Temperature Estimation Device, Plasma Processing System, Temperature Estimation Method, and Temperature Estimation Program

Abstract

To provide a temperature estimation device, a plasma processing system, a temperature estimation method, and a temperature estimation program that estimate the temperature according to a change in the state of a processing space in which plasma processing is performed.SOLUTION: A temperature estimation device includes an estimation unit that sequentially estimates temperature data by sequentially inputting a new time-series process data related to the state in a processing space to a generated time-series model in which data in each time range of time-series process data related to a state in the processing space where the plasma processing is performed is associated with data in each time of time-series temperature data measured in the processing space.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a temperature estimation device, a plasma processing system, a temperature estimation method, and a temperature estimation program.

Background Art

[0002] In the semiconductor manufacturing process, in order to maintain the quality of the wafer to be plasma processed, it is important to adjust the temperature in the processing space to a predetermined range. On the other hand, in the case of the semiconductor manufacturing process, it is difficult to permanently install a temperature sensor in the processing space and directly measure the temperature in the processing space. For this reason, the temperature in the processing space is indirectly obtained by estimation or the like.

[0003] As an example, in Patent Document 1 below and the like, an estimation method for estimating the temperature in the processing space using the process conditions during plasma processing has been proposed. According to the estimation method, by acquiring the process conditions before the start of plasma processing, the temperature in the processing space during plasma processing can be estimated.

[0004] However, even if the process conditions are the same, if the state in the processing space has changed (for example, if the temperature at the start of plasma processing has risen / fallen, or if the temperature of the parts in the processing space has risen during plasma processing), the estimation accuracy of the temperature decreases.

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 temperature estimation device, a plasma processing system, a temperature estimation method, and a temperature estimation program for estimating a temperature according to a change in the state within a processing space where plasma processing is performed.

Means for Solving the Problems

[0007] The temperature estimation device according to one aspect of the present disclosure has, for example, the following configuration. That is, An estimation unit that sequentially estimates temperature data by sequentially inputting new time-series process data related to the state within the processing space into a generated time-series model in which data in each time range of time-series process data related to the state within the processing space where plasma processing is performed is associated with data at each time of the time-series temperature data measured within the processing space and , a control unit that controls the processing time of the plasma processing or the amount of power of the RF power supply for plasma processing so that the temperature data sequentially estimated by the estimation unit reaches a target temperature before the plasma processing is started or while the plasma processing is being performed and has.

Advantages of the Invention

[0008] According to the present disclosure, it is possible to provide a temperature estimation device, a plasma processing system, a temperature estimation method, and a temperature estimation program for estimating a temperature according to a change in the state within a processing space where plasma processing is performed.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Mode for Carrying Out the Invention

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

[0011] [First Embodiment] <System Configuration of Plasma Processing System> First, the system configuration of a plasma processing system to which the temperature estimation device according to the first embodiment is applied will be described. In the first embodiment, the temperature estimation device has functions executed in the model generation phase and functions executed in the estimation phase. Therefore, hereinafter, the plasma processing system to which the temperature estimation device in which each function is executed is applied will be described separately.

[0012] (1) System Configuration of Plasma Processing System to which Temperature Estimation Device in Model Generation Phase is Applied FIG. 1 is a diagram showing an example of the system configuration of a plasma processing system to which the temperature estimation device in the model generation phase is applied. As shown in FIG. 1, in the model generation phase, the plasma processing system 100 includes a semiconductor manufacturing process, time series data acquisition devices 140_1 to 140_n, and a temperature estimation device 160.

[0013] In a semiconductor manufacturing process, in chamber 120 which is a processing space where plasma processing is performed, plasma processing is performed on an object (unprocessed wafer 110), and a resultant (processed wafer 130) is generated. Here, the unprocessed wafer 110 refers to the wafer (substrate) before plasma processing is performed in chamber 120, and the processed wafer 130 refers to the wafer (substrate) after plasma processing is performed in chamber 120.

[0014] In the model generation phase, a temperature sensor is installed in chamber 120. Then, time-series data (temperature data for model generation) before the plasma processing of the unprocessed wafer 110 in chamber 120 starts or during the plasma processing is measured by the temperature sensor. The example of FIG. 1 shows a state where temperature sensor 151 is installed at the position of the upper electrode in chamber 120 and temperature sensor 152 is installed at the position of the side wall in chamber 120. Note that the installation positions of temperature sensors 151 and 152 in chamber 120 are just an example, and they may be installed at positions different from those in FIG. 1. Also, the number of temperature sensors installed in chamber 120 is not limited to two.

[0015] Each of the time-series data (temperature data for model generation) measured by temperature sensor 151 and temperature sensor 152 is stored in data storage unit 163 for model generation of temperature estimation device 160.

[0016] Time-series data acquisition devices 140_1 to 140_n each measure a time-series data group (process data group for model generation) before the plasma processing of the unprocessed wafer 110 in chamber 120 starts or during the plasma processing. The time-series data acquisition devices 140_1 to 140_n are each composed of, for example, a plurality of sensors (for example, n sensors), and each time-series data acquisition device measures process data for different types of measurement items. Note that the number of measurement items measured by each of the time-series data acquisition devices 140_1 to 140_n may be one or a plurality.

[0017] The time-series data groups (process data groups for model generation) measured by the time-series data acquisition devices 140_1 to 140_n are stored in the model generation data storage unit 163 in association with the time-series data (temperature data for model generation) in the model generation phase.

[0018] A temperature estimation program is installed in the temperature estimation device 160. In the model generation phase, the temperature estimation device 160 functions as the model generation unit 161 when the program is executed.

[0019] The model generation unit 161 performs model generation processing on the time-series model using the model generation data (process data groups for model generation, temperature data for model generation) stored in the model generation data storage unit 163, and provides the generated time-series model.

[0020] (2) System configuration of the plasma processing system to which the temperature estimation device in the estimation phase is applied FIG. 2 is a diagram showing an example of the system configuration of the plasma processing system to which the temperature estimation device in the estimation phase is applied. The differences from FIG. 1 are that no temperature sensor is attached inside the chamber 120, and functions different from those in the model generation phase are executed in the temperature estimation device 160.

[0021] When the temperature estimation program is executed in the estimation phase, the temperature estimation device 160 functions as the estimation unit 200, the determination unit 210, and the control unit 220.

[0022] The estimation unit 200 has the generated time-series model provided by the model generation unit 161 in the model generation phase. The estimation unit 200 sequentially inputs the data at each time of the time-series data group (process data group for estimation) measured by the time-series data acquisition devices 140_1 to 140_n and stored in the time-series data group storage unit 230 into the generated time-series model. Thereby, the estimation unit 200 acquires the estimated temperature data sequentially output from the generated time-series model. Further, the estimation unit 200 notifies either or both of the determination unit 210 and the control unit 220 of the acquired estimated temperature data.

[0023] The determination unit 210 constantly monitors the current estimated temperature data in the chamber 120 notified by the estimation unit 200, and when it exceeds a predetermined temperature range, it gives an alarm in real time. Thereby, the user of the plasma processing system 100 can grasp in real time that the temperature in the chamber 120 during plasma processing has exceeded the predetermined temperature range.

[0024] Also, among the past time-series data groups (process data groups for estimation) stored in the time-series data group storage unit 230, for example, based on the time-series data group during plasma processing of the specific processed wafer 130, it is assumed that the estimation unit 200 notifies the estimated temperature data. In this case, the determination unit 210 visualizes the time range during which plasma processing has been performed exceeding the predetermined temperature range. Thereby, the user of the plasma processing system 100 can retrospectively grasp whether the temperature during plasma processing of the specific processed wafer 130 has exceeded the predetermined temperature range.

[0025] The control unit 220 controls the semiconductor manufacturing process in real time so that the current estimated temperature data in the chamber 120 notified by the estimation unit 200 reaches the target temperature (for example, appropriately setting the power amount of the RF power supply or the processing time of the plasma processing, etc.). Thereby, for example, it becomes possible to adjust the starting temperature when starting plasma processing on the pre-process wafer 110 to the target temperature.

[0026] Further, the control unit 220 determines the suitability of the process conditions based on the estimated temperature data in the chamber 120 notified by the estimation unit 200 (for example, the estimated temperature data during plasma processing for the previous processed wafer 110). Further, the control unit 220 optimizes the process conditions when performing plasma processing on the next processed wafer 110 (for example, appropriately setting the power amount of the RF power source or the processing time of the plasma processing). Thereby, for example, the temperature when performing plasma processing on the next processed wafer 110 can be kept within a predetermined temperature range.

[0027] <Hardware Configuration of Temperature Estimation Device> Next, the hardware configuration of the temperature estimation device 160 will be described. FIG. 3 is a diagram showing an example of the hardware configuration of the temperature estimation device. As shown in FIG. 3, the temperature estimation device 160 includes a CPU (Central Processing Unit) 301, a ROM (Read Only Memory) 302, and a RAM (Random Access Memory) 303. The temperature estimation device 160 also includes a GPU (Graphics Processing Unit) 304. Note that a processor (processing circuit, Processing Circuit, Processing Circuitry) such as the CPU 301 and the GPU 304, and a memory such as the ROM 302 and the RAM 303 form a so-called computer.

[0028] Furthermore, the temperature estimation device 160 includes an auxiliary storage device 305, a display device 306, an operation device 307, an I / F (Interface) device 308, and a drive device 309. Note that each hardware of the temperature estimation device 160 is connected to each other via a bus 310.

[0029] The CPU 301 is an arithmetic device that executes various programs (for example, a temperature estimation program, etc.) installed in the auxiliary storage device 305.

[0030] The ROM 302 is a non-volatile memory and functions as the main memory device. The ROM 302 stores various programs, data, etc. necessary for the CPU 301 to execute the various programs installed in the auxiliary storage device 305. Specifically, the ROM 302 stores boot programs such as BIOS (Basic Input / Output System) and EFI (Extensible Firmware Interface).

[0031] The RAM 303 is a volatile memory such as DRAM (Dynamic Random Access Memory) or SRAM (Static Random Access Memory) and functions as the main memory device. The RAM 303 provides a working area where various programs installed in the auxiliary storage device 305 are expanded when executed by the CPU 301.

[0032] The GPU 304 is an arithmetic device for image processing. In this embodiment, when the temperature estimation program is executed by the CPU 301, the GPU 304 performs high-speed arithmetic on the time-series data group by parallel processing. The GPU 304 is equipped with an internal memory (GPU memory) and temporarily holds information necessary for performing parallel processing on the time-series data group.

[0033] The auxiliary storage device 305 stores various programs and various data used when the various programs are executed by the CPU 301. For example, the model generation data storage unit 163 and the time-series data group storage unit 230 are realized in the auxiliary storage device 305.

[0034] The display device 306 is, for example, a display device that displays an alarm to the user of the plasma processing system 100. The operation device 307 is, for example, an input device used when the user of the plasma processing system 100 or the administrator of the temperature estimation device 160 inputs various instructions to the temperature estimation device 160. The I / F device 308 is a connection device for connecting to a network (not shown) and performing communication.

[0035] The drive device 309 is a device for setting the recording medium 320. The recording medium 320 here includes media that optically, electrically, or magnetically record information, such as CD-ROMs, flexible disks, magneto-optical disks, etc. Further, the recording medium 320 may include semiconductor memories that electrically record information, such as ROMs, flash memories, etc.

[0036] Note that various programs installed in the auxiliary storage device 305 are installed, for example, when the distributed recording medium 320 is set in the drive device 309 and the various programs recorded on the recording medium 320 are read by the drive device 309. Alternatively, various programs installed in the auxiliary storage device 305 may be installed by being downloaded via a network (not shown).

[0037] <Specific Examples of Model Generation Data> Next, specific examples of the model generation data (the process data group for model generation and the temperature data for model generation) stored in the model generation data storage unit 163 will be described. FIG. 4 is a diagram showing an example of the model generation data (the process data group for model generation and the temperature data for model generation). In the example of FIG. 4, for the sake of simplifying the explanation, it is assumed that the time series data acquisition devices 140_1 to 140_n each measure one-dimensional data, but one time series data acquisition device may measure two-dimensional data (a data set of multiple types of one-dimensional data).

[0038] FIG. 4(a) schematically shows a time series data group (the process data group for model generation) composed of time series data measured by the time series data acquisition devices 140_1 to 140_n in the same time range.

[0039] In FIG. 4(a), for example, time-series data 1 schematically shows predetermined gas flow rate data (for example, data measured by a sensor that measures the gas flow rate of the gas supplied into chamber 120). Here, the gas referred to includes all types of gases (process gas and inert gas) supplied into chamber 120. Further, the sensors for measuring the gas flow rate include sensors provided in the gas lines of each type of gas (however, here, for the sake of convenience, only one time-series data is shown).

[0040] Also, in FIG. 4(a), for example, time-series data 2 schematically shows the pressure data inside chamber 120 (for example, data measured by a sensor that measures the pressure inside chamber 120). Further, for example, time-series data 3 schematically shows RF power supply data (for example, data measured by a sensor that measures the power amount of the RF power supply for plasma processing).

[0041] Also, in FIG. 4(a), for example, time-series data n-1 schematically shows impedance data (for example, data measured by a sensor for measuring chamber impedance (matching position, current, voltage, etc.)). Further, for example, time-series data n schematically shows heater power data (for example, data measured by a sensor that measures the power amount of the heater that heats the inside of chamber 120).

[0042] On the other hand, FIG. 4(b) schematically shows time-series data (temperature data for model generation) measured in the corresponding time range by temperature sensor 151 attached to the position of the upper electrode. Also, FIG. 4(b) schematically shows time-series data (temperature data for model generation) measured in the corresponding time range by temperature sensor 152 attached to the position of the inner wall of chamber 120.

[0043] <Relationship between Process Data Group and Temperature Data> Next, the relationship between the time-series data group (process data group for model generation) measured by the time-series data acquisition devices 140_1 to 140_n and the time-series data (temperature data for model generation) measured by the temperature sensors 151 and 152 will be described.

[0044] FIG. 5 is a diagram showing an example of measured values of process data and temperature data. Among these, FIG. 5(a) shows the measured value of RF power supply data, where the horizontal axis represents time and the vertical axis represents the power level. Further, FIG. 5(b) shows the measured value of temperature data measured by the temperature sensor 151 attached to the position of the upper electrode, where the horizontal axis represents time and the vertical axis represents temperature.

[0045] As shown in FIGS. 5(a) and 5(b), the temperature data in the chamber 120 varies with a predetermined time delay with respect to the variation of the process data. This is because it takes a certain amount of time for the heat-conducting substances constituting each part in the chamber 120 to conduct heat. Also, it takes a certain amount of time for the temperature of each part to stabilize after heat is conducted to each part in the chamber 120.

[0046] In view of such temperature characteristics in the chamber 120, in the temperature estimation device 160 according to the present embodiment, model generation processing is performed on a time-series model, which is a model capable of expressing a time delay, and temperature data is estimated using the generated time-series model provided.

[0047] <Overview of the model generation unit> Next, the overview of the model generation unit 161 of the temperature estimation device 160 will be described. The model generation unit 161 has, for example, a time-series model such as an ARX model. Then, the model generation unit 161 performs batch-type model generation processing on the time-series model using the model generation data (process data group for model generation, temperature data for model generation) stored in the model generation data storage unit 163.

[0048] Specifically, the model generation unit 161 reads out a process data group for model generation from the model generation data storage unit 163 and sequentially inputs it into the time series model. Further, the model generation unit 161 compares the output results sequentially output from the time series model with the corresponding temperature data for model generation (for example, the temperature data measured by the temperature sensor 151 attached to the position of the upper electrode), and calculates the respective errors.

[0049] Furthermore, the model generation unit 161 determines the model parameters of the time series model so that the sum of the squares of the calculated respective errors is minimized.

[0050] Note that the generated time series model with determined model parameters can be represented, for example,

[0051]

Number

[0052] As is clear from the above formula, in the time series model, the current temperature data is calculated by weighted addition of the process data group in a predetermined past time range m b and the temperature data in a predetermined past time range m a using the determined model parameters.

[0053] Accordingly, according to the temperature estimation device 160, even when the state in the chamber 120 has changed, temperature data corresponding to the fluctuations in the process data can be estimated using the generated time-series model.

[0054] Here, the case where the model parameters of the time-series model are determined based on the temperature data measured by the temperature sensor 151 attached to the position of the upper electrode has been described. However, the same process can be executed for the temperature data measured by the temperature sensor 152 attached to the position of the side wall in the chamber 120, so that the model parameters of the time-series model can be determined.

[0055] However, since different model parameters are obtained when using the temperature data measured by the temperature sensor 151 and when using the temperature data measured by the temperature sensor 152, the model generation unit 161 manages them as separate generated time-series models.

[0056] Also, in the above description, the selection method (order selection method) of the predetermined time range m a , m b was not mentioned, but it is assumed that the order of the time-series model is optimized while being adjusted as appropriate. Similarly, in the above description, the selection method of the process data group to be input to the time-series model among the process data groups for model generation was not mentioned, but it is assumed that the process data group to be input to the time-series model is also optimized while being adjusted as appropriate.

[0057] <Flow of model generation process> Next, the flow of the model generation process of the plasma processing system in the model generation phase will be described. FIG. 6 is a flowchart showing the flow of the model generation process.

[0058] In step S601, the temperature estimation device 160 acquires model generation data and verification data. Specifically, the temperature estimation device 160 acquires a process data group and temperature data from the time series data acquisition devices 140_1 to 140_n and the temperature sensor 151 (or 152) as model generation data. Similarly, the temperature estimation device 160 acquires a process data group and temperature data from the time series data acquisition devices 140_1 to 140_n and the temperature sensor 151 (or 152) as verification data.

[0059] In step S602, the temperature estimation device 160 selects a process data group necessary for estimating temperature data from among the process data groups for model generation.

[0060] In step S603, the temperature estimation device 160 selects the order of the time series model that the model generation unit 161 has.

[0061] In step S604, the temperature estimation device 160 performs model generation processing on the time series model so that the sum of the squares of the errors when the selected process data group is input is minimized, and determines the model parameters of the time series model.

[0062] In step S605, the temperature estimation device 160 verifies the time series model (generated time series model) for which the model parameters have been determined, using the verification data.

[0063] As a result of the verification, it is determined whether or not the target estimation accuracy has been reached. If it is determined that the target estimation accuracy has not been reached (if No in step S605), the process returns to step S602. In this case, in step S602, the temperature estimation device 160 adds process data that contributes to improving the estimation accuracy to the existing selected process data group, or selects a process data group with a combination different from the previous combination.

[0064] On the other hand, when it is determined in step S605 that the target estimation accuracy has been reached (when Yes in step 605), the model generation process is terminated.

[0065] <Specific Example of Functional Configuration and Processing of Estimation Unit> Next, a specific example of the functional configuration of the estimation unit 200 and the processing performed by the estimation unit 200 will be described. FIG. 7 is a diagram showing a specific example of the functional configuration and processing of the estimation unit.

[0066] As shown in FIG. 7, the estimation unit 200 has a generated time series model 710 provided by the model generation unit 161.

[0067] The estimation unit 200 sequentially inputs the time series data group (process data group for estimation) acquired by the time series data acquisition devices 140_1 to 140_n into the generated time series model 710. Note that the time series data group (process data group for estimation) input at this time is the selected process data group (time series process data group related to the state of the chamber 120) when it is determined to have a predetermined estimation accuracy in the model generation process.

[0068] Note that, before inputting the selected process data group, the estimation unit 200 executes, for example, the following temperature initialization sequence. · The process of sufficiently stabilizing the temperature in the chamber 120 is continued for a certain period of time or more. At this time, the process data group (selected process data group) and the temperature data are collected for a time period or more during which the model parameters are specified. · Using the collected process data group and temperature data as initial values, they are input into the generated time series model 710.

[0069] In the example of FIG. 7, the current process data group is a time series data group at the time indicated by reference numeral 721, and shows a state in which the process data group is input.

[0070] Note that, as shown in FIG. 7, in the generated time series model 710, the time range m is larger than the current process data groupb Only the past process data group is used for calculating the estimated temperature data. Also, in the generated time series model 710, the time range m is larger than the current estimated temperature data (the estimated temperature data at the time indicated by the symbol 721). a Only the past estimated temperature data is used for calculating the current estimated temperature data.

[0071] That is, in the generated time series model 710,[[]] · The time range m is larger than the process data group at present (symbol 721). b Only the past process data group (the process data group within a predetermined time range in the past compared to the current process data group) and · The time range m is larger than the estimated temperature data at present (symbol 721). a Only the past estimated temperature data (the estimated temperature data within a predetermined time range estimated in the past compared to the estimated temperature data to be estimated) and Based on these, the estimated temperature data of the current (symbol 721) object to be estimated is calculated. Also, the generated time series model 710 sequentially notifies the calculated estimated temperature data of the current (symbol 721) object to be estimated to the determination unit 210 and the control unit 220.

[0072] In this way, the estimation unit 200 sequentially outputs the estimated temperature data by sequentially inputting a new time series of process data groups related to the state in the chamber 120 to the generated time series model 710.

[0073] Although FIG. 7 describes the case of estimating the estimated temperature data at the position of the upper electrode, when using the generated time series model 710 for estimating the estimated temperature data at the position of the side wall in the chamber 120, the estimated temperature data can be sequentially estimated.

[0074] <Specific Example of the Functional Configuration and Processing of the Determination Unit> Next, the functional configuration of the determination unit 210 and a specific example of the processing by the determination unit 210 will be described. FIG. 8 is a diagram showing the functional configuration and a specific example of the processing of the determination unit.

[0075] As shown in FIG. 8, the determination unit 210 includes a deviation amount calculation unit 810, a determination criterion setting unit 820, and a notification unit 830.

[0076] The deviation amount calculation unit 810 acquires, for example, the real-time estimated temperature data notified from the estimation unit 200 at a predetermined cycle. Further, each time the deviation amount calculation unit 810 acquires the real-time estimated temperature data, it determines whether the estimated temperature data exceeds the temperature range preset by the determination criterion setting unit 820.

[0077] In addition, when the deviation amount calculation unit 810 determines that the estimated temperature data exceeds the preset temperature range, it calculates the deviation amount and notifies the notification unit 830. In FIG. 8, the graph 840 shows the real-time estimated temperature data notified from the estimation unit 200 by the deviation amount calculation unit 810. Note that the graph 840 shows the estimated temperature data when plasma processing is continuously performed on a plurality of pre-process wafers, the horizontal axis represents the processing time of each pre-process wafer, and the vertical axis represents the estimated temperature data.

[0078] Also, in FIG. 8, the graph 860 is an enlarged view of the time range 841 of the graph 840. In the graph 860, the dotted line 862 indicates the upper limit value of the temperature range preset by the determination criterion setting unit 820, and the dotted line 863 indicates the lower limit value of the temperature range preset by the determination criterion setting unit 820.

[0079] According to the graph 860, since the estimated temperature data 861 exceeds a predetermined temperature range (in the example of FIG. 8, it is below the lower limit value of the dotted line 863), the deviation amount calculation unit 810 determines that the estimated temperature data 861 exceeds the preset temperature range and calculates the deviation amount. In this case, the notification unit 830 notifies the user of the plasma processing system 100 of an alarm indicating that the temperature exceeds the predetermined temperature range.

[0080] On the one hand, in FIG. 8, graph 850 shows an enlarged view of time range 842 of graph 840. In graph 850, dotted line 852 indicates the upper limit value of the temperature range preset by determination criterion setting unit 820, and dotted line 853 indicates the lower limit value of the temperature range preset by determination criterion setting unit 820, respectively.

[0081] According to graph 850, since estimated temperature data 851 is within a predetermined temperature range, deviation amount calculation unit 810 determines that estimated temperature data 851 does not exceed the preset temperature range. In this case, notification unit 830 does not notify the user of plasma processing system 100 of an alarm.

[0082] In the above description, the case where determination unit 210 performs real-time determination processing on the estimated temperature data notified by estimation unit 200 has been described. However, the same applies to the case of performing determination processing on the estimated temperature data notified by estimation unit 200 based on the past time series data group stored in model generation data storage unit 163.

[0083] However, in this case, notification unit 830 notifies the user of plasma processing system 100 by visualizing the time range during which plasma processing has been performed beyond a predetermined temperature range.

[0084] <Specific Examples of the Functional Configuration and Processing of the Control Unit> Next, the functional configuration of control unit 220 and specific examples of the processing performed by control unit 220 will be described. FIG. 9 is a diagram showing the functional configuration and specific examples of the processing of the control unit.

[0085] As shown in FIG. 9, control unit 220 includes temperature adjustment unit 910, target temperature setting unit 920, recipe adjustment unit 930, and the like.

[0086] The temperature adjustment unit 910 generates control data so that the current estimated temperature data in the chamber 120 reaches the target temperature based on, for example, the real-time estimated temperature data notified by the estimation unit 200 during the seasoning process. Note that the target temperature is set by, for example, the target temperature setting unit 920.

[0087] Further, the temperature adjustment unit 910 adjusts the temperature in the chamber 120 by transmitting the generated control data to the semiconductor manufacturing process.

[0088] Conventionally, for example, even if the temperature at the time of starting plasma processing had dropped to the temperature shown by reference numeral 941, the estimated temperature data at that time could not be accurately estimated, so the plasma processing was started as it was. In contrast, since the current estimated temperature data is notified to the estimation unit 200 in real time, the temperature adjustment unit 910 can, for example, adjust the temperature in the chamber 120 to reach the target temperature shown by reference numeral 942 in the seasoning process. As a result, even for the first pre-process wafer, the temperature change during plasma processing becomes the same as the temperature change for the pre-process wafers after the second one, and the quality of the first processed wafer after plasma processing can be maintained.

[0089] The recipe adjustment unit 930 determines the suitability of the process conditions based on, for example, the estimated temperature data output during plasma processing (for example, the estimated temperature data output during plasma processing for the previous pre-process wafer 110). Further, the recipe adjustment unit 930 optimizes the process conditions for performing plasma processing on the next pre-process wafer 110 based on the determination result of the suitability of the process conditions, and adjusts the recipe. Furthermore, the recipe adjustment unit 930 executes plasma processing using the adjusted recipe by transmitting the adjusted recipe to the semiconductor manufacturing process.

[0090] As a result, for example, even if the temperature in the chamber 120 used to change during continuous plasma processing in the past and the same recipe was used, according to the recipe adjustment unit 930, a recipe corresponding to the temperature change can be used (see reference numerals 951 and 952). As a result, the temperature at the time of performing plasma processing on the wafer 110 before the next process can be kept within a predetermined temperature range.

[0091] In the example of FIG. 9, the function of adjusting the temperature in the chamber 120 during the seasoning process and the function of adjusting the recipe during the plasma process are illustrated. However, the function that the control unit 220 adjusts based on the estimated temperature data is not limited to these.

[0092] <Flow of Estimation Process> Next, the flow of the estimation process in the estimation phase of the plasma processing system will be described. FIG. 10 is a flowchart showing the flow of the estimation process.

[0093] In step S1001, the time series data acquisition devices 140_1 to 140_n start measuring a time series data group (a process data group for estimation), and store the measured time series data group in the time series data group storage unit 230.

[0094] In step S1002, the temperature estimation device 160 determines whether to execute real-time processing using the time series data group. Note that real-time processing refers to processing in which, before plasma processing is started or while plasma processing is being executed, the estimated temperature data is output in real time by inputting the time series data group (the process data group for estimation) that has been generated into the time series model.

[0095] If it is determined in step S1002 that real-time processing is to be executed (Yes in step S1002), the process proceeds to step S1011.

[0096] In step S1011, the temperature estimation device 160 inputs a process data group (a time-series process data group related to the state of the chamber) selected from the measured time-series data group (process data group for estimation) into the generated time-series model. Note that at the start of the estimation process, the temperature estimation device 160 inputs the initial value of the temperature data into the generated time-series model. Thereby, the temperature estimation device 160 can output real-time estimated temperature data.

[0097] In step S1012, the temperature estimation device 160 determines whether to execute the determination mode or the control mode. If it is determined in step S1012 to execute the determination mode, the process proceeds to step S1013.

[0098] In step S1013, the temperature estimation device 160 performs real-time determination processing and issues an alarm if the current estimated temperature data exceeds a preset temperature range.

[0099] On the other hand, if it is determined in step S1012 to execute the control mode, the process proceeds to step S1014.

[0100] In step S1014, the temperature estimation device 160 performs temperature adjustment processing to adjust the temperature inside the chamber so that the current estimated temperature data reaches the target temperature. Alternatively, the temperature estimation device 160 determines the appropriateness of the process conditions when performing plasma processing on the previous processed wafer. Then, the temperature estimation device 160 optimizes the process conditions for performing plasma processing on the next processed wafer and adjusts the recipe.

[0101] On the other hand, if it is determined in step S1002 not to execute real-time processing (if the answer is No in step S1002), the process proceeds to step S1021.

[0102] In step S1021, the temperature estimation device 160 selects, from the time-series data group (process data group for estimation) stored in the time-series data group storage unit 230, · for example, the time-series data group during plasma processing of the processed wafer 130 after a specific process, · the selected process data group (time-series process data group related to the state of the chamber), and reads them out. Further, the temperature estimation device 160 inputs the read process data group into the generated time-series model and outputs estimated temperature data.

[0103] In step S1022, the temperature estimation device 160 performs a determination process, visualizes the time range during which plasma processing was performed outside a predetermined temperature range from the estimated temperature data, and notifies the user of the plasma processing system 100.

[0104] In step S1030, the temperature estimation device 160 determines whether to end the estimation process. If it is determined in step S1030 to continue the estimation process (if No in step S1030), the process returns to step S1002.

[0105] On the other hand, if it is determined in step S1030 to end the estimation process (if Yes in step S1030), the estimation process ends.

[0106] <Summary> As is clear from the above description, the temperature estimation device 160 according to the first embodiment · performs model generation processing on a time-series model that associates the data of each time range of the time-series process data group related to the state in the chamber where plasma processing is performed with the data of each time of the time-series temperature data measured in the chamber. Thereby, a generated time-series model is provided. · By sequentially inputting a new time-series process data group related to the state in the chamber into the provided generated time-series model, the temperature data is sequentially estimated.

[0107] Thus, in the first embodiment, in view of the specific circumstances of the semiconductor manufacturing process that it is difficult to directly measure the temperature by permanently installing a temperature sensor in the chamber, the temperature inside the chamber is indirectly estimated from a time-series process data group. At this time, in the first embodiment, time-series temperature data is estimated by using the data in each time range of the time-series process data group related to the state of the chamber.

[0108] Accordingly, according to the first embodiment, even when the state inside the chamber has changed, temperature data corresponding to the fluctuations in the process data can be estimated.

[0109] That is, according to the first embodiment, it is possible to provide a temperature estimation device, a plasma processing system, a temperature estimation method, and a temperature estimation program that estimate the temperature corresponding to the change in the state inside the processing space where plasma processing is performed.

[0110] [Second Embodiment] In the above first embodiment, the model generation unit 161 has been described as performing model generation processing for the ARX model. However, the time-series model for which the model generation unit 161 performs model generation processing is not limited to the ARX model. For example, any model that can calculate the correlation of time-series data (for example, an RNN (Recurrent Neural Network) model or the like) may be used.

[0111] In the case of the RNN model, the model generation unit 161 determines model parameters by learning processing and provides a learned RNN model. Specifically, in the case of the RNN model, the model generation unit 161 performs learning processing using a data set for learning in which the process data group for model generation is input data and the temperature data for model generation is correct answer data, and determines model parameters.

[0112] That is, the model generation unit 161 functions as a learning unit, and performs learning processing by the error backpropagation method or the like so that the output data when the input data is input to the RNN model approaches the correct data, and provides a learned RNN model.

[0113] Also, in the above-described first embodiment, it has been described that the recipe adjustment unit 930 generates an adjusted recipe based on the estimated temperature data. However, the recipe adjustment unit 930 may analyze the dynamic events in the chamber 120 based on the estimated temperature data, for example, and calculate characteristic values for adjusting the recipe. Here, the characteristic values refer to, for example, C / D (Critical Dimension) values, E / R (Etching Rate) values, and the like.

[0114] Also, in the above-described first embodiment, the case where the temperature adjustment unit 910 adjusts the temperature in the chamber 120 during the seasoning process has been described. However, the temperature adjustment unit 910 adjusts the temperature in the chamber 120 is not limited to during the seasoning process. For example, it may be during the plasma processing of the wafer before processing. Here, the plasma processing is assumed to include etching processing, film formation processing, ashing processing, and the like.

[0115] Also, in the above-described first embodiment, the semiconductor manufacturing process and the temperature estimation device 160 are configured as separate bodies. However, at least some functions of the temperature estimation device 160 may be configured to be realized in the semiconductor manufacturing process.

[0116] Also, in the above-described first embodiment, it has been described that the model generation phase and the estimation phase are executed by the same temperature estimation device 160. However, the temperature estimation device that executes the model generation phase and the temperature estimation device that executes the estimation phase may be configured separately.

[0117] In addition, in the above-described first embodiment, the temperature estimation device 160 that executes the estimation phase has been described as functioning as the estimation unit 200, the determination unit 210, and the control unit 220. However, the temperature estimation device 160 that executes the estimation phase may be configured by dividing it into, for example, an estimation unit 200, a determination unit 210, and a control unit 220. That is, it may be configured by dividing it into a temperature estimation device having the estimation unit 200, an alarm output device having the determination unit 210, and a temperature control device having the control unit 220.

[0118] Note that the configurations and the like described in the above embodiments are not limited to the configurations shown here, such as combinations with other elements. Regarding these points, it is possible to make changes without departing from the spirit of the present invention, and it can be appropriately determined according to the application form.

Description of Reference Numerals

[0119] 100: Plasma processing system 110: Wafer before processing 120: Chamber 130: Wafer after processing 140_1~140_n: Time-series data acquisition device 151: Temperature sensor 152: Temperature sensor 160: Temperature estimation device 161: Model generation unit 200: Estimation unit 210: Determination unit 220: Control unit 710: Generated time-series model 810: Deviation amount calculation unit 820: Determination criterion setting unit 830: Notification unit 910: Temperature adjustment unit 920: Target temperature setting unit 930: Recipe adjustment unit

Claims

1. In a generated time-series model in which data for each time range of time-series process data related to the state within the processing space where plasma processing is performed is associated with data for each time of time-series temperature data measured within the processing space, by sequentially inputting new time-series process data related to the state within the processing space, an estimation unit that sequentially estimates temperature data; A control unit that controls the processing time of the plasma processing or the amount of power of the RF power source for plasma processing so that the temperature data sequentially estimated by the estimation unit reaches a target temperature before the plasma processing is started or during the plasma processing. A temperature estimation device having the above.

2. The temperature estimation device according to claim 1, wherein the new time-series process data related to the state within the processing space is a plurality of time-series process data newly measured by each of a plurality of sensors.

3. The temperature estimation device according to claim 2, wherein the plurality of sensors includes at least any one of a sensor for measuring the pressure within the processing space, a sensor for measuring the gas flow rate of the gas supplied into the processing space, a sensor for measuring the amount of power of the RF power source for plasma processing, a sensor for measuring the chamber impedance, and a sensor for measuring the amount of power of the heater for heating the inside of the processing space.

4. The temperature estimation device according to claim 2, wherein the new time-series process data related to the state within the processing space is a plurality of time-series process data newly measured before the plasma processing is started or during the plasma processing.

5. The temperature estimation device according to claim 2, wherein the generated time-series model outputs the temperature data to be estimated by weighted addition of process data in a predetermined time range in the past compared to the current process data and temperature data in a predetermined time range estimated in the past compared to the temperature data to be estimated, using the parameters of the generated time-series model.

6. By sequentially inputting time-series process data related to the state within the processing space where plasma processing is performed, based on the error between the temperature data sequentially output from the time-series model and the data at each time of the time-series temperature data measured within the processing space, the temperature estimation apparatus according to claim 1, further comprising a model generation unit that determines the parameters of the time-series model to provide the generated time-series model.

7. The model generation unit determines the parameters of the time-series model based on the error between the data at each time of the time-series temperature data measured at a predetermined position within the processing space, thereby providing a generated time-series model corresponding to the measured position. The temperature estimation apparatus according to claim 6.

8. The temperature estimation apparatus according to any one of claims 1 to 7, and an alarm output device that outputs an alarm when the temperature data sequentially estimated by the estimation unit exceeds a predetermined temperature range. A plasma processing system having the same.

9. A step of sequentially estimating temperature data by sequentially inputting data in each time range of time-series process data related to the state within the processing space where plasma processing is performed and data at each time of the time-series temperature data measured within the processing space into a generated time-series model in which they are associated, and a step of controlling the processing time of the plasma processing or the power amount of the RF power source for plasma processing so that the sequentially estimated temperature data reaches a target temperature before the plasma processing is started or during the plasma processing is being performed. A temperature estimation method having the same.

10. A step of sequentially estimating temperature data by sequentially inputting data in each time range of time-series process data related to the state within the processing space where plasma processing is performed and data at each time of the time-series temperature data measured within the processing space into a generated time-series model in which they are associated, and a step of controlling the processing time of the plasma processing or the power amount of the RF power source for plasma processing so that the sequentially estimated temperature data reaches a target temperature before the plasma processing is started or during the plasma processing is being performed. A temperature estimation program for causing a computer to execute the same.

Images