CN117352110B - System for testing high-temperature flow characteristics of tantalum melt based on rotating turbidity method - Google Patents
System for testing high-temperature flow characteristics of tantalum melt based on rotating turbidity method Download PDFInfo
- Publication number
- CN117352110B CN117352110B CN202311652741.3A CN202311652741A CN117352110B CN 117352110 B CN117352110 B CN 117352110B CN 202311652741 A CN202311652741 A CN 202311652741A CN 117352110 B CN117352110 B CN 117352110B
- Authority
- CN
- China
- Prior art keywords
- viscosity coefficient
- flow
- coefficient
- tantalum melt
- tantalum
- 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
- 229910052715 tantalum Inorganic materials 0.000 title claims abstract description 284
- GUVRBAGPIYLISA-UHFFFAOYSA-N tantalum atom Chemical compound [Ta] GUVRBAGPIYLISA-UHFFFAOYSA-N 0.000 title claims abstract description 284
- 238000012360 testing method Methods 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012549 training Methods 0.000 claims abstract description 86
- 238000010801 machine learning Methods 0.000 claims abstract description 50
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000013480 data collection Methods 0.000 claims abstract description 7
- 238000004848 nephelometry Methods 0.000 claims description 33
- 239000013078 crystal Substances 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 13
- 239000002994 raw material Substances 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 6
- 238000010008 shearing Methods 0.000 claims description 4
- 238000010998 test method Methods 0.000 claims description 3
- 238000005266 casting Methods 0.000 abstract description 10
- 229910045601 alloy Inorganic materials 0.000 abstract description 8
- 239000000956 alloy Substances 0.000 abstract description 8
- 238000007405 data analysis Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000011056 performance test Methods 0.000 abstract 1
- 238000013528 artificial neural network Methods 0.000 description 32
- 238000004364 calculation method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000005259 measurement Methods 0.000 description 7
- 239000007788 liquid Substances 0.000 description 6
- 229910052751 metal Inorganic materials 0.000 description 6
- 239000002184 metal Substances 0.000 description 6
- 238000004879 turbidimetry Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 5
- 238000000518 rheometry Methods 0.000 description 5
- XKRFYHLGVUSROY-UHFFFAOYSA-N Argon Chemical compound [Ar] XKRFYHLGVUSROY-UHFFFAOYSA-N 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 4
- 238000005304 joining Methods 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 229910000601 superalloy Inorganic materials 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 229910052786 argon Inorganic materials 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 239000000155 melt Substances 0.000 description 2
- 238000005058 metal casting Methods 0.000 description 2
- 238000004021 metal welding Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000009987 spinning Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N11/00—Investigating flow properties of materials, e.g. viscosity, plasticity; Analysing materials by determining flow properties
- G01N11/10—Investigating flow properties of materials, e.g. viscosity, plasticity; Analysing materials by determining flow properties by moving a body within the material
- G01N11/14—Investigating flow properties of materials, e.g. viscosity, plasticity; Analysing materials by determining flow properties by moving a body within the material by using rotary bodies, e.g. vane
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention relates to the technical field of alloy performance test, and discloses a system for testing high-temperature flow characteristics of tantalum melt based on a rotating turbidity method, which comprises a data collection module, a data analysis module and a data analysis module, wherein the data collection module is used for collecting flow coefficient training data and viscosity coefficient training data; the model training module is used for training a first machine learning model and a second machine learning model; the characteristic data acquisition module is used for acquiring viscosity coefficient characteristic data and flow coefficient characteristic data; the viscosity coefficient acquisition module is used for acquiring an initial viscosity coefficient and an actual viscosity coefficient of the tantalum melt; the flow coefficient acquisition module is used for acquiring the flow coefficient of the tantalum melt; the analysis and judgment module is used for comparing and analyzing the flow coefficients and determining the flow performance grade of the tantalum melt; the invention has high test efficiency and low cost, can accurately and rapidly measure the fluidity and the flow performance grade of the high-temperature tantalum melt, and is beneficial to providing a certain data support for the casting industry.
Description
Technical Field
The invention relates to the technical field of alloy performance testing, in particular to a system for testing high-temperature flow characteristics of tantalum melt based on a rotating nephelometry.
Background
Tantalum (Ta) is an important high temperature material with excellent high temperature stability, corrosion resistance and mechanical properties; it has wide application in nuclear energy, aerospace, electronic industry, chemical industry and other fields; however, under high temperature conditions, the performance of tantalum depends on its melt flow characteristics, which is critical to the design and engineering application of the material; the high temperature flow characteristics are important parameters for evaluating the performance of a material under high temperature conditions; this includes viscosity, temperature, rheology, etc. of the melt; the high temperature flow characteristics of tantalum melt are directly related to its engineering applications in high temperature environments, such as the manufacture of high temperature melting vessels, high temperature heating elements, etc.; currently, traditional methods for evaluating high temperature flow characteristics of tantalum melts involve complex experimental conditions and equipment and are not efficient enough; accordingly, there is a need for a new system and method to more accurately and more conveniently test the high temperature flow characteristics of tantalum melt.
At present, although there are some related technical patents in lack of a system or a method for testing the high-temperature flow characteristics of tantalum melt, for example, patent publication No. CN112102896B discloses an alloy composition optimizing method and an alloy composition optimizing device for improving the fluidity of casting superalloy; for another example, patent publication CN112014266a discloses a device for testing dynamic fluidity of high-temperature metal melt and a method for measuring metal melt flow; although the above method can test melt fluidity, research and practical application of the above method and the prior art have found that the above method and the prior art have at least the following partial drawbacks:
(1) The testing efficiency is low, the automation degree is low, the cost is high, the testing process is complex, the fluidity of the high-temperature tantalum melt cannot be accurately and rapidly measured, the flow performance grade of the high-temperature tantalum melt cannot be determined, and certain data support is difficult to provide for the casting industry;
(2) Lack of consideration of influencing factors can easily lead to serious deviation of Gao Wentan melt test results.
Disclosure of Invention
In order to overcome the above-described deficiencies of the prior art, embodiments of the present invention provide a system for testing high temperature flow characteristics of tantalum melt based on spin nephelometry.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a system for testing high temperature flow characteristics of tantalum melt based on spin nephelometry, said system comprising:
the data collection module is used for collecting flow coefficient training data of the tantalum melt and viscosity coefficient training data of the tantalum melt;
the model training module is used for training a first machine learning model for feeding back the flow coefficient of the tantalum melt based on the flow coefficient training data; training a second machine learning model for feeding back the corrected viscosity coefficient of the tantalum melt based on the viscosity coefficient training data;
The characteristic data acquisition module is used for acquiring the viscosity coefficient characteristic data of the tantalum melt and acquiring the flow coefficient characteristic data of the tantalum melt;
the viscosity coefficient acquisition module is used for acquiring an initial viscosity coefficient of the tantalum melt and acquiring an actual viscosity coefficient of the tantalum melt based on the initial viscosity coefficient, the viscosity coefficient characteristic data and a second machine learning model for feeding back the corrected viscosity coefficient of the tantalum melt;
the flow coefficient acquisition module is used for acquiring the flow coefficient of the tantalum melt based on the actual viscosity coefficient, the flow coefficient characteristic data and a first machine learning model for feeding back the flow coefficient of the tantalum melt;
and the analysis and judgment module is used for comparing and analyzing the flow coefficients to determine the flow performance grade of the tantalum melt, wherein the flow performance grade comprises a first flow performance grade, a second flow performance grade and a third flow performance grade.
Further, the flow coefficient training data of the tantalum melt comprise flow coefficient characteristic data and corresponding flow coefficients thereof; the flow coefficient characteristic data comprise tantalum melt quality, tantalum melt density, crystal size, shear stress and viscosity coefficient;
the viscosity coefficient training data of the tantalum melt comprises the components and proportions of raw materials of the tantalum melt, the relation between each degree centigrade temperature and the first viscosity coefficient difference and the relation between each pressure and the second viscosity coefficient difference.
Further, the logic for obtaining the relationship between each degree celsius temperature and the first viscosity coefficient difference is as follows:
a1: measuring a measured viscosity coefficient of the tantalum melt at an ith temperature by a spin nephelometry during the collection stage;
a2: extracting a standard viscosity coefficient of the tantalum melt at a preset standard temperature from system data;
a3: calculating the difference value between the measured viscosity coefficient of the tantalum melt at the ith temperature and the standard viscosity coefficient, and taking the difference value between the measured viscosity coefficient of the tantalum melt at the ith temperature and the standard viscosity coefficient as a first viscosity coefficient difference;
a4: comparing the first viscosity coefficient difference with a preset first viscosity coefficient difference threshold value, if the first viscosity coefficient difference is smaller than the preset first viscosity coefficient difference threshold value, making i=i+1, and returning to the step a1; if the first viscosity coefficient difference is greater than or equal to a preset first viscosity coefficient difference threshold, recording the relation between the ith temperature and the first viscosity coefficient difference, enabling i=i+1, and returning to the step a1;
a5: repeating the steps a1 to a4 until i is equal to the set temperature Q, ending the circulation to obtain the relation between each temperature and the first viscosity coefficient difference, taking the relation between each temperature and the first viscosity coefficient difference as viscosity coefficient training data, wherein i and Q are positive integers which are larger than zero.
Further, the logic for obtaining the relationship between each pressure and the second viscosity coefficient difference is as follows:
b1: measuring the measured viscosity coefficient of the tantalum melt at the j-th pressure by a spin nephelometry during the collection stage;
b2: extracting a standard viscosity coefficient of the tantalum melt under a preset standard pressure in system data;
b3: calculating the difference between the measured viscosity coefficient of the tantalum melt at the j-th pressure and the standard viscosity coefficient, and taking the difference between the measured viscosity coefficient of the tantalum melt at the j-th pressure and the standard viscosity coefficient as a second viscosity coefficient difference;
b4: comparing the second viscosity coefficient difference with a preset second viscosity coefficient difference threshold value, if the second viscosity coefficient difference is smaller than the preset second viscosity coefficient difference threshold value, enabling j=j+1, and returning to the step b1; if the second viscosity coefficient difference is greater than or equal to a preset second viscosity coefficient difference threshold, recording the relationship between the j-th pressure and the second viscosity coefficient difference, enabling j=j+1, and returning to the step b1;
b5: repeating the steps b 1-b 4 until j is equal to the set pressure P, ending the circulation to obtain the relation between each pressure and the second viscosity coefficient difference, taking the relation between each pressure and the second viscosity coefficient difference as viscosity coefficient training data, wherein j and P are positive integers larger than zero.
Further, the logic for obtaining the actual viscosity coefficient of the tantalum melt is as follows:
measuring an initial viscosity coefficient of the tantalum melt by using a rotating turbidity method;
inputting the viscosity coefficient characteristic data into a second machine learning model for feeding back the corrected viscosity coefficient of the tantalum melt to obtain the corrected viscosity coefficient;
and carrying out numerical correction on the initial viscosity coefficient of the tantalum melt by using the corrected viscosity coefficient to obtain the actual viscosity coefficient of the tantalum melt.
Further, the logic for obtaining the flow coefficient of the tantalum melt is as follows:
replacing the actual viscosity coefficient with the viscosity coefficient in the flow coefficient characteristic data;
extracting tantalum melt quality, tantalum melt density, crystal size, shear stress and actual viscosity coefficient from the replaced flow coefficient characteristic data;
the mass, the density, the crystal size, the shearing stress and the actual viscosity coefficient of the tantalum melt are input into a first machine learning model for feeding back the flow coefficient of the tantalum melt, and the flow coefficient of the tantalum melt is obtained.
Further, the comparison analysis of the flow coefficients includes:
setting flow coefficient threshold values Th1 and Th2, wherein Th1 is larger than Th2, and comparing the flow coefficient with the flow coefficient threshold values;
If the flow coefficient is greater than the flow coefficient threshold Th1, dividing the flow performance of the corresponding tantalum melt into a first flow performance level;
if the flow coefficient is smaller than or equal to the flow coefficient threshold Th1 and larger than or equal to the flow coefficient threshold Th2, dividing the flow performance of the corresponding tantalum melt into a second flow performance level;
if the flow coefficient is less than the flow coefficient threshold Th2, the flow properties of the corresponding tantalum melt are classified into a third flow property class.
Further, a method for testing high temperature flow characteristics of tantalum melt based on a spin nephelometry, based on a system implementation of a spin nephelometry based tantalum melt high temperature flow characteristics testing, the method comprising:
s101: collecting flow coefficient training data of the tantalum melt and collecting viscosity coefficient training data of the tantalum melt;
s102: training a first machine learning model for feeding back the flow coefficient of the tantalum melt based on the flow coefficient training data; training a second machine learning model for feeding back the corrected viscosity coefficient of the tantalum melt based on the viscosity coefficient training data;
s103: acquiring viscosity coefficient characteristic data of the tantalum melt and acquiring flow coefficient characteristic data of the tantalum melt;
S104: acquiring an initial viscosity coefficient of the tantalum melt, and acquiring an actual viscosity coefficient of the tantalum melt based on the initial viscosity coefficient, the viscosity coefficient characteristic data and a second machine learning model for feeding back a corrected viscosity coefficient of the tantalum melt;
s105: obtaining the flow coefficient of the tantalum melt based on the actual viscosity coefficient, the flow coefficient characteristic data and a first machine learning model for feeding back the flow coefficient of the tantalum melt;
s106: the flow coefficients are compared and analyzed to determine flow performance levels of the tantalum melt, including a first flow performance level, a second flow performance level, and a third flow performance level.
An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the above-described method for testing tantalum melt high temperature flow characteristics based on a spin nephelometry when executing the computer program.
A computer readable storage medium having stored thereon a computer program which when executed implements the above-described method of testing tantalum melt high temperature flow characteristics based on a spin nephelometry.
Compared with the prior art, the invention has the beneficial effects that:
the application discloses a system for testing high-temperature flow characteristics of tantalum melt based on a rotating turbidity method, which comprises a data collection module, a data analysis module and a data analysis module, wherein the data collection module is used for collecting flow coefficient training data and viscosity coefficient training data; the model training module is used for training a first machine learning model and a second machine learning model; the characteristic data acquisition module is used for acquiring viscosity coefficient characteristic data and flow coefficient characteristic data; the viscosity coefficient acquisition module is used for acquiring an initial viscosity coefficient and an actual viscosity coefficient of the tantalum melt; the flow coefficient acquisition module is used for acquiring the flow coefficient of the tantalum melt; the analysis and judgment module is used for comparing and analyzing the flow coefficients and determining the flow performance grade of the tantalum melt; through the module, the high-temperature tantalum melt flow measuring device can accurately and quickly measure the fluidity of the high-temperature tantalum melt and determine the flow performance grade of the high-temperature tantalum melt, is favorable for providing certain data support for the casting industry, and has low cost, high test efficiency and high automation degree; in addition, the invention corrects the test result according to the consideration of the influence factors, thereby being beneficial to avoiding the deviation of the test result of the high-temperature tantalum melt.
Drawings
FIG. 1 is a schematic diagram of a system for testing the high temperature flow characteristics of tantalum melt based on spin nephelometry according to the present invention;
FIG. 2 is a schematic diagram of a method for testing the high temperature flow characteristics of tantalum melt based on spin nephelometry according to the present invention;
FIG. 3 is a schematic diagram of the principle of measurement by the rotary nephelometry provided by the invention;
fig. 4 is a schematic structural diagram of an electronic device according to the present invention;
fig. 5 is a schematic structural diagram of a computer readable storage medium according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
Example 1
Referring to fig. 2, the disclosure of the present embodiment provides a method for testing high temperature flow characteristics of tantalum melt based on a spin nephelometry, the method comprising:
s101: collecting flow coefficient training data of the tantalum melt and collecting viscosity coefficient training data of the tantalum melt;
Specifically, the flow coefficient training data of the tantalum melt comprises flow coefficient characteristic data and corresponding flow coefficients thereof; the flow coefficient characteristic data comprise tantalum melt quality, tantalum melt density, crystal size, shear stress and viscosity coefficient;
it should be appreciated that: the mass, the density and the crystal size of the tantalum melt are manually set and then input, and the argon pressure is measured by a pressure sensor; the flow coefficient is specifically the flow rate of the tantalum melt, which is obtained based on the prior art equipment, such as a microcomputer tester disclosed in paper ZLWY-1 model casting alloy fluidity microcomputer tester; the source of this document is: limin, zhang Jinsong, xu Lin research on a microcomputer tester for fluidity of ZLWY-1 cast alloy [ J ]. Computer development and application, 2000, (10): 11-12;
wherein the shear stress is calculated by a rheology model, and the formula of the rheology model is expressed as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein: />Is the shear stress in pascals (Pa), K is the rheological constant of the fluid, +.>Is the shear rate of the velocity field, n is the power law exponent;
specifically, the viscosity coefficient is obtained based on measurement and calculation of a rotational turbidity method, and the calculation formula of the viscosity coefficient is as follows:
；
Wherein:is the initial viscosity coefficient value; />、/>The radius of the coaxial inner cylinder and the radius of the coaxial outer cylinder; />The depth of the inner column body immersed in the liquid; />For viscous moment +.>Is the angular velocity of the rotating cylinder; wherein (1)>The method comprises the steps of carrying out a first treatment on the surface of the Wherein: />For cohesive force +.>Is a cylindrical surface area;
it should be noted that: as shown in fig. 3 (schematic diagram of measurement principle of the rotating nephelometry), the measurement principle of the rotating nephelometry is: the device consists of two concentric cylinders with different radiuses, and the outer side of the device is a hollow cylinder (crucible); filling liquid with viscosity to be measured between two concentric cylinders, and then enabling an inner cylinder to rotate at a constant speed by using external force while an outer cylinder keeps static, so that a velocity gradient is generated in the liquid positioned at the radial distance between the two cylinders; due to the action of the viscous force, a moment is generated on the column body to balance the column body;
specifically, the viscosity coefficient training data of the tantalum melt comprises the raw material components and proportions of the tantalum melt, the relation between each degree centigrade temperature and the first viscosity coefficient difference and the relation between each pressure and the second viscosity coefficient difference;
in practice, the acquisition logic for each temperature in degrees celsius versus the first viscosity coefficient difference is as follows:
a1: under an experimental scene, measuring a viscosity coefficient of the tantalum melt at the ith temperature by a rotating turbidimetry;
It should be noted that: the acquisition of the measured viscosity coefficient of the tantalum melt at the ith temperature is the same as the description and the calculation formula of the rotating turbidity method, and is not repeated;
a2: extracting a standard viscosity coefficient of the tantalum melt at a preset standard temperature from system data;
it should be appreciated that: setting a standard viscosity coefficient of the tantalum melt at a standard temperature through manual previous experiment setting;
a3: calculating the difference value between the measured viscosity coefficient of the tantalum melt at the ith temperature and the standard viscosity coefficient, and taking the difference value between the measured viscosity coefficient of the tantalum melt at the ith temperature and the standard viscosity coefficient as a first viscosity coefficient difference;
a4: comparing the first viscosity coefficient difference with a preset first viscosity coefficient difference threshold value, if the first viscosity coefficient difference is smaller than the preset first viscosity coefficient difference threshold value, making i=i+1, and returning to the step a1; if the first viscosity coefficient difference is greater than or equal to a preset first viscosity coefficient difference threshold, recording the relation between the ith temperature and the first viscosity coefficient difference, enabling i=i+1, and returning to the step a1;
a5: repeating the steps a1 to a4 until i is equal to the set temperature Q, ending the circulation to obtain the relation between each temperature and the first viscosity coefficient difference, taking the relation between each temperature and the first viscosity coefficient difference as viscosity coefficient training data, wherein i and Q are positive integers larger than zero;
In practice, the acquisition logic for each pressure versus second viscosity coefficient difference is as follows:
b1: under an experimental scene, measuring the viscosity coefficient of the tantalum melt under the j-th pressure by a rotating turbidimetry;
it should be noted that: the acquisition of the measured viscosity coefficient of the tantalum melt at the j-th pressure is described in the description and calculation formulas above with respect to the spinning turbidimetry, and the details are referred to above;
b2: extracting a standard viscosity coefficient of the tantalum melt under a preset standard pressure in system data;
it should be appreciated that: the standard viscosity coefficient of the tantalum melt at the set standard temperature is the same as that of the tantalum melt at the set standard temperature, and the standard viscosity coefficient of the tantalum melt at the set standard pressure is obtained through artificial pre-experiment setting;
b3: calculating the difference between the measured viscosity coefficient of the tantalum melt at the j-th pressure and the standard viscosity coefficient, and taking the difference between the measured viscosity coefficient of the tantalum melt at the j-th pressure and the standard viscosity coefficient as a second viscosity coefficient difference;
b4: comparing the second viscosity coefficient difference with a preset second viscosity coefficient difference threshold value, if the second viscosity coefficient difference is smaller than the preset second viscosity coefficient difference threshold value, enabling j=j+1, and returning to the step b1; if the second viscosity coefficient difference is greater than or equal to a preset second viscosity coefficient difference threshold, recording the relationship between the j-th pressure and the second viscosity coefficient difference, enabling j=j+1, and returning to the step b1;
b5: repeating the steps b 1-b 4 until j is equal to the set pressure P, ending the circulation to obtain the relation between each pressure and the second viscosity coefficient difference, taking the relation between each pressure and the second viscosity coefficient difference as viscosity coefficient training data, wherein j and P are positive integers larger than zero;
s102: training a first machine learning model for feeding back the flow coefficient of the tantalum melt based on the flow coefficient training data; training a second machine learning model for feeding back the corrected viscosity coefficient of the tantalum melt based on the viscosity coefficient training data;
in implementation, the training logic of the first machine learning model is as follows:
dividing the flow coefficient training data into a flow coefficient training set and a flow coefficient testing set;
constructing a first neural network regression model, inputting the tantalum melt quality, the tantalum melt density, the crystal size, the shear stress and the viscosity coefficient in the flow coefficient training set as the first neural network regression model, outputting the flow coefficient value corresponding to the flow coefficient characteristic data in the flow coefficient training set as the first neural network regression model, and training the first neural network regression model to obtain a trained first neural network regression model;
Performing model verification on the trained first neural network regression model by using the flow coefficient test set, and outputting the trained first neural network regression model with the accuracy greater than or equal to a preset first test accuracy as a first machine learning model;
it should be noted that: the first machine learning model is specifically one of an RNN neural network, a DNN neural network or a CNN neural network model;
in implementation, the training logic of the second machine learning model is as follows:
extracting tantalum melt raw material components and proportions, the relation between each degree centigrade temperature and the first viscosity coefficient difference and the relation between each pressure and the second viscosity coefficient difference in the viscosity coefficient training data;
dividing the raw material components and proportions of the tantalum melt, the relation between each temperature and the first viscosity coefficient difference and the relation between each pressure and the second viscosity coefficient difference into a viscosity coefficient training set and a viscosity coefficient testing set;
constructing a second neural network regression model, inputting the tantalum melt raw material components and proportions, the relation between each degree centigrade temperature and the first viscosity coefficient difference and the relation between each pressure and the second viscosity coefficient difference in the viscosity coefficient training into the second neural network regression model for training, and obtaining a trained second neural network regression model;
Performing model verification on the trained second neural network regression model by using the viscosity coefficient test set, and outputting the trained second neural network regression model with the accuracy greater than or equal to the preset second test accuracy as a second machine learning model;
it should be noted that: the second machine learning model is specifically one of an RNN neural network, a DNN neural network or a CNN neural network model;
s103: acquiring viscosity coefficient characteristic data of the tantalum melt and acquiring flow coefficient characteristic data of the tantalum melt;
specifically, the viscosity coefficient characteristic data of the tantalum melt comprises the raw material components, the proportion, the temperature and the pressure of the tantalum melt;
it should be noted that: the viscosity coefficient characteristic data is acquired by various sensors, including but not limited to temperature sensors, pressure sensors and the like;
s104: acquiring an initial viscosity coefficient of the tantalum melt, and acquiring an actual viscosity coefficient of the tantalum melt based on the initial viscosity coefficient, the viscosity coefficient characteristic data and a second machine learning model for feeding back a corrected viscosity coefficient of the tantalum melt;
in practice, the logic to obtain the actual viscosity coefficient of the tantalum melt is as follows:
Measuring an initial viscosity coefficient of the tantalum melt by using a rotating turbidity method;
it should be noted that: the initial viscosity coefficient of the tantalum melt is obtained in the same manner as described above and calculated by the spin nephelometry, and the details are referred to above;
inputting the viscosity coefficient characteristic data into a second machine learning model for feeding back the corrected viscosity coefficient of the tantalum melt to obtain the corrected viscosity coefficient;
performing numerical correction on the initial viscosity coefficient of the tantalum melt by using the corrected viscosity coefficient to obtain the actual viscosity coefficient of the tantalum melt;
an exemplary illustration is: if the initial viscosity coefficient of the tantalum melt is measured to be 21 pascal seconds (Pa.s) by using a rotational turbidity method, and then the viscosity coefficient characteristic data is input into a second machine learning model for feeding back the corrected viscosity coefficient of the tantalum melt to obtain the corrected viscosity coefficient, wherein the corrected viscosity coefficient is-3 pascal seconds (Pa.s), the actual viscosity coefficient of the tantalum melt obtained by carrying out numerical correction on the initial viscosity coefficient of the tantalum melt by using the corrected viscosity coefficient is 18 pascal seconds (Pa.s);
s105: obtaining the flow coefficient of the tantalum melt based on the actual viscosity coefficient, the flow coefficient characteristic data and a first machine learning model for feeding back the flow coefficient of the tantalum melt;
Specifically, the logic for obtaining the flow coefficient of the tantalum melt is:
replacing the actual viscosity coefficient with the viscosity coefficient in the flow coefficient characteristic data;
extracting tantalum melt quality, tantalum melt density, crystal size, shear stress and actual viscosity coefficient from the replaced flow coefficient characteristic data;
inputting the mass, the density, the crystal size, the shearing stress and the actual viscosity coefficient of the tantalum melt into a first machine learning model for feeding back the flow coefficient of the tantalum melt to obtain the flow coefficient of the tantalum melt;
s106: comparing and analyzing the flow coefficient to determine the flow performance grade of the tantalum melt, wherein the flow performance grade comprises a first flow performance grade, a second flow performance grade and a third flow performance grade;
in an implementation, the comparison analysis of flow coefficients includes:
setting flow coefficient threshold values Th1 and Th2, wherein Th1 is larger than Th2, and comparing the flow coefficient with the flow coefficient threshold values;
if the flow coefficient is greater than the flow coefficient threshold Th1, dividing the flow performance of the corresponding tantalum melt into a first flow performance level;
if the flow coefficient is smaller than or equal to the flow coefficient threshold Th1 and larger than or equal to the flow coefficient threshold Th2, dividing the flow performance of the corresponding tantalum melt into a second flow performance level;
If the flow coefficient is smaller than the flow coefficient threshold Th2, dividing the flow property of the corresponding tantalum melt into a third flow property level;
it should be noted that: the first flow performance level > the second flow performance level > the third flow performance level; the higher the flow performance level, the higher the flow performance of the tantalum melt, which can help the metal to better fill the mold or weld joint for better forming and joining; conversely, the lower the flow performance grade is, the lower the flow performance of the tantalum melt is, and the tantalum melt has certain high-temperature stability;
it should be appreciated that: the quality of the high-temperature flow characteristic is not reflected on the excellent tantalum casting product, and depends on the use object and the use situation of the tantalum casting product; in some cases, higher flow properties may be advantageous; for example, in metal casting and welding processes, higher high temperature flow characteristics can help the metal fill the mold or weld better for better forming and joining; however, even in these cases, too high flow properties may lead to instability and poor results; in other cases, such as where superalloys are used in the aerospace field, it is desirable to have some high temperature stability to avoid losing structural strength of the material at high temperatures; in this case, higher flow performance may not be a primary consideration.
Example 2
Referring to fig. 1, according to the above embodiment 1, a system for testing high temperature flow characteristics of tantalum melt based on a spin nephelometry is disclosed, which comprises:
a data collection module 210 for collecting flow coefficient training data of the tantalum melt and viscosity coefficient training data of the tantalum melt;
specifically, the flow coefficient training data of the tantalum melt comprises flow coefficient characteristic data and corresponding flow coefficients thereof; the flow coefficient characteristic data comprise tantalum melt quality, tantalum melt density, crystal size, shear stress and viscosity coefficient;
it should be appreciated that: the mass, the density and the crystal size of the tantalum melt are manually set and then input, and the argon pressure is measured by a pressure sensor; the flow coefficient is specifically the flow rate of the tantalum melt, which is obtained based on the prior art equipment, such as a microcomputer tester disclosed in paper ZLWY-1 model casting alloy fluidity microcomputer tester; the source of this document is: limin, zhang Jinsong, xu Lin research on a microcomputer tester for fluidity of ZLWY-1 cast alloy [ J ]. Computer development and application, 2000, (10): 11-12;
Wherein the shear stress is calculated by a rheology model, and the formula of the rheology model is expressed as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein: />Is the shear stress in pascals (Pa), K is the rheological constant of the fluid, +.>Is the shear rate of the velocity field, n is the power law exponent;
specifically, the viscosity coefficient is obtained based on measurement and calculation of a rotational turbidity method, and the calculation formula of the viscosity coefficient is as follows:
；
wherein:is the initial viscosity coefficient value; />、/>The radius of the coaxial inner cylinder and the radius of the coaxial outer cylinder; />The depth of the inner column body immersed in the liquid; />For viscous moment +.>Is the angular velocity of the rotating cylinder; wherein (1)>The method comprises the steps of carrying out a first treatment on the surface of the Wherein: />For cohesive force +.>Is a cylindrical surface area;
it should be noted that: as shown in fig. 3 (schematic diagram of measurement principle of the rotating nephelometry), the measurement principle of the rotating nephelometry is: the device consists of two concentric cylinders with different radiuses, and the outer side of the device is a hollow cylinder (crucible); filling liquid with viscosity to be measured between two concentric cylinders, and then enabling an inner cylinder to rotate at a constant speed by using external force while an outer cylinder keeps static, so that a velocity gradient is generated in the liquid positioned at the radial distance between the two cylinders; due to the action of the viscous force, a moment is generated on the column body to balance the column body;
Specifically, the viscosity coefficient training data of the tantalum melt comprises the raw material components and proportions of the tantalum melt, the relation between each degree centigrade temperature and the first viscosity coefficient difference and the relation between each pressure and the second viscosity coefficient difference;
in practice, the acquisition logic for each temperature in degrees celsius versus the first viscosity coefficient difference is as follows:
a1: under an experimental scene, measuring a viscosity coefficient of the tantalum melt at the ith temperature by a rotating turbidimetry;
it should be noted that: the acquisition of the measured viscosity coefficient of the tantalum melt at the ith temperature is the same as the description and the calculation formula of the rotating turbidity method, and is not repeated;
a2: extracting a standard viscosity coefficient of the tantalum melt at a preset standard temperature from system data;
it should be appreciated that: setting a standard viscosity coefficient of the tantalum melt at a standard temperature through manual previous experiment setting;
a3: calculating the difference value between the measured viscosity coefficient of the tantalum melt at the ith temperature and the standard viscosity coefficient, and taking the difference value between the measured viscosity coefficient of the tantalum melt at the ith temperature and the standard viscosity coefficient as a first viscosity coefficient difference;
a4: comparing the first viscosity coefficient difference with a preset first viscosity coefficient difference threshold value, if the first viscosity coefficient difference is smaller than the preset first viscosity coefficient difference threshold value, making i=i+1, and returning to the step a1; if the first viscosity coefficient difference is greater than or equal to a preset first viscosity coefficient difference threshold, recording the relation between the ith temperature and the first viscosity coefficient difference, enabling i=i+1, and returning to the step a1;
a5: repeating the steps a1 to a4 until i is equal to the set temperature Q, ending the circulation to obtain the relation between each temperature and the first viscosity coefficient difference, taking the relation between each temperature and the first viscosity coefficient difference as viscosity coefficient training data, wherein i and Q are positive integers larger than zero;
in practice, the acquisition logic for each pressure versus second viscosity coefficient difference is as follows:
b1: under an experimental scene, measuring the viscosity coefficient of the tantalum melt under the j-th pressure by a rotating turbidimetry;
it should be noted that: the acquisition of the measured viscosity coefficient of the tantalum melt at the j-th pressure is described in the description and calculation formulas above with respect to the spinning turbidimetry, and the details are referred to above;
b2: extracting a standard viscosity coefficient of the tantalum melt under a preset standard pressure in system data;
it should be appreciated that: the standard viscosity coefficient of the tantalum melt at the set standard temperature is the same as that of the tantalum melt at the set standard temperature, and the standard viscosity coefficient of the tantalum melt at the set standard pressure is obtained through artificial pre-experiment setting;
b3: calculating the difference between the measured viscosity coefficient of the tantalum melt at the j-th pressure and the standard viscosity coefficient, and taking the difference between the measured viscosity coefficient of the tantalum melt at the j-th pressure and the standard viscosity coefficient as a second viscosity coefficient difference;
b4: comparing the second viscosity coefficient difference with a preset second viscosity coefficient difference threshold value, if the second viscosity coefficient difference is smaller than the preset second viscosity coefficient difference threshold value, enabling j=j+1, and returning to the step b1; if the second viscosity coefficient difference is greater than or equal to a preset second viscosity coefficient difference threshold, recording the relationship between the j-th pressure and the second viscosity coefficient difference, enabling j=j+1, and returning to the step b1;
b5: repeating the steps b 1-b 4 until j is equal to the set pressure P, ending the circulation to obtain the relation between each pressure and the second viscosity coefficient difference, taking the relation between each pressure and the second viscosity coefficient difference as viscosity coefficient training data, wherein j and P are positive integers larger than zero;
the model training module 220 is configured to train a first machine learning model for feeding back the flow coefficient of the tantalum melt based on the flow coefficient training data; training a second machine learning model for feeding back the corrected viscosity coefficient of the tantalum melt based on the viscosity coefficient training data;
in implementation, the training logic of the first machine learning model is as follows:
dividing the flow coefficient training data into a flow coefficient training set and a flow coefficient testing set;
constructing a first neural network regression model, inputting the tantalum melt quality, the tantalum melt density, the crystal size, the shear stress and the viscosity coefficient in the flow coefficient training set as the first neural network regression model, outputting the flow coefficient value corresponding to the flow coefficient characteristic data in the flow coefficient training set as the first neural network regression model, and training the first neural network regression model to obtain a trained first neural network regression model;
Performing model verification on the trained first neural network regression model by using the flow coefficient test set, and outputting the trained first neural network regression model with the accuracy greater than or equal to a preset first test accuracy as a first machine learning model;
it should be noted that: the first machine learning model is specifically one of an RNN neural network, a DNN neural network or a CNN neural network model;
in implementation, the training logic of the second machine learning model is as follows:
extracting tantalum melt raw material components and proportions, the relation between each degree centigrade temperature and the first viscosity coefficient difference and the relation between each pressure and the second viscosity coefficient difference in the viscosity coefficient training data;
dividing the raw material components and proportions of the tantalum melt, the relation between each temperature and the first viscosity coefficient difference and the relation between each pressure and the second viscosity coefficient difference into a viscosity coefficient training set and a viscosity coefficient testing set;
constructing a second neural network regression model, inputting the tantalum melt raw material components and proportions, the relation between each degree centigrade temperature and the first viscosity coefficient difference and the relation between each pressure and the second viscosity coefficient difference in the viscosity coefficient training into the second neural network regression model for training, and obtaining a trained second neural network regression model;
Performing model verification on the trained second neural network regression model by using the viscosity coefficient test set, and outputting the trained second neural network regression model with the accuracy greater than or equal to the preset second test accuracy as a second machine learning model;
it should be noted that: the second machine learning model is specifically one of an RNN neural network, a DNN neural network or a CNN neural network model;
the feature data obtaining module 230 is configured to obtain viscosity coefficient feature data of the tantalum melt, and obtain flow coefficient feature data of the tantalum melt;
specifically, the viscosity coefficient characteristic data of the tantalum melt comprises the raw material components, the proportion, the temperature and the pressure of the tantalum melt;
it should be noted that: the viscosity coefficient characteristic data is acquired by various sensors, including but not limited to temperature sensors, pressure sensors and the like;
the viscosity coefficient obtaining module 240 is configured to obtain an initial viscosity coefficient of the tantalum melt, and obtain an actual viscosity coefficient of the tantalum melt based on the initial viscosity coefficient, the viscosity coefficient feature data, and a second machine learning model for feeding back a corrected viscosity coefficient of the tantalum melt;
In practice, the logic to obtain the actual viscosity coefficient of the tantalum melt is as follows:
measuring an initial viscosity coefficient of the tantalum melt by using a rotating turbidity method;
it should be noted that: the initial viscosity coefficient of the tantalum melt is obtained in the same manner as described above and calculated by the spin nephelometry, and the details are referred to above;
inputting the viscosity coefficient characteristic data into a second machine learning model for feeding back the corrected viscosity coefficient of the tantalum melt to obtain the corrected viscosity coefficient;
performing numerical correction on the initial viscosity coefficient of the tantalum melt by using the corrected viscosity coefficient to obtain the actual viscosity coefficient of the tantalum melt;
an exemplary illustration is: if the initial viscosity coefficient of the tantalum melt is measured to be 21 pascal seconds (Pa.s) by using a rotational turbidity method, and then the viscosity coefficient characteristic data is input into a second machine learning model for feeding back the corrected viscosity coefficient of the tantalum melt to obtain the corrected viscosity coefficient, wherein the corrected viscosity coefficient is-3 pascal seconds (Pa.s), the actual viscosity coefficient of the tantalum melt obtained by carrying out numerical correction on the initial viscosity coefficient of the tantalum melt by using the corrected viscosity coefficient is 18 pascal seconds (Pa.s);
a flow coefficient obtaining module 250, configured to obtain a flow coefficient of the tantalum melt based on the actual viscosity coefficient, the flow coefficient characteristic data, and a first machine learning model for feeding back the flow coefficient of the tantalum melt;
Specifically, the logic for obtaining the flow coefficient of the tantalum melt is:
replacing the actual viscosity coefficient with the viscosity coefficient in the flow coefficient characteristic data;
extracting tantalum melt quality, tantalum melt density, crystal size, shear stress and actual viscosity coefficient from the replaced flow coefficient characteristic data;
inputting the mass, the density, the crystal size, the shearing stress and the actual viscosity coefficient of the tantalum melt into a first machine learning model for feeding back the flow coefficient of the tantalum melt to obtain the flow coefficient of the tantalum melt;
an analysis decision module 260 for comparing the flow coefficients to determine flow performance levels of the tantalum melt, the flow performance levels including a first flow performance level, a second flow performance level, and a third flow performance level;
in an implementation, the comparison analysis of flow coefficients includes:
setting flow coefficient threshold values Th1 and Th2, wherein Th1 is larger than Th2, and comparing the flow coefficient with the flow coefficient threshold values;
if the flow coefficient is greater than the flow coefficient threshold Th1, dividing the flow performance of the corresponding tantalum melt into a first flow performance level;
if the flow coefficient is smaller than or equal to the flow coefficient threshold Th1 and larger than or equal to the flow coefficient threshold Th2, dividing the flow performance of the corresponding tantalum melt into a second flow performance level;
If the flow coefficient is smaller than the flow coefficient threshold Th2, dividing the flow property of the corresponding tantalum melt into a third flow property level;
it should be noted that: the first flow performance level > the second flow performance level > the third flow performance level; the higher the flow performance level, the higher the flow performance of the tantalum melt, which can help the metal to better fill the mold or weld joint for better forming and joining; conversely, the lower the flow performance grade is, the lower the flow performance of the tantalum melt is, and the tantalum melt has certain high-temperature stability;
it should be appreciated that: the quality of the high-temperature flow characteristic is not reflected on the excellent tantalum casting product, and depends on the use object and the use situation of the tantalum casting product; in some cases, higher flow properties may be advantageous; for example, in metal casting and welding processes, higher high temperature flow characteristics can help the metal fill the mold or weld better for better forming and joining; however, even in these cases, too high flow properties may lead to instability and poor results; in other cases, such as where superalloys are used in the aerospace field, it is desirable to have some high temperature stability to avoid losing structural strength of the material at high temperatures; in this case, higher flow performance may not be a primary consideration.
Example 3
Referring to fig. 4, the disclosure provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the method for testing the high-temperature flow characteristics of the tantalum melt based on the rotating nephelometry when executing the computer program.
Since the electronic device described in this embodiment is an electronic device for implementing a method for testing high-temperature flow characteristics of tantalum melt based on a rotating turbidity method in this embodiment, a method for testing high-temperature flow characteristics of tantalum melt based on a rotating turbidity method in this embodiment is described in this application, and a person skilled in the art can understand the specific implementation of the electronic device in this embodiment and various modifications thereof, so how to implement the method in this embodiment of this application in this electronic device will not be described in detail herein. The electronic device used by those skilled in the art to implement a method for testing the high temperature flow characteristics of tantalum melt based on the spin nephelometry in the embodiments of the present application is within the scope of the protection sought herein.
Example 4
Referring to fig. 5, a computer readable storage medium has a computer program stored thereon, which when executed implements the above-described method for testing tantalum melt high temperature flow characteristics based on a spin turbidity method.
The above formulas are all formulas with dimensionality removed and numerical value calculated, the formulas are formulas with the latest real situation obtained by software simulation by collecting a large amount of data, and preset parameters, weights and threshold selection in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center over a wired network or a wireless network. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely one, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (9)
1. A system for testing high temperature flow characteristics of tantalum melt based on spin nephelometry, said system comprising:
the data collection module is used for collecting flow coefficient training data of the tantalum melt and viscosity coefficient training data of the tantalum melt;
the flow coefficient training data of the tantalum melt comprise flow coefficient characteristic data and corresponding flow coefficients thereof; the flow coefficient characteristic data comprise tantalum melt quality, tantalum melt density, crystal size, shear stress and viscosity coefficient;
the viscosity coefficient training data of the tantalum melt comprises the components and proportions of raw materials of the tantalum melt, the relation between each degree centigrade temperature and the first viscosity coefficient difference and the relation between each pressure and the second viscosity coefficient difference;
the model training module is used for training a first machine learning model for feeding back the flow coefficient of the tantalum melt based on the flow coefficient training data; training a second machine learning model for feeding back the corrected viscosity coefficient of the tantalum melt based on the viscosity coefficient training data;
the characteristic data acquisition module is used for acquiring the viscosity coefficient characteristic data of the tantalum melt and acquiring the flow coefficient characteristic data of the tantalum melt;
The viscosity coefficient acquisition module is used for acquiring an initial viscosity coefficient of the tantalum melt and acquiring an actual viscosity coefficient of the tantalum melt based on the initial viscosity coefficient, the viscosity coefficient characteristic data and a second machine learning model for feeding back the corrected viscosity coefficient of the tantalum melt;
the flow coefficient acquisition module is used for acquiring the flow coefficient of the tantalum melt based on the actual viscosity coefficient, the flow coefficient characteristic data and a first machine learning model for feeding back the flow coefficient of the tantalum melt;
and the analysis and judgment module is used for comparing and analyzing the flow coefficients to determine the flow performance grade of the tantalum melt, wherein the flow performance grade comprises a first flow performance grade, a second flow performance grade and a third flow performance grade.
2. The system for testing high temperature flow characteristics of tantalum melt based on rotary nephelometry according to claim 1, wherein said obtaining logic for each degree celsius relationship to the first viscosity coefficient difference is as follows:
a1: measuring a measured viscosity coefficient of the tantalum melt at an ith temperature by a spin nephelometry during the collection stage;
a2: extracting a standard viscosity coefficient of the tantalum melt at a preset standard temperature from system data;
a3: calculating the difference value between the measured viscosity coefficient of the tantalum melt at the ith temperature and the standard viscosity coefficient, and taking the difference value between the measured viscosity coefficient of the tantalum melt at the ith temperature and the standard viscosity coefficient as a first viscosity coefficient difference;
a4: comparing the first viscosity coefficient difference with a preset first viscosity coefficient difference threshold value, if the first viscosity coefficient difference is smaller than the preset first viscosity coefficient difference threshold value, making i=i+1, and returning to the step a1; if the first viscosity coefficient difference is greater than or equal to a preset first viscosity coefficient difference threshold, recording the relation between the ith temperature and the first viscosity coefficient difference, enabling i=i+1, and returning to the step a1;
a5: repeating the steps a1 to a4 until i is equal to the set temperature Q, ending the circulation to obtain the relation between each temperature and the first viscosity coefficient difference, taking the relation between each temperature and the first viscosity coefficient difference as viscosity coefficient training data, wherein i and Q are positive integers which are larger than zero.
3. The system for testing high temperature flow characteristics of tantalum melt based on rotary nephelometry according to claim 2, wherein said obtaining logic for each pressure versus second viscosity coefficient difference is as follows:
b1: measuring the measured viscosity coefficient of the tantalum melt at the j-th pressure by a spin nephelometry during the collection stage;
b2: extracting a standard viscosity coefficient of the tantalum melt under a preset standard pressure in system data;
b3: calculating the difference between the measured viscosity coefficient of the tantalum melt at the j-th pressure and the standard viscosity coefficient, and taking the difference between the measured viscosity coefficient of the tantalum melt at the j-th pressure and the standard viscosity coefficient as a second viscosity coefficient difference;
b4: comparing the second viscosity coefficient difference with a preset second viscosity coefficient difference threshold value, if the second viscosity coefficient difference is smaller than the preset second viscosity coefficient difference threshold value, enabling j=j+1, and returning to the step b1; if the second viscosity coefficient difference is greater than or equal to a preset second viscosity coefficient difference threshold, recording the relationship between the j-th pressure and the second viscosity coefficient difference, enabling j=j+1, and returning to the step b1;
b5: repeating the steps b 1-b 4 until j is equal to the set pressure P, ending the circulation to obtain the relation between each pressure and the second viscosity coefficient difference, taking the relation between each pressure and the second viscosity coefficient difference as viscosity coefficient training data, wherein j and P are positive integers larger than zero.
4. A system for testing the high temperature flow characteristics of a tantalum melt based on spin nephelometry according to claim 3, wherein said logic for obtaining the actual viscosity coefficient of the tantalum melt is as follows:
Measuring an initial viscosity coefficient of the tantalum melt by using a rotating turbidity method;
inputting the viscosity coefficient characteristic data into a second machine learning model for feeding back the corrected viscosity coefficient of the tantalum melt to obtain the corrected viscosity coefficient;
and carrying out numerical correction on the initial viscosity coefficient of the tantalum melt by using the corrected viscosity coefficient to obtain the actual viscosity coefficient of the tantalum melt.
5. The system for testing high temperature flow characteristics of tantalum melt based on rotary nephelometry according to claim 4, wherein said logic for obtaining flow coefficients of tantalum melt comprises:
replacing the actual viscosity coefficient with the viscosity coefficient in the flow coefficient characteristic data;
extracting tantalum melt quality, tantalum melt density, crystal size, shear stress and actual viscosity coefficient from the replaced flow coefficient characteristic data;
the mass, the density, the crystal size, the shearing stress and the actual viscosity coefficient of the tantalum melt are input into a first machine learning model for feeding back the flow coefficient of the tantalum melt, and the flow coefficient of the tantalum melt is obtained.
6. The system for testing high temperature flow characteristics of tantalum melt based on rotary nephelometry according to claim 5, wherein said comparison of flow coefficients comprises:
Setting flow coefficient threshold values Th1 and Th2, wherein Th1 is larger than Th2, and comparing the flow coefficient with the flow coefficient threshold values;
if the flow coefficient is greater than the flow coefficient threshold Th1, dividing the flow performance of the corresponding tantalum melt into a first flow performance level;
if the flow coefficient is smaller than or equal to the flow coefficient threshold Th1 and larger than or equal to the flow coefficient threshold Th2, dividing the flow performance of the corresponding tantalum melt into a second flow performance level;
if the flow coefficient is less than the flow coefficient threshold Th2, the flow properties of the corresponding tantalum melt are classified into a third flow property class.
7. A method of testing tantalum melt high temperature flow characteristics based on a spin nephelometry, based on a system implementation of testing tantalum melt high temperature flow characteristics based on a spin nephelometry according to any of claims 1-6, said method comprising:
s101: collecting flow coefficient training data of the tantalum melt and collecting viscosity coefficient training data of the tantalum melt;
the flow coefficient training data of the tantalum melt comprise flow coefficient characteristic data and corresponding flow coefficients thereof; the flow coefficient characteristic data comprise tantalum melt quality, tantalum melt density, crystal size, shear stress and viscosity coefficient;
The viscosity coefficient training data of the tantalum melt comprises the components and proportions of raw materials of the tantalum melt, the relation between each degree centigrade temperature and the first viscosity coefficient difference and the relation between each pressure and the second viscosity coefficient difference;
s102: training a first machine learning model for feeding back the flow coefficient of the tantalum melt based on the flow coefficient training data; training a second machine learning model for feeding back the corrected viscosity coefficient of the tantalum melt based on the viscosity coefficient training data;
s103: acquiring viscosity coefficient characteristic data of the tantalum melt and acquiring flow coefficient characteristic data of the tantalum melt;
s104: acquiring an initial viscosity coefficient of the tantalum melt, and acquiring an actual viscosity coefficient of the tantalum melt based on the initial viscosity coefficient, the viscosity coefficient characteristic data and a second machine learning model for feeding back a corrected viscosity coefficient of the tantalum melt;
s105: obtaining the flow coefficient of the tantalum melt based on the actual viscosity coefficient, the flow coefficient characteristic data and a first machine learning model for feeding back the flow coefficient of the tantalum melt;
s106: the flow coefficients are compared and analyzed to determine flow performance levels of the tantalum melt, including a first flow performance level, a second flow performance level, and a third flow performance level.
8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the computer program, implements a method of testing tantalum melt high temperature flow characteristics based on a spin nephelometry as claimed in claim 7.
9. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, which when executed implements a method for testing tantalum melt high temperature flow characteristics based on a spin turbidity method according to claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311652741.3A CN117352110B (en) | 2023-12-05 | 2023-12-05 | System for testing high-temperature flow characteristics of tantalum melt based on rotating turbidity method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311652741.3A CN117352110B (en) | 2023-12-05 | 2023-12-05 | System for testing high-temperature flow characteristics of tantalum melt based on rotating turbidity method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117352110A CN117352110A (en) | 2024-01-05 |
| CN117352110B true CN117352110B (en) | 2024-02-13 |
Family
ID=89367032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311652741.3A Active CN117352110B (en) | 2023-12-05 | 2023-12-05 | System for testing high-temperature flow characteristics of tantalum melt based on rotating turbidity method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117352110B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109336380A (en) * | 2018-12-04 | 2019-02-15 | 秦皇岛玻璃工业研究设计院有限公司 | A kind of ultra-clear glasses and its production method and special equipment |
| CN112417583A (en) * | 2020-08-28 | 2021-02-26 | 上海交通大学 | Quantitative prediction method for loose defect of large complex thin-wall high-temperature alloy casting |
| CN114970320A (en) * | 2022-04-27 | 2022-08-30 | 中南大学 | Method and system for dynamically monitoring temperature field of aluminum electrolysis cell |
| CN115584375A (en) * | 2022-11-01 | 2023-01-10 | 唐山惠唐物联科技有限公司 | Method and system for automatic tapping of converter based on image recognition |
| CN116913404A (en) * | 2023-07-17 | 2023-10-20 | 燕山大学 | Machine learning-based integral die-casting heat treatment-free aluminum alloy component design method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11915105B2 (en) * | 2019-02-05 | 2024-02-27 | Imagars Llc | Machine learning to accelerate alloy design |
-
2023
- 2023-12-05 CN CN202311652741.3A patent/CN117352110B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109336380A (en) * | 2018-12-04 | 2019-02-15 | 秦皇岛玻璃工业研究设计院有限公司 | A kind of ultra-clear glasses and its production method and special equipment |
| CN112417583A (en) * | 2020-08-28 | 2021-02-26 | 上海交通大学 | Quantitative prediction method for loose defect of large complex thin-wall high-temperature alloy casting |
| CN114970320A (en) * | 2022-04-27 | 2022-08-30 | 中南大学 | Method and system for dynamically monitoring temperature field of aluminum electrolysis cell |
| CN115584375A (en) * | 2022-11-01 | 2023-01-10 | 唐山惠唐物联科技有限公司 | Method and system for automatic tapping of converter based on image recognition |
| CN116913404A (en) * | 2023-07-17 | 2023-10-20 | 燕山大学 | Machine learning-based integral die-casting heat treatment-free aluminum alloy component design method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117352110A (en) | 2024-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cayeux | Time, pressure and temperature dependent rheological properties of drilling fluids and their automatic measurements | |
| CN105928833A (en) | Correction method for rheological test data of coaxial cylinder rheometer | |
| US11035772B2 (en) | Measurement of fluid properties | |
| CN108181205A (en) | A kind of oil-soluble polymers turbulent flow drag reduction Installation for Efficiency Measurement of Hydro | |
| CN105004749B (en) | Solid-liquid phase change material melting heat transfer performance parameter testing system and its method | |
| CN108319664A (en) | A kind of dam and the recognition methods of project security monitoring data error and system | |
| CN117352110B (en) | System for testing high-temperature flow characteristics of tantalum melt based on rotating turbidity method | |
| CN109100051A (en) | The temperature correction and device of the dynamic response of temperature sensor | |
| JP7346070B2 (en) | How to determine the viscosity of a substance using a rotational viscometer | |
| Bürger et al. | A review of flux identification methods for models of sedimentation | |
| CN116067838A (en) | Drilling fluid rheological measurement while drilling method based on tubular viscometer system | |
| Medina-Bañuelos et al. | Rheo-PIV of yield-stress fluids in a 3D-printed fractal vane-in-cup geometry | |
| CN117538013A (en) | Flow resistance measuring method for viscoelastic fluid of complex-structure pipeline | |
| CN105181526B (en) | The detection method of viscosity in sizing agent production process | |
| Chan et al. | Perspective on edge fracture | |
| Ofoche et al. | Predictive modelling of drilling fluid rheology: numerical, analytical, experimental and statistical studies of marsh funnel flow | |
| Yue et al. | Experimental study and numerical simulation of viscosity measurement of solid propellant slurry by press bar‐fall ball viscometer | |
| CN115452062A (en) | Flow measuring method, flow measuring device, computer equipment and storage medium | |
| CN110672435B (en) | Ocean soil dynamic shear modulus test analysis method and device | |
| Li et al. | Numerical estimation of hemolysis from the point of view of signal and system | |
| CN107063169A (en) | A kind of method of size changing amount under the conditions of quantitative assessment metal material cold cycling | |
| CN206583571U (en) | A kind of pull pressure sensor caliberating device | |
| CN107064205A (en) | A kind of method of change in size speed under the conditions of quantitative assessment metal material cold cycling | |
| CN106124744A (en) | A kind of method testing coal tar pitch rheological characteristic | |
| Wein et al. | AWS rotational viscometry of polysaccharide solutions using a novel KK sensor |
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 |