Growth condition determination support device, single crystal growth system, growth condition determination support method and program

Abstract

To select a parameter to be a control object from among many parameter candidates.SOLUTION: A rearing condition determination support apparatus, which is an apparatus for supporting determination of a rearing condition of a crystal, includes an acquisition part for acquiring learning data in which the rearing condition is related to quality information of the crystal, and a prediction model learning part for updating a prediction model in each use frequency, by machine learning based on learning data classified according to use frequency of a rearing device used for rearing of the crystal.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to a growth condition determination support device, a single crystal growth system, a growth condition determination support method, and a program. [Background technology]

[0002] The LT and LN single crystals used in SAW filters are primarily grown by the Czochralski method (hereafter referred to as the "Cz method"). The Cz method involves contacting a seed crystal with the surface of the raw material melt in a crucible, then pulling the seed crystal upward while rotating it to grow a cylindrical single crystal of the same orientation. In the Cz method, the rotation speed and pulling speed of the crystal, as well as the temperature environment during growth, must be appropriately selected depending on the type of crystal.

[0003] For example, Patent Document 1 discloses a method for evaluating the state of melting of a seed crystal based on the fluctuation range of the weight measured when the seed crystal is melted, with the aim of accurately evaluating the state of melting of the seed crystal. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2019-112264 Summary of the Invention [Problem to be solved by the invention]

[0005] Conventionally, growth devices such as crucibles are subject to significant deterioration due to use, and the quality of the grown crystal changes depending on the number of times it is used, making it difficult to accurately predict the quality.

[0006] The present invention has been made in view of the above circumstances, and aims to support the determination of growth conditions according to the number of times a crystal growth apparatus is used. [Means for solving the problem]

[0007] In order to achieve the above object, a cultivation condition determination support device according to one aspect of the present invention comprises: An apparatus for assisting in determining crystal growth conditions, comprising: an acquisition unit that acquires learning data in which growth conditions and crystal quality information are associated; a prediction model learning unit that updates a prediction model for each number of uses by machine learning using the associated growth conditions as an input and the crystal quality information as an output, based on the learning data classified according to the number of uses of the growth device used to grow the crystal; a quality prediction value calculation unit that calculates a predicted quality value of the crystal for each number of times the growth apparatus is used by inputting growth conditions into the prediction model for each number of times the growth apparatus is used; a growth condition determination unit that determines the growth conditions to be output based on the calculated quality prediction value; Equipped with 、 Each of the prediction models for each of the number of uses is a logistic regression model, The prediction model learning unit updates the prediction model so that a loss function of the logistic regression model is minimized. do. [Effects of the Invention]

[0008] It is possible to assist in determining growth conditions according to the number of times the crystal growth device is used. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an example of a system configuration of a single crystal growth system. [Figure 2] FIG. 1 is a diagram illustrating an example of a hardware configuration of a single crystal growth apparatus. [Figure 3] FIG. 2 is a diagram illustrating an example of a hardware configuration of a growth condition determination support device. [Figure 4] FIG. 2 is a diagram illustrating an example of a functional configuration of a growth condition determination support device. [Figure 5] 10 is a flowchart illustrating an example of the flow of a machine learning process. [Figure 6]10 is a flowchart showing an example of the flow of a cultivation condition determination support process. [Figure 7] FIG. 10 is a diagram illustrating an example of learning data. [Figure 8] FIG. 10 is a diagram showing experimental results. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an embodiment of the present invention (the present embodiment) will be described with reference to the drawings.

[0011] (System configuration of single crystal growth system 1) FIG. 1 is a diagram showing an example of the system configuration of a single crystal growth system.

[0012] The single crystal growth system 1 according to this embodiment includes a single crystal growth apparatus 2, a growth condition determination support device 3, and a growth management database 4. The single crystal growth apparatus 2, the growth condition determination support device 3, and the growth management database 4 are communicatively connected via a communication network 5. The communication network 5 may be the Internet or an in-house network.

[0013] The single crystal growth apparatus 2 is equipped with a crucible and the like, and is an apparatus for growing a single crystal of lithium niobate or the like. The single crystal growth apparatus 2 uses growth conditions determined by the growth condition determination support device 3 to bring a seed crystal into contact with a raw material melt obtained by melting raw materials, and raises the seed crystal while rotating it to grow a crystal.

[0014] The growth condition determination support device 3 receives and analyzes the growth result data from the growth management database 4. The growth condition determination support device 3 then outputs information indicating the growth conditions based on the results of the analysis.

[0015] The growth conditions are, for example, conditions related to the crystal pulling speed, the crystal rotation speed, and temperature control of a heater, such as a high-frequency heating device. The growth conditions may also include various measurement results during the crystal growth process. Examples of growth conditions include the time at which a shoulder is formed after the crystal melt and the seed crystal come into contact, the time at which the crystal diameter reaches the diameter of the straight body portion, the temperature change of the crucible storing the melt, the ambient temperature inside the device, and the temperature change of the cooling section. These conditions do not have to be directly related to the crystal pulling speed, rotation speed, or temperature control of the heating device, and may be statistical values ​​combining these. More specifically, the growth conditions include the start or end time of the shoulder of the crystal, the start or end of the body, the crucible bottom temperature or temperature change, the time or amount of heat generated by solidification and the weight of the melt at that time, the start or end time of power output, the power rise time, duration, or power rise amount, the start time of seeding, the average temperature of the chamber, the average temperature of the cooler, the average temperature of the crucible stand, the average temperature of the window, the average temperature of the inflow or outflow into the chamber, the average temperature of the high-frequency power source, the average temperature of the tube or cable output from the cooler, the average temperature of the seal, the average temperature of the chamber door, the average temperature of the chamber body, the flow rate of the inflow or outflow into the chamber, the average inflow and outflow rate of the water cooler, the flow rate of oil used for sealing, the average flow rate of the water-cooled tubes in the chamber, the weight at the time of convergence of hunting, the average growth rate of the body, the average difference between the shoulder and diameter, the time of bottoming out, etc. Note that the values ​​exemplified as averages can be appropriately changed to maximum or minimum values.

[0016] The growth management database 4 is a device that stores information for managing the growth state of the single crystal. The growth management database 4 transmits growth result data to the growth condition determination support device 3. The growth result data is data indicating the results of the single crystal growth, and is data that associates the single crystal growth conditions with quality information of the grown single crystal (specifically, the result of determining whether it is good or bad). The growth management database 4 also transmits information indicating the growth conditions to the single crystal growth device 2. The information indicating the growth conditions and the quality information of the single crystal are associated with each other using an initially set ID or the like. The growth management database 4 may store information indicating the growth conditions and the quality information in association with each other.

[0017] Here, quality information on single crystals refers to information on the polycrystallization of crystals, information on the occurrence of cracks or breaks in crystals pulled by the Cz method, and information on crystal falls. A single crystal is composed of a single crystallite, while a polycrystal is composed of multiple crystallites. Therefore, if a visual inspection reveals the presence of an amorphous pattern, it is assumed that the crystal has become polycrystallized. This can also be confirmed by observing the cross section using electron backscatter diffraction (EBSD). In the case of polycrystalline bodies, it can be confirmed that there are crystallites with multiple orientations.

[0018] In this embodiment, the quality information of the single crystal is information obtained by visually inspecting the growth result and determining that the crystals that have not been polycrystallized are "good" and that the crystals that have been polycrystallized are "bad."

[0019] (Hardware configuration of each device) Next, the hardware configuration of each device will be described. Fig. 2 is a diagram showing an example of the hardware configuration of a single crystal growth device. Fig. 2 is a diagram conceptually showing the device for growing a single crystal.

[0020] The single crystal growth apparatus 2 is an apparatus that brings a seed crystal SC into contact with a raw material melt L obtained by melting raw materials in a crucible 10, and raises the seed crystal SC while rotating it to grow a single crystal CR. The single crystal growth apparatus 2 includes, for example, the crucible 10, a crucible stand 20, a crucible lifting mechanism 30, a pulling shaft 40, a heater 50, a refractory inner cylinder 60, a refractory shield plate 70, a refractory material 80, and a control device 90. Also shown as related components are the seed crystal 100, the raw material melt 110, and the single crystal 120.

[0021] The crucible 10 is placed on a crucible stand 20. A refractory material 80 is arranged in the chamber so as to surround the crucible 10. A heater 50 is arranged between the crucible 10 and the refractory material 80. If necessary, the heaters 50 may be arranged in multiple stages. FIG. 1 shows heaters 50 arranged in two stages. The crucible 10 is heated by the heaters 50.

[0022] Furthermore, a refractory inner cylinder 60 and a refractory shield plate 70 may be installed to surround the upper part of the crucible 10. The refractory inner cylinder 60 and the refractory shield plate 70 are provided to keep the pulled single crystal 120 warm. A pulling shaft 40 is provided above the refractory material 80 so as to be rotatable and movable in the vertical direction. A seed crystal holder 41 is provided at the tip of the lower end of the pulling shaft 40, and holds the seed crystal 100. The crucible 10 and the crucible stand 20 are movable up and down by a crucible lifting mechanism 30.

[0023] The crucible 10 is a container for storing and holding the raw material melt and growing a single crystal. Since oxide crystals such as LN are grown in an oxygen-containing atmosphere, it is preferable that the crucible be made of a heat-resistant, oxygen-insensitive precious metal such as Pt (platinum), Rh (rhodium), or Ir (iridium), or an alloy thereof. The crucible 10 is an example of a growth device used for growing crystals.

[0024] Crucible stand 20 is provided as a support stand that supports crucible 10 from below. Crucible stand 20 may be made of various materials as long as it has sufficient heat resistance to withstand the heat of heater 50 and durability to support crucible 10.

[0025] Crucible lifting mechanism 30 is a drive mechanism for lifting and lowering crucible 10. In this embodiment, crucible 10 is placed on crucible stand 20, and therefore crucible 10 may be lifted and lowered by lifting and lowering lifting plate 31 supporting crucible stand 20. In other words, it is sufficient if crucible 10 can be lifted and lowered directly or indirectly.

[0026] Crucible lifting mechanism 30 is configured to be able to lift and lower crucible 10 without rotating it. Any mechanism may be used for crucible lifting mechanism 30 as long as it can lift and lower crucible 10 without rotating it. For example, a ball screw may be used to lift lift plate 31, and an intermediate jig may be provided to prevent lift plate 31 from rotating together with the ball screw.

[0027] The pulling shaft 40 is a means for holding a seed crystal 100 on a seed crystal holder 41 at its lower end, bringing the seed crystal 100 into contact with the surface of the raw material melt 110 held in the crucible 10, and pulling up a single crystal while rotating. The pulling shaft 40 has the seed crystal holder 41 for holding the seed crystal 100 at its lower end, and is equipped with a pulling shaft drive motor (not shown). The pulling shaft drive motor is a rotation drive mechanism for rotating the crystal while pulling it up.

[0028] Heater 50 is a means for heating crucible 10, and is arranged so as to surround the periphery of crucible 10. It may be a resistance heating heater or a high-frequency induction heating heater that uses an induction coil for heating.

[0029] The refractory inner cylinder 60, the refractory shield plate 70 and the refractory material 80 are made of sintered refractories such as alumina, zirconia, magnesia and calcia, and function to prevent heat from leaking to the outside.

[0030] The control device 90 controls the overall operation of the single crystal growth apparatus 2. The control device 90 is composed of, for example, a CPU, a storage device such as a main memory or a hard disk, a communication device for wired or wireless communication, an input device such as a keyboard, a touch panel or a mouse, a computer equipped with a display device such as a display, a sequencer, etc. The control device 90 executes various processes in accordance with programs stored in the storage device. The control device 90 may also be used (or supplied) alone as a control device for controlling a growth apparatus that grows a single crystal by the rotational pulling method. In other words, the control device 90 can be applied alone to known single crystal growth apparatuses.

[0031] The control device 90 controls the temperature of the heater 50. The control device 90 also controls the rotation and elevation of the pulling shaft 40 by controlling the pulling shaft drive motor.

[0032] Next, a description will be given of the hardware configuration of the cultivation condition determination support device 3. Fig. 3 is a diagram showing an example of the hardware configuration of the cultivation condition determination support device.

[0033] The growth condition determination support device 3 includes a CPU (Central Processing Unit) 101, a main memory device 102, an auxiliary memory device 103, an input device 104, a display device 105, a communication interface device 106, and a drive device 107. These devices are connected via a bus.

[0034] The CPU 101 is a main control unit that controls the operation of the growth condition determination support device 3, and realizes various functions described below by reading and executing programs stored in the main storage device 102.

[0035] The main memory device 102 reads and stores the program from the auxiliary memory device 103 when the growth condition determination support device 3 is started up. The auxiliary memory device 103 stores the installed program, as well as files, data, etc. required for various functions described later.

[0036] The input device 104 is a device for inputting various types of information and is realized by, for example, a keyboard or a pointing device. The display device 105 is for displaying various types of information and is realized by, for example, a display. The communication interface device 106 includes a LAN card or the like and is used for connecting to the development management database 20.

[0037] The program according to this embodiment is at least a part of various programs that control the growth condition determination support device 3. The program is provided, for example, by distributing a storage medium 108 or by downloading it from a network. The storage medium 108 on which the program is recorded can be of various types, including storage media that record information optically, electrically, or magnetically, such as a CD-ROM, a flexible disk, or a magneto-optical disk, and semiconductor memories that record information electrically, such as a ROM or a flash memory.

[0038] When storage medium 108 storing the program is set in drive device 107, the program is installed from storage medium 108 into auxiliary storage device 103 via drive device 107. A program downloaded from a network is installed into auxiliary storage device 103 via communication interface device 106.

[0039] (Functional configuration of the cultivation condition determination support device 3) Next, a description will be given of the functions of the cultivation condition determination support device 3. Fig. 4 is a diagram showing an example of the functional configuration of the cultivation condition determination support device.

[0040] The growth condition determination support device 3 includes an acquisition unit 31, a learning unit 32, a quality prediction value calculation unit 33, a growth condition determination unit 34, and an output unit 35.

[0041] In the learning process, the acquisition unit 31 acquires learning data in which growth conditions are associated with crystal quality information.

[0042] The learning unit 32 updates the prediction model by learning based on the learning data. Specifically, the learning unit 32 includes a learning data classification unit 321 and a prediction model learning unit 322. The learning data classification unit 321 classifies the learning data according to the number of times the crucible 10 has been used. Note that the crucible 10 is an example of a growth device, and other devices may be used.

[0043] The prediction model learning unit 322 updates the prediction model for each use count by machine learning based on the classified learning data. That is, a prediction model is constructed for each use count of the crucible 10. If the upper limit of the use count of the crucible 10 is 20, 20 prediction models from 0 to 19 are constructed. Then, for example, the prediction model learning unit 322 updates the prediction model for the Nth use count based on the learning data for the Nth use count. The prediction model is, for example, a logistic regression model. The prediction model may be other models, such as a support vector machine or a neural network.

[0044] The quality prediction value calculation unit 33 calculates a predicted value of quality according to given growth conditions. These growth conditions include the number of times the crucible 10 has been used. The quality prediction value calculation unit 33 then calculates a predicted value of quality based on a prediction model according to the number of times it has been used. The predicted value of quality is, for example, a value that indicates the probability that the quality is good, expressed as a number between 0 and 1. In this case, if the probability of good quality is 100%, the predicted value is 1, and if the probability of good quality is 50%, the predicted value is 0.5.

[0045] The growth condition determination unit 34 determines the growth conditions to be output based on the calculated threshold value, and the output unit 35 outputs information indicating the determined growth conditions.

[0046] (Operation of the cultivation condition determination support device 3) Next, the operation of the breeding condition determination support device 3 will be described with reference to the drawings. Figure 5 is a flowchart showing an example of the flow of machine learning processing.

[0047] The growth condition determination support device 3 executes machine learning processing periodically or at a timing according to a user's operation. When the growth condition determination support device 3 starts the machine learning processing, the acquisition unit 31 acquires learning data in which the growth conditions and quality information are associated from the growth management database 4 (step S11). Next, the learning data classification unit 321 classifies the learning data according to the number of times the crucible 10 has been used (step S12).

[0048] The prediction model learning unit 322 updates the prediction model for each number of uses of the crucible 10 by learning based on the classified learning data (step S13). Specifically, each prediction model is a logistic function that expresses the probability y that the quality of the single crystal will be good depending on the growth condition x.

[0049]

number

[0050] The prediction model learning unit 322 determines the parameters w and b so that the loss function L is minimized, with probability y of the single crystal being good being 0.5 or more as good and probability y of the single crystal being poor being poor being poor if it is less than 0.5.

[0051]

number

[0052] Here, N is the number of samples of data for each growth condition, M is the number of growth conditions, and y j is the quality of the single crystal predicted from the jth growth condition, t j is the quality of the single crystal grown under the jth growth condition.

[0053]

number

[0054] 6 is a flowchart showing an example of the flow of the growth condition determination support process. The growth condition determination support device 3 executes the growth condition determination support process at a timing according to a user operation, such as before starting the growth of a single crystal.

[0055] When the growth condition determination support device 3 starts the growth condition determination support process, the quality prediction value calculation unit 33 receives an input of the growth conditions (step S21). The growth conditions include the number of times the crucible 10 has been used. For example, when starting growth using a crucible 10 that has been used N times, the quality prediction value calculation unit 33 receives an input of the growth conditions including the number N of times the crucible 10 has been used.

[0056] Next, the quality prediction value calculation unit 33 calculates a quality prediction value under the input growing conditions using the prediction model with the number of uses N that has been learned by the above-mentioned machine learning process (step S22). The quality prediction value is, for example, a value indicating the probability that the quality is good, with a value between 0 and 1.

[0057] Next, the growth condition determination unit 34 determines whether the quality prediction value is equal to or greater than a threshold value (step S23). The threshold value is a preset value, for example, 0.5.

[0058] If the growth condition determination unit 34 determines that the quality prediction value is not equal to or greater than the threshold value (step S23: No), the process returns to step S21.

[0059] If the growth condition determination unit 34 determines that the quality prediction value is equal to or greater than the threshold value (step S23: Yes), it determines the input growth conditions and ends the growth condition determination support process.

[0060] 7 is a diagram showing an example of learning data. The learning data is data in which growth conditions are associated with quality information (good or bad) determined under the growth conditions. In the example of FIG. 7, for example, LotID indicates the number of times the crucible 10 has been used.

[0061] (Experimental results) The prediction model produced by the above-described cultivation condition determination support device 3 was evaluated. The performance of the prediction model for each number of uses was evaluated using the F1 score. The F1 score was calculated from the confusion matrix shown in Table 1.

[0062] [Table 1]

[0063] As shown in Table 1, the confusion matrix is ​​classified into four categories: true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN), and summarizes the number of prediction results that fall into each category. From these, the recall, precision, and F1 score that are judged to be "good" or "bad" can be expressed as follows:

[0064] Good recall = TP / (TP+FN) Good precision Precision=TP / (TP+FP) Good F-score = 2 x Recall x Precision / (Recall + Precision) Defect reproducibility rate TNR=TN / (TN+FP) Defective precision = TN / (TN+FN) F-score for defectives = 2 × TNR × precision for defectives / (TNR + precision for defectives) F1 score = (number of good samples x F-score of good samples + number of bad samples x F-score of bad samples) / total number of samples

[0065] Fig. 8 shows experimental results. For comparison, Fig. 8 shows results 902 predicted using a single prediction model regardless of the number of uses, and results 901 predicted using the prediction model according to this embodiment. Note that result 902 shows the average value of the F1 score because calculations according to the number of uses of crucible 10 are not performed.

[0066] In the prediction model according to the present embodiment, the F1 score differs depending on the number of times the crucible 10 is used, but the F1 score for each number of uses exceeded the F1 score (approximately 0.4) in result 902. Note that in result 901 predicted by the prediction model according to the present embodiment, analysis could not be performed for the 4th, 10th, 11th, and 12th uses due to the small number of defective products and the small number of samples. Note that the average F1 score that could be analyzed was approximately 0.6.

[0067] The growth condition determination support device 3 according to this embodiment can support the determination of growth conditions according to the number of times of use by machine learning according to the number of times the crucible 10, which is an example of a growth device, has been used.

[0068] In each of the above-described embodiments, an example was shown in which the judgment result included in the growth result data 30 is a binary value of "good" or "bad." However, depending on the prediction model used, it may not be a binary value. For example, if an unnecessary element of the product, such as a scratch or stain, is found, but the degree of the defect does not affect the performance of the product, it may be added as a "△" or the like, indicating a state between "good" (○) and "bad" (×).

[0069] Although the present invention has been described above based on the embodiments, the present invention is not limited to the requirements shown in the above embodiments. These requirements can be changed without departing from the spirit of the present invention, and can be appropriately determined depending on the application form. [Industrial Applicability]

[0070] The present invention can be applied to crystal growth. [Explanation of symbols]

[0071] 1. Single crystal growth system 2. Single crystal growth equipment 3. Support device for determining cultivation conditions 4. Development management database 5. Communication Network 31 Acquisition Department 32 Learning Department 33 Quality prediction value calculation unit 34. Development Condition Determination Unit 35 Output section 321 Training Data Classification Unit 322 Prediction Model Learning Unit

Claims

1. An apparatus for assisting in determining crystal growth conditions, comprising: an acquisition unit that acquires learning data in which growth conditions and crystal quality information are associated; a prediction model learning unit that updates a prediction model for each number of uses by machine learning using the associated growth conditions as an input and the crystal quality information as an output, based on the learning data classified according to the number of uses of the growth device used to grow the crystal; a quality prediction value calculation unit that calculates a predicted quality value of the crystal for each number of times the growth apparatus is used by inputting growth conditions into the prediction model for each number of times the growth apparatus is used; a growth condition determination unit that determines the growth conditions to be output based on the calculated quality prediction value; Equipped with Each of the prediction models for each of the number of uses is a logistic regression model, the prediction model learning unit updates the prediction model so as to minimize a loss function of the logistic regression model. A support device for determining cultivation conditions.

2. a training data classification unit that classifies the training data acquired by the acquisition unit according to the number of times the growth device used to grow the crystal has been used; The cultivation condition determination support device according to claim 1.

3. A single crystal growth system comprising a single crystal growth apparatus and a growth condition determination support apparatus, The cultivation condition determination support device comprises: An apparatus for assisting in determining crystal growth conditions, comprising: an acquisition unit that acquires learning data in which growth conditions and crystal quality information are associated; a prediction model learning unit that updates a prediction model for each number of uses by machine learning using the associated growth conditions as an input and the crystal quality information as an output, based on the learning data classified according to the number of uses of the growth device used to grow the crystal; a quality prediction value calculation unit that calculates a predicted quality value of the crystal for each number of times the growth apparatus is used by inputting growth conditions into the prediction model for each number of times the growth apparatus is used; a growth condition determination unit that determines the growth conditions to be output based on the calculated quality prediction value, Each of the prediction models for each of the number of uses is a logistic regression model, the prediction model learning unit updates the prediction model so as to minimize a loss function of the logistic regression model; The single crystal growth apparatus is growing a single crystal according to the output growth conditions; Single crystal growth system.

4. 1. A computer-implemented method comprising: acquiring learning data that associates growth conditions with crystal quality information; updating a prediction model for each number of uses by machine learning using the learning data classified according to the number of uses of the growth device used to grow the crystal, with the associated growth conditions as input and the quality information of the crystal as output; calculating a predicted value of crystal quality for each number of times the growth apparatus is used by inputting growth conditions into the prediction model for each number of times the growth apparatus is used; determining growth conditions to be output based on the calculated quality prediction value; Equipped with Each of the prediction models for each of the number of uses is a logistic regression model, the updating step updates the prediction model so as to minimize a loss function of the logistic regression model. A method for supporting the determination of development conditions.

5. On the computer, acquiring learning data that associates growth conditions with crystal quality information; updating a prediction model for each number of uses by machine learning using the learning data classified according to the number of uses of the growth device used to grow the crystal, with the associated growth conditions as input and the quality information of the crystal as output; calculating a predicted value of crystal quality for each number of times the growth apparatus is used by inputting growth conditions into the prediction model for each number of times the growth apparatus is used; determining growth conditions to be output based on the calculated quality prediction value; Execute Each of the prediction models for each of the number of uses is a logistic regression model, the updating step updates the prediction model so as to minimize a loss function of the logistic regression model. program.

Images