Data acquisition device, data acquisition method, data acquisition program, and substrate processing method

Abstract

To collect appropriate data in exploring process conditions for substrate processing.SOLUTION: 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, and a data collection device connected to the first substrate processing apparatus and the second substrate processing apparatus, and further includes a correction amount calculation unit that compares observation data observed when substrates of the same or similar shape are processed in the first processing space and the second processing space under the same processing conditions, and calculates a correction amount for correcting the observation data observed when processed in the second processing space, and a collection unit that, when searching for processing conditions by processing substrates under different processing conditions in the second processing space, corrects the observation data observed when processed in the second processing space on the basis of the correction amount, and collects the corrected observation data.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a data collection system, a data collection device, a data collection method, and a data collection program.

Background Art

[0002] In the field of substrate processing apparatuses, for example, in order for the shape of a processed substrate to match a target substrate shape when processing the substrate, experiments are repeated while changing processing conditions to search for optimal processing conditions.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the case of current substrate processing apparatuses, it is difficult to collect detailed data indicating the state within the processing space. Therefore, it is difficult to predict how to change the processing conditions to approach the target substrate shape. For this reason, in order to efficiently search for optimal processing conditions, it is desirable to collect detailed data indicating the state within the processing space.

[0005] Also, for example, even if the optimal processing conditions searched using a substrate processing apparatus of a laboratory machine are applied to a substrate processing apparatus of a mass production machine, due to the differences between the two, the target substrate shape may not be obtained on the mass production machine. In such a case, further experiments are required. For this reason, in order to efficiently search for optimal processing conditions, it is desirable to collect data equivalent to that of a mass production machine during experiments.

[0006] The present disclosure is Data acquisition device for processing substrates under appropriate processing conditionsData collection method 、 Data collection program and a substrate processing method are provided. . [Means for solving the problem]

[0007] Data collection in one aspect of this disclosure Device For example, it has the following configuration: 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, Communicate Data acquisition device and , A correction amount calculation unit compares the observed data obtained when identical or similarly shaped substrates are processed in the first processing space and the second processing space under the same processing conditions, and calculates a correction amount to correct the observed data obtained when processed in the second processing space. When exploring processing conditions by processing the substrate in the second processing space with varying processing conditions, the observed data observed as a result of processing in the second processing space is corrected based on the correction amount, and the corrected observed data , as observational data observed when processed in the first processing space It has a collection unit for collecting data. [Effects of the Invention]

[0008] This invention provides a data acquisition system, data acquisition device, data acquisition method, and data acquisition program for collecting appropriate data in the search for processing conditions in substrate processing. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 is a diagram showing the configuration and processing overview of the data collection system according to the first embodiment. [Figure 2] Figure 2 shows a specific example of the calibration amount calculation process performed by the data acquisition system according to the first embodiment. [Figure 3]FIG. 3 is a diagram showing a specific example of correction amount calculation processing executed by the data collection system according to the first embodiment. [Figure 4] FIG. 4 is a diagram showing a specific example of data collection processing and condition change processing executed by the data collection system according to the first embodiment. [Figure 5] FIG. 5 is a diagram showing an example of collected data. [Figure 6] FIG. 6 is a diagram showing specific examples of virtual measurement model learning processing, shape simulation model learning processing, and condition narrowing processing executed by the data collection system according to the first embodiment. [Figure 7] FIG. 7 is a diagram showing a detailed specific example of virtual measurement model learning processing. [Figure 8] FIG. 8 is a diagram showing a detailed specific example of shape simulation model learning processing. [Figure 9] FIG. 9 is a diagram showing a detailed specific example of condition narrowing processing. [Figure 10] FIG. 10 is a diagram showing specific examples of virtual measurement processing and shape simulation processing executed by the data collection system according to the first embodiment. [Figure 11] FIG. 11 is a diagram showing an example of the hardware configuration of a data collection device and a data analysis device. [Figure 12] FIG. 12 is a diagram showing an overview of the configuration and processing of the data collection system according to the second embodiment. [Figure 13] FIG. 13 is a diagram showing a specific example of correction amount calculation processing executed by the data collection system according to the second embodiment. [Figure 14] FIG. 14 is a diagram showing a specific example of correction amount calculation processing executed by the data collection system according to the third embodiment. MODE FOR CARRYING OUT THE INVENTION

[0010] Hereinafter, each embodiment will be described with reference to the accompanying drawings. In the present specification and drawings, components having substantially the same function are denoted by the same reference numerals, and redundant descriptions are omitted.

[0011] [First Embodiment] <Outline of Configuration and Processing of Data Collection System> First, an outline of the configuration of the data collection system according to the first embodiment and the processing executed by the data collection system according to the first embodiment will be described. FIG. 1 is a diagram showing an outline of the configuration and processing of the data collection system according to the first embodiment.

[0012] As shown in FIG. 1, the data collection system 100 includes · a substrate processing apparatus 110, which is an example of a reference substrate processing apparatus, · a substrate processing apparatus A 120, which is an example of a first substrate processing apparatus, · substrate processing apparatuses B 131, C 132, and D 133, which are examples of second substrate processing apparatuses, · a data collection apparatus 140, · a data analysis apparatus 150, and has them.

[0013] The data collection system 100 is applied, for example, in a scene where a substrate processing apparatus manufacturer supports a substrate manufacturer so that the substrate manufacturer can mass-produce substrates with a target substrate shape.

[0014] The substrate processing apparatus 110 is, for example, a so-called mass-production machine installed in a substrate manufacturer. The substrate processing apparatus 110 has a reference chamber, which is an example of a reference processing space, and processes a substrate under predetermined processing conditions. Various observation sensors are attached to the substrate processing apparatus 110, and observation data observed by the various observation sensors during the processing of the substrate is output.

[0015] The substrate processing apparatus A120 is installed, for example, at a substrate processing apparatus manufacturer (same as a mass production machine). The substrate processing apparatus A120 has a first chamber, which is an example of a first processing space identical to the reference processing space, and processes substrates under predetermined processing conditions. Various observation sensors are attached to the substrate processing apparatus A120, and observation data observed by the various observation sensors during substrate processing is output.

[0016] The substrate processing apparatus B131 is a so-called experimental machine, installed, for example, at 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 the reference processing space, and processes substrates under predetermined processing conditions. Various observation sensors are attached to the substrate processing apparatus B131, and observation data observed by these sensors during substrate processing is output. In addition, a plasma probe is installed in the second chamber, and plasma measurement data measured by the plasma probe during substrate processing is output.

[0017] The substrate processing device C132 is installed, for example, at a substrate processing device manufacturer (experimental unit). The substrate processing device C132 has a third chamber, which is an example of a second processing space identical to the reference processing space, and processes substrates under predetermined processing conditions. Various observation sensors are attached to the substrate processing device C132, and observation data observed by the various observation sensors during substrate processing is output. In addition, a consumption amount sensor is installed inside the third chamber, and consumption amount measurement data indicating the amount of consumption of parts inside the third chamber, measured by the consumption amount sensor during substrate processing, is output.

[0018] The substrate processing apparatus D133 is installed, for example, at a substrate processing apparatus manufacturer (experimental unit). The substrate processing apparatus D133 has a fourth chamber, which is an example of a second processing space identical to the reference processing space, and processes substrates under predetermined processing conditions. Various observation sensors are attached to the substrate processing apparatus D133, and observation data observed by the various observation sensors during substrate processing is output. In addition, a particle sensor is installed in the fourth chamber, and particle measurement data indicating particles in the fourth chamber, measured by the particle sensor during substrate processing, is output.

[0019] Although not shown in Figure 1, the data acquisition system 100 includes a shape measuring device for measuring the shape of the substrate before and after processing, and is configured to output the measured shape data.

[0020] The data acquisition device 140 is installed, for example, at a manufacturer of substrate processing equipment. The data acquisition device 140 is connected to the substrate processing equipment 110, substrate processing equipment A120, substrate processing equipment B131 to D133, and a shape measuring device (not shown).

[0021] As a result, the data acquisition device 140 collects the processing conditions used by each substrate processing device when processing the substrate, as well as observation data observed by various observation sensors while each substrate processing device is processing the substrate.

[0022] Furthermore, the data acquisition device 140 collects shape data measured for the pre-processing and post-processing substrates processed by each substrate processing device.

[0023] Furthermore, the data acquisition device 140 collects plasma measurement data, consumption measurement data, and particle measurement data, respectively, that are measured by the plasma probe, consumption sensor, and particle sensor while the substrate processing devices B131 to D133 are processing the substrate.

[0024] The data analysis device 150 is installed, for example, at a manufacturer of substrate processing equipment. The data analysis device 150 uses the data collected by the data acquisition device 140 (referred to as collected data) to perform learning processing on various models.

[0025] The following describes the processes performed by the data acquisition system 100 (processes performed individually by each device constituting the data acquisition system 100, or by multiple devices working together). Note that, as shown in Figure 1, the processes performed by the data acquisition system 100 are as follows: • "Experimental phase for searching for optimal conditions," • "Processing phase under optimal conditions," They can be broadly categorized into these two groups.

[0026] Of these, the experimental phase for finding optimal conditions is the phase in which the optimal processing conditions for achieving the target substrate shape are searched for. The processing phase under optimal conditions is the phase in which the substrate is processed under the searched optimal processing conditions. The outline of the processing in each phase is described below.

[0027] (1) Experimental phase for finding the optimal conditions In step S161, the substrate processing apparatus 110, the substrate processing apparatus A120, and the data acquisition device 140 perform calibration amount calculation processing.

[0028] Specifically, the substrate processing apparatus 110 and the substrate processing apparatus A120 process substrates of the same or similar shape under the same processing conditions, and the data acquisition device 140 collects the observation data observed by various observation sensors.

[0029] Furthermore, the data acquisition device 140 calculates a calibration amount to calibrate the difference in observation data based on "machine differences" between the substrate processing device 110 and the substrate processing device A120.

[0030] The data acquisition device 140 then calibrates the observation data output from the substrate processing device A120 based on the calculated calibration amount. As a result, the data acquisition device 140 can subsequently collect the same observation data from the substrate processing device A120 as the observation data output when substrates of the same or similar shape are processed by the substrate processing device 110 under the same processing conditions.

[0031] In step S162, the substrate processing device A120, the substrate processing devices B131 to D133, and the data acquisition device 140 perform correction amount calculation processing. Specifically, the substrate processing devices A120 and B131 to D133 process substrates of the same or similar shape under the same processing conditions, and the data acquisition device 140 collects the observation data observed by various observation sensors.

[0032] Furthermore, the data acquisition device 140 calculates a correction amount to compensate for the effects of disturbances caused by the installation of the plasma probe in the second chamber by calculating the difference in various observation data collected from the substrate processing device A120 and the substrate processing device B131.

[0033] The data acquisition device 140 then corrects the observed data output from the substrate processing device B131 based on the calculated correction amount. As a result, the data acquisition device 140 can subsequently acquire from the substrate processing device B131 the same observed data that would be collected when substrates of the same or similar shape are processed by the substrate processing device A120 under the same processing conditions.

[0034] Similarly, the data acquisition device 140 calculates a correction amount to compensate for the disturbance caused by the installation of the consumption sensor in the third chamber by calculating the difference in various observation data collected from the substrate processing device A120 and the substrate processing device C132.

[0035] The data acquisition device 140 then corrects the observed data output from the substrate processing device C132 based on the calculated correction amount. As a result, the data acquisition device 140 can subsequently acquire from the substrate processing device C132 the same observed data that would be collected when substrates of the same or similar shape are processed by the substrate processing device A120 under the same processing conditions.

[0036] Similarly, the data acquisition device 140 calculates a correction amount to compensate for the effects of disturbances caused by the installation of the particle sensor in the fourth chamber by calculating the differences in various observation data collected from the substrate processing device A120 and the substrate processing device D133.

[0037] The data acquisition device 140 then corrects the observed data output from the substrate processing device D133 based on the calculated correction amount. As a result, the data acquisition device 140 can subsequently collect the same observed data from the substrate processing device D133 as the observed data collected when substrates of the same or similar shape are processed by the substrate processing device A120 under the same processing conditions.

[0038] In step S163, the data acquisition device 140 changes the processing conditions used by the substrate processing devices B131 to D133 when processing the substrate in order to search for the optimal processing conditions for achieving the target substrate shape. The data acquisition device 140 also sets the changed processing conditions in the substrate processing devices B131 to D133.

[0039] In step S164, the substrate processing devices B131 to D133 and the data acquisition device 140 perform data acquisition processing.

[0040] Specifically, substrate processing devices 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. In addition, a shape measuring device (not shown) outputs shape data of the substrate before processing and shape data of the substrate after processing.

[0041] Furthermore, the data acquisition device 140 corrects various observation data using a correction amount and collects the corrected observation data. The data acquisition device 140 also collects plasma measurement data output from the substrate processing device B131, consumption amount measurement data output from the substrate processing device C132, and particle measurement data output from the substrate processing device D133 (these are collectively referred to as "various measurement data"). In addition, the data acquisition device 140 collects pre-processing substrate shape data and post-processing substrate shape data (these are collectively referred to as "various shape data") output from a shape measuring device (not shown).

[0042] Furthermore, the data acquisition device 140 displays the acquired data (previous processing conditions, various observation data, various measurement data, and various shape data) to the experimenter. This allows the experimenter to observe the various shape data while referring to various measurement data, which are detailed data representing the state inside the chamber, as well as various observation data. As a result, the experimenter can set more appropriate processing conditions for the next processing to approach the target substrate shape, and efficiently search for the optimal processing conditions.

[0043] The condition change process in step S163 and the data acquisition process in step S164 are executed repeatedly. After a predetermined number of repetitions, the correction amount calculation process in step S162 is executed. This is because the various measurement data output from substrate processing devices B131 to D133 change over time, and by periodically updating the correction amount, the effects of disturbances can always be eliminated.

[0044] In this way, by performing the calibration amount calculation process (step S161) and the correction amount calculation process (step S162), the data acquisition device 140 searches for the optimal processing conditions. • Effects of differences between aircraft, • The effects of the disturbance, Observational data with the unwanted elements removed (observational data equivalent to the observational data output from the mass-production substrate processing machine 110) can be collected from substrate processing machines B131 to D133.

[0045] Once a certain amount of data has been collected through repeated execution of the condition change process in step S163 and the data collection process in step S164, in step S165, the data analysis device 150 uses the collected data to perform learning processing on a virtual measurement model. The virtual measurement model is a model that predicts various measurement data (plasma measurement data, consumption amount measurement data, particle measurement data) during substrate processing based on various observation data.

[0046] The data analysis device 150 uses various observation data as input data and various measurement data as ground truth data for learning processing. This allows the data analysis device 150 to generate a trained virtual measurement model.

[0047] The generated, trained virtual measurement model is then installed, for example, on a substrate processing apparatus 110 that does not have a plasma probe, consumption sensor, or particle sensor attached.

[0048] As a result, when processing a substrate in the "optimal processing phase" of the substrate processing apparatus 110, plasma measurement data, consumption measurement data, and particle measurement data can be predicted based on various observation data and displayed to the operator.

[0049] In step S166, the data analysis device 150 uses the collected data to perform a learning process on the shape simulation model. The shape simulation model is a model that predicts the shape data of the substrate after processing.

[0050] The data analysis device 150 takes various observation data, various measurement data, processing conditions, and pre-processing substrate shape data as input data and performs learning processing using the post-processing substrate shape data as ground truth data. As a result, the data analysis device 150 generates a trained shape simulation model.

[0051] In this way, by including not only various observational data but also various measurement data as input data and performing learning processing, it is possible to generate a trained shape simulation model with high prediction accuracy.

[0052] The generated trained shape simulation model is, for example, installed in the substrate processing apparatus 110. This allows the substrate processing apparatus 110 to predict the shape data of the processed substrate after processing the substrate during the "optimal processing phase".

[0053] If the target substrate shape has not been reached at this point (when step S166 is completed) (if the difference from the target substrate shape is greater than or equal to a predetermined threshold), the search for the optimal processing conditions will continue while changing the processing conditions.

[0054] Specifically, in step S167, the substrate processing device A120, the substrate processing devices B131 to D133, and the data acquisition device 140 perform the correction amount calculation process. Note that the correction amount calculation process in step S167 is the same as the correction amount calculation process in step S162, so the explanation is omitted here.

[0055] In step S168, the data acquisition device 140 and the data analysis device 150 perform a condition refinement process to narrow down the processing conditions using the trained shape simulation model generated in step S166.

[0056] Specifically, the data analysis device 150 uses a trained shape simulation model to predict the shape data of the processed substrate, thereby narrowing down the processing conditions to approach the target substrate shape.

[0057] In parallel, the data analysis device 150 narrows down the processing conditions for which data has not been collected in order to improve the prediction accuracy of the trained shape simulation model.

[0058] As a result, the data analysis device 150 sets the modified processing conditions, either those narrowed down from the perspective of searching for optimal processing conditions or those narrowed down from the perspective of improving prediction accuracy, to the substrate processing devices B131 to D133.

[0059] In step S169, the substrate processing devices B131 to D133 and the data acquisition device 140 perform data acquisition processing. Since the data acquisition processing in step S169 is the same as the data acquisition processing in step S164, the explanation is omitted here.

[0060] Furthermore, the condition refinement process in step S168 and the data collection process in step S169 are also executed repeatedly, similar to the condition change process in step S163 and the data collection process in step S164. However, unlike in steps S163 and S164, the processing conditions are appropriately refined in step S168, which accelerates the speed at which the optimal processing conditions are approached (i.e., the optimal processing conditions can be searched for more efficiently).

[0061] Furthermore, similar to step S162, if the substrate processing under the modified processing conditions is repeated a predetermined number of times, the correction amount calculation process in step S167 is executed to correct the effects of changes over time in various observation data output from substrate processing devices B131 to D133.

[0062] In this way, by repeatedly processing the substrate while changing the processing conditions, when the target substrate shape is reached (when the error from the target substrate shape is less than a predetermined threshold), the processing conditions at that point are determined to be the optimal processing conditions. This concludes the experimental phase for searching for the optimal conditions.

[0063] Once the experimental phase for finding the optimal conditions is complete, the process moves to the "processing phase under optimal conditions." In the processing phase under optimal conditions, the substrate is processed under optimal conditions using the substrate processing apparatus 110, which is equipped with the trained virtual measurement model and trained shape simulation model generated in the experimental phase for finding the optimal conditions.

[0064] Furthermore, as shown in Figure 1, in step S171, the substrate processing apparatus 110 performs virtual measurement processing when processing the substrate under optimal processing conditions. As a result, various observation data observed during substrate processing are input into a trained virtual measurement model, and various measurement data (plasma measurement data, consumption measurement data, particle measurement data) are predicted. The predicted various measurement data are also displayed to the operator or other relevant parties.

[0065] This allows workers to monitor plasma measurement data, consumption measurement data, and particle measurement data that were previously impossible to monitor when processing substrates.

[0066] In step S172, the substrate processing apparatus 110 performs shape simulation processing when processing the substrate under optimal processing conditions. 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 trained shape simulation model. The trained shape simulation model also predicts the shape data of the substrate after processing and displays the predicted shape data to the operator or other relevant personnel.

[0067] As a result, workers can determine the quality of the processed substrates without having to perform a full inspection of each one.

[0068] <Specific examples of processes performed by the data collection system> Next, we will describe specific examples of each process performed by the data collection system 100.

[0069] (1) Specific example of the calibration amount calculation process (step S161) First, a specific example of the calibration amount calculation process (step S161) performed by the data acquisition system 100 will be described. Figure 2 is a diagram showing a specific example of the calibration amount calculation process performed by the data acquisition system according to the first embodiment.

[0070] The example in Figure 2 shows how the substrate processing apparatus 110 and the substrate processing apparatus A120 process substrates of the same or similar shape under processing condition = "condition 0", resulting in the output of observation data = "observation data M_α0" and "observation data M_A0", respectively.

[0071] Furthermore, the data acquisition device 140 has a data acquisition program installed, and when this program is executed, the data acquisition device 140 will... ·Calibration amount calculation unit 210, ·Correction amount calculation unit 220, • Collection unit 230, • Condition change section 240, It functions as such.

[0072] In the calibration amount calculation process (step 161), the data acquisition device 140 operates the calibration amount calculation unit 210 and acquires the observation data = "Observation Data M_α0" output from the substrate processing device 110. The calibration amount calculation unit 210 also acquires the observation data = "Observation Data M_A0" output from the substrate processing device A120. The calibration amount calculation unit 210 also calculates the calibration amount a required to match the observation data = "Observation Data M_A0" to the observation data = "Observation Data M_α0". Furthermore, the calibration amount calculation unit 210 notifies the correction amount calculation unit 220 of the calculated calibration amount a.

[0073] (2) Specific example of the correction amount calculation process (step S162) Next, a specific example of the correction amount calculation process (step S162) performed by the data acquisition system 100 will be described. Figure 3 is a diagram showing a specific example of the correction amount calculation process performed by the data acquisition system according to the first embodiment.

[0074] The example in Figure 3 shows how substrate processing devices A120 and B131-D133 process substrates of the same shape under processing condition "Condition 1," resulting in the output of observation data "Observation Data M_A1" to "Observation Data M_D1," respectively.

[0075] In the correction amount calculation process (step S162), the data acquisition device 140 operates the correction amount calculation unit 220 and acquires 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.

[0076] Furthermore, the correction amount calculation unit 220 calibrates the acquired observation data = "Observation Data M_A1" using the calibration amount a, and generates the calibrated observation data.

[0077] Furthermore, the correction amount calculation unit 220 calculates a correction amount b to make the observed data = "Observed Data M_B1" match the calibrated observed data, and notifies the collection unit 230 of this.

[0078] Similarly, the correction amount calculation unit 220 calculates a correction amount c to make the observed data = "Observed Data M_C1" match the calibrated observed data, and notifies the collection unit 230 of this.

[0079] Similarly, the correction amount calculation unit 220 calculates a correction amount d to make the observed data = "Observed Data M_D1" match the calibrated observed data, and notifies the collection unit 230 of this.

[0080] (3) Specific examples of condition change processing (step S163) and data collection processing (step S164) Next, specific examples of the condition change process (step S163) and the data acquisition process (step S164) performed by the data acquisition system 100 will be described. Figure 4 is a diagram showing specific examples of the data acquisition process and the condition change process performed by the data acquisition system according to the first embodiment.

[0081] In the condition change process (step S163), the condition change unit 240 of the data acquisition device 140 is activated. The example in Figure 4 shows how the condition change unit 240 sequentially transmits processing conditions = "condition 2", "condition 3", ... to the substrate processing device B131, substrate processing device C132, and substrate processing device D133.

[0082] Furthermore, the example in Figure 4 shows that the substrate processing apparatus B131 processes pre-processing substrates of the same shape under processing conditions = "Condition 2", "Condition 3", ..., respectively. Observation data = "Observation data M_B2", "Observation data M_B3", ... • Measurement data = "Measurement data I_B2", "Measurement data I_B3", ... This shows the output. Also, the example in Figure 4 shows that the substrate is processed by the substrate processing device B131. From the pre-processing substrate with shape data = "Shape data S_B2", "Shape data S_B3", etc. • Shape data = "Shape data S_B2'", "Shape data S_B3'", ...the substrate after processing, This shows how it was generated.

[0083] Similarly, the example in Figure 4 shows that the substrate processing apparatus C132 processes pre-processing substrates of the same shape under processing conditions = "Condition 2", "Condition 3", ..., respectively. Observation data = "Observation data M_C2", "Observation data M_C3", ... • Measurement data = "Measurement data I_C2", "Measurement data I_B3", ... This shows the output. Also, the example in Figure 4 shows that the substrate processing device C132 processes the data. From the pre-processing substrate with shape data = "Shape data S_C2", "Shape data S_C3", etc. • Shape data = "Shape data S_C2'", "Shape data S_C3'", ...the substrate after processing, This shows how it was generated.

[0084] Similarly, the example in Figure 4 shows that the substrate processing apparatus D133 processes pre-processing substrates of the same shape under processing conditions = "Condition 2", "Condition 3", ..., respectively. Observation data = "Observation data M_D2", "Observation data M_D3", ... • Measurement data = "Measurement data I_D2", "Measurement data I_D3", ... This shows the output. Also, the example in Figure 4 shows that the substrate processing device D133 processes the data. From the pre-processing substrate with shape data = "Shape data S_D2", "Shape data S_D3", ... • Shape data = "Shape data S_D2'", "Shape data S_D3'", ...the substrate after processing, This shows how it was generated.

[0085] Furthermore, during the data acquisition process (step S164), the data acquisition device 140 operates the acquisition unit 230. As shown in Figure 4, the acquisition unit 230 has storage units 401, 403, 405 and correction storage units 402, 404, 406.

[0086] In the example shown in Figure 4, the storage unit 401 is • Shape data of the substrate before processing = "Shape data S_B2", "Shape data S_B3", ... • Shape data of the processed substrate = "Shape data S_B2'", "Shape data S_B3'", ... This shows how the collected data is stored in the data storage unit 250.

[0087] Furthermore, the example in Figure 4 shows how the correction storage unit 402 corrects the observed data = "Observed Data M_B2", "Observed Data M_B3", ... using the correction amount b, and stores the corrected observed data in the collected data storage unit 250. It also shows how the correction storage unit 402 stores the measured data = "Measured Data I_B2", "Measured Data I_B3", ... in the collected data storage unit 250.

[0088] Similarly, in the example in Figure 4, the storage unit 403 is • Shape data of the substrate before processing = "Shape data S_C2", "Shape data S_C3", ... This shows how the shape data of the processed substrate, namely "Shape Data S_C2'", "Shape Data S_C3'", etc., is stored in the data collection storage unit 250.

[0089] Furthermore, the example in Figure 4 shows how the correction storage unit 404 corrects the observed data = "Observed Data M_C2", "Observed Data M_C3", ... using a correction amount c, and stores the corrected observed data in the collected data storage unit 250. It also shows how the correction storage unit 404 stores the measured data = "Measured Data I_C2", "Measured Data I_C3", ... in the collected data storage unit 250.

[0090] Similarly, in the example in Figure 4, the storage unit 405 is • Shape data of the substrate before processing = "Shape data S_D2", "Shape data S_D3", ... This shows how the shape data of the processed substrate, namely "Shape Data S_D2'", "Shape Data S_D3'", etc., is stored in the collected data storage unit 250.

[0091] Furthermore, the example in Figure 4 shows how the correction storage unit 406 corrects the observed data = "Observed Data M_D2", "Observed Data M_D3", ... using a correction amount d, and stores the corrected observed data in the collected data storage unit 250. It also shows how the correction storage unit 406 stores the measured data = "Measured Data I_D2", "Measured Data I_D3", ... in the collected data storage unit 250.

[0092] Next, we will explain the collected data stored in the collected data storage unit 250. Figure 5 shows an example of collected data.

[0093] As shown in Figure 5, the collected data 500 includes the following information items: "processing conditions", "observation data", "measurement data", "pre-processing substrate shape data", and "post-processing substrate shape data".

[0094] The "processing conditions" include, for example, 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 = "condition 2", "condition 3", ... "condition x" shall consist of combinations in which at least one of these setting values ​​is different.

[0095] The "observation data" stores observed values ​​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, namely "Observation Data M_B1," "Observation Data M_C1," and "Observation Data M_D1," are each composed of combinations of these observed values.

[0096] The "measurement data" contains measurement values ​​from additionally installed sensors, such as plasma measurement data, consumption measurement data, and particle measurement data. Specifically, "measurement data = "measurement data I_B1" contains the plasma measurement data. "measurement data = "measurement data I_C1" contains the consumption measurement data. "measurement data = "measurement data I_D1" contains the particle measurement data.

[0097] The "pre-processing substrate shape data" stores shape values ​​such as limit dimensions, depth, taper angle, tilt angle, and bowing. The pre-processing substrate shape data, from "shape data S_B2" to "shape data S_D2", is composed of combinations of these shape values.

[0098] The "processed substrate shape data" stores shape values ​​such as limit dimensions, depth, taper angle, tilt angle, and bowing. The processed substrate shape data, "shape data S_B2'" to "shape data S_D2'", are each composed of combinations of these shape values.

[0099] (4) Specific examples of the virtual measurement model learning process (step S165), the shape simulation model learning process (step S166), and the condition narrowing process (step S168) (4-1) Specific Examples (Overview) Next, specific examples (overviews) of the virtual measurement model learning process (step S165), shape simulation model learning process (step S166), and condition filtering process (step S168) performed by the data acquisition system 100 will be described.

[0100] Figure 6 shows specific examples of the virtual measurement model learning process, shape simulation model learning process, and condition filtering process performed by the data acquisition system according to the first embodiment.

[0101] The data analysis device 150 has a data analysis program installed, and when this program is executed, the data analysis device 150 performs the following actions: • Virtual measurement model learning unit 610, • Shape simulation model learning unit 630, • 640 pre-trained shape simulation models, • Shape simulation control unit 650 (an example of a control unit and determination unit) It functions as such.

[0102] In the virtual measurement model learning process (step S165), the data analysis device 150 operates the virtual measurement model learning unit 610 and reads the collected data 500 stored in the collected data storage unit 250. The virtual measurement model learning unit 610 also uses the read collected data 500 to perform learning processing on the virtual measurement model.

[0103] The trained virtual measurement model 620, which is generated by the virtual measurement model learning unit 610 performing a training process on the virtual measurement model, is mounted on the substrate processing device 110.

[0104] Meanwhile, in the shape simulation model learning process (step S166), the data analysis device 150 operates the shape simulation model learning unit 630 and reads the collected data 500 stored in the collected data storage unit 250. The shape simulation model learning unit 630 then uses the read collected data 500 to perform learning processing on the shape simulation model.

[0105] The trained shape simulation model 640, generated by the training process performed by the shape simulation model learning unit 630, is mounted on the substrate processing device 110. Furthermore, the trained shape simulation model 640 is executed by the shape simulation control unit 650 during the condition filtering process (step S168).

[0106] Specifically, in the condition narrowing process (step S168), the shape simulation control unit 650 of the data analysis device 150 is activated. The shape simulation control unit 650 runs the trained shape simulation model under various processing conditions and obtains prediction results for the shape data of the processed substrate. The shape simulation control unit 650 also compares the predicted shape data of the processed substrate with the target substrate shape to narrow down the processing conditions that can realize the target substrate shape. Furthermore, the narrowed-down processing conditions are notified to the condition change unit 240 of the data acquisition device 140. As a result, the condition change unit 240 can set the narrowed-down processing conditions as the modified processing conditions from the perspective of searching for the optimal processing conditions to the substrate processing devices B131 to D133.

[0107] Furthermore, the shape simulation control unit 650 refers to the collected data 500 stored in the collected data storage unit 250 and determines processing conditions that are not used in the learning process of the shape simulation model. The shape simulation control unit 650 then notifies the condition change unit 240 of the determined processing conditions. As a result, the condition change unit 240 sets the processing conditions determined by the shape simulation control unit 650 as the modified processing conditions in the substrate processing devices B131 to D133. Consequently, data acquisition processing (step S169) is performed in the substrate processing devices B131 to D133 and the data acquisition device 140, and the collected data 500 in the collected data storage unit 250 contains the processing conditions corresponding to the determined processing conditions. • Various observational data, • Various measurement data, • Various shape data (pre-processing substrate shape data, post-processing substrate shape data), This will be stored in a new location.

[0108] The shape simulation control unit 650 performs a retraining process on the trained shape simulation model using the determined processing conditions and newly stored various observation data, various measurement data, and various shape data (pre-processing substrate shape data, post-processing substrate shape data). The shape simulation control unit 650 repeatedly performs the determination of processing conditions and the retraining process multiple times. At this time, the shape simulation control unit 650 identifies processing conditions with low prediction accuracy and notifies the condition change unit 240 of these identified processing conditions with low prediction accuracy (i.e., it narrows down the processing conditions for performing the retraining process on the trained shape simulation model). As a result, the condition change unit 240 can set the narrowed-down processing conditions, from the perspective of improving the prediction accuracy of the trained shape simulation model 640, as the modified processing conditions in the substrate processing devices B131 to D133.

[0109] (4-2) Detailed Specific Example (Virtual Measurement Model Learning Process (Step S165)) Next, we will describe a more detailed specific example of the virtual measurement model learning process (step S165). Figure 7 shows a detailed specific example of the virtual measurement model learning process.

[0110] As shown in Figure 7, the virtual measurement model learning unit 610 includes a virtual measurement model 710 and a comparison / modification unit 720.

[0111] The virtual measurement model 710 receives the setting values ​​stored in the "processing conditions" of the collected data 500 and the observed values ​​stored in the "observed data" as input data. Based on this, the virtual measurement model 710 outputs output data.

[0112] Meanwhile, the comparison / modification unit 720 receives the measured values ​​stored in the "measurement data" of the collected data 500 as ground truth data. The comparison / modification unit 720 calculates the error by comparing the output data output from the virtual measurement model 710 with the measured values ​​input as ground truth data, and updates the model parameters of the virtual measurement model 710 according to the calculated error. As a result, the virtual measurement model learning unit 610 can generate a trained virtual measurement model 620.

[0113] (4-2) Detailed Specific Example (Shape Simulation Model Learning Process (Step S166)) Next, we will describe a more detailed specific example of the shape simulation model learning process (step S166). Figure 8 shows a detailed specific example of the shape simulation model learning process.

[0114] As shown in Figure 8, the shape simulation model learning unit 630 includes a shape simulation model 810 and a comparison / modification unit 820.

[0115] The shape simulation model 810 receives the following as input data: the setting values ​​stored in the "processing conditions" of the collected data 500, the observed values ​​stored in the "observed data," the measured values ​​stored in the "measured data," and the shape values ​​stored in the "pre-processed substrate shape data." Based on this, the shape simulation model 810 outputs output data.

[0116] Meanwhile, the comparison / modification unit 820 receives the shape values ​​stored in the "processed substrate shape data" of the collected data 500 as the correct data. The comparison / modification unit 820 calculates the error by comparing the output data output from the shape simulation model 810 with the shape values ​​input as the correct data, and updates the model parameters of the shape simulation model 810 according to the calculated error. As a result, the shape simulation model learning unit 630 can generate a trained shape simulation model 640.

[0117] (4-3) Details of the specific example (Details of the condition filtering process (step S168)) Next, we will describe a more detailed example of the condition filtering process (step S168). Figure 9 is a diagram showing the details of a specific example of the condition filtering process.

[0118] As shown in the lower right of Figure 9, the shape simulation control unit 650 executes the trained shape simulation model under processing conditions = "condition 101", "condition 102", .... This allows the shape simulation control unit 650 to acquire the shape data of the processed substrate ("shape data S101", "shape data S102", ...) predicted by the trained shape simulation model 640.

[0119] 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 to narrow down the processing conditions that can realize the target substrate shape. In addition, it notifies the condition change unit 240 of the data acquisition device 140 of the narrowed-down processing conditions.

[0120] The example in Figure 9 shows how, by narrowing down the processing conditions from the perspective of searching for the optimal processing conditions, the processing condition = "condition x" was ultimately found to be the optimal processing condition.

[0121] Furthermore, the shape simulation control unit 650 refers to the collected data 500 stored in the collected data storage unit 250 and determines processing conditions that are not used in the learning process of the shape simulation model.

[0122] The dashed area 900 shown in the lower left of Figure 9 schematically represents the range that can be searched as a processing condition. On the other hand, in Figure 9, the solid area 910 schematically represents the range (interpolation range) used in the learning process of the shape simulation model.

[0123] As described above, the shape simulation control unit 650 narrows down the processing conditions that have low prediction accuracy among the processing conditions that were not used in the training process of the shape simulation model 640, from the viewpoint of improving the prediction accuracy of the trained shape simulation model 640.

[0124] The example in Figure 9 shows how the shape simulation control unit 650 narrows down the area within the dashed area 900 to the solid area 920 from among the areas other than the solid area 910.

[0125] Furthermore, the example in Figure 9 shows how the shape simulation control unit 650 notifies the condition change unit 240 of "condition x+1", "condition x+2", ... as processing conditions included in the solid line region 920, and inputs them into the learned shape simulation model 640.

[0126] As a result, in the trained shape simulation model 640, Processing conditions = "condition x+1", "condition x+2", ... and so on. • Processing conditions = "condition x+1", "condition x+2", ... under which substrate processing devices B131 to D133 process the substrate, various observation data, various measurement data, and pre-processing substrate shape data are collected. Use the following as input data: • Processing conditions = "condition x+1", "condition x+2", ...the shape data of the substrate after processing when substrate processing devices B131 to D133 process the substrate. Using this as ground truth data, the trained shape simulation model 640 can be retrained.

[0127] (5) Specific examples of virtual measurement processing (step S171) and shape simulation processing (step S172) Next, specific examples of the virtual measurement process (step S171) and shape simulation process (step S172) performed by the data acquisition system 100 will be described. Figure 10 is a diagram showing specific examples of the virtual measurement process and shape simulation process performed by the data acquisition system according to the first embodiment.

[0128] The example in Figure 10 shows how, when a substrate is processed under processing condition "condition x", observation data "observation data M_αx" is output. The example in Figure 10 also shows how, when various observation data are input into the trained virtual measurement model 620, plasma measurement data, consumption measurement data, and particle measurement data are predicted, and measurement data "measurement data I_αx" is output.

[0129] In this way, by outputting "Measurement Data I_αx" which includes plasma measurement data, consumption measurement data, and particle measurement data, operators can monitor measurement data that they were previously unable to monitor.

[0130] Furthermore, the example in Figure 10 shows the input of processing conditions = "condition x", observation data = "observation data M_αx", measurement data = "measurement data I_αx", and pre-processing substrate shape data = "shape data S_αx" into the trained shape simulation model 640. In addition, the example in Figure 10 shows the output of processed substrate shape data = "shape data S_αx'" from the trained shape simulation model 640.

[0131] In this way, by predicting the shape data of the processed substrate, workers can determine the quality of the processed substrate without having to perform a full inspection of each substrate.

[0132] <Hardware configuration of data acquisition and data analysis equipment> Next, the hardware configuration of the data acquisition device 140 and the data analysis device 150 will be described. Figure 11 shows an example of the hardware configuration of the data acquisition device and the data analysis device.

[0133] (1) Data acquisition device As shown in Figure 11a, the data acquisition device 140 includes a processor 1101, memory 1102, auxiliary storage device 1103, I / F (Interface) device 1104, communication device 1105, and drive device 1106. The hardware components of the data acquisition device 140 are interconnected via a bus 1107.

[0134] The processor 1101 has various computing devices such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The processor 1101 reads various programs (for example, data acquisition programs, etc.) into the memory 1102 and executes them.

[0135] Memory 1102 has main memory devices such as ROM (Read Only Memory) and RAM (Random Access Memory). The processor 1101 and memory 1102 form a so-called computer, and the computer realizes the above-mentioned functions by having the processor 1101 execute various programs read into memory 1102.

[0136] The auxiliary storage device 1103 stores various programs and various data used when these programs are executed by the processor 1101. The data collection storage unit 250 described above is implemented in the auxiliary storage device 1103.

[0137] The I / F device 1104 is a connecting device that connects the display device 1108, the operating device 1109, and the data acquisition device 140.

[0138] The communication device 1105 is a communication device for communicating with the substrate processing device 110, substrate processing device A120, substrate processing devices B131 to D133, shape measuring device 1110, data analysis device 150, etc., via a network.

[0139] The drive device 1106 is a device for setting the recording medium 1111. The recording medium 1111 here includes media that record information optically, electrically, or magnetically, such as CD-ROMs, flexible disks, and magneto-optical disks. The recording medium 1111 may also include semiconductor memory that records information electrically, such as ROMs and flash memory.

[0140] The various programs to be installed on the auxiliary storage device 1103 are installed, for example, when the distributed recording medium 1111 is set in the drive device 1106 and the various programs recorded on the recording medium 1111 are read. Alternatively, the various programs to be installed on the auxiliary storage device 1103 may be installed by downloading them from the network via the communication device 1105.

[0141] (2) Data analysis device As shown in Figure 11, 11b, the hardware configuration of the data analysis device 150 is the same as that of the data acquisition device 140. Therefore, the differences between the two devices will be explained here.

[0142] In the case of the data analysis device 150, the processor 1121 reads the data analysis program into memory 1122 and executes it.

[0143] In addition, in the case of the data analysis device 150, the communication device 1125 communicates with the substrate processing device 110 and the data acquisition device 140.

[0144] <Summary> As is clear from the above description, the collection system according to the first embodiment is The system comprises 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 acquisition device 140 connected to substrate processing apparatuses A and B to D. - Various observational data observed when identical or similarly shaped substrates are processed in the first chamber and the second chamber under the same conditions are compared, and a correction amount is calculated to correct the various observational data observed when processed in the second chamber. • When searching for optimal processing conditions by processing the substrate in the second chamber while changing the processing conditions, the observation data observed during processing in the second chamber is corrected based on a correction amount, and the corrected observation data is collected.

[0145] Thus, the data collection system according to the first embodiment uses multiple substrate processing devices to process substrates of the same or similar shape under the same conditions and collects observational data corrected for the effects of disturbances. As a result, according to the first embodiment, appropriate (disturbance-free) various observational data can be collected when searching for processing conditions in substrate processing.

[0146] Furthermore, the collection system according to the first embodiment is The first chamber is configured to be identical to the reference chamber in the reference substrate processing device. - The calibration amount based on instrument error is calculated from various observational data obtained by processing identical or similarly shaped substrates in the reference chamber and the first chamber under identical conditions.

[0147] As a result, according to the first embodiment, appropriate (machine-dependent) observational data can be collected when searching for processing conditions in substrate processing.

[0148] Furthermore, the collection system according to the first embodiment is Plasma probes, consumption sensors, and particle sensors are added and installed in the second chambers of each substrate processing unit B to D to collect and display various measurement data (plasma measurement data, consumption measurement data, particle measurement data) during substrate processing.

[0149] As a result, according to the first embodiment, it becomes possible to change the processing conditions while referring to various measurement data, which are detailed data representing the state inside the chamber, and to efficiently search for the optimal processing conditions.

[0150] Furthermore, the collection system according to the first embodiment is • Generate a pre-trained virtual measurement model that predicts various measurement data during substrate processing. • The learning process includes various measurement data during substrate processing to generate a trained shape simulation model.

[0151] This improves the prediction accuracy of the trained shape simulation model. Furthermore, it allows for the refinement of processing conditions using the trained shape simulation model, enabling efficient searching for the optimal processing conditions.

[0152] Furthermore, the collection system according to the first embodiment is The generated, trained virtual measurement model and trained shape simulation model are mounted on the substrate processing equipment of the mass production machine.

[0153] This allows for the monitoring of various measurement data that could not be monitored previously when processing substrates in mass-production substrate processing equipment. Furthermore, it becomes possible to predict and display the shape data of the processed substrate, making it possible to determine the quality of the processed substrate without performing a 100% inspection.

[0154] [Second Embodiment] In the data acquisition system 100 according to the first embodiment described above, it was explained that the same substrate processing apparatus A (mass production machine) as the substrate processing apparatus (reference substrate processing apparatus) installed at the substrate processing apparatus manufacturer is installed at the substrate processing apparatus manufacturer. However, the configuration of the data acquisition system is not limited to this, and for example, the data acquisition system may be configured without installing the substrate processing apparatus A at the substrate processing apparatus manufacturer. The data acquisition system according to the second embodiment will be described below.

[0155] <Overview of the Data Collection System's Configuration and Processing> First, the configuration of the data collection system according to the second embodiment and an overview of the processing performed by the data collection system according to the second embodiment will be described. Figure 12 is a diagram showing the configuration and overview of the processing of the data collection system according to the second embodiment.

[0156] As shown in Figure 12, the data acquisition system 1200 is • An example of a first substrate processing apparatus is the substrate processing apparatus A1210. • Examples of second substrate processing devices include substrate processing devices B131, C132, and D133. • Data acquisition device 140, • Data analysis device 150, It has the following. In this embodiment, for the sake of explanation, the system configuration is such that the substrate processing apparatus A1210 is installed at the substrate manufacturer instead of the substrate processing apparatus 110.

[0157] Similar to the first embodiment described above, the data acquisition system 1200 is applied in scenarios such as when a substrate processing equipment manufacturer supports a substrate manufacturer so that the substrate manufacturer can mass-produce substrates with a target substrate shape.

[0158] The substrate processing device A1210 is installed, for example, in a substrate manufacturer (mass production machine). The substrate processing device A1210 has a first chamber and processes substrates under predetermined processing conditions. Various observation sensors are attached to the substrate processing device A1210, and observation data observed by the various observation sensors during substrate processing is output.

[0159] Note that the substrate processing devices B131 to D133, data acquisition device 140, and data analysis device 150 shown in Figure 12 are the same as those in Figure 1, so their explanation is omitted here.

[0160] Furthermore, each process included in the "experimental phase for searching for optimal conditions" is the same as in Figure 1, except that the calibration amount calculation process (step S161) is not included, so we will omit the explanation here.

[0161] Furthermore, since each process included in the "processing phase under optimal conditions" is the same as in Figure 1, except that it is performed by the substrate processing device A1210, we will omit the explanation here.

[0162] <Specific examples of processes performed by the data collection system> Next, a specific example of the correction amount calculation process (step S162) performed by the data acquisition system 1200 will be described.

[0163] (1) Specific example of the correction amount calculation process (step S162) Figure 13 shows a specific example of the correction amount calculation process performed by the data acquisition system according to the second embodiment.

[0164] The example in Figure 13 shows how substrate processing equipment A120 and substrate processing equipment B131-D133 processed substrates of the same or similar shape under processing condition = "Condition 1". Furthermore, the example in Figure 13 shows how observation data = "Observation Data M_A1" to "Observation Data M_D1" were output from substrate processing equipment A120 and substrate processing equipment B131-D133, respectively.

[0165] The difference from Figure 3 is that in Figure 13, the correction amount calculation unit 220 calculates correction amounts b', c', and d' (correction amounts to eliminate the effects of both instrument error and disturbance) as correction amounts to match the acquired observation data = "Observation Data M_A1".

[0166] <Summary> As is clear from the above explanation, the data collection system according to the second embodiment is • The same substrate processing device A (reference substrate processing device) installed at the substrate manufacturer is used to configure the data acquisition system without installing it at the substrate processing device manufacturer. - Various observational data observed when identical or similarly shaped substrates are processed in the first chamber and the second chamber under the same conditions are compared, and a correction amount is calculated to correct the various observational data observed when processed in the second chamber. • When searching for optimal processing conditions by processing the substrate in the second chamber while changing the processing conditions, the observation data observed during processing in the second chamber is corrected based on a correction amount, and the corrected observation data is collected.

[0167] As a result, according to the second embodiment, appropriate observational data (without the influence of machine differences and disturbances) can be collected when searching for processing conditions in substrate processing.

[0168] [Third Embodiment] In the first and second embodiments described above, the correction amount calculation process (steps S162 and S167) was described as calculating correction amounts for various observation data. In contrast, in the third embodiment, the correction amount calculation process also calculates correction amounts for various measurement data (specifically, particle measurement data). The third embodiment will now be described, focusing on the differences from the first and second embodiments.

[0169] Figure 14 shows a specific example of the correction amount calculation process performed by the data acquisition system according to the third embodiment. The example in Figure 14 shows that the substrate processing apparatus A1210 processes the pre-processed QC substrate under processing conditions = "condition 0", thereby obtaining a post-processed QC substrate and measuring particle measurement data = "particle measurement data A0".

[0170] Furthermore, the example in Figure 14 shows how the substrate processing device D133 outputs particle measurement data = "particle measurement data D0" after processing the substrate before processing.

[0171] In the data acquisition system according to the third embodiment, the correction amount calculation unit 1410 operates during the correction amount calculation process (steps S162, S167). At this time, the correction amount calculation unit 1410 acquires particle measurement data, "particle measurement data A0" and "particle measurement data D0", output from the substrate processing device A1210 and the substrate processing device D133.

[0172] Furthermore, the correction amount calculation unit 1410 calculates a correction amount p to match the acquired particle measurement data = "particle measurement data D0" to the particle measurement data = "particle measurement data A0", and notifies the collection unit 230 of this correction amount p. As a result, the data collection device 140 can then correct the particle measurement data output from the substrate processing device D133 using the correction amount p and store it in the collected data storage unit 250.

[0173] As a result, according to the third embodiment, appropriate measurement data (without the influence of machine differences and disturbances) can be collected when searching for processing conditions in substrate processing.

[0174] [Fourth Embodiment] In the first to third embodiments described above, it was explained that the optimal processing conditions for achieving the target substrate shape can be searched in the condition narrowing process (step S168). However, it is conceivable that there may be cases in which the data analysis device 150 cannot search for the optimal processing conditions.

[0175] In such cases, the system may be configured to output a result indicating that the target substrate shape cannot be achieved simply by changing the current processing conditions.

[0176] Furthermore, the system may be configured to propose changes to processing conditions other than the current processing conditions. Changes to processing conditions other than the current processing conditions include, for example, pulse modulation and impedance control.

[0177] [Other embodiments] Although specific examples of substrate processing by the substrate processing apparatus were not mentioned in the first to fourth embodiments described above, substrate processing by the substrate processing apparatus may include, for example, film deposition processing and etching processing. Furthermore, although specific examples of the substrate processing apparatus were not mentioned in the first to fourth embodiments described above, the substrate processing apparatus may include etching apparatus, film deposition apparatus, ashing apparatus, annealing apparatus, doping apparatus, etc.

[0178] Furthermore, in the first to fourth embodiments described above, examples of substrate shape data were given, such as limit dimensions, depth, taper angle, tilt angle, bowing, etc., which relate to the appearance of the substrate. However, substrate shape data is not limited to data relating to the appearance of the substrate. For example, substrate shape data may include data other than data relating to the appearance of the substrate, such as film thickness, film type, and film characteristics.

[0179] Furthermore, the term "same processing conditions" in the first to fourth embodiments described above is not limited to cases where the processing conditions are exactly the same. For example, it may include processing conditions that yield the same effect in terms of the change in substrate shape data before and after processing. The term "same effect" here does not mean that the change in substrate shape data before and after processing must be exactly the same, but rather that the change in substrate shape data is of a similar degree (within a predetermined range).

[0180] Furthermore, the term "substrates of the same or similar shape" in the first to fourth embodiments described above includes substrates with similar shape data (within a predetermined range).

[0181] Furthermore, in the first embodiment described above, plasma measurement data, consumption amount measurement data, and particle measurement data were given as examples of various measurement data, but the invention is not limited to these and may include other measurement data.

[0182] Furthermore, although the first embodiment described above assumes that various measurement data are measured by sensors installed inside the substrate processing apparatus, the various measurement data may also be acquired from outside the substrate processing apparatus. In other words, the other measurement data may include, for example, component analysis data obtained by XPS (X-ray Photoelectron Spectroscopy). Alternatively, the other measurement data may include characteristic data obtained by process processing by another process processing apparatus.

[0183] Furthermore, in the first to fourth embodiments described above, the data acquisition device 140 and the data analysis device 150 were configured as separate components, but the data acquisition device 140 and the data analysis device 150 may be configured as a single unit.

[0184] Furthermore, in the first to fourth embodiments described above, the data acquisition device 140 and the data analysis device 150 were configured separately from the substrate processing device 110, or the substrate processing devices A120, B131 to D133. However, the data acquisition device 140 or the data analysis device 150 may be provided inside the substrate processing device 110, or the substrate processing devices A120, B131 to D133.

[0185] Furthermore, in the first to fourth embodiments described above, the data acquisition device 140 and the data analysis device 150 were described as executing the data acquisition program and the data analysis program independently. However, the data acquisition device 140 and the data analysis device 150 may each be composed of, for example, multiple computers, and by installing the data acquisition program or the data analysis program on each, the data acquisition program or the data analysis program may be executed in a distributed computing manner.

[0186] Furthermore, in the first to fourth embodiments described above, one example of a method for installing the data collection program to the auxiliary storage device 1103 of the data collection device 140 was described as downloading and installing it via a network. Similarly, one example of a method for installing the data analysis program to the auxiliary storage device 1123 of the data analysis device 150 was described as downloading and installing it via a network. In this case, the download source was not specifically mentioned, but when installing by this method, the download source may be, for example, a server device that stores the data collection program or data analysis program in an accessible manner. Alternatively, the server device may be a cloud-based device that accepts access from the data collection device 140 or the data analysis device 150 via a network and downloads the data collection program or data analysis program on the condition of payment. In other words, the server device may be a cloud-based device that provides a service for providing the data collection program or data analysis program.

[0187] Furthermore, although the details of the virtual measurement model were not mentioned in the first to fourth embodiments, the virtual measurement model used in the first to fourth embodiments may be, for example, an ARX model. Also, although the details of the shape simulation model were not mentioned in the first to fourth embodiments, the shape simulation model used in the first to fourth embodiments may be, for example, a model based on a convolutional neural network. However, the various models used in the first to fourth embodiments are not limited to these examples, and may include other machine learning learning models including deep learning, statistical models, or models that combine such models.

[0188] It should be noted that the present invention is not limited to the configurations shown in the above embodiments, including combinations with other elements. These aspects can be modified without departing from the spirit of the present invention and can be appropriately determined according to their application.

[0189] This application claims priority based on Japanese Patent Application No. 2021-032890, filed on 2 March 2021, which is incorporated herein by reference to the entire contents of the said Japanese Patent Application. [Explanation of Symbols]

[0190] 100: Data collection system 110: Substrate processing equipment 120: Substrate processing device A 131: Substrate processing device B 132: Substrate Processing Equipment C 133: Substrate Processing Equipment D 140: Data acquisition device 150: Data analysis device 210: Calibration amount calculation section 220: Correction amount calculation section 230: Collection Department 240: Condition Change Section 500: Collected data 610: Virtual Measurement Model Learning Unit 620: Pre-trained virtual measurement model 630: Shape Simulation Model Learning Unit 640: Pre-trained shape simulation model 650: Shape Simulation Control Unit 1200: Data acquisition system 1210: Substrate processing device A

Claims

1. A data acquisition device that communicates 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, A correction amount calculation unit compares the observed data obtained when identical or similarly shaped substrates are processed in the first processing space and the second processing space under the same processing conditions, and calculates a correction amount to correct the observed data obtained when processed in the second processing space. When exploring processing conditions by processing the substrate in the second processing space with varying processing conditions, the collection unit corrects the observed data observed when the substrate is processed in the second processing space based on the correction amount, and collects the corrected observed data as the observed data observed when the substrate is processed in the first processing space. A data acquisition device having the following features.

2. The processing space in Exp. 1 is the same as the reference processing space. The data acquisition device is The system further includes a calibration amount calculation unit that calculates a calibration amount based on machine error from observation data observed when substrates of the same or similar shape are processed in the reference processing space and the first processing space, respectively, under the same processing conditions. The data acquisition device according to claim 1, wherein the observation data observed by processing in the first processing space, which is compared when the correction amount calculation unit calculates the correction amount, is observation data that has been calibrated based on the calibration amount.

3. The second substrate processing apparatus is equipped with additional sensors that are not attached to the first substrate processing apparatus. The aforementioned collection unit is The data acquisition device according to claim 1, which collects measurement data measured by the additionally attached sensor when exploring processing conditions by processing a substrate in the second processing space by changing the processing conditions.

4. The second substrate processing apparatus includes: A substrate processing apparatus to which a sensor for measuring plasma in the second processing space is additionally attached, A substrate processing apparatus to which a sensor for measuring the amount of wear of parts in the second processing space is additionally attached, A substrate processing apparatus to which a sensor for measuring particles in the second processing space is additionally attached, The data acquisition device according to claim 1, comprising at least one of the following:

5. The data acquisition device according to claim 3, which displays measurement data measured by the additionally attached sensor when searching for processing conditions by processing a substrate with different processing conditions in the second processing space.

6. The data acquisition device according to claim 1, further comprising a virtual measurement model learning unit that learns a virtual measurement model using corrected observation data collected by the acquisition unit as input data and measurement data collected by the acquisition unit as ground truth data.

7. The first substrate processing apparatus has a learned virtual measurement model learned by the virtual measurement model learning unit, The data acquisition device according to claim 6, which displays predicted measurement data by inputting the observed data, which is processed in the first processing space, into the trained virtual measurement model.

8. The data acquisition device according to claim 6, further comprising a shape simulation model learning unit that learns a shape simulation model using corrected observation data acquired by the acquisition unit, measurement data acquired by the acquisition unit, and processing conditions for processing the substrate in the second processing space as input data, and processing data of the processed substrate obtained by processing the substrate in the second processing space with different processing conditions as ground truth data.

9. The trained shape simulation model learned by the shape simulation model learning unit, When exploring processing conditions by processing the substrate in the second processing space by changing the processing conditions, a control unit narrows down the processing conditions so that the shape data of the processed substrate predicted by the learned shape simulation model approaches the target shape data. The data acquisition device according to claim 8, further comprising the following:

10. The data acquisition device according to claim 9, further comprising a control unit that narrows down processing conditions for collecting corrected observation data and measurement data used to retrain the learned shape simulation model based on the prediction accuracy of the processed substrate shape data predicted by the learned shape simulation model.

11. The data acquisition device according to claim 9, further comprising a determination unit that, when searching for processing conditions by processing a substrate by changing the processing conditions in the second processing space, predicts the shape data of the substrate after processing using the learned shape simulation model, and determines whether or not it is possible to search for processing conditions in which the difference from the target shape data is less than a predetermined threshold.

12. The first substrate processing apparatus has a learned shape simulation model learned by the shape simulation model learning unit, The data acquisition device according to claim 8, which displays the shape data of a processed substrate predicted by inputting observation data observed by processing in the first processing space, measurement data predicted by inputting the observation data into the trained virtual measurement model, and processing conditions for processing the substrate in the first processing space into the trained shape simulation model.

13. A data acquisition method for a data acquisition device that communicates 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, A step of comparing observation data observed when substrates of the same or similar shape are processed in the first processing space and the second processing space under the same processing conditions, and calculating a correction amount to correct the observation data observed when processed in the second processing space, When exploring processing conditions by processing the substrate in the second processing space with varying processing conditions, the process involves correcting the observed data observed when the substrate is processed in the second processing space based on the correction amount, and collecting the corrected observed data as the observed data observed when the substrate is processed in the first processing space. A data collection method that has [a certain characteristic].

14. A computer in a data acquisition device that communicates 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, A step of comparing observation data observed when substrates of the same or similar shape are processed in the first processing space and the second processing space under the same processing conditions, and calculating a correction amount to correct the observation data observed when processed in the second processing space, When exploring processing conditions by processing the substrate in the second processing space with varying processing conditions, the process involves correcting the observed data observed when the substrate is processed in the second processing space based on the correction amount, and collecting the corrected observed data as the observed data observed when the substrate is processed in the first processing space. A data collection program that has the following features.

15. A method for processing substrates using a mass production machine having a first processing space, The process includes a step of processing a substrate having the same or similar shape as the substrate used when exploring the processing conditions, in the first processing space, under processing conditions explored using an experimental machine having a second processing space. The mass production machine, when processing under the searched processing conditions, is capable of acquiring the searched processing conditions, the shape data of the processed substrate processed in the second processing space under the searched processing conditions, and the corrected observation data observed by processing in the second processing space under the searched processing conditions. The corrected observation data is corrected as observation data observed when processed in the first processing space, based on a correction amount calculated from observation data observed when substrates of the same or similar shape are processed in the first processing space and the second processing space under the same processing conditions. Substrate processing method.

16. A pre-trained virtual measurement model is trained using observational data observed when a circuit board is processed in a mass production machine as input data, and measurement data that is not observed when the circuit board is processed in the mass production machine but is measured when the circuit board is processed by a sensor added to the mass production machine as ground truth data. In a mass production machine to which the aforementioned sensor is added, a trained shape simulation model is trained using the corrected observation data obtained by correcting the observation data observed when the substrate is processed, the measurement data measured by the aforementioned sensor when the substrate is processed, the processing conditions when the substrate is processed, and the shape data of the substrate before processing as input data, and the shape data of the substrate after processing as the ground truth data. The computer in the mounted circuit board processing unit, A step of inputting observation data observed when a substrate is processed in a mass production machine, and displaying the measurement data predicted by the trained virtual measurement model, A process of inputting observation data observed when a substrate is processed in a mass production machine, measurement data predicted by the trained virtual measurement model, processing conditions when the substrate is processed, and the shape data of the substrate before processing, and then displaying the shape data of the substrate after processing, which was predicted by the trained shape simulation model. A substrate processing method that performs this operation.

Images