CN112859771A - Quality prediction method, preparation method and system of gallium oxide based on deep learning and model-guiding method - Google Patents
Quality prediction method, preparation method and system of gallium oxide based on deep learning and model-guiding method Download PDFInfo
- Publication number
- CN112859771A CN112859771A CN202011640976.7A CN202011640976A CN112859771A CN 112859771 A CN112859771 A CN 112859771A CN 202011640976 A CN202011640976 A CN 202011640976A CN 112859771 A CN112859771 A CN 112859771A
- Authority
- CN
- China
- Prior art keywords
- data
- preparation
- gallium oxide
- crystal
- target
- 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.)
- Pending
Links
- 238000002360 preparation method Methods 0.000 title claims abstract description 159
- AJNVQOSZGJRYEI-UHFFFAOYSA-N digallium;oxygen(2-) Chemical compound [O-2].[O-2].[O-2].[Ga+3].[Ga+3] AJNVQOSZGJRYEI-UHFFFAOYSA-N 0.000 title claims abstract description 133
- 229910001195 gallium oxide Inorganic materials 0.000 title claims abstract description 133
- 238000000034 method Methods 0.000 title claims abstract description 120
- 238000013135 deep learning Methods 0.000 title claims abstract description 37
- 239000013078 crystal Substances 0.000 claims abstract description 252
- 238000003062 neural network model Methods 0.000 claims abstract description 87
- 238000007781 pre-processing Methods 0.000 claims abstract description 41
- 238000012549 training Methods 0.000 claims description 104
- 238000004321 preservation Methods 0.000 claims description 58
- 238000010438 heat treatment Methods 0.000 claims description 40
- 239000013598 vector Substances 0.000 claims description 27
- 238000001816 cooling Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 230000007613 environmental effect Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 3
- 239000000155 melt Substances 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- 230000006870 function Effects 0.000 description 10
- 230000006698 induction Effects 0.000 description 8
- 238000009826 distribution Methods 0.000 description 6
- 239000007788 liquid Substances 0.000 description 5
- 238000011176 pooling Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000002994 raw material Substances 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 239000012535 impurity Substances 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000002109 crystal growth method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 150000002500 ions Chemical class 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 239000000498 cooling water Substances 0.000 description 1
- 238000002425 crystallisation Methods 0.000 description 1
- 230000008025 crystallization Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- QZQVBEXLDFYHSR-UHFFFAOYSA-N gallium(III) oxide Inorganic materials O=[Ga]O[Ga]=O QZQVBEXLDFYHSR-UHFFFAOYSA-N 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000011081 inoculation Methods 0.000 description 1
- 229910052741 iridium Inorganic materials 0.000 description 1
- GKOZUEZYRPOHIO-UHFFFAOYSA-N iridium atom Chemical compound [Ir] GKOZUEZYRPOHIO-UHFFFAOYSA-N 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010899 nucleation Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 238000005204 segregation Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000000825 ultraviolet detection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by quality surveillance of production
-
- 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
- C30B15/00—Single-crystal growth by pulling from a melt, e.g. Czochralski method
- C30B15/34—Edge-defined film-fed crystal-growth using dies or slits
-
- 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
- C30B29/16—Oxides
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Organic Chemistry (AREA)
- Crystallography & Structural Chemistry (AREA)
- Materials Engineering (AREA)
- Metallurgy (AREA)
- Inorganic Chemistry (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Crystals, And After-Treatments Of Crystals (AREA)
Abstract
The invention discloses a quality prediction method, a preparation method and a system of gallium oxide based on deep learning and a mode-guiding method, wherein the quality prediction method comprises the following steps: acquiring preparation data of preparing the gallium oxide single crystal by a guide die method, wherein the preparation data comprises seed crystal data, environment data and control data, and the control data comprises the width and the thickness of a die opening gap; preprocessing the preparation data to obtain preprocessed preparation data; inputting the preprocessing preparation data into a trained neural network model, and obtaining the corresponding prediction quality data of the gallium oxide single crystal through the trained neural network model. The invention can predict the quality of the gallium oxide single crystal through the trained neural network model, thereby adjusting the preparation data to obtain the required performance of the gallium oxide single crystal and optimizing the performance of the gallium oxide single crystal.
Description
Technical Field
The invention relates to the field of gallium oxide crystal preparation, in particular to a gallium oxide quality prediction method, a gallium oxide quality prediction preparation method and a gallium oxide quality prediction system based on deep learning and a mode-guiding method.
Background
β-Ga2O3(gallium oxide) is a direct band gap wide band gap semiconductor material, and the band gap is about 4.8-4.9 eV. The high-temperature high-power semiconductor laser has the advantages of large forbidden band width, high saturated electron drift speed, high thermal conductivity, high breakdown field strength, stable chemical property and the like, and has wide application prospect in the field of high-temperature, high-frequency and high-power electronic devices. In addition, the sensor can also be used for LED chips, solar blind ultraviolet detection, various sensor elements, camera elements and the like.
At present, the large-size gallium oxide crystals are prepared in batches mainly by adopting a mold guiding preparation technology. The mold-guiding method is a mature single crystal preparation technology and has the advantages of special-shaped crystal growth, high growth speed and low growth cost. The mold guiding method is a crystal growth method obtained by improving the mold guiding method, and the exploration of crystal growth equipment and a growth process is relatively more complicated. The guided mode method requires placing a mold in a crucible, the crystal growth interface is located on the upper surface of the mold, and the melt rises to the upper surface of the mold along capillaries in the mold due to the action of surface tension at high temperature. The rise height H of the melt along the capillary is represented by the formula
And determining, wherein gamma is the surface tension of the melt, theta is the contact angle between the melt and the capillary, rho is the density of the melt, g is the acceleration of gravity, and r is the radius of the capillary.
Compared with the guided mode method, the preparation method of the gallium oxide crystal by the guided mode method has the following advantages:
1. the convection of the melt in the capillary tube of the mold is weak, impurity ions in the melt are difficult to return to the crucible again after rising to a solid-liquid interface from the capillary tube, the segregation coefficient of the impurity ions in the crystal is generally close to 1, and the distribution consistency of the upper and lower impurities of the crystal is good;
2. the solid-liquid interface for crystal growth is positioned above the die, the shape of the interface can be regulated and controlled by the geometric shape of the surface of the die, and the position of the solid-liquid interface in a temperature field is always unchanged and is not influenced by the disturbance of melt in the crucible, so that the solid-liquid interface for crystal growth in the die guide method is more stable;
3. the crystal growth speed of the mode-guiding method is high, the energy consumption is reduced, the special-shaped crystal can be grown, and the crystal processing cost and the processing loss are reduced.
However, in the process of preparing gallium oxide crystal by using the guided mode method, the temperature field distribution near the die opening, the selection of seed crystal, the pulling speed of the seed crystal rod, the crystal growth atmosphere environment, and the changes of parameters such as heating power and cooling power all have great influence on the quality of the prepared gallium oxide crystal. The existing process for preparing gallium oxide crystal by the mold-guiding method is to set parameters by relying on the experience of operators, and the repeatability is poor, so that the stability of the prepared gallium oxide crystal product is poor.
Accordingly, the prior art is yet to be improved and developed.
Disclosure of Invention
The invention aims to solve the technical problems that the quality prediction method, the preparation method and the system of gallium oxide based on deep learning and a mold guiding method are provided aiming at overcoming the defects of the prior art, and the problems that the quality and the stability of the prepared gallium oxide crystal are poor due to poor repeatability of the gallium oxide crystal prepared by the existing mold guiding method because parameters are set by depending on the experience of an operator are solved.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a gallium oxide quality prediction method based on deep learning and a guided mode method comprises the following steps:
acquiring preparation data of preparing the gallium oxide single crystal by a guide die method, wherein the preparation data comprises seed crystal data, environment data and control data, and the control data comprises the width and the thickness of a die opening gap;
preprocessing the preparation data to obtain preprocessed preparation data;
inputting the preprocessing preparation data into a trained neural network model, and obtaining the corresponding prediction quality data of the gallium oxide single crystal through the trained neural network model.
The gallium oxide quality prediction method based on the deep learning and model-guiding method comprises the following steps of preprocessing the preparation data to obtain preprocessed preparation data:
and obtaining pre-processing preparation data according to the seed crystal data, the environment data and the control data, wherein the pre-processing preparation data is a matrix formed by the seed crystal data, the environment data and the control data.
The gallium oxide quality prediction method based on the deep learning and mode-guiding method is characterized in that the seed crystal data comprise: the half-height width of the diffraction peak of the seed crystal, the deviation value of the half-height width of the diffraction peak of the seed crystal, the thickness of the seed crystal and the width of the seed crystal;
the environmental data includes: the thermal resistance value of the upper heat-preservation cover, the thermal resistance value deviation value of the upper heat-preservation cover, the shape factor of a crystal growth channel, the shape factor of a crystal growth observation hole, the thermal resistance value of the lower heat-preservation cover, the thermal resistance value deviation value of the lower heat-preservation cover, the relative height of the crucible and the heating coil, and the relative height of the heating ring and the heating coil;
the control data includes: heating power, cooling power, atmosphere type, cavity pressure, gas flow and seed rod pulling speed.
The gallium oxide quality prediction method based on the deep learning and model-guiding method comprises the following steps of obtaining preprocessing preparation data according to the seed crystal data, the environmental data and the control data:
determining a preparation vector according to the seed crystal data, the environment data and the control data; wherein, the first element in the preparation vector is one of the full width at half maximum of the diffraction peak of the seed crystal, the deviation value of the full width at half maximum of the diffraction peak of the seed crystal, the thickness of the seed crystal and the width of the seed crystal; the second element in the preparation vector is one of the thermal resistance value of the upper heat-preservation cover, the thermal resistance value deviation value of the upper heat-preservation cover, the shape factor of a crystal growth channel, the shape factor of a crystal growth observation hole, the thermal resistance value of the lower heat-preservation cover, the thermal resistance value deviation value of the lower heat-preservation cover, the relative height of the crucible and the heating coil, the relative height of the heating ring and the heating coil, the width of a gap of a mold opening and the thickness of the gap of the mold opening; the third element in the preparation vector is one of the heating power, the cooling power, the atmosphere type, the cavity pressure, the gas flow and the seed rod pulling speed;
and determining the preprocessing preparation data according to the preparation vector.
The gallium oxide quality prediction method based on the deep learning and guided mode method is characterized in that the prediction quality data comprise: predicting crack data, predicting mixed crystal data, predicting half height width of a diffraction peak, predicting half height width deviation value of the diffraction peak, predicting shouldering symmetry of the gallium oxide crystal, predicting left edge folding and unfolding degree of the gallium oxide crystal, predicting right edge folding and unfolding degree of the gallium oxide crystal, predicting thickness of the gallium oxide crystal and predicting thickness deviation of the gallium oxide crystal.
The gallium oxide quality prediction method based on the deep learning and model-guiding method is characterized in that the trained neural network model is obtained by training through the following training steps:
acquiring training data of gallium oxide single crystal preparation by a guide mode method and corresponding actual quality data, wherein the training data comprises: seed crystal training data, environment training data and control training data;
preprocessing the training data to obtain preprocessed training data;
inputting the preprocessed training data into a preset neural network model, and obtaining predicted training generation quality data corresponding to the preprocessed training data through the preset neural network model;
and adjusting and correcting the model parameters of the preset neural network model according to the predicted training generated quality data and the actual quality data to obtain the trained neural network model.
The gallium oxide quality prediction method based on the deep learning and model-guiding method is characterized in that the preset neural network model comprises the following steps: a feature extraction module and a full-connection module,
inputting the preprocessed training data into a preset neural network model, and obtaining the predicted training generation quality data corresponding to the preprocessed training data through the preset neural network model, wherein the step of obtaining the predicted training generation quality data comprises the following steps:
inputting the preprocessed training data into the feature extraction module, and obtaining feature vectors corresponding to the preprocessed training data through the feature extraction module;
and inputting the feature vector into the full-connection module, and obtaining prediction training generation quality data corresponding to the preprocessing training data through the full-connection module.
A gallium oxide preparation method based on deep learning and a guided mode method is disclosed, wherein the preparation method comprises the following steps:
obtaining target quality data of a target gallium oxide single crystal;
determining target preparation data corresponding to the target gallium oxide single crystal according to the target quality data and the trained neural network model, wherein the target preparation data comprises: target seed crystal data, target environment data and target control data, wherein the target environment data comprises the width of a target die opening gap and the thickness of the target die opening gap;
and preparing the target gallium oxide single crystal according to the target preparation data based on a mode-guiding method.
The gallium oxide preparation method based on the deep learning and guided mode method comprises the following steps of determining target preparation data corresponding to target gallium oxide single crystals according to the target quality data and a trained neural network model, and comprises the following steps:
acquiring preset preparation data, and preprocessing the preset preparation data to obtain preprocessed preset preparation data;
inputting the preprocessing preset preparation data into a trained neural network model, and obtaining prediction quality data corresponding to the preprocessing preset preparation data through the trained neural network model;
and correcting the preset preparation data according to the predicted quality data and the target quality data to obtain target preparation data corresponding to the target gallium oxide single crystal.
A gallium oxide preparation system based on deep learning and a guided mode method comprises a memory and a processor, wherein the memory stores a computer program, and the processor is characterized in that the processor implements the steps of the prediction method or the preparation method when executing the computer program.
Has the advantages that: the invention provides a gallium oxide quality prediction method and a preparation method based on deep learning and a guided mode method. The invention can predict the quality of the gallium oxide single crystal through the trained neural network model, thereby adjusting the preparation data to obtain the required performance of the gallium oxide single crystal and optimizing the performance of the gallium oxide single crystal.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic structural diagram of a crystal growth furnace for preparing gallium oxide crystals by a guided mode method according to the present invention.
Fig. 2 is a flowchart of a gallium oxide quality prediction method based on deep learning and guided mode method according to a preferred embodiment of the present invention.
Fig. 3 is a flowchart of a method for preparing gallium oxide based on deep learning and guided mode method according to a preferred embodiment of the present invention.
Fig. 4 is an internal structure diagram of a gallium oxide preparation system based on deep learning and a mode-guiding method provided by the invention.
Detailed Description
The invention provides a gallium oxide crystal preparation method and system based on deep learning and a guided mode method, and in order to make the purpose, technical scheme and effect of the invention clearer and clearer, the invention is further described in detail below by referring to the attached drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The invention will be further explained by the description of the embodiments with reference to the drawings.
The mode-guiding method is a traditional crystal growth method, when a crystal is grown by adopting the mode-guiding method, raw materials in a crucible are melted by heating, the temperature of a melt is accurately adjusted, then a seed crystal is immersed in the melt, and simultaneously the seed crystal is pulled and rotated at a proper speed to induce the melt in the crucible to crystallize. The method has higher requirements on the temperature field design, the stability of heating power and the experience of operators when the crystal is grown by the mode-guiding method.
The invention provides a crystal growth furnace for growing gallium oxide crystals by a guide mode method, which comprises a lower heat-insulating cover 11, wherein a crucible 12 is arranged in the lower heat-insulating cover 11, a mould 13 forming a capillary siphon effect is arranged in the crucible 12, and a heating ring 14 is arranged outside the crucible 12, as shown in figure 1; the upper heat-preservation cover 15 is arranged above the lower heat-preservation cover, a crystal growth channel 16 is arranged inside the upper heat-preservation cover 15, a crystal growth observation hole 17 is formed in the side edge of the upper heat-preservation cover, and an induction coil 18 is further arranged on the periphery of the lower heat-preservation cover 10.
Firstly, the crystal growth furnace for preparing the gallium oxide crystal is installed, wherein the crystal growth furnace comprises an upper heat-insulating cover material selection, an axial opening size of the upper heat-insulating cover, an opening window shape and size, a lower heat-insulating cover material selection, a height position of a crucible relative to an induction coil, a relative height of a heating ring and the induction coil and the like, and the heat field distribution in the device can be influenced, so that the product performance of the gallium oxide crystal is influenced.
To orient the beta-Ga in a specific orientation2O3The seed crystal is placed in a seed crystal holder and fixed by binding, and the orientation of the seed crystal can be [010 ]]、[001]Direction, etc.;
firstly, starting a mechanical pump and a diffusion pump in sequence to vacuumize the equipment, closing the vacuum equipment when the equipment is vacuumized to a preset vacuum degree, and slowly inflating the equipment according to the volume ratio of mixed gas;
then, heating the crucible by the heating body by setting heating power, so that after the gallium oxide raw material placed in the crucible is completely melted, the melted gallium oxide is conveyed to the top of the mold through capillary siphon action and is unfolded at the top until the gallium oxide raw material is completely covered; then, slowly lowering the seed rod to enable the seed crystal to be 3-5mm away from the top of the iridium mould for seed crystal preheating, and starting inoculation after 5-10 minutes; after the seed crystal and the melt are fully welded, carrying out seeding and necking operation to avoid the original defects of the seed crystal from extending into the crystal, ensuring the crystal quality, and then carrying out shoulder-expanding growth to ensure that the crystal transversely expands to the whole mould; then carrying out equal-diameter growth; after the crystal growth is finished, slowly cooling to room temperature, and taking out the crystal to obtain the gallium oxide crystal. In the process of preparing the gallium oxide crystal, the product performance of the gallium oxide crystal can be influenced by heating power, cooling power, atmosphere type, pressure in a cavity, flow rate of atmosphere cooling water and pulling speed of a seed crystal rod.
Based on this, the present embodiment provides a method for predicting gallium oxide quality based on deep learning and guided mode method, as shown in fig. 2, which includes the following steps:
s100, obtaining preparation data of preparing the gallium oxide single crystal by a guide die method, wherein the preparation data comprises seed crystal data, environment data and control data, and the control data comprises the width and the thickness of a die opening gap.
Specifically, the preparation data refers to data for preparing the gallium oxide single crystal by using a guided mode method, and the preparation data is data which can be configured according to needs, for example, when the performance of the gallium oxide single crystal obtained under a certain preparation data needs to be predicted, the preparation data only needs to be determined, the preparation data is preprocessed to obtain preprocessed preparation data, the preprocessed preparation data is input into a trained neural network model, predicted quality data is obtained through the trained neural network model, that is, after the preparation data is determined, the quality data of the gallium oxide single crystal can be predicted through the trained neural network model without performing experiments.
In this embodiment, the preparation data includes: the method comprises the following steps of seed crystal data, environment data and control data, wherein the seed crystal data refer to the data of seed crystals adopted in the process of preparing the gallium oxide single crystal by adopting a guide die method, the environment data refer to the data of the environment where the crystals are located in the process of preparing the gallium oxide single crystal by adopting the guide die method, and the control data refer to the data for controlling the crystal growth in the process of preparing the gallium oxide single crystal by adopting the guide die method. In this embodiment, the control data includes the width of the die orifice gap and the thickness of the die orifice gap, and the molten gallium oxide is transported to the top of the die mainly by capillary siphoning of the die orifice gap, so that a gallium oxide crystal gradually grows on the seed crystal. Therefore, the width and thickness of the die orifice gap have a great influence on the quality of the gallium oxide single crystal.
S200, preprocessing the preparation data to obtain preprocessed preparation data.
Specifically, after the preparation data is obtained, the preparation data is preprocessed to obtain preprocessed preparation data, so that the preprocessed preparation data can be input into a trained neural network model, and the preprocessed preparation data can be processed through the trained neural network model.
In an implementation manner of the embodiment of the present application, the step S200 of preprocessing the preparation data to obtain preprocessed preparation data includes:
s210, obtaining preprocessing preparation data according to the seed crystal data, the environment data and the control data, wherein the preprocessing preparation data are matrixes formed by the seed crystal data, the environment data and the control data.
Specifically, after preparation data is obtained, the preparation data is preprocessed to obtain preprocessed preparation data. Since the sub-data (such as seed data, environmental data, and control data) in the preparation data are mutually influenced, but the degree of the mutual influence between the sub-data cannot be determined at present, the preparation data needs to be preprocessed, and the sub-data in the preparation data are rearranged and combined to form preprocessed preparation data.
In another embodiment of the present application, the seed data includes: the half-height width of the diffraction peak of the seed crystal, the deviation value of the half-height width of the diffraction peak of the seed crystal, the thickness of the seed crystal and the width of the seed crystal; the environmental data further includes: the thermal resistance value of the upper heat-preservation cover, the thermal resistance value deviation value of the upper heat-preservation cover, the shape factor of a crystal growth channel, the shape factor of a crystal growth observation hole, the thermal resistance value of the lower heat-preservation cover, the thermal resistance value deviation value of the lower heat-preservation cover, the relative height of the crucible and the heating coil, and the relative height of the heating ring and the heating coil; the control data includes: heating power, cooling power, atmosphere type, cavity pressure, gas flow and seed rod pulling speed.
Specifically, the full width at half maximum of the diffraction peak of the seed crystal can be tested by an X-ray diffractometer, the full width at half maximum deviation value of the diffraction peak of the seed crystal comprises a full width at half maximum radial deviation value of the diffraction peak of the seed crystal and a full width at half maximum axial deviation value of the diffraction peak of the seed crystal, the radial direction is a direction on the horizontal plane, and the axial direction is a direction perpendicular to the horizontal plane, namely an axis in the vertical direction. The radial deviation value of the half-height width of the diffraction peak of the seed crystal can be obtained by radially testing the half-height width of the diffraction peak of the seed crystal and solving the difference value between the half-height widths of the diffraction peaks of the seed crystal in the radial direction of the seed crystal. The axial deviation value of the half-height width of the diffraction peak of the seed crystal can be obtained by axially testing the half-height width of the diffraction peak of the seed crystal and calculating the difference value between the half-height widths of the diffraction peaks of the seed crystal in the axial direction of the seed crystal. The thickness and the width of the seed crystal can be directly measured.
As described above, when the crystal growth furnace shown in fig. 1 is used to prepare a gallium oxide single crystal, the upper heat-insulating cover and the lower heat-insulating cover both provide a stable thermal field for the growth of the gallium oxide single crystal. The thermal resistance value of the upper heat-preservation cover refers to the temperature difference between the inner side and the outer side of the heat-preservation cover when unit heat passes through the upper heat-preservation cover in unit time. The larger the thermal resistance value of the upper heat-insulating cover is, the stronger the heat transfer resistance of the upper heat-insulating cover is, and the better the heat-insulating effect of the upper heat-insulating cover is.
The upper heat preservation cover thermal resistance value deviation value comprises an upper heat preservation cover thermal resistance value radial deviation value and an upper heat preservation cover thermal resistance value axial deviation value. The radial deviation value of the thermal resistance of the upper heat-preservation cover can be obtained by testing the thermal resistance of the upper heat-preservation cover on the radial two sides of the upper heat-preservation cover and calculating the difference value between the thermal resistance values of the upper heat-preservation cover on the radial two sides of the upper heat-preservation cover. The axial deviation value of the thermal resistance value of the upper heat-preservation cover can be obtained by testing the thermal resistance values of the upper heat-preservation cover on the two axial sides of the upper heat-preservation cover and calculating the difference value between the thermal resistance values of the upper heat-preservation cover on the two axial sides of the upper heat-preservation cover.
Similarly, the thermal resistance value of the lower heat-preservation cover and the thermal resistance deviation value of the lower heat-preservation cover can be obtained by the same method, and the thermal resistance deviation value of the lower heat-preservation cover comprises a radial deviation value of the thermal resistance value of the lower heat-preservation cover and an axial deviation value of the thermal resistance value of the lower heat-preservation cover.
The crystal growth channel shape factor refers to a value of a shape and a size of a crystal growth channel, for example, when the crystal growth channel is cylindrical, the crystal growth channel shape factor includes: the diameter and height of the crystal growth channel; when the crystal growth channel is cubic, the crystal growth channel shape factor comprises the length, height and width of the crystal growth channel; the crystal growth channel shape factor also affects the thermal field distribution of the crystal growth environment, thereby affecting the crystal growth performance.
The shape factor of the crystal growth observation hole also refers to the value of the shape and the size of the crystal growth observation hole, and the shape of the crystal growth observation hole also influences the thermal field distribution of the crystal growth environment, so that the crystal growth performance is influenced.
Since the crucible is heated by the induction coil and the heating ring, the relative heights of the crucible and the induction coil and the heating ring and the induction coil affect the thermal field distribution of the crystal growth environment.
Along with the use of the device for growing the gallium oxide crystal, the thermal resistance value of the upper heat-preservation cover, the thermal resistance value of the lower heat-preservation cover, the thermal resistance value deviation value of the upper heat-preservation cover and the thermal resistance value deviation value of the lower heat-preservation cover can be changed, but can not be changed in a short time, and the environmental data can be retested after the gallium oxide crystal is grown for a certain number of times.
The heating power refers to the heating power of the heating ring to the crucible, the cooling power refers to the power for cooling the environment in the crystal growth furnace by adopting liquid, the atmosphere type refers to the type of gas introduced into the crystal growth furnace, and the gas type comprises O2，Ar，N2，CO2The cavity pressure refers to the pressure in the crystal growth furnace, the gas flow refers to the gas flow introduced into the crystal growth furnace, and the seed rod pulling speedThe crystal growth rate is the speed of pulling up a seed rod in the crystal growth process, the crystal rotating speed is the speed of driving the crystal to rotate by the seed rod in the crystal growth process, the crystallization rate is the proportion of melting gallium oxide raw materials to form crystals, and the ratio of the crystal to crucible diameter is the proportion of the generated crystal diameter to the crucible diameter. These parameters are all control parameters that influence the preparation of crystals by the guided mode method.
In an implementation manner of this embodiment, the step S210 of obtaining the pre-processing preparation data according to the seed crystal data, the environment data and the control data includes:
s211, determining a preparation vector according to the seed crystal data, the environment data and the control data; wherein, the first element in the preparation vector is one of the full width at half maximum of the diffraction peak of the seed crystal, the deviation value of the full width at half maximum of the diffraction peak of the seed crystal, the thickness of the seed crystal and the width of the seed crystal; the second element in the preparation vector is one of the thermal resistance value of the upper heat-preservation cover, the thermal resistance value deviation value of the upper heat-preservation cover, the shape factor of a crystal growth channel, the shape factor of a crystal growth observation hole, the thermal resistance value of the lower heat-preservation cover, the thermal resistance value deviation value of the lower heat-preservation cover, the relative height of the crucible and the heating coil, the relative height of the heating ring and the heating coil, the width of a gap of a mold opening and the thickness of the gap of the mold opening; the third element in the preparation vector is one of the heating power, the cooling power, the atmosphere type, the cavity pressure, the gas flow and the seed rod pulling speed;
s212, determining the preprocessing preparation data according to the preparation vector.
Specifically, from the seed data a, the environment data B, and the control data C, the preparation vector (a, B, C) is determined. Seed data a is selected from: the seed crystal diffraction peak half-height width A1, the seed crystal diffraction peak half-height width deviation A2, the seed crystal thickness A3 and the seed crystal width A4. The environmental data B is selected from: the thermal resistance value of the upper heat-preservation cover B1, the thermal resistance value deviation value of the upper heat-preservation cover B2, the crystal growth channel shape factor B3, the crystal growth observation hole shape factor B4, the thermal resistance value of the lower heat-preservation cover B5, the thermal resistance value deviation value of the lower heat-preservation cover B6, the relative height B7 of the crucible and the induction coil, the relative height B8 of the heating ring and the induction coil, the width B9 of the die opening gap and the thickness B10 of the die opening gap. The control data C is selected from: heating power C1, cooling power C2, atmosphere type C3, cavity pressure C4, gas flow C5 and seed rod pulling speed C6. That is, a in the preparation vector (a, B, C) may be one of a1, a2, A3, a4, B may be one of B1, B2, B3, B4, B5, B6, B7, B8, B9, B10, and C may be one of C1, C2, C3, C4, C5, C6. 240 preparation vectors can be formed.
And arranging all the preparation vectors according to the sequence numbers to form a matrix, thus obtaining the preprocessed preparation data.
Specifically, the preparation data for the pretreatment were as follows:
of course, other arrangements are also used to obtain the pre-processed preparation data.
S300, inputting the preprocessed preparation data into a trained neural network model, and obtaining the corresponding prediction quality data of the gallium oxide single crystal through the trained neural network model.
Specifically, the prediction quality data includes: predicting crack data, predicting mixed crystal data, predicting half height width of a diffraction peak, predicting half height width deviation value of the diffraction peak, predicting shouldering symmetry of the gallium oxide crystal, predicting left edge folding and unfolding degree of the gallium oxide crystal, predicting right edge folding and unfolding degree of the gallium oxide crystal, predicting thickness of the gallium oxide crystal and predicting thickness deviation of the gallium oxide crystal. The crack data refers to crack grade data, and the predicted crack data refers to predicted crack grade data, for example, the crack may be divided into a plurality of grades, for example, if the crack is divided into 3 grades, the crack data are: 1. 2 and 3.
The mixed crystal data refers to mixed crystal grade data, and the predicted mixed crystal data refers to predicted mixed crystal grade data, for example, the mixed crystal can be divided into multiple grades, for example, the mixed crystal is divided into 3 grades, and then the mixed crystal data are respectively: 1. 2 and 3.
The predicted half-height width of the diffraction peak refers to the predicted half-height width of the diffraction peak, the predicted half-height width radial deviation value of the diffraction peak refers to the predicted difference value of the half-height width of the diffraction peak in the radial direction, and the predicted half-height width axial deviation value of the diffraction peak refers to the predicted difference value of the half-height width of the diffraction peak in the axial direction.
In some embodiments, the trained neural network model is obtained by training using the following training steps:
s01, acquiring training data of gallium oxide single crystal preparation by a guide mode method and corresponding actual quality data, wherein the training data comprises: seed training data, environmental training data, and control training data.
Specifically, the training data refers to data used for training in preparing the gallium oxide single crystal by the guided mode method, and the actual quality data refers to data of the actual quality of the gallium oxide single crystal prepared by the guided mode method. And forming a training set through the training data and the actual quality data, and training a preset neural network model based on the training set to obtain the trained neural network model.
When data are collected to obtain a training set, preparing the gallium oxide single crystal by adopting a guide mode method, recording data of preparing the gallium oxide single crystal as training data, and analyzing the quality of the gallium oxide single crystal after the gallium oxide single crystal is obtained to obtain actual quality data. In order to facilitate the training of the neural network model, data as much as possible can be collected to form a training set.
And S02, preprocessing the training data to obtain preprocessed training data.
Specifically, after the training data is obtained, the training data is preprocessed to obtain preprocessed training data. The preprocessing process may refer to step S200.
And S03, inputting the preprocessed training data into a preset neural network model, and obtaining the predicted training generation quality data corresponding to the preprocessed training data through the preset neural network model.
Specifically, the preprocessed training data are input into a preset neural network model, and quality data generated by predictive training are obtained through the preset neural network model. The predictive training generation quality data comprises: predicting the crack data generated by training, predicting the mixed crystal data generated by training, predicting the full width at half maximum of the diffraction peak generated by training, predicting the radial deviation value of the full width at half maximum of the diffraction peak generated by training and predicting the axial deviation value of the full width at half maximum of the diffraction peak generated by training.
And S04, adjusting and correcting the model parameters of the preset neural network model according to the predicted training generated quality data and the actual quality data to obtain the trained neural network model.
Specifically, according to the predicted training generated quality data and the actual quality data, the model parameters of the preset neural network model are corrected, the preprocessed training data are continuously input into the preset neural network model, and the step (i.e., step S03) of obtaining the predicted training generated quality data corresponding to the preprocessed training data through the preset neural network model is performed until a preset training condition is met, so that the trained neural network model is obtained.
Specifically, according to the quality data generated by the predictive training and the actual quality data, the model parameters of the preset neural network model are corrected, the preprocessing training data are input into the preset neural network model, and the quality data generated by the predictive training corresponding to the preprocessing training data are obtained through the preset neural network model until preset training conditions are met, so that the trained neural network model is obtained. That is, if the preset neural network model meets the preset training condition, the trained neural network model is obtained. And if the preset neural network model does not meet the preset training condition, returning to the step S03 until the preset neural network model meets the preset training condition to obtain the trained neural network model.
In an implementation manner of the embodiment of the present invention, a loss function value of a preset neural network model is determined according to the prediction training generated quality data and the actual quality data, and a model parameter of the preset neural network model is corrected according to the loss function value. Specifically, a gradient-based method is adopted to correct parameters of the preset neural network model, and after a loss function value of the preset neural network model is determined, the corrected parameters of the preset neural network model are determined according to the gradient of the loss function value to the parameters of the preset neural network model, the parameters of the preset neural network model and a preset learning rate.
The preset training conditions comprise: and the loss function value meets the preset requirement and/or the training times of the preset neural network model reach the preset times.
The preset requirement is determined according to the precision and efficiency of the preset neural network model, for example, the loss function value of the preset neural network model reaches a minimum value or does not change any more. The preset number is the maximum training number of the preset neural network model, for example, 4000 times.
The loss function of the preset neural network model comprises the following steps: mean square error, root mean square error, mean absolute error, and the like.
In an implementation manner of the embodiment of the present application, the preset neural network model includes: the device comprises a feature extraction module and a full connection module.
For example, the preset neural network model includes: the device comprises a first convolution unit, a second convolution unit, a third convolution unit, a fourth convolution unit and a full connection unit. Specifically, the first convolution unit includes: two convolutional layers and one pooling layer. The second convolution unit, the third convolution unit and the fourth convolution unit all comprise three convolution layers and one pooling layer. The full-link unit includes three full-link layers.
The convolutional layer and the full link layer are responsible for mapping input data, and this process uses parameters such as weight and bias, and also needs to use an activation function. The pooling layer is a fixed and invariant function operation. Specifically, the convolutional layer functions to extract features; the pooling layer performs pooling operation on the input features to change the space size of the input features; and the full connection layer is fully connected to all data in the previous layer.
In some embodiments, the step S03 of inputting the preprocessed training data into a preset neural network model, and obtaining, by the preset neural network model, predicted training generation quality data corresponding to the preprocessed training data includes:
s031 inputting the preprocessed training data into the feature extraction module, and obtaining feature vectors corresponding to the preprocessed training data through the feature extraction module;
s032, inputting the feature vector into the full-connection module, and obtaining prediction training generation quality data corresponding to the pre-processing training data through the full-connection module.
Specifically, the preprocessed training data are input into a preset neural network model, a feature vector corresponding to the preprocessed training data is output through the feature extraction module in the preset neural network model, the feature vector is input into the full-connection module, and quality data generated by predictive training corresponding to the preprocessed training data output by the full-connection module are obtained.
Based on the above method for predicting gallium oxide quality based on deep learning and guided mode method, this embodiment provides a method for preparing gallium oxide based on deep learning and guided mode method, as shown in fig. 3, where the method includes:
and S10, acquiring target quality data of the target gallium oxide single crystal.
Specifically, if it is desired to obtain a target gallium oxide single crystal, target mass data of the target gallium oxide single crystal, that is, mass data of the desired gallium oxide single crystal, may be determined first. The target quality data comprises: target crack data, target mixed crystal data, target diffraction peak full width at half maximum radial deviation value and target diffraction peak full width at half maximum axial deviation value.
S20, determining target preparation data corresponding to the target gallium oxide single crystal according to the target quality data and the trained neural network model, wherein the target preparation data comprise: target seed crystal data, target environment data and target control data, wherein the target environment data comprises the width of a target die orifice gap and the thickness of the target die orifice gap.
Specifically, target preparation data corresponding to the target gallium oxide single crystal is determined according to the target quality data and a trained neural network model. When it is required to be mentioned, since different preparation data can obtain the same quality data, when the target preparation data corresponding to the target gallium oxide single crystal is determined according to the target quality data and the trained neural network model, the target preparation data is not unique, and one target preparation data is determined according to the control difficulty of each data in a plurality of target preparation data, thereby facilitating to obtain the target gallium oxide single crystal.
In some embodiments, the step S20 of determining target preparation data corresponding to the target gallium oxide single crystal according to the target quality data and the trained neural network model includes:
s21, acquiring preset preparation data, and preprocessing the preset preparation data to obtain preprocessed preset preparation data;
s22, inputting the preprocessing preset preparation data into a trained neural network model, and obtaining prediction quality data corresponding to the preprocessing preset preparation data through the trained neural network model;
and S23, correcting the preset preparation data according to the predicted quality data and the target quality data to obtain target preparation data corresponding to the target gallium oxide single crystal.
Specifically, the preparation data may be preset first, and the preset preparation data is preprocessed to obtain preprocessed preset preparation data, where the specific preprocessing process may refer to step S200. Inputting the preprocessed preset preparation data into a trained neural network model to obtain predicted quality data for correcting the preprocessed preset preparation data, then correcting the preset preparation data according to the predicted quality data and the target quality data, and when a difference value between the predicted quality data and the target quality data is smaller than a preset threshold value, using the corrected preset preparation data as the target preparation data.
And S30, preparing and obtaining the target gallium oxide single crystal according to the target preparation data based on a mode guide method.
Specifically, after the target preparation data is obtained, the target gallium oxide single crystal can be prepared according to the target preparation data by a mold-guiding method.
Based on the prediction method or the preparation method, the invention provides a gallium oxide preparation system based on a deep learning and mode-guiding method, which can be computer equipment, and the internal structure of the system is shown in fig. 4. The system comprises a processor, a memory, a network interface, a display screen and an input device which are connected through a system bus. Wherein the processor of the system is configured to provide computing and control capabilities. The memory of the system comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the system is used for communicating with an external terminal through network connection. The computer program is executed by a processor to realize a prediction method of gallium oxide based on the deep learning and guided mode method or a preparation method of gallium oxide based on the deep learning and guided mode method. The display screen of the system can be a liquid crystal display screen or an electronic ink display screen, and the input device of the system can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on a system shell, an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the block diagram of FIG. 4 is merely a partial block diagram of the structure associated with the disclosed aspects and is not intended to limit the systems to which the disclosed aspects apply, and that a particular system may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a system for preparing gallium oxide based on deep learning and guided mode method is provided, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the prediction method or the steps of the preparation method when executing the computer program.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A gallium oxide quality prediction method based on deep learning and a guided mode method is characterized by comprising the following steps:
acquiring preparation data of preparing the gallium oxide single crystal by a guide die method, wherein the preparation data comprises seed crystal data, environment data and control data, and the control data comprises the width and the thickness of a die opening gap;
preprocessing the preparation data to obtain preprocessed preparation data;
inputting the preprocessing preparation data into a trained neural network model, and obtaining the corresponding prediction quality data of the gallium oxide single crystal through the trained neural network model.
2. The method for predicting the quality of gallium oxide based on deep learning and guided mode method according to claim 1, wherein the step of preprocessing the preparation data to obtain preprocessed preparation data comprises:
and obtaining pre-processing preparation data according to the seed crystal data, the environment data and the control data, wherein the pre-processing preparation data is a matrix formed by the seed crystal data, the environment data and the control data.
3. The method for predicting the quality of gallium oxide based on deep learning and guided mode method according to claim 2, wherein the seed data comprises: the half-height width of the diffraction peak of the seed crystal, the deviation value of the half-height width of the diffraction peak of the seed crystal, the thickness of the seed crystal and the width of the seed crystal;
the environmental data further includes: the thermal resistance value of the upper heat-preservation cover, the thermal resistance value deviation value of the upper heat-preservation cover, the shape factor of a crystal growth channel, the shape factor of a crystal growth observation hole, the thermal resistance value of the lower heat-preservation cover, the thermal resistance value deviation value of the lower heat-preservation cover, the relative height of the crucible and the heating coil, and the relative height of the heating ring and the heating coil;
the control data includes: heating power, cooling power, atmosphere type, cavity pressure, gas flow and seed rod pulling speed.
4. The method for predicting the quality of gallium oxide based on deep learning and guided mode method according to claim 3, wherein the step of obtaining pre-processing preparation data according to the seed crystal data, environmental data and control data comprises:
determining a preparation vector according to the seed crystal data, the environment data and the control data; wherein, the first element in the preparation vector is one of the full width at half maximum of the diffraction peak of the seed crystal, the deviation value of the full width at half maximum of the diffraction peak of the seed crystal, the thickness of the seed crystal and the width of the seed crystal; the second element in the preparation vector is one of the thermal resistance value of the upper heat-preservation cover, the thermal resistance value deviation value of the upper heat-preservation cover, the shape factor of a crystal growth channel, the shape factor of a crystal growth observation hole, the thermal resistance value of the lower heat-preservation cover, the thermal resistance value deviation value of the lower heat-preservation cover, the relative height of the crucible and the heating coil, the relative height of the heating ring and the heating coil, the width of a gap of a mold opening and the thickness of the gap of the mold opening; the third element in the preparation vector is one of the heating power, the cooling power, the atmosphere type, the cavity pressure, the gas flow and the seed rod pulling speed;
and determining the preprocessing preparation data according to the preparation vector.
5. The method for predicting the quality of gallium oxide based on deep learning and guided mode method according to claim 1, wherein the prediction quality data comprises: predicting crack data, predicting mixed crystal data, predicting half height width of a diffraction peak, predicting half height width deviation value of the diffraction peak, predicting shouldering symmetry of the gallium oxide crystal, predicting left edge folding and unfolding degree of the gallium oxide crystal, predicting right edge folding and unfolding degree of the gallium oxide crystal, predicting thickness of the gallium oxide crystal and predicting thickness deviation of the gallium oxide crystal.
6. The method for predicting the quality of gallium oxide based on deep learning and guided mode method according to claim 1, wherein the trained neural network model is obtained by training with the following training steps:
acquiring training data of gallium oxide single crystal preparation by a guide mode method and corresponding actual quality data, wherein the training data comprises: seed crystal training data, environment training data and control training data;
preprocessing the training data to obtain preprocessed training data;
inputting the preprocessed training data into a preset neural network model, and obtaining predicted training generation quality data corresponding to the preprocessed training data through the preset neural network model;
and adjusting and correcting the model parameters of the preset neural network model according to the predicted training generated quality data and the actual quality data to obtain the trained neural network model.
7. The method for predicting the quality of gallium oxide based on deep learning and guided mode method according to claim 6, wherein the preset neural network model comprises: a feature extraction module and a full-connection module,
inputting the preprocessed training data into a preset neural network model, and obtaining the predicted training generation quality data corresponding to the preprocessed training data through the preset neural network model, wherein the step of obtaining the predicted training generation quality data comprises the following steps:
inputting the preprocessed training data into the feature extraction module, and obtaining feature vectors corresponding to the preprocessed training data through the feature extraction module;
and inputting the feature vector into the full-connection module, and obtaining prediction training generation quality data corresponding to the preprocessing training data through the full-connection module.
8. A gallium oxide preparation method based on deep learning and a guided mode method is characterized by comprising the following steps:
obtaining target quality data of a target gallium oxide single crystal;
determining target preparation data corresponding to the target gallium oxide single crystal according to the target quality data and the trained neural network model, wherein the target preparation data comprises: target seed crystal data, target environment data and target control data, wherein the target environment data comprises the width of a target die opening gap and the thickness of the target die opening gap;
and preparing the target gallium oxide single crystal according to the target preparation data based on a mode-guiding method.
9. The method for preparing gallium oxide based on deep learning and guided mode method according to claim 8, wherein the target preparation data corresponding to the target gallium oxide single crystal is determined according to the target quality data and the trained neural network model, comprising the steps of:
acquiring preset preparation data, and preprocessing the preset preparation data to obtain preprocessed preset preparation data;
inputting the preprocessing preset preparation data into a trained neural network model, and obtaining prediction quality data corresponding to the preprocessing preset preparation data through the trained neural network model;
and correcting the preset preparation data according to the predicted quality data and the target quality data to obtain target preparation data corresponding to the target gallium oxide single crystal.
10. A system for preparing gallium oxide based on deep learning and guided mode method, comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor executes the computer program to implement the steps of the prediction method according to any one of claims 1 to 7 or the steps of the preparation method according to any one of claims 8 to 9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011640976.7A CN112859771A (en) | 2020-12-31 | 2020-12-31 | Quality prediction method, preparation method and system of gallium oxide based on deep learning and model-guiding method |
| PCT/CN2021/076086 WO2022141768A1 (en) | 2020-12-31 | 2021-02-08 | Quality prediction method, preparation method, and preparation system for gallium oxide based on deep learning and edge-defined film-fed growth technique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011640976.7A CN112859771A (en) | 2020-12-31 | 2020-12-31 | Quality prediction method, preparation method and system of gallium oxide based on deep learning and model-guiding method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112859771A true CN112859771A (en) | 2021-05-28 |
Family
ID=76000789
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011640976.7A Pending CN112859771A (en) | 2020-12-31 | 2020-12-31 | Quality prediction method, preparation method and system of gallium oxide based on deep learning and model-guiding method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112859771A (en) |
| WO (1) | WO2022141768A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115874267A (en) * | 2022-12-15 | 2023-03-31 | 中国科学院上海光学精密机械研究所 | Thermal field structure for growing symmetrical shouldered gallium oxide crystal by die-guiding method |
| CN116934727A (en) * | 2023-07-28 | 2023-10-24 | 保定景欣电气有限公司 | Seed crystal welding control method and device in crystal pulling process and electronic equipment |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111695287A (en) * | 2020-04-22 | 2020-09-22 | 山东天岳先进材料科技有限公司 | Method and equipment for predicting overall temperature field in SiC single crystal furnace |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07118090A (en) * | 1993-10-20 | 1995-05-09 | Sumitomo Metal Ind Ltd | Method for growing single crystal and its device |
| JP4611103B2 (en) * | 2005-05-09 | 2011-01-12 | 株式会社光波 | Method for producing β-Ga2O3 crystal |
| CN111368434B (en) * | 2020-03-05 | 2023-05-12 | 包头美科硅能源有限公司 | Prediction method of Czochralski method monocrystalline silicon solid-liquid interface based on ANN |
| CN111893563A (en) * | 2020-08-25 | 2020-11-06 | 连城凯克斯科技有限公司 | Single crystal furnace capable of automatically adjusting shouldering process parameters and control method |
-
2020
- 2020-12-31 CN CN202011640976.7A patent/CN112859771A/en active Pending
-
2021
- 2021-02-08 WO PCT/CN2021/076086 patent/WO2022141768A1/en active Application Filing
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111695287A (en) * | 2020-04-22 | 2020-09-22 | 山东天岳先进材料科技有限公司 | Method and equipment for predicting overall temperature field in SiC single crystal furnace |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115874267A (en) * | 2022-12-15 | 2023-03-31 | 中国科学院上海光学精密机械研究所 | Thermal field structure for growing symmetrical shouldered gallium oxide crystal by die-guiding method |
| CN116934727A (en) * | 2023-07-28 | 2023-10-24 | 保定景欣电气有限公司 | Seed crystal welding control method and device in crystal pulling process and electronic equipment |
| CN116934727B (en) * | 2023-07-28 | 2024-03-08 | 保定景欣电气有限公司 | Seed crystal welding control method and device in crystal pulling process and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022141768A1 (en) | 2022-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112834700B (en) | Quality prediction method, preparation method and system of high-resistance gallium oxide based on deep learning and guided mode method | |
| CN112859771A (en) | Quality prediction method, preparation method and system of gallium oxide based on deep learning and model-guiding method | |
| WO2022141752A1 (en) | Deep learning and czochralski method-based quality prediction method and preparation method and system for conductive gallium oxide | |
| CN112820360A (en) | Quality prediction method, preparation method and system of high-resistance gallium oxide based on deep learning and Czochralski method | |
| CN112837758A (en) | Conductive gallium oxide quality prediction method, preparation method and system based on deep learning and guided mode method | |
| WO2022141766A1 (en) | Conductivity type gallium oxide preparation method based on deep learning and heat exchange method | |
| WO2022141756A1 (en) | Gallium oxide preparation method and system based on deep learning and bridgman-stockbarger method | |
| CN112853470A (en) | Quality prediction method, preparation method and system of gallium oxide based on deep learning and Czochralski method | |
| US12026616B2 (en) | Preparation method of high resistance gallium oxide based on deep learning and vertical bridgman growth method | |
| US12031230B2 (en) | Quality prediction method, preparation method and system of high resistance gallium oxide based on deep learning and Czochralski method | |
| WO2022141750A1 (en) | Gallium oxide preparation method and system based on deep learning and heat exchange method | |
| WO2022141755A1 (en) | High-resistance type gallium oxide preparation method based on deep learning and heat exchange method | |
| US20230170055A1 (en) | Preparation method of conductive gallium oxide based on deep learning and vertical bridgman growth method | |
| JPWO2022141752A5 (en) | ||
| JPWO2022141758A5 (en) |
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 |