Method for analyzing processed data, and information processing device.

Abstract

To provide a technique that appropriate parts of processed data can be stably analyzed while shortening the time required to analyze processed data.SOLUTION: A processed data analysis method analyzes processed data acquired during operation of a substrate processing apparatus. The processed data analysis method includes the steps of: acquiring processed data; dividing the processed data into multiple sections in time series; and diagnosing a health condition of the substrate processing apparatus on the basis of the processed data in a specific section of the divided multiple sections. In the process of dividing the processed data into multiple sections, start and end points of the multiple sections are determined at a time point to be a prescribed value or a time point changed from the prescribed value, for one or more parameters selected from the parameters of multiple sensors.SELECTED DRAWING: Figure 7

Description

Technical Field

[0001] The present disclosure relates to a method for analyzing processing data and an information processing apparatus.

Background Art

[0002] During the processing of a substrate, a substrate processing apparatus measures various parameters by a plurality of sensors and stores processing data (log information) in which each of the various parameters is associated with time. Then, when a defect occurs in the substrate processing or the like, an information processing apparatus connected to the substrate processing apparatus identifies the cause of the abnormality based on the processing data.

[0003] For example, Patent Document 1 discloses a state prediction apparatus (information processing apparatus) having an algorithm for analyzing tasting data (processing data). This state prediction apparatus predicts the state of a plasma processing apparatus using a first feature amount of processing data measured by a normal apparatus and a second feature amount of processing data measured by an apparatus to be evaluated.

[0004] In recent years, in order to perform more precise substrate processing, the control content has become more sophisticated. Along with this, the amount of parameters during the implementation period of substrate processing has also become enormous, and it is necessary to diagnose the state of the apparatus from a large amount of parameters.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] The present disclosure provides a technique capable of stably analyzing an appropriate portion of processing data while shortening the time required for analyzing the processing data.

Means for Solving the Problems

[0007] According to one aspect of this disclosure, a method for analyzing processing data acquired during the operation of a substrate processing apparatus, ,before The recorded processing data is a combination of the parameters measured by each of the multiple sensors of the substrate processing device and the measured time, and the process involves acquiring the processing data and storing it in the storage unit. A step of determining whether or not the trigger condition for determining the necessity of analyzing the processing data has been met, and if it is determined that the trigger condition has been met, The method for analyzing processing data includes the steps of: reading the processing data from the storage unit and dividing the processing data into a plurality of intervals in a time series according to the measured time; and diagnosing the health status of the substrate processing apparatus based on the processing data in a specific interval among the plurality of intervals, wherein in the step of dividing into a plurality of intervals, the start and end times of the plurality of intervals are determined by the time when one or more parameters selected from the parameters of the plurality of sensors reach a predetermined value or change from the predetermined value. [Effects of the Invention]

[0008] According to one embodiment, it is possible to stably analyze appropriate parts of the processed data while shortening the time required for analyzing the processed data. [Brief explanation of the drawing]

[0009] [Figure 1] This is a diagram showing an example of an information processing system having an information processing device according to one embodiment. [Figure 2] This is a schematic cross-sectional diagram showing the overall configuration of the FPD manufacturing equipment. [Figure 3] This is a hardware configuration diagram showing an example of a computer. [Figure 4] This graph illustrates the time evolution of high-frequency power parameters. [Figure 5] This is a block diagram showing the functional blocks of the server that performs the data processing and analysis method. [Figure 6] This flowchart shows the interval partitioning process for the processed data. [Figure 7]This graph shows an example of dividing the parameters of high-frequency power into multiple intervals. [Figure 8] This is a flowchart showing the process for calculating health values. [Figure 9] This flowchart shows the method for analyzing processed data. [Modes for carrying out the invention]

[0010] The following describes embodiments for implementing this disclosure with reference to the drawings. In each drawing, the same reference numerals are used for identical components, and redundant explanations may be omitted.

[0011] <Configuration of Information Processing System 100> Figure 1 is a configuration diagram showing an example of an information processing system 100 having an information processing device according to one embodiment. As shown in Figure 1, the information processing system 100 includes a plurality of FPD (Flat Panel Display) manufacturing devices 1 and a server 110 to which each FPD manufacturing device 1 is connected via a network 120. The network 120 may employ various communication environments (wired LAN, wireless LAN, etc.) that enable communication between the FPD manufacturing devices 1 and the server 110.

[0012] Multiple FPD manufacturing apparatus 1 is an example of a substrate processing apparatus that processes substrates. The FPD manufacturing apparatus 1 includes multiple sensors 8 that measure various parameters (physical quantities) in substrate processing, and an apparatus controller 9 that controls substrate processing.

[0013] The FPD manufacturing apparatus 1 may have the device controller 9 mounted on the main body of the apparatus, or the device controller 9 may be installed in a separate location and connected to the main body of the apparatus in a communication manner. The device controller 9 outputs commands to the FPD manufacturing apparatus 1 to control the control components of the FPD manufacturing apparatus 1. The device controller 9 also acquires the measured values ​​from each sensor 8 of the FPD manufacturing apparatus 1 that it is controlling as parameters.

[0014] Furthermore, the apparatus controller 9 has a function of a user interface that provides information related to the FPD manufacturing apparatus 1 to the user and receives instructions for the FPD manufacturing apparatus 1 from the operator. Note that the information processing system 100 may have the function as a user interface of each FPD manufacturing apparatus 1 on the server 110 side. Further, one apparatus controller 9 may have a function of directly communicating with the apparatus controller 9 of another FPD manufacturing apparatus 1 or communicating with the apparatus controller 9 of another FPD manufacturing apparatus 1 via the server 110. Thereby, the apparatus controller 9 can utilize information related to a plurality of FPD manufacturing apparatuses 1 (parameters when substrate processing is executed according to the same recipe, etc.).

[0015] Each apparatus controller 9 performs information communication with the server 110 via the network 120. The server 110 manages information related to each FPD manufacturing apparatus 1 transmitted from each apparatus controller 9 and transmits and receives programs, recipes, etc. executed by each apparatus controller 9.

[0016] Note that the information processing system 100 shown in FIG. 1 is an example, and it is needless to say that there are various system configuration examples according to applications and purposes. For example, the information processing system 100 may include a controller that integrates the apparatus controllers 9 of a plurality of FPD manufacturing apparatuses 1 into one apparatus controller, and the server 110 may be applied to this controller.

[0017] <Configuration of the FPD manufacturing apparatus 1> Next, an example of the FPD manufacturing apparatus 1 applied to the information processing system 100 described above will be described while referring to FIG. 2. FIG. 2 is a cross-sectional schematic view showing the overall configuration of the FPD manufacturing apparatus ①. The FPD manufacturing apparatus 1 shown in FIG. 2 is an inductively coupled plasma (ICP) processing apparatus that performs various substrate processes on a flat rectangular substrate G for an FPD.

[0018] It should be noted that there is an error in the number "①" in the original text you provided. It should be "1" in the translation.The FPD may be any of the following: liquid crystal display (LCD), electroluminescence (EL), plasma display panel (PDP), etc. The substrate G is mainly made of glass, but depending on the application, transparent synthetic resin may also be used. The substrate G may have electronic circuits or light-emitting elements patterned on its surface, or it may be a support substrate. Substrate processing for the FPD manufacturing apparatus 1 may include etching or film deposition using the CVD (Chemical Vapor Deposition) method.

[0019] The FPD manufacturing apparatus 1 comprises a rectangular box-shaped processing container 10, a rectangular substrate mounting table 60 in plan view on which the substrate G is placed inside the processing container 10, and the apparatus controller 9 described above.

[0020] The processing container 10 is divided vertically by a dielectric plate 11. The upper space, the antenna chamber, is formed by the upper chamber container 12, and the lower space, the processing chamber S, is formed by the lower chamber container 13. The processing container 10 is provided with a rectangular frame-shaped support frame 14 at the boundary between the upper chamber container 12 and the lower chamber container 13, and the dielectric plate 11 is placed on this support frame 14 as a window member. The processing container 10 is also grounded via a grounding wire 13e.

[0021] The lower chamber container 13 has an inlet / outlet 13b on its side wall 13a for loading and unloading substrates G, and a gate valve 20 for opening and closing the inlet / outlet 13b. A transport module (not shown) equipped with a transport mechanism is adjacent to the lower chamber container 13. The FPD manufacturing apparatus 1 opens the gate valve 20 and loads and unloads substrates G via the inlet / outlet 13b using the transport mechanism.

[0022] Furthermore, the lower chamber container 13 has multiple exhaust ports 13f on its bottom plate 13d. A gas exhaust unit 50 is connected to the exhaust ports 13f. The gas exhaust unit 50 includes a gas exhaust pipe 51 connected to the exhaust ports 13f, a pressure control valve 52 and an exhaust device 53 provided on the gas exhaust pipe 51. The exhaust device 53 includes a turbomolecular pump, a vacuum pump, etc., and reduces the pressure inside the lower chamber container 13 during substrate processing.

[0023] At the upper end of the lower chamber container 13, a shower head 30, consisting of multiple elongated members, is provided to discharge processing gas into the processing chamber S, and also serves as a support beam for supporting the dielectric plate 11. The shower head 30 is made of a metal such as aluminum and has been surface-treated by anodizing. The shower head 30 has a gas flow path 31 extending in the horizontal direction and a plurality of gas discharge holes 32 that communicate between the gas flow path 31 and the processing chamber S.

[0024] The processing container 10 has a gas introduction pipe 45 connected to the upper surface of the dielectric plate 11, which communicates with the gas flow path 31. The gas introduction pipe 45 airtightly penetrates the ceiling 12a of the upper chamber container 12 and is connected to the processing gas supply unit 40. The processing gas supply unit 40 includes a gas supply pipe 41 connected to the gas introduction pipe 45, an on / off valve 42 and a flow rate controller 43 located midway along the gas supply pipe 41, and a processing gas supply source 44 that supplies processing gas. The processing gas is supplied from the processing gas supply source 44 to the shower head 30 via the gas supply pipe 41 and the gas introduction pipe 45, and discharged to the processing chamber S via the gas flow path 31 and the gas discharge hole 32.

[0025] The processing container 10 is equipped with a high-frequency antenna 15 inside an upper chamber container 12 that forms an antenna chamber. The high-frequency antenna 15 is formed by winding an antenna wire 15a made of a conductive metal such as copper in an annular or spiral shape.

[0026] The upper chamber container 12 has a power supply member 16 that extends upward from the terminal of the antenna wire 15a. A power supply line 17 is connected to the upper end of this power supply member 16. The power supply line 17 is connected to a high-frequency power supply 19 outside the processing container 10 via an impedance matching unit 18. The FPD manufacturing apparatus 1 generates an induced electric field in the lower chamber container 13 by supplying high-frequency power of, for example, 13.56 MHz to the high-frequency antenna 15 from the high-frequency power supply 19. This induced electric field causes the processing gas supplied to the processing chamber S from the shower head 30 to be plasma-activated, generating an inductively coupled plasma, and ions and neutral radicals in the plasma are supplied to the substrate G.

[0027] On the other hand, the substrate mounting table 60 includes a base material 63 and an electrostatic chuck 66 installed on the upper surface 63a of the base material 63. The base material 63 is formed in a rectangular shape in plan view, having planar dimensions similar to those of the substrate G. The base material 63 is made of stainless steel, aluminum, aluminum alloy, etc. A meandering temperature control medium channel 62a is provided inside the base material 63. The temperature control medium channel 62a may be provided inside the electrostatic chuck 66.

[0028] Circulation pipes 62b are connected to both ends of the temperature-controlled medium flow path 62a, allowing the temperature-controlled medium to flow in and out of the flow path 62a. The circulation pipes 62b are connected to the chiller 62c. The chiller 62c circulates a temperature-controlled medium such as Garden® or Fluorinert®. The base material 63 may have a built-in heater for temperature control, or it may be configured to control temperature using both the temperature-controlled medium and the heater. A temperature sensor such as a thermocouple is installed in the base material 63, and the measured values ​​(parameters) from the temperature sensors are transmitted to the device controller 9. The device controller 9 controls the temperature control operation of the chiller 62c based on the transmitted parameters.

[0029] Inside the substrate mounting table 60, there are multiple lift pins 78 (for example, 12) that receive and transfer substrates G to and from the transport mechanism (Figure 1 shows two lift pins 78 as a representative example). The multiple lift pins 78 pass through the substrate mounting table 60 and move up and down by the power of a motor transmitted via a connecting member. A base 68 made of insulating material and having a stepped portion on the inside is fixed on the bottom plate 13d of the lower chamber container 13. A base material 63 is placed on the stepped portion of the base 68, and an electrostatic chuck 66 for directly placing the substrate G is installed on the upper surface of the base material 63.

[0030] The electrostatic chuck 66 has a ceramic layer 64, which is a dielectric film formed by thermal spraying ceramics such as alumina, and an adsorption electrode 65 provided inside the ceramic layer 64 to perform electrostatic adsorption. The adsorption electrode 65 is connected to a DC power supply 75 via a power supply line 74 and a switch 76. The device controller 9 applies a DC voltage from the DC power supply 75 to the adsorption electrode 65 by turning on the switch 76. As a result, the adsorption electrode 65 generates a Coulomb force and electrostatically adsorbs the substrate G to the electrostatic chuck 66. When the switch 76 is turned off and a switch 77 interposed in the ground line branched from the power supply line 74 is turned on, the charge accumulated on the adsorption electrode 65 flows to the ground.

[0031] A rectangular frame-shaped focus ring 69, made of ceramics such as alumina or quartz, is placed on the upper surface of the base 68 on the outer circumference of the electrostatic chuck 66. The upper surface of the focus ring 69 is set to be lower than the upper surface of the electrostatic chuck 66.

[0032] A power supply member 70 is connected to the lower surface of the substrate 63, and a power supply line 71 is connected to the lower end of the power supply member 70. The power supply line 71 is connected to a high-frequency power supply 73, which is a bias source, via an impedance matching unit 72. The high-frequency power supply 73 supplies high-frequency power of, for example, 3.2 MHz to the substrate mounting stage 60. As a result, the substrate 63 attracts ions generated in the processing chamber S to the substrate G.

[0033] In other words, the high-frequency power supply 19 connected to the high-frequency antenna 15 is a source for plasma generation, and the high-frequency power supply 73 connected to the substrate mounting table 60 is a bias source that attracts the generated ions and imparts kinetic energy to them. As a result, the FPD manufacturing apparatus 1 can independently generate plasma and control ion energy, thereby increasing the degree of freedom in substrate processing.

[0034] The sensors 8 of the FPD manufacturing apparatus 1 are installed at appropriate locations within the processing container 10 and perform measurements during substrate processing and other operations. For example, the sensors 8 include a source power sensor 81 that detects power supplied from the high-frequency power supply 19 and power reflected from inside the processing container 10, and a bias power sensor 82 that detects power supplied from the high-frequency power supply 73 and power reflected from inside the processing container 10. The source power sensor 81 is installed in the matching unit 18. The bias power sensor 82 is installed in the matching unit 72. The source power sensor 81 and the bias power sensor 82 measure power at sampling intervals of, for example, every 0.1 seconds and transmit the measured power to the apparatus controller 9 or the like. Other examples of sensors 8 in the FPD manufacturing apparatus 1 include a pressure sensor that detects the pressure inside the processing container 10, a temperature sensor that detects the temperature of the substrate 63, and a flow rate sensor that detects the flow rate of the supplied processing gas.

[0035] The parameters (measured values) measured by each sensor 8 are transmitted to the device controller 9 and used by the device controller 9 to control each configuration. The parameters are also transmitted from the device controller 9 to the server 110 via the network 120 and used by the server 110 to manage the status of the FPD manufacturing apparatus 1. Alternatively, the information processing system 100 may be configured to transmit the parameters of each sensor 8 directly to the server 110 without going through the device controller 9.

[0036] <Hardware configuration of the information processing device> The device controller 9 and server 110 of the information processing system 100 shown in Figure 1 are implemented by a computer 500 (information processing device) with a hardware configuration such as that shown in Figure 3. Figure 3 is a hardware configuration diagram showing an example of the computer 500.

[0037] The computer 500 in Figure 3 is equipped with an input device 501, an output device 502, an external I / F (interface) 503, RAM (Random Access Memory) 504, ROM (Read Only Memory) 505, a CPU (Central Processing Unit) 506, a communication I / F 507, and an HDD 508, and these components are interconnected by bus B.

[0038] The input device 501 and output device 502 constitute the user interface described above, and for example, a touch panel may be applied. Alternatively, the input device 501 may be a keyboard, mouse, microphone, etc., and the output device 502 may be a display, speaker, etc. The external I / F 503 is an interface with an external device. The computer 500 can read from and write to an external device such as an external recording medium 503a via the external I / F 503. The communication I / F 507 is an interface that connects the computer 500 to the network 120.

[0039] RAM504 is an example of volatile semiconductor memory (storage device) that temporarily holds programs and data. ROM505 is an example of non-volatile semiconductor memory (storage device) where programs and data are installed. HDD508 is an example of non-volatile storage device that stores programs, data, recipes, etc. The CPU506 reads programs and data from storage devices such as ROM505 and HDD508 onto RAM504 and performs calculations to realize the overall control and functions of the computer 500.

[0040] The computer 500 receives the parameters measured by each sensor 8 during substrate processing of the FPD manufacturing apparatus 1 and stores them in a storage device (e.g., HDD 508) as processing data D (log information) for substrate processing, along with the time being measured within the computer 500. For example, the computer 500 stores the parameters of the RF source traveling wave 83 and RF source reflected wave 84 detected by the source power sensor 81, and the RF bias traveling wave 85 and RF bias reflected wave 86 detected by the bias power sensor 82.

[0041] Figure 4 is a graph illustrating the time evolution of the parameters of high-frequency power (RF source forward wave 83, RF source reflected wave 84, RF bias forward wave 85, RF bias reflected wave 86). In Figure 4, the horizontal axis represents time, and the vertical axis represents high-frequency power.

[0042] For example, the RF bias traveling wave 85 shown in Figure 4 rises sharply from a near-zero state during substrate processing, and then becomes constant at a set power value (specified value). Furthermore, after a predetermined time has elapsed, the RF bias traveling wave 85 experiences a falling power value and becomes constant at a lower power (specified value). After a predetermined time has elapsed at this low power, the RF bias traveling wave 85 experiences another falling power value and becomes near zero.

[0043] On the other hand, the RF bias reflected wave 86 is generated by impedance mismatch when the high-frequency power supply 19 is supplied with high-frequency power, and therefore exhibits a waveform that is linked to the change in the RF bias forward wave 85. Specifically, the RF bias reflected wave 86 repeats its amplitude during the rising edge of the RF bias forward wave 85, and returns to almost zero when the RF bias forward wave 85 stabilizes at a specified value. Furthermore, the RF bias reflected wave 86 repeats its amplitude again during the falling edge of the RF bias forward wave 85, and returns to zero.

[0044] Furthermore, the RF source forward wave 83 rises sharply after the falling edge of the RF bias reflected wave 86 and stabilizes at a power value (specified value) greater than that of the RF bias forward wave. Then, the RF source forward wave 83 falls sharply after a predetermined period of time has elapsed while remaining at the specified value.

[0045] On the other hand, the RF source reflected wave 84 is generated by impedance mismatch when the high-frequency power supply 73 is supplied with high-frequency power, and therefore exhibits a waveform that is linked to the changes in the RF source forward wave 83. In other words, the RF source reflected wave 84 exhibits a waveform in which the amplitude repeats with the rising and falling edges of the RF source forward wave.

[0046] <Monitoring of sensor 8 measurements> The information processing system 100 then performs a processing data analysis method to diagnose the health status of the FPD manufacturing apparatus 1 based on the measurement results measured by each sensor 8 during substrate processing and the state of the substrate during substrate processing. In particular, in this embodiment, a server 110 to which multiple FPD manufacturing apparatuses 1 are connected collects the parameters of each sensor 8 in each FPD manufacturing apparatus 1 and performs the processing data analysis method. Alternatively, the processing data analysis method may be performed for each FPD manufacturing apparatus 1 by the apparatus controller 9 of the FPD manufacturing apparatus 1.

[0047] Figure 5 is a block diagram showing the functional blocks of the server 110 that implements the processing data analysis method. The CPU 506 of the server 110 (see Figure 3) performs calculations on the program stored in the memory device, thereby forming the functional units shown in Figure 5 within the server 110. Specifically, the server 110 contains a processing data acquisition unit 111, a storage area 112, and a data analysis unit 113.

[0048] The processing data acquisition unit 111 acquires processing data D stored in the device controller 9 via the network 120 and stores it in the storage area 112. The processing data D is continuously accumulated in the device controller 9 as time-series information linking the parameters of each sensor 8 with time. The storage area 112 is configured to have a large storage capacity in order to store this processing data D. It is preferable that the processing data acquisition unit 111 labels the parameters of each sensor 8 in each of the multiple FPD manufacturing devices 1 and stores them in the storage area 112. Alternatively, the server 110 may directly receive the parameters of each sensor 8 and form and store time-linked processing data D within the server 110.

[0049] The data analysis unit 113 is a functional unit that analyzes the processing data D stored in the memory area 112 and actually diagnoses the health status of the FPD manufacturing apparatus 1. In particular, the data analysis unit 113 improves processing efficiency by dividing the processing data D into multiple sections during the analysis of the processing data D.

[0050] In other words, over the entire substrate processing period in each FPD manufacturing apparatus 1, the number of parameters measured by each sensor 8 becomes enormous. If a defect occurs in the substrate G during substrate processing, it would take a great deal of time (man-hours) to check all the parameters of each sensor 8 over the entire substrate processing period to search for the cause of the defect. Therefore, in the analysis method of processing data D, a predetermined rule for dividing the processing data D is set in the recipe, and the processing data D is divided into sections, and processing data D of a specific section (section of interest) is extracted from the multiple divided sections. This makes it possible for the server 110 to narrow down the number of parameters to check and shorten the time required for analysis.

[0051] Specifically, the data analysis unit 113 includes an interval setting unit 114 and a diagnostic unit 115 internally. The interval setting unit 114 has the function of dividing the time series of the processed data D into multiple intervals and extracting the processed data D from the divided intervals.

[0052] The processing data D is divided according to the following division rules (A) to (C) set in the recipe, setting multiple intervals and making it possible to extract the processing data D (parameters of multiple sensors 8) for the predetermined intervals. (A) As the first condition, identify the point in time when the value of the processing data D from any sensor changes to a predetermined value, such as being greater than, less than, or equal to. (B) As interval conditions (second condition), the first condition is combined to specify the start and end points of each interval, thereby defining multiple intervals. (C) Extract processing data D within the range that satisfies the start and end points of the interval.

[0053] Based on the above rules, the section setting unit 114 contains an automatic division setting unit 114a and a user division setting unit 114b for dividing the data into sections. The automatic division setting unit 114a is a functional unit that automatically sets the sections to be divided from the processing data D. The user division setting unit 114b is a functional unit that allows the user to set the sections to be divided from the processing data D via the input device 501 and the output device 502 (see Figure 3).

[0054] When the automatic division setting unit 114a receives a trigger condition to start analyzing the processing data, it automatically sets multiple sections of the processing data D based on the recipe rules read from the storage device. Examples of trigger conditions include receiving a code to perform analysis from the FPD manufacturing apparatus 1, or receiving a command to perform analysis from the user via the input device 501. For example, the device controller 9 of the FPD manufacturing apparatus 1 may request analysis when it detects an anomaly through self-diagnosis. Alternatively, the user may perform analysis if a defect occurs in the substrate G after substrate processing. Alternatively, the trigger condition may be the timing of the elapsed of a predetermined monitoring period or the timing of the performed substrate processing a predetermined number of times.

[0055] Below, the procedure for setting intervals in high-frequency power (RF source forward wave 83, RF source reflected wave 84, RF bias forward wave 85, and RF bias reflected wave 86) as processing data D will be described in detail with reference to the processing flow in Figure 6. Figure 6 is a flowchart showing the interval division process of processing data D.

[0056] In the interval division process, the automatic division setting unit 114a first identifies the point in time when the power value of the RF source traveling wave 83 or the power value of the RF bias traveling wave 85 changes (becomes larger or smaller) by a predetermined value or more (step S11). This process conforms to the division rule of (A) described above. The "predetermined value" for capturing the change in the processed data D is a predetermined numerical range, which is preferably determined by the characteristics of each sensor 8, for example, a value greater than or equal to the noise that can exclude the noise generated in each sensor 8.

[0057] Next, the automatic division setting unit 114a determines whether the power value of the high-frequency power has transitioned from zero (specified value) at the point in time identified in step S11 (step S12). If the power value has transitioned from zero (step S12: YES), the unit proceeds to step S13; if the power value has transitioned from a value other than zero (step S12: NO), the unit proceeds to step S17.

[0058] In step S13, the automatic division setting unit 114a sets the start of the change in power value from zero to the start of the interval. This process conforms to the division rule (B) described above. As a result, the automatic division setting unit 114a can include the point in time when the power value of appropriate parameters (RF source traveling wave 83, RF bias traveling wave 85) rises from zero in one interval, that is, an interval in which the parameters change from zero and become unstable.

[0059] After step S13, the automatic division setting unit 114a sets the termination point to the time when either the RF source forward wave 83 or the RF bias forward wave 85 reaches a specified value and the RF source reflected wave 84 or the RF bias reflected wave 86 becomes zero (step S14). This process also conforms to the division rule of (B) described above. The "specified value" in this step corresponds to the power for the RF source output by the high-frequency power supply 19 to the processing container 10, or the power for the RF bias output by the high-frequency power supply 73, and can therefore be calculated from the value described in the recipe. This allows the automatic division setting unit 114a to include the range of power value changes from when the power value of an appropriate parameter changes until it stabilizes at a specified value in the aforementioned interval where the parameter is unstable after changing from zero.

[0060] Furthermore, the automatic division setting unit 114a sets the same time point as in step S14 as the start time of the next section (step S15). This process also conforms to the division rule in (B) described above. This allows the automatic division setting unit 114a to easily set the start time of the next section.

[0061] After step S15, the automatic division setting unit 114a sets the end point to the point in time when the RF source traveling wave 83 or RF bias traveling wave 85, which is at a predetermined value, changes (step S16). This process also conforms to the division rule of (B) described above. As a result, the automatic division setting unit 114a can include the range of power values ​​from the point in time when the power value of the appropriate parameter stabilizes at a predetermined value until the point in time when it changes, within the interval in which the parameter is in a stable state.

[0062] On the other hand, if the power value transitions from a non-zero value, the automatic division setting unit 114a sets the start of that non-zero change to the start of the interval (step S17). This process also conforms to the division rule of (B) described above. When the power value transitions from a non-zero value, the RF source reflected wave 84 or RF bias reflected wave 86 remains almost unchanged and continues to be at zero. Therefore, the automatic division setting unit 114a can capture the change point of each traveling wave by monitoring the RF source traveling wave 83 or RF bias traveling wave 85.

[0063] After step S17, the automatic division setting unit 114a sets the point in time when the RF source forward wave 83 or RF bias forward wave 85 reaches a specified value as the end point (step S18). This process also conforms to the division rule (B) described above. As a result, even if the power value transitions from a non-zero value, the automatic division setting unit 114a can include the range of power values ​​up to the point in time when the power value reaches a specified value in a single interval.

[0064] Then, after step S18, the automatic division setting unit 114a proceeds to step S19, similar to the end of step S16. After step S16 or S18, the automatic division setting unit 114a determines whether or not the setting of the intervals of the processing data D has been performed over the entire period of the substrate processing (step S19). If it has not been performed over the entire period of the substrate processing (step S19: NO), it returns to step S12 and repeats the same processing flow thereafter. On the other hand, if it has been performed over the entire period of the substrate processing (step S19: YES), it proceeds to step S20.

[0065] In step S20, the automatic division setting unit 114a selects a specific section (section of interest) from which to extract the processed data D from among multiple sections set by repeating steps S12 to S18. This process conforms to the division rule (C) described above. The section of interest can be set automatically or by prior selection by the user, depending on the content of the board processing and the state of the board G.

[0066] For example, if a defect occurs in the substrate processing on almost the entire surface of substrate G, it is assumed that the supply of high-frequency power during substrate processing is lower than the target. Therefore, the automatic division setting unit 114a identifies the section in which the power value is stable at a specified value as the section of interest. Alternatively, for example, based on receiving abnormal codes such as voltage rise and fall times from the FPD manufacturing apparatus 1, the automatic division setting unit 114a may identify the unstable state during the rise and fall of the power value as the section of interest.

[0067] Then, the automatic segmentation setting unit 114a extracts the parameters of each sensor 8 in the section of interest identified in step S20 (step S21). As a result, the automatic segmentation setting unit 114a provides only the processing data D in the automatically segmented section and in the section of interest, thereby streamlining the subsequent processing in the diagnostic unit 115.

[0068] Next, an example of high-frequency power divided by the interval division process described above will be explained using Figure 7. Figure 7 is a graph showing an example of dividing the parameters of high-frequency power into multiple intervals.

[0069] Each parameter of the high-frequency power is divided into sections A to G by the section division process. Here, section A starts at time t1 and ends at time t2. Time t1 is the starting point when the RF bias traveling wave 85 rises sharply from zero, and is identified in step S13 of Figure 6. Time t2 is the ending point when the RF bias traveling wave 85 reaches a predetermined value and the RF bias reflected wave 86 becomes zero, and is identified in step S14 of Figure 6.

[0070] Furthermore, in section B, time t2 is the start point and time t3 is the end point. Time t2, which is the start point of section B, is identified in step S15 of Figure 6. Time t3 is the end point when the RF bias traveling wave 85 falls, and is identified in step S16 of Figure 6.

[0071] Interval C begins at time t3 and ends at time t4. Time t3, the starting point of interval C, is identified in step S17 of Figure 6. Time t4 is identified in step S18 of Figure 6.

[0072] Interval D starts at time t4 and ends at time t5. Time t4, as the starting point of interval D, is identified in step S16 of Figure 6. Time t5 is identified in step S17 of Figure 6.

[0073] Similarly, the RF source forward wave can also be divided into segments. Specifically, segment E captures the range of change during the rising edge of the RF source forward wave 83, with time t6 as the start point and time t7 as the end point. Segment F captures the stable range where the RF source forward wave 83 stabilizes at a specified value, with time t7 as the start point and time t8 as the end point. Segment G captures the range of change during the falling edge of the RF source forward wave 83, with time t8 as the start point and time t9 as the end point.

[0074] In this way, the automatic division setting unit 114a can smoothly divide each parameter in the substrate processing into stable and unstable sections by performing the above-described section division processing flow. Furthermore, the automatic division setting unit 114a can, of course, divide the processing data D of other sensors 8 into change range and stable range sections using the same section division processing.

[0075] Returning to Figure 5, the diagnostic unit 115 of the data analysis unit 113 diagnoses the health status of each FPD manufacturing device 1 by calculating the health status of each interval of interest based on the processing data D of the interval of interest extracted by the interval setting unit 114. The "health status" of the device refers to, for example, the extent to which each parameter of the processing data D deviates from the reference value in the normal state of the device, which is quantified as a health value (an indicator of health status), or a determination of normal or abnormal based on the health value. The "reference value" in this case can be set to an appropriate value by pre-setting it at the time of shipment of the device through experiments or simulations, or by learning the parameters of a specific number of processing data D that are considered normal as training data during the operation of the device.

[0076] Therefore, the diagnostic unit 115 internally includes a health value calculation unit 115a and an abnormality determination unit 115b. For example, the health value calculation unit 115a performs a health value calculation process as shown in Figure 8 in order to calculate a health value based on the processing data D of the interval of interest by the interval setting unit 114. Figure 8 is a flowchart of the health value calculation process.

[0077] In the health value calculation process, the health value calculation unit 115a acquires processing data D for the section of interest selected by the section setting unit 114 (step S31). At this time, the health value calculation unit 115a may acquire all parameters in the processing data D for the section of interest, or it may extract specific parameters based on the possibility of abnormality. For example, if it is estimated that there is an abnormality in the health status of the power system of the FPD manufacturing apparatus 1, the health value calculation unit 115a acquires parameters of the processing data D related to the power system.

[0078] Furthermore, the health value calculation unit 115a standardizes each parameter of the acquired sensor 8 in the interval of interest and calculates a health value for each (step S32). In calculating this health value, for example, the following equation (1) is used to apply the feature quantities V of each parameter of the standardized processed data D.

[0079] V = (Da - X) / Y …(1)

[0080] Here, Da in equation (1) is a parameter of the processing data D before standardization. X is the mean of all samples of features in a normal FPD manufacturing device 1. Y is the variance (or standard deviation) of all samples of features in a normal FPD manufacturing device 1.

[0081] The feature quantity V of the processed data D calculated using the above formula (1) corresponds to a health value, which is a numerical indicator of the health status of the device, showing how far it deviates from its normal state. Therefore, the larger this health value, the further the device is from its normal state, and conversely, the smaller this value, the closer the device is to its normal state. For this reason, in step S32, the health value calculation unit 115a calculates all feature quantities V for each parameter of the processed data D of the interval of interest and stores them in the memory. Through the above health value calculation process, the diagnostic unit 115 can obtain the health value (feature quantity V) of the interval of interest for each sensor 8.

[0082] Furthermore, the abnormality determination unit 115b of the diagnostic unit 115 determines whether the FPD manufacturing apparatus 1 is normal or abnormal using the health values ​​of each sensor 8 in the interval of interest. For example, the abnormality determination unit 115b compares the health values ​​of each sensor 8 in the interval of interest with a preset acceptable range for the health values ​​of each sensor 8. The abnormality determination unit 115b then determines that there is no abnormality in the FPD manufacturing apparatus 1 if the health values ​​are within the acceptable range, while determining that there is an abnormality in the FPD manufacturing apparatus 1 if the health values ​​are outside the acceptable range.

[0083] Furthermore, if the health value falls outside the acceptable range, the abnormality determination unit 115b identifies the sensor 8 and determines which part of the device is malfunctioning. For example, if the health value calculated in the interval of interest of the RF bias traveling wave 85 falls outside the acceptable range, the abnormality determination unit 115b identifies a malfunction in the components related to the RF bias traveling wave 85 (power supply member 70, power supply line 71, matching unit 72, high-frequency power supply 73, etc.). The diagnostic unit 115 then notifies the user of the identified malfunction via the output device 502, prompting the user to take necessary action.

[0084] The diagnostic unit 115 is not limited to a configuration that determines whether the device is normal or abnormal by comparing the health value with an acceptable range. For example, the diagnostic unit 115 may display the health value directly on the output device 502 as the health status of the FPD manufacturing apparatus 1. In displaying this health status, the health value may be associated with display information that is easy for the user to recognize (for example, image information such as normal, caution, maintenance required) to provide notification. Furthermore, the information processing system 100 may take measures such as stopping the operation of the FPD manufacturing apparatus 1 that has been determined to be abnormal, or not performing substrate processing.

[0085] The information processing system 100 according to this embodiment is basically configured as described above, and its operation (method of analyzing processed data) will be explained below.

[0086] The server 110 of the information processing system 100 communicates with the device controller 9 of each FPD manufacturing device 1 and manages the status of each FPD manufacturing device 1 (whether it is in operation, whether there are substrates G, the operation details of substrate processing, processing time, etc.). The server 110 also issues commands to transport modules installed adjacent to each FPD manufacturing device 1, causing the transport mechanism to move substrates G into and out of the processing chamber S of each FPD manufacturing device 1.

[0087] The device controller 9 of each FPD manufacturing apparatus 1 places the substrate G in the processing container 10 and then performs substrate processing on the substrate G. During substrate processing, each sensor 8 continuously takes measurements and transmits the measured values ​​to the device controller 9, which then appropriately controls each component based on the measured values ​​of each sensor 8. The device controller 9 also stores processing data D, which links the measured values ​​(parameters) of each sensor 8 with time, in a storage device.

[0088] Figure 9 is a flowchart showing the method for analyzing processing data. After the substrate processing by the FPD manufacturing apparatus 1, the server 110 acquires the processing data D stored in the apparatus controller 9 and stores it in the server 110's storage area 112, as shown in Figure 9 (step S1).

[0089] The server 110 then determines whether the trigger condition for analyzing the processed data D has been met (step S2). As mentioned above, the trigger condition may be an analysis request from the FPD manufacturing apparatus 1 or an analysis request made by the user.

[0090] Server 110 enters a standby state if the trigger condition is not met. If there is no need for analysis, the trigger condition will not be met, and the process will terminate (Step S2: NO). On the other hand, if the trigger condition is met (Step S2: YES), Server 110 proceeds to analyze the processing data D of the target FPD manufacturing device 1. The same applies if the trigger condition is met while in the standby state.

[0091] At this point, the data analysis unit 113 performs a subroutine for interval division processing on the processing data D of each sensor 8 stored in the memory area 112 (step S3). In the interval division processing, the automatic division setting unit 114a divides the processing data D of each sensor 8 into multiple intervals by performing the processing flow shown in Figure 6 above, and further extracts the processing data D of the interval of interest.

[0092] Next, the diagnostic unit 115 uses the processing data D of the interval of interest extracted in step S3 to perform a health value calculation subroutine (step S4) which calculates the health value of the interval of interest for each sensor 8. In the health value calculation process, the diagnostic unit 115 calculates the health value by performing the processing flow shown in Figure 8 above.

[0093] The diagnostic unit 115 then compares the calculated health value for each of the 8 sensors with the acceptable range to determine whether the health value is within the acceptable range (step S5). If the health value is within the acceptable range (step S5: YES), the unit proceeds to step S6; however, if the health value is outside the acceptable range (step S5: NO), the unit proceeds to step S7.

[0094] In step S6, the data analysis unit 113 notifies the FPD manufacturing apparatus 1 of the normal operation of the processed data D via the output device 502. At this time, the data analysis unit 113 may also perform processing such as displaying the processed data D that has been analyzed, or displaying the calculated health value for each sensor 8.

[0095] On the other hand, in step S7, the data analysis unit 113 notifies the FPD manufacturing apparatus 1 of any abnormalities in the processed data D via the output device 502. At this time, the data analysis unit 113 may perform processing such as displaying the location of the abnormality identified based on the processed data D for each sensor 8, or displaying the calculated health value for each sensor 8.

[0096] Then, when the processing flow of step S6 or S7 is completed, the server 110 terminates the analysis method for the processed data D.

[0097] The analysis method for processing data D and the information processing apparatus relating to this disclosure are not limited to those described above and can be modified in various ways. For example, the analysis method for processing data D can also analyze parameters such as temperature, pressure, and flow rate of the substrate processing apparatus in the same way as the analysis of high-frequency power described above. Alternatively, for example, the analysis method for processing data D may first divide the processing data D based on multiple steps in the substrate processing, and then set multiple sections and perform a health status diagnosis for the processing data D of a predetermined step. This can further shorten the time required for the analysis of processing data D. The order of steps S1 and S2 may also be reversed. Specifically, for example, the analysis process in step S2 may be started by setting the fulfillment of the trigger condition for performing the analysis as an input condition, acquiring the processing data D and storing it in the storage area 112. Subsequently, the processing from step S3 onward is carried out in the same manner as described above.

[0098] The analysis method for processing data D may involve diagnosing the health status of the device using the time lengths of the intervals into which the processing data D is divided. For example, if the time length of the interval in an unstable state in the processing data D is longer than the reference time, it can be determined that there is an abnormality in the device. Furthermore, in the analysis method for processing data D, the processing flow for calculating health values ​​from the divided processing data D is not limited to the example in Figure 8, and various processing flows may be adopted. For example, the diagnostic unit 115 may calculate the correlation coefficient between each parameter of the processing data D and its corresponding reference value, and use the calculated correlation coefficient as the health value.

[0099] The technical ideas and effects of this disclosure, as described in the embodiments above, are described below.

[0100] A first aspect of the present invention is a method for analyzing processing data D acquired during the operation of a substrate processing apparatus (FPD manufacturing apparatus 1), wherein the processing data D is a combination of parameters measured by each of a plurality of sensors 8 of the substrate processing apparatus and the time at which they were measured, and comprises the steps of: acquiring the processing data and storing it in a storage unit (HDD 508); reading the processing data D from the storage unit and dividing the processing data D into a plurality of intervals in a time series according to the time at which it was measured; and diagnosing the health status of the substrate processing apparatus based on the processing data D in a specific interval (interval of interest) among the plurality of intervals, wherein in the step of dividing into a plurality of intervals, the start and end times of the plurality of intervals are determined by the time at which one or more parameters selected from the parameters of the plurality of sensors 8 reach a predetermined value or change from a predetermined value.

[0101] As described above, the analysis method for processing data D can easily limit the processing data D used to diagnose the health status of the substrate processing apparatus (FPD manufacturing apparatus 1) by dividing it into multiple intervals based on the point in time when the selected parameter reaches a specified value or changes from a specified value. This allows the analysis method for processing data D to stably analyze the appropriate parts of the processing data D while shortening the time required for analysis. As a result, the analysis method for processing data D can accurately diagnose the health status of the substrate processing apparatus.

[0102] Furthermore, if one or more parameters change during the process of dividing into multiple sections, the section is divided into a section containing parameters that become unstable as a result of the change, and a section containing only parameters that remain stable after the change. This allows the analysis method of the processed data D to divide the data into sections where the parameters are unstable and sections where the parameters are stable, enabling a proper diagnosis of the health of the substrate processing apparatus (FPD manufacturing apparatus 1) according to the purpose.

[0103] Furthermore, an unstable state occurs when one or more parameters change from zero. This allows the analysis method for processed data D to smoothly divide the data into a section of transient phenomena in the parameters when they change from zero, and a section of stable parameters.

[0104] Furthermore, the analysis method for processed data D defines the end of one interval as the start of the next interval following that interval. This allows for easy configuration of the first and next intervals in the analysis method for processed data D.

[0105] Furthermore, in the process of dividing the data into multiple intervals, the point at which the parameter becomes larger than a predetermined numerical range relative to the specified value, or smaller than a predetermined numerical range, is identified as the point at which the parameter changes from the specified value. This allows the analysis method of the processed data D to easily exclude noise generated in the sensor 8 and identify the point at which the parameter changes.

[0106] Furthermore, in the process of diagnosing the health status of the substrate processing apparatus (FPD manufacturing apparatus 1), a health value, which is a numerical indicator of the health status of the substrate processing apparatus, is calculated based on the processing data D of a specific interval (interval of interest). By calculating the health value based on the processing data D of the interval of interest in this way, the method of analyzing the processing data makes it possible to make the user aware of the numerical health status.

[0107] Furthermore, in the process of diagnosing the health status of the substrate processing apparatus (FPD manufacturing apparatus 1), the calculated health value is compared to whether it is within the set tolerance range. If the health value is within the tolerance range, the substrate processing apparatus is determined to be normal; if the health value is outside the tolerance range, the substrate processing apparatus is determined to be abnormal. As a result, the processing data analysis method can accurately determine whether the substrate processing apparatus is normal or abnormal based on the calculated health value.

[0108] Furthermore, processing data D consists of parameters measured by each of the multiple sensors 8 when substrate processing is performed in the substrate processing apparatus (FPD manufacturing apparatus 1). This allows the analysis method of processing data D to effectively monitor the health status of the substrate processing apparatus using the parameters during substrate processing.

[0109] Furthermore, the substrate processing apparatus (FPD manufacturing apparatus 1) is a plasma processing apparatus that applies plasma processing to a substrate. The multiple sensors 8 include a source power sensor 81 that measures the RF source traveling wave and RF source reflected wave as parameters, and a bias power sensor 82 that measures the RF bias traveling wave and RF bias reflected wave as parameters. In the process of dividing into multiple sections, the start time of the section is defined as the point in time when the RF source traveling wave or RF bias traveling wave changes from zero, and the end time of the section is defined as the point in time when the RF source reflected wave or RF bias reflected wave stabilizes at zero after the start time of the section. As a result, the analysis method for processing data D can appropriately set the sections for dividing the processing data D based on the RF source traveling wave, RF source reflected wave, RF bias traveling wave, and RF bias reflected wave.

[0110] Furthermore, a second aspect of this disclosure is an information processing device (device controller 9, server 110) that analyzes processing data D acquired during the operation of a substrate processing device (FPD manufacturing device 1), wherein the processing data D is a combination of parameters measured by each of the multiple sensors 8 of the substrate processing device and the time at which they were measured, and the information processing device performs the steps of acquiring the processing data D and storing it in a storage unit (HDD 508), reading the processing data D from the storage unit and dividing the processing data D into multiple intervals in a time series according to the time at which it was measured, and diagnosing the health status of the substrate processing device based on the processing data D in a specific interval (interval of interest) among the divided intervals, and in the step of dividing into multiple intervals, the start and end times of the multiple intervals are determined by the time at which one or more parameters selected from the parameters of the multiple sensors 8 reach predetermined values ​​or change from predetermined values. Even in this case, the information processing device can stably analyze appropriate parts of the processing data D while shortening the time required to analyze the processing data D.

[0111] The method for analyzing processed data D and the information processing apparatus according to the embodiments disclosed herein are illustrative and not restrictive in all respects. The embodiments can be modified and improved in various ways without departing from the scope and spirit of the appended claims. The matters described in the above embodiments can be configured in other ways and combined in a non-consistent manner.

[0112] The substrate processing apparatus described herein can, of course, be applied to substrate processing apparatuses other than FPD manufacturing apparatus 1, such as semiconductor wafer processing apparatuses. Furthermore, although this disclosure describes an inductively coupled plasma (ICP) processing apparatus that uses a dielectric plate as a window member, an inductively coupled plasma (ICP) processing apparatus that uses a metal plate as a window member instead of a dielectric plate may also be used. Moreover, the invention is not limited to inductively coupled plasma (ICP) processing apparatuses; for example, substrate processing apparatuses include Atomic Layer Deposition (ALD) apparatuses, Capacitively Coupled Plasma (CCP) apparatuses, Radial Line Slot Antenna (RLSA) apparatuses, Electron Cyclotron Resonance Plasma (ECR) apparatuses, Helicon Wave Plasma (HWP) apparatuses, and the like. [Explanation of symbols]

[0113] 1 FPD manufacturing equipment 8 sensors 9. Device Controller 110 Servers D Processing data HDD 508

Claims

1. A method for analyzing processing data acquired during the operation of a substrate processing device, The processing data is a combination of the parameters measured by each of the multiple sensors of the substrate processing device and the measured time. The process of acquiring the aforementioned processing data and storing it in the storage unit, A step of determining whether or not the trigger condition for determining the necessity of analyzing the processing data has been met, When it is determined that the trigger condition has been met, the process involves reading the processing data from the storage unit and dividing the processing data into multiple intervals in a time series according to the measured time, The process includes a step of diagnosing the health status of the substrate processing apparatus based on the processing data in a specific section among the multiple divided sections, In the process of dividing into multiple sections, The start and end times of the multiple aforementioned intervals are determined by the time when one or more parameters selected from the parameters of the multiple aforementioned sensors reach a predetermined value or when they change from that predetermined value. Method for analyzing processed data.

2. If one or more of the parameters change during the process of dividing into multiple sections, the section is divided into a section containing the parameter that becomes unstable as a result of the change, and a section containing only the parameter that remains stable after the change. The method for analyzing processed data according to claim 1.

3. The aforementioned unstable state occurs when one or more of the aforementioned parameters change from zero. The method for analyzing processed data according to claim 2.

4. The end time of one of the aforementioned sections shall be the start time of the next section following the first aforementioned section. A method for analyzing processed data according to any one of claims 1 to 3.

5. In the step of dividing into multiple intervals, the point in time when the parameter becomes greater than or less than a predetermined numerical range relative to the specified value is identified as the point in time when it changes from the specified value. A method for analyzing processed data according to any one of claims 1 to 3.

6. In the step of diagnosing the health status of the substrate processing apparatus, a health value, which is a numerical value of an indicator showing the health status of the substrate processing apparatus, is calculated based on the processing data of a specific section. A method for analyzing processed data according to any one of claims 1 to 3.

7. In the step of diagnosing the health status of the substrate processing apparatus, the calculated health value is compared with whether it is within a set tolerance range, and if the health value is within the tolerance range, it is determined that the substrate processing apparatus is normal, and if the health value is not within the tolerance range, it is determined that the substrate processing apparatus is abnormal. The method for analyzing processed data according to claim 6.

8. The processing data is a set of parameters measured by each of the multiple sensors when substrate processing is performed in the substrate processing apparatus. A method for analyzing processed data according to any one of claims 1 to 3.

9. The aforementioned substrate processing apparatus is a plasma processing apparatus that performs plasma processing on a substrate, The plurality of sensors include a source power sensor that measures the RF source traveling wave and the RF source reflected wave as parameters, and a bias power sensor that measures the RF bias traveling wave and the RF bias reflected wave as parameters, In the step of dividing into multiple sections, the start time of the section is defined as the point in time when the RF source forward wave or the RF bias forward wave changes from zero, and the end time of the section is defined as the point in time after the start time of the section when the RF source reflected wave or the RF bias reflected wave stabilizes at zero. A method for analyzing processed data according to any one of claims 1 to 3.

10. An information processing device for analyzing processing data acquired during the operation of a substrate processing device, The processing data is a combination of the parameters measured by each of the multiple sensors of the substrate processing device and the measured time. The aforementioned information processing device is The process of acquiring the aforementioned processing data and storing it in the storage unit, A step of determining whether or not the trigger condition for determining the necessity of analyzing the processing data has been met, When it is determined that the trigger condition has been met, the process involves reading the processing data from the storage unit and dividing the processing data into multiple intervals in a time series according to the measured time, The process involves diagnosing the health status of the substrate processing apparatus based on the processing data in a specific section among the multiple divided sections, In the process of dividing into multiple sections, The start and end times of the multiple aforementioned intervals are determined by the time when one or more parameters selected from the parameters of the multiple aforementioned sensors reach a predetermined value or when they change from that predetermined value. Information processing device.

Images