining input characteristic variables and output targets of a clustering model;
d3: initializing model parameters, taking result data and intermediate environment feedback data as characteristic sample data, and loading N characteristic sample data sets;
d4: initializing training times, calculating information of each input characteristic of preset oxygen concentration values of the oxygen concentration in the first stage to the fourth stage by using an extreme gradient lifting algorithm, and normalizing to adapt to the requirement of clustering analysis on data;
d5: calling a training and parameter optimizing function Xgboost train in the Xgboost model, and determining the maximum tree depth and iteration times;
d6: when the target times are not reached, obtaining a predicted value according to a forward propagation mode, calculating a gradient value l according to the difference between an actual value and the predicted value, updating a characteristic variable and an output target through a backward propagation mode, and adding 1 to the iteration times;
d7: when the target times are reached, an output target function is obtained, then a test set is entered for testing, and if the training target is not met, the initial training times are returned until the training target is reached.
Specifically, as shown in fig. 3, the Xgboost model trained by the data set can obtain a prediction model with higher prediction accuracy.
Further, the Xgboost prediction model expression is as follows:
wherein (1)>Representing the predicted value for i samples, +.>Within the F set->Representing the prediction of the ith sample by the kth tree;
training to obtain K trees, constructing a training objective function, and constructing an objective functionobjThe expression is as follows:
wherein,for the samplex i Training error of->A canonical term representing the kth tree,nis the total number of samples.
The Xgboost of the implementation is one of the BOOSTING algorithms, and the concept of the BOOSTING algorithm is to integrate a plurality of weak classifiers together to form a strong classifier. Because Xgboost is a lifting tree model, it integrates many tree models together to form a strong classifier. The tree model used is the CART regression tree model. Through the Xgboost model trained by the data set, the model prediction module inputs the type and quality of the slurry, and can predict and output the preset oxygen concentration values of the oxygen concentration in the first stage to the fourth stage for the new slurry which does not exist in the slurry database, so that the preset oxygen concentration values of different time stages of the anaerobic cabin can be accurately and rapidly judged, the time of manual writing is greatly shortened, and the convenience of using the batching device is improved.
The foregoing description is only of the optional embodiments of the present invention, and is not intended to limit the scope of the invention, and all the equivalent structural changes made by the description of the present invention and the accompanying drawings or the direct/indirect application in other related technical fields are included in the scope of the invention.
Claims (6)
1. A method of weighing centrifugal dosing of fuel cell catalyst slurry, the dosing method comprising the steps of:
inputting raw materials into a batching assembly in an anaerobic cabin body, and weighing the raw materials; the mixing of the raw materials requires an oxygen-free environment;
the nitrogen supply assembly continuously introduces nitrogen into the anaerobic chamber body and discharges oxygen in the anaerobic chamber body;
the oxygen detection assembly compares the real-time oxygen concentration in the anaerobic cabin with the preset oxygen concentration, the weighing module compares the real-time weight and the preset weight of the raw materials, and when the real-time oxygen concentration is smaller than or equal to the preset oxygen concentration and the real-time weight meets the range value of the preset weight, the batching assembly mixes and doses the raw materials to form catalyst slurry;
the batching method further comprises the following steps:
before mixing ingredients, defining the oxygen concentration of the anaerobic tank body before the raw materials are input into the ingredients assembly as a first-stage oxygen concentration, defining the oxygen concentration of the anaerobic tank body during the raw materials are input into the ingredients assembly as a second-stage oxygen concentration, defining the oxygen concentration of the anaerobic tank body during the mixing ingredients of the raw materials in the ingredients tank as a third-stage oxygen concentration, and defining the oxygen concentration of the anaerobic tank body which stands after the raw materials are mixed as a fourth-stage oxygen concentration;
setting corresponding preset oxygen concentration values for the first-stage oxygen concentration, the second-stage oxygen concentration, the third-stage oxygen concentration and the fourth-stage oxygen concentration of the anaerobic cabin body;
in the raw material mixing and proportioning process, an oxygen detection component detects the first-stage oxygen concentration, the second-stage oxygen concentration, the third-stage oxygen concentration and the fourth-stage oxygen concentration of the anaerobic cabin in real time;
and respectively comparing the real-time oxygen concentration value of the first stage oxygen concentration, the second stage oxygen concentration, the third stage oxygen concentration and the fourth stage oxygen concentration with the corresponding preset oxygen concentration value, and if the real-time oxygen concentration value is higher than the corresponding preset oxygen concentration value, improving the air inlet flow of the nitrogen supply assembly by the regulating module.
2. The method of gravimetric centrifugal dosing of a fuel cell catalyst slurry according to claim 1, further comprising the step of:
the raw materials comprise a carrier, catalyst metal, a solvent and an ionomer, and the preset oxygen concentration values of the first stage oxygen concentration, the second stage oxygen concentration, the third stage oxygen concentration and the fourth stage oxygen concentration are adjusted according to the types of the catalyst metal.
3. The method of gravimetric centrifugal dosing of a fuel cell catalyst slurry according to claim 2, further comprising the step of:
the collection module records the components and the quality of the first slurry, the second slurry and the N slurry and the corresponding preset oxygen concentration values of the oxygen concentration of the first stage to the fourth stage, and respectively generates a first slurry database, a second slurry database and the N slurry database;
the matching module detects the type of the current slurry and which stage is the first stage to the fourth stage, and invokes a slurry database which is the same as the current slurry;
the adjusting module compares the oxygen concentration of the current slurry in the stage with the preset oxygen concentration value of the corresponding stage in the slurry database according to the preset oxygen concentration values of the oxygen concentrations of the first stage to the fourth stage in the slurry database and the stage of the current slurry, and if the oxygen concentration of the current slurry in the stage is higher than the preset oxygen concentration value, the adjusting module improves the air inflow and the air inflow pressure of the nitrogen supply assembly.
4. A method of gravimetric centrifugal dosing of a fuel cell catalyst slurry according to claim 3, further comprising the step of:
carrying out data normalization on a slurry database of the acquisition module, and dividing the slurry database into training data and test data;
based on an Xgboost algorithm, a model prediction module carries out model training on training data to obtain model parameters;
inputting Xgboost model parameters and test data, and predicting the stage where the slurry is and the corresponding preset oxygen concentration value;
and performing error evaluation on the Xgboost model prediction result to obtain prediction data of a preset oxygen concentration value and outputting the prediction data.
5. The method of gravimetric centrifugal dosing of a fuel cell catalyst slurry according to claim 4, further comprising the step of:
collecting historical data of a slurry database to form a sample set for modeling;
preprocessing current raw material data, and determining input characteristic variables and output targets of a clustering model;
initializing model parameters, taking result data and intermediate environment feedback data as characteristic sample data, and loading N characteristic sample data sets;
initializing training times, calculating information of each input characteristic of preset oxygen concentration values of the oxygen concentration in the first stage to the fourth stage by using an extreme gradient lifting algorithm, and normalizing to adapt to the requirement of clustering analysis on data;
calling a training and parameter optimizing function XGBOOST in the XGBOOST model, and determining the maximum tree depth and the iteration times;
when the target times are not reached, obtaining a predicted value according to a forward propagation mode, calculating a gradient value l according to the difference between an actual value and the predicted value, updating a characteristic variable and an output target through a backward propagation mode, and adding 1 to the iteration times;
when the target times are reached, an output target function is obtained, then a test set is entered for testing, and if the training target is not met, the initial training times are returned until the training target is reached.
6. The method of claim 5, wherein the Xgboost predictive model expression is as follows:
wherein (1)>Representing the predicted value for i samples, +.>Belonging to the range of the F set,representing the prediction of the ith sample by the kth tree;
training to obtain K trees, constructing a training objective function, and constructing an objective functionobjThe expression is as follows:
wherein,for the samplex i Training error of->A canonical term representing the kth tree,nis the total number of samples.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311362678.XA CN117101529B (en) | 2023-10-20 | 2023-10-20 | Weighing type centrifugal batching method and batching device for fuel cell catalyst slurry |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311362678.XA CN117101529B (en) | 2023-10-20 | 2023-10-20 | Weighing type centrifugal batching method and batching device for fuel cell catalyst slurry |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117101529A CN117101529A (en) | 2023-11-24 |
CN117101529B true CN117101529B (en) | 2024-02-09 |
Family
ID=88798673
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311362678.XA Active CN117101529B (en) | 2023-10-20 | 2023-10-20 | Weighing type centrifugal batching method and batching device for fuel cell catalyst slurry |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117101529B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4981826A (en) * | 1989-11-17 | 1991-01-01 | Exxon Chemical Patents Inc. | Polymerization catalyst prepared with a halogenated silane compound |
JP2012223693A (en) * | 2011-04-19 | 2012-11-15 | Sumitomo Chemical Co Ltd | Method for producing electrode catalyst |
CN216120374U (en) * | 2021-08-31 | 2022-03-22 | 上海氢晟新能源科技有限公司 | Device for dispersing catalyst slurry of mixed fuel cell |
CN217288051U (en) * | 2022-01-20 | 2022-08-26 | 大连瑞源动力股份有限公司 | Fixed-ratio feeding equipment of platinum-carbon catalyst for hydrogen fuel cell preparation |
-
2023
- 2023-10-20 CN CN202311362678.XA patent/CN117101529B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4981826A (en) * | 1989-11-17 | 1991-01-01 | Exxon Chemical Patents Inc. | Polymerization catalyst prepared with a halogenated silane compound |
JP2012223693A (en) * | 2011-04-19 | 2012-11-15 | Sumitomo Chemical Co Ltd | Method for producing electrode catalyst |
CN216120374U (en) * | 2021-08-31 | 2022-03-22 | 上海氢晟新能源科技有限公司 | Device for dispersing catalyst slurry of mixed fuel cell |
CN217288051U (en) * | 2022-01-20 | 2022-08-26 | 大连瑞源动力股份有限公司 | Fixed-ratio feeding equipment of platinum-carbon catalyst for hydrogen fuel cell preparation |
Also Published As
Publication number | Publication date |
---|---|
CN117101529A (en) | 2023-11-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Limon‐Lason et al. | Reactor properties of a high‐speed bead mill for microbial cell rupture | |
Brahme et al. | Modelling of a slurry reaction. Hydrogenation of glucose on Raney nickel | |
CN103676668A (en) | Fuel cell semi-physical simulation testing system based on VC and building method | |
CN1869420A (en) | Combustion controller and controll method of miniature gas turbine | |
CN110764011A (en) | Fuel cell testing platform | |
CN114813105A (en) | Gear box fault early warning method and system based on working condition similarity evaluation | |
CN113094988A (en) | Data-driven slurry circulating pump operation optimization method and system | |
CN117101529B (en) | Weighing type centrifugal batching method and batching device for fuel cell catalyst slurry | |
CN109603617B (en) | Mixed homogenate system and application thereof | |
CN113314739B (en) | Transient modeling method for hydrogen circulating pump in fuel cell system | |
CN111864233B (en) | Hydrogen purity detection device of hydrogen supply system | |
CN101748186A (en) | FSVM-based lysine fermentation process key state variable soft measuring method and system | |
CN105628429A (en) | Full-automatic microwave pretreatment device | |
CN107341359A (en) | Stalk fermentation produces the flexible measurement method of ethanol process key parameters | |
CN205719601U (en) | Full-automatic microwave device | |
Liotta et al. | Real-time estimation and control of particle size in semi-batch emulsion polymerization | |
CN114447378A (en) | Parameter optimization method of proton exchange membrane fuel cell | |
CN110390132B (en) | Nonferrous metallurgy unit procedure digitalization and modeling method based on process state space | |
CN114857061A (en) | Modeling and multi-target control method of aviation fuel cell air supply system | |
CN1687921A (en) | Rare-earth cascade extraction separation component content soft measuring method | |
CN112434739A (en) | Chemical process fault diagnosis method of support vector machine based on multi-core learning | |
CN212315686U (en) | Water treatment control system | |
CN114880926A (en) | Digital twinning system based on Grignard reaction | |
CN104450499A (en) | Early warning method of pichia pastoris fermentation process based on support vector machine | |
CN211553481U (en) | Automatic liquid raw material sampling device for standard gas preparation |
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 |