CN115595667A - Intelligent growth method, system, equipment and storage medium for cadmium zinc telluride crystals - Google Patents
Intelligent growth method, system, equipment and storage medium for cadmium zinc telluride crystals Download PDFInfo
- Publication number
- CN115595667A CN115595667A CN202211282330.5A CN202211282330A CN115595667A CN 115595667 A CN115595667 A CN 115595667A CN 202211282330 A CN202211282330 A CN 202211282330A CN 115595667 A CN115595667 A CN 115595667A
- Authority
- CN
- China
- Prior art keywords
- zinc telluride
- cadmium zinc
- crystal
- growth
- temperature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000013078 crystal Substances 0.000 title claims abstract description 191
- QWUZMTJBRUASOW-UHFFFAOYSA-N cadmium tellanylidenezinc Chemical compound [Zn].[Cd].[Te] QWUZMTJBRUASOW-UHFFFAOYSA-N 0.000 title claims abstract description 140
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000004088 simulation Methods 0.000 claims abstract description 19
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 229910052793 cadmium Inorganic materials 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims description 19
- 239000007788 liquid Substances 0.000 claims description 15
- 238000012512 characterization method Methods 0.000 claims description 14
- 238000012544 monitoring process Methods 0.000 claims description 14
- 239000011701 zinc Substances 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 229910052714 tellurium Inorganic materials 0.000 claims description 10
- PORWMNRCUJJQNO-UHFFFAOYSA-N tellurium atom Chemical compound [Te] PORWMNRCUJJQNO-UHFFFAOYSA-N 0.000 claims description 10
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 claims description 9
- 239000010453 quartz Substances 0.000 claims description 8
- 238000005204 segregation Methods 0.000 claims description 7
- HCHKCACWOHOZIP-UHFFFAOYSA-N Zinc Chemical compound [Zn] HCHKCACWOHOZIP-UHFFFAOYSA-N 0.000 claims description 6
- 239000002244 precipitate Substances 0.000 claims description 6
- 239000000047 product Substances 0.000 claims description 6
- 229910052725 zinc Inorganic materials 0.000 claims description 6
- 238000002834 transmittance Methods 0.000 claims description 4
- 229910004611 CdZnTe Inorganic materials 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 238000012549 training Methods 0.000 description 9
- 238000012360 testing method Methods 0.000 description 7
- 238000012706 support-vector machine Methods 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000017525 heat dissipation Effects 0.000 description 3
- 238000010438 heat treatment Methods 0.000 description 3
- MCMNRKCIXSYSNV-UHFFFAOYSA-N Zirconium dioxide Chemical compound O=[Zr]=O MCMNRKCIXSYSNV-UHFFFAOYSA-N 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000002109 crystal growth method Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- PXXKQOPKNFECSZ-UHFFFAOYSA-N platinum rhodium Chemical compound [Rh].[Pt] PXXKQOPKNFECSZ-UHFFFAOYSA-N 0.000 description 2
- 229910052580 B4C Inorganic materials 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- INAHAJYZKVIDIZ-UHFFFAOYSA-N boron carbide Chemical compound B12B3B4C32B41 INAHAJYZKVIDIZ-UHFFFAOYSA-N 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 229910002804 graphite Inorganic materials 0.000 description 1
- 239000010439 graphite Substances 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- HBMJWWWQQXIZIP-UHFFFAOYSA-N silicon carbide Chemical compound [Si+]#[C-] HBMJWWWQQXIZIP-UHFFFAOYSA-N 0.000 description 1
- 229910010271 silicon carbide Inorganic materials 0.000 description 1
- 238000007711 solidification Methods 0.000 description 1
- 230000008023 solidification Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Images
Classifications
-
- C—CHEMISTRY; METALLURGY
- C30—CRYSTAL GROWTH
- C30B—SINGLE-CRYSTAL GROWTH; UNIDIRECTIONAL SOLIDIFICATION OF EUTECTIC MATERIAL OR UNIDIRECTIONAL DEMIXING OF EUTECTOID MATERIAL; REFINING BY ZONE-MELTING OF MATERIAL; PRODUCTION OF A HOMOGENEOUS POLYCRYSTALLINE MATERIAL WITH DEFINED STRUCTURE; SINGLE CRYSTALS OR HOMOGENEOUS POLYCRYSTALLINE MATERIAL WITH DEFINED STRUCTURE; AFTER-TREATMENT OF SINGLE CRYSTALS OR A HOMOGENEOUS POLYCRYSTALLINE MATERIAL WITH DEFINED STRUCTURE; APPARATUS THEREFOR
- C30B29/00—Single crystals or homogeneous polycrystalline material with defined structure characterised by the material or by their shape
- C30B29/10—Inorganic compounds or compositions
- C30B29/46—Sulfur-, selenium- or tellurium-containing compounds
- C30B29/48—AIIBVI compounds wherein A is Zn, Cd or Hg, and B is S, Se or Te
-
- C—CHEMISTRY; METALLURGY
- C30—CRYSTAL GROWTH
- C30B—SINGLE-CRYSTAL GROWTH; UNIDIRECTIONAL SOLIDIFICATION OF EUTECTIC MATERIAL OR UNIDIRECTIONAL DEMIXING OF EUTECTOID MATERIAL; REFINING BY ZONE-MELTING OF MATERIAL; PRODUCTION OF A HOMOGENEOUS POLYCRYSTALLINE MATERIAL WITH DEFINED STRUCTURE; SINGLE CRYSTALS OR HOMOGENEOUS POLYCRYSTALLINE MATERIAL WITH DEFINED STRUCTURE; AFTER-TREATMENT OF SINGLE CRYSTALS OR A HOMOGENEOUS POLYCRYSTALLINE MATERIAL WITH DEFINED STRUCTURE; APPARATUS THEREFOR
- C30B11/00—Single-crystal growth by normal freezing or freezing under temperature gradient, e.g. Bridgman-Stockbarger method
- C30B11/006—Controlling or regulating
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/10—Analysis or design of chemical reactions, syntheses or processes
Landscapes
- Chemical & Material Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Engineering & Computer Science (AREA)
- Organic Chemistry (AREA)
- Materials Engineering (AREA)
- Metallurgy (AREA)
- Inorganic Chemistry (AREA)
- Analytical Chemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Theoretical Computer Science (AREA)
- Crystals, And After-Treatments Of Crystals (AREA)
Abstract
The invention discloses a tellurium-zinc-cadmium crystal intelligent growth method, a system, equipment and a storage medium, wherein the method comprises the following steps: the terminal receives the initial growth conditions of the cadmium zinc telluride crystal sent by the microcomputer, and the initial growth conditions of the cadmium zinc telluride crystal are input into a crystal growth model for calculation to obtain temperature parameters required by the growth of the cadmium zinc telluride crystal; the terminal judges whether the high-quality cadmium zinc telluride crystal can be grown under the temperature parameter by carrying out simulation processing on the initial growth condition of the cadmium zinc telluride crystal and the temperature parameter; when the high-quality cadmium zinc telluride crystal can be grown under the temperature parameter, the terminal sends the temperature parameter to the microcomputer, so that the microcomputer controls the temperature information in the cadmium zinc telluride crystal growth furnace according to the temperature parameter.
Description
Technical Field
The invention relates to the technical field, in particular to a tellurium-zinc-cadmium crystal intelligent growth method, a system, equipment and a storage medium.
Background
Cadmium zinc telluride (Cd) 1-x Zn x Te, CZT) is an important group II-VI ternary compound semiconductor that is widely used to fabricate nuclear radiation detectors because of its good photoelectric properties. In addition, the lattice constant of the tellurium-zinc-cadmium crystal can be continuously regulated and controlled along with the change of the zinc content, so that the tellurium-zinc-cadmium crystal is completely matched with the lattice of tellurium-cadmium-Mercury (MCT) with any component, and has higher infrared transmittance, so that the tellurium-zinc-cadmium is an optimal substrate material for epitaxial growth of the tellurium-cadmium-mercury.
The cadmium zinc telluride has the defects of difficult growth, poor growth repeatability and difficult growth of high-quality cadmium zinc telluride crystals at lower cost due to the factors of high growth temperature, low thermal conductivity, small stacking fault energy, high Cd component equilibrium vapor pressure, large Zn segregation coefficient, larger difference of temperature parameters required by the growth of cadmium zinc telluride crystals with different zinc values and the like.
Disclosure of Invention
The technical problem solved by the scheme provided by the embodiment of the invention is that the growth of the cadmium zinc telluride crystal cannot intelligently provide proper temperature parameters, so that the cadmium zinc telluride crystal has low single crystal rate and poor growth repeatability, and the high-quality cadmium zinc telluride crystal is difficult to grow at low cost.
The intelligent growth method of the cadmium zinc telluride crystal provided by the embodiment of the invention comprises the following steps:
the terminal receives the initial growth conditions of the cadmium zinc telluride crystal sent by the microcomputer, and inputs the initial growth conditions of the cadmium zinc telluride crystal into a crystal growth model for calculation to obtain temperature parameters required by the growth of the cadmium zinc telluride crystal;
the terminal judges whether the high-quality cadmium zinc telluride crystal can be grown under the temperature parameter by carrying out simulation processing on the initial growth condition of the cadmium zinc telluride crystal and the temperature parameter;
when the high-quality cadmium zinc telluride crystal can grow under the temperature parameter, the terminal sends the temperature parameter to the microcomputer, so that the microcomputer controls the temperature information in the cadmium zinc telluride crystal growth furnace according to the temperature parameter.
According to the embodiment of the invention, the intelligent growth system of the cadmium zinc telluride crystal comprises:
the terminal is used for receiving the initial growth conditions of the cadmium zinc telluride crystal sent by the microcomputer and inputting the initial growth conditions of the cadmium zinc telluride crystal into the crystal growth model for calculation to obtain temperature parameters required by the growth of the cadmium zinc telluride crystal; carrying out simulation treatment on the initial growth conditions of the cadmium zinc telluride crystal and the temperature parameters, and judging whether a high-quality cadmium zinc telluride crystal can grow under the temperature parameters; when the high-quality cadmium zinc telluride crystals can grow under the temperature parameters, the temperature parameters are sent to the microcomputer;
and the microcomputer is used for sending the initial growth conditions of the cadmium zinc telluride crystal to the terminal, receiving the temperature parameters sent by the terminal and controlling the temperature information in the cadmium zinc telluride crystal growth furnace according to the temperature parameters.
According to an embodiment of the present invention, there is provided an electronic apparatus including: a memory; a processor; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement a cadmium zinc telluride crystal smart growth method.
A computer-readable storage medium according to an embodiment of the present invention is provided, on which a computer program is stored; the computer program is executed by a processor to realize an intelligent growth method of the cadmium zinc telluride crystal.
According to the scheme provided by the embodiment of the invention, the method has the characteristics of big data analysis, crystal growth numerical simulation, intelligent growth, centralized control of a crystal growth furnace, high-precision and high-stability temperature control and the like, and the aim of growing high-quality cadmium zinc telluride crystals at low cost is fulfilled.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow chart of an intelligent CdZnTe crystal growth method provided by the embodiment of the invention;
FIG. 2 is a schematic diagram of an intelligent CdZnTe crystal growth system provided by an embodiment of the present invention;
FIG. 3 is a flow chart of an intelligent CdZnTe crystal growth method provided by the embodiment of the invention;
fig. 4 is a schematic diagram of an intelligent growth system for cadmium zinc telluride crystals provided by an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, and it should be understood that the preferred embodiments described below are only for the purpose of illustrating and explaining the present invention, and are not to be construed as limiting the present invention.
Fig. 1 is a flowchart of an intelligent growth method of a cadmium zinc telluride crystal according to an embodiment of the present invention, as shown in fig. 1, including:
step S101: the terminal receives the initial growth conditions of the cadmium zinc telluride crystal sent by the microcomputer, and the initial growth conditions of the cadmium zinc telluride crystal are input into a crystal growth model for calculation to obtain temperature parameters required by the growth of the cadmium zinc telluride crystal;
step S102: the terminal judges whether the high-quality cadmium zinc telluride crystal can be grown under the temperature parameter by carrying out simulation processing on the initial growth condition of the cadmium zinc telluride crystal and the temperature parameter;
step S103: when the high-quality cadmium zinc telluride crystal can be grown under the temperature parameter, the terminal sends the temperature parameter to the microcomputer, so that the microcomputer controls the temperature information in the cadmium zinc telluride crystal growth furnace according to the temperature parameter.
Specifically, the initial growth conditions of the cadmium zinc telluride crystal comprise: the method comprises the following steps of (1) determining the zinc content in cadmium zinc telluride, the quality of cadmium zinc telluride polycrystal used for growing cadmium zinc telluride crystals, the type of a crucible, the size of the crucible, the size of a quartz tube, the type of a support and a growing method; the temperature parameters include: a temperature-raising program, a temperature-lowering program and a temperature gradient. Wherein the zinc content in the tellurium-zinc-cadmium is specifically 0-30%. The quality of the cadmium zinc telluride polycrystal for growing the cadmium zinc telluride crystal is specifically 0-10 kg. The crucible types include quartz crucibles, boron carbide crucibles, graphite crucibles. The crucible size comprises crucible width, crucible length and crucible wall thickness. The size of the quartz tube comprises the diameter of the quartz tube, the length of the quartz tube, the wall thickness of the quartz tube and the size of a shouldering angle. The support species include silicon carbide, zirconia. The growth method comprises a Bridgman method, a moving heater method and a vertical gradient solidification method.
Further, the step of judging whether the high-quality cadmium zinc telluride crystal can be grown under the temperature parameter by the terminal through simulation processing of the initial growth condition of the cadmium zinc telluride crystal and the temperature parameter comprises the following steps: the terminal carries out simulation processing on the initial growth conditions and the temperature parameters of the cadmium zinc telluride crystal to obtain the shape of a solid-liquid interface, the segregation coefficient of Zn and the temperature field distribution in the growth process of the cadmium zinc telluride crystal; and when the solid-liquid interface shape in the growth process of the cadmium zinc telluride crystal is a plane or a micro convex surface, the segregation coefficient of Zn is close to 1, and the temperature field distribution is a proper temperature gradient, the terminal judges that the high-quality cadmium zinc telluride crystal can be grown under the temperature parameter.
The embodiment of the invention also comprises the following steps: when the high-quality cadmium zinc telluride crystal cannot be grown under the temperature parameter, the terminal retrains the crystal growth model to obtain a trained crystal growth model; the terminal obtains temperature parameters required by the growth of the cadmium zinc telluride crystal by using the trained crystal growth model, and sends the temperature parameters to the microcomputer when the high-quality cadmium zinc telluride crystal can be grown under the temperature parameters.
The embodiment of the invention also comprises the following steps: and establishing a crystal growth model containing the initial growth conditions, the temperature parameters and the characterization data of the cadmium zinc telluride crystal.
The embodiment of the invention also comprises the following steps: in the growth process of the cadmium zinc telluride crystal, the microcomputer monitors the growth process of the cadmium zinc telluride crystal in real time to obtain cadmium zinc telluride crystal growth monitoring data, and periodically sends the cadmium zinc telluride crystal growth monitoring data to the terminal; the terminal predicts whether a high-quality cadmium zinc telluride crystal can grow under the monitoring data of the cadmium zinc telluride crystal growth by analyzing the monitoring data of the cadmium zinc telluride crystal growth; and when the high-quality cadmium zinc telluride crystal cannot be grown under the cadmium zinc telluride crystal growth monitoring data, the terminal calculates the current temperature parameter required in the current cadmium zinc telluride crystal growth process according to the cadmium zinc telluride crystal growth monitoring data and the crystal growth model, and sends the current temperature parameter to the microcomputer.
Specifically, the characterization data includes resistivity, leakage current, dislocation density, tellurium precipitate size, tellurium precipitate density, tellurium inclusion size, infrared transmittance, electron mobility-lifetime product, hole mobility-lifetime product.
Fig. 2 is a schematic diagram of an intelligent growth system of cadmium zinc telluride crystals provided by an embodiment of the present invention, as shown in fig. 2, including: the terminal 201 is used for receiving the initial growth conditions of the cadmium zinc telluride crystal sent by the microcomputer, and inputting the initial growth conditions of the cadmium zinc telluride crystal into the crystal growth model for calculation to obtain temperature parameters required by the growth of the cadmium zinc telluride crystal; carrying out simulation treatment on the initial growth conditions of the cadmium zinc telluride crystal and the temperature parameters, and judging whether a high-quality cadmium zinc telluride crystal can grow under the temperature parameters; when the high-quality cadmium zinc telluride crystal can grow under the temperature parameter, sending the temperature parameter to the microcomputer; and the microcomputer 202 is used for sending the initial growth conditions of the cadmium zinc telluride crystal to the terminal, receiving the temperature parameters sent by the terminal, and controlling the temperature information in the cadmium zinc telluride crystal growth furnace according to the temperature parameters.
An electronic device provided in an embodiment of the present application includes: a memory; a processor; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement a cadmium zinc telluride crystal smart growth method.
A computer-readable storage medium provided in an embodiment of the present application has a computer program stored thereon; the computer program is executed by a processor to realize an intelligent growth method of the cadmium zinc telluride crystal.
As shown in fig. 3, a database is established by the initial growth conditions, temperature parameters and characterization data of a large number of cadmium zinc telluride crystals. The terminal carries out statistical learning through a large number of initial growth conditions, temperature parameters and characterization data of the cadmium zinc telluride crystal in the database, a model for coupling the initial growth conditions, the temperature parameters and the characterization data is concluded, the model can intelligently output proper temperature parameters for the cadmium zinc telluride crystal growth according to the input initial growth conditions, and the temperature parameters and the input initial growth conditions are simulated through crystal growth numerical simulation software built in the terminal, so that the solid-liquid interface shape, the segregation coefficient of Zn and the temperature field distribution in the growth process of the cadmium zinc telluride crystal are obtained, and whether the temperature parameters are reasonable or not is judged. If the solid-liquid interface shape in the simulation result is a plane or a micro-convex surface, the segregation coefficient of Zn is close to 1 and the temperature gradient is proper, the terminal sends the temperature parameter to the microcomputer through the data exchanger; otherwise, the model is deduced again until the proper temperature parameters are obtained.
The terminal is internally provided with a Programmable Logic Controller (PLC), an LIBSVM software package and CGSim Basic simulation software.
Wherein, the temperature gradient calculation formula is as follows:
n is a unit vector in the normal direction of the isotherm,
is the directional derivative of the temperature along the normal direction.
The temperature gradient value, the temperature raising program and the temperature lowering program are intelligently given by the terminal through a coupled model and a simulation result according to the crystal growth condition input by the microcomputer and are input to the microcomputer through a data exchanger.
The terminal performs statistical learning specifically comprises the following steps:
establishing a database by using the initial growth conditions and temperature parameters of the cadmium zinc telluride crystal and the corresponding characterization data of the cadmium zinc telluride crystal, and applying a support vectorA machine induction model. A Support Vector Machine (SVM) is a two-class model. Given a training set D = { (x) 1 ,y 1 ),(x 2 ,y 2 )...(x m ,y m ) Find a hyperplane S:
separating the samples in the training set D by using the quality of the wafer as a standard, wherein the quality of the wafer is judged by the standard of the characterization data, and if the volume resistivity rho is more than or equal to 10 10 Omega cm, leakage current less than or equal to 100nA, dislocation density less than 10 4 cm -2 The size of tellurium precipitate is less than 25nm, and the density of tellurium precipitate is less than 10 5 cm -3 Tellurium inclusion density < 1X 10 5 cm -3 Tellurium inclusion size less than 5 μm, infrared transmittance greater than 60%, electron mobility-lifetime product>10 -3 cm 2 V, hole mobility-lifetime product>10 -5 cm 2 The quality of the wafer is judged to be high, otherwise, the quality is judged to be low, so that a model for coupling the initial growth condition, the temperature parameter and the characterization data is summarized, and the internal relation between the initial growth condition, the temperature parameter and the crystal quality is found.
Firstly, a set-out method is used for dividing a sample into two mutually exclusive two-part collections, so that the problem that the model brings deviation due to data inconsistency in the process of dividing a test set and a training set is avoided, the consistency of the data distribution of the test set and the training set is ensured as far as possible in the process of dividing the test set and the training set, namely, the positive proportion and the negative proportion of the test set and the training set are the same.
4/5 samples in the established database are used as a training set, and the rest samples are used as a testing set. Suppose a training sample set D = { (x) 1 ,y 1 ),(x 2 ,y 2 ),…,(x n ,y n ) In which y is i E { -1, +1} represents that the characterization result shows low-quality crystals and high-quality crystals, respectively.
The task of an SVM is to find the "maximum separation" of the division hyperplanes, and thus the SVM is expressed as:
ξ i ≥0,i＝1,2,…,m (3)
in the formula (I), the compound is shown in the specification,
is a plane normal vector, b is a displacement, ξ i Is a slack variable, C is a penalty factor,
for the x-mapped feature vector, s.t is an abbreviation for subject to, i.e., a constraint.
Model for obtaining maximum soft interval partition hyperplane for solving
Firstly, obtaining 'dual problem' of SVM basic type by using lagrange multiplier method, and then solving
And b.
Introduce lagrange function:
wherein alpha is i ≥0，μ i More than or equal to 0 is Lagrange multiplier.
Order to
Are respectively paired
b, xi, calculating the partial derivative and making the partial derivative value zero to obtain:
C＝α i +μ i (7)
a dual problem is obtained:
s.t.0≤α i ≤C,i＝1,2,…,m (9)
wherein
For a Gaussian kernel function, the expression is as follows:
and sigma is a Gaussian kernel function width parameter, the influence range of the Gaussian function is controlled, and the larger the sigma is, the larger the influence range of the Gaussian function is.
By the formula (8), (9), (10) and (11) to obtain alpha i
According to the formulas (11) and (12) and the solved alpha i Solving for
b. Wherein
With a unique solution, b there may be multiple solutions; when there are multiple solutions for b, the average is solved as the only solution.
Finally, obtaining a model of the maximum soft interval division hyperplane and a classification decision function:
where sign (·) is a sign function.
And (3) judging the performance of the model obtained by training:
first, accuracy
The model classifies the proportion of the number of correct samples in the test set to the number of the test lumped samples, and the precision calculation formula is as follows:
wherein m is the total number of samples,
to classify the correct number of samples.
Second, rate of accuracy
The precision rate is called Cha Jinglv, and refers to the probability that the sample is actually positive in all samples predicted to be positive, namely the probability that a high-quality crystal can be grown according to the crystal growth temperature parameter output by the model. The formula is as follows:
where P is the precision, TP is the true case number, and FP is the false positive case number.
The terminal carries out simulation specifically:
geometric modeling: and (3) creating a digital description of the geometric configuration of the growth system, wherein the system is in axisymmetric distribution, and a two-dimensional axisymmetric calculation model is adopted.
Grid generation: carrying out gridding dispersion on the growth system;
description of the model: setting material properties of each component of a growth system and a physical process to be considered by the system;
the control equation: the tellurium-zinc-cadmium crystal growth control equation has the following form:
continuity equation:
boundary conditions: given the energy and mass exchange conditions between the growth system and the environment.
In addition, the microcomputer records and uploads the data monitored in real time in the growth process of the cadmium zinc telluride crystal to the terminal, the terminal records and analyzes the data again, and the terminal sends a corresponding operation command to the microcomputer according to an analysis result. The initial growth conditions, temperature parameters and characterization data of the grown cadmium zinc telluride crystal are intelligently controlled by the terminal and are recorded into a database for the terminal to learn.
During the growth process of the CdZnTe crystal, the temperature in the CdZnTe crystal growth furnace is changed. Taking the vertical gradient method as an example, firstly, the raw materials are heated to about forty ℃ above the melting point and are kept warm for a period of time so as to be completely melted. Then the solid-liquid interface is moved from the head to the tail at a certain speed according to the preset temperature gradient and the temperature reduction rate, thereby finishing the crystal growth.
The data monitored in real time in the growth process of the cadmium zinc telluride crystal mainly comprise the temperature and the temperature gradient of each temperature zone of the crystal growth furnace and the shape of a solid-liquid interface for crystal growth. The solid-liquid interface is divided into a plane, a convex surface and a concave surface. When the heat dissipation of the solid-liquid interface is equal to the heat source amount, the solid-liquid interface is a plane, but the plane is difficult to maintain for a long time in the crystal growth process, and the shape of the interface which is kept to be slightly convex is favorable for the crystal growth; when the heat dissipation amount of the solid-liquid interface is less than the heat source amount, the solid-liquid interface is a convex surface; when the heat dissipation amount of the solid-liquid interface is larger than the heat source amount, the solid-liquid interface is a concave surface.
Specifically, the microcomputer uploads the detected real-time data to the terminal, the terminal inputs the real-time data and the initial growth condition to simulation software, and the quality of crystals grown under the real-time data is predicted through simulation; if the high-quality crystal can grow under the current data, the terminal does not adjust the real-time data; otherwise, the model compares and analyzes the real-time data with the data in the database, then the model gives out the temperature parameter which is considered to be capable of growing high-quality crystals, whether the temperature parameter is proper or not is verified through simulation, if so, the terminal sends the temperature parameter to the microcomputer, and the monitored real-time data are adjusted; if not, the model will re-output the temperature parameter until the temperature parameter is appropriate.
As shown in fig. 4, a system for intelligent growth of cadmium zinc telluride crystals comprises: the system comprises a terminal, a microcomputer, a temperature controller and a crystal growth furnace, wherein the microcomputer and the terminal as well as the temperature controller and the microcomputer respectively exchange data through a data exchanger to upload monitoring information and receive operation commands, and the temperature controller and the microcomputer are mutually independent in function. The terminal is connected with the microcomputer, the microcomputer and the temperature controller through data exchangers respectively. Firstly, inputting initial conditions for the growth of the CdZnTe crystal into a microcomputer, wherein the initial conditions specifically comprise the zinc content in the CdZnTe, the CdZnTe polycrystalline quality for growing the CdZnTe crystal, the type of a crucible, the size of the crucible, the size of a quartz tube, the type of a support and a growth method. The terminal intelligently outputs proper temperature parameters for the CdZnTe crystal growth according to the initial growth conditions input by n (n is more than or equal to 1) microcomputers and the crystal growth numerical simulation results, and the temperature parameters are respectively sent to the corresponding microcomputers through the data exchangers. The microcomputer receives the temperature parameters sent by the terminal and automatically sets a heating program, a cooling program and a temperature gradient. The microcomputer respectively controls m (m is more than or equal to 1) temperature control systems according to the temperature parameters, and uploads the monitored real-time temperature change signals of the crystal growth furnace to the terminal, and the terminal sends corresponding operation commands to the microcomputer according to the real-time temperature signals of the crystal growth furnace uploaded by the microcomputer. If the temperature is lower than the set value, the terminal sends an operation command for continuing heating until the temperature reaches the set value, and at the moment, the terminal sends an operation command for maintaining the current temperature; if the temperature control system fails or overshoots and the temperature rises to exceed the set value and the alarm value, the terminal sends an alarm command to the microcomputer, and the microcomputer immediately gives an alarm.
The operation instruction sent by the microcomputer receiving terminal comprises a temperature rising program, a temperature lowering program and temperature gradient setting. The microcomputer can realize independent control of m (m is more than or equal to 1) temperature control systems, and each temperature control system has a PID self-adaptive function. The temperature controller comprises a high-quality transformer, a heating unit and a high-precision platinum-rhodium thermocouple, wherein the high-quality transformer, the high-precision platinum-rhodium thermocouple and the heating unit form closed-loop temperature control, and high-precision and high-stability temperature control is realized.
According to the scheme provided by the embodiment of the invention, the terminal intelligently outputs the temperature parameters suitable for the growth of the cadmium zinc telluride crystal according to the input crystal growth initial conditions, the model for coupling the temperature parameters with the characterization data and the crystal growth numerical simulation result, thereby laying a foundation for growing the high-quality cadmium zinc telluride crystal; in addition, the initial growth conditions, temperature parameters and characterization data of the grown cadmium zinc telluride crystal are intelligently controlled by the terminal to be recorded into the database for the terminal to learn, a virtuous cycle is formed between the terminal and the crystal growth, so that the model induced by the terminal is more accurate and suitable, and the quality of the grown cadmium zinc telluride crystal is higher and higher. In addition, the terminal intelligently outputs proper temperature parameters for the growth of the cadmium zinc telluride crystal to each microcomputer according to the initial conditions for the growth of the cadmium zinc telluride crystal input by n (n is more than or equal to 1) microcomputers. The terminal monitors the crystal growth process and sends corresponding operation commands to the microcomputer in real time. The microcomputer can realize the independent control of m (m is more than or equal to 1) temperature control systems, thereby greatly improving the crystal growth efficiency, realizing the centralized monitoring and management of crystal growth and saving the crystal growth cost.
Although the present invention has been described in detail hereinabove, the present invention is not limited thereto, and various modifications can be made by those skilled in the art in light of the principle of the present invention. Thus, modifications made in accordance with the principles of the present invention should be understood to fall within the scope of the present invention.
Claims (10)
1. An intelligent growth method of a cadmium zinc telluride crystal is characterized by comprising the following steps:
the terminal receives the initial growth conditions of the cadmium zinc telluride crystal sent by the microcomputer, and the initial growth conditions of the cadmium zinc telluride crystal are input into a crystal growth model for calculation to obtain temperature parameters required by the growth of the cadmium zinc telluride crystal;
the terminal judges whether the high-quality cadmium zinc telluride crystal can be grown under the temperature parameter by carrying out simulation processing on the initial growth condition of the cadmium zinc telluride crystal and the temperature parameter;
when the high-quality cadmium zinc telluride crystal can be grown under the temperature parameter, the terminal sends the temperature parameter to the microcomputer, so that the microcomputer controls the temperature information in the cadmium zinc telluride crystal growth furnace according to the temperature parameter.
2. The method of claim 1, wherein the tellurium-zinc-cadmium crystal initial growth conditions comprise: the method comprises the following steps of (1) determining the zinc content in cadmium zinc telluride, the quality of cadmium zinc telluride polycrystal used for growing cadmium zinc telluride crystals, the type of a crucible, the size of the crucible, the size of a quartz tube, the type of a support and a growing method; the temperature parameters include: a temperature-raising program, a temperature-lowering program and a temperature gradient.
3. The method as claimed in claim 1, wherein the determining, by the terminal performing simulation processing on the initial growth conditions of the cadmium zinc telluride crystal and the temperature parameters, whether the cadmium zinc telluride crystal with high quality can be grown under the temperature parameters comprises:
the terminal carries out simulation processing on the initial growth conditions and the temperature parameters of the cadmium zinc telluride crystal to obtain the shape of a solid-liquid interface, the segregation coefficient of Zn and the temperature field distribution in the growth process of the cadmium zinc telluride crystal;
and when the solid-liquid interface shape in the growth process of the cadmium zinc telluride crystal is a plane or a micro convex surface, the segregation coefficient of Zn is close to 1, and the temperature field distribution is a proper temperature gradient, the terminal judges that the high-quality cadmium zinc telluride crystal can be grown under the temperature parameter.
4. The method of claim 3, further comprising:
when the high-quality cadmium zinc telluride crystal cannot be grown under the temperature parameter, the terminal retrains the crystal growth model to obtain a trained crystal growth model;
the terminal obtains temperature parameters required by the growth of the cadmium zinc telluride crystal by using the trained crystal growth model, and sends the temperature parameters to the microcomputer when the high-quality cadmium zinc telluride crystal can be grown under the temperature parameters.
5. The method of claim 1, further comprising: and establishing a crystal growth model containing the initial growth conditions, the temperature parameters and the characterization data of the cadmium zinc telluride crystal.
6. The method of claim 5, further comprising:
in the growth process of the cadmium zinc telluride crystal, the microcomputer monitors the growth process of the cadmium zinc telluride crystal in real time to obtain cadmium zinc telluride crystal growth monitoring data, and periodically sends the cadmium zinc telluride crystal growth monitoring data to the terminal;
the terminal predicts whether a high-quality cadmium zinc telluride crystal can grow under the monitoring data of the cadmium zinc telluride crystal growth by analyzing the monitoring data of the cadmium zinc telluride crystal growth;
and when the high-quality cadmium zinc telluride crystal cannot be grown under the cadmium zinc telluride crystal growth monitoring data, the terminal calculates the current temperature parameter required in the current cadmium zinc telluride crystal growth process according to the cadmium zinc telluride crystal growth monitoring data and the crystal growth model, and sends the current temperature parameter to the microcomputer.
7. The method of claim 6, wherein the characterization data comprises resistivity, leakage current, dislocation density, tellurium precipitate size, tellurium precipitate density, tellurium inclusion size, infrared transmittance, electron mobility-lifetime product, hole mobility-lifetime product.
8. An intelligent growth system of a cadmium zinc telluride crystal is characterized by comprising:
the terminal is used for receiving the initial growth conditions of the cadmium zinc telluride crystal sent by the microcomputer and inputting the initial growth conditions of the cadmium zinc telluride crystal into the crystal growth model for calculation to obtain temperature parameters required by the growth of the cadmium zinc telluride crystal; carrying out simulation treatment on the initial growth conditions of the cadmium zinc telluride crystal and the temperature parameters, and judging whether a high-quality cadmium zinc telluride crystal can grow under the temperature parameters; when the high-quality cadmium zinc telluride crystal can grow under the temperature parameter, sending the temperature parameter to the microcomputer;
and the microcomputer is used for sending the initial growth conditions of the cadmium zinc telluride crystal to the terminal, receiving the temperature parameters sent by the terminal and controlling the temperature information in the cadmium zinc telluride crystal growth furnace according to the temperature parameters.
9. An electronic device, comprising: a memory; a processor; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1-7.
10. A computer-readable storage medium, having stored thereon a computer program; the computer program is executed by a processor to implement the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211282330.5A CN115595667B (en) | 2022-10-18 | 2022-10-18 | Intelligent growth method, system, equipment and storage medium for tellurium-zinc-cadmium crystals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211282330.5A CN115595667B (en) | 2022-10-18 | 2022-10-18 | Intelligent growth method, system, equipment and storage medium for tellurium-zinc-cadmium crystals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115595667A true CN115595667A (en) | 2023-01-13 |
| CN115595667B CN115595667B (en) | 2023-11-14 |
Family
ID=84848332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211282330.5A Active CN115595667B (en) | 2022-10-18 | 2022-10-18 | Intelligent growth method, system, equipment and storage medium for tellurium-zinc-cadmium crystals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115595667B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116168788A (en) * | 2023-04-25 | 2023-05-26 | 北京大学 | Method and system for analyzing segregation coefficient of molten liquid silicon based on big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6325851B1 (en) * | 1998-09-16 | 2001-12-04 | Komatsu Electronic Metals Co. | Crystal manufacturing apparatus and method |
| CN112466407A (en) * | 2020-11-25 | 2021-03-09 | 哈尔滨工业大学 | Method for obtaining large-size chalcopyrite single crystals based on CGSim software simulation |
| CN113106539A (en) * | 2020-06-05 | 2021-07-13 | 眉山博雅新材料有限公司 | Crystal preparation system |
| CN113130017A (en) * | 2020-06-05 | 2021-07-16 | 北京世纪金光半导体有限公司 | Crystal growth analysis method and system based on artificial intelligence |
| CN114411236A (en) * | 2022-02-10 | 2022-04-29 | 北京青禾晶元半导体科技有限责任公司 | Growth method of simulated crystal, growth method of crystal and device |
-
2022
- 2022-10-18 CN CN202211282330.5A patent/CN115595667B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6325851B1 (en) * | 1998-09-16 | 2001-12-04 | Komatsu Electronic Metals Co. | Crystal manufacturing apparatus and method |
| CN113106539A (en) * | 2020-06-05 | 2021-07-13 | 眉山博雅新材料有限公司 | Crystal preparation system |
| CN113130017A (en) * | 2020-06-05 | 2021-07-16 | 北京世纪金光半导体有限公司 | Crystal growth analysis method and system based on artificial intelligence |
| CN112466407A (en) * | 2020-11-25 | 2021-03-09 | 哈尔滨工业大学 | Method for obtaining large-size chalcopyrite single crystals based on CGSim software simulation |
| CN114411236A (en) * | 2022-02-10 | 2022-04-29 | 北京青禾晶元半导体科技有限责任公司 | Growth method of simulated crystal, growth method of crystal and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116168788A (en) * | 2023-04-25 | 2023-05-26 | 北京大学 | Method and system for analyzing segregation coefficient of molten liquid silicon based on big data |
| CN116168788B (en) * | 2023-04-25 | 2023-08-11 | 北京大学 | Method and system for analyzing segregation coefficient of molten liquid silicon based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115595667B (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Derby et al. | Thermal-capillary analysis of Czochralski and liquid encapsulated Czochralski crystal growth: II. Processing strategies | |
| CN115595667B (en) | Intelligent growth method, system, equipment and storage medium for tellurium-zinc-cadmium crystals | |
| Liu et al. | Nonlinear generalized predictive control of the crystal diameter in CZ-Si crystal growth process based on stacked sparse autoencoder | |
| Zhang et al. | Nucleation and bulk growth control for high efficiency silicon ingot casting | |
| CN108914201A (en) | A kind of Modelling of Crystal Growth in CZ-Si Pulling process parameter optimization method | |
| CN111368434A (en) | Prediction method of Czochralski method monocrystalline silicon solid-liquid interface based on ANN | |
| CN109056056B (en) | A kind of Modelling of Crystal Growth in CZ-Si Pulling process thermal field identification Method | |
| KR20010022606A (en) | Device and method for growing crystals | |
| Winkler et al. | A review of the automation of the Czochralski crystal growth process | |
| WO2022141768A1 (en) | Quality prediction method, preparation method, and preparation system for gallium oxide based on deep learning and edge-defined film-fed growth technique | |
| Gevelber et al. | Advanced control design considerations for the Czochralski process | |
| Geng et al. | Prediction of the cement grate cooler pressure in the cooling process based on a multi-model fusion neural network | |
| CN116736907A (en) | Intelligent regulation and control method for production temperature of low borosilicate glass | |
| WO2022141756A1 (en) | Gallium oxide preparation method and system based on deep learning and bridgman-stockbarger method | |
| WO2022141766A1 (en) | Conductivity type gallium oxide preparation method based on deep learning and heat exchange method | |
| CN115857315A (en) | Event trigger-based semiconductor silicon single crystal growth model prediction control method | |
| WO2022141751A1 (en) | High-resistance gallium oxide prediction method and preparation method based on deep learning and bridgman-stockbarger method | |
| Abdollahi et al. | Model predictive temperature tracking in crystal growth processes | |
| WO2022141764A1 (en) | Quality prediction method for conductive gallium oxide on the basis of deep learning and edge-defined film-fed growth method, and preparation method and system | |
| CN104389019A (en) | Process robotic system for growing sapphire crystal by virtue of kyropous method | |
| WO2022141750A1 (en) | Gallium oxide preparation method and system based on deep learning and heat exchange method | |
| Wan et al. | Model-free sliding mode iterative learning control for Cz silicon single crystal diameter | |
| Anbu et al. | Modelling on modified heater design of DS system for improving the quality of mc-silicon ingot | |
| WO2022141760A1 (en) | Conductive gallium oxide preparation method based on deep learning and bridgman method | |
| WO2022141755A1 (en) | High-resistance type gallium oxide preparation method based on deep learning and heat exchange method |
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 |