A method, preparation method and system for predicting the quality of conductive gallium oxide based on deep learning and a guided mode method

Abstract

The application discloses a kind of based on deep learning and guided mode method's electrically conductive gallium oxide quality prediction method, preparation method and system, quality prediction method includes steps: obtaining the preparation data of guided mode method preparation electrically conductive gallium oxide single crystal, the preparation data includes seed crystal data, environmental data and control data, the control data includes doping element concentration, doping element type;The preparation data is preprocessed, and preprocessed preparation data is obtained;The preprocessed preparation data is input into the trained neural network model, and the predicted quality data corresponding to the electrically conductive gallium oxide single crystal is obtained by the trained neural network model, and the predicted quality data includes predicted carrier concentration.The electrically conductive gallium oxide single crystal quality can be predicted by the trained neural network model, so the performance of the required electrically conductive gallium oxide single crystal can be obtained by adjusting the preparation data, so that the performance of the electrically conductive gallium oxide single crystal is optimized.

Description

Technical Field

[0001] This invention relates to the field of conductive gallium oxide crystal fabrication, and particularly to a method, fabrication method, and system for predicting the quality of conductive gallium oxide based on deep learning and the guided mode method. Background Technology

[0002] β-Ga₂O₃ (conductive gallium oxide) is a direct wide-bandgap semiconductor material with a bandgap of approximately 4.8–4.9 eV. It possesses numerous advantages, including a large bandgap, high saturated electron drift velocity, high thermal conductivity, high breakdown field strength, and stable chemical properties, making it promising for applications in high-temperature, high-frequency, and high-power power electronic devices. Furthermore, it can be used in LED chips, solar-blind ultraviolet detectors, various sensor components, and camera elements.

[0003] Currently, the main method for mass production of large-size conductive gallium oxide crystals is the mold-guided method. The mold-guided method is a mature single-crystal preparation technique with advantages such as irregular crystal growth, fast growth speed, and low growth cost. The mold-guided method is a crystal growth method improved upon the mold-guided method, and its crystal growth equipment and processes are relatively more complex. The mold-guided method requires placing a mold inside a crucible, with the crystal growth interface located on the upper surface of the mold. At high temperatures, due to surface tension, the melt rises along the capillary in the mold to the upper surface. The height H of the melt rising along the capillary is given by the formula... The formula is determined by the following: γ is the surface tension of the melt, θ is the contact angle between the melt and the capillary, ρ is the melt density, g is the gravitational acceleration, and r is the radius of the capillary.

[0004] Compared with the mode-guided method, the mode-guided method has the following advantages in preparing conductive gallium oxide crystals:

[0005] 1. The melt convection in the mold capillary is weak. After the impurity ions in the melt rise from the capillary to the solid-liquid interface, it is difficult for them to return to the crucible. The segregation coefficient of impurity ions in the crystal is generally close to 1, and the distribution of impurities in the upper and lower parts of the crystal is good.

[0006] 2. The solid-liquid interface of crystal growth is located above the mold, and the interface shape can be controlled by the geometry of the mold surface. The position of the solid-liquid interface in the temperature field remains unchanged and is not affected by the disturbance of the melt in the crucible. Therefore, the solid-liquid interface of crystal growth is more stable in the mold guiding method.

[0007] 3. The guided crystal growth method has a faster crystal growth rate, which helps to reduce energy consumption. It can grow irregularly shaped crystals, thereby reducing crystal processing costs and processing losses.

[0008] However, in the process of preparing conductive gallium oxide crystals using the guided mold method, variations in parameters such as the temperature field distribution near the mold opening, the selection of the seed crystal, the seed rod pulling speed, the crystal growth atmosphere, and the heating and cooling power all significantly affect the quality of the resulting conductive gallium oxide crystals. Existing guided mold methods for preparing conductive gallium oxide crystals rely on operator experience to set parameters, resulting in poor repeatability and consequently, poor stability of the prepared conductive gallium oxide crystal products.

[0009] Therefore, existing technologies still need to be improved and developed. Summary of the Invention

[0010] The technical problem to be solved by this invention is to provide a quality prediction method, preparation method and system for conductive gallium oxide based on deep learning and the guided mode method, which addresses the shortcomings of the existing technology. The aim is to solve the problem that the process of preparing conductive gallium oxide crystals by the guided mode method relies on the operator's experience to set parameters, which has poor repeatability and results in poor quality and stability of the prepared conductive gallium oxide crystals.

[0011] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0012] A method for predicting the quality of conductive gallium oxide based on deep learning and the guided mode method, comprising the following steps:

[0013] The preparation data for preparing conductive gallium oxide single crystals by the guided mode method are obtained. The preparation data includes seed crystal data, environmental data, and control data. The control data includes dopant concentration and dopant type.

[0014] The preparation data is preprocessed to obtain preprocessed preparation data;

[0015] The preprocessed data is input into a trained neural network model, and the predicted quality data corresponding to the conductive gallium oxide single crystal is obtained through the trained neural network model. The predicted quality data includes the predicted carrier concentration.

[0016] The method for predicting the quality of conductive gallium oxide based on deep learning and the guided mode method includes the following step: preprocessing the preparation data to obtain preprocessed preparation data.

[0017] Based on the seed crystal data, environmental data, and control data, pretreatment preparation data is obtained, which is a matrix formed by the seed crystal data, environmental data, and control data.

[0018] The method for predicting the quality of conductive gallium oxide based on deep learning and mode guidance includes seed crystal data such as: seed crystal diffraction peak full width at half maximum (FWHM), seed crystal diffraction peak FWHM deviation value, seed crystal thickness, and seed crystal width.

[0019] The environmental data also includes: thermal resistance value of the upper insulation cover, thermal resistance value deviation of the upper insulation cover, shape factor of the crystal growth channel, shape factor of the crystal growth observation hole, thermal resistance value of the lower insulation cover, thermal resistance value deviation of the lower insulation cover, relative height between the crucible and the heating coil, relative height between the heating ring and the heating coil, width of the mold opening gap, and thickness of the mold opening gap.

[0020] The control data includes: heating power, cooling power, atmosphere type, cavity pressure, gas flow rate, and seed crystal rod pulling speed.

[0021] The method for predicting the quality of conductive gallium oxide based on deep learning and the guided mode method includes the following steps for obtaining preprocessed preparation data based on the seed crystal data, environmental data, and control data:

[0022] Based on the seed crystal data, environmental data, and control data, a preparation vector is determined. The first element of the preparation vector is one of the seed crystal diffraction peak full width at half maximum (FWHM), the seed crystal diffraction peak FWHM deviation, the seed crystal thickness, and the seed crystal width. The second element of the preparation vector is one of the upper insulation cover thermal resistance, the upper insulation cover thermal resistance deviation, the crystal growth channel shape factor, the crystal growth observation hole shape factor, the lower insulation cover thermal resistance, the lower insulation cover thermal resistance deviation, the relative height between the crucible and the heating coil, the relative height between the heating ring and the heating coil, the width of the mold opening gap, the thickness of the mold opening gap, the doping element concentration, and the doping element type, where the doping element type includes Si, Ge, Sn, Zr, Hf, In, Ta, Nb, V, W, and Mo. The third element of the preparation vector is one of the heating power, cooling power, atmosphere type, cavity pressure, gas flow rate, and seed crystal rod pulling speed.

[0023] The preprocessing preparation data is determined based on the preparation vector.

[0024] The method for predicting the quality of conductive gallium oxide based on deep learning and the guided mode method includes the following predicted quality data: predicted crack data, predicted impurity data, predicted diffraction peak full width at half maximum (FWHM), predicted diffraction peak FWHM deviation, predicted shoulder symmetry of conductive gallium oxide crystal, predicted shrinkage / expansion of the left edge of conductive gallium oxide crystal, predicted shrinkage / expansion of the right edge of conductive gallium oxide crystal, predicted thickness of conductive gallium oxide crystal, predicted thickness deviation of conductive gallium oxide crystal, predicted radial deviation of carrier concentration, and predicted axial deviation of carrier concentration.

[0025] The aforementioned method for predicting the quality of conductive gallium oxide based on deep learning and the guided mode method, wherein the trained neural network model is trained using the following steps:

[0026] Training data for preparing conductive gallium oxide single crystals using the guided mode method, as well as corresponding actual quality data, are obtained. The training data includes seed crystal training data, environmental training data, and control training data.

[0027] The training data is preprocessed to obtain preprocessed training data;

[0028] The preprocessed training data is input into a preset neural network model, and the preset neural network model is used to obtain the prediction training generation quality data corresponding to the preprocessed training data.

[0029] The model parameters of the preset neural network model are adjusted and corrected based on the predicted training quality data and the actual quality data to obtain a trained neural network model.

[0030] The aforementioned method for predicting the quality of conductive gallium oxide based on deep learning and guided modeling, wherein the preset neural network model includes: a feature extraction module and a fully connected module.

[0031] The steps of inputting the preprocessed training data into a preset neural network model and obtaining prediction training generation quality data corresponding to the preprocessed training data through the preset neural network model include:

[0032] The preprocessed training data is input into the feature extraction module, and the feature extraction module obtains the feature vector corresponding to the preprocessed training data.

[0033] The feature vector is input into the fully connected module, and the prediction training generation quality data corresponding to the preprocessed training data is obtained through the fully connected module.

[0034] A method for fabricating conductive gallium oxide based on deep learning and mode guidance, wherein the fabrication method includes the following steps:

[0035] Obtain target quality data for a target conductivity gallium oxide single crystal, wherein the target quality data includes the target carrier concentration;

[0036] Based on the target quality data and the trained neural network model, the target preparation data corresponding to the target conductive gallium oxide single crystal is determined. The target preparation data includes: target seed crystal data, target environment data, and target control data. The target environment data includes the target doping element concentration and the target doping element type.

[0037] Based on the guided mode method, a target conductive gallium oxide single crystal was prepared according to the target preparation data.

[0038] The method for preparing conductive gallium oxide based on deep learning and the guided model method includes the following steps: determining the target preparation data corresponding to the target conductive gallium oxide single crystal based on the target quality data and the trained neural network model.

[0039] Obtain preset preparation data, and preprocess the preset preparation data to obtain preprocessed preset preparation data;

[0040] The pre-processed preset preparation data is input into a trained neural network model, and the predicted quality data corresponding to the pre-processed preset preparation data is obtained through the trained neural network model.

[0041] Based on the predicted quality data and the target quality data, the preset preparation data is corrected to obtain the target preparation data corresponding to the target conductive gallium oxide single crystal.

[0042] A conductive gallium oxide fabrication system based on deep learning and mode guidance method, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that the processor executes the computer program to implement the steps of the prediction method according to any one of the present invention, or the steps of the fabrication method according to any one of the present invention.

[0043] Beneficial Effects: This invention proposes a method for predicting and preparing conductive gallium oxide (GaO) single crystals based on deep learning and the guided model method. First, the preparation data of conductive GaO single crystals prepared by the guided model method is preprocessed to obtain preprocessed preparation data. Then, the preprocessed preparation data is input into a trained neural network model, which obtains the predicted quality data corresponding to the conductive GaO single crystal. This invention can predict the quality of conductive GaO single crystals through a trained neural network model, thus allowing for adjustments to the preparation data to obtain the desired performance of the conductive GaO single crystal, thereby optimizing its performance. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a schematic diagram of a crystal growth furnace for preparing conductive gallium oxide crystals using the guided-mode method provided by the present invention.

[0046] Figure 2 This is a flowchart of a preferred embodiment of a method for predicting the quality of conductive gallium oxide based on deep learning and the guided mode method provided by the present invention.

[0047] Figure 3 This is a flowchart of a preferred embodiment of a method for preparing conductive gallium oxide based on deep learning and the guided mode method provided by the present invention.

[0048] Figure 4 This is an internal structure diagram of a conductive gallium oxide fabrication system based on deep learning and the guided mode method provided by the present invention. Detailed Implementation

[0049] This invention provides a method and system for preparing conductive gallium oxide crystals based on deep learning and mode guidance. To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining the invention and are not intended to limit the invention.

[0050] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0051] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0052] The invention will be further explained below with reference to the accompanying drawings and the description of the embodiments.

[0053] This invention provides a crystal growth furnace for growing conductive gallium oxide crystals using a mode-guided method, such as... Figure 1 As shown, it includes a lower heat insulation cover 11, a crucible 12 is disposed inside the lower heat insulation cover 11, a mold 13 for forming a capillary effect is disposed inside the crucible 12, and a heating ring 14 is disposed outside the crucible 12; an upper heat insulation cover 15 is disposed above the lower heat insulation cover, a crystal growth channel 16 is disposed inside the upper heat insulation cover 15, a crystal growth observation hole 17 is disposed on the side of the upper heat insulation cover, and an induction coil 18 is disposed around the lower heat insulation cover 10.

[0054] Based on the crystal growth furnace described above, conductive gallium oxide crystals can be prepared. First, the crystal growth furnace for preparing conductive gallium oxide crystals is installed. This includes the selection of the material of the upper heat insulation cover, the size of the axial opening of the upper heat insulation cover, the shape and size of the opening window, the selection of the material of the lower heat insulation cover, the height position of the crucible relative to the induction coil, the relative height of the heating ring and the induction coil, etc. These factors will affect the thermal field distribution inside the device, thereby affecting the product performance of conductive gallium oxide crystals.

[0055] A β-Ga2O3 seed crystal with a specific orientation is placed in a seed crystal fixture and bound and fixed. The orientation of the seed crystal can be

[010] ,

[001] , etc.

[0056] First, turn on the mechanical pump and diffusion pump in sequence to evacuate the equipment. When the predetermined vacuum level is reached, turn off the vacuum equipment and slowly fill the equipment with gas according to the mixed gas volume ratio.

[0057] Then, by setting the heating power, the crucible is heated through the heating element to completely melt the gallium oxide raw material and dopant material placed in the crucible. The molten gallium oxide and dopant material are transported to the top of the mold by capillary action and spread out until they completely cover the top. Subsequently, the seed crystal rod is slowly lowered so that the seed crystal is 3-5 mm above the top of the iridium mold for preheating. After 5-10 minutes, seeding begins. After the seed crystal and the melt are fully fused, a necking operation is performed to prevent the original defects of the seed crystal from extending into the crystal, ensuring crystal quality. Next, shoulder growth is performed to allow the crystal to expand laterally to fill the entire mold. Then, constant diameter growth is performed. After the crystal growth is completed, it is slowly cooled to room temperature, and the crystal is removed, thus obtaining a conductive gallium oxide crystal. During the preparation of conductive gallium oxide crystals, the heating power, cooling power, atmosphere type, cavity pressure, gas flow rate, and seed crystal rod pulling speed all affect the product performance of conductive gallium oxide crystals.

[0058] Based on this, this embodiment provides a method for predicting the quality of conductive gallium oxide based on deep learning and the guided mode method, such as... Figure 2 As shown, it includes the following steps:

[0059] S100. Obtain preparation data for preparing conductive gallium oxide single crystals using the guided mode method. The preparation data includes seed crystal data, environmental data, and control data. The control data includes dopant concentration and dopant type.

[0060] Specifically, the preparation data refers to the data used to prepare conductive gallium oxide single crystals using the guided-mode method. This preparation data can be configured as needed. For example, if it is necessary to predict the performance of conductive gallium oxide single crystals obtained under a certain preparation data, it is only necessary to determine the preparation data, preprocess the preparation data to obtain preprocessed preparation data, and then input the preprocessed preparation data into a trained neural network model. The predicted quality data can be obtained through the trained neural network model. In other words, no experiment is required. After determining the preparation data, the quality data of conductive gallium oxide single crystals can be predicted through the trained neural network model.

[0061] In this embodiment, the preparation data includes: seed crystal data, environmental data, and control data. The seed crystal data refers to the data of the seed crystal used in the preparation of conductive gallium oxide single crystals using the guided-mode method. The environmental data refers to the data of the environment in which the crystal is located during the preparation of conductive gallium oxide single crystals using the guided-mode method. The control data refers to the data controlling crystal growth during the preparation of conductive gallium oxide single crystals using the guided-mode method. The doping element concentration refers to the concentration of doping elements in conductive gallium oxide. The doping element types include: Si, Ge, Sn, Zr, Hf, In, Ta, Nb, V, W, Mo, etc.

[0062] S200. The preparation data is preprocessed to obtain preprocessed preparation data.

[0063] Specifically, after obtaining the preparation data, the preparation data is first preprocessed to obtain preprocessed preparation data, which can then be input into a trained neural network model so that the trained neural network model can process the preprocessed preparation data.

[0064] In one embodiment of this application, step S200, preprocessing the preparation data to obtain preprocessed preparation data, includes:

[0065] S210. Based on the seed crystal data, environmental data, and control data, pretreatment preparation data is obtained, wherein the pretreatment preparation data is a matrix formed by the seed crystal data, environmental data, and control data.

[0066] Specifically, after obtaining the preparation data, it is first preprocessed to obtain preprocessed preparation data. Since the various sub-data in the preparation data (such as seed crystal data, environmental data, and control data) can influence each other, but the extent of their mutual influence is currently unclear, it is necessary to preprocess the preparation data to rearrange and recombine the various sub-data to form preprocessed preparation data.

[0067] In another embodiment of this application, the seed crystal data includes: seed crystal diffraction peak full width at half maximum (FWHM), seed crystal diffraction peak FWHM deviation value, seed crystal thickness, and seed crystal width; the environmental data also includes: upper insulation cover thermal resistance value, upper insulation cover thermal resistance deviation value, crystal growth channel shape factor, crystal growth observation hole shape factor, lower insulation cover thermal resistance value, lower insulation cover thermal resistance deviation value, relative height between the crucible and the heating coil, relative height between the heating ring and the heating coil, mold opening gap width, and mold opening gap thickness; the control data includes: heating power, cooling power, atmosphere type, cavity pressure, gas flow rate, and seed crystal rod pulling speed.

[0068] Specifically, the full width at half maximum (FWHM) of the seed crystal diffraction peaks can be measured using an X-ray diffractometer. The FWHM deviation values ​​include the radial deviation and the axial deviation. The radial direction is the direction on the horizontal plane, and the axial direction is the direction perpendicular to the horizontal plane, i.e., the vertical axis. The radial deviation value can be obtained by measuring the FWHM of the seed crystal diffraction peaks radially and calculating the difference between the radial and axial deviations. The axial deviation value can be obtained by measuring the FWHM of the seed crystal axially and calculating the difference between the axial deviations. The thickness and width of the seed crystal can be directly measured.

[0069] As mentioned above, in adopting Figure 1 When preparing conductive gallium oxide single crystals in the crystal growth furnace shown, both the upper and lower insulation covers provide a stable thermal field for the growth of the conductive gallium oxide single crystals. The thermal resistance value of the upper insulation cover refers to the temperature difference between the inside and outside of the insulation cover when a unit of heat passes through the upper insulation cover per unit time. The larger the thermal resistance value of the upper insulation cover, the stronger its ability to resist heat transfer and the better its insulation effect.

[0070] The thermal resistance deviation of the upper insulation cover includes both radial and axial deviations. The radial deviation can be obtained by measuring the thermal resistance on both radial sides of the upper insulation cover and calculating the difference between these values. Similarly, the axial deviation can be obtained by measuring the thermal resistance on both axial sides of the upper insulation cover and calculating the difference between these values.

[0071] Similarly, the thermal resistance value of the lower insulation cover and the deviation value of the thermal resistance value of the lower insulation cover can be obtained by using the same method. The deviation value of the thermal resistance value of the lower insulation cover includes the radial deviation value and the axial deviation value of the thermal resistance value of the lower insulation cover.

[0072] The crystal growth channel shape factor refers to the value of the shape and size of the 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 includes 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.

[0073] The crystal growth observation hole shape factor also refers to the value of the shape and size of the crystal growth observation hole. The shape of the crystal growth observation hole will also affect the thermal field distribution of the crystal growth environment, thereby affecting the crystal growth performance.

[0074] Since the crucible is heated by an induction coil and a heating ring, the relative height between the crucible and the induction coil, and the relative height between the heating ring and the induction coil, will affect the thermal field distribution of the crystal growth environment.

[0075] In this embodiment, the control data includes the width and thickness of the mold opening gap. Molten conductive gallium oxide is mainly transported to the top of the mold through the capillary action of the mold opening gap, thereby gradually growing into a conductive gallium oxide crystal on the seed crystal. Therefore, the width and thickness of the mold opening gap have a significant impact on the quality of the conductive gallium oxide single crystal.

[0076] With the use of the device for growing conductive gallium oxide crystals, the thermal resistance values ​​of the upper and lower insulation covers, as well as the deviation values ​​of the upper and lower insulation covers, will change. However, these changes will not occur in a short period of time. These environmental data can be retested after a certain number of crystal growth cycles.

[0077] The heating power refers to the heating power of the heating ring on the crucible; the cooling power refers to the power of the liquid used to cool the environment inside the crystal growth furnace; the atmosphere type refers to the type of gas introduced into the crystal growth furnace, including O2, Ar, N2, CO2, etc.; the cavity pressure refers to the pressure inside the crystal growth furnace; the gas flow rate refers to the gas flow rate introduced into the crystal growth furnace; the seed rod pulling speed refers to the speed at which the seed rod is pulled upwards during crystal growth; the crystal rotation speed refers to the speed at which the seed rod drives the crystal to rotate during crystal growth; the crystallization rate refers to the proportion of molten conductive gallium oxide raw material to form crystals; and the crystal-to-crucible diameter ratio refers to the ratio of the diameter of the generated crystal to the diameter of the crucible. These parameters are all control parameters affecting the crystal preparation method using the guided mold method.

[0078] In one embodiment of this example, step S210, the step of obtaining preprocessing preparation data based on the seed crystal data, environmental data, and control data, includes:

[0079] S211. Based on the seed crystal data, environmental data, and control data, determine the preparation vector; wherein, the first element of the preparation vector is one of the seed crystal diffraction peak half-width at half-maximum (FWHM), the seed crystal diffraction peak FWHM deviation value, the seed crystal thickness, and the seed crystal width; the second element of the preparation vector is one of the upper heat insulation cover thermal resistance value, the upper heat insulation cover thermal resistance deviation value, the crystal growth channel shape factor, the crystal growth observation hole shape factor, the lower heat insulation cover thermal resistance value, the lower heat insulation cover thermal resistance deviation value, the relative height between the crucible and the heating coil, the relative height between the heating ring and the heating coil, the width of the mold opening gap, the thickness of the mold opening gap, the doping element concentration, and the doping element type, wherein the doping element type includes Si, Ge, Sn, Zr, Hf, In, Ta, Nb, V, W, and Mo; the third element of the preparation vector is one of the heating power, cooling power, atmosphere type, cavity pressure, gas flow rate, and seed crystal rod pulling speed.

[0080] S212. Determine the preprocessing preparation data based on the preparation vector.

[0081] Specifically, the preparation vector (A, B, C) is determined based on seed crystal data A, environmental data B, and control data C. Seed crystal data A is selected from: seed crystal diffraction peak full width at half maximum (FWHM) A1, seed crystal diffraction peak FWHM deviation value A2, seed crystal thickness A3, and seed crystal width A4. Environmental data B is selected from: upper insulation cover thermal resistance value B1, upper insulation cover thermal resistance deviation value B2, crystal growth channel shape factor B3, crystal growth observation hole shape factor B4, lower insulation cover thermal resistance value B5, lower insulation cover thermal resistance deviation value B6, relative height between the crucible and the induction coil B7, relative height between the heating ring and the induction coil B8, mold opening gap width B9, mold opening gap thickness B10, dopant concentration 11, and dopant type 12. Control data C is selected from: heating power C1, cooling power C2, atmosphere type C3, cavity pressure C4, gas flow rate C5, and seed crystal rod pulling speed C6. In other words, in the preparation vector (A, B, C), A can be one of A1, A2, A3, A4; B can be one of B1, B2, B3, B4, B5, B6, B7, B8, B9, B10, B11, B12; and C can be one of C1, C2, C3, C4, C5, C6. This results in 288 preparation vectors.

[0082] Arrange all the preparation vectors in order of their numbers to form a matrix, and you will get the preprocessed preparation data.

[0083] Specifically, the preparation data for the pretreatment are as follows:

[0084]

[0085] Of course, other arrangement methods were also used to obtain preprocessed preparation data.

[0086] S300. Input the preprocessed preparation data into the trained neural network model, and obtain the predicted quality data corresponding to the conductive gallium oxide single crystal through the trained neural network model.

[0087] Specifically, the predicted quality data includes: predicted crack data, predicted impurity crystal data, predicted diffraction peak full width at half maximum (FWHM), predicted diffraction peak FWHM deviation, predicted shoulder symmetry of conductive gallium oxide crystal, predicted shrinkage / expansion of the left edge of conductive gallium oxide crystal, predicted shrinkage / expansion of the right edge of conductive gallium oxide crystal, predicted thickness of conductive gallium oxide crystal, and predicted thickness deviation of conductive gallium oxide crystal. Crack data refers to crack grade data, and predicted crack data refers to the predicted crack grade data. For example, cracks can be divided into multiple grades. For instance, if cracks are divided into 3 grades, the crack data would be 1, 2, and 3 respectively.

[0088] Impurity data refers to impurity grade data, while predicted impurity data refers to predicted impurity grade data. For example, impurities can be divided into multiple grades. For instance, if impurities are divided into 3 grades, then the impurity data are 1, 2, and 3 respectively.

[0089] The predicted half-width at half-maximum (WHM) of a diffraction peak refers to the predicted WHM of the diffraction peak. The radial deviation value of the predicted WHM of the diffraction peak refers to the predicted difference in the radial WHM of the diffraction peak. The axial deviation value of the predicted WHM of the diffraction peak refers to the predicted difference in the axial WHM of the diffraction peak.

[0090] In some implementations, the trained neural network model is trained using the following steps:

[0091] S01. Obtain training data for preparing conductive gallium oxide single crystals using the guided mode method, as well as corresponding actual quality data, wherein the training data includes: seed crystal training data, environmental training data, and control training data.

[0092] Specifically, training data refers to the data used for training in the fabrication of conductive gallium oxide single crystals using the guided-mode method, while actual quality data refers to the actual quality data of the conductive gallium oxide single crystals fabricated using the guided-mode method. A training set is formed using the training data and actual quality data, and a pre-defined neural network model is trained based on this training set to obtain the trained neural network model.

[0093] When collecting data to obtain the training set, conductive gallium oxide single crystals were prepared using the guided mode method, and the data from the preparation of the conductive gallium oxide single crystals were recorded as training data. After obtaining the conductive gallium oxide single crystals, the quality of the conductive gallium oxide single crystals was analyzed to obtain actual quality data. To facilitate the training of the neural network model, as much data as possible can be collected to form the training set.

[0094] S02. Preprocess the training data to obtain preprocessed training data.

[0095] Specifically, after obtaining the training data, the training data is preprocessed to obtain preprocessed training data. The preprocessing process can be referred to step S200.

[0096] S03. Input the preprocessed training data into a preset neural network model, and obtain the prediction training generation quality data corresponding to the preprocessed training data through the preset neural network model.

[0097] Specifically, the preprocessed training data is input into a preset neural network model, and the predicted training generated quality data is obtained through the preset neural network model. The predicted training generated quality data includes: predicted training generated crack data, predicted training generated impurity data, predicted training generated diffraction peak full width at half maximum (FWHM), predicted training generated diffraction peak FWHM radial deviation value, and predicted training generated diffraction peak FWHM axial deviation value.

[0098] S04. Adjust and correct the model parameters of the preset neural network model based on the predicted training generated quality data and the actual quality data to obtain the trained neural network model.

[0099] Specifically, based on the predicted training generated quality data and the actual quality data, the model parameters of the preset neural network model are corrected, and the process of inputting the preprocessed training data into the preset neural network model and obtaining the predicted training generated quality data corresponding to the preprocessed training data through the preset neural network model (i.e., step S03) continues until the preset training conditions are met and a trained neural network model is obtained.

[0100] Specifically, based on the predicted training quality data and the actual quality data, the model parameters of the preset neural network model are corrected, and the process continues to execute the step of inputting the preprocessed training data into the preset neural network model, and obtaining the predicted training quality data corresponding to the preprocessed training data through the preset neural network model, until the preset training conditions are met, resulting in a trained neural network model. That is, if the preset neural network model meets the preset training conditions, a trained neural network model is obtained. If the preset neural network model does not meet the preset training conditions, the process returns to step S03 until the preset neural network model meets the preset training conditions, resulting in a trained neural network model.

[0101] In one implementation of this invention, a loss function value for a preset neural network model is determined based on the predicted training generated quality data and the actual quality data. The model parameters of the preset neural network model are then corrected based on the loss function value. Specifically, a gradient-based method is used to correct the parameters of the preset neural network model. After determining the loss function value of the preset neural network model, the corrected parameters of the preset neural network model are determined based on the gradient of the loss function value with respect to the parameters of the preset neural network model, the parameters of the preset neural network model, and a preset learning rate.

[0102] The preset training conditions include: the loss function value meets preset requirements and / or the preset number of training iterations of the neural network model reaches a preset number.

[0103] The preset requirements are determined based on the accuracy and efficiency of the preset neural network model. For example, the loss function value of the preset neural network model reaches its minimum value or no longer changes. The preset number of training iterations is the maximum number of training iterations for the preset neural network model, for example, 4000 times.

[0104] The default loss functions for neural network models include: mean squared error, root mean square error, and mean absolute error.

[0105] In one implementation of this application, the preset neural network model includes a feature extraction module and a fully connected module.

[0106] For example, the preset neural network model includes: a first convolutional unit, a second convolutional unit, a third convolutional unit, a fourth convolutional unit, and a fully connected unit. Specifically, the first convolutional unit includes: two convolutional layers and one pooling layer. The second, third, and fourth convolutional units each include three convolutional layers and one pooling layer. The fully connected unit includes three fully connected layers.

[0107] Convolutional and fully connected layers are responsible for mapping and transforming the input data. This process uses parameters such as weights and biases, and also requires activation functions. Pooling layers are fixed-function operations. Specifically, convolutional layers extract features; pooling layers perform pooling operations on the input features, changing their spatial dimensions; and fully connected layers fully connect all the data from the previous layer.

[0108] In some embodiments, step S03, inputting the preprocessed training data into a preset neural network model, and obtaining prediction training generation quality data corresponding to the preprocessed training data through the preset neural network model, includes:

[0109] S031 The preprocessed training data is input into the feature extraction module, and the feature extraction module obtains the feature vector corresponding to the preprocessed training data;

[0110] S032. Input the feature vector into the fully connected module, and obtain the prediction training generation quality data corresponding to the preprocessed training data through the fully connected module.

[0111] Specifically, the preprocessed training data is input into a preset neural network model, the feature extraction module in the preset neural network model outputs the feature vector corresponding to the preprocessed training data, and the feature vector is input into the fully connected module to obtain the prediction training generation quality data corresponding to the preprocessed training data output by the fully connected module.

[0112] Based on the aforementioned method for predicting the quality of conductive gallium oxide using deep learning and mode guidance, this embodiment provides a method for preparing conductive gallium oxide based on deep learning and mode guidance, such as... Figure 3 As shown, the preparation method includes:

[0113] S10. Obtain the target quality data of the target conductivity gallium oxide single crystal, wherein the target quality data includes the target carrier concentration.

[0114] Specifically, if a target conductivity gallium oxide single crystal is required, the target quality data of the target conductivity gallium oxide single crystal can be determined first. That is, the desired quality data of the conductivity gallium oxide single crystal is determined. The target quality data also includes: target crack data, target impurity crystal data, target diffraction peak full width at half maximum (FWHM), target diffraction peak FWHM deviation, target conductivity gallium oxide crystal shoulder symmetry, target conductivity gallium oxide crystal left edge contraction / expansion, target conductivity gallium oxide crystal right edge contraction / expansion, target conductivity gallium oxide crystal thickness, target conductivity gallium oxide crystal thickness deviation, target carrier concentration radial deviation, and target carrier concentration axial deviation.

[0115] S20. Based on the target quality data and the trained neural network model, determine the target preparation data corresponding to the target conductive gallium oxide single crystal, wherein the target preparation data includes: target seed crystal data, target environment data and target control data, and the target environment data includes the target doping element concentration and the target doping element type.

[0116] Specifically, based on the target quality data and the trained neural network model, the target fabrication data corresponding to the target conductive gallium oxide single crystal is determined. It should be noted that since different fabrication data can yield the same quality data, the target fabrication data is not unique when determining the target fabrication data for the target conductive gallium oxide single crystal based on the target quality data and the trained neural network model. A single target fabrication data point is determined based on the controllability of each data point among multiple target fabrication data points, thereby facilitating the acquisition of the target conductive gallium oxide single crystal.

[0117] In some embodiments, step S20, determining the target fabrication data corresponding to the target conductivity gallium oxide single crystal based on the target quality data and the trained neural network model, includes:

[0118] S21. Obtain preset preparation data, and preprocess the preset preparation data to obtain preprocessed preset preparation data;

[0119] S22. Input the pre-processed preset preparation data into the trained neural network model, and obtain the prediction quality data corresponding to the pre-processed preset preparation data through the trained neural network model;

[0120] S23. Based on the predicted quality data and the target quality data, the preset preparation data is corrected to obtain the target preparation data corresponding to the target conductive gallium oxide single crystal.

[0121] Specifically, pre-prepared data can be preset and preprocessed to obtain pre-processed pre-prepared data. The specific preprocessing process can be found in step S200. The pre-processed pre-prepared data is then input into a trained neural network model to obtain predicted quality data that corrects the pre-processed pre-prepared data. The preset prepared data is then corrected based on the predicted quality data and the target quality data. When the difference between the predicted quality data and the target quality data is less than a preset threshold, the corrected preset prepared data can be used as the target prepared data.

[0122] S30. Based on the guided mode method, a target conductive gallium oxide single crystal is prepared according to the target preparation data.

[0123] Specifically, after obtaining the target preparation data, the target conductive gallium oxide single crystal can be prepared using the guided mode method based on the target preparation data.

[0124] Based on the above prediction method or the above preparation method, this invention provides a conductive gallium oxide preparation system based on deep learning and the guided mode method. This system can be a computer device, with an internal structure as follows: Figure 4 As shown, the system includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a prediction method for conductive gallium oxide based on deep learning and model guidance, or a fabrication method for conductive gallium oxide based on deep learning and model guidance. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the system casing, or an external keyboard, touchpad, or mouse.

[0125] Those skilled in the art will understand that Figure 4The diagram shown is merely a partial structural diagram related to the present application and does not constitute a limitation on the system to which the present application is applied. A specific system may include more or fewer components than those shown in the diagram, or may combine certain components, or may have different component arrangements.

[0126] In one embodiment, a conductive gallium oxide fabrication system based on deep learning and mode guidance is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the prediction method or the steps of the fabrication method.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the quality of conductive gallium oxide based on deep learning and the leaky mode method, characterized in that, Including the following steps: Data for preparing conductive gallium oxide single crystals using the guided-mode method is obtained. This data includes seed crystal data, environmental data, and control data. The environmental data includes dopant concentration and dopant type. The crystal growth furnace used in the guided-mode method includes a lower insulation hood, inside which is a crucible containing a mold for forming a capillary effect. A heating ring is located outside the crucible. An upper insulation hood is positioned above the lower insulation hood, containing a crystal growth channel. A crystal growth observation hole is located on the side of the upper insulation hood. The lower insulation hood is further surrounded by... The induction coil; the seed crystal data includes: seed crystal diffraction peak half-width at half-maximum (FWHM), seed crystal diffraction peak FWHM deviation value, seed crystal thickness, and seed crystal width; the environmental data also includes: upper insulation cover thermal resistance value, upper insulation cover thermal resistance deviation value, crystal growth channel shape factor, crystal growth observation hole shape factor, lower insulation cover thermal resistance value, lower insulation cover thermal resistance deviation value, relative height between the crucible and the heating coil, relative height between the heating ring and the heating coil, mold opening gap width, and mold opening gap thickness; the control data includes: heating power, cooling power, atmosphere type, cavity pressure, gas flow rate, and seed crystal rod pulling speed; Based on the seed crystal data, environmental data, and control data, a preparation vector is determined. The first element of the preparation vector is one of the seed crystal diffraction peak full width at half maximum (FWHM), the seed crystal diffraction peak FWHM deviation, the seed crystal thickness, and the seed crystal width. The second element of the preparation vector is one of the upper insulation cover thermal resistance, the upper insulation cover thermal resistance deviation, the crystal growth channel shape factor, the crystal growth observation hole shape factor, the lower insulation cover thermal resistance, the lower insulation cover thermal resistance deviation, the relative height between the crucible and the heating coil, the relative height between the heating ring and the heating coil, the width of the mold opening gap, the thickness of the mold opening gap, the doping element concentration, and the doping element type, where the doping element type includes Si, Ge, Sn, Zr, Hf, In, Ta, Nb, V, W, and Mo. The third element of the preparation vector is one of the heating power, cooling power, atmosphere type, cavity pressure, gas flow rate, and seed crystal rod pulling speed. Based on the preparation vector, pretreatment preparation data is determined, wherein the pretreatment preparation data is a matrix formed by rearranging and combining the seed crystal data, environmental data, and control data; The preprocessed data is input into a trained neural network model, and the predicted quality data corresponding to the conductive gallium oxide single crystal is obtained through the trained neural network model. The predicted quality data includes the predicted carrier concentration. The trained neural network model was obtained by the following training steps: Training data for preparing conductive gallium oxide single crystals using the guided mode method, as well as corresponding actual quality data, are obtained. The training data includes seed crystal training data, environmental training data, and control training data. The training data is preprocessed to obtain preprocessed training data; The preprocessed training data is input into a preset neural network model, and the preset neural network model is used to obtain the prediction training generation quality data corresponding to the preprocessed training data. The model parameters of the preset neural network model are adjusted and corrected based on the predicted training quality data and the actual quality data to obtain a trained neural network model.

2. The method for predicting the quality of conductive gallium oxide based on deep learning and guided mode method according to claim 1, characterized in that, The predicted quality data includes: predicted crack data, predicted impurity crystal data, predicted diffraction peak full width at half maximum (FWHM), predicted diffraction peak FWHM deviation, predicted shoulder symmetry of conductive gallium oxide crystal, predicted expansion / contraction of the left edge of conductive gallium oxide crystal, predicted expansion / contraction of the right edge of conductive gallium oxide crystal, predicted thickness of conductive gallium oxide crystal, predicted thickness deviation of conductive gallium oxide crystal, predicted radial deviation of carrier concentration, and predicted axial deviation of carrier concentration.

3. The method for predicting the quality of conductive gallium oxide based on deep learning and guided mode method according to claim 1, characterized in that, The preset neural network model includes: a feature extraction module and a fully connected module. The steps of inputting the preprocessed training data into a preset neural network model and obtaining prediction training generation quality data corresponding to the preprocessed training data through the preset neural network model include: The preprocessed training data is input into the feature extraction module, and the feature extraction module obtains the feature vector corresponding to the preprocessed training data. The feature vector is input into the fully connected module, and the prediction training generation quality data corresponding to the preprocessed training data is obtained through the fully connected module.

4. A method for preparing conductive gallium oxide based on deep learning and mode guidance, characterized in that, The preparation method includes the following steps: Obtain target quality data for a target conductivity gallium oxide single crystal, wherein the target quality data includes the target carrier concentration; Obtain preset preparation data, and preprocess the preset preparation data to obtain preprocessed preset preparation data; The pre-processed preset preparation data is input into a trained neural network model, and the trained neural network model obtains predicted quality data corresponding to the pre-processed preset preparation data. Based on the predicted quality data and the target quality data, the preset preparation data is corrected to obtain the target preparation data corresponding to the target conductive gallium oxide single crystal. The target preparation data includes: target seed crystal data, target environment data, and target control data. The target environment data includes the target doping element concentration and the target doping element type. Based on the guided mode method, a target conductive gallium oxide single crystal was prepared according to the target preparation data. The trained neural network model was obtained by the following training steps: Training data for preparing conductive gallium oxide single crystals using the guided mode method, as well as corresponding actual quality data, are obtained. The training data includes seed crystal training data, environmental training data, and control training data. The training data is preprocessed to obtain preprocessed training data; The preprocessed training data is input into a preset neural network model, and the preset neural network model is used to obtain the prediction training generation quality data corresponding to the preprocessed training data. The model parameters of the preset neural network model are adjusted and corrected based on the predicted training quality data and the actual quality data to obtain a trained neural network model.

5. A conductive gallium oxide fabrication system based on deep learning and mode guidance method, characterized in that, The device includes a memory and a processor, the memory storing a computer program, characterized in that the processor executes the computer program to implement the steps of the prediction method according to any one of claims 1 to 3, or the steps of the preparation method according to claim 4.

Images