A method for preparing conductive gallium oxide based on deep learning and heat exchange

Abstract

The application relates to a preparation method of conductive gallium oxide based on deep learning and heat exchange, and a prediction method, which comprises the following steps: obtaining preparation data of conductive gallium oxide single crystal; the preparation data comprises seed crystal data, environment data, control data and raw material data; the control data comprises seed crystal cooling medium flow; the raw material data comprises doping type data and conductive doping concentration; the preparation data is pretreated; the pretreated preparation data is input into a trained neural network model to obtain corresponding predicted property data of the conductive gallium oxide single crystal; the predicted property data comprises a predicted carrier concentration. The preparation data is pretreated to obtain pretreated preparation data, the pretreated preparation data is input into the trained neural network model to obtain corresponding predicted property data of the conductive gallium oxide single crystal, and by adjusting the preparation data, the conductive gallium oxide with a predetermined carrier concentration can be obtained.

Description

Technical Field

[0001] This application relates to the field of gallium oxide preparation technology, and in particular to a method for preparing conductive gallium oxide based on deep learning and heat exchange. Background Technology

[0002] Gallium oxide (Ga₂O₃) single crystal is a transparent semiconductor oxide, belonging to the wide bandgap semiconductor materials. Generally, β-phase gallium oxide (β-Ga₂O₃) is more stable. β-Ga₂O₃ possesses many advantages, including a large bandgap, high saturated electron drift velocity, high thermal conductivity, high breakdown field strength, and stable chemical properties. The high bandgap results in a high breakdown voltage, and its high saturated electron drift velocity, high thermal conductivity, and stable chemical properties make β-Ga₂O₃ single crystals promising for wide applications in electronic devices. The heat exchange method is one of the methods for preparing gallium oxide. However, in current technologies, when preparing conductive gallium oxide using the heat exchange method, it is impossible to obtain conductive gallium oxide with a predetermined carrier concentration.

[0003] Therefore, existing technologies need to be improved. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method for preparing conductive gallium oxide based on deep learning and heat exchange method, so as to predict and obtain conductive gallium oxide with a predetermined carrier concentration.

[0005] This invention provides a method for predicting the conductivity of gallium oxide based on deep learning and heat exchange, comprising:

[0006] Data on the preparation of conductive gallium oxide single crystals is obtained; wherein, the preparation data includes: seed crystal data, environmental data, control data, and raw material data; the control data includes: seed crystal cooling medium flow rate, and the raw material data includes: doping type data and conductive doping concentration;

[0007] The preparation data is preprocessed to obtain preprocessed preparation data;

[0008] The preprocessed preparation data is input into a trained neural network model, and the predicted property data corresponding to the conductive gallium oxide single crystal is obtained through the trained neural network model; the predicted property data includes: predicted carrier concentration.

[0009] The aforementioned method for predicting conductive gallium oxide based on deep learning and heat exchange methods, wherein the preprocessing of the preparation data to obtain preprocessed preparation data includes:

[0010] Based on the seed crystal data, the environmental data, the control data, and the raw material data, pretreatment preparation data is obtained; wherein, the pretreatment preparation data is a matrix formed by the seed crystal data, the environmental data, the control data, and the raw material data.

[0011] The aforementioned method for predicting conductive gallium oxide based on deep learning and heat exchange method includes seed crystal data comprising: seed crystal diffraction peak full width at half maximum (FWHM), seed crystal diffraction peak FWHM deviation value, and seed crystal diameter.

[0012] The environmental data includes: thermal resistance value of the insulation layer, thermal resistance value deviation of the insulation layer, and shape factor of the insulation layer;

[0013] The control data also includes: coil input power and coil cooling power.

[0014] The aforementioned method for predicting conductive gallium oxide based on deep learning and heat exchange includes obtaining preprocessed preparation data from the seed crystal data, environmental data, control data, and raw material data, comprising:

[0015] Based on the seed crystal data, the environmental data, the control data, and the raw material data, a preparation vector is determined; wherein, 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 value, and the seed crystal diameter; the second element of the preparation vector is one of the insulation layer thermal resistance value, the insulation layer thermal resistance deviation value, and the insulation layer shape factor; the third element of the preparation vector is one of the coil input power, the coil cooling power, and the seed crystal cooling medium flow rate; and the fourth element of the preparation vector is one of the doping type data and the conductive doping concentration.

[0016] Based on the preparation vector, the preparation data for the preprocessing is determined.

[0017] The aforementioned method for predicting conductive gallium oxide based on deep learning and heat exchange includes the following predicted property data: predicted crack data, predicted impurity crystal data, predicted diffraction peak full width at half maximum (FWHM), predicted radial deviation of predicted FWHM, predicted axial deviation of predicted FWHM, predicted carrier concentration, predicted radial deviation of predicted carrier concentration, and predicted axial deviation of predicted carrier concentration.

[0018] A method for preparing conductive gallium oxide based on deep learning and heat exchange, the method comprising:

[0019] Acquire target property data of the target conductivity type gallium oxide single crystal; the target property data includes: target carrier concentration;

[0020] Based on the target property data and the trained neural network model, the target preparation data corresponding to the target conductive gallium oxide single crystal is determined; wherein, the target preparation data includes: seed crystal data, environmental data, control data, and raw material data; the control data includes: seed crystal cooling medium flow rate, and the raw material data includes: doping type data and conductive doping concentration;

[0021] Based on the heat exchange method, a target conductive gallium oxide single crystal was prepared according to the target preparation data.

[0022] The method for preparing conductive gallium oxide based on deep learning and heat exchange, wherein determining the target preparation data corresponding to the target conductive gallium oxide single crystal according to the target property data and the trained neural network model includes:

[0023] Obtain preset preparation data, and preprocess the preset preparation data to obtain preprocessed preset preparation data;

[0024] The pre-processed preset preparation data is input into a trained neural network model, and the predicted property data corresponding to the conductive gallium oxide single crystal is obtained through the trained neural network model.

[0025] Based on the predicted property data and the target property data, the preset preparation data is corrected to obtain the target preparation data corresponding to the target conductive gallium oxide single crystal.

[0026] The aforementioned method for preparing conductive gallium oxide based on deep learning and heat exchange, wherein the trained neural network model is obtained through the following steps:

[0027] Acquire training data for conductive gallium oxide single crystals and the corresponding actual property data; wherein, the training data includes: seed crystal training data, environmental training data, control training data, and raw material training data; the control training data includes: seed crystal cooling medium flow rate training data, and the raw material training data includes: doping type data and conductive doping concentration;

[0028] The training data is preprocessed to obtain preprocessed training data;

[0029] The preprocessed training data is input into a preset neural network model, and the predicted generation property data corresponding to the preprocessed training data is obtained through the preset neural network model; the predicted generation property data includes: predicted generation carrier concentration;

[0030] The model parameters of the preset neural network model are adjusted and corrected based on the predicted property data and the actual property data to obtain a trained neural network model.

[0031] The aforementioned method for preparing conductive gallium oxide based on deep learning and heat exchange, wherein the preset neural network model includes: a feature extraction module and a fully connected module.

[0032] The step of inputting the preprocessed training data into a preset neural network model and obtaining the prediction generation property data corresponding to the preprocessed training data through the preset neural network model includes:

[0033] 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.

[0034] The feature vector is input into the fully connected module, and the prediction generation property data obtained from the preprocessed training data is obtained through the fully connected module.

[0035] A conductive gallium oxide fabrication system based on deep learning and heat exchange method includes a memory and a processor. The memory stores a computer program. The system is characterized in that the processor executes the computer program to implement the steps of the prediction method described above, or the steps of the fabrication method described above.

[0036] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0037] First, the preparation data is preprocessed to obtain preprocessed preparation data. Then, the preprocessed preparation data is input into a trained neural network model. The trained neural network model is used to obtain the predicted property data of the conductive gallium oxide single crystal. The performance of the conductive gallium oxide single crystal can be predicted by the trained neural network model. Therefore, by adjusting the preparation data, a conductive gallium oxide with a predetermined carrier concentration can be obtained. Attached Figure Description

[0038] 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 described below 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.

[0039] Figure 1 This is a flowchart of a method for predicting conductive gallium oxide based on deep learning and heat exchange in an embodiment of the present invention;

[0040] Figure 2 This is a schematic diagram of the crystal growth furnace in an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram showing the position and temperature of the crystal inside the furnace in an embodiment of the present invention;

[0042] Figure 4 This is an internal structure diagram of the conductive gallium oxide preparation system based on deep learning and heat exchange method in an embodiment of the present invention. Detailed Implementation

[0043] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] The heat exchange method utilizes a heat exchanger to remove heat, creating a vertical temperature gradient within the crystal growth region—cooler at the bottom, hotter at the top. This temperature gradient is controlled by adjusting the gas flow rate within the heat exchanger and by varying the heating and cooling power, thus allowing the melt in the crucible to solidify slowly from bottom to top, forming a crystal. Figure 2 As shown.

[0045] Various non-limiting embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0046] See Figures 1-3 This paper illustrates a method for predicting the conductivity of gallium oxide based on deep learning and a heat exchange method, according to an embodiment of the present invention. In this embodiment, the prediction method may include, for example, the following steps:

[0047] S100. Obtain the preparation data of conductive gallium oxide single crystal; wherein, the preparation data includes: seed crystal data, environmental data, control data and raw material data; the control data includes: seed crystal cooling medium flow rate, and the raw material data includes: doping type data and conductive doping concentration.

[0048] Specifically, preparation data refers to data from the preparation of conductive gallium oxide single crystals. Obtaining preparation data for conductive gallium oxide single crystals can be done using data configured as needed. For example, if it's necessary to predict the performance of a conductive gallium oxide single crystal under specific preparation data, it's only necessary to determine the preparation data, preprocess it to obtain preprocessed preparation data, and then input the preprocessed preparation data into a trained neural network model. The predicted property data is then obtained through the trained neural network model. In other words, without conducting experiments, the property data of conductive gallium oxide single crystals can be predicted once the preparation data is determined.

[0049] The preparation data includes: seed crystal data, environmental data, control data, and raw material data. Seed crystal data refers to the data of the seed crystal used in the preparation of conductive gallium oxide single crystals. Environmental data refers to the data of the environment in which the crystal is located during the preparation of conductive gallium oxide single crystals. Control data refers to the data on controlling crystal growth during the preparation of conductive gallium oxide single crystals. Raw material data refers to the data of the raw materials used in the preparation of conductive gallium oxide single crystals. Conductivity doping concentration refers to the concentration of conductive dopants in gallium oxide. Conductivity dopants include: Si, Ge, Sn, Zr, Hf, In, Ta, Nb, V, W, Mo, etc. Doping type data refers to the type of dopant. Seed crystal cooling medium flow rate refers to the flow rate of the gas used to cool the area near the seed crystal at the bottom of the crucible.

[0050] S200. The preparation data is preprocessed to obtain preprocessed preparation data.

[0051] Specifically, after obtaining the preparation data, the preparation data is first preprocessed to obtain preprocessed preparation data, which can then be input into the trained neural network model so that the trained neural network model can process the preprocessed preparation data.

[0052] In one implementation of this application embodiment, step S200, preprocessing the preparation data to obtain preprocessed preparation data, includes:

[0053] S210. Based on the seed crystal data, the environmental data, the control data, and the raw material data, pretreatment preparation data is obtained; wherein, the pretreatment preparation data is a matrix formed by the seed crystal data, the environmental data, the control data, and the raw material data.

[0054] Specifically, after obtaining the preparation data, the preparation data is first preprocessed to obtain preprocessed preparation data. Since the various sub-data in the preparation data (such as seed crystal data, environmental data, control data, and raw material data) will affect each other, but it is currently impossible to determine the extent of the mutual influence between the sub-data, it is necessary to preprocess the preparation data to rearrange and combine the various sub-data in the preparation data to form preprocessed preparation data.

[0055] In one implementation 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, and seed crystal diameter; the environmental data includes: insulation layer thermal resistance value, insulation layer thermal resistance deviation value, and insulation layer shape factor; the control data further includes: coil input power and coil cooling power.

[0056] Specifically, the full width at half maximum (FWHM) of the seed crystal diffraction peak can be measured using an X-ray diffractometer. The FWHM deviation values ​​include the radial deviation and the axial deviation. Radial deviation refers to the direction on the horizontal plane, and axial deviation refers to the direction perpendicular to the horizontal plane, i.e., the vertical axis. The radial deviation value can be obtained by measuring the FWHM on both radial sides of the seed crystal and calculating the difference between the FWHM values ​​on both sides. Similarly, the axial deviation value can be obtained by measuring the FWHM on both axial sides of the seed crystal and calculating the difference between the FWHM values ​​on both sides.

[0057] In the heat exchange method for preparing gallium oxide single crystals, the cooling gas is typically blown from bottom to top, resulting in a higher temperature above the crucible than below. Figure 2 As shown, by continuously blowing cooling gas from below the crucible, the cooling energy is transferred from bottom to top, and the gallium oxide melt in the crucible gradually grows into a gallium oxide single crystal. The bottom of crucible 1 narrows to form a pointed tip, and the seed crystal is located at the tip. That is to say, during the crystal growth process, due to the continuous blowing of cooling gas from below the crucible, the temperature of the crucible gradually decreases from bottom to top, and the melt 3 starts to grow from the seed crystal at the bottom of crucible 1, gradually growing into crystal 2. Of course, the seed crystal can be placed at the tip of crucible 1 after the gallium oxide in crucible 1 has completely melted. The tip is connected to a cooling medium transfer pipe, through which the cooling medium is transferred. The seed crystal cooling medium includes water, gas, and oil; preferably, gas is used as the seed crystal cooling medium.

[0058] like Figure 2 As shown, an insulation layer is provided outside the induction coil 4 to maintain the temperature. The thermal resistance of the insulation layer refers to the temperature difference between the two ends of the insulation layer when a unit of heat passes through the insulation layer per unit time. The higher the thermal resistance of the insulation layer, the stronger its ability to resist heat transfer, and the better its insulation effect.

[0059] The thermal resistance deviation of the insulation layer includes two values: radial thermal resistance deviation and axial thermal resistance deviation. The radial thermal resistance deviation can be obtained by measuring the thermal resistance on both radial sides of the insulation layer and calculating the difference between these values. Similarly, the axial thermal resistance deviation can be obtained by measuring the thermal resistance on both axial sides of the insulation layer and calculating the difference between these values.

[0060] The shape factor of an insulation layer refers to the value of the shape and dimensions of the insulation area. For example, when using a cylindrical insulation layer, the shape factor includes the diameter and height of the insulation layer. When using a cubic insulation layer, the shape factor includes the length, width, and height of the insulation layer.

[0061] Coil input power refers to the input power of the induction coil during crystal growth, while coil cooling power refers to the corresponding power during cooling. Since the induction coil is hollow, a cooling medium is introduced into it during cooling, forming a cooling coil. Cooling occurs through the continuous flow of the cooling medium within the cooling coil. The coil cooling power can be determined based on the type and flow rate of the cooling medium. Cooling media types include water, oil, and gas, and the flow rate can be determined based on the flow velocity of the cooling medium and the diameter of the cooling coil. Seed crystal cooling water flow rate refers to the flow rate of the cooling water during cooling.

[0062] In one implementation of this application embodiment, step S210, obtaining preprocessed preparation data based on the seed crystal data, the environmental data, and the control data, includes:

[0063] S211. Based on the seed crystal data, the environmental data, and the control data, determine the preparation vector; wherein, 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 value, and the seed crystal diameter; the second element of the preparation vector is one of the insulation layer thermal resistance value, the insulation layer thermal resistance deviation value, and the insulation layer shape factor; the third element of the preparation vector is one of the coil input power, the coil cooling power, and the seed crystal cooling medium flow rate; and the fourth element of the preparation vector is one of the doping type data and the conductive doping concentration.

[0064] S212. Determine the preparation data for the preprocessing based on the preparation vector.

[0065] Specifically, based on seed crystal data A, environmental data B, control data C, and raw material data D, a preparation vector (A, B, C, D) is determined. 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, and seed crystal diameter A3. Environmental data B is selected from: insulation layer thermal resistance value B1, insulation layer thermal resistance deviation value B2, and insulation layer shape factor B3. Control data C is selected from: coil input power C1, coil cooling power C2, and seed crystal cooling medium flow rate C3. Raw material data D is selected from: doping type data D1 and conductive doping concentration D2. In other words, in the preparation vector (A, B, C, D), A can be one of A1, A2, and A3; B can be one of B1, B2, and B3; C can be one of C1, C2, and C3; and D can be one of D1 and D2. This results in 54 preparation vectors.

[0066] Arrange all the preparation vectors in order of their numbers to form a matrix, and you will get the preprocessed preparation data.

[0067] Specifically, the preparation data for the pretreatment are as follows:

[0068]

[0069] Of course, other arrangement methods were also used to obtain preprocessed preparation data.

[0070] S300. Input the preprocessed preparation data into the trained neural network model, and obtain the predicted property data corresponding to the conductive gallium oxide single crystal through the trained neural network model; the predicted property data includes: predicted carrier concentration.

[0071] The predicted property data also includes: predicted crack data, predicted impurity crystal data, predicted diffraction peak half-width at half-maximum (FWHM), predicted radial deviation of predicted FWHM, predicted axial deviation of predicted FWHM, predicted radial deviation of predicted carrier concentration, and predicted axial deviation of predicted carrier concentration.

[0072] Crack data refers to crack grade data, while predicted crack data refers to 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.

[0073] 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.

[0074] 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 between the WHM of the diffraction peak on both sides in the radial direction. The axial deviation value of the predicted WHM of the diffraction peak refers to the predicted difference between the WHM of the diffraction peak on both sides in the axial direction.

[0075] By inputting the preprocessed data into a trained neural network model, the model obtains predicted property data. It should be noted that the predicted property data can be one or more; for example, only crack prediction data may be needed.

[0076] In one implementation of this application, the trained neural network model is trained using the following steps:

[0077] A100, acquire training data for conductive gallium oxide single crystals and the corresponding actual property data; wherein, the training data includes: seed crystal training data, environmental training data, control training data, and raw material training data; the raw material training data includes: doping type data and conductive doping concentration.

[0078] Specifically, training data refers to data used for training in the preparation of conductive gallium oxide single crystals, while actual property data refers to data on the actual properties of the prepared conductive gallium oxide single crystals. A training set is formed using both training data and actual property data. A pre-defined neural network model is trained based on this training set to obtain the trained neural network model. The control data includes: coil input power and coil cooling power. The seed crystal training data includes: seed crystal diffraction peak FWHM training data, seed crystal diffraction peak FWHM deviation training data, and seed crystal diameter training data. The environmental training data includes: insulation layer thermal resistance training data, insulation layer thermal resistance deviation training data, and insulation layer shape factor training data. The control training data includes: seed crystal cooling medium flow rate; of course, the control training data also includes: coil input power training data and coil cooling power training data. The raw material training data includes: doping type training data and conductive doping concentration training data. The actual property data includes: actual carrier concentration. Of course, the actual property data may also include: actual crack data, actual impurity crystal data, actual diffraction peak half width at half maximum (FWHM), actual diffraction peak FWHM radial deviation value, actual diffraction peak FWHM axial deviation value, actual carrier concentration radial deviation value, and actual carrier concentration axial deviation value.

[0079] Alternatively, a training set can be formed using training data and actual data, and a pre-defined neural network model can be trained based on this training set to obtain a well-trained neural network model.

[0080] When collecting data to obtain the training set, conductive gallium oxide single crystals were prepared using a heat exchange 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, their properties were analyzed to obtain actual property data. To facilitate the training of the neural network model, as much data as possible can be collected to form the training set.

[0081] A200. The training data is preprocessed to obtain preprocessed training data.

[0082] 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.

[0083] A300. Input the preprocessed training data into a preset neural network model, and obtain the predicted generation property data corresponding to the preprocessed training data through the preset neural network model; the predicted generation property data includes: predicted generation carrier concentration.

[0084] Specifically, the preprocessed training data is input into a preset neural network model, and the predicted generated property data is obtained through the preset neural network model. The predicted generated property data also includes: predicted generated crack data, predicted generated impurity crystal data, predicted generated diffraction peak full width at half maximum (FWHM), predicted generated diffraction peak FWHM radial deviation value, predicted generated diffraction peak FWHM axial deviation value, predicted generated carrier concentration radial deviation value, and predicted generated carrier concentration axial deviation value.

[0085] A400. Adjust the model parameters of the preset neural network model according to the predicted property data and the actual property data to obtain a trained neural network model.

[0086] Specifically, based on the predicted property data and the actual property 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 property data corresponding to the preprocessed training data through the preset neural network model (i.e., step A300) continues until the preset training conditions are met, and a trained neural network model is obtained.

[0087] Specifically, based on the predicted property data and the actual property 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 property 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 A300 until the preset neural network model meets the preset training conditions, resulting in a trained neural network model.

[0088] In one implementation of this invention, a loss function value for a preset neural network model is determined based on the predicted property data and the actual property 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.

[0089] The preset training conditions include: the loss function value meets the first preset requirement and / or the preset number of training iterations of the neural network model reaches the first preset number of iterations.

[0090] The first preset requirement is 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 first preset number of training iterations is the maximum number of training iterations for the preset neural network model, for example, 4000 times.

[0091] The loss functions of the preset neural network model include: mean squared error, root mean square error, and mean absolute error.

[0092] In one implementation of this application, the preset neural network model includes a feature extraction module and a fully connected module.

[0093] 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.

[0094] 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.

[0095] Step A300: Input the preprocessed training data into a preset neural network model, and obtain the prediction generation property data corresponding to the preprocessed training data through the preset neural network model, including:

[0096] A310. Input the preprocessed training data into the feature extraction module, and obtain the feature vector corresponding to the preprocessed training data through the feature extraction module;

[0097] A320. Input the feature vector into the fully connected module, and obtain the prediction generation property data obtained from the preprocessed training data through the fully connected module.

[0098] 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 in the pre-trained model to obtain the prediction generation property data corresponding to the preprocessed training data output by the fully connected module.

[0099] Alternatively, the preprocessed training data can be input into a preset neural network model, the feature extraction module in the preset neural network model can output the feature vector corresponding to the preprocessed training data, and the feature vector can be input into the fully connected module in the pre-trained model to obtain the prediction generation property data corresponding to the preprocessed training data output by the fully connected module.

[0100] Based on the above-mentioned method for predicting conductive gallium oxide using deep learning and heat exchange, this embodiment provides a method for preparing conductive gallium oxide using deep learning and heat exchange, the preparation method comprising:

[0101] B100. Obtain target property data of the target conductivity type gallium oxide single crystal; the target property data includes: target carrier concentration.

[0102] Specifically, if a target conductivity type gallium oxide single crystal is required, the target property data of the target conductivity type gallium oxide single crystal can be determined first; that is, the property data of the desired conductivity type gallium oxide single crystal can be determined. Alternatively, the target property data of the target conductivity type gallium oxide single crystal can also be determined first, that is, the property data of the desired conductivity type gallium oxide single crystal can be determined. The target property data also includes: target crack data, target impurity crystal data, target diffraction peak full width at half maximum (FWHM), target diffraction peak radial deviation value, target diffraction peak axial deviation value, target carrier concentration radial deviation value, and target carrier concentration axial deviation value.

[0103] B200. Based on the target property 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: seed crystal data, environmental data, control data, and raw material data; the raw material data includes: doping type data and conductive doping concentration.

[0104] Specifically, the target preparation data corresponding to the target conductive gallium oxide single crystal is determined based on the target property data and the trained neural network model. Alternatively, the target preparation data can also be determined based on the target property data and the trained neural network model. It should be noted that since different preparation data can yield the same property data, the target preparation data is not unique when determining the target preparation data for the target conductive gallium oxide single crystal based on the target property data and the trained neural network model. A single target preparation data point is determined based on the ease of control over each data point among multiple target preparation data points, thereby facilitating the acquisition of the target conductive gallium oxide single crystal.

[0105] In one implementation of this embodiment, B200 determines the target fabrication data corresponding to the target conductivity type gallium oxide single crystal based on the target property data and the trained neural network model, including:

[0106] B210. Obtain preset preparation data, and preprocess the preset preparation data to obtain preprocessed preset preparation data.

[0107] B220. Input the pre-processed preset preparation data into the trained neural network model, and obtain the predicted property data corresponding to the conductive gallium oxide single crystal through the trained neural network model.

[0108] B230. Based on the predicted property data and the target property data, the preset preparation data is corrected to obtain the target preparation data corresponding to the target conductive gallium oxide single crystal.

[0109] Specifically, pre-prepared data can be preset and preprocessed to obtain preprocessed pre-prepared data. The specific preprocessing process can be found in step S200. The preset pre-prepared data is input into a trained neural network model to obtain predicted property data. Then, based on the predicted property data and the target property data, the preset pre-prepared data is corrected. When the difference between the predicted property data and the target property data is less than a preset threshold, the preset pre-prepared data can be used as the target pre-prepared data. Correction of the preset pre-prepared data can be automatic or manual. Alternatively, a loss function value can be determined based on the predicted property data and the target property data, and the preset pre-prepared data can be corrected based on this loss function value. When the loss function value meets preset correction conditions, the preset pre-prepared data can be used as the target pre-prepared data. Preset correction conditions include: the loss function value meets a second preset requirement and / or the number of corrections to the preset pre-prepared data reaches a second preset number.

[0110] It should be noted that the preset preparation data includes: preset seed crystal data, preset environmental data, preset control data, and preset raw material data; the preset seed crystal data includes: preset seed crystal diffraction peak full width at half maximum (FWHM), preset seed crystal diffraction peak FWHM deviation value, and preset seed crystal diameter; the preset environmental data includes: preset insulation layer thermal resistance value, preset insulation layer thermal resistance deviation value, and preset insulation layer shape factor; the preset control data includes: preset coil input power, preset coil cooling power, and preset seed crystal cooling medium flow rate. The preset raw material data includes: preset doping type data and preset conductive doping concentration.

[0111] B300, based on the heat exchange method, a target conductive gallium oxide single crystal is prepared according to the target preparation data.

[0112] Specifically, after obtaining the target preparation data, the target conductive gallium oxide single crystal can be prepared based on the heat exchange method according to the target preparation data.

[0113] 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 heat exchange method. This system can be a computer device, with an internal structure as follows: Figure 4As 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 gallium oxide prediction method based on deep learning and a heat exchange method, or a gallium oxide preparation method based on deep learning and a heat exchange method. 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.

[0114] Those skilled in the art will understand that Figure 4 The 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.

[0115] In one embodiment, a conductive gallium oxide fabrication system based on deep learning and heat exchange method 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.

[0116] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A method for predicting the conductivity of gallium oxide based on deep learning and heat exchange, characterized in that, The prediction method includes: Acquire preparation data for conductive gallium oxide single crystals; wherein, the preparation data includes: seed crystal data, environmental data, control data, and raw material data; The preparation data is preprocessed to obtain preprocessed preparation data; The preprocessed preparation data is input into a trained neural network model, and the predicted property data corresponding to the conductive gallium oxide single crystal is obtained through the trained neural network model; the predicted property data includes: predicted carrier concentration; The preprocessing of the preparation data to obtain preprocessed preparation data includes: Based on the seed crystal data, the environmental data, the control data, and the raw material data, pretreatment preparation data is obtained; wherein, the pretreatment preparation data is a matrix formed by rearranging and combining the seed crystal data, the environmental data, the control data, and the raw material data; The seed crystal data includes: seed crystal diffraction peak full width at half maximum (FWHM) A1, seed crystal diffraction peak FWHM deviation value A2, and seed crystal diameter A3; the environmental data includes: insulation layer thermal resistance value B1, insulation layer thermal resistance deviation value B2, and insulation layer shape factor B3; the control data includes: coil input power C1, coil cooling power C2, and seed crystal cooling medium flow rate C3; the raw material data includes: doping type data D1 and conductivity doping concentration D2; the pre-processing preparation data obtained based on the seed crystal data, the environmental data, the control data, and the raw material data includes: Based on the seed crystal data, the environmental data, the control data, and the raw material data, a preparation vector is determined; wherein, 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 value, and the seed crystal diameter; the second element of the preparation vector is one of the insulation layer thermal resistance value, the insulation layer thermal resistance deviation value, and the insulation layer shape factor; the third element of the preparation vector is one of the coil input power, the coil cooling power, and the seed crystal cooling medium flow rate; and the fourth element of the preparation vector is one of the doping type data and the conductive doping concentration. Based on the preparation vector, determine the preparation data for the preprocessing; The preparation data for the pretreatment are as follows: The trained neural network model was obtained by training the following steps: Acquire training data for conductive gallium oxide single crystals and the corresponding actual property data; wherein, the training data includes: seed crystal training data, environmental training data, control training data, and raw material training data; the control training data includes: seed crystal cooling medium flow rate training data, and the raw material training data includes: doping type training data and conductive doping concentration 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 predicted generation property data corresponding to the preprocessed training data is obtained through the preset neural network model; the predicted generation property data includes: predicted generation carrier concentration; The model parameters of the preset neural network model are adjusted and corrected based on the predicted property data and the actual property data to obtain a trained neural network model. The preset neural network model includes: a feature extraction module and a fully connected module. The step of inputting the preprocessed training data into a preset neural network model and obtaining the prediction generation property data corresponding to the preprocessed training data through the preset neural network model includes: 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 generation property data corresponding to the preprocessed training data is obtained through the fully connected module.

2. The method for predicting conductive gallium oxide based on deep learning and heat exchange method according to claim 1, characterized in that, The predicted property data also includes: predicted crack data, predicted impurity crystal data, predicted diffraction peak half-width at half-maximum (FWHM), predicted radial deviation of predicted FWHM, predicted axial deviation of predicted FWHM, predicted radial deviation of predicted carrier concentration, and predicted axial deviation of predicted carrier concentration.

3. A method for preparing conductive gallium oxide based on deep learning and heat exchange, characterized in that, The preparation method includes: Acquire target property data of the target conductivity type gallium oxide single crystal; the target property data includes: target carrier concentration; Based on the target property data and the trained neural network model, the target preparation data corresponding to the target conductive gallium oxide single crystal is determined; wherein, the target preparation data includes: seed crystal data, environmental data, control data, and raw material data; the control data includes: seed crystal cooling medium flow rate, and the raw material data includes: doping type data and conductive doping concentration; Based on the heat exchange method, a target conductive gallium oxide single crystal was prepared according to the target preparation data. The trained neural network model was obtained by training the following steps: Acquire training data for conductive gallium oxide single crystals and the corresponding actual property data; wherein, the training data includes: seed crystal training data, environmental training data, control training data, and raw material 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 predicted generation property data corresponding to the preprocessed training data is obtained through the preset neural network model; the predicted generation property data includes: predicted generation carrier concentration; The model parameters of the preset neural network model are adjusted and corrected based on the predicted property data and the actual property data to obtain a trained neural network model. The preprocessing of the training data to obtain preprocessed training data includes: Based on the seed crystal training data, the environment training data, the control training data, and the raw material training data, preprocessed training data is obtained; wherein, the preprocessed training data is a matrix formed by rearranging and combining the seed crystal training data, the environment training data, the control training data, and the raw material training data; The step of determining the target fabrication data corresponding to the target conductivity gallium oxide single crystal based on the target property data and the trained neural network model includes: 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 predicted property data corresponding to the conductive gallium oxide single crystal is obtained through the trained neural network model. Based on the predicted property data and the target property data, the preset preparation data is corrected to obtain the target preparation data corresponding to the target conductive gallium oxide single crystal; The seed crystal training data includes: seed crystal diffraction peak full width at half maximum (FWHM) training data A1, seed crystal diffraction peak FWHM deviation value training data A2, and seed crystal diameter training data A3; the environmental training data includes: insulation layer thermal resistance value training data B1, insulation layer thermal resistance value deviation value training data B2, and insulation layer shape factor training data B3; the control training data includes: coil input power training data C1, coil cooling power training data C2, and seed crystal cooling medium flow rate training data C3; the raw material data includes: doping type data training data D1 and conductivity doping concentration training data D2; the preprocessed training data obtained based on the seed crystal training data, the environmental training data, the control training data, and the raw material training data includes: Based on the seed crystal training data, the environmental training data, the control training data, and the raw material training data, a preparation vector is determined; wherein, the first element of the preparation vector is one of the seed crystal diffraction peak full width at half maximum (FWHM) training data, the seed crystal diffraction peak FWHM deviation value training data, and the seed crystal diameter training data; the second element of the preparation vector is one of the insulation layer thermal resistance value training data, the insulation layer thermal resistance value deviation value training data, and the insulation layer shape factor training data; the third element of the preparation vector is one of the coil input power training data, the coil cooling power training data, and the seed crystal cooling medium flow rate training data; and the fourth element of the preparation vector is one of the doping type training data and the conductivity doping concentration training data. Based on the prepared vector, the preprocessed training data is determined; The preprocessed training data is as follows: The preset neural network model includes: a feature extraction module and a fully connected module. The step of inputting the preprocessed training data into a preset neural network model and obtaining the prediction generation property data corresponding to the preprocessed training data through the preset neural network model includes: 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 generation property data corresponding to the preprocessed training data is obtained through the fully connected module.

4. A conductive gallium oxide fabrication system based on deep learning and heat exchange 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 2, or the steps of the preparation method according to claim 3.

Images