Data collection system, data collection device, data collection method, and program product

Abstract

In the exploration of processing conditions in substrate processing, appropriate data is collected. A data collection system has a first substrate processing device having a first processing space, a second substrate processing device having a second processing space, and a data collection device connected to the first and second substrate processing devices, has a correction amount calculation section that compares observation data observed by processing substrates of the same or similar shape in the first and second processing spaces under the same processing conditions, and calculates a correction amount for correcting the observation data observed by processing in the second processing space, and a collection section that corrects the observation data observed by processing in the second processing space based on the correction amount and collects the corrected observation data when processing conditions are explored by changing the processing conditions in the second processing space to process substrates.

Description

Technical Field

[0001] This disclosure relates to data collection systems, data collection devices, data collection methods, and data collection procedures. Background Technology

[0002] In the field of substrate processing apparatus, for example, by repeatedly conducting experiments while changing processing conditions, the optimal processing conditions are explored so that the shape of the processed substrate matches the target substrate shape.

[0003] [Existing Technical Documents]

[0004] [Patent Documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 2008-034877

[0006] [Patent Document 2] Japanese Patent Application Publication No. 2019-207951 Summary of the Invention

[0007] [The problem the invention aims to solve]

[0008] However, in existing substrate processing apparatuses, it is difficult to predict how to change processing conditions to approximate the target substrate shape because it is difficult to collect detailed data representing the state within the processing space. Therefore, in order to efficiently explore the optimal processing conditions, it is desirable to collect detailed data representing the state within the processing space.

[0009] Furthermore, for example, even if the optimal processing conditions explored using a substrate processing apparatus on a testing machine are applied to a substrate processing apparatus on a mass production machine, the target substrate shape may not always be obtained in the mass production machine due to the differences between the two. In such cases, further experimentation is required. Therefore, in order to effectively explore the optimal processing conditions, it is desirable to collect data equivalent to that used in mass production during experiments.

[0010] This disclosure provides a data collection system, data collection apparatus, data collection method, and data collection procedure for collecting appropriate data during the exploration of processing conditions in substrate processing.

[0011] [Methods for solving the problem]

[0012] A data collection system according to one aspect of this disclosure may, for example, have the following configuration:

[0013] A data collection system includes: a first substrate processing apparatus having a first processing space; a second substrate processing apparatus having a second processing space different from the first processing space; and a data collection apparatus connected to the first substrate processing apparatus and the second substrate processing apparatus.

[0014] The correction calculation unit compares observation data observed by processing substrates of the same or similar shape in the first and second processing spaces under the same processing conditions, and calculates a correction amount to correct the observation data observed by processing in the second processing space; and

[0015] The collection unit, when exploring processing conditions by changing processing conditions in the second processing space to process the substrate, corrects the observation data observed by processing in the second processing space based on the correction amount, and collects the corrected observation data.

[0016] [The effects of the invention]

[0017] A data collection system, data collection device, data collection method, and data collection procedure can be provided to collect appropriate data during the exploration of processing conditions in substrate processing. Attached Figure Description

[0018] Figure 1 This is a diagram showing the general structure and processing of the data collection system according to the first embodiment.

[0019] Figure 2 This is a diagram illustrating a specific example of the correction amount calculation process performed by the data collection system according to the first embodiment.

[0020] Figure 3 This is a diagram illustrating a specific example of the correction amount calculation process performed by the data collection system according to the first embodiment.

[0021] Figure 4 This is a diagram illustrating a specific example of data collection processing and condition change processing performed by the data collection system according to the first embodiment.

[0022] Figure 5 This is a diagram illustrating an example of data collection.

[0023] Figure 6 This is a diagram illustrating specific examples of virtual measurement model learning processing, shape simulation model learning processing, and conditional filtering processing performed by the data collection system according to the first embodiment.

[0024] Figure 7 This is a diagram illustrating a detailed example of the learning process of the virtual measurement model.

[0025] Figure 8 This is a diagram illustrating a detailed example of the shape simulation model's learning process.

[0026] Figure 9This is a diagram showing a detailed example of conditional filtering processing.

[0027] Figure 10 This is a diagram illustrating a specific example of virtual measurement processing and shape simulation processing performed by the data collection system according to the first embodiment.

[0028] Figure 11 This diagram illustrates an example of the hardware configuration of a data collection device and a data analysis device.

[0029] Figure 12 This is a diagram showing the general structure and processing of the data collection system according to the second embodiment.

[0030] Figure 13 This is a diagram illustrating a specific example of the correction amount calculation process performed by the data collection system according to the second embodiment.

[0031] Figure 14 This is a diagram illustrating a specific example of the correction amount calculation process performed by the data collection system according to the third embodiment. Detailed Implementation

[0032] Hereinafter, various embodiments will be described with reference to the accompanying drawings. Furthermore, in this specification and the accompanying drawings, components having substantially the same function are labeled with the same symbols, thereby omitting redundant descriptions.

[0033] [First Implementation]

[0034] <An overview of the structure and processing of data collection systems>

[0035] First, the configuration of the data collection system according to the first embodiment and the outline of the processes performed by the data collection system according to the first embodiment will be described. Figure 1 This is a diagram showing an outline of the structure and processing of the data collection system according to the first embodiment.

[0036] like Figure 1 As shown, the data collection system 100 includes:

[0037] • Substrate processing apparatus 110, as an example of a reference substrate processing apparatus

[0038] • Substrate processing apparatus A120, as an example of the first substrate processing apparatus

[0039] • Examples of the second substrate processing apparatus: substrate processing apparatus B131, substrate processing apparatus C132, and substrate processing apparatus D133

[0040] Data collection device 140

[0041] • Data parsing device 150.

[0042] The data collection system 100 is applicable, for example, to scenarios where a substrate processing device manufacturer supports a substrate manufacturer so that the substrate manufacturer can mass-produce substrates of the desired substrate shape.

[0043] The substrate processing apparatus 110 is, for example, a mass production machine installed in a substrate manufacturer. The substrate processing apparatus 110 has a reference chamber, which serves as a reference processing space, and processes substrates under specified processing conditions. Various observation sensors are mounted on the substrate processing apparatus 110, and output observation data observed by these sensors during substrate processing.

[0044] A substrate processing apparatus A120 is provided, for example, at a substrate processing apparatus manufacturer (similar to a mass production machine). The substrate processing apparatus A120 has a first chamber, which is an example of a first processing space identical to a reference processing space, and processes substrates under specified processing conditions. Various observation sensors are mounted on the substrate processing apparatus A120, and observation data observed by these sensors during substrate processing is output.

[0045] The substrate processing apparatus B131 is, for example, a so-called experimental machine installed by a substrate processing apparatus manufacturer. The substrate processing apparatus B131 has a second chamber, which is an example of a second processing space identical to a reference processing space, and processes substrates under specified processing conditions. Various observation sensors are mounted on the substrate processing apparatus B131, and observation data observed by these sensors during substrate processing is output. Furthermore, a plasma probe is additionally installed in the second chamber, and plasma measurement data measured by the plasma probe is output during substrate processing.

[0046] The substrate processing apparatus C132 is installed, for example, at a substrate processing apparatus manufacturer (experimental machine). The substrate processing apparatus C132 has a third chamber, which is an example of a second processing space identical to a reference processing space, and processes substrates under specified processing conditions. Various observation sensors are mounted on the substrate processing apparatus C132, and observation data observed by these sensors during substrate processing is output. Furthermore, a consumption sensor is additionally installed in the third chamber, and consumption measurement data, measured by the consumption sensor during substrate processing, indicating the consumption amount of components within the third chamber, is output.

[0047] The substrate processing apparatus D133 is installed, for example, at a substrate processing apparatus manufacturer (experimental machine). The substrate processing apparatus D133 has a fourth chamber, which is an example of a second processing space identical to a reference processing space, and processes substrates under specified processing conditions. Various observation sensors are mounted on the substrate processing apparatus D133, and observation data observed by these sensors during substrate processing is output. Additionally, a particle sensor is installed in the fourth chamber, and particle measurement data representing the particles within the fourth chamber, measured by the particle sensor during substrate processing, is output.

[0048] In addition, although Figure 1 It is not explicitly stated, but is described as follows: The data collection system 100 includes a shape measuring device for measuring the shape of a substrate before and after processing, and is configured to output the measured shape data.

[0049] The data collection device 140 is installed, for example, at a substrate processing apparatus manufacturer. The data collection device 140 is connected to each of the substrate processing apparatuses 110, A120, B131 to D133, and a shape measuring device (not shown).

[0050] Thus, the data collection device 140 collects the processing conditions used by each substrate processing device when processing the substrate, and the observation data observed by various observation sensors during the processing of the substrate by each substrate processing device.

[0051] In addition, the data collection device 140 collects shape data measured on the substrate before and after processing by each substrate processing device.

[0052] Furthermore, the data collection device 140 collects plasma measurement data, consumption measurement data, and particle measurement data measured by the plasma probe, consumption sensor, and particle sensor respectively during the substrate processing by the substrate processing devices B131 to D133.

[0053] The data analysis device 150 is installed, for example, at a substrate processing device manufacturer. The data analysis device 150 uses data collected by the data collection device 140 (referred to as collected data) to perform learning processing on various models.

[0054] The following is a summary description of the processes performed by the data collection system 100 (processes performed individually by each device constituting the data collection system 100 or in cooperation by multiple devices). Additionally, as... Figure 1 As shown, the processing performed by the data collection system 100 can be roughly divided into:

[0055] • "Experimental phase of exploring optimal conditions"

[0056] • "Processing phase based on optimal conditions".

[0057] The experimental phase for exploring optimal conditions is the phase where the optimal processing conditions for achieving the target substrate shape are explored. The processing phase based on optimal conditions refers to the phase where the substrate is processed under the explored optimal processing conditions. The following is a summary of the processing in each phase.

[0058] (1) Experimental phase for exploring optimal conditions

[0059] In step S161, the substrate processing apparatus 110, the substrate processing apparatus A120, and the data collection apparatus 140 perform correction amount calculation processing.

[0060] Specifically, substrate processing apparatus 110 and substrate processing apparatus A120 process substrates of the same or similar shape under the same processing conditions, thereby data collection apparatus 140 collects observation data observed by various observation sensors.

[0061] In addition, the data collection device 140 calculates a correction amount for correcting the difference in the observation data based on the "mechanical difference" between the substrate processing device 110 and the substrate processing device A120.

[0062] In the data collection device 140, the observation data output from the substrate processing device A120 is subsequently corrected based on the calculated correction amount. As a result, in the data collection device 140, the same observation data as that output by the substrate processing device A120 when processing a substrate of the same or similar shape under the same processing conditions can be collected from the substrate processing device A120.

[0063] In step S162, substrate processing apparatus A120, substrate processing apparatuses B131 to D133, and data collection apparatus 140 perform correction calculation processing. Specifically, substrate processing apparatus A120 and substrate processing apparatuses B131 to D133 process substrates of the same or similar shapes under the same processing conditions, thereby the data collection apparatus 140 collects observation data observed by various observation sensors.

[0064] In addition, the data collection device 140 calculates the correction amount to correct for the interference caused by the installation of the plasma probe in the second chamber by calculating the differences in various observation data collected by the substrate processing device A120 and the substrate processing device B131.

[0065] In the data collection device 140, the observation data output by the substrate processing device B131 is then corrected based on the calculated correction amount. As a result, in the data collection device 140, the same observation data as that collected when the substrate processing device A120 processes a substrate of the same or similar shape under the same processing conditions can be collected from the substrate processing device B131.

[0066] Similarly, the data collection device 140 calculates the correction amount to correct for the interference caused by the installation of the consumption sensor in the third chamber by calculating the differences in various observation data collected by the substrate processing device A120 and the substrate processing device C132.

[0067] In the data collection device 140, the observation data output by the substrate processing device C132 is then corrected based on the calculated correction amount. As a result, in the data collection device 140, the same observation data as that collected when the substrate processing device A120 processes a substrate of the same or similar shape under the same processing conditions can be collected from the substrate processing device C132.

[0068] Similarly, the data collection device 140 calculates the correction amount used to correct the interference caused by the installation of the particle sensor in the fourth chamber by calculating the differences in various observation data collected by the substrate processing device A120 and the substrate processing device D133.

[0069] In the data collection device 140, the observation data output by the substrate processing device D133 is then corrected based on the calculated correction amount. As a result, in the data collection device 140, the same observation data as that collected when the substrate processing device A120 processes a substrate of the same or similar shape under the same processing conditions can be collected from the substrate processing device D133.

[0070] In step S163, the data collection device 140 changes the processing conditions used by the substrate processing devices B131 to D133 when processing the substrate in order to explore the optimal processing conditions for achieving the target substrate shape. Furthermore, the data collection device 140 sets the modified processing conditions for the substrate processing devices B131 to D133.

[0071] In step S164, substrate processing apparatus B131 to substrate processing apparatus D133 and data collection apparatus 140 perform data collection processing.

[0072] Specifically, substrate processing apparatuses B131 to D133 process substrates of the same or similar shape under modified processing conditions, and output various observation data, plasma measurement data, consumption measurement data, and particle measurement data. Additionally, a shape measurement device (not shown) outputs shape data of the substrate before processing and shape data of the substrate after processing.

[0073] In addition, the data collection device 140 corrects various observation data using correction amounts and collects the corrected observation data. Furthermore, the data collection device 140 collects plasma measurement data output from the substrate processing device B131, consumption measurement data output from the substrate processing device C132, and particle measurement data output from the substrate processing device D133 (these are referred to as "various measurement data"). Furthermore, the data collection device 140 collects shape data of the substrate before processing and shape data of the substrate after processing output from a shape measurement device (not shown) (these are referred to as "various shape data").

[0074] Furthermore, the data collection device 140 displays the collected data (previous processing conditions, various observation data, various measurement data, and various shape data) to the experimenter. Thus, the experimenter can refer not only to the various observation data but also to the various measurement data, which are detailed data representing the state within the chamber, while simultaneously observing the various shape data. As a result, as the next processing condition, the experimenter can set more appropriate processing conditions to approximate the target substrate shape, and can efficiently explore the optimal processing conditions.

[0075] In addition, the condition change processing in step S163 and the data collection processing in step S164 are repeated. Furthermore, after repeating the process a predetermined number of times, the correction amount calculation processing in step S162 is performed. This is because the various measurement data output from the substrate processing apparatus B131 to the substrate processing apparatus D133 change over time, so by periodically updating the correction amount, the influence of interference can always be eliminated.

[0076] Thus, by performing correction calculation processing (step S161) and correction calculation processing (step S162), in the data collection device 140, during the exploration of optimal processing conditions, the following influences can be eliminated:

[0077] • The effect of mechanical difference

[0078] • The impact of interference

[0079] The observation data (which is the same as the observation data output by the substrate processing device 110, which is a mass production machine) is collected by substrate processing devices B131 to D133.

[0080] When a certain amount of data is collected by repeatedly executing the condition change processing in step S163 and the data collection processing in step S164, in step S165, the data parsing device 150 uses the collected data to perform learning processing on the virtual measurement model. The virtual measurement model is a model based on various observation data to predict various measurement data (plasma measurement data, consumption measurement data, particle measurement data) during substrate processing.

[0081] In the data analysis device 150, various observation data are used as input data, and various measurement data are used as forward solution data for learning processing. Thus, the data analysis device 150 can generate a learned virtual measurement model.

[0082] In addition, the generated virtual measurement model is mounted on a substrate processing device 110 that does not have a plasma probe, consumption sensor, or particle sensor installed.

[0083] Therefore, in the substrate processing apparatus 110, when processing the substrate in the "processing stage based on optimal conditions", it is possible to predict plasma measurement data, consumption measurement data, particle measurement data, etc. based on various observation data and display them to the operator.

[0084] In step S166, the data parsing device 150 uses the collected data to perform learning processing on the shape simulation model. The shape simulation model is a model that predicts the shape data of the substrate after processing.

[0085] In the data analysis device 150, various observation data, various measurement data, processing conditions, and the shape data of the substrate before processing are used as input data, and the shape data of the substrate after processing is used as forward retrieval data for learning processing. As a result, a learned shape simulation model is generated in the data analysis device 150.

[0086] In this way, by including not only various observation data but also various measurement data in the input data for learning processing, a learned shape simulation model with high prediction accuracy can be generated.

[0087] The generated, learned shape simulation model is mounted on the substrate processing apparatus 110, for example. Thus, in the substrate processing apparatus 110, during the "processing stage based on optimal conditions", the shape data of the processed substrate can be predicted.

[0088] Furthermore, at this moment (the moment when step S166 ends), if the target substrate shape is not achieved (if the difference from the target substrate shape is above a predetermined threshold), the processing conditions are changed and the optimal processing conditions are explored.

[0089] Specifically, firstly, in step S167, the substrate processing apparatus A120, substrate processing apparatuses B131 to D133, and data collection apparatus 140 perform correction amount calculation processing. Furthermore, the correction amount calculation processing in step S167 is the same as the correction amount calculation processing in step S162, therefore, its description is omitted here.

[0090] In step S168, the data collection device 140 and the data parsing device 150 use the learned shape simulation model generated in step S166 to perform conditional filtering processing of the filtering conditions.

[0091] Specifically, the data analysis device 150 uses the learned shape simulation model to predict the shape data of the processed substrate, thereby selecting processing conditions to approximate the target substrate shape.

[0092] In addition, in parallel, the data parsing device 150 filters out processing conditions for which no collected data has been obtained in order to improve the prediction accuracy of the learned shape simulation model.

[0093] Therefore, the data analysis device 150 sets the modified processing conditions in the substrate processing apparatus B131 to substrate processing apparatus D133, either from the perspective of exploring the optimal processing conditions or from the perspective of improving prediction accuracy.

[0094] In step S169, substrate processing apparatuses B131 to D133 and data collection apparatus 140 perform data collection processing. Furthermore, the data collection processing in step S169 is the same as that in step S164, therefore, its description is omitted here.

[0095] Furthermore, the condition filtering process in step S168 and the data collection process in step S169 are executed repeatedly in the same way as the condition change process in step S163 and the data collection process in step S164. However, unlike steps S163 and S164, because the processing conditions are appropriately filtered in step S168, the speed at which the optimal processing conditions are approached is accelerated (that is, the optimal processing conditions can be explored more efficiently).

[0096] In addition, similar to step S162, if the substrate processing is repeated a predetermined number of times based on the changed processing conditions, the correction amount calculation process in step S167 is performed to correct the effects of time-dependent changes in various observation data output from substrate processing apparatus B131 to substrate processing apparatus D133.

[0097] In this way, by repeatedly processing the substrate while changing the processing conditions, if the target substrate shape is reached (the error between the target substrate shape and the target substrate shape is less than a predetermined threshold), the processing conditions at the time of reaching that shape are determined as the optimal processing conditions. Thus, the experimental phase for exploring the optimal conditions ends.

[0098] When the experimental phase for exploring optimal conditions ends, the process moves to the "processing phase based on optimal conditions". In the processing phase based on optimal conditions, the substrate is processed under optimal processing conditions using a substrate processing apparatus 110 equipped with a learned virtual measurement model and a learned shape simulation model generated in the experimental phase for exploring optimal conditions.

[0099] In addition, such as Figure 1 As shown, in step S171, when the substrate processing apparatus 110 processes the substrate under optimal processing conditions, it performs virtual measurement processing. Here, various observation data observed during substrate processing are input into the learned virtual measurement model to predict various measurement data (plasma measurement data, consumption measurement data, particle measurement data). Furthermore, the predicted measurement data are displayed to the operator, etc.

[0100] As a result, operators are able to monitor plasma measurement data, consumption measurement data, and particle measurement data that were previously impossible to monitor when processing substrates.

[0101] In step S172, when the substrate is processed under optimal processing conditions, the substrate processing apparatus 110 performs shape simulation processing. As a result, various observation data observed during substrate processing, various predicted measurement data, processing conditions, and the shape data of the substrate before processing are input into the learned shape simulation model. Furthermore, the learned shape simulation model predicts the shape data of the substrate after processing, and the predicted shape data is displayed to the operator, etc.

[0102] As a result, operators can determine the quality of the processed substrates even without performing a full inspection.

[0103] <Specific examples of processing performed by the data collection system>

[0104] Next, specific examples of the processes performed by the data collection system 100 will be described.

[0105] (1) Specific example of correction amount calculation and processing (step S161)

[0106] First, a specific example of the correction amount calculation process (step S161) performed by the data collection system 100 will be explained. Figure 2This is a diagram illustrating a specific example of the correction amount calculation process performed by the data collection system according to the first embodiment.

[0107] Figure 2 The example illustrates a scenario where substrate processing apparatus 110 and substrate processing apparatus A120 process substrates of the same or similar shape before processing based on processing condition "condition 0", thereby outputting observation data "observation data M_α0" and "observation data M_A0" respectively.

[0108] In addition, a data collection program is installed in the data collection device 140. By executing this program, the data collection device 140 can perform the following functions:

[0109] • Calibration Calculation Unit 210

[0110] • Correction Calculation Unit 220

[0111] Collection Department 230

[0112] • Conditions Change Department 240.

[0113] In the correction amount calculation process (step 161), the data collection device 140 activates the correction amount calculation unit 210 to acquire the observation data "Observation data M_α0" output from the substrate processing device 110. Additionally, the correction amount calculation unit 210 acquires the observation data "Observation data M_A0" output from the substrate processing device A120. Furthermore, the correction amount calculation unit 210 calculates a correction amount 'a' to make the observation data "Observation data M_A0" consistent with the observation data "Observation data M_α0". The correction amount calculation unit 210 then notifies the correction amount calculation unit 220 of the calculated correction amount 'a'.

[0114] (2) Specific example of correction amount calculation and processing (step S162)

[0115] Next, a specific example of the correction calculation process (step S162) performed by the data collection system 100 will be described. Figure 3 This is a diagram illustrating a specific example of the correction amount calculation process performed by the data collection system according to the first embodiment.

[0116] Figure 3 An example is shown in the following situation: Substrate processing apparatus A120 and substrate processing apparatuses B131 to D133 process substrates of the same shape before processing based on processing condition = "condition 1", thereby outputting observation data = "observation data M_A1" to "observation data M_D1" respectively.

[0117] In the correction amount calculation process (step S162), the data collection device 140 activates the correction amount calculation unit 220 to obtain the observation data "observation data M_A1" to "observation data M_D1" output from the substrate processing device A120 and the substrate processing devices B131 to D133.

[0118] In addition, the correction calculation unit 220 uses the correction amount a to correct the obtained observation data = "observation data M_A1" and generates corrected observation data.

[0119] In addition, the correction calculation unit 220 calculates the correction amount b used to make the observation data "observation data M_B1" consistent with the corrected observation data, and notifies the collection unit 230.

[0120] Similarly, the correction calculation unit 220 calculates the correction amount c used to make the observation data = "observation data M_C1" consistent with the corrected observation data, and notifies the collection unit 230.

[0121] Similarly, the correction calculation unit 220 calculates the correction amount d used to make the observation data = "observation data M_D1" consistent with the corrected observation data, and notifies the collection unit 230.

[0122] (3) Specific examples of condition change processing (step S163) and data collection processing (step S164)

[0123] Next, specific examples of the condition change processing (step S163) and data collection processing (step S164) performed by the data collection system 100 will be described. Figure 4 This is a diagram illustrating a specific example of data collection processing and condition change processing performed by the data collection system according to the first embodiment.

[0124] In the condition change processing (step S163), the data collection device 140 causes the condition change unit 240 to operate. Figure 4 The example illustrates the situation where the condition change unit 240 sends the processing conditions = "condition 2", "condition 3", ... sequentially to the substrate processing apparatus B131, substrate processing apparatus C132, and substrate processing apparatus D133.

[0125] In addition, Figure 4 The example represents the following situation:

[0126] The substrate processing apparatus B131 processes substrates of the same shape before processing based on processing conditions "condition 2", "condition 3", ... and outputs them respectively:

[0127] • Observation data = "Observation data M_B2", "Observation data M_B3", ...

[0128] • Measurement data = "Measurement data I_B2", "Measurement data I_B3", ...

[0129] in addition, Figure 4 Examples represent the following situations:

[0130] Processed by the substrate processing apparatus B131, according to:

[0131] • Shape data = "Shape data S_B2", "Shape data S_B3", ... Substrate before processing

[0132] generate:

[0133] • The processed substrate with shape data = "shape data S_B2'", "shape data S_B3'", ...

[0134] Similarly, in Figure 4 The example represents the following situation:

[0135] The substrate processing apparatus C132 processes substrates of the same shape before processing based on processing conditions "condition 2", "condition 3", ..., thereby outputting the following respectively:

[0136] • Observation data = "Observation data M_C2", "Observation data M_C3", ...

[0137] • Measurement data = "Measurement data I_C2", "Measurement data I_B3", ...

[0138] in addition, Figure 4 Examples represent the following situations:

[0139] Processed by the substrate processing apparatus C132, according to:

[0140] • The substrate before processing of shape data "shape data S_C2", "shape data S_C3", ...

[0141] generate:

[0142] • Shape data = “Shape data S_C2'”, “Shape data S_C3'”, ... processed substrate.

[0143] same, Figure 4 The example represents the following situation:

[0144] The substrate processing apparatus D133 processes substrates of the same shape before processing based on processing conditions "condition 2", "condition 3", ..., thereby outputting the following:

[0145] • Observation data = "Observation data M_D2", "Observation data M_D3", ...

[0146] • Measurement data = "Measurement data I_D2", "Measurement data I_D3", ...

[0147] in addition, Figure 4 Examples represent the following situations:

[0148] Processed by the substrate processing apparatus D133, according to:

[0149] • The substrate before processing, containing shape data such as "shape data S_D2", "shape data S_D3", etc.

[0150] generate:

[0151] • The processed substrate with shape data = "shape data S_D2'", "shape data S_D3'", ...

[0152] Additionally, in the data collection and processing (step S164), the data collection device 140 activates the collection unit 230. For example... Figure 4 As shown, the collection unit 230 has storage units 401, 403, 405 and correction storage units 402, 404, 406.

[0153] exist Figure 4 The example represents the following situation:

[0154] Storage unit 401 will:

[0155] • The shape data of the substrate before processing is "shape data S_B2", "shape data S_B3", ...

[0156] • The processed substrate shape data = "shape data S_B2'", "shape data S_B3'", ...

[0157] Stored in the data collection and storage unit 250.

[0158] in addition, Figure 4 An example is shown in the following scenario: the correction storage unit 402 uses the correction amount b to correct the observation data = "observation data M_B2", "observation data M_B3", ..., and stores the corrected observation data in the collection data storage unit 250. Alternatively, the correction storage unit 402 stores the measurement data = "measurement data I_B2", "measurement data I_B3", ... in the collection data storage unit 250.

[0159] Similarly, in Figure 4 In the example, storage unit 403 represents the following situation:

[0160] Will:

[0161] • The shape data of the substrate before processing is "shape data S_C2", "shape data S_C3", ...

[0162] • The processed substrate shape data = "shape data S_C2'", "shape data S_C3'", ...

[0163] Stored in the data collection and storage unit 250.

[0164] in addition, Figure 4 The example illustrates a scenario where the correction storage unit 404 corrects the observation data = "Observation data M_C2", "Observation data M_C3", ... using the correction amount c, and stores the corrected observation data in the collection data storage unit 250. Alternatively, it illustrates a scenario where the correction storage unit 404 stores the measurement data = "Measurement data I_C2", "Measurement data I_C3", ... in the collection data storage unit 250.

[0165] Similarly, in Figure 4 The example represents the following situation:

[0166] Storage Unit 405 will:

[0167] • The shape data of the substrate before processing = "shape data S_D2", "shape data S_D3", ...

[0168] • The processed substrate shape data = "shape data S_D2'", "shape data S_D3'", ...

[0169] The status is stored in the data collection unit 250.

[0170] in addition, Figure 4 An example is shown in the following scenario: the correction storage unit 406 corrects the observation data = "observation data M_D2", "observation data M_D3", ... using the correction amount d, and stores the corrected observation data in the collection data storage unit 250. Alternatively, the correction storage unit 406 stores the measurement data = "measurement data I_D2", "measurement data I_D3", ... in the collection data storage unit 250.

[0171] Next, the collected data stored in the data storage unit 250 will be explained. Figure 5 This is a diagram illustrating an example of data collection.

[0172] like Figure 5 As shown, among the collected data 500, the items that are information include "processing conditions", "observation data", "measurement data", "substrate shape data before processing" and "substrate shape data after processing".

[0173] The "Processing Conditions" section stores settings such as the power of the high-frequency power supply, the power of the low-frequency power supply, the pressure inside the chamber, the temperature inside the chamber, the gas flow rate, and the type of gas. The Processing Conditions are defined as "Condition 2", "Condition 3", ... "Condition x", and consist of at least any one of these different combinations of settings.

[0174] The "Observation Data" stores observations such as DC self-bias voltage, potential difference, reflected wave power, gas flow rate, plasma density, ion energy, and ion flow rate. The "Observation Data" sets, such as "Observation Data M_B1", "Observation Data M_C1", and "Observation Data M_D1", are combinations of these observations.

[0175] The "Measurement Data" section stores measurement values ​​from additionally installed sensors, such as plasma measurement data, consumption measurement data, and particle measurement data. Specifically, measurement data for plasma measurement is included in Measurement Data="Measurement Data I_B1". Measurement data for consumption measurement is included in Measurement Data="Measurement Data I_C1". Measurement data for particle measurement is included in Measurement Data="Measurement Data I_D1".

[0176] The "Pre-processing Substrate Shape Data" stores shape values ​​such as boundary dimensions, depth, cone angle, tilt angle, and curvature. The "Pre-processing Substrate Shape Data" from "Shape Data S_B2" to "Shape Data S_D2" are each composed of combinations of these shape values.

[0177] The "Processed Substrate Shape Data" stores shape values ​​such as boundary dimensions, depth, taper angle, tilt angle, and curvature. The processed substrate shape data "Shape Data S_B2" to "Shape Data S_D2" are each composed of combinations of these shape values.

[0178] (4) Specific examples of virtual measurement model learning processing (step S165), shape simulation model learning processing (step S166), and conditional filtering processing (step S168)

[0179] (4-1) Specific examples (outline)

[0180] Next, specific examples (summaries) of the virtual measurement model learning process (step S165), shape simulation model learning process (step S166), and conditional filtering process (step S168) performed by the data collection system 100 will be described.

[0181] Figure 6 This is a diagram illustrating specific examples of virtual measurement model learning processing, shape simulation model learning processing, and conditional filtering processing performed by the data collection system according to the first embodiment.

[0182] A data parsing program is installed in the data parsing device 150. By executing this program, the data parsing device 150 performs the following functions:

[0183] Virtual Measurement Model Learning Department 610

[0184] Shape Simulation Model Learning Department 630

[0185] • Completed learning of shape simulation model 640

[0186] • Shape simulation control unit 650 (an example of a control unit and a determination unit).

[0187] In the virtual measurement model learning process (step S165), the data parsing device 150 activates the virtual measurement model learning unit 610 to read the collected data 500 stored in the collected data storage unit 250. Furthermore, the virtual measurement model learning unit 610 uses the read collected data 500 to perform learning processing on the virtual measurement model.

[0188] In addition, the learned virtual measurement model 620, which is generated by the virtual measurement model learning unit 610 through learning processing of the virtual measurement model, is mounted on the substrate processing device 110.

[0189] On the other hand, in the shape simulation model learning process (step S166), the data parsing device 150 activates the shape simulation model learning unit 630 to read the collected data 500 stored in the collected data storage unit 250. Furthermore, the shape simulation model learning unit 630 uses the read collected data 500 to perform learning processing on the shape simulation model.

[0190] Furthermore, the learned shape simulation model 640, generated through learning processing by the shape simulation model learning unit 630, is mounted on the substrate processing apparatus 110. Additionally, the learned shape simulation model 640 is processed by the shape simulation control unit 650 in the conditional filtering process (step S168).

[0191] Specifically, in the condition filtering process (step S168), the shape simulation control unit 650 operates in the data analysis device 150. Under various processing conditions, the shape simulation control unit 650 executes the learned shape simulation model and obtains a prediction result for the shape data of the processed substrate. Furthermore, the shape simulation control unit 650 filters processing conditions that can achieve the target substrate shape by comparing the shape data of the processed substrate (as the prediction result) with the target substrate shape. Then, the filtered processing conditions are notified to the condition modification unit 240 of the data collection device 140. Thus, the condition modification unit 240 can set the modified processing conditions, selected from the perspective of exploring optimal processing conditions, as modified processing conditions in substrate processing devices B131 to D133.

[0192] Furthermore, the shape simulation control unit 650 determines the processing conditions not used in the learning process of the shape simulation model by referring to the collected data 500 stored in the collected data storage unit 250. Then, the shape simulation control unit 650 notifies the condition modification unit 240 of the determined processing conditions. As a result, the condition modification unit 240 sets the processing conditions determined by the shape simulation control unit 650 as modified processing conditions in the substrate processing apparatus B131 to D133. Consequently, data collection processing is performed in the substrate processing apparatus B131 to D133 and the data collection device 140 (step S169), and the collected data 500 in the collected data storage unit 250 newly stores the following data corresponding to the determined processing conditions:

[0193] Various observation data

[0194] Various measurement data

[0195] • Various shape data (substrate shape data before processing, substrate shape data after processing).

[0196] In the shape simulation control unit 650, the learned shape simulation model is relearned using the determined processing conditions and newly stored various observation data, various measurement data, and various shape data (substrate shape data before processing and substrate shape data after processing). Furthermore, the shape simulation control unit 650 repeatedly performs the determination of processing conditions and the relearning process. At this time, the shape simulation control unit 650 identifies processing conditions with low prediction accuracy and notifies the condition modification unit 240 of these low-precision conditions (that is, it selects processing conditions for relearning the learned shape simulation model). Therefore, the condition modification unit 240 can set modified processing conditions, selected from the viewpoint of improving the prediction accuracy of the learned shape simulation model 640, as modified processing conditions in substrate processing apparatuses B131 to D133.

[0197] (4-2) Detailed specific example (virtual measurement model learning processing (step S165))

[0198] Next, a more detailed example of the virtual measurement model learning process (step S165) will be described. Figure 7 This is a diagram illustrating a detailed example of the learning process of the virtual measurement model.

[0199] like Figure 7 As shown, the virtual measurement model learning unit 610 includes a virtual measurement model 710 and a comparison / change unit 720.

[0200] In the virtual measurement model 710, the set values ​​stored in the "processing conditions" of the collected data 500 and the observed values ​​stored in the "observation data" are used as input data. Therefore, the virtual measurement model 710 outputs output data.

[0201] On the other hand, the measured values ​​stored in the "measurement data" of the collected data 500 are input as positive solution data to the comparison / modification unit 720. In the comparison / modification unit 720, the error is calculated by comparing the output data output from the virtual measurement model 710 with the measured values ​​input as positive solution data, and the model parameters of the virtual measurement model 710 are updated based on the calculated error. As a result, the virtual measurement model learning unit 610 is able to generate the learned virtual measurement model 620.

[0202] (4-2) Detailed specific example (shape simulation model learning processing (step S166))

[0203] Next, a more detailed example of the shape simulation model learning process (step S166) will be explained. Figure 8 This is a diagram illustrating a detailed example of the shape simulation model's learning process.

[0204] like Figure 8 As shown, the shape simulation model learning unit 630 includes a shape simulation model 810 and a comparison / modification unit 820.

[0205] In the shape simulation model 810, the set values ​​stored in the "processing conditions" of the collected data 500, the observed values ​​stored in the "observation data", the measured values ​​stored in the "measurement data", and the shape values ​​stored in the "substrate shape data before processing" are used as input data. As a result, the shape simulation model 810 outputs output data.

[0206] On the other hand, the shape values ​​stored in the "processed substrate shape data" of the collected data 500 are input as forward solving data into the comparison / modification unit 820. In the comparison / modification unit 820, the error is calculated by comparing the output data output from the shape simulation model 810 with the shape values ​​input as forward solving data, and the model parameters of the shape simulation model 810 are updated based on the calculated error. As a result, the learned shape simulation model 640 can be generated in the shape simulation model learning unit 630.

[0207] (4-3) Detailed examples (details of conditional filtering process (step S168))

[0208] Next, a more detailed example of the conditional filtering process (step S168) will be explained. Figure 9 This is a diagram showing the details of a specific example of conditional filtering.

[0209] like Figure 9 As shown in the lower right corner, the shape simulation control unit 650 executes the learned shape simulation model based on the processing conditions = "condition 101", "condition 102", ... . As a result, the shape simulation control unit 650 obtains the shape data ("shape data S101", "shape data S102", ...) of the processed substrate predicted by the learned shape simulation model 640.

[0210] Furthermore, the shape simulation control unit 650 compares the acquired shape data ("shape data S101", "shape data S102", ...) with the shape data of the target substrate shape, and filters out processing conditions that can realize the target substrate shape. Then, the filtered processing conditions are notified to the condition modification unit 240 of the data collection device 140.

[0211] Figure 9 The example illustrates how, by filtering processing conditions from the perspective of exploring optimal processing conditions, the case where processing condition = "condition x" is ultimately found to be the optimal processing condition.

[0212] In addition, the shape simulation control unit 650 refers to the collected data 500 stored in the collected data storage unit 250 to determine the processing conditions that were not used in the learning process of the shape simulation model.

[0213] Figure 9 The dashed area 900 shown in the lower left corner schematically represents the range that can be explored as a processing condition. On the other hand, in Figure 9 In the diagram, the solid line region 910 schematically represents the range (interpolation range) used in the learning process of the shape simulation model.

[0214] As described above, in the shape simulation control unit 650, from the viewpoint of improving the prediction accuracy of the learned shape simulation model 640, processing conditions with low prediction accuracy that were not used in the learning process of the shape simulation model are selected.

[0215] Figure 9 The example illustrates the case where the shape simulation control unit 650 filters the solid line region 920 from the region outside the solid line region 910 within the dashed line region 900.

[0216] in addition, Figure 9 The example represents the situation where the shape simulation control unit 650 notifies the condition change unit 240 of "condition x+1", "condition x+2", ... as processing conditions contained in the solid line area 920, and inputs them into the learned shape simulation model 640.

[0217] Therefore, after learning the shape simulation model 640, the following will be the basis:

[0218] • Processing conditions = "condition x+1", "condition x+2", ...

[0219] • Processing conditions = "condition x+1", "condition x+2", ...

[0220] The various observation data, various measurement data, and pre-processing substrate shape data obtained from substrate processing apparatuses B131 to D133 during substrate processing are used as input data, and will be based on the following:

[0221] • Processing conditions = "condition x+1", "condition x+2", ...

[0222] The shape data of the substrate after processing by the substrate processing apparatus B131 to substrate processing apparatus D133 is used as forward retrieval data, which can be used to relearn the learned shape simulation model 640.

[0223] (5) Specific examples of virtual measurement processing (step S171) and shape simulation processing (step S172)

[0224] Next, specific examples of the virtual measurement process (step S171) and shape simulation process (step S172) performed by the data collection system 100 will be described. Figure 10 This is a diagram illustrating a specific example of virtual measurement processing and shape simulation processing performed by the data collection system according to the first embodiment.

[0225] Figure 10 The example illustrates the case where, when processing the substrate under the condition "condition x", the output observation data is "observation data M_αx". Additionally, Figure 10The example illustrates the scenario where various observational data are input into the learned virtual measurement model 620 to predict plasma measurement data, consumption measurement data, and particle measurement data, and output measurement data = "measurement data I_αx".

[0226] In this way, by outputting "Measurement Data I_αx" which includes plasma measurement data, consumption measurement data, and particle measurement data, operators and others can monitor measurement data that were previously impossible to monitor.

[0227] in addition, Figure 10 The example illustrates the case where the processing condition "condition x", observation data "observation data M_αx", measurement data "measurement data I_αx", and pre-processing substrate shape data "shape data S_αx" are input into the learned shape simulation model 640. Furthermore, Figure 10 The example illustrates the case where the processed substrate shape data = "shape data S_αx'" is output from the learned shape simulation model 640.

[0228] In this way, by predicting the shape data of the processed substrate, operators can determine the quality of the processed substrate even without inspecting all of them.

[0229] <Hardware Composition of Data Collection and Data Analysis Devices>

[0230] Next, the hardware configuration of the data collection device 140 and the data parsing device 150 will be described. Figure 11 This diagram illustrates an example of the hardware configuration of a data collection device and a data analysis device.

[0231] (1) Data collection device

[0232] like Figure 11 As shown in 11a, the data collection device 140 includes a processor 1101, a memory 1102, an auxiliary storage device 1103, an I / F (interface) device 1104, a communication device 1105, and a drive device 1106. Furthermore, the various hardware components of the data collection device 140 are interconnected via a bus 1107.

[0233] The processor 1101 has various computing devices such as CPU (Central Processing Unit) and GPU (Graphics Processing Unit). The processor 1101 reads various programs (e.g., data collection programs) into memory 1102 and executes them.

[0234] The memory 1102 includes main storage devices such as ROM (Read-Only Memory) and RAM (Random Access Memory). The processor 1101 and the memory 1102 form a so-called computer, whereby the processor 1101 executes various programs read from the memory 1102, thereby enabling the computer to perform the aforementioned functions.

[0235] The auxiliary storage device 1103 stores various programs and various data used by the processor 1101 when these programs are executed. The aforementioned data collection and storage unit 250 is implemented in the auxiliary storage device 1103.

[0236] I / F device 1104 is a connection device that connects display device 1108, operation device 1109 and data collection device 140.

[0237] The communication device 1105 is a communication device used to communicate with the substrate processing device 110, substrate processing device A120, substrate processing devices B131 to D133, shape measuring device 1110, data parsing device 150, etc. via a network.

[0238] The drive unit 1106 is a device for setting the recording medium 1111. The recording medium 1111 referred to here includes media that record information optically, electrically, or magnetically, such as CD-ROMs, floppy disks, and optical discs. Alternatively, the recording medium 1111 may also include semiconductor memories that electrically record information, such as ROMs and flash memory.

[0239] Additionally, various programs installed in the auxiliary storage device 1103 can be installed, for example, by placing the distributed recording medium 1111 in the drive device 1106 and reading the various programs recorded on the recording medium 1111. Alternatively, they can be installed by downloading the various programs installed in the auxiliary storage device 1103 from the network via the communication device 1105.

[0240] (2) Data parsing device

[0241] like Figure 11 As shown in 11b, the hardware configuration of the data parsing device 150 is the same as that of the data collection device 140. Therefore, the differences between the data parsing device 150 and the data collection device 140 will be explained here.

[0242] In the case of the data parsing device 150, the processor 1121 reads the data parsing program into the memory 1122 and executes it.

[0243] In addition, in the case of the data parsing device 150, the communication device 1125 communicates with the substrate processing device 110 and the data collection device 140.

[0244] <Summary>

[0245] As can be seen from the above description, the collection system according to the first embodiment is:

[0246] • It includes: a substrate processing apparatus A having a first chamber, substrate processing apparatuses B to D having a second chamber different from the first chamber, and a data collection device 140 connected to substrate processing apparatus A and substrate processing apparatuses B to D.

[0247] • By comparing various observation data observed under the same conditions in the first and second chambers respectively, the correction amount for the various observation data observed by processing in the second chamber is calculated.

[0248] • When exploring the optimal processing conditions by processing the substrate while changing the processing conditions in the second chamber, the observation data observed during processing in the second chamber is corrected according to the correction amount, and the corrected observation data is collected.

[0249] Thus, according to the collection system of the first embodiment, multiple substrate processing devices are used to process substrates of the same or similar shapes under the same conditions, and observation data corrected for the effects of interference are collected. Therefore, according to the first embodiment, in the exploration of processing conditions during substrate processing, appropriate (with the effects of interference eliminated) various observation data can be collected.

[0250] Furthermore, according to the collection system of the first embodiment:

[0251] • The first chamber is configured identically to the reference chamber of the reference substrate processing device.

[0252] • Calculate the correction amount based on mechanical difference based on various observation data obtained by processing substrates of the same or similar shape in the reference chamber and the first chamber under the same conditions.

[0253] Therefore, according to the first embodiment, in the exploration of processing conditions in substrate processing, it is possible to collect appropriate (excluding the influence of mechanical differences) various observation data.

[0254] The collection system according to the first embodiment also includes:

[0255] • In each of the second chambers of the substrate processing apparatus B to D, a plasma probe, a consumption sensor, and a particle sensor are additionally installed to collect and display various measurement data (plasma measurement data, consumption measurement data, and particle measurement data) during substrate processing.

[0256] Therefore, according to the first embodiment, while referring to various measurement data that represent detailed data of the state inside the chamber, the processing conditions can be changed, and the optimal processing conditions can be explored efficiently.

[0257] Furthermore, according to the collection system of the first embodiment:

[0258] • Generate a virtual measurement model that has completed learning various measurement data in the prediction substrate processing.

[0259] • It learns and processes various measurement data, including those from substrate processing, to generate a learned shape simulation model.

[0260] This improves the prediction accuracy of the learned shape simulation model. Furthermore, the learned shape simulation model can be used to filter processing conditions, enabling efficient exploration of optimal processing conditions.

[0261] Furthermore, according to the collection system of the first embodiment:

[0262] • The generated virtual measurement model and the learned shape simulation model are mounted on the substrate processing device of the mass production machine.

[0263] Therefore, when processing substrates in the substrate processing apparatus of a mass production machine, it is possible to monitor various measurement data that were previously impossible to monitor. In addition, it is possible to predict and display the shape data of the processed substrates, so that the quality of the processed substrates can be determined even without performing a full inspection of all processed substrates.

[0264] [Second Implementation]

[0265] In the data collection system 100 according to the first embodiment described above, it is described that a substrate processing apparatus A (mass production machine) identical to the substrate processing apparatus (reference substrate processing apparatus) provided at the substrate manufacturer is installed at the substrate processing apparatus manufacturer. However, the configuration of the data collection system is not limited to this; for example, the data collection system may be configured without installing the substrate processing apparatus A at the substrate processing apparatus manufacturer. Hereinafter, the data collection system according to the second embodiment will be described.

[0266] <An overview of the structure and processing of data collection systems>

[0267] First, an overview of the configuration of the data collection system according to the second embodiment and the processes performed by the data collection system according to the second embodiment will be described. Figure 12 This is a diagram showing the general structure and processing of the data collection system according to the second embodiment.

[0268] like Figure 12 As shown, the data collection system 1200 includes:

[0269] • Substrate processing apparatus A1210, as an example of the first substrate processing apparatus

[0270] • Examples of the second substrate processing apparatus: substrate processing apparatus B131, substrate processing apparatus C132, and substrate processing apparatus D133

[0271] Data collection device 140

[0272] • Data parsing device 150.

[0273] In addition, for ease of explanation in this embodiment, the substrate processing apparatus A1210 is provided instead of the substrate processing apparatus 110 in a system configuration at the substrate manufacturer.

[0274] The data collection system 1200 is the same as in the first embodiment described above. For example, it is used in a scenario where a substrate processing device manufacturer supports a substrate manufacturer, so that the substrate manufacturer can mass-produce substrates of the desired substrate shape.

[0275] The substrate processing apparatus A1210 is installed, for example, at a substrate manufacturer (mass production machine). The substrate processing apparatus A1210 has a first chamber and processes substrates under specified processing conditions. Various observation sensors are mounted on the substrate processing apparatus A1210, and the apparatus outputs observation data observed by these sensors during substrate processing.

[0276] in addition, Figure 12 The substrate processing apparatus B131 to D133, data collection device 140, and data parsing device 150 shown are... Figure 1 The same applies, so the explanation is omitted here.

[0277] Furthermore, the treatments included in the "experimental phase for exploring optimal conditions" are identical to those in step S161, except that they do not include the correction calculation treatment. Figure 1 The same applies, so the explanation is omitted here.

[0278] Furthermore, the processes included in the "processing stage based on optimal conditions" are also, except that they are performed by the substrate processing apparatus A1210, and similar to... Figure 1 The same applies, so the explanation is omitted here.

[0279] <Specific examples of processing performed by the data collection system>

[0280] Next, a specific example of the correction calculation process (step S162) performed by the data collection system 1200 will be described.

[0281] (1) Specific example of correction amount calculation and processing (step S162)

[0282] Figure 13 This is a diagram illustrating a specific example of the correction amount calculation process performed by the data collection system according to the second embodiment.

[0283] Figure 13 An example is shown in the following scenario: Substrate processing apparatus A120 and substrate processing apparatuses B131 to D133 process substrates of the same or similar shape before processing, based on processing condition = "Condition 1". Furthermore, Figure 13 An example is shown in the following situation: observation data "observation data M_A1" to "observation data M_D1" are output from substrate processing device A120 and substrate processing devices B131 to D133 respectively.

[0284] and Figure 3 The difference is that, in Figure 13 In the case of correction, the correction calculation unit 220 calculates corrections b', c', and d' (corrections used to eliminate the influence of both mechanical error and interference) as corrections to be consistent with the obtained observation data "observation data M_A1".

[0285] <Summary>

[0286] As can be seen from the above description, the data collection system according to the second embodiment is as follows:

[0287] • A data collection system is formed by installing a substrate processing device A, which is not the same as the substrate processing device (reference substrate processing device) installed at the substrate manufacturer's site.

[0288] • By comparing various observation data observed under the same conditions in the first and second chambers respectively, the correction amount for the various observation data observed by processing in the second chamber is calculated.

[0289] • When exploring the optimal processing conditions by processing the substrate while changing the processing conditions in the second chamber, the observation data observed during processing in the second chamber is corrected according to the correction amount, and the corrected observation data is collected.

[0290] Therefore, according to the second embodiment, in the exploration of processing conditions in substrate processing, it is possible to collect appropriate (excluding the influence of mechanical differences and interference) various observation data.

[0291] [Third Implementation]

[0292] In the first and second embodiments described above, the correction amounts for various observation data are calculated in the correction amount calculation process (steps S162 and S167). In contrast, in the third embodiment, the correction amount calculation process also calculates the correction amount for various measurement data (specifically, particle measurement data). Hereinafter, the third embodiment will be described focusing on the differences between it and the first and second embodiments described above.

[0293] Figure 14 This is a diagram illustrating a specific example of the correction amount calculation process performed by the data collection system according to the third embodiment. Figure 14 An example is shown in the following case: The substrate processing apparatus A1210 processes the QC substrate before processing based on the processing condition "condition 0", thereby obtaining the QC substrate after processing, and measuring the particle measurement data "particle measurement data A0".

[0294] in addition, Figure 14 An example is shown in the following situation: The substrate processing device D133 outputs particle measurement data "particle measurement data D0" by processing the substrate before processing.

[0295] In the data collection system according to the third embodiment, the correction amount calculation unit 1410 operates during the correction amount calculation process (steps S162 and S167). At this time, the correction amount calculation unit 1410 obtains the particle measurement data "particle measurement data A0" and "particle measurement data D0" output from the substrate processing apparatus A1210 and the substrate processing apparatus D133.

[0296] Furthermore, the correction calculation unit 1410 calculates a correction amount p to make the acquired particle measurement data "particle measurement data D0" consistent with the particle measurement data "particle measurement data A0", and notifies the collection unit 230. Therefore, the particle measurement data output from the substrate processing device D133 can then be corrected using the correction amount p in the data collection device 140 and stored in the collection data storage unit 250.

[0297] Therefore, according to the third embodiment, in the exploration of processing conditions in substrate processing, appropriate measurement data (eliminating the influence of mechanical differences and interference) can be collected.

[0298] [Fourth Implementation]

[0299] In the first to third embodiments described above, the explanation is based on the premise that the optimal processing conditions for achieving the target substrate shape can be explored during the condition screening process (step S168). However, it is also possible to imagine a situation where the optimal processing conditions cannot be explored in the data analysis device 150.

[0300] In such a case, the output judgment result can also be that the target substrate shape cannot be achieved simply by changing the current processing conditions.

[0301] Furthermore, it can also constitute processing conditions other than those for which a change to the current status quo is recommended. Changes to processing conditions other than the current status quo processing conditions mentioned here include, for example, pulse modulation and impedance control.

[0302] [Other Implementation Methods]

[0303] In the first to fourth embodiments described above, no specific examples of substrate processing performed using a substrate processing apparatus are mentioned. However, substrate processing performed using a substrate processing apparatus may include, for example, film formation processing and etching processing. In addition, in the first to fourth embodiments described above, no specific examples of a substrate processing apparatus are mentioned. However, a substrate processing apparatus may include an etching apparatus, a film formation apparatus, an ashing apparatus, an annealing apparatus, a doping apparatus, etc.

[0304] Furthermore, in the first to fourth embodiments described above, examples of substrate shape data include data related to the appearance of the substrate, such as limit dimensions, depth, taper angle, tilt angle, and bending. However, the substrate shape data is not limited to data related to the appearance of the substrate. For example, the substrate shape data may also include data other than those related to the appearance of the substrate, such as film thickness, film type, and film properties.

[0305] Furthermore, the "same processing conditions" in the above-described embodiments 1 to 4 are not limited to cases where the processing conditions are exactly the same. For example, it may also include processing conditions in which the same effect is obtained in the changes in substrate shape data before and after processing. In addition, the "same effect" referred to here does not mean that the changes in substrate shape data before and after processing are exactly the same, but rather that the changes in substrate shape data are of the same degree (within a specified range).

[0306] Furthermore, the "substrate with the same or similar shape" in the above-described embodiments 1 to 4 is assumed to include cases where the substrate shape data are similar to each other (within a specified range).

[0307] Furthermore, in the first embodiment described above, plasma measurement data, consumption measurement data, and particle measurement data are listed as various measurement data, but it is not limited to these and may also include other measurement data.

[0308] Furthermore, in the first embodiment described above, various measurement data are described using sensors installed within the substrate processing apparatus. However, various measurement data can also be obtained from outside the substrate processing apparatus. That is, the other measurement data described above may include, for example, compositional analysis data based on XPS (X-ray Photoelectron Spectroscopy). Alternatively, the other measurement data described above may include characteristic data obtained through process processing performed by other process processing apparatuses.

[0309] In addition, in the above-described embodiments 1 to 4, the data collection device 140 and the data parsing device 150 are separate components, but the data collection device 140 and the data parsing device 150 may also be integrated.

[0310] Furthermore, in the first to fourth embodiments described above, the data collection device 140 and the data parsing device 150 are configured separately from the substrate processing device 110, or the substrate processing device A120, or the substrate processing devices B131 to D133. However, the data collection device 140 or the data parsing device 150 may also be disposed inside the substrate processing device 110, or the substrate processing device A120, or the substrate processing devices B131 to D133.

[0311] Furthermore, in the first to fourth embodiments described above, the data collection device 140 and the data parsing device 150 are described as executing data collection programs and data parsing programs separately as individual units. However, the data collection device 140 and the data parsing device 150 may each be composed of multiple computers, for example, or the data collection program or the data parsing program may be installed separately and executed in a distributed computing manner.

[0312] Furthermore, in the first to fourth embodiments described above, as an example of a method for installing a data collection program on the auxiliary storage device 1103 of the data collection device 140, a method of downloading and installing via a network was mentioned. Similarly, as an example of a method for installing a data parsing program on the auxiliary storage device 1123 of the data parsing device 150, a method of downloading and installing via a network was mentioned. While no specific download source is mentioned here, in the case of installation using this method, the download source could, for example, be a server device that accessibly stores the data collection program or the data parsing program. Furthermore, this server device could also be a cloud-based device that accepts access from either the data collection device 140 or the data parsing device 150 via a network and downloads the data collection program or the data parsing program on a paid basis. That is, the server device could also be a cloud-based device that provides services for the data collection program or the data parsing program.

[0313] Furthermore, while details of the virtual measurement model are not mentioned in embodiments 1 to 4 above, the virtual measurement model used in embodiments 1 to 4 could, for example, be an ARX model. Similarly, while details of the shape simulation model are not mentioned in embodiments 1 to 4 above, the shape simulation model used in embodiments 1 to 4 could, for example, be a convolutional neural network-based model. However, the various models used in embodiments 1 to 4 are not limited to these examples; they could also include other deep learning machine learning models, statistical models, or models combining these models.

[0314] Furthermore, the present invention is not limited to the structures listed in the above embodiments, or the structures shown herein in combination with other elements. Modifications can be made in these aspects without departing from the spirit of the invention, and appropriate provisions can be made according to its application.

[0315] This application asserts priority based on Japanese Patent Application No. 2021-032890, filed on March 2, 2021, and is incorporated herein by reference in the entirety of that Japanese Patent Application.

[0316] [Explanation of Symbols]

[0317] 100: Data Collection System

[0318] 110: Substrate processing apparatus

[0319] 120: Substrate Processing Apparatus A

[0320] 131: Substrate Processing Apparatus B

[0321] 132: Substrate processing apparatus C

[0322] 133: Substrate Processing Apparatus D

[0323] 140: Data collection device

[0324] 150: Data parsing device

[0325] 210: Calibration Calculation Department

[0326] 220: Correction Calculation Department

[0327] 230: Collection Department

[0328] 240: Conditions Change Department

[0329] 500: Data Collection

[0330] 610: Virtual Measurement Model Learning Department

[0331] 620: Learning the virtual measurement model is complete.

[0332] 630: Shape Simulation Model Learning Department

[0333] 640: Learning about shape simulation models is complete.

[0334] 650: Shape Simulation Control Unit

[0335] 1200: Data Collection System

[0336] 1210: Substrate processing apparatus A.

Claims

1. A data collection device for communicating with a first substrate processing device having a first processing space and a second substrate processing device having a second processing space different from the first processing space, wherein the first substrate processing device is a mass production machine or a device corresponding to a mass production machine, and the second substrate processing device is an experimental machine, the data collection device comprising: The correction calculation unit compares observation data observed by processing substrates of similar shape or within a specified range in the first processing space and the second processing space under the same processing conditions, and calculates a correction amount to correct the observation data observed by processing in the second processing space; and The collection unit, when exploring processing conditions by changing processing conditions in the second processing space to process the substrate, corrects the observation data observed by processing in the second processing space based on the correction amount, and collects the corrected observation data as the observation data observed when processing in the first processing space.

2. The data collection device according to claim 1, wherein, The first processing space is the same as the baseline processing space. The data collection device, It also includes a correction calculation unit that calculates a correction amount based on mechanical differences based on observation data obtained by processing substrates of similar shape within the same or specified range in the reference processing space and the first processing space under the same processing conditions. The observation data that is compared when the correction amount is calculated by the correction amount calculation unit and observed by processing in the first processing space is the observation data corrected based on the correction amount.

3. The data collection device according to claim 1, wherein, In the second substrate processing apparatus, a sensor not installed in the first substrate processing apparatus is additionally installed. The collection section, While exploring the processing conditions by changing the processing conditions in the second processing space, measurement data measured by the additionally installed sensor is collected.

4. The data collection device according to claim 1, wherein, The second substrate processing apparatus includes at least one of the following: The substrate processing apparatus is additionally equipped with a sensor for measuring plasma within the second processing space; The substrate processing apparatus is additionally equipped with a sensor for measuring the consumption of parts within the second processing space; The substrate processing apparatus is additionally equipped with a sensor for measuring particles within the second processing space.

5. The data collection apparatus according to claim 3, wherein, When exploring the processing conditions by changing the processing conditions in the second processing space to process the substrate, measurement data measured by the additionally installed sensor is displayed.

6. The data collection apparatus according to claim 1, wherein, It also has a virtual measurement model learning unit, which uses the corrected observation data collected by the collection unit as input data and the measurement data collected by the collection unit as forward solution data to enable the virtual measurement model to learn.

7. The data collection apparatus according to claim 6, wherein, The first substrate processing apparatus has a learned virtual measurement model obtained by the virtual measurement model learning unit. Display: Measurement data predicted by inputting the observation data observed through processing in the first processing space into the learned virtual measurement model.

8. The data collection apparatus according to claim 6, wherein, It also has a shape simulation model learning unit, which takes the corrected observation data collected by the collection unit, the measurement data collected by the collection unit, and the processing conditions when processing the substrate in the second processing space as input data, and takes the shape data of the processed substrate obtained by changing the processing conditions in the second processing space as forward solution data to enable the shape simulation model to learn.

9. The data collection apparatus according to claim 8, wherein, It also includes: a learned shape simulation model obtained by the shape simulation model learning unit; and When the control unit explores processing conditions by changing the processing conditions in the second processing space to process the substrate, it selects processing conditions in a manner that makes the shape data of the processed substrate predicted by the learned shape simulation model as close as possible to the target shape data.

10. The data collection apparatus according to claim 9, wherein, It also has a control unit that, based on the prediction accuracy of the processed substrate shape data predicted by the learned shape simulation model, filters the processing conditions for collecting corrected observation data and measurement data for relearning the learned shape simulation model.

11. The data collection apparatus according to claim 9, wherein, It also has a determination unit that, when exploring processing conditions by changing processing conditions in the second processing space to process the substrate, predicts the shape data of the processed substrate by using the learned shape simulation model, and determines whether it is possible to explore processing conditions where the difference between the target shape data and the target shape data is less than a predetermined threshold.

12. The data collection apparatus according to claim 8, wherein, The first substrate processing apparatus has a learned shape simulation model obtained by the shape simulation model learning unit. The shape data of the substrate after processing is displayed, which is predicted by inputting observation data observed through processing in the first processing space, measurement data predicted by inputting the observation data into the learned virtual measurement model, and processing conditions when processing the substrate in the first processing space into the learned shape simulation model.

13. A data collection system comprising: a first substrate processing apparatus having a first processing space; a second substrate processing apparatus having a second processing space different from the first processing space; and a data collection apparatus communicating with the first substrate processing apparatus and the second substrate processing apparatus, wherein the first substrate processing apparatus is a mass production machine or an apparatus corresponding to a mass production machine, and the second substrate processing apparatus is an experimental machine; the data collection system comprising: The correction calculation unit compares observation data observed by processing substrates of similar shape or within a specified range in the first processing space and the second processing space under the same processing conditions, and calculates a correction amount to correct the observation data observed by processing in the second processing space; and The collection unit, when exploring processing conditions by changing processing conditions in the second processing space to process the substrate, corrects the observation data observed by processing in the second processing space based on the correction amount, and collects the corrected observation data as the observation data observed when processing in the first processing space.

14. A data collection method for a data collection device, the data collection device communicating with a first substrate processing device having a first processing space and a second substrate processing device having a second processing space different from the first processing space, wherein the first substrate processing device is a mass production machine or a device corresponding to a mass production machine, and the second substrate processing device is an experimental machine, the data collection method comprising: A process of comparing observation data observed by processing substrates of similar shape or within a specified range in the first and second processing spaces under the same processing conditions, and calculating a correction amount for the observation data observed by processing in the second processing space; and When exploring processing conditions by processing the substrate in the second processing space by changing the processing conditions, the observation data observed by processing in the second processing space is corrected based on the correction amount, and the corrected observation data is collected as the observation data observed when processing in the first processing space.

15. A program product comprising a data collection program that causes a computer of a data collection device communicating with a first substrate processing apparatus having a first processing space and a second substrate processing apparatus having a second processing space different from the first processing space to perform the following steps: the first substrate processing apparatus is a mass production machine or an apparatus corresponding to a mass production machine, and the second substrate processing apparatus is an experimental machine: A process of comparing observation data observed by processing substrates of similar shape or within a specified range in the first and second processing spaces under the same processing conditions, and calculating a correction amount for the observation data observed by processing in the second processing space; and When exploring processing conditions by processing the substrate in the second processing space by changing the processing conditions, the observation data observed by processing in the second processing space is corrected based on the correction amount, and the corrected observation data is collected as the observation data observed when processing in the first processing space.

Images