Data prediction device and quartz glass crucible manufacturing system

Abstract

To provide a data prediction device capable of greatly shortening a cycle time required to adjust melting conditions in manufacturing a quartz glass crucible.SOLUTION: A data prediction device comprises: a storage part 12 which stores a data set generated by linking a measured value (input data) of a dimension at a predetermined position and a measured value (teacher data) of weight of a quartz glass crucible actually manufactured under melting conditions set to a crucible manufacturing device to each other; model generation means (control part 11) which generates a data prediction model for predicting the weight of the quartz glass crucible through machine learning using the data set; and data prediction means (control part 11) which receives as input data the measured value of the dimension at the predetermined position output from the crucible manufacturing device in a manufacturing process, and outputs a predicted weight of the quartz glass crucible manufactured in the manufacturing proces using the learnt data prediction model.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present invention relates to a data prediction device for predicting the weight of a vitreous silica crucible and a vitreous silica crucible manufacturing system. [Background technology]

[0002] The Czochralski method (CZ method) is widely used for growing silicon single crystals. In this method, a seed crystal is brought into contact with the surface of silicon melt formed in a quartz glass crucible (hereinafter sometimes simply referred to as "crucible"), and while the crucible is rotated, the seed crystal is pulled upward while rotating in the opposite direction, thereby growing a single crystal at the bottom of the seed crystal.

[0003] The quartz glass crucible used to contain this silicon melt generally has a two-layer structure, with a transparent layer made of high-purity synthetic silica glass on the inner surface and an opaque layer made of natural silica glass with excellent thermal properties on the outer surface.

[0004] The rotating mold method is known as an example of a method for manufacturing such a quartz glass crucible. In the rotating mold method, first, a raw material powder of natural silica glass (natural silica powder) is layered on the surface of a rotating crucible mold, and then a raw material powder of synthetic silica glass (synthetic silica powder) is layered on the surface of the natural silica powder layer to form a raw material powder layer (molding process). Next, this raw material powder layer is heated and melted from the inside to the outside by arc discharge, and then cooled to form a synthetic silica glass layer (transparent layer) on the inner surface and a natural silica glass layer (opaque layer) on the outer surface, resulting in a two-layered crucible molded body (melting process). Finally, the upper end of the crucible molded body is cut off to obtain a two-layered quartz glass crucible (cutting process).

[0005] Furthermore, the quartz glass crucible obtained by the above manufacturing method requires high weight accuracy. Therefore, after the above cutting process, the weight of the actually manufactured quartz glass crucible is measured (measurement process). Then, the melting conditions are adjusted based on the actual weight value obtained from this measurement. The adjustment of the melting conditions is usually performed based on the experience of the manufacturing operator.

[0006] On the other hand, studies have been conducted on a method in which a manufacturing condition setting support device (computer) determines manufacturing conditions (including melting conditions) based on measurement data of actually manufactured quartz glass crucibles, without relying on the experience of the manufacturing worker (see Patent Document 1).

[0007] For example, Patent Document 1 describes a method of calculating the degree of agreement between data obtained by a simulation based on predetermined physical property parameters and manufacturing conditions and measurement data of a crucible actually manufactured based on those manufacturing conditions, and then repeatedly running the simulation while changing the physical property parameters and manufacturing conditions until the degree of agreement reaches a predetermined level, and adopting the manufacturing conditions when the degree of agreement reaches or exceeds the predetermined level as improved manufacturing conditions. [Prior art documents] [Patent documents]

[0008] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-128509 Summary of the Invention [Problem to be solved by the invention]

[0009] However, in conventional methods for manufacturing quartz glass crucibles, a process of measuring the weight (a process of obtaining measurement data) is carried out after the crucible is manufactured, so adjustment of the melting conditions based on the measurement data is a task that is performed after the measurement data of the completed crucible has been fed back to the manufacturing workers.

[0010] In other words, when using conventional methods for manufacturing vitreous silica crucibles, adjustment of the melting conditions, whether performed by a person or a computer, can only be performed after the crucible is actually manufactured and the measurement data is fed back. Therefore, for example, the time (cycle time) from when the melting conditions are set in a specific manufacturing process to when the adjusted melting conditions are set next can be significantly longer than the time (lead time) required to complete the crucible in the manufacturing process. This lengthy cycle time needs to be improved from the perspective of improving the efficiency of crucible manufacturing.

[0011] The present invention has been made in consideration of the above-mentioned problems, and aims to provide a data prediction device and a quartz glass crucible manufacturing system that can significantly shorten the cycle time required to adjust melting conditions in the manufacture of quartz glass crucibles. [Means for solving the problem]

[0012] The data prediction device of the present invention is characterized by comprising: a memory means (corresponding to the memory unit 12 described later) that stores a dataset created by linking the input data to the teacher data, using the actual measured values ​​of the dimensions at a predetermined position of a quartz glass crucible actually manufactured under melting conditions set in a crucible manufacturing apparatus as input data and the actual measured values ​​of the weight of a quartz glass crucible actually manufactured under the melting conditions; a model generation means (corresponding to the control unit 11 described later) that generates a data prediction model by machine learning using the dataset read from the memory means; and a data prediction means (corresponding to the control unit 11 described later) that accepts the actual measured values ​​of the dimensions at a predetermined position output from the crucible manufacturing apparatus during a measurement process in the quartz glass crucible manufacturing process as input data, and uses the trained data prediction model to output a predicted weight of the quartz glass crucible manufactured in the manufacturing process.

[0013] According to the data prediction device of the present invention, instead of measuring the weight using a completed quartz glass crucible, the weight of a quartz glass crucible to be completed is predicted using a pre-trained data prediction model. This significantly reduces the time until the weight is fed back to the manufacturing worker compared to measuring the weight using a completed quartz glass crucible, allowing the manufacturing worker to start adjusting the melting conditions earlier. Therefore, for example, the cycle time from when the melting conditions are set in a specific manufacturing process to when the adjusted melting conditions are next set can be significantly reduced.

[0014] Furthermore, it is desirable that the data prediction device according to the present invention further comprises a display means for displaying the predicted weight output by the data prediction means.

[0015] Furthermore, it is desirable that the data prediction device of the present invention sets the actual measured values ​​of the dimensions at the specified positions as all or part of the outer diameter of the straight body portion of the quartz glass crucible, the thickness of the bottom portion, the thickness of the corner portion, the thickness of the straight body portion, the thickness of the transparent layer at the bottom portion, the thickness of the transparent layer at the corner portion, and the thickness of the transparent layer at the straight body portion.

[0016] The quartz glass crucible manufacturing system of the present invention comprises the data prediction device and a crucible manufacturing apparatus that manufactures quartz glass crucibles through a manufacturing process including a molding process, a melting process, and a measurement process, and is characterized in that the crucible manufacturing apparatus carries out the melting process under melting conditions that are adjusted based on the trend in the predicted weight of the quartz glass crucible output from the data prediction device, which operates as a machine-learned data prediction model.

[0017] Furthermore, in the silica glass crucible manufacturing system according to the present invention, it is desirable that the melting conditions be data on the melting process including the current value, voltage value, integrated power value, electrode opening, electrode position, melting temperature, pressure, cooling water temperature, cooling water flow rate, and melting time during melting. [Effects of the Invention]

[0018] The data prediction device and vitreous silica crucible manufacturing system according to the present invention have the effect of significantly shortening the cycle time required for adjusting melting conditions in the manufacture of vitreous silica crucibles. [Brief explanation of the drawings]

[0019] [Figure 1] FIG. 1 is a diagram showing an example of the system configuration of a silica glass crucible manufacturing system according to the present invention. [Figure 2] FIG. 2 is a diagram showing an example of the configuration of a crucible manufacturing apparatus. [Figure 3] FIG. 3 is a flowchart showing an example of a manufacturing process for a silica glass crucible. [Figure 4] FIG. 4 is a cross-sectional view of the crucible molded body formed in the melting step. [Figure 5] FIG. 5 is a cross-sectional view of the vitreous silica crucible obtained by the cutting step. [Figure 6] FIG. 6 is a diagram showing an example of the hardware configuration of a computer that operates as a data prediction device according to the present invention. [Figure 7] FIG. 7 is a diagram illustrating an example of a data set for generating a data prediction model. [Figure 8] FIG. 8 is a diagram illustrating an example of the configuration of a neural network. [Figure 9] FIG. 9 is a diagram illustrating an example of the configuration of input data. [Figure 10] FIG. 10 is a diagram showing the results of evaluation of learning. [Figure 11] FIG. 11 is a diagram showing prediction results using a trained data prediction model. DETAILED DESCRIPTION OF THE INVENTION

[0020] Hereinafter, an embodiment of a data prediction device and a quartz glass crucible manufacturing system according to the present invention will be described in detail with reference to the drawings. Note that the present invention is not limited to this embodiment. Furthermore, in the specification and drawings of the present application, elements that can be similarly described may be designated by the same reference numerals, and duplicated explanations may be omitted.

[0021] <System configuration> 1 is a diagram showing an example of the system configuration of a vitreous silica crucible manufacturing system according to the present invention. The vitreous silica crucible manufacturing system of this embodiment comprises a data prediction device 1 that operates as a host computer that performs processing to predict the weight of a vitreous silica crucible to be actually manufactured (hereinafter referred to as data prediction processing) and processing to generate a learning model that executes the weight prediction (hereinafter referred to as learning model generation processing), and a crucible manufacturing device 3 that manufactures vitreous silica crucibles in accordance with melting conditions adjusted and set by a manufacturing operator 2 based on the weight prediction results.

[0022] <Crucible manufacturing equipment> As an example, the crucible manufacturing apparatus 3 of this embodiment uses a rotating mold method to manufacture a two-layer quartz glass crucible having a transparent layer formed of high-purity synthetic silica glass on the inner surface and an opaque layer formed of natural silica glass with excellent thermal properties on the outer surface.

[0023] 2 is a cross-sectional view showing an example of the configuration of a crucible manufacturing apparatus 3 of this embodiment. This crucible manufacturing apparatus 3 includes a crucible molding mold 34 that includes, for example, an inner member 31 formed of a metal mold having a plurality of through holes (not shown) drilled therein, and a holder 33 that holds the inner member 31 and has a ventilation portion 32 provided on its outer periphery.

[0024] A rotating shaft 35 connected to a rotating means (not shown) is fixed to the bottom of the holder 33, and rotatably supports a crucible mold 34. The ventilation section 32 is connected to an exhaust port 36 that penetrates from approximately the center of the bottom of the holder 33 in the axial direction of the rotating shaft 35, and the exhaust port 36 is further connected to a pressure reducing mechanism 37.

[0025] In addition, an arc electrode 38 for arc discharge, and although not shown, a raw material supply nozzle and a nozzle for spraying gas (nitrogen gas, oxygen gas, etc.) onto a predetermined portion of the crucible are provided on the upper part facing the inner member 31.

[0026] Here, a description will be given of a method for manufacturing a silica glass crucible using the crucible manufacturing apparatus 3. Fig. 3 is a flow chart showing an example of a manufacturing process for a silica glass crucible.

[0027] To manufacture a silica glass crucible using the crucible manufacturing apparatus 3, first, a rotary drive source (not shown) is used to rotate the rotation shaft 35 in the direction of the arrow (see FIG. 2 ), thereby rotating the crucible mold 34 at a predetermined speed. Then, the pressure in the ventilation section 32 is reduced by driving the pressure reducing mechanism 37, and silica glass raw material powder (natural silica powder, synthetic silica powder) is supplied into the inner member 31 from the raw material supply nozzle while suctioning the inner surface of the inner member 31 through the numerous through-holes formed in the inner member 31. Specifically, coarse-grained natural silica powder is first supplied, and a layer of natural silica powder is formed on the surface of the inner member 31 by suction and centrifugal force. Then, fine-grained synthetic silica powder is supplied, and another layer of synthetic silica powder is formed on the surface of the natural silica powder by suction and centrifugal force, forming a two-layered raw material powder laminate (Step S1: molding step).

[0028] After forming the raw material powder laminate, current is passed through the arc electrode 38 to heat and melt the raw material powder laminate from the inside, first vitrifying the surface layer (forming a synthetic silica glass layer), while continuing to reduce the pressure using the pressure reduction mechanism 37. Thereafter, the pressure reduction using the pressure reduction mechanism 37 and the heating and melting using the arc electrode 38 are continued, and the raw material powder laminate is vitrified all the way to the outer surface (forming a natural silica glass layer), forming a two-layered crucible molded body (step S2: melting step).

[0029] Fig. 4 is a cross-sectional view of a molded crucible formed in the melting step. The molded crucible 40 shown in Fig. 4 is composed of a transparent layer 40a forming a synthetic silica glass layer and an opaque layer 40b forming a natural silica glass layer.

[0030] After the molded crucible body 40 is formed, an appearance inspection and dimensional measurement are performed using this crucible formed body 40 (step S3: measurement step). In the dimensional measurement, for example, the outer diameter, wall thickness, and transparent layer thickness at predetermined positions of the crucible formed body 40 are measured.

[0031] Finally, the upper end of the crucible molded body 40 is cut at a predetermined height to obtain a quartz glass crucible with a two-layer structure (step S4: cutting step). Specifically, a quartz glass crucible with a two-layer structure is obtained by cutting the crucible molded body 40 shown in Figure 4 along the dotted lines. Generally, the crucible molded body 40 produced by the rotational mold method is manufactured so that it is taller than the required dimensions of the finished quartz glass crucible, and the required dimensions are met by cutting the upper opening portion of the crucible molded body 40.

[0032] Fig. 5 is a cross-sectional view of the silica glass crucible obtained by the cutting process. The silica glass crucible 41 shown in Fig. 5 is composed of a transparent layer 41a forming a synthetic silica glass layer and an opaque layer 41b forming a natural silica glass layer.

[0033] In this embodiment, the case of manufacturing a quartz glass crucible with a two-layer structure has been described as an example, but the present invention is not limited to this. The data prediction device and quartz glass crucible manufacturing system of the present invention can also be applied to the case of manufacturing a quartz glass crucible with a three-layer structure or more. That is, they can also be applied to the case of manufacturing a quartz glass crucible with a three-layer structure formed by an inner layer, an intermediate layer, and an outer layer, or even a quartz glass crucible with a four-layer structure or more formed with multiple intermediate layers. For example, when manufacturing a quartz glass crucible with a three-layer structure or more, a raw material powder laminate and a crucible molded body with a three-layer structure or more composed of an inner layer, one or more intermediate layers, and an outer layer are formed in the molding process and melting process described above, thereby obtaining a quartz glass crucible with a three-layer structure or more.

[0034] <Configuration of data prediction device> FIG. 6 is a diagram illustrating an example of the hardware configuration of a computer operating as a data prediction device according to the present invention. In FIG. 6, the data prediction device 1 includes a control unit 11 including a central processing unit (CPU) and a field programmable gate array (FPGA), a storage unit 12 including various types of memory such as read-only memory (ROM) and random access memory (RAM), an input unit 13 including a user interface such as a keyboard and a mouse, an interface unit 14 performing input / output processing such as printing and scanning, a display unit 15 serving as a display, and a communication unit 16 for communicating with the outside via a predetermined network. While FIG. 6 illustrates the data prediction device 1 including the input unit 13 including a user interface such as a keyboard and a mouse, the present invention is not limited to this. The display unit 15 may have touch panel functionality, eliminating the input unit 13 or using the input unit 13 in combination.

[0035] 6, the control unit 11 executes, for example, a data prediction program for predicting the weight of a quartz glass crucible and a learning model generation program for generating a learning model for weight prediction, in order to realize the data prediction process and learning model generation process by the data prediction device 1 of this embodiment. The storage unit 12 stores programs (data prediction program, learning model generation program) related to the data prediction process and learning model generation process of this embodiment, various information (datasets for learning, etc.), and various data obtained during the process (dimensions of predetermined positions, predicted weight, etc.). The control unit 11 executes the data prediction process and learning model generation process of this embodiment by reading out the various programs stored in the storage unit 12.

[0036] The storage unit 12 is not limited to an internal memory, and may be an external storage medium such as a DVD (Digital Versatile Disc) or an SD memory, or may be configured with both an internal memory and an external storage medium (such as a DVD or an SD memory). For ease of explanation, the hardware configuration of the data prediction device 1 of this embodiment lists the configuration related to the data prediction process and learning model generation process of this embodiment, and does not represent all the functions of the computer that constitutes the data prediction device 1.

[0037] Furthermore, the data prediction device 1 of this embodiment is assumed to be a general-purpose PC such as a desktop personal computer or a notebook computer, but is not limited to these and may also be, for example, a mobile terminal such as a smartphone or a tablet terminal.

[0038] <Learning model generation process> Next, before describing the data prediction process in the data prediction device 1 of this embodiment, the learning model generation process, which is the premise of the data prediction process, will be described in detail. Note that the input data used in the learning model generation process and the data prediction process is assumed to be standardized in advance by the control unit 11. That is, as a preprocessing before machine learning and weight prediction, the control unit 11 performs a standardization process on the actual measured values ​​of dimensions at predetermined positions that make up the input data, individually setting the average value to 0 and the standard deviation to 1.

[0039] In the data prediction device 1 of this embodiment, the control unit 11 operates as a learning model that predicts the weight of the quartz glass crucible, i.e., a data prediction model, and receives as input data, for example, actual measurement values ​​of dimensions at a predetermined position output from the crucible manufacturing device 3 in the measurement step (step S3) in the manufacturing process shown in Fig. 3, and outputs the weight (predicted weight) of the quartz glass crucible. This data prediction model is generated using a known machine learning algorithm, such as a neural network.

[0040] In addition, the dataset used in the machine learning algorithm is created by, for example, using the measured values ​​of the dimensions of a specified position of a quartz glass crucible actually manufactured under the melting conditions set in the crucible manufacturing device 3 (such as the current value and melting time during melting, which will be described later) as input data, using the measured value of the weight of a quartz glass crucible actually manufactured under the melting conditions described above as the output label (correct label), and linking the output label to this input data.

[0041] As described above, the input data of the data set are actual measurement values ​​of dimensions corresponding to predetermined positions of an actually manufactured silica glass crucible, but in this embodiment, as an example, nine dimensions (mm) are used: the outer diameter of the crucible at position G, the outer diameter at position F, the outer diameter at position E, the wall thickness at position A, the wall thickness at position D, the wall thickness at position F, the transparent layer thickness at position A, the transparent layer thickness at position D, and the transparent layer thickness at position F. Note that each position (A, D, E, F, G) refers to, for example, the bottom (A), corner (D), and straight body (E, F, G) as shown in the cross-sectional view of the silica glass crucible 41 in Figure 5.

[0042] Furthermore, in this embodiment, as described above, the input data is the nine dimensions. However, the present invention is not limited to this. The input data may be, for example, a portion of the nine dimensions, or may include other dimensions in addition to the nine dimensions. Furthermore, the input data may include parameters other than dimensions, such as melting data (e.g., current value during melting, melting time) and environmental conditions such as climatic conditions. When parameters other than dimensions are included in the input data, if the parameters include non-numeric qualitative data (e.g., equipment such as electrodes and molds), the qualitative data is converted into quantitative data (numeric values) and then input. The method of quantification is not particularly limited, but may include, for example, dummy variables (one-hot encoding) or the like to convert the qualitative data into quantitative data.

[0043] Fig. 7 is a diagram showing an example of a dataset for generating a data prediction model. In Fig. 7, the dataset for performing machine learning on a neural network is composed of a combination of the above-mentioned input data (actually measured values ​​of the outer diameter at position G, the outer diameter at position F, the outer diameter at position E, the wall thickness at position A, the wall thickness at position D, the wall thickness at position F, the thickness of the transparent layer at position A, the thickness of the transparent layer at position D, the thickness of the transparent layer at position F, etc. of an actually manufactured crucible) and the above-mentioned output label (actually measured value of the weight of an actually manufactured crucible).

[0044] In this embodiment, for example, a dataset for training the data prediction model (the dataset shown in FIG. 7 ) is stored in advance in the storage unit 12. Approximately 80% of the dataset stored in the storage unit 12 is used as training data, and approximately 20% is used as evaluation data. Here, the training data is a dataset used to train the data prediction model, and the evaluation data is a dataset that is not used for model training but is used to verify whether the trained data prediction model has versatility. The data prediction model was verified using a holdout method. It is desirable to prepare a number of training data sets that is sufficient to achieve a desired accuracy in the data prediction model. In addition, the performance of the data prediction model in this embodiment is evaluated using the mean squared error (MES), which is one of the evaluation indices. That is, the difference between the actual measurement value and the predicted value is squared, and the sum is divided by the number of data sets to be used as the evaluation target value. Therefore, for example, the smaller this value, the lower the error of the model. Note that the evaluation indices are not limited to this.

[0045] Then, with the prepared data set (training data, evaluation data) stored in the memory unit 12 as described above, the control unit 11 reads out the training data from the memory unit 12 and generates a data prediction model optimized for predicting the weight of the crucible by performing supervised learning using the training data, for example, using a neural network, which is one of the machine learning algorithms.

[0046] <An example of a machine learning algorithm> FIG. 8 is a diagram showing an example of the configuration of a neural network for performing machine learning. The machine learning algorithm used in this embodiment is a fully connected neural network, which is composed of, for example, an input layer, an intermediate layer having one or more layers, and an output layer. Each unit in the input layer of this neural network corresponds one-to-one to the dimensions (x1, x2, x3, ...) of a predetermined position that constitutes the input data in the above-mentioned dataset. In other words, the number of each dimension that constitutes the input data is the number of input units. Meanwhile, the number of units in the output layer corresponds to the weight of the crucible (output label: z), and is one in this embodiment.

[0047] In this embodiment, the activation function in the intermediate layer is a ReLU (Rectified Linear Unit) function, and the activation function in the output layer is a linear function. The number of intermediate layers and the number of units are not specified and can be set arbitrarily. Therefore, the number of intermediate layers and the number of units are appropriately determined depending on the amount of data, the type of data, the required output accuracy, and other factors. For example, as the number of intermediate layers and the number of units increase, the performance of the neural network, such as analytical flexibility and output accuracy, improves. However, the amount of data, memory usage, and calculation volume also increase.

[0048] Specifically, first, the control unit 11 reads one training data from the storage unit 12, and calculates the input data (x1, x2, x3, ..., x n ) is input to each unit of the input layer. Then, the input data (x1, x2, x3, ..., x n ) with weights (w 11 ~w 1m ,w 21 ~w 2m ,w 31 ~w 3m ,…,w n1 ~w nm ), and the multiplication result is output to each unit in the next layer (middle layer). This allows the input values ​​(y1, y2, y3, ..., y m) is as follows: n is the number of units in the input layer, m is the number of units in the hidden layer, and b1, b2, b3, ..., b m is the bias. Also, the weight (w 11 ~w 1m ,w 21 ~w 2m ,w 31 ~w 3m ,…,w n1 ~w nm ) and bias (b1,b2,b3,,b m ) is a value that is updated during the learning process. y1=x1w 11 +x2w 21 +x3w 31 +...+x n w n1 +b1 y2=x1w 12 +x2w 22 +x3w 32 +...+x n w n2 +b2 y3=x1w 13 +x2w 23 +x3w 33 +...+x n w n3 +b3 … y m =x1w 1m +x2w 2m +x3w 3m +...+x n w nm +b m

[0049] Next, each unit in the hidden layer receives multiple input values ​​(y1, y2, y3, ..., y m ), the ReLU function described in the following formula is calculated for each, and the result is output to each unit in the next layer, where M is between 1 and m.

[0050]

number

[0051] In the output layer, for example, a linear function is applied to sum up the input values ​​received from each unit in the intermediate layer, and the sum is output as a predicted value of the crucible weight (predicted weight).

[0052] Then, the control unit 11 calculates the mean square error between the predicted value, which is the output of the output layer, and the weight of the training data, and trains the data prediction model (updating the weights and biases) by repeatedly learning over a predefined number of epochs so as to minimize this error.

[0053] In this embodiment, the learning model is generated using the dataset shown in Fig. 7, but the input data of the dataset is not limited to this. For example, some dimensions may be selected from the dimensions constituting the input data shown in Fig. 7, and supervised learning may be performed using a dataset in which the selected dimensions (input data) are linked to the measured values ​​(output labels) of the weights of crucibles that have actually been manufactured. Alternatively, supervised learning may be performed using a dataset in which input data in which other parameters have been newly added to the above input data are linked to the measured values ​​(output labels) of the weights of crucibles that have actually been manufactured.

[0054] In addition, in this embodiment, a neural network is used as an example of a machine learning algorithm to generate the above-described data prediction model, but the machine learning algorithm for generating the data prediction model is not limited to this. For example, an algorithm that combines a decision tree and gradient boosting, such as LightGBM, can be used.

[0055] <Data prediction processing> Next, the data prediction process in the data prediction device 1 of this embodiment will be described in detail.

[0056] In this embodiment, the control unit 11, which operates as a trained data prediction model, receives as input data, for example, the actual measurement values ​​of dimensions at predetermined positions (outer diameter at position G, outer diameter at position F, outer diameter at position E, wall thickness at position A, wall thickness at position D, wall thickness at position F, thickness of the transparent layer at position A, thickness of the transparent layer at position D, thickness of the transparent layer at position F) output by the crucible manufacturing apparatus 3 in the measurement step (step S3) in the manufacturing process shown in Fig. 3, and outputs the weight (predicted weight) of the quartz glass crucible being manufactured. In other words, the control unit 11 immediately predicts the weight of the quartz glass crucible to be completed by inputting the actual measurement values ​​of the dimensions at predetermined positions obtained in the measurement step (step S3), without waiting for the quartz glass crucible to be completed.

[0057] Specifically, first, an operator (manufacturing worker 2) of the data prediction device 1 uses a user interface (input unit 13 including a keyboard and mouse) to input actual measurement values ​​of dimensions at predetermined positions obtained in the measurement process (step S3) as input data to the data prediction device 1 (step S11 in FIG. 3). At this time, the actual measurement values ​​of dimensions at the same positions as when the data prediction model was generated are input as input data. FIG. 9 is a diagram showing an example of the configuration of input data. Note that when parameters other than dimensions are included in the input data, for example, if the parameters include non-numerical qualitative data, the qualitative data is converted into quantitative data in the same manner as when the data prediction model was generated, and then input. Then, the control unit 11, operating as a trained data prediction model, receives the input data shown in FIG. 9 and outputs the weight of the quartz glass crucible to be completed as a predicted weight (step S12 in FIG. 3). The weight predicted here (predicted weight) is then displayed on the display unit 15 of the data prediction device 1.

[0058] <Reflection in manufacturing processes> By checking the predicted weight displayed on the display unit 15 of the data prediction device 1, the manufacturing worker 2 can know the tendency (large or small dimensions) of the quartz glass crucible that will be manufactured if the melting process is carried out under the current melting conditions. Therefore, based on the predicted weight displayed on the display unit 15, the manufacturing worker 2 adjusts the current melting conditions (step S13 in FIG. 3), for example, so that the weight value becomes smaller if the tendency of the weight value is larger than the assumed value, or so that the weight value becomes larger if the tendency of the weight value is smaller than the assumed value, and reflects this in the melting process of the crucible (step S14 in FIG. 3).

[0059] The adjustment of the melting conditions involves, for example, adjusting data on the melting process (melting data). The melting data to be adjusted includes, for example, the current value (current value of the arc electrode 38) during melting, the voltage value, the integrated power value, the electrode opening, the electrode position, the melting temperature, the pressure, the cooling water temperature, the cooling water flow rate, and the melting time. The numerical data during melting includes a set value, an average value, a maximum value, a minimum value, an integrated value, and the like.

[0060] <Effects> The data prediction device 1 of this embodiment is equipped with a memory unit 12 that stores a dataset created by linking the input data to the teacher data, using the actual measured values ​​of the dimensions at a predetermined position of a quartz glass crucible actually manufactured under the melting conditions set in the crucible manufacturing apparatus 3 as input data and the actual measured values ​​of the weight of the quartz glass crucible actually manufactured under the melting conditions as training data, a model generation means (control unit 11) that generates a data prediction model by machine learning using the dataset read from the memory unit 12, and a data prediction means (control unit 11) that accepts the actual measured values ​​of the dimensions at a predetermined position output from the crucible manufacturing apparatus 3 during the measurement process in the quartz glass crucible manufacturing process as input data, and uses the trained data prediction model to output a predicted weight of the quartz glass crucible manufactured in the manufacturing process.

[0061] In this embodiment, instead of measuring the weight using a completed quartz glass crucible (without waiting for the completion of the quartz glass crucible), a pre-trained data prediction model is used to predict the weight of the quartz glass crucible that is to be completed. This significantly reduces the time until the weight is fed back to the manufacturing worker 2 compared to when the weight is measured using a completed quartz glass crucible, and therefore allows the manufacturing worker 2 to start adjusting the melting conditions earlier. Therefore, for example, the cycle time from when the melting conditions are set in a specific manufacturing process until the adjusted melting conditions are then set can be significantly reduced. [Example]

[0062] Next, an example of a data prediction model optimized in the learning model generation process will be described.

[0063] In this example, for example, in generating a data prediction model for predicting the weight of a crucible, 6,000 data sets were prepared for use in learning. These data sets were then randomly divided into training data and evaluation data. The breakdown was 4,800 training data sets and 1,200 evaluation data sets. Furthermore, mean squared error (MES), which is one of the loss functions, was used to evaluate the performance of the model.

[0064] The optimization algorithm used was "Adam," with the activation function in the intermediate layer being a ReLU function and the activation function in the output layer being a linear function. Furthermore, the initial learning rate was set to "0.01," and the learning rate was automatically decreased as the learning progressed. The batch size was set to 32. Furthermore, the initial value for the number of epochs was set to 1000, and in order to prevent overfitting, learning was terminated if the error had not improved compared to the previous epoch.

[0065] Then, we used the training data to perform machine learning on the neural network with the above specifications, and had the trained data prediction model predict weight using nine test data sets that had been prepared in advance.

[0066] FIG. 10 is a diagram showing the results of the learning evaluation, showing, for example, the transition of the mean squared error with respect to the degree of learning (epochs). As shown in FIG. 10, the mean squared error of the data prediction model of this embodiment decreases as the learning progresses, confirming that the learning is progressing smoothly. Furthermore, the mean squared error becomes sufficiently small from about epoch number 4 onwards, and thereafter, there is no change in the mean squared error. Therefore, in this embodiment, it can be said that an epoch number of about 4 is suitable for learning the data prediction model.

[0067] FIG. 11 shows the prediction results of the trained data prediction model using test data. Here, the predicted values ​​output from the data prediction model that predicts the crucible weight and the weight (actual measured value) of the training data were plotted, and the results were observed. Observation of the plotted data in FIG. 11 showed that there was little variation in the predicted values ​​compared to the training data, with a maximum error of about 5%. [Explanation of symbols]

[0068] 1. Data prediction device 2 Manufacturing workers 3 Crucible manufacturing equipment 11 Control section 12 Storage section 13 Input section 14 Output section 15 Display section 16 Communications Department 31 Inner member 32 Ventilation section 33 Holding body 34 Crucible molding mold 35 Rotation axis 36 Exhaust port 37 Pressure reducing mechanism 38 Arc Electrode 40 Crucible molding 40a,41a transparent layer 40b,41b Opaque layer 41 Quartz glass crucible

Claims

1. A storage means for storing a data set created by using the measured values ​​of the dimensions of a predetermined position of a quartz glass crucible actually manufactured under the melting conditions set in the crucible manufacturing device as input data and the measured values ​​of the weight of the quartz glass crucible actually manufactured under the melting conditions as training data and linking the training data to the input data; A model generation means for generating a data prediction model for predicting the weight of a quartz glass crucible by machine learning using the data set read from the storage means; A data prediction means for receiving as input data the actual measurement values ​​of the dimensions at a predetermined position output from the crucible manufacturing apparatus in a measurement step within the manufacturing process of the quartz glass crucible, and outputting a predicted weight of the quartz glass crucible manufactured in the manufacturing process using a trained data prediction model; Equipped with A data prediction device comprising:

2. moreover, a display means for displaying the predicted weight output by the data prediction means; Equipped with 2. The data prediction device according to claim 1.

3. The actual measured values ​​of the dimensions at the predetermined positions are all or part of the outer diameter of the straight body part of the quartz glass crucible, the thickness of the bottom part, the thickness of the corner parts, the thickness of the straight body part, the thickness of the transparent layer at the bottom part, the thickness of the transparent layer at the corner parts, and the thickness of the transparent layer at the straight body part.

3. The data prediction device according to claim 1 or 2.

4. A data prediction device according to claim 1, 2 or 3; A crucible manufacturing apparatus for manufacturing a quartz glass crucible through a manufacturing process including a molding process, a melting process, and a measuring process; Equipped with The crucible manufacturing apparatus carries out a melting process under melting conditions adjusted based on the trend of the predicted weight of the quartz glass crucible output from the data prediction device operating as a machine-learned data prediction model. A quartz glass crucible manufacturing system characterized by:

5. The melting conditions are melting process data including a current value, a voltage value, an integrated power value, an electrode opening degree, an electrode position, a melting temperature, a pressure, a cooling water temperature, a cooling water flow rate, and a melting time during melting.

5. The quartz glass crucible manufacturing system according to claim 4.

Images