Information processing device and machine difference analysis method

Abstract

This technology improves the accuracy of analyzing machine differences using sensor data from multiple sensors in multiple substrate processing devices. [Solution] An information processing device for analyzing differences between multiple substrate processing devices, comprising: an acquisition unit for acquiring sensor data from a sensor that detects the state of a substrate processing device while it is executing the same process including multiple steps; a determination unit for determining a normalization coefficient for the sensor and the summary value of the sensor data for each step based on the sensor data for each execution of the process; a normalization processing unit for performing a normalization process on the sensor and the summary value of each step using the normalization coefficient; an analysis unit for analyzing the differences between substrate processing devices based on the summary value after the normalization process; and a display control unit for displaying the results of the analysis.

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus and a machine difference analysis method.

Background Art

[0002] The analysis of the machine differences of conventional substrate processing apparatuses is performed, for example, by an expert who has knowledge about the substrate processing apparatus checking the sensor data of the sensors to be analyzed after narrowing down the sensors to be analyzed from the sensors of the substrate processing apparatus.

[0003] In Patent Document 1, even when the power supplied to the heating unit is made the same, a difference occurs in the temperature profile due to the presence of machine differences, which are individual differences of the apparatus. Therefore, a technique has been proposed in which the target temperature used for controlling the heating unit is corrected so as to absorb the machine differences of the apparatus and the uniformity of the temperature profile is achieved.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The present disclosure provides a technique for improving the accuracy of analyzing machine differences using sensor data of a plurality of sensors of a plurality of substrate processing apparatuses.

Means for Solving the Problems

[0006] One aspect of the present disclosure is an information processing device for analyzing differences between multiple substrate processing devices, comprising: an acquisition unit for acquiring sensor data of a sensor that detects the state of the substrate processing device while it is executing the same process including multiple steps; a determination unit for determining a normalization coefficient for the sensor and the summary value of the sensor data for each step based on the sensor data for each execution of the process; a normalization processing unit for performing a normalization process on the sensor and the summary value for each step using the normalization coefficient; an analysis unit for analyzing differences between the substrate processing devices based on the summary value after the normalization process; and a display control unit for displaying the results of the analysis. [Effects of the Invention]

[0007] According to this disclosure, the accuracy of analyzing machine differences using sensor data from multiple sensors of multiple substrate processing devices can be improved. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram showing an example of the configuration of the substrate processing system 1 according to this embodiment. [Figure 2] This is a hardware configuration diagram of an example computer. [Figure 3] This is a functional block diagram showing an example of a server device 16 according to this embodiment. [Figure 4] This is a flowchart of an example of the machine difference analysis method according to this embodiment. [Figure 5] This figure shows an example of a recipe and sensor data. [Figure 6] This is a flowchart of an example of the process in step S14. [Figure 7] This is an explanatory diagram illustrating an example of the process in step S14. [Figure 8] This is a flowchart of an example of the process in step S14. [Figure 9] This is an explanatory diagram illustrating an example of the process in step S14. [Modes for carrying out the invention]

[0009] The embodiments for carrying out the present invention will be described below with reference to the drawings.

[0010] <System Configuration> Figure 1 is a configuration diagram of an example of a substrate processing system 1 according to this embodiment. The substrate processing system 1 shown in Figure 1 includes a substrate processing apparatus 10, an apparatus controller 12, a sensor 14, a server apparatus 16, and an operator terminal 18.

[0011] The substrate processing apparatus 10, the apparatus controller 12, and the sensor 14 are installed in the manufacturing plant 2. The server apparatus 16 and the worker terminal 18 may be installed in the manufacturing plant 2 or elsewhere. The worker terminal 18 is an information processing terminal operated by an operator, such as an apparatus operator or analysis operator, of the substrate processing apparatus 10 installed in the manufacturing plant 2. The worker terminal 18 is, for example, a PC (Personal Computer) or a smartphone.

[0012] The substrate processing apparatus 10, apparatus controller 12, sensor 14, server device 16, and worker terminal 18 are connected to each other via networks N1 and N2, such as the Internet or LAN (Local Area Network).

[0013] The substrate processing apparatus 10 is an apparatus that performs processes such as film deposition, etching, or ashing, and processes substrates such as semiconductor wafers. The substrate processing apparatus 10 is, for example, a semiconductor manufacturing apparatus, a heat treatment apparatus, or a film deposition apparatus.

[0014] The substrate processing device 10 receives control commands from the device controller 12, for example, according to a recipe, and executes the process. The recipe specifies the steps of the process to be executed by the substrate processing device 10. The process includes multiple steps. For example, the recipe is configured to divide the process into multiple steps (sections).

[0015] The substrate processing apparatus 10 is equipped with a plurality of sensors 14. The sensors 14 detect the state of the substrate processing apparatus 10. The sensors 14 include temperature sensors, humidity sensors, pressure sensors, vibration sensors, distance sensors, flow rate sensors, and the like. The sensor data of the sensors 14 is time-series data. The plurality of substrate processing apparatuses 10 that analyze the machine differences have sensors 14 for comparison targets to analyze the machine differences.

[0016] The substrate processing apparatus 10 may be equipped with the device controller 12, or may not be equipped with the device controller 12 as long as it is communicably connected. Also, although the device controller 12 shown in FIG. 1 is provided for each substrate processing apparatus 10, it may be provided for a plurality of substrate processing apparatuses 10.

[0017] The device controller 12 causes the substrate processing apparatus 10 to execute a process including a plurality of steps by outputting a control command for controlling the control components of the substrate processing apparatus 10 according to a recipe. Note that in the substrate processing apparatus 10, executing a process may be expressed as "RUN". Also, the number of times a process is executed in the substrate processing apparatus 10 may be expressed as the "RUN count".

[0018] The device controller 12 has the function of a man-machine interface that receives instructions for the substrate processing apparatus 10 from an operator and provides information about the substrate processing apparatus 10 to the operator. The device controller 12 receives sensor data output from the plurality of sensors 14 installed in the substrate processing apparatus 10. The device controller 12 may store the sensor data for each execution (hereinafter referred to as "RUN") of the process executed according to the recipe.

[0019] The server device 16 acquires sensor data for each run from the multiple substrate processing devices 10 in the manufacturing plant 2 from the device controller 12 or sensors 14. Based on the acquired sensor data for each run, the server device 16 determines a normalization coefficient for the summary value of the sensor data as described below, performs a normalization process for the summary value of the sensor data using that normalization coefficient, and analyzes the machine differences of the substrate processing devices 10 based on the summary value after the normalization process. The server device 16 may also display the results of the analysis.

[0020] The server device 16 may have a function to provide a human-machine interface to the worker. The server device 16 may also have a function to provide a human-machine interface to the worker who operates the worker terminal 18 using a web application or the like. For example, the worker terminal 18 may receive and display the results analyzed by the server device 16.

[0021] The device controller 12 and the server device 16 may display the information to be presented to the worker on the worker terminal 18. The device controller 12, server device 16, and worker terminal 18 shown in Figure 1 are examples of information processing devices according to this embodiment. For example, at least a part of the process of analyzing the machine differences of the substrate processing device 10, which was described as being performed by the server device 16, may be performed by the device controller 12 or the worker terminal 18.

[0022] It should be noted that the substrate processing system 1 shown in Figure 1 is just one example, and there are various system configurations depending on the application and purpose. The classification of devices such as the device controller 12, server device 16, and worker terminal 18 shown in Figure 1 is just one example. Various configurations are possible, such as a configuration in which at least two of the device controller 12, server device 16, and worker terminal 18 are integrated, or a configuration in which they are further separated.

[0023] <Hardware Configuration> The device controller 12, server device 16, and worker terminal 18 of the substrate processing system 1 shown in Figure 1 are implemented by a computer (information processing device) with the hardware configuration shown in Figure 2, for example. Figure 2 is a hardware configuration diagram of an example computer.

[0024] The computer 500 in Figure 2 includes an input device 501, an output device 502, an external interface 503, RAM (Random Access Memory) 504, ROM (Read Only Memory) 505, a CPU (Central Processing Unit) 506, a communication interface 507, and an HDD (Hard Disk Drive) 508, all of which are interconnected via bus B. The input device 501 and output device 502 may be connected and used only when necessary.

[0025] The input device 501 is a keyboard, mouse, touch panel, etc., used by the operator to input various operation signals. The output device 502 is a display, etc., which displays the processing results from the computer 500. The communication I / F 507 is an interface that connects the computer 500 to network N1 or N2. The HDD 508 is an example of a non-volatile storage device that stores programs and data.

[0026] External I / F 503 is an interface to external devices. Computer 500 can read from and / or write to recording media 503a such as an SD (Secure Digital) memory card via External I / F 503. ROM 505 is an example of a non-volatile semiconductor memory (storage device) that stores programs and data. RAM 504 is an example of a volatile semiconductor memory (storage device) that temporarily holds programs and data.

[0027] The CPU 506 is a processing unit that reads programs and data from storage devices such as the ROM 505 and HDD 508 onto the RAM 504 and executes processing, thereby realizing the overall control and functions of the computer 500.

[0028] The device controller 12, server device 16, and worker terminal 18 in Figure 1 can perform various functions described later by executing programs on the computer 500 with the hardware configuration shown in Figure 2.

[0029] <Functional Configuration> The following describes an example where the information processing device that analyzes the differences between multiple substrate processing devices 10 is a server device 16. The information processing device that analyzes the differences between multiple substrate processing devices 10 may also be a device controller 12 or an operator terminal 18.

[0030] The server device 16 of the substrate processing system 1 according to this embodiment is implemented, for example, by the functional block shown in Figure 3. Figure 3 is a functional block diagram showing an example of the server device 16 according to this embodiment. Note that the functional block diagram in Figure 3 omits the illustration of components that are not necessary for the explanation of this embodiment.

[0031] The server device 16 in Figure 3 implements an acquisition unit 30, a data storage unit 32, a determination unit 34, a standardization processing unit 36, an analysis unit 38, an input reception unit 40, and a display control unit 42 by executing a program for the server device 16.

[0032] The acquisition unit 30 acquires sensor data from multiple sensors 14 that detect the state of the substrate processing apparatus 10 while it is executing the same process. The acquisition unit 30 may acquire the sensor data from the substrate processing apparatus 10, the device controller 12, or the sensors 14 while it is executing the same process. The acquisition unit 30 acquires sensor data for each run. The acquisition unit 30 stores the acquired sensor data for each run of the substrate processing apparatus 10 in the data storage unit 32.

[0033] The input reception unit 40 receives various operations from the operator. For example, operations received from the operator include launching an application and performing various operations on the launched application. The input reception unit 40 notifies the decision unit 34 and the display control unit 42 of the details of the various operations received from the operator.

[0034] The determination unit 34 determines the normalization coefficients for the sensor data and the summary values ​​of the sensor data for each step, based on the sensor data for each run, as described below. Sensor data for each sensor and the sensor data for each step refer to sensor data for each sensor 14 that is separated into steps included in the process.

[0035] Summary values ​​for sensor data are statistics derived from sensor 14 and step-by-step sensor data. Examples of summary values ​​for sensor data include the maximum, minimum, mean, median, or variance of sensor 14 and step-by-step sensor data.

[0036] The normalization coefficient for the summary values ​​of sensor data is used in the normalization process of the summary values ​​of sensor data. Normalization is the process of converting the units or scales of data to a common standard in order to facilitate comparison or analysis.

[0037] The normalization processing unit 36 ​​uses the normalization coefficient determined by the determination unit 34 to perform normalization processing on the sensor 14 and the summary values ​​of the sensor data for each step, as described later.

[0038] The analysis unit 38 analyzes the differences between multiple substrate processing devices 10 based on the summary values ​​of the sensor data after the normalization process performed by the normalization processing unit 36, as described below.

[0039] The display control unit 42 displays the results of the analysis performed by the analysis unit 38 on the output device 502 of the server device 16 or the output device 502 of the worker terminal 18. The display control unit 42 may also display the results of the analysis performed by the analysis unit 38 on the output device 502 of the device controller 12.

[0040] Note that the functional block diagram shown in Figure 3 is just one example. At least a portion of the functional blocks in Figure 3 may be provided in computers 500 other than the server device 16. At least a portion of the functional blocks in Figure 3 may be provided, for example, in the device controller 12 or the worker terminal 18.

[0041] <Normalization process> For example, sensor data normalization processing may be performed based on the resolution of the sensor data of sensor 14. Resolution corresponds to, for example, the sensitivity of sensor 14, and may also be the limit of the fineness of measurement by sensor 14. When sensor data normalization processing is performed based on the resolution of the sensor data of sensor 14, if the sensor data is A and the resolution is B, then A × 10 B Normalization processing is performed by this. Note that B becomes "1" when the resolution is "0.1" and "3" when the resolution is "0.001".

[0042] There may be no correspondence between the resolution of the sensor data from sensor 14 and the amount of change in the sensor data under normal conditions. Therefore, when sensor data normalization is performed based on the sensor data resolution, if the sensor data resolution is very small and the amount of change in the sensor data under normal conditions (a change within the normal range) is large, the instrument difference may be overestimated in the analysis. For example, sensor data with a resolution difference of an order of magnitude will have a 10-fold difference in the amount of change after normalization.

[0043] Therefore, in this embodiment, the sensor data normalization process is improved as follows in order to improve the accuracy of the analysis of machine differences using sensor data from multiple sensors 14 of multiple substrate processing devices 10.

[0044] <Processing> The machine difference analysis method according to this embodiment can be implemented, for example, by the procedure shown in the flowchart of Figure 4. Figure 4 is a flowchart of an example of the machine difference analysis method according to this embodiment. Here, an example in which the server device 16 performs the machine difference analysis method according to this embodiment will be described.

[0045] In step S10, the acquisition unit 30 of the server device 16 acquires sensor data for each run of multiple substrate processing devices 10 that have been executed according to the same process procedure shown in the recipe, and stores it in the data storage unit 32.

[0046] Figure 5 shows an example of a recipe and sensor data. Figure 5(a) shows an example of a recipe. In the recipe in Figure 5(a), the process conditions for recipe A, which is executed by multiple substrate processing devices 10, are shown for each process step. In Figure 5(a), temperature, humidity, pressure, RF, and processing time are shown as examples of process conditions.

[0047] Figures 5(b) and 5(c) show examples of sensor data. Figure 5(b) shows an example of sensor data detected by a sensor 14 called Sensor A of a substrate processing device 10 while the device 10 called Device A is executing Recipe A. Figure 5(c) shows an example of sensor data detected by a sensor 14 called Sensor A of a substrate processing device 10 while the device 10 called Device B is executing Recipe A. Sensor A in Figures 5(b) and 5(c) is the same type of sensor 14 and shows an example of a sensor 14 to be used as a comparison target when analyzing machine differences.

[0048] The sensor data in Figures 5(b) and 5(c) are examples of sensor data for each process run. The sensor data in Figures 5(b) and 5(c) can be divided into steps, with each step representing a period that defines the processing time for each step of the process conditions set in Recipe A in Figure 5(a).

[0049] For example, the sensor data in Figure 5(b) can be divided into sensor data for "Step 1" of Recipe A, sensor data for "Step 2" of Recipe A, sensor data for "Step 3" of Recipe A, and sensor data for "Step 4" of Recipe A, based on the sensor data detected by sensor A of the substrate processing apparatus 10 called apparatus A.

[0050] Furthermore, for example, the sensor data in Figure 5(b) can be divided into sensor data for "Step 1" of Recipe A, sensor data for "Step 2" of Recipe A, sensor data for "Step 3" of Recipe A, and sensor data for "Step 4" of Recipe A, based on the sensor data detected by sensor A of the substrate processing device 10 called device B.

[0051] Note that the sensor data for "Step 1" of Recipe A, the sensor data for "Step 2" of Recipe A, the sensor data for "Step 3" of Recipe A, and the sensor data for "Step 4" of Recipe A are examples of sensor 14 and the sensor data for each step.

[0052] In step S12, the determination unit 34 separates the sensor data for each RUN of the multiple substrate processing apparatus 10 into sensor data for each sensor 14 and sensor data for each step. The determination unit 34 converts the sensor data for each sensor 14 and sensor data for each step into summary values. By performing the processing in step S12, the determination unit 34 calculates summary values ​​for the substrate processing apparatus 10, RUN, sensor 14, and sensor data for each step.

[0053] In step S14, the determination unit 34 determines the normalization coefficients for the sensor 14 converted in step S12 and the summary values ​​of the sensor data for each step. For example, the processing in step S14 may be carried out according to the procedure shown in Figure 6.

[0054] Figure 6 is a flowchart of an example of the process in step S14. Figure 7 is an explanatory diagram of an example of the process in step S14. The five datasets in Figure 7(a) are created, for example, for each of the multiple substrate processing devices 10 that analyze machine differences. The five datasets in Figure 7(a) contain summary values ​​of sensor data from multiple substrate processing devices 10 that are executing the same step of the same process. For example, dataset "1" contains summary values ​​of sensor data from a substrate processing device 10 executing a specific step of a specific process, for a run count of "3". The five datasets in Figure 7(a) are an example of multiple datasets.

[0055] In step S30 of Figure 6, the decision unit 34 selects a dataset with a run count of at least a specific value (specific number of times). The reason for selecting a dataset with a run count of at least a specific value is that if the dataset includes sensor data from sensor 14 with large fluctuations between runs, the summary value of a dataset with an extremely low run count may deviate significantly from the summary values ​​of other datasets. If the summary values ​​deviate significantly, the analyzed instrument difference may become an extremely large value. For example, the decision unit 34 selects a dataset with a run count of 3 or more times.

[0056] For example, in Figure 7(a), datasets "1," "4," and "5," which have 3 or more runs, are selected. Datasets "2" and "3" are excluded from the calculation because they have fewer than 3 runs.

[0057] In step S32, the determination unit 34 calculates the standard deviation of the sensor 14 and the summary values ​​of the sensor data for each step in the dataset selected in step S30. In step S32, the standard deviation of the summary values ​​of the sensor data for each sensor 14 in the dataset selected in step S30 is calculated.

[0058] For example, in Figure 7(a), the standard deviation of the summary values ​​of the sensor data for datasets "1", "4", and "5" is calculated for each sensor 14. For example, in Figure 7(a), the standard deviations of the summary values ​​of the sensor data for sensor 14 called "Sensor A" are calculated as "0.5", "0.6", and "0.05". Also, in Figure 7(a), a resolution is set for each sensor 14. The resolution in Figure 7(a) is the minimum resolution of sensor 14.

[0059] In step S34, the determination unit 34 determines the maximum standard deviation calculated in step S32 as the normalization coefficient. For example, in Figure 7(a), the maximum standard deviation of "0.6" is determined as the normalization coefficient from the standard deviations of "0.5", "0.6", and "0.05" of the summary values ​​of the sensor data of sensor 14 called "sensor A".

[0060] Furthermore, if the minimum resolution is greater than the calculated maximum standard deviation, the determination unit 34 determines the minimum resolution as the normalization coefficient. For example, in Figure 7(a), the minimum resolution "0.01" is greater than the maximum standard deviation "0.008" of the summary value of the sensor data of sensor 14 called "sensor B", so the minimum resolution "0.01" is determined as the normalization coefficient.

[0061] The determination unit 34 determines, for example, the normalization coefficient shown in Figure 7(b) for each sensor 14 from the dataset in Figure 7(a). Figure 7(b) shows an example of a summary value normalization dictionary where the determined normalization coefficient is set for each sensor 14. The process in step S14 can also be expressed as max(maximum standard deviation of summary values ​​included in the dataset with a RUN count of a specific value or more, minimum resolution). max() is a function that outputs the maximum value of the data in parentheses.

[0062] Returning to step S16 in Figure 4, the normalization processing unit 36 ​​performs normalization processing on the sensor 14 and the summary values ​​for each step using the normalization coefficient determined in step S14. The normalization processing in step S16 is performed as shown in equation (1) below.

[0063]

number

[0064] In step S18, the analysis unit 38 analyzes the differences between the multiple substrate processing devices 10 based on the summary values ​​after the normalization process. For example, the analysis unit 38 compresses the data space of the summary values ​​after the normalization process using principal component analysis, and analyzes the differences between the substrate processing devices based on the magnitude of the distance between the summary values ​​in the data space after dimensionality compression.

[0065] In this embodiment, the data is reduced in size through conversion from sensor data to summary values ​​and dimensionality reduction after normalization processing, making it easier to analyze the differences between sensors 14. Furthermore, since normalization processing is performed based on the difference between runs of sensor data, the differences between sensors 14 can be uniformly evaluated as the degree of deviation from the difference between runs, allowing for efficient detection of differences between sensors.

[0066] In step S20, the display control unit 42 displays the results of the analysis in step S18 on the server device 16, the worker terminal 18, or the output device 502 of the device controller 12. The processing in step S20 may also be done by sending an email to the worker notifying them of the results of the analysis in step S18, or by printing it on paper.

[0067] The process in step S14 may also be carried out according to the procedure shown in Figure 8. Figure 8 is a flowchart of an example of the process in step S14. Figure 9 is an explanatory diagram of an example of the process in step S14.

[0068] In step S50, the decision unit 34 selects a dataset that satisfies the conditions. The conditions include having a run count of "2" or more. In step S50, a dataset with a run count of "2" or more is selected in order to perform normalization processing based on the run-to-run difference of the sensor data.

[0069] In step S52, the determination unit 34 calculates the variance (unbiased variance) of the sensor 14 and the summary values ​​of the sensor data for each step of the dataset selected in step S50.

[0070] In step S54, the determination unit 34 calculates the standard deviation using the weighted mean of the number of data points (RUN count) of the calculated variance. The process in step S54 is performed as shown in equation (2) below.

[0071]

number

[0072] In Figure 9(b), the mean of the standard deviations, "0.37," is calculated based on the standard deviations of three substrate processing machines: "0.35" for machine A, "0.21" for machine B, and "0.50" for machine C. The mean of the standard deviations is calculated after converting them to variances.

[0073] In step S56, the determination unit 34 determines the average of the standard deviations of the multiple substrate processing devices 10 calculated in step S54 as the normalization coefficient. In Figure 9(b), the average of the standard deviations calculated in step S54, "0.37", is determined as the normalization coefficient.

[0074] The "Before Normalization" value in Figure 9(a) is a summary value of the sensor data of a specific sensor 14 during the execution of a specific step, and is a summary value converted for each substrate processing device 10 and RUN. The "After Normalization" value in Figure 9(a) is the value obtained by dividing the "Before Normalization" value in Figure 9(a) by the normalization coefficient determined in step S56. For example, the "After Normalization" value "28.2" for "Unit A" and "RUN1" in Figure 9(a) is the value obtained by dividing the "Before Normalization" value "10.5" by the normalization coefficient "0.37" determined in step S56. In addition, the values ​​set in the bottom row of cells in Figure 9(a) represent the range of the summary value before normalization and the range of the summary value after normalization.

[0075] By using equation (2) described above, the normalization coefficient can be prevented from becoming excessively large, even if there are abnormal summary values ​​in the dataset with the largest number of data points.

[0076] According to this embodiment, an expert with knowledge of the substrate processing apparatus 10 can comprehensively analyze the differences between multiple substrate processing apparatuses 10 from the sensor data of all sensors 14, without having to narrow down the sensors 14 to be analyzed from among the sensors 14 of the substrate processing apparatus 10. Furthermore, by comprehensively analyzing the differences between all sensors 14 from the sensor data of all sensors 14, the possibility of missing a sensor 14 that is undergoing a state change from the analysis target can be reduced. In addition, according to this embodiment, a person without knowledge of the substrate processing apparatus 10 can analyze the individual differences (machine differences) of the substrate processing apparatus 10 without having to go through the process of narrowing down the sensors 14 to be analyzed.

[0077] According to this embodiment, the accuracy of machine difference analysis using sensor data from multiple sensors 14 of multiple substrate processing devices 10 can be improved. Furthermore, according to this embodiment, machine difference analysis using sensor data from multiple sensors 14 of multiple substrate processing devices 10 can be facilitated. The machine difference analysis method according to this embodiment can be used, for example, to confirm that there is no difference between the reference device and the mass production device of the substrate processing device 10, that is, to confirm that the reference device and the mass production device are not operating differently. The machine difference analysis method according to this embodiment may also be used to analyze machine differences caused by individual device differences between sensors 14, individual part differences, or assembly errors.

[0078] Although preferred embodiments of the present invention have been described in detail above, the present invention is not limited to the embodiments described above, and various modifications and substitutions can be made to the embodiments described above without departing from the scope of the present invention. [Explanation of Symbols]

[0079] 1. Substrate Processing System 10 Substrate Processing Equipment 12. Device Controller 14 sensors 16 Server Devices 18. Worker terminal N1, N2 Network 30 Acquisition Department 32 Data Storage Unit 34 Decision Section 36. Standardization Processing Unit 38 Analysis Department 40 Input reception section 42 Display Control Unit

Claims

1. An information processing device for analyzing differences between multiple substrate processing devices, An acquisition unit that acquires sensor data from a sensor that detects the state of the substrate processing apparatus while it is executing the same process which includes multiple steps, A determination unit that determines the normalization coefficient of the sensor and the summary value of the sensor data for each step based on the sensor data for each execution of the process, A normalization processing unit performs normalization processing of the sensor and the summary value for each step using the normalization coefficient, Based on the summary value after the standardization process, an analysis unit analyzes the machine differences of the substrate processing device, A display control unit that displays the results of the analysis, An information processing device having

2. The determination unit calculates the standard deviation of the sensor and the summary value of the sensor data for each step included in a dataset from a plurality of datasets that include the sensor data for which the number of executions of the process is greater than or equal to a specific value, selects the largest standard deviation from the calculated standard deviations, and determines the largest standard deviation as the normalization coefficient. The information processing apparatus according to claim 1.

3. The determination unit determines the normalization coefficient to be the larger of the maximum standard deviation or the minimum resolution. The information processing apparatus according to claim 2.

4. The determination unit determines the normalization coefficient to be the standard deviation calculated by using a plurality of datasets that satisfy the conditions, and by using the weighted average of the number of times the process is executed to the variance of the sensor and the summary values ​​of the sensor data for each step included in the dataset. The information processing apparatus according to claim 1.

5. The summary value of the sensor data is a statistical quantity converted from the sensor and the sensor data for each step. The information processing apparatus according to any one of claims 1 to 4.

6. The analysis unit compresses the data space of the summary values ​​after the normalization process using principal component analysis, and analyzes the differences between the substrate processing devices based on the magnitude of the distances between the summary values ​​in the data space after dimensionality compression. The information processing apparatus according to any one of claims 1 to 4.

7. An information processing device that analyzes the differences between multiple substrate processing devices, To acquire sensor data from a sensor that detects the state of the substrate processing apparatus while it is executing the same process which includes multiple steps, Based on the sensor data for each execution of the process, a normalization coefficient is determined for the sensor and the summary value of the sensor data for each step. Using the aforementioned normalization coefficient, the sensor and the summary value for each step are normalized. Based on the summary value after the standardization process, the machine differences of the substrate processing device are analyzed. To display the results of the aforementioned analysis, A method for analyzing differences between machines, including machine differences.

Images