Information processing apparatus and performance evaluation method

Abstract

The present invention provides a technique for improving the ease of performance evaluation of a recipe of a substrate processing apparatus. The information processing apparatus according to the present invention performs performance evaluation on a recipe of a substrate processing apparatus that performs film formation processing according to the recipe, and comprises: a prediction unit that predicts a film formation result of the substrate processing apparatus that performs film formation processing according to the recipe; a recipe performance evaluation unit that evaluates the performance of the recipe for each evaluation item on the basis of the predicted film formation results of the substrate processing apparatus; and a display control unit that displays the performance evaluation of the recipe for each of the evaluation items.

Description

Technical Field

[0001] This invention relates to information processing apparatus and performance evaluation methods. Background Technology

[0002] For example, a digital twin technique is known for reproducing the temperature behavior of a substrate processing device in cyberspace. Through digital twins, it is possible to reproduce changes in the physical space, such as the state of the substrate processing device during the process, in the virtual space.

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2022-168572 Summary of the Invention

[0006] The technical problem that the invention aims to solve

[0007] This invention provides a technique to improve the ease of performance evaluation of substrate processing apparatus recipes.

[0008] Technical means to solve the problem

[0009] One aspect of the present invention provides an information processing apparatus for evaluating the performance of a formulation of a substrate processing apparatus for film formation according to a formulation, comprising: a prediction unit that predicts the film formation result of the substrate processing apparatus for film formation according to the formulation; a formulation performance evaluation unit that evaluates the performance of the formulation for each evaluation item based on the predicted film formation result of the substrate processing apparatus; and a display control unit that displays the performance evaluation of the formulation for each evaluation item.

[0010] Invention Effects

[0011] According to the present invention, a technique is provided that improves the ease of performance evaluation of substrate processing apparatus formulations. Attached Figure Description

[0012] Figure 1 This is a structural diagram of an example of the substrate processing system of this embodiment.

[0013] Figure 2 This is a hardware structure diagram of an example of a computer.

[0014] Figure 3 This is a functional block diagram illustrating an example of the server device in this embodiment.

[0015] Figure 4This is a functional block diagram illustrating an example of the prediction unit in this embodiment.

[0016] Figure 5 This is a functional block diagram illustrating an example of the prediction unit in this embodiment.

[0017] Figure 6 This is an explanatory diagram illustrating an example of the learning process of the machine learning model in this embodiment.

[0018] Figure 7 This is a flowchart illustrating an example of the server device in this embodiment performing a recipe performance evaluation process based on a substrate processing device in a virtual operation.

[0019] Figure 8 This is an illustrative diagram illustrating an example of the evaluation items for formula performance evaluation.

[0020] Figure 9 This is a screenshot illustrating an example of how the performance evaluation of a formula is displayed for each evaluation item.

[0021] Figure 10 This is an illustrative diagram of an example of film-forming stability score.

[0022] Figure 11 This is an illustrative diagram of an example of film-forming stability score.

[0023] Figure 12 This is a longitudinal cross-sectional view of a batch processing apparatus, which is a schematic representation of a substrate processing apparatus in this embodiment.

[0024] Figure 13 It is a cross-sectional view showing the general structure of the heat treatment furnace. Detailed Implementation

[0025] Hereinafter, this embodiment will be described with reference to the accompanying drawings.

[0026] <System Structure>

[0027] Figure 1 This is a structural diagram of an example of the substrate processing system 1 of this embodiment. Figure 1 The substrate processing system 1 shown includes a substrate processing device 10, a device controller 12, a measuring device 14, a server device 16, and an operator terminal 18.

[0028] The substrate processing unit 10, the unit controller 12, and the measuring device 14 are located in the manufacturing plant 2. The server unit 16 and the operator terminal 18 may be located in the manufacturing plant 2 or elsewhere. The operator terminal 18 is an information processing terminal such as a PC (Personal Computer) or a smartphone operated by operators such as the unit manager or analysis manager of the substrate processing unit 10.

[0029] The substrate processing device 10, device controller 12, measuring device 14, server device 16 and operator terminal 18 are communicatively connected via networks N1 and N2 such as the Internet or LAN (Local Area Network).

[0030] The substrate processing apparatus 10 is an apparatus that performs processes such as film formation, etching, or ashing, for example, processing a substrate such as a wafer W. The substrate processing apparatus 10 is, for example, a semiconductor manufacturing apparatus, a heat treatment apparatus, or a film formation apparatus.

[0031] The substrate processing apparatus 10 receives control commands (set values) according to the formula from the apparatus controller 12, and executes the process. The substrate processing apparatus 10 is equipped with multiple sensors, such as a temperature sensor for measuring temperature and a pressure sensor for measuring pressure.

[0032] The device controller 12 receives instructions from the operator to the substrate processing apparatus 10. The device controller 12 has a human-machine interface function that provides information about the substrate processing apparatus 10 to the operator. The device controller 12 receives sensor data output from multiple sensors installed on the substrate processing apparatus 10. The device controller 12 can also perform setpoint optimization, anomaly detection, or anomaly prediction for the substrate processing apparatus 10.

[0033] In addition, the device controller 12 can store historical information (process log) of processes such as film formation performed by the substrate processing device 10. The device controller 12 can output the process log to the server device 16 or the operator terminal 18.

[0034] Figure 1 The device controller 12 shown is provided for each substrate processing device 10, but it can also be provided for multiple substrate processing devices 10. The device controller 12 can be located inside or outside the housing of the substrate processing device 10.

[0035] Measuring device 14 is a measuring device used to measure process results, such as a film thickness measuring device, a thin film resistance measuring device, and a particle measuring device. Measuring device 14 measures, for example, the adhesion condition (film thickness, etc.) of a film on a substrate such as a wafer W. Hereinafter, the film thickness included in the process results measured by measuring device 14 will be referred to as the actual film thickness.

[0036] Server device 16 can receive and store information about multiple substrate processing devices 10 of one or more manufacturing plants 2. For example, server device 16 can store process logs and process results of multiple substrate processing devices 10 of one or more manufacturing plants 2.

[0037] Server device 16 may have a human-machine interface function that provides information about substrate processing device 10 to operators using web applications or the like. For example, the information about substrate processing device 10 displayed by server device 16 using web applications or the like may include, as described later, a recipe performance evaluation based on the virtual operation of substrate processing device 10.

[0038] The operator terminal 18 can receive and save information about multiple substrate processing devices 10 of one or more manufacturing plants 2. For example, the operator terminal 18 can save process logs and process results of multiple substrate processing devices 10 of one or more manufacturing plants 2.

[0039] The operator terminal 18 may have a human-machine interface function, providing operators with information about the substrate processing apparatus 10 via web applications or the like. For example, the information about the substrate processing apparatus 10 displayed on the operator terminal 18 via web applications or the like includes, as described later, a recipe performance evaluation based on the virtual operation of the substrate processing apparatus 10.

[0040] Figure 1 The device controller 12, server device 16, and operator terminal 18 shown are examples of the information processing apparatus of this embodiment. Furthermore, Figure 1 The substrate processing system 1 shown is an example; various system architecture examples certainly exist depending on the purpose and intended use. Figure 1 The distinction between devices such as device controller 12, server device 16, and operator terminal 18 is one example. For example, various structures can be adopted, such as a structure in which at least two of the device controller 12, server device 16, and operator terminal 18 are integrated into one unit, or a structure that is further divided.

[0041] <Hardware Structure>

[0042] Figure 1 The device controller 12, server device 16, and operator terminal 18 shown can, for example, be accessed via... Figure 2 The hardware structure shown is implemented using a computer. Figure 2 This is a hardware structure diagram of a computer 500.

[0043] Figure 2The computer 500 includes an input device 501, an output device 502, an external I / F (interface) 503, RAM (Random Access Memory) 504, ROM (Read Only Memory) 505, a CPU (Central Processing Unit) 506, a communication I / F 507, and an HDD (Hard Disk Drive) 508, all of which are connected to each other via bus B. The input device 501 and the output device 502 can be connected and used as needed.

[0044] Input device 501 includes a keyboard, mouse, touch panel, etc., for operators to input operation signals. Output device 502 includes a monitor, etc., to display the processing results of computer 500. Communication I / O 507 connects computer 500 to... Figure 1 The interface between networks N1 and N2 is shown. The HDD508 is an example of a non-volatile storage device for storing programs and data.

[0045] External I / F 503 is an interface for connecting to external devices. Computer 500 can read from recording media 503a such as SD (Secure Digital) memory cards via external I / F 503. External I / F 503 can also be used to write to recording media 503a such as SD memory cards.

[0046] ROM 505 is an example of a non-volatile semiconductor memory (storage device) that stores programs and data. RAM 504 is an example of a volatile semiconductor memory (storage device) that temporarily stores programs and data. CPU 506 is an arithmetic unit that reads programs and data from storage devices such as ROM 505 or HDD 508 into RAM 504 and performs processing to realize the overall control and functions of computer 500.

[0047] Figure 1 The substrate processing system 1 shown includes a device controller 12, a server device 16, and an operator terminal 18, which are connected via a... Figure 2 The computer 500 shown executes programs to perform various functions.

[0048] <Functional Structure>

[0049] The following describes an example of an information processing device, consisting of a server device 16, that evaluates the performance of a substrate processing apparatus 10 that performs film formation according to a formula. Alternatively, the information processing device that evaluates the performance of a substrate processing apparatus 10 that performs film formation according to a formula may also be an apparatus controller 12 or an operator terminal 18.

[0050] The server device 16 of the substrate processing system 1 in this embodiment, for example, is via... Figure 3 The functional modules shown are implemented. Figure 3 This is a functional block diagram illustrating an example of the server device 16 in this embodiment. Additionally, Figure 3 The functional module diagram omits structures that are not required in the description of this embodiment.

[0051] Figure 3 The server device 16 executes a program for the server device 16 to realize the acquisition unit 130, data storage unit 132, temperature control unit 134, prediction unit 136, formula performance evaluation unit 138, input receiving unit 140 and display control unit 142.

[0052] The acquisition unit 130 acquires the recipe of the substrate processing apparatus 10. A recipe refers to information that sets the control commands (set values) required for the substrate processing apparatus 10 to perform film formation processing. For example, the recipe may include parameters such as temperature, time, and gas flow rate. The acquisition unit 130 may receive the recipe input into the substrate processing apparatus 10 from an operator, from a device storing recipes for the substrate processing apparatus 10, or from a device that allows operators to generate recipes for the substrate processing apparatus 10.

[0053] The formula for the substrate processing apparatus 10 acquired by the acquisition unit 130 may include, for example, the initial temperature of each component constituting the substrate processing apparatus 10. Furthermore, the components constituting the substrate processing apparatus 10 may include, as described later, an insulation cylinder and a crystal boat. The acquisition unit 130 stores the acquired formula for the substrate processing apparatus 10 in the data storage unit 132.

[0054] The input receiving unit 140 receives various operations from the operators. For example, the operations received from the operators include launching an application (app) and various operations for an already launched application. The input receiving unit 140 notifies the temperature control unit 134, the prediction unit 136, the formula performance evaluation unit 138, and the display control unit 142 of the content of the various operations performed by the operators.

[0055] The temperature control unit 134 uses the same control algorithm as the temperature control unit of the substrate processing apparatus 10. The temperature control unit 134 obtains a set temperature based on the recipe stored in the data storage unit 132. Based on the obtained set temperature and the temperature of the temperature sensor predicted by the thermal model 150 of the prediction unit 136 as described later, the temperature control unit 134 performs feedback control on the virtual heater power to bring the temperature of the wafer W in the processing container close to the set temperature.

[0056] In this way, the server device 16 uses a temperature control unit 134 that has the same control algorithm as the substrate processing device 10, which is the actual device. Therefore, by having the temperature control unit 134 cooperate with the prediction unit 136, the temperature behavior of the substrate processing device 10 can be reproduced in virtual space. The server device 16 of this embodiment can reproduce the temperature behavior of the substrate processing device 10 that performs film formation processing according to the formula in virtual space by applying digital twin technology.

[0057] The prediction unit 136 predicts the film formation result of the substrate processing apparatus 10 performing film formation processing according to the formula stored in the data storage unit 132. The prediction unit 136 predicts the temperature of each component constituting the substrate processing apparatus 10 using the thermal model 150 described later. Additionally, the prediction unit 136 predicts the film formation result of the substrate processing apparatus 10 performing film formation processing according to the formula using the chemical reaction model 152 or the machine learning model 154 described later. The prediction unit 136 stores the film formation result of the virtual operation of the substrate processing apparatus 10 performing film formation processing according to the formula as the prediction result in the data storage unit 132.

[0058] The formulation performance evaluation unit 138 evaluates the formulation performance according to each evaluation item described later, based on the prediction results of the prediction unit 136, i.e., the film formation results (predicted film thickness, etc.) of the virtual operation of the substrate processing apparatus 10. Details of the processing by the formulation performance evaluation unit 138 will be described later. The display control unit 142 displays the formulation performance evaluations made by the formulation performance evaluation unit 138 on the output device 502, according to each evaluation item. Details of the processing by the display control unit 142 will be described later.

[0059] Figure 3 For example, the prediction section 136 is composed of Figure 4 The functional modules shown are implemented. Figure 4 This is a functional block diagram illustrating an example of the prediction unit 136 in this embodiment. Additionally, Figure 4 The functional module diagram omits structures that are not required in the description of this embodiment.

[0060] Figure 4 The prediction unit 136 includes a thermal model 150 and a chemical reaction model 152. The thermal model 150 is a physical model that predicts the temperature of the substrate processing apparatus 10 undergoing film formation according to a formula. The physical model establishes the thermal relationships (thermal coupling relationships) between components through physical equations, simulating the temperature of each component. The thermal model 150 can use thermal simulation models such as 1DCAE.

[0061] The thermal model 150 predicts the temperature of each component constituting the substrate processing apparatus 10 based on the virtual heater power output by the temperature control unit 134 and the initial temperature of each component constituting the substrate processing apparatus 10, according to the thermal relationships between components such as the heat output of the heater and the heat capacity of each component. The thermal model 150 outputs the predicted temperature of each component constituting the substrate processing apparatus 10 to the chemical reaction model 152.

[0062] The chemical reaction model 152 is a physical model of the chemical reaction (film formation reaction) that predicts the film formation result of the substrate processing apparatus 10 performing film formation according to the formula. The physical model of the chemical reaction calculates the film formation rate (X nm / sec, etc.) based on various parameters required for the chemical reaction, such as the temperature of each component constituting the substrate processing apparatus 10, the pressure set in the formula, and the gas flow rate. The prediction unit 136 can output a predicted film thickness as a prediction result by integrating the film formation rate for each cycle (1 sec, etc.). Furthermore, the prediction unit 136 can also output predicted film thicknesses at multiple locations on the wafer W (e.g., two locations at the center and two at the ends, etc.).

[0063] Thus, according to Figure 4 The prediction unit 136 combines the thermal model 150 with the chemical reaction model 152 to output the film formation result of the substrate processing device 10 that processes the substrate according to the formula, i.e., the predicted film thickness.

[0064] Figure 3 The prediction department 136 can also be used through Figure 5 The functional modules shown are used to implement this. Figure 5 This is a functional block diagram illustrating an example of the prediction unit 136 in this embodiment. Additionally, Figure 5 The functional module diagram omits structures that are not required in the description of this embodiment.

[0065] Figure 5 The prediction unit 136 has a thermal model 150 and a machine learning model 154. Figure 5 Thermal model 150 and Figure 4 The thermal model 150 is the same as the thermal model 150, so the description is omitted. The thermal model 150 outputs the predicted temperature of each component constituting the substrate processing device 10 to the machine learning model 154.

[0066] Machine learning model 154 is a chemical reaction virtual machine (VM) that predicts the film formation result of the substrate processing apparatus 10 performing film formation according to the formula. The chemical reaction virtual machine can output a predicted film thickness as a prediction result based on various parameters required for prediction, such as the temperature of each component constituting the substrate processing apparatus 10, the pressure set in the formula, and the gas flow rate. The predicted film thickness output by machine learning model 154 can be the predicted film thickness at multiple locations on the wafer W.

[0067] Machine learning model 154, for example Figure 6 As shown, the relationship between the temperature and formulation of each component of the substrate processing apparatus 10 and the film formation result of the substrate processing apparatus 10 has been learned (i.e., trained). Figure 6 This is an explanatory diagram illustrating an example of the learning process of the machine learning model 154 in this embodiment. Figure 6 The learning department 200 uses existing machine learning methods to enable the machine learning model 154 to learn (train).

[0068] Machine learning model 154 uses process logs and process results from the substrate processing device 10 (hereinafter referred to as the reference device) as a reference to perform film formation according to the formula, and learns the relationship between the temperature and formula of the reference device and the film formation results of the reference device through existing machine learning methods.

[0069] The process log used by machine learning includes the temperature (measurement temperature) measured by the temperature sensor of the reference device performing film formation according to the formula, as well as the pressure and gas flow rate set in the formula. The process results used by machine learning include the film formation results of the actual operation of the reference device. The film formation results of the actual operation of the reference device include the actual film thickness measured by the measuring device 14.

[0070] The machine learning model 154 uses the adjustment unit 202 to adjust the parameters so that when the measurement temperature of the reference device for film formation according to the formula and the pressure and gas flow rate set in the formula are input, it can output the film formation result (actual film thickness) of the reference device.

[0071] The adjustment unit 202 adjusts the parameters of the machine learning model 154 to reduce the difference between the film formation result (predicted film thickness) of the reference device output by the machine learning model 154 and the actual film formation result (actual film thickness) of the reference device included in the process results.

[0072] Furthermore, the machine learning model 154, which has already undergone machine learning using the process logs and process results from the film formation process performed by the reference device according to the formula, can be directly used in other substrate processing devices 10 of the same model as the reference device. The machine learning model 154, after completing the machine learning process, can also be used... Figure 6 The learning mechanism shown uses process logs and process results from film formation processes performed by other substrate processing devices 10 of the same model according to the formula to correct the parameters of the machine learning model 154.

[0073] By using process logs and process results from film formation processes performed by other substrate processing units 10 of the same model according to a formula, the parameters of the machine learning model 154 after machine learning is completed are corrected, enabling the learning unit 200 to realize a machine learning model 154 that can cope with equipment differences. The process logs and process results used to correct the parameters of the machine learning model 154 after machine learning are completed can be logs and results of film formation processes with fewer runs.

[0074] Thus, according to Figure 5 The prediction unit 136 combines the thermal model 150 with the machine learning model 154 to output the film formation result of the substrate processing apparatus 10 processed according to the formula, i.e., the predicted film thickness.

[0075] <Processing>

[0076] Server device 16, for example, according to Figure 7 The processing sequence shown is used to evaluate the formulation performance through virtual operation based on the substrate processing device 10. Figure 7 This is a flowchart illustrating an example of the server device 16 performing a recipe performance evaluation process based on the virtual operation of the substrate processing device 10 in this embodiment.

[0077] In step S10, the server device 16 receives from the operator the recipe selected for performance evaluation through virtual operation of the substrate processing device 10.

[0078] In step S12, the prediction unit 136 of the server device 16 predicts the temperature of each component constituting the substrate processing device 10 by using the thermal model 150.

[0079] In step S14, the prediction unit 136 of the server device 16 predicts the film formation result of the substrate processing device 10 that performs film formation according to the formula by using a chemical reaction model 152 or a machine learning model 154.

[0080] In the processing of steps S10 to S14, the substrate processing device 10, which performs film formation processing according to the formula, can output prediction results such as predicted film thickness through virtual operation.

[0081] In step S16, the formulation performance evaluation unit 138, based on the prediction results of the prediction unit 136, i.e., the prediction results of the virtual operation of the substrate processing apparatus 10, performs the following steps: Figure 8 Each evaluation item shown is used to evaluate the performance of the formulation.

[0082] Figure 8 This is an illustrative diagram representing an example of the evaluation items for formula performance evaluation. In Figure 8In the example of the evaluation items for formula performance evaluation, the scores are film thickness, film stability, production efficiency, particle generation, energy consumption, process gas consumption, and temperature control.

[0083] Figure 8 The evaluation items shown are one example of formulation performance evaluation. For example, the evaluation items for formulation performance evaluation may include at least one of film thickness score, film formation stability score, and production efficiency score. Alternatively, for example, the evaluation items for formulation performance evaluation may also include at least one of particle generation score, energy consumption score, process gas consumption score, and temperature control score, in addition to at least one of film thickness score, film formation stability score, and production efficiency score.

[0084] The film thickness score is an example of a formulation evaluation method that evaluates the difference between the predicted film thickness and the target film thickness using the target film thickness as a standard. For example, if the predicted film thickness predicted by the prediction unit 136 is "85nm" and the target film thickness of the formulation is "80nm", the formulation performance evaluation unit 138 calculates the difference between the predicted film thickness and the target film thickness using the following formula (1).

[0085] Predicted film thickness "85nm" - target film thickness "80nm" = difference "5nm"... (1)

[0086] The formulation performance evaluation unit 138 standardizes the difference in target film thickness using the following formula (2).

[0087] Difference of “5nm” / target film thickness of “80nm” = 1 / 16 ……(2)

[0088] The formulation performance evaluation unit 138 converts the standardized values ​​into scores (and scores them) using the following formula (3).

[0089] 100×(1-1 / 16)=film thickness score "93.75pt" ……(3)

[0090] In this way, the formulation performance evaluation unit 138 uses the calculated film thickness score to quantify the evaluation of the film thickness of the formulation of the substrate processing apparatus 10, and can visualize the performance of the formulation.

[0091] Film formation stability score is an example of a formulation evaluation method that assesses the dispersion (degree of fluctuation, such as standard deviation) of the predicted film thickness when conditions are changed. For example, the formulation performance evaluation unit 138 evaluates the dispersion of the predicted film thickness when the initial temperature of each component constituting the substrate processing apparatus 10 is changed. The formulation performance evaluation unit 138 may also evaluate the dispersion of the predicted film thickness when the gas flow rate is changed. Here, an example of evaluating the dispersion of the predicted film thickness when the initial temperature of each component constituting the substrate processing apparatus 10 is described.

[0092] For example, the operator sets upper and lower limits for the fluctuation of the initial temperature of each component constituting the substrate processing apparatus 10. Within the range of these upper and lower limits, the formulation performance evaluation unit 138 calculates the dispersion of the predicted film thickness when the initial temperature of each component constituting the substrate processing apparatus 10 is changed. Here, an example of a predicted film thickness dispersion of "0.5 nm" will be explained.

[0093] The formulation performance evaluation unit 138 uses the target film thickness to standardize the discreteness of the predicted film thickness using the following formula (4), and converts the standardized value into a score.

[0094] 100×(1-0.5 / 80)=film stability score "99.4pt" ……(4)

[0095] In this way, the formulation performance evaluation unit 138 uses the calculated film-forming stability score to quantify the evaluation of the film-forming stability (robustness) of the formulation for the substrate processing apparatus 10, and can visualize the performance of the formulation. Furthermore, in the evaluation of the film-forming stability (robustness) of the formulation for the substrate processing apparatus 10, if the predicted film thickness dispersion is within ±0.5% of the target film thickness, it is set as "score A", and if the predicted film thickness dispersion is within ±3% of the target film thickness, it is set as "score B".

[0096] Production efficiency scores are an example of formulation evaluation methods used to assess production efficiency. For instance, the formulation performance evaluation unit 138 evaluates the production efficiency of the substrate processing apparatus 10, which performs film formation according to a formulation, from a formulation perspective. In evaluating production efficiency from a formulation perspective, the shorter the time required for film formation, the higher the evaluation.

[0097] For example, the formulation performance evaluation unit 138 converts the number of wafers W that can be formed per unit time, the time required for 1 run (1 cycle), or the time required for 1 wafer W into a score. The evaluation of production efficiency from the perspective of formulation can be performed on a per-substrate processing unit 10 or on a per-fab manufacturing plant 2.

[0098] Particle generation score is one example of a formulation evaluation method for assessing the degree of particle generation. For example, prediction unit 136 predicts the degree of particle generation. Formulation performance evaluation unit 138 quantifies the probability or number of particles generated. For example, prediction unit 136 can use a particle generation model to predict the degree of particle generation, wherein the particle generation model is generated using process logs and process results based on the correlation between the formulation, cumulative film thickness, and particle measurement results measured by measuring instrument 14.

[0099] For example, the formulation performance evaluation unit 138 scores the probability or number of particles generated predicted by the prediction unit 136 in a manner that the higher the probability or number of particles generated, the worse the score. The formulation performance evaluation unit 138 can score the number of particles generated in 1 Run.

[0100] Energy consumption score is an example of a formulation evaluation method for evaluating energy consumption. For example, prediction unit 136 predicts the energy consumption of substrate processing apparatus 10. For example, prediction unit 136 can use an energy consumption model to predict the energy consumption of substrate processing apparatus 10 that performs film formation according to a formulation, wherein the energy consumption model is generated using process logs and process results based on the correlation between the formulation, cumulative film thickness, and energy consumption of substrate processing apparatus 10.

[0101] For example, the formulation performance evaluation unit 138 can score the predicted energy consumption. For example, the formulation performance evaluation unit 138 can score the energy consumption of the substrate processing apparatus 10 for 1 run (1 batch cycle).

[0102] The process gas consumption score is an example of a formulation evaluation method that assesses the total consumption of process gases. For example, the prediction unit 136 predicts the total consumption of process gases in the substrate processing apparatus 10. For example, the prediction unit 136 uses a process gas consumption model to predict the total consumption of process gases in the substrate processing apparatus 10 that performs film formation according to the formulation. This process gas consumption model is generated using process logs and process results, based on the correlation between the formulation, cumulative film thickness, and the consumption of process gases in the substrate processing apparatus 10.

[0103] For example, the formulation performance evaluation unit 138 can score the predicted total consumption of process gases. The formulation performance evaluation unit 138 can, for example, score the total consumption of process gases in 1 Run of the substrate processing apparatus 10.

[0104] Temperature control score is an example of a formulation evaluation method that evaluates temperature control. For example, prediction unit 136 predicts whether the temperature control of substrate processing apparatus 10 is within the range. For example, prediction unit 136 predicts whether the temperature control performed by temperature control unit 134 of substrate processing apparatus 10, which performs film formation processing according to the formulation, is within the range.

[0105] For example, the formulation performance evaluation unit 138 can output a prediction of whether the temperature control of the temperature control unit 134 of the substrate processing apparatus 10, which performs film formation according to the formulation, is within the range using Safe / Out, etc., and can also perform scoring.

[0106] Back Figure 7 In step S18, the display control unit 142, for example, Figure 9As shown, the performance evaluation of the formulation made by the formulation performance evaluation unit 138 is displayed on the output device 502 according to each evaluation item.

[0107] Figure 9 This is a screenshot illustrating an example of how the performance evaluation of a formula is displayed for each evaluation item. Figure 9 The image 1000 represents Figure 8 Examples of evaluation items for formula performance evaluation are shown. Figure 9 The screen displays (visualizes) the performance evaluation of the formula by each evaluation item, making it easy for operators to understand the performance of the formula.

[0108] For example, Figure 8 The priority of the various evaluation items shown varies depending on the operator. Operators aiming to reduce environmental impact should prioritize... Figure 8 The scores for energy consumption and process gas consumption are also important. Additionally, operators looking to improve production efficiency should pay attention to... Figure 8 The production efficiency score. (Displayed by...) Figure 9 With a screen size of 1000, operators can focus on the evaluation items they want to prioritize when evaluating the formulation's performance.

[0109] Figure 10 This is an illustrative diagram of an example of film-forming stability score. Figure 10 The horizontal axis of the graph represents time. Additionally, Figure 10 The graphs represent the time-varying temperature of wafer W and the time-varying predicted film thickness of wafer W. Figure 10 The curves represent the changes in the initial temperature of each component constituting the substrate processing apparatus 10. Therefore, there is a discrepancy between the time-varying temperature of wafer W and the time-varying predicted film thickness of wafer W.

[0110] like Figure 10 As shown, the server device 16 of this embodiment can generate a formulation for obtaining the desired target film thickness by calculating the average and dispersion of the predicted film thickness when the initial temperature of each component constituting the substrate processing apparatus 10 is changed. In addition, the server device 16 of this embodiment can quantify the evaluation of the film-forming stability (robustness) of the formulation of the substrate processing apparatus 10, thereby making the performance of the formulation visible.

[0111] Furthermore, the server device 16 in this embodiment can also... Figure 10 The graph is displayed on output device 502 for operator confirmation. Operators can refer to... Figure 10 The graphs show the influence of the initial temperature and other initial state of the formulation of each component of the substrate processing apparatus 10 on the film formation process. Furthermore, operators can refer to... Figure 10The graph shows the time required for heat dissipation to reach a level that won't affect the next run. Operators can understand the required standby time between runs, thus reducing the interval between runs.

[0112] In addition, Figure 10 In the curve graph, the smaller the difference between the target film thickness and the predicted film thickness, and the smaller the dispersion of the predicted film thickness, the easier it is to obtain the required film thickness, which means that the formulation has high film formation stability.

[0113] In addition, such as Figure 11 As shown, the server device 16 of this embodiment can be represented by a graph to show the predicted film thickness of each formulation of the substrate processing device 10. Figure 11 This is an illustrative diagram of an example of film-forming stability score. Figure 11 The horizontal axis of the graph represents a zone. A zone is a unit area that can be heated using a heater.

[0114] like Figure 11 As shown, the server device 16 of this embodiment calculates the degree of fluctuation (discretion) of the film formation result of the formulation that changes the initial temperature of each component constituting the substrate processing device 10, and quantifies the evaluation of the film formation stability (robustness) of the formulation of the substrate processing device 10, thereby enabling visualization of the formulation's performance.

[0115] According to the server device 16 of this embodiment, since the performance evaluation of the formula is displayed (visualized) for each evaluation item, operators can easily grasp the performance of the formula, and comparisons between formulas and the potential for improvement of the formula become easier. According to the server device 16 of this embodiment, the performance evaluation of the formula of the substrate processing device 10 does not overly rely on personal experience, and even operators without highly specialized knowledge can easily perform the performance evaluation of the formula of the substrate processing device 10.

[0116] Furthermore, the server device 16 according to this embodiment can perform the following work cycle: evaluating the performance of the generated recipe, visualizing the performance of the recipe, correcting the recipe based on the performance evaluation, and evaluating the performance of the corrected recipe. Thus, according to this embodiment, a technique can be provided that improves the ease of recipe performance evaluation for the substrate processing apparatus 10.

[0117] Figure 12This is a schematic longitudinal cross-sectional view of a batch processing apparatus, representing an example of the substrate processing apparatus 10 in this embodiment. The substrate processing apparatus 10 includes a vertical heat treatment furnace 60. The substrate processing apparatus 10 holds and houses wafers W along the longitudinal direction at predetermined intervals in a wafer boat, and performs various heat treatments on the wafers W, such as oxidation, diffusion, and reduced pressure CVD. The substrate processing apparatus 10 performs film formation treatment on the surface of the wafers W disposed within the processing container 65 by supplying process gases into the processing container 65.

[0118] Figure 12 The substrate processing apparatus 10 has a loading platform (loading port) 20, a housing 30, and an apparatus controller 100. The housing 30 has a loading area (working area) 40 and a heat treatment furnace 60.

[0119] The loading area 40 is located at the lower part of the housing 30. The heat treatment furnace 60 is located above the loading area 40 within the housing 30. In addition, a base plate 31 is provided between the loading area 40 and the heat treatment furnace 60.

[0120] The loading stage (loading port) 20 is used for feeding and unloading wafers W into and out of the housing 30. Storage containers 21 and 22 are mounted on the loading stage (loading port) 20. Storage containers 21 and 22 are closed-type storage containers (FOUPs) capable of holding multiple wafers W (e.g., approximately 25 wafers) at predetermined intervals, and have removable covers (not shown) on their front surfaces.

[0121] Additionally, an alignment device (aligner) 23 may be provided below the stage 20 to align the notches (e.g., grooves) on the outer periphery of the wafer W transferred by the transfer mechanism 47 in one direction.

[0122] The loading area (working area) 40 is used for transferring wafers W between the receiving containers 21 and 22 and the wafer boat 44, feeding (loading) the wafer boat 44 into the processing container 65, and unloading the wafer boat 44 from the processing container 65. The loading area 40 is equipped with a door mechanism 41, a baffle mechanism 42, a cover 43, the wafer boat 44, a base 45a, and a base 45b. Figure 13 The lifting mechanism 46 and the transfer mechanism 47.

[0123] Door mechanism 41 is a component used to remove the lids of storage containers 21 and 22, opening the interior of storage containers 21 and 22 to communicate with the loading area 40. Baffle mechanism 42 is disposed above the loading area 40. Baffle mechanism 42 is configured to cover (or block) the furnace opening 68a to suppress or prevent heat from the furnace opening 68a from escaping into the loading area 40 when the lid 43 is opened.

[0124] The cover 43 has a heat-insulating cylinder 48 and a rotating mechanism 49. The heat-insulating cylinder 48 is disposed on the cover 43. The heat-insulating cylinder 48 is used to prevent the crystal boat 44 from cooling due to heat transfer with the cover 43 side, and to keep the crystal boat 44 warm. The rotating mechanism 49 is installed at the lower part of the cover 43. The rotating mechanism 49 is used to rotate the crystal boat 44. The rotation shaft of the rotating mechanism 49 is configured to pass through the cover 43 in an airtight manner, so as to rotate the rotating table disposed on the cover 43.

[0125] The lifting mechanism 46 drives the lifting of the cover 43 when the crystal boat 44 is fed into and out of the processing container 65 from the loading area 40. When the cover 43, after being raised by the lifting mechanism 46, is sent into the processing container 65, the cover 43 is configured to abut against the furnace opening 68a and seal the furnace opening 68a.

[0126] The wafer boat 44, placed within the cover 43, can hold the wafer W within the processing container 65 so that it can rotate in a horizontal plane. Furthermore, the substrate processing apparatus 10 may also have multiple wafer boats 44. Wafer boats 44a and 44b are provided in the loading area 40.

[0127] A base 45a, a base 45b, and a crystal boat transport mechanism are provided in the loading area 40. Bases 45a and 45b are platforms for transferring crystal boats 44a and 44b from the cover 43, respectively. The crystal boat transport mechanism is used to transfer crystal boats 44a or 44b from the cover 43 to bases 45a or 45b.

[0128] Ships 44a and 44b, for example, are made of quartz and mount large-diameter wafers W, for example, 300 mm in diameter, horizontally at predetermined intervals (pitch width) in the vertical direction. Ships 44a and 44b have multiple (e.g., three) support pillars between the top and bottom plates. Each support pillar has claws for holding the wafer W. Additionally, auxiliary pillars may be appropriately provided along with the support pillars in ship 44a and 44b.

[0129] The transfer mechanism 47 is used to transfer wafer W between the receiving container 21 or 22 and the wafer boat 44a or 44b. The transfer mechanism 47 has a base 57, a lifting arm 58, and multiple forks (transfer plates) 59. The base 57 is configured to be able to lift and rotate. The lifting arm 58 is configured to be able to move in the vertical direction (lift and lower) via a ball screw or the like. The base 57 is mounted on the lifting arm 58 in a manner that allows it to rotate horizontally.

[0130] Figure 13 It is a cross-sectional view showing the general structure of the heat treatment furnace. Figure 13 The heat treatment furnace 60 is an example of a vertical furnace used to house multiple thin, circular wafers W and perform prescribed heat treatments. The heat treatment furnace 60 has a enclosure 62, a heater 63, a space 64, and a processing container 65.

[0131] Processing container 65 is used to house and heat-treat the wafer W held by the crystal boat 44. Processing container 65 is, for example, made of quartz and has an elongated shape. Processing container 65 is supported on base plate 66 via a lower manifold 68. Gas is supplied to processing container 65 from manifold 68 through ejector 71. Ejector 71 supplies gas into processing container 65 from a blow-out portion (hole). Ejector 71 is connected to gas supply source 72. Additionally, the gas supplied to processing container 65 is exhausted through exhaust port 73 from exhaust system 74 equipped with a vacuum pump capable of pressure reduction control.

[0132] The cover 43 seals the furnace opening 68a at the lower part of the manifold 68 when the wafer boat 44 is fed into the processing container 65. The cover 43 is configured to be able to move up and down via the lifting mechanism 46. An insulation cylinder 48 is placed on the upper part of the cover 43. A wafer boat 44, which holds multiple wafers W at predetermined intervals in the vertical direction, is provided on the upper part of the insulation cylinder 48.

[0133] The enclosure 62 is arranged to surround the processing container 65, and a space 64 is defined around the processing container 65. The enclosure 62, like the processing container 65, has a cylindrical shape. The enclosure 62 is supported by a base plate 66. An insulating material 62a, such as glass wool, may be provided on the inner side of the enclosure 62 and on the outer side of the space 64.

[0134] The heater 63 is arranged to surround the processing container 65. For example, the heater 63 is located inside the housing 62 and outside the space 64. The heater 63 heats the processing container 65 and also heats the wafer W held in the crystal boat 44, i.e., the wafer W inside the processing container 65. The heater 63 functions as a heating element for heating the wafer W.

[0135] In addition, the heater 63 includes, for example, a heating resistor such as a carbon filament, which can control the temperature of the gas flowing inside the space 64 and can heat the processing container 65 to a specified temperature (e.g., 50~1200°C).

[0136] The space within space 64 and processing container 65 is divided longitudinally into multiple unit regions, for example, 10 unit regions A1, A2, A3, A4, A5, A6, A7, A8, A9, and A10. Heaters 63 are divided into 63-1, 63-2, 63-3, 63-4, 63-5, 63-6, 63-7, 63-8, 63-9, and 63-10, corresponding to any one of the unit regions along the vertical direction. Heaters 63-1 to 63-10 are configured such that heating can be independently controlled corresponding to each unit region A1 to A10 via the output (heater power) of a heater output section 86, for example, including a thyristor. Heaters 63-1 to 63-10 are examples of heating elements.

[0137] Measurement signals from temperature sensors Ao1 to Ao10 are each input to the device controller 100 via line 81. Measurement signals from temperature sensors Ai1 to Ai10 are each input to the device controller 100 via line 82. Based on the set temperature, the device controller 100, having received the measurement signals, controls the heater power output by the heater output unit 86. The heater output unit 86 supplies heater power to heaters 63-1 to 63-10 via heater output line 87 and heater terminals 88.

[0138] Alternatively, the heat treatment furnace 60 may also have a cooling mechanism 90 for cooling the treatment container 65. The cooling mechanism 90 may include, for example, a blower 91, an air duct 92, and an exhaust duct 94.

[0139] The preferred embodiments of this implementation have been described in detail above. However, this implementation is not limited to the above embodiments, and various modifications and substitutions can be applied to the above embodiments without departing from the scope of this implementation.

[0140] The substrate processing system 1 of the present invention is not limited to Figure 1 The structure shown can be used for various purposes and system configurations. The substrate processing apparatus 10 of the present invention can be applied to any of the following devices: a single-chip device that processes substrates one by one, a batch device that processes multiple substrates uniformly, and a semi-batch device.

[0141] Explanation of reference numerals in the attached figures

[0142] 1: Substrate processing system; 10: Substrate processing device; 12: Device controller; 16: Server device; 18: Operator terminal; 130: Acquisition unit; 132: Data storage unit; 134: Temperature control unit; 136: Prediction unit; 138: Formulation performance evaluation unit; 140: Input receiving unit; 142: Display control unit; 150: Thermal model; 152: Chemical reaction model; 154: Machine learning model.

Claims

1. An information processing apparatus for evaluating the performance of a substrate processing apparatus for film formation according to a formula, wherein, include: The prediction unit predicts the film formation result of the substrate processing apparatus performing film formation treatment according to the stated formula; The formulation performance evaluation department evaluates the performance of the formulation for each evaluation item based on the predicted film formation results of the substrate processing device. and The display control unit displays the performance evaluation of the formulation for each of the evaluation items.

2. The information processing apparatus according to claim 1, wherein, The prediction unit includes: a thermal physical model that predicts the temperature of the substrate processing apparatus undergoing film formation according to the formula; and a chemical reaction physical model that predicts the film formation result of the substrate processing apparatus undergoing film formation according to the formula. The physical model of the chemical reaction predicts the film formation result of the substrate processing device based on the temperature of the substrate processing device predicted by the physical model of the heat and the formulation.

3. The information processing apparatus according to claim 1, wherein, The prediction unit includes: a thermal physics model that predicts the temperature of the substrate processing apparatus performing film formation according to the formula; and a machine learning model of the chemical reaction that predicts the film formation result of the substrate processing apparatus performing film formation according to the formula. The machine learning model for the chemical reaction has learned the relationship between the temperature of the substrate processing device and the formulation and the film formation result of the substrate processing device. Based on the temperature of the substrate processing device and the formulation predicted by the thermal physics model, the film formation result of the substrate processing device is predicted.

4. The information processing apparatus according to any one of claims 1 to 3, wherein, The formulation performance evaluation unit evaluates at least one of film thickness, film stability, and production efficiency based on the film formation results of the substrate processing device predicted by the prediction unit.

5. The information processing apparatus according to claim 4, wherein, The formulation performance evaluation unit, based on the film formation results of the substrate processing device predicted by the prediction unit, also evaluates the performance of at least one of particle generation, energy consumption, process gas consumption, and temperature control as evaluation items.

6. The information processing apparatus according to claim 4, wherein, The formulation performance evaluation unit evaluates the film thickness by using a standardized evaluation method that compares the difference between the predicted film thickness predicted by the prediction unit and the target film thickness of the formulation with the target film thickness.

7. The information processing apparatus according to claim 4, wherein, The formulation performance evaluation unit evaluates the film-forming stability by evaluating the discrepancy of the predicted film thickness predicted by the prediction unit when conditions change.

8. A performance evaluation method, wherein an information processing device evaluates the performance of a substrate processing apparatus for film formation according to a formula, wherein, include: A step of predicting the film formation result of the substrate processing apparatus performing film formation according to the stated formula; Based on the predicted film formation results of the substrate processing device, the performance evaluation of the formulation is carried out for each evaluation item. and The steps for evaluating the performance of the formulation are displayed for each of the evaluation items.

Images