Recipe optimization method, and heat processing device

Abstract

To provide a technique capable of obtaining a recipe of deposition processing efficiently and at low cost.SOLUTION: A recipe optimization method optimizes a recipe of deposition processing for depositing a film over a plurality of substrates stored in a processing container. The recipe optimization method includes the steps of: (a) generating a prediction model which predicts a process model indicating a relation between a temperature change amount and a film thickness change amount based on past evaluation data; (b) executing deposition processing of pre-implementation upon the substrate; (c) determining whether or not a film thickness of the substrate on which the film is deposited in the deposition processing is within an allowable range; (d) calculating a recipe of the deposition processing of the pre-implementation based on the prediction model in a case where it is determined that the film thickness is out of the allowable range, using the recipe to perform the deposition processing of the pre-implementation again and then returning to the step (c); and (e) obtaining the recipe of the deposition processing with which the film thickness is within the allowable range in a case where it is determined that the film thickness is within the allowable range.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present disclosure relates to a recipe optimization method and a thermal processing apparatus. [Background technology]

[0002] Patent Document 1 discloses a substrate processing system (heat processing apparatus) that performs film formation processing by supplying a film formation gas into a processing vessel containing multiple substrates and heating each substrate. A control device of this substrate processing system calculates film formation conditions that satisfy target film characteristics using measurement results of the characteristics of a film formed according to film formation conditions (recipe), a process model that represents the influence of the film formation conditions on the film characteristics, and actual measurement values ​​of the film formation conditions. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-174983 Summary of the Invention [Problem to be solved by the invention]

[0004] The present disclosure provides a technique that allows for efficient and low-cost generation of film formation recipes. [Means for solving the problem]

[0005] According to one aspect of the present disclosure, there is provided a recipe optimization method for optimizing a recipe for a film formation process for forming a film on a plurality of substrates housed in a processing vessel, the recipe optimization method comprising: (a) generating a prediction model that predicts a process model showing a relationship between a temperature change amount and a film thickness change amount based on past evaluation data; (b) performing a pre-operation film formation process on the substrate; (c) determining whether the film thickness of the substrate formed by the film formation process is within an acceptable range; (d) if it is determined in step (c) that the film thickness is outside the acceptable range, calculating a recipe for the pre-operation film formation process based on the prediction model in step (b), performing the pre-operation film formation process again using the recipe, and then returning to step (c); and (e) if it is determined in step (c) that the film thickness is within the acceptable range, obtaining the recipe for the film formation process that is within the acceptable range. [Effects of the Invention]

[0006] According to one aspect, a film formation recipe can be obtained efficiently and at low cost. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a cross-sectional view schematically showing a heat treatment apparatus according to an embodiment. [Figure 2] 2A is a graph illustrating the relationship between temperature and film formation rate, and FIG. 2B is a graph illustrating the generation of a prediction model for a process model. [Figure 3] FIG. 2 is a block diagram showing functional blocks of a control unit formed to optimize a recipe for a film formation process in a heat treatment apparatus. [Figure 4] 10 is a flowchart showing a processing flow of a prediction model generation process of the recipe optimization method. [Figure 5] 10 is a flowchart showing a processing flow of a main generation process of the recipe optimization method. [Figure 6] 10 is a flowchart showing the process flow of a re-creation subroutine of the recipe optimization method. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In the drawings, the same components are denoted by the same reference numerals, and redundant explanations may be omitted.

[0009] <Configuration of Heat Treatment Device 1> Fig. 1 is a cross-sectional view schematically showing a heat treatment apparatus according to an embodiment. As shown in Fig. 1, the heat treatment apparatus 1 according to the embodiment is a semiconductor manufacturing system that arranges a plurality of substrates W in a vertical direction (up and down direction) and performs a film formation process to form a desired film on the surface of the substrate W. The substrate W may be, for example, a semiconductor substrate such as a silicon wafer or a compound semiconductor wafer, or a glass substrate.

[0010] The heat treatment apparatus 1 includes a processing container 10 that accommodates a plurality of substrates W, and a temperature-controlled furnace 50 that is disposed around the processing container 10. The heat treatment apparatus 1 also includes a control unit 90 that controls the operation of each component of the heat treatment apparatus 1.

[0011] The processing vessel 10 is formed in a cylindrical shape extending in the vertical direction. An internal space IS is formed inside the processing vessel 10, in which multiple substrates W can be arranged vertically. The processing vessel 10 includes, for example, a cylindrical inner cylinder 11 with an open upper end (ceiling) and lower end, and a cylindrical outer cylinder 12 disposed outside the inner cylinder 11, having a ceiling but an open lower end. The inner cylinder 11 and the outer cylinder 12 are formed of a heat-resistant material such as quartz and have a double structure arranged coaxially. The processing vessel 10 is not limited to a double structure, and may be a single-cylinder structure or a multiple-cylinder structure consisting of three or more cylinders.

[0012] The inner cylinder 11 has a diameter larger than the diameter of each substrate W, and an axial length large enough to accommodate each substrate W (for example, equal to or greater than the height of each substrate W). A processing space (part of the internal space IS) is formed inside the inner cylinder 11, where a gas is discharged onto each accommodated substrate W to perform a film formation process. An opening 15 is provided at the upper end of the inner cylinder 11, which communicates with the processing space and allows gas to flow into a communication space (another part of the internal space IS) between the inner cylinder 11 and the outer cylinder 12.

[0013] Furthermore, a housing portion 13 for housing a gas nozzle 31 is formed along the vertical direction at a portion of the circumferential direction of the inner cylinder 11. As an example, the housing portion 13 is provided inside a protrusion 14 that protrudes a portion of the side wall of the inner cylinder 11 radially outward. Note that instead of the opening 15 at the upper end, the inner cylinder 11 may be provided with a vertically long opening (not shown) at an appropriate position on the circumferential wall (for example, on the opposite side of the central axis from the housing portion 13).

[0014] The outer cylinder 12 has a larger diameter than the inner cylinder 11, covers the inner cylinder 11 without contacting it, and forms the outer shape of the processing vessel 10. A flow space between the inner cylinder 11 and the outer cylinder 12 is formed above and to the sides of the inner cylinder 11, and allows gas that has moved upward to flow vertically downward.

[0015] The lower end of the processing vessel 10 is supported by a cylindrical manifold 17 made of stainless steel. For example, the manifold 17 has a manifold-side flange 17f at its upper end. The manifold-side flange 17f fixes and supports an outer cylinder-side flange 12f formed at the lower end of the outer cylinder 12. A seal member 19 that airtightly seals the outer cylinder 12 and the manifold 17 is provided between the outer cylinder-side flange 12f and the manifold-side flange 17f.

[0016] The manifold 17 also has an annular support portion 20 on the inner wall on the upper side. The support portion 20 protrudes radially inward to fix and support the lower end of the inner cylinder 11. A lid body 21 is removably attached to a lower end opening 17o of the manifold 17.

[0017] The lid 21 is part of a substrate placement unit 22 that places the wafer boat 16 holding the substrates W inside the processing vessel 10. The lid 21 is made of, for example, stainless steel and has a disk shape. With the substrates W placed in the internal space IS, the lid 21 airtightly closes the lower end opening 17o of the manifold 17 via a seal member 18 provided at the lower end of the manifold 17.

[0018] A rotation shaft 24 that rotatably supports the wafer boat 16 via a magnetic fluid seal 23 penetrates the center of the lid 21. A lower portion of the rotation shaft 24 is supported by an arm 25A of a lifting mechanism 25 that is configured by a boat elevator or the like. By raising and lowering the arm 25A of the lifting mechanism 25, the heat treatment apparatus 1 moves the lid 21 and the wafer boat 16 up and down together, thereby inserting and removing the wafer boat 16 into and from the processing vessel 10.

[0019] A rotating plate 26 is provided at the upper end of the rotating shaft 24. The wafer boat 16, which holds the substrates W, is supported on the rotating plate 26 via a heat insulating unit 27. The wafer boat 16 is configured as a shelf that can hold the substrates W at regular intervals along the vertical direction. When the substrates W are held by the wafer boat 16, the surfaces of the substrates W extend horizontally relative to each other.

[0020] The gas supply unit 30 is inserted into the processing vessel 10 via the manifold 17. The gas supply unit 30 introduces gases such as a processing gas, a purge gas, and a cleaning gas into the internal space IS of the inner cylinder 11. The gas supply unit 30 has gas nozzles 31 that introduce the processing gas, the purge gas, the clean gas, and the like. Although only one gas nozzle 31 is shown in FIG. 1, the gas supply unit 30 may be provided with multiple gas nozzles 31. For example, multiple gas nozzles 31 may be provided for each type of gas, such as the processing gas, the purge gas, and the clean gas.

[0021] The gas nozzle 31 is a quartz injector tube that extends vertically within the inner cylinder 11 and is bent at its lower end into an L-shape so as to penetrate the inside and outside of the manifold 17. The gas nozzle 31 is fixed to and supported by the manifold 17. The gas nozzle 31 has a plurality of gas holes 31h spaced at regular intervals along the vertical direction, and discharges gas horizontally through each gas hole 31h. The intervals between the gas holes 31h are set to be the same as the intervals between the substrates W supported on the wafer boat 16, for example. The vertical positions of the gas holes 31h are set to be midway between the substrates W adjacent to each other in the vertical direction. This allows the gas holes 31h to smoothly circulate through the gaps between the substrates W.

[0022] The gas supply unit 30 supplies a processing gas, a purge gas, a cleaning gas, etc. to a gas nozzle 31 inside the processing vessel 10 while controlling the flow rate outside the processing vessel 10. The processing gas may be selected appropriately depending on the type of film to be formed on the substrate W. For example, when forming a silicon oxide film, a silicon-containing gas such as dichlorosilane (DCS) gas and an oxidizing gas such as ozone (O) gas can be used as the processing gas. For example, nitrogen (N) gas or argon (Ar) gas can be used as the purge gas.

[0023] The gas exhaust unit 40 exhausts gas inside the processing vessel 10 to the outside. The gas supplied by the gas supply unit 30 moves from the processing space of the inner cylinder 11 to the circulation space, and then is exhausted through the gas outlet 41. The gas outlet 41 is formed above the support unit 20 in the manifold 17. An exhaust path 42 of the gas exhaust unit 40 is connected to the gas outlet 41. The gas exhaust unit 40 includes, in order from upstream to downstream of the exhaust path 42, a pressure adjustment valve 43 and a vacuum pump 44. The gas exhaust unit 40 sucks gas inside the processing vessel 10 using the vacuum pump 44 and adjusts the flow rate of the exhausted gas using the pressure adjustment valve 43, thereby adjusting the pressure inside the processing vessel 10.

[0024] Furthermore, a temperature sensor 80 is provided in the internal space IS of the processing vessel 10 (e.g., the processing space of the inner cylinder 11) to detect the temperature inside the processing vessel 10. The temperature sensor 80 has multiple (five in this embodiment) temperature sensors 81-85 at different vertical positions. The multiple temperature sensors 81-85 may be thermocouples, resistance temperature sensors, or the like. The temperature sensors 81-85 are provided at positions corresponding to multiple zones (described below) set along the vertical direction of the processing vessel 10. The temperature sensor 80 transmits the temperatures detected by each of the multiple temperature sensors 81-85 to the control unit 90.

[0025] On the other hand, the temperature-controlled furnace 50 is formed in a cylindrical shape that covers the entire processing vessel 10, and heats and cools each substrate W accommodated in the processing vessel 10. Specifically, the temperature-controlled furnace 50 has a cylindrical housing 51 with a ceiling and a heater 52 provided inside the housing 51.

[0026] The housing 51 is formed to be larger than the processing vessel 10, and its central axis is installed at approximately the same position as the central axis of the processing vessel 10. For example, the housing 51 is attached to the upper surface of a base plate 54 to which the outer cylinder side flange 12f is fixed. The housing 51 is installed at a distance from the outer peripheral surface of the processing vessel 10, thereby forming a temperature-controlled space 53 between the outer peripheral surface of the processing vessel 10 and the inner peripheral surface of the housing 51. The temperature-controlled space 53 is provided so as to be continuous with the sides and above the processing vessel 10.

[0027] The housing 51 includes a heat insulating section 51a having a ceiling and covering the entire processing vessel 10, and a reinforcing section 51b that reinforces the heat insulating section 51a on the outer periphery of the heat insulating section 51a. That is, the sidewall of the housing 51 has a laminated structure of the heat insulating section 51a and the reinforcing section 51b. The heat insulating section 51a is formed mainly of, for example, silica, alumina, or the like, and suppresses heat transfer within the heat insulating section 51a. The reinforcing section 51b is formed of a metal such as stainless steel. In addition, to suppress thermal influence on the outside of the temperature-controlled furnace 50, the outer periphery of the reinforcing section 51b is covered with a water-cooling jacket (not shown).

[0028] The heater 52 of the temperature-controlled furnace 50 may have an appropriate configuration for heating the plurality of substrates W in the processing chamber 10. For example, the heater 52 may be an infrared heater that heats the processing chamber 10 by emitting infrared rays.

[0029] The heater 52 is divided into multiple sections (five in this embodiment) along the vertical direction of the temperature-controlled furnace 50, and each section is connected to a temperature control driver 55. The temperature control driver 55 is connected to a control unit 90, and supplies power adjusted under the control of the control unit 90 to the connected heater 52 to heat the heater 52. This allows the heat treatment apparatus 1 to independently adjust the temperature of the processing vessel 10 for each of the multiple zones in which the multiple divided heaters 52 are provided.

[0030] Furthermore, the temperature-controlled furnace 50 includes an external circulation unit 60 that circulates a cooling gas (air, inert gas) through the temperature-controlled space 53 to cool the processing vessel 10 during the film formation process. Specifically, the external circulation unit 60 includes an external supply path 61 and a flow rate regulator 62 that are provided outside the temperature-controlled furnace 50, a supply flow path 63 that is provided in the reinforcing portion 51b, and a supply hole 64 that is provided in the heat-insulating portion 51a. The external supply path 61 may also be provided with a temperature regulator (heat exchanger, radiator, etc.) to regulate the temperature of the air flowing into the temperature-controlled space 53.

[0031] The external circulation unit 60 also has an exhaust hole 65 in the ceiling of the housing 51 that exhausts air supplied into the temperature-controlled space 53. The exhaust hole 65 is connected to an external exhaust path 66 provided outside the housing 51. The external exhaust path 66 exhausts the air in the temperature-controlled space 53 toward an appropriate waste portion. Alternatively, the external circulation unit 60 may be configured to circulate the air used in the temperature-controlled space 53 by connecting the external exhaust path 66 to the external supply path 61.

[0032] The control unit 90 of the heat treatment apparatus 1 may be a computer having a processor 91, a memory 92, an input / output interface (not shown), a communication interface, etc. The processor 91 may be one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a circuit made up of multiple discrete semiconductors, etc. The memory 92 may include a main storage device made up of a semiconductor memory or the like, and an auxiliary storage device made up of a disk, semiconductor memory (flash memory), etc. The memory 92 may be configured by appropriately combining volatile memory and non-volatile memory (e.g., a compact disk, a digital versatile disc (DVD), a hard disk, flash memory, etc.).

[0033] The memory 92 stores a program for operating the heat treatment apparatus 1 and a recipe for process conditions for the film formation process (substrate processing). The processor 91 controls each component of the heat treatment apparatus 1 by reading and executing the program from the memory 92. In other words, in this disclosure, the control unit 90 is an electronic circuit having a CPU, GPU, ASIC, FPGA, etc., and performs the various control operations described in this specification by executing instruction codes stored in the memory 92 or by being a circuit designed for a specific purpose. The control unit 90 may be configured as a host computer or multiple client computers that communicate with each other via a network.

[0034] A user interface 95 is also connected to the control unit 90 via an input / output interface. Examples of the user interface 95 include a touch panel (input / output device), a monitor, a speaker, a keyboard, a mouse, a speaker, and a microphone. The control unit 90 receives a recipe for the heat treatment apparatus 1 input by a user via the user interface 95, and controls each component of the heat treatment apparatus 1 based on this recipe. When the control unit 90 receives information from each component during a film formation process or the like, it appropriately notifies the user of information about the film formation process (status, errors, etc.) via the user interface 95.

[0035] The heat treatment apparatus 1 described above calculates an optimal recipe (process conditions) using a process model that indicates the relationship between the amount of change in film thickness (film formation rate) and the amount of change in temperature during actual operation of the film formation process on each substrate W. In other words, the process model is a function of energy, including temperature, for obtaining a target film thickness in the film formation process. The heat treatment apparatus 1 needs to prepare a process model in advance before actual operation.

[0036] In conventional heat treatment equipment, a process model is obtained by conducting multiple pre-tests of the film formation process before actual operation. For example, in the pre-test, film formation processes are performed multiple times while varying the temperature of each substrate in the processing chamber, and the film thickness of each film formation process is measured to obtain the film thickness change relative to the temperature change. Furthermore, in vertical heat treatment equipment in which multiple substrates W are arranged vertically, this pre-test is performed for each heater zone. Therefore, the heat treatment equipment performs multiple film formation processes during this pre-test. Furthermore, when the recipe for the film formation process, such as the gas type and gas flow rate, is changed, or when the equipment hardware is modified (including component replacement during maintenance), the process model must be re-created. Thus, conventional heat treatment equipment requires multiple re-tests of the film formation process during startup and maintenance, which increases the time and cost required for actual operation.

[0037] <Generating a predictive model> Therefore, the heat treatment apparatus 1 according to the embodiment aims to reduce the time and cost required to obtain an optimum recipe for actual operation by generating a prediction model of the process model using evaluation data of film formation processes performed in the past. The prediction model of the process model will be described below with reference to FIG.

[0038] Figure 2(A) is a graph illustrating the relationship between temperature and film formation rate. Figure 2(B) is a graph illustrating the generation of a predictive model for a process model. In each graph, the horizontal axis is the reciprocal of temperature T (= 1 / T), and the vertical axis is the film formation rate k [angstroms / sec], which is the film thickness per unit time (Å or nm).

[0039] As described above, the process model of the heat treatment apparatus 1 is a model that shows the relationship between the amount of change in temperature and the amount of change in film thickness. This process model can be expressed by the following equation (1) based on the Arrhenius equation of the film formation rate.

[0040]

number

[0041] And the activation energy E in Eq. (1) a is a value that indicates the gradient of the change in the film formation rate k with respect to the temperature change in the graph of FIG. 2(A). In other words, the process model is a This is a function that shows the relationship between temperature and film thickness, which can be expressed by the following formula. Conventionally, as mentioned above, in a preliminary test, the film formation process is performed multiple times at different temperatures to obtain film thicknesses corresponding to each temperature, and this activation energy E a In order to facilitate understanding of the invention, Fig. 2(A) shows an example in which the film formation rate k decreases linearly, but the change in the film formation rate k may be nonlinear.

[0042] In response to this, the control unit 90 of the heat treatment apparatus 1 according to the embodiment generates a prediction model of the process model using a plurality of past evaluation data. For example, the prediction model uses the activation energy E a It is calculated as a function close to

[0043] The past evaluation data used to calculate the prediction model is information linking the film thickness of a film actually formed in various heat treatment apparatuses that have performed film formation processes in the past with the temperature (target temperature or measured temperature) of the film formation process at that time. The film thickness may be the film formation rate. Furthermore, the past evaluation data may include process models used in the film formation processes of various heat treatment apparatuses. In addition, the past evaluation data preferably includes all or some parameters such as the film formation process recipe (process conditions) when the data was obtained, the actual measured values ​​of various sensors, and hardware information. The film formation process recipe may include the temperature, type of process gas, flow rate, pressure, and processing time of the process gas. The actual measured values ​​of various sensors are values ​​actually measured during the film formation process by sensors equipped in various heat treatment apparatuses. Furthermore, the hardware information may include the spacing (pitch width) between each substrate W placed on the wafer boat 16, the diameter of the inner cylinder 11, the diameter of the outer cylinder 12, etc.

[0044] The control unit 90 can generate a prediction model by using a known regression method for the temperature and film thickness (e.g., film rate) of the acquired evaluation data, as shown in FIG. 2B. The process model is based on the activation energy E a The prediction model calculated by the regression method also uses this activation energy E a The regression method may be selected from linear regression (Ridge regression, Lasso regression), nonlinear regression, polynomial regression, least squares method, etc.

[0045] For example, the control unit 90 acquires multiple pieces of past evaluation data for heat treatment apparatuses of different models than the current heat treatment apparatus 1, or evaluation data for different types of film formation processes. In this case, the control unit 90 associates and stores parameters, such as recipes for different models and types of film formation processes, actual measurement values ​​from various sensors, and hardware information, with data (process models) such as temperature and film thickness (film formation rate). The control unit 90 then extracts temperature and film thickness data associated with similar parameters and can obtain a prediction model using a well-known regression method. The more evaluation data used in this process, the higher the accuracy of generating the prediction model.

[0046] Furthermore, for example, when the film formation process has been performed multiple times using the current heat treatment apparatus 1, the control unit 90 may generate the prediction model using only multiple pieces of past evaluation data for the current heat treatment apparatus 1. Alternatively, the control unit 90 may generate the prediction model using only multiple pieces of past evaluation data for heat treatment apparatuses that are the same model as the current heat treatment apparatus 1. This makes it possible to quickly obtain a prediction model for the current heat treatment apparatus 1 that is sufficiently close to the process model used in actual operation.

[0047] <Functional blocks of the control unit 90> Fig. 3 is a block diagram showing functional blocks of a control unit 90 formed to optimize a recipe for a film formation process in the heat treatment apparatus 1. A processor 91 of the control unit 90 executes a program stored in a memory 92 to form a film formation process control unit 911, a prediction model generation unit 912, a process model generation unit 913, and an optimization calculation unit 914, as shown in Fig. 3. The memory 92 also has an evaluation data storage area 921, a prediction model storage area 922, a process model storage area 923, a recipe storage area 924, an explanatory variable storage area 925, etc.

[0048] The film formation process control unit 911 is a functional unit that controls the film formation process during actual operation in the heat treatment apparatus 1 and the film formation process during standard pre-operation. The standard pre-operation is a process to check whether the heat treatment apparatus 1 operates according to the set recipe when the heat treatment apparatus 1 is started up, during maintenance, when process conditions are changed, etc., and is always performed before actual operation. Even in this standard pre-operation film formation process, each parameter for the film formation process is set. For example, in the standard pre-operation film formation process, the process gas planned for actual operation is used, and other parameters (such as the temperature of the substrate W, the flow rate and pressure of the process gas) are set arbitrarily by the user or the standard settings of the apparatus are adopted. The user can set each parameter based on experience, a manual, etc.

[0049] The prediction model generation unit 912 generates a prediction model of the process model as described above (see also FIG. 2(B)) using multiple pieces of past evaluation data stored in the evaluation data storage area 921. The generated prediction model is stored in the prediction model storage area 922.

[0050] The process model generation unit 913 generates a process model using the generated prediction model and each parameter used in the film formation process of the reference preliminary operation. The parameters used in the film formation process of the reference preliminary operation are explanatory variables for obtaining a process model, which is a target variable, and are stored in an explanatory variable storage area 925. The parameters used in the film formation process of the reference preliminary operation include recipe information such as the target temperature of the substrates W, the type of process gas, the gas flow rate, and pressure. Alternatively, each parameter may include actual measurement values ​​of each sensor measured in the film formation process of the reference preliminary operation. Furthermore, each parameter includes hardware information such as the structure of the wafer boat 16 (such as the spacing between each substrate W), the diameter of the inner cylinder 11, and the diameter of the outer cylinder 12. The process model generated based on the prediction model and each parameter is stored in a process model storage area 923.

[0051] After obtaining a process model from the prediction model, the optimization calculation unit 914 performs a recipe optimization calculation using this process model to calculate an optimal recipe for achieving a target film thickness in actual operation. The calculated recipe is, for example, the temperature conditions for the film formation process in actual operation. In this recipe optimization calculation, a known method can be used to optimize the recipe based on the film thickness (actual measured value) of the film formed on each substrate W by the film formation process in a reference preliminary operation and the process model. In addition, in the recipe optimization calculation, the optimization calculation unit 914 may use a thermal model stored in advance to calculate the time change in the target temperature for each of multiple zones in the vertical direction. The calculated recipe is stored in the recipe storage area 924.

[0052] The control unit 90 performs the standard pre-operation film formation process using each of the above functional units, but by minimizing the number of times it is performed, it is possible to quickly obtain a process model and film formation process recipe for actual operation.

[0053] <Recipe optimization method> The heat treatment apparatus 1 according to the embodiment is basically configured as described above, and its operation (recipe optimization method) will be described below with reference to Figs. 4 to 6. Fig. 4 is a flowchart showing the processing flow of the prediction model generation process of the recipe optimization method. Fig. 5 is a flowchart showing the processing flow of the main generation process of the recipe optimization method. Fig. 6 is a flowchart showing the processing flow of the re-creation subroutine of the recipe optimization method.

[0054] The control unit 90 executes a recipe optimization method before an actual operation in order to set an optimal recipe to be used in an actual film formation process. In the recipe optimization method, the control unit 90 controls steps S101 to S102 of Fig. 4, steps S111 to S119 of Fig. 5, and steps S115-1 to S115-2 of Fig. 6. Specifically, the control unit 90 executes a prediction model generation process that generates a prediction model of the process model shown in Fig. 4, and a main generation process that generates a process model and an optimal recipe using the prediction model shown in Fig. 5 and Fig. 6. The prediction model generation process is executed at least before the step in the main generation process that uses the prediction model.

[0055] In the prediction model generation method, the control unit 90 first acquires past evaluation data of the heat treatment apparatus (step S101). As described above, the past evaluation data may be only data for the current heat treatment apparatus 1, or may be data for film formation processes performed in other heat treatment apparatuses. For example, in the recipe optimization method, a storage device (not shown) in which past evaluation data for film formation processes is stored in advance is provided to the user. By connecting this storage device to the control unit 90, the user of the heat treatment apparatus 1 can import the accumulated evaluation data into the control unit 90. Alternatively, the control unit 90 may access a server that stores past evaluation data for film formation processes via a network and import the evaluation data from the server.

[0056] Next, the control unit 90 generates a prediction model of the process model by a regression method using the acquired multiple pieces of past evaluation data (step S102). As described above, each of the multiple pieces of evaluation data is linked to parameters such as recipe information (target temperature of the substrate W, type of process gas, gas flow rate, pressure), hardware information (structure of the wafer boat 16, diameter of the inner cylinder 11, diameter of the outer cylinder 12), etc. Therefore, the prediction model is generated as a model in which parameters are added to the relationship between temperature and film thickness.

[0057] On the other hand, in the main generation process, the control unit 90 performs a film formation process of a standard preliminary operation, creates a process model according to the film formation state at this time, and performs optimization calculation of the recipe. Specifically, the control unit 90 sequentially executes the process flow shown in FIG. 5 as the main generation process.

[0058] In the main generation process, the control unit 90 first executes a film formation process of a reference pre-operation based on a user's operation (step S111). The film formation process control unit 911 of the control unit 90 accommodates multiple substrates W in the processing vessel 10, supplies the same processing gas as that used in the actual operation into the processing vessel 10, exhausts the gas inside the processing vessel 10, and adjusts the temperature of each substrate W using the temperature-controlled furnace 50. The target flow rate of the processing gas, the target pressure inside the processing vessel 10, the target temperature of each substrate W, etc. are set by the user (or standard settings for the apparatus are adopted). The control unit 90 may execute a recipe optimization calculation using the prediction model generated by the above-mentioned prediction model generation method, and execute the film formation process of the reference pre-operation using a recipe based on the prediction model.

[0059] After the film formation process of the reference pre-operation, the control unit 90 acquires the film thickness of the film formed on each substrate W (step S112). For example, in a system including the heat treatment device 1, when the wafer boat 16 is unloaded from the processing chamber 10 and the substrates W are transported by the transport device, the film on the substrates W is automatically measured by a film thickness measuring device (not shown). The control unit 90 can obtain film thickness information from this film thickness measuring device.

[0060] Then, the control unit 90 compares the acquired film thickness with information on the allowable range pre-stored in the memory 92, and determines whether or not the film thickness is within the allowable range (step S113). The allowable range of film thickness may be set by the user (or automatically) according to the target film thickness and target accuracy in actual operation.

[0061] If the film thickness of the substrate W is within the allowable range (step S113: YES), the target film thickness has been formed, and the film formation recipe that obtained that film thickness can be adopted. On the other hand, if the film thickness of the substrate W is outside the allowable range (step S113: NO), the film formation recipe that obtained that film thickness cannot be adopted. In this case, the control unit 90 proceeds to step S114.

[0062] In step S114, the control unit 90 determines whether the heat treatment apparatus 1 has performed the film formation process of the reference pre-operation for the first time or has performed the film formation process for the second or subsequent times. In the first film formation process, only a prediction model exists in the control unit 90, whereas in the second or subsequent times, a prediction model and a process model generated based on this prediction model exist. Step S114 is a determination for distinguishing between these. If the control unit 90 has performed the film formation process for the second or subsequent times (reference pre-operation) (step S114: YES), the control unit 90 proceeds to step S115. On the other hand, if the control unit 90 has performed the first film formation process (step S114: NO), the control unit 90 skips step S115 and proceeds to step S116 and subsequent times.

[0063] In the second and subsequent film formation processes, the film formation process is performed using the process model generated in the previous film formation process. Therefore, if the film thickness falls outside the allowable range even in the second and subsequent film formation processes, it is assumed that the prediction model used to generate the process model was insufficient. Therefore, in step S115, the control unit 90 executes a re-creation subroutine to re-create a prediction model (see FIG. 6).

[0064] Specifically, the prediction model generation unit 912 of the control unit 90 adds the evaluation data of the current film formation process to the past evaluation data (step S115-1). Like the past evaluation data, the current evaluation data is linked to data indicating the relationship between temperature and film thickness, as well as recipe information, hardware information, and the like. Since the memory 92 of the control unit 90 has already stored the past evaluation data, the user only needs to import the current evaluation data into the control unit 90.

[0065] The control unit 90 then recreates a prediction model for the process model by the regression method using a data set in which the current evaluation data is added to the past evaluation data (step S115-2). The data set is more complete than when the prediction model was created last time due to the addition of the current evaluation data. Therefore, in the recreate subroutine, the control unit 90 can generate a more accurate prediction model. Alternatively, the control unit 90 may change the regression method to another method when recreating the prediction model. This makes it possible to obtain a prediction model different from the previous one.

[0066] 5, the control unit 90 inputs the parameters of the film formation process for the substrate W, the film thickness state of which has been determined in step S113, into the prediction model (step S116). As described above, the parameters of the film formation process include recipe information and hardware information, and the control unit 90 uses these as explanatory variables when generating the process model.

[0067] Then, the control unit 90 generates a process model, which is a response variable, based on the input parameters (explanatory variables) and the prediction model (step S117). The generated process model includes an activation energy E a is (or is a good approximation).

[0068] Therefore, the control unit 90 performs optimization calculations for the recipe using the generated process model, thereby calculating an optimal recipe based on this process model (step S118).

[0069] Furthermore, the control unit 90 updates the recipe to the calculated recipe and executes the second and subsequent film formation processes (standard pre-operations) based on this recipe again (step S119). Through this film formation process, a film is formed on each substrate W accommodated in the processing vessel 10 according to the recipe. After this film formation process, the control unit 90 returns to step S112, where the control unit 90 measures the thickness of the film formed on each substrate W, and repeats the process flow from the main generation process onwards.

[0070] By repeating the above process flow of the main generation process, the heat treatment apparatus 1 can smoothly obtain a process model and recipe that will keep the film thickness of the substrate W within the allowable range, in other words, that will allow a film to be formed with a target film thickness. In particular, by creating a prediction model using a regression method with past evaluation data, the process model for the current heat treatment apparatus 1 can be efficiently generated. This makes it possible to reduce the number of film formation processes performed before actual operation, allowing for an earlier start of actual operation, and also significantly reduces the cost required to obtain a recipe for actual operation.

[0071] Even if the film formation recipe (process conditions) or hardware changes, the heat treatment apparatus 1 can easily obtain an optimal film formation recipe by performing a standard pre-operation using a prediction model. In other words, the heat treatment apparatus 1 does not need to perform pre-testing to obtain a process model. Therefore, the heat treatment apparatus 1 can efficiently obtain an appropriate recipe when starting up the apparatus or during maintenance, improving the productivity of the entire operation of the apparatus.

[0072] The recipe optimization method and heat treatment apparatus 1 according to the present disclosure are not limited to the above embodiment and may take various modified forms. For example, in the above embodiment, a vertical heat treatment apparatus 1 in which a plurality of substrates W are arranged vertically and a film formation process is performed has been described. However, the heat treatment apparatus 1 may also be a horizontal apparatus in which substrates W are arranged horizontally and a film formation process is performed. In this case, an optimal recipe can be obtained in a similar manner.

[0073] The technical ideas and effects of the present disclosure explained in the above embodiments will be described below.

[0074] A first aspect of the present disclosure is a recipe optimization method for optimizing a recipe for a film formation process for forming a film on a plurality of substrates W housed in a processing vessel 10, the method comprising the steps of: (a) generating a prediction model that predicts a process model showing the relationship between temperature change and film thickness change based on past evaluation data; (b) performing a pre-operation film formation process on the substrates W; (c) determining whether the film thickness of the substrates W formed by the film formation process is within an acceptable range; (d) if it is determined in step (c) that the film thickness is outside the acceptable range, calculating a recipe for the pre-operation film formation process based on the prediction model in step (b), performing the pre-operation film formation process again using the recipe, and then returning to step (c); and (e) if it is determined in step (c) that the film thickness is within the acceptable range, obtaining a recipe for the film formation process that is within the acceptable range.

[0075] As described above, the recipe optimization method generates a prediction model based on past evaluation data and optimizes the recipe based on this prediction model, thereby enabling efficient and low-cost generation of a film formation recipe. In other words, by using the prediction model, the recipe optimization method can reduce the number of film formation processes required to generate a process model. For example, the recipe optimization method can obtain a film formation recipe for actual operation without conducting a pre-test, using only a pre-operational film formation process before actual operation, thereby significantly reducing time and costs.

[0076] In step (d), a process model is generated based on the prediction model, and the generated process model is used to optimize the recipe. This allows the recipe optimization method to easily and accurately obtain a process model and recipe for an actual film formation process.

[0077] In step (d), a process model, which is a target variable, is generated by inputting the parameters of the film formation process in the previous operation as explanatory variables along with the prediction model. As a result, the recipe optimization method can obtain a good process model corresponding to the model and film formation process of the current time, even when the prediction model is generated using past evaluation data for various models and film formation processes.

[0078] The parameters of the pre-operational film formation process include a recipe for the pre-operational film formation process, which includes a target temperature for the substrate W, a type of process gas, a gas flow rate, and pressure, and information about the hardware of the apparatus. By using these parameters as explanatory variables, the recipe optimization method can generate a process model for the film formation process of the current apparatus with higher accuracy.

[0079] Furthermore, when step (d) is performed multiple times based on the determination of step (c), the prediction model is recreated by adding the results of the film formation process of the previous operation that was outside the tolerance range, and a process model is generated based on the recreated prediction model. This allows the recipe optimization method to enrich the evaluation data for generating the prediction model, and generate a process model with even greater accuracy.

[0080] The prediction model is calculated by a regression method using past evaluation data of film formation processes performed in other equipment, which allows the recipe optimization method to easily calculate the prediction model based on the past evaluation data.

[0081] In the film formation process, a process gas is supplied to a plurality of substrates arranged vertically inside a process chamber, and the temperatures of the plurality of substrates are adjusted to a target temperature. This makes it possible to easily obtain a recipe for a film formation process that can be actually used in the vertical heat treatment apparatus 1.

[0082] A second aspect of the present disclosure is a heat treatment apparatus 1 including a processing vessel 10 that accommodates a plurality of substrates W, a gas supply unit 30 that supplies a processing gas into the processing vessel 10, a temperature-controlled furnace 50 that adjusts the temperatures of the plurality of substrates W to a target temperature, and a control unit 90 that optimizes a recipe for a film formation process for forming films on the plurality of substrates W and controls the gas supply unit 30 and the temperature-controlled furnace 50, wherein the control unit 90 (a) creates a prediction model that predicts a process model that indicates a relationship between a temperature change amount and a film thickness change amount based on past evaluation data. (b) a step of performing a preliminary film formation process on the substrate W, (c) a step of determining whether the film thickness of the substrate W formed by the film formation process is within an allowable range, (d) if it is determined in step (c) that the film thickness is outside the allowable range, a step of calculating a recipe for the preliminary film formation process based on the prediction model in step (b), performing the preliminary film formation process again using the recipe, and then returning to step (c), and (e) if it is determined in step (c) that the film thickness is within the allowable range, a step of obtaining a recipe for the film formation process that is within the allowable range. Even in this case, the heat treatment apparatus 1 can obtain a film formation process recipe efficiently and at low cost.

[0083] The recipe optimization method and heat treatment apparatus 1 according to the presently disclosed embodiments are illustrative in all respects and not restrictive. The embodiments may be modified and improved in various ways without departing from the spirit and scope of the appended claims. The features described in the above embodiments may be configured differently and may be combined within a consistent range. [Explanation of symbols]

[0084] 1. Heat treatment equipment 10 Processing container 30 Gas supply unit 50 Temperature controlled furnace 90 Control Unit W substrate

Claims

1. A recipe optimization method for optimizing a recipe for a film formation process for forming films on a plurality of substrates accommodated in a process vessel, comprising: (a) generating a prediction model that predicts a process model showing a relationship between a temperature change amount and a film thickness change amount based on past evaluation data; (b) performing a pre-operational deposition process on the substrate; (c) determining whether the thickness of the film formed on the substrate by the film forming process is within an allowable range; (d) when it is determined in the step (c) that the result is outside the allowable range, calculating a recipe for the preliminary operation film formation process based on the prediction model in the step (b), and performing the preliminary operation film formation process again using the calculated recipe, and then returning to the step (c); (e) when it is determined in the step (c) that the result is within the allowable range, obtaining the recipe for the film formation process that falls within the allowable range. How to optimize recipes.

2. In the step (d), the process model is generated based on the prediction model, and the recipe is optimized using the generated process model. The recipe optimization method of claim 1 .

3. In the step (d), the process model, which is a target variable, is generated by inputting parameters of the film formation process of the preliminary operation as explanatory variables together with the prediction model. The recipe optimization method of claim 2 .

4. The parameters of the pre-operational film formation process include a recipe for the pre-operational film formation process having a target temperature of the substrate, a type of process gas, a gas flow rate, and a pressure, and information on hardware of the apparatus. The recipe optimization method of claim 3 .

5. When the step (d) is performed multiple times based on the determination in the step (c), recreate the prediction model by adding the result of the film formation process of the preliminary operation that was outside the tolerance range, and generate the process model based on the recreated prediction model. The recipe optimization method of claim 2 .

6. the prediction model is calculated by a regression method using the past evaluation data of the film formation process performed in another apparatus; The method of claim 1 .

7. In the film formation process, a process gas is supplied to the plurality of substrates arranged vertically inside the process chamber, and the temperatures of the plurality of substrates are adjusted to a target temperature. The method of claim 1 .

8. a processing vessel for accommodating a plurality of substrates; a gas supply unit that supplies a processing gas into the processing vessel; a temperature control furnace that adjusts the temperatures of the plurality of substrates to a target temperature; a control unit that optimizes a recipe for a film formation process for forming films on the plurality of substrates and controls the gas supply unit and the temperature-controlled furnace, The control unit (a) generating a prediction model that predicts a process model showing a relationship between a temperature change amount and a film thickness change amount based on past evaluation data; (b) performing a pre-operational deposition process on the substrate; (c) determining whether the thickness of the film formed on the substrate by the film forming process is within an allowable range; (d) when it is determined in the step (c) that the result is outside the allowable range, calculating a recipe for the preliminary operation film formation process based on the prediction model in the step (b), and performing the preliminary operation film formation process again using the calculated recipe, and then returning to the step (c); (e) when it is determined in the step (c) that the result is within the allowable range, obtaining the recipe for the film formation process that falls within the allowable range. Heat treatment equipment.

Images