Prediction method and information processing apparatus

Abstract

To predict the processing results of plasma etching process.SOLUTION: A prediction method has a calculation process and a prediction process. The calculation process calculates a correlation between a spatial distribution value of a magnetic field in a chamber when a plasma etching process is performed on a substrate placed in the chamber and a processing result of the plasma etching process on the substrate. The prediction process predicts, based on the calculated correlation, a processing result of the plasma etching process for the substrate from the spatial distribution value of the magnetic field in the chamber.SELECTED DRAWING: Figure 5

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a technique for controlling the gradient of the interface between the ion sheath and the bulk plasma of the plasma generated in the processing container by energizing a plurality of annular coils provided at the upper part of the processing container to function as an electromagnet and generating a magnetic field.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The present disclosure provides a technique for predicting the processing result of plasma etching processing.

Means for Solving the Problems

[0005] A prediction method according to an aspect of the present disclosure includes a calculation step and a prediction step. The calculation step calculates the correlation between the spatial distribution value of the magnetic field in the chamber when plasma etching processing is performed on a substrate disposed in the chamber and the processing result of the plasma etching processing on the substrate. The prediction step predicts the processing result of the plasma etching processing on the substrate from the spatial distribution value of the magnetic field in the chamber based on the calculated correlation.

Effects of the Invention

[0006] According to the present disclosure, the processing result of plasma etching processing can be predicted.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12A

Figure 12B

Figure 12C

Figure 12D

Figure 12E

Figure 12F

Figure 13

Figure 14A

Figure 14B

Figure 14C

Figure 14D

Figure 14E

Figure 15

Figure 16

[0008] Hereinafter, embodiments of the prediction method and the information processing apparatus disclosed in the present application will be described in detail with reference to the drawings. Note that the prediction method and the information processing apparatus disclosed are not limited by this embodiment.

[0009] Incidentally, with the progress of high integration and miniaturization of semiconductor devices, the aspect ratio of patterns formed on semiconductor wafers has increased, and the recesses of the patterns have become deeper. For example, in the pillar process for manufacturing 3D NAND, it is required to vertically plasma etch holes with a high aspect ratio and contact a predetermined position in the lower layer. However, a phenomenon such as tilting where the holes progress obliquely may occur. Tilting causes contact failure and thus needs to be suppressed.

[0010] Tilting is caused by the incident direction of etching ions being oblique to the wafer surface. In plasma etching processing, by making the interface between the bulk plasma and the sheath (hereinafter referred to as the "sheath surface") parallel to the wafer surface, the incident direction of the etching ions can be made perpendicular to the wafer surface. Therefore, it is known that a method of providing a plurality of annular coils at the upper part of the processing chamber, energizing the annular coils, and controlling the plasma density distribution using a magnetic field generated by an electromagnet to adjust the sheath surface is effective.

[0011] However, with the conventional method, it has been difficult to predict the processing result of plasma etching processing. For example, with the conventional method, it has only been possible to adjust the current supplied to the electromagnet based on empirical rules, and it has been difficult to accurately predict how tilting will change when the current supplied to the electromagnet is controlled. Therefore, a technique for predicting the processing result of plasma etching processing has been expected.

[0012] [Embodiment] [Device Configuration of Plasma Processing Apparatus] First, an example of a plasma processing apparatus that performs plasma etching processing will be described. In the embodiment described below, the case where the plasma processing apparatus is a plasma processing system in a system configuration will be described as an example. FIG. 1 is a diagram showing an example of a schematic configuration of a plasma processing system according to the embodiment.

[0013] A configuration example of a plasma processing system will be described below. The plasma processing system includes a capacitively coupled plasma processing apparatus 1 and a control unit 2. The capacitively coupled plasma processing apparatus 1 includes a plasma processing chamber 10, a gas supply unit 20, a power supply 30, and an exhaust system 40. The plasma processing apparatus 1 also includes a substrate support unit 11 and a gas introduction unit. The gas introduction unit is configured to introduce at least one processing gas into the plasma processing chamber 10. The gas introduction unit includes a shower head 13. The substrate support unit 11 is disposed in the plasma processing chamber 10. The shower head 13 is disposed above the substrate support unit 11. In one embodiment, the shower head 13 constitutes at least a part of the ceiling of the plasma processing chamber 10. The plasma processing chamber 10 has a plasma processing space 10s defined by the shower head 13, the side wall 10a of the plasma processing chamber 10, and the substrate support unit 11. The plasma processing chamber 10 has at least one gas supply port for supplying at least one processing gas to the plasma processing space 10s and at least one gas discharge port for discharging gas from the plasma processing space. The side wall 10a is grounded. The shower head 13 and the substrate support unit 11 are electrically insulated from the plasma processing chamber 10 housing.

[0014] The substrate support portion 11 includes a main body portion 111 and a ring assembly 112. The main body portion 111 has a central region (substrate support surface) 111a for supporting a substrate (wafer) W and an annular region (ring support surface) 111b for supporting the ring assembly 112. The annular region 111b of the main body portion 111 surrounds the central region 111a of the main body portion 111 in a plan view. The substrate W is disposed on the central region 111a of the main body portion 111, and the ring assembly 112 is disposed on the annular region 111b of the main body portion 111 so as to surround the substrate W on the central region 111a of the main body portion 111. In one embodiment, the main body portion 111 includes a base and an electrostatic chuck. The base includes a conductive member. The conductive member of the base functions as a lower electrode. The electrostatic chuck is disposed on the base. The upper surface of the electrostatic chuck has the substrate support surface 111a. The ring assembly 112 includes one or more annular members. At least one of the one or more annular members is an edge ring. Also, although not shown, the substrate support portion 11 may include a temperature control module configured to adjust at least one of the electrostatic chuck, the ring assembly 112, and the substrate to a target temperature. The temperature control module may include a heater, a heat transfer medium, a flow path, or a combination thereof. A heat transfer fluid such as brine or gas flows through the flow path. Further, the substrate support portion 11 may include a heat transfer gas supply portion configured to supply a heat transfer gas between the back surface of the substrate W and the substrate support surface 111a.

[0015] The showerhead 13 is configured to introduce at least one process gas from the gas supply unit 20 into the plasma processing space 10s. The showerhead 13 has at least one gas supply port 13a, at least one gas diffusion chamber 13b, and a plurality of gas introduction ports 13c. The process gas supplied to the gas supply port 13a passes through the gas diffusion chamber 13b and is introduced into the plasma processing space 10s from the plurality of gas introduction ports 13c. Further, the showerhead 13 includes a conductive member. The conductive member of the showerhead 13 functions as an upper electrode. Note that the gas introduction part may include, in addition to the showerhead 13, one or more side gas injectors (SGI) attached to one or more openings formed in the side wall 10a.

[0016] The gas supply unit 20 may include at least one gas source 21 and at least one flow controller 22. In one embodiment, the gas supply unit 20 is configured to supply at least one process gas from the corresponding gas source 21 to the showerhead 13 via the corresponding flow controller 22. Each flow controller 22 may include, for example, a mass flow controller or a pressure-controlled flow controller. Further, the gas supply unit 20 may include one or more flow modulation devices for modulating or pulsing the flow rate of at least one process gas.

[0017] The power supply 30 includes an RF power supply 31 coupled to the plasma processing chamber 10 via at least one impedance matching circuit. The RF power supply 31 is configured to supply at least one RF signal (RF power), such as a source RF signal and a bias RF signal, to the conductive member of the substrate support 11 and / or the conductive member of the showerhead 13. Thereby, plasma is formed from at least one processing gas supplied to the plasma processing space 10s. Accordingly, the RF power supply 31 can function as at least a part of a plasma generation unit configured to generate plasma from one or more processing gases in the plasma processing chamber 10. Further, by supplying a bias RF signal to the conductive member of the substrate support 11, a bias potential is generated on the substrate W, and the ion component in the formed plasma can be drawn into the substrate W.

[0018] In one embodiment, the RF power supply 31 includes a first RF generation unit 31a and a second RF generation unit 31b. The first RF generation unit 31a is coupled to the conductive member of the substrate support unit 11 and / or the conductive member of the shower head 13 via at least one impedance matching circuit, and is configured to generate a source RF signal (source RF power) for plasma generation. In one embodiment, the source RF signal has a frequency in the range of 13 MHz to 150 MHz. In one embodiment, the first RF generation unit 31a may be configured to generate a plurality of source RF signals having different frequencies. The generated one or more source RF signals are supplied to the conductive member of the substrate support unit 11 and / or the conductive member of the shower head 13. The second RF generation unit 31b is coupled to the conductive member of the substrate support unit 11 via at least one impedance matching circuit, and is configured to generate a bias RF signal (bias RF power). In one embodiment, the bias RF signal has a frequency lower than that of the source RF signal. In one embodiment, the bias RF signal has a frequency in the range of 400 kHz to 13.56 MHz. In one embodiment, the second RF generation unit 31b may be configured to generate a plurality of bias RF signals having different frequencies. The generated one or more bias RF signals are supplied to the conductive member of the substrate support unit 11. Also, in various embodiments, at least one of the source RF signal and the bias RF signal may be pulsed.

[0019] In addition, the power supply 30 may include a DC power supply 32 coupled to the plasma processing chamber 10. The DC power supply 32 includes a first DC generation unit 32a and a second DC generation unit 32b. In one embodiment, the first DC generation unit 32a is connected to a conductive member of the substrate support unit 11 and is configured to generate a first DC signal. The generated first bias DC signal is applied to the conductive member of the substrate support unit 11. In one embodiment, the first DC signal may be applied to other electrodes such as the electrodes in the electrostatic chuck. In one embodiment, the second DC generation unit 32b is connected to a conductive member of the shower head 13 and is configured to generate a second DC signal. The generated second DC signal is applied to the conductive member of the shower head 13. In various embodiments, at least one of the first and second DC signals may be pulsed. Note that the first and second DC generation units 32a and 32b may be provided in addition to the RF power supply 31, or the first DC generation unit 32a may be provided in place of the second RF generation unit 31b.

[0020] The exhaust system 40 can be connected to, for example, a gas outlet 10e provided at the bottom of the plasma processing chamber 10. The exhaust system 40 may include a pressure regulating valve and a vacuum pump. The pressure in the plasma processing space 10s is adjusted by the pressure regulating valve. The vacuum pump may include a turbo molecular pump, a dry pump, or a combination thereof.

[0021] An electromagnet 50 is disposed on the upper surface of the plasma processing chamber 10. The electromagnet 50 is disposed above the shower head 13. The electromagnet 50 has a plurality of coils 51. The plurality of coils 51 are arranged concentrically.

[0022] FIG. 2 is a diagram showing an example of a schematic configuration of the electromagnet 50 according to the embodiment. The electromagnet 50 according to the present embodiment has five coils 51 (51a, 51b, 51c, 51d, 51e). The coils 51a, 51b, 51c, 51d, 51e each have a predetermined radius It is formed in a ring shape and arranged concentrically. The electromagnet 50 holds the coils 51a, 51b, 51c, 51d, 51e concentrically by a holding member 52 made of a soft magnetic material, and has an integrally formed structure. The electromagnet 50 is arranged such that the central axis Z of the plurality of coils 51 arranged concentrically coincides with the center of the substrate support portion 11. When an electric current flows through the coil 51, a magnetic field is generated in the electromagnet 50. In FIG. 2, the direction of the electric current flowing through each coil 51 is indicated by an arrow respectively.

[0023] Returning to FIG. 1. The outer coil 51e of the electromagnet 50 is formed with a radius larger than the radius of the substrate W and is disposed upward so as to cover the outside of the ring assembly 112. Further, the innermost coil 51a of the electromagnet 50 is disposed so as to be located above the central portion of the substrate W.

[0024] Both ends of each of the coils 51a, 51b, 51c, 51d, 51e are electrically connected to the electromagnet excitation circuit 56. The electromagnet excitation circuit 56 can supply an electric current with an arbitrary current value to each of the coils 51a, 51b, 51c, 51d, 51e under the control of the control unit 2. When an electric current flows through the coils 51a, 51b, 51c, 51d, 51e, the electromagnet 50 can form a magnetic field in the plasma processing space 10s.

[0025] The control unit 2 is an information processing device such as a computer, for example. The control unit 2 controls each part of the plasma processing apparatus 1. The operation of the plasma processing apparatus 1 is comprehensively controlled by the control unit 2.

[0026] The control unit 2 controls the plasma etching process. For example, the control unit 2 controls the exhaust system 40 to evacuate the inside of the plasma processing chamber 10 to a predetermined degree of vacuum. The control unit 2 controls the gas supply unit 20 to introduce a processing gas from the gas supply unit 20 into the plasma processing space 10s. The control unit 2 controls the power supply 30 and supplies a source RF signal and a bias RF signal from the first RF generation unit 31a and the second RF generation unit 31b in accordance with the introduction of the processing gas to generate plasma in the plasma processing chamber 10 and perform the plasma etching process. Further, during the plasma etching process, the control unit 2 controls the current value and the direction of the current supplied from the electromagnet excitation circuit 56 to the coils 51a, 51b, 51c, 51d, 51e, thereby controlling the magnetic field formed in the plasma processing space 10s.

[0027] Incidentally, as described above, with the high integration and miniaturization of semiconductor devices, the aspect ratio of the patterns formed on the substrate W has increased, and the recesses of the patterns have become deeper. In the plasma processing apparatus 1, when the plasma etching process is performed on the substrate W, tilting may occur in which the holes on the substrate W progress obliquely.

[0028] FIG. 3 is a diagram showing an example of tilting according to the embodiment. FIG. 3 schematically shows the state of the plasma when the plasma etching process is being performed on the substrate W. FIG. 3 shows a bulk region 60 of plasma with a high electron density n e and a sheath region 61 with a low electron density n e . Further, FIG. 3 shows a sheath surface 62 that is the boundary surface between the bulk region 60 and the sheath region 61. The ions in the bulk region 60 are accelerated in the sheath region 61 to etch the substrate W. As shown in FIG. 3, when the sheath surface 62 is inclined with respect to the substrate W, the incident direction of the ions becomes inclined with respect to the substrate W, and tilting occurs in which the holes 63 on the substrate W progress obliquely. The direction of tilting occurs from the thinner side to the thicker side of the thickness of the sheath region 61. By making the sheath surface 62 parallel to the substrate W, the incident direction of the ions can be made perpendicular to the substrate W.

[0029] In the plasma processing apparatus 1 according to the embodiment, by energizing the coil 51 of the electromagnet 50 provided above the plasma processing chamber 10 and controlling the plasma density distribution using the magnetic field generated by the electromagnet 50, the sheath surface 62 can be adjusted.

[0030] However, conventionally, in the plasma processing apparatus 1, the current supplied to each coil 51 of the electromagnet 50 has been adjusted based on empirical rules, and it has been difficult to accurately predict how tilting would change depending on how the current supplied to each coil 51 is controlled.

[0031] Therefore, in the embodiment, the correlation between the spatial distribution value of the magnetic field in the plasma processing chamber 10 and the processing result of the plasma etching process on the substrate W when the plasma etching process is performed by the information processing apparatus 200 described below is calculated. Then, based on the calculated correlation, the information processing apparatus 200 predicts the processing result of the plasma etching process.

[0032] [Configuration of the Information Processing Apparatus] Next, an example of the information processing apparatus 200 according to the embodiment will be described. FIG. 4 is a diagram showing an example of the schematic configuration of the information processing apparatus 200 according to the embodiment. The information processing apparatus 200 is an information processing apparatus such as a computer, for example. In the present embodiment, the information processing apparatus 200 corresponds to the information processing apparatus of the present disclosure.

[0033] The information processing apparatus 200 includes an external I / F (interface) unit 210, a display unit 211, an input unit 212, a storage unit 213, and a controller 214. Note that the information processing apparatus 200 may have various functional units that a known computer has in addition to the functional units shown in FIG. 4.

[0034] The external I / F unit 210 is an interface for inputting and outputting information with other devices. For example, the external I / F unit 210 is an interface for performing communication control with other devices. As one aspect of such an external I / F unit 210, a network interface card such as a LAN card can be adopted. For example, the external I / F unit 210 transmits and receives various data to and from the plasma processing apparatus 1 and other information processing devices via a network. Note that the external I / F unit 210 may be an interface such as a USB (Universal Serial Bus) port, for example.

[0035] The display unit 211 is a display device for displaying various information. Examples of the display unit 211 include display devices such as an LCD (Liquid Crystal Display) and a CRT (Cathode Ray Tube). The display unit 211 displays various information.

[0036] The input unit 212 is an input device for inputting various information. For example, examples of the input unit 212 include input devices such as a mouse and a keyboard. The input unit 212 receives an operation input from an administrator or the like and inputs operation information indicating the received operation content to the controller 214.

[0037] The storage unit 213 is a storage device for storing various data. For example, the storage unit 213 is a storage device such as a hard disk, an SSD (Solid State Drive), or an optical disk. Note that the storage unit 213 may be a semiconductor memory capable of rewriting data such as a RAM (Random Access Memory), a flash memory, or an NVSRAM (Non Volatile Static Random Access Memory).

[0038] The storage unit 213 stores an OS (Operating System) and various programs executed by the controller 214. For example, the storage unit 213 stores various programs including a prediction program that executes calculation processing and prediction processing described later. Further, the storage unit 213 stores various data used in the programs executed by the controller 214. For example, the storage unit 213 stores processing condition data 221, processing result data 222, prediction model data 223, and magnetic field calculation model data 224. Note that the storage unit 213 can also store other data in addition to the data exemplified above. Also, various programs and data may be those stored in a computer-readable computer recording medium (for example, an optical disk such as a hard disk, a DVD, a flexible disk, a semiconductor memory, etc.). Also, various programs and data can be transmitted from other devices at any time and used online.

[0039] The processing condition data 221 is data that stores the processing conditions for performing the plasma etching process. The processing conditions include, for each coil 51, the current value of the current supplied to the coil 51 and the set current value indicating the direction in which the current flows. The processing result data 222 is data that stores the processing results of the plasma etching process for each processing condition. The prediction model data 223 is data of a prediction model that predicts the processing results of the plasma etching process. Details of the processing condition data 221, the processing result data 222, and the prediction model data 223 will be described later.

[0040] The magnetic field calculation model data 224 is data of a magnetic field calculation model for calculating the magnetic field in the plasma processing chamber 10. The plasma processing apparatus 1 has a determined apparatus configuration such as the shape of the plasma processing chamber 10 and the arrangement positions of the respective coils 51, and the electrical characteristics of the apparatus are also determined. For this reason, the plasma processing apparatus 1 can determine a magnetic field calculation model for calculating the magnetic field in the plasma processing chamber 10 from the set current values of the respective coils 51 in consideration of the apparatus configuration. For example, in the plasma processing apparatus 1, an arithmetic expression for calculating the magnetic field in the plasma processing chamber 10 from the set current values of the respective coils 51 is determined. For example, in the magnetic field calculation model data 224, an arithmetic expression for calculating the magnetic field in the plasma processing chamber 10 from the set current values of the respective coils 51 is stored as the magnetic field calculation model.

[0041] The controller 214 is a device that controls the information processing apparatus 200. As the controller 214, an electronic circuit such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), or an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array) can be adopted. The controller 214 has an internal memory for storing programs and data. The controller 214 reads out various programs including the prediction program stored in the storage unit 213 and executes the processing of the read programs. The controller 214 functions as various processing units when the programs operate. For example, the controller 214 includes a calculation unit 231, a prediction unit 232, and a display control unit 233. In the present embodiment, the case where the controller 214 includes the calculation unit 231, the prediction unit 232, and the display control unit 233 will be described as an example. However, the functions of the calculation unit 231, the prediction unit 232, and the display control unit 233 may be realized in a distributed manner by a plurality of controllers.

[0042] In the information processing apparatus 200, when calculating the correlation, the processing condition data 221 and the processing result data 222 are prepared and stored in the storage unit 213. The processing condition data 221 stores a plurality of processing conditions under which the plasma etching process is performed on the substrate W by the plasma processing apparatus 1. The processing result data 222 stores the processing results of the plasma etching process on the substrate W for each processing condition.

[0043] To generate the processing condition data 221 and the processing result data 222, the plasma processing apparatus 1 performs the plasma etching process on the substrate W under a plurality of processing conditions, and measures the processing results of the plasma etching process on the substrate W for each processing condition. For example, the flow rate of the processing gas during the plasma etching process, the pressure within the plasma processing space for 10 s, and the RF power supplied from the power supply 30 are made the same, and the plasma etching process is performed on the substrate W under a plurality of processing conditions in which only the set current value of each coil 51 of the electromagnet 50 is changed. Then, the processing results of the plasma etching process on the substrate W for each processing condition are measured. For example, about 10 to 20 patterns of a plurality of processing conditions are created by changing either the current value or the direction of the current flowing through each coil 51 of the electromagnet 50 according to the experimental design method. Then, the plasma etching process of the photoresist formed on the substrate W is performed with the set current value of each created processing condition, and as the processing result for each processing condition, the distribution of the etching rate on the substrate W is measured. The substrate W is circular. Therefore, the distribution of the etching rate on the substrate W is symmetric with respect to the radial direction with respect to the center of the substrate W. The distribution of the etching rate is measured by measuring the etching rate at each position in the radial direction of the substrate W. For example, for each processing condition, the etching rate is measured at 26 points at regular intervals in the radial direction from the center of the substrate W. The etching rate may be a value obtained by normalizing the measured value. For example, the distribution of the etching rate may be obtained as the distribution of the value normalized with the baseline condition being 1.

[0044] The processing condition data 221 stores a plurality of processing conditions implemented in this way. For example, the processing condition data 221 stores the set current value of each coil 51 for each processing condition. For example, the processing condition data 221 stores the set current value of each coil 51 for each processing condition created by the experimental design method.

[0045] The processing result data 222 stores the processing results of the plasma etching process on the substrate W for each processing condition. For example, the processing condition data 221 stores data on the distribution of the etching rate for each processing condition. For example, the processing condition data 221 stores data on the etching rate at each of 26 points at regular intervals in the radial direction from the center of the substrate W for each processing condition.

[0046] The calculation unit 231 calculates the correlation between the spatial distribution value of the magnetic field in the plasma processing chamber 10 and the processing result of the plasma etching process on the substrate W from the processing condition data 221 and the processing result data 222.

[0047] FIG. 5 is a diagram for explaining the flow of calculating the correlation according to the embodiment.

[0048] The calculation unit 231 calculates the spatial distribution of the magnetic field in the plasma processing chamber 10 from the set current value of each coil 51 using the magnetic field calculation model of the magnetic field calculation model data 224 for each processing condition stored in the processing result data 222. For example, the calculation unit 231 calculates the spatial distribution of the magnetic field in the plasma processing chamber 10 from the set current value of each coil 51 using the arithmetic expression of the magnetic field calculation model for each processing condition.

[0049] FIG. 6 is a diagram showing an example of the spatial distribution of the magnetic field in the plasma processing chamber 10 according to the embodiment. FIG. 6 shows a schematic cross-section of the plasma processing chamber 10, and the strength of the magnetic field is schematically shown by a pattern. The plasma processing chamber 10 is formed in a cylindrical shape. Therefore, the spatial distribution of the magnetic field in the plasma processing chamber 10 has symmetry in the radial direction with respect to the central axis. The calculation unit 231 calculates the spatial distribution of the magnetic field in the cross-section of the plasma processing chamber 10 from the set current values of the respective coils 51 for each processing condition using the arithmetic expression of the magnetic field calculation model. For example, the calculation unit 231 calculates the spatial distribution of the magnetic field by calculating the magnetic field at each position where the radius r from the central axis in the plasma processing chamber 10 and the height z are at regular intervals with the radius r and the height z. For example, the calculation unit 231 calculates the magnetic field at each of 4000 points in the plasma processing chamber 10 from the set current values of the respective coils 51 for each processing condition using the arithmetic expression of the magnetic field calculation model. The magnetic field may use the absolute value of the magnetic field vector, may calculate the radial component, the height direction component, or a combination thereof, and may use the calculated value after normalization as the value.

[0050] The calculation unit 231 performs principal component analysis on the data of the spatial distribution of the magnetic field in the plasma processing chamber 10 including all of the plurality of processing conditions, and calculates the principal components of the magnetic field. For example, the calculation unit 231 performs principal component analysis on the magnetic field data at each position in the plasma processing chamber 10 including all of the plurality of processing conditions, and calculates the principal components equal to or less than the number of coils 51 of the electromagnet 50. For example, five principal components from the first principal component to the fifth principal component are calculated. The number of principal components to be calculated may be equal to or less than the number of coils 51 of the electromagnet 50. For example, it may be up to a specific principal component such as the first principal component to the third principal component, or may change dynamically. For example, the cumulative contribution rate obtained by cumulatively adding the contribution rates of the principal components in order from the first principal component may be obtained, and the principal components may be calculated until the cumulative contribution rate exceeds a predetermined value (for example, 80%).

[0051] Then, for each processing condition, the calculation unit 231 converts the data of the spatial distribution of the magnetic field in the plasma processing chamber 10 into the data of the scores of each main component of the magnetic field. For example, for each processing condition, the calculation unit 231 converts the magnetic field data at each of the 4000 points in the plasma processing chamber 10 into the data of the scores of the first to fifth main components. Thereby, the data of the spatial distribution of the magnetic field can be greatly compressed.

[0052] Also, the calculation unit 231 performs principal component analysis on the data of the distribution of all etching rates corresponding to a plurality of processing conditions stored in the processing result data 222, and calculates the principal components of the etching rate. For example, the calculation unit 231 performs principal component analysis on the etching rate data at each position in the radial direction from the center of the substrate W corresponding to a plurality of processing conditions. For example, five principal components from the first principal component to the fifth principal component are calculated. The number of principal components to be calculated may be equal to or more than the number of coils 51 of the electromagnet 50. For example, it may be up to a specific principal component such as the first principal component to the third principal component, or may change dynamically. For example, the cumulative contribution rate obtained by cumulatively adding the contribution rates of the principal components in order from the first principal component may be obtained, and the principal components until the cumulative contribution rate exceeds a predetermined value (for example, 80%) may be calculated.

[0053] Then, for each processing condition, the calculation unit 231 converts the data of the distribution of the etching rate into the data of the scores of each main component of the etching rate. For example, for each processing condition, the etching rate data at each of the 26 points in the radial direction from the center of the substrate W is converted into the data of the scores of the first to fifth main components. Thereby, the data of the distribution of the etching rate can be greatly compressed.

[0054] The calculation unit 231 calculates the correlation between the spatial distribution value of the magnetic field in the plasma processing chamber 10 when the plasma etching process is performed on the substrate W disposed in the plasma processing chamber 10 and the processing result of the plasma etching process on the substrate W. For example, the calculation unit 231 calculates the correlation between the score data of each main component of the magnetic field for each processing condition and the score data of each main component of the etching rate. For example, the calculation unit 231 calculates a relational expression showing the correlation between the score data of each main component of the magnetic field for each processing condition and the score data of each main component of the etching rate using a multivariate analysis model. In this case, each main component of the magnetic field is used as an explanatory variable, and each main component of the etching rate is used as an objective variable. Examples of the multivariate analysis model include a multiple regression model and a Gaussian process regression model. For example, the calculation unit 231 calculates a regression equation for calculating the score of each main component of the etching rate from the score of each main component of the magnetic field using a multiple regression model.

[0055] The calculation unit 231 stores the calculated correlation data as a prediction model in the prediction model data 223. For example, the calculation unit 231 stores the calculated regression equation in the prediction model data 223.

[0056] In the information processing apparatus 200, when making a prediction, the processing conditions of the plasma processing apparatus 1 for making the prediction are input as prediction conditions. The prediction conditions may be input from the input unit 212 or may be input as data from the external I / F unit 210 via a network. For example, the set current value of each coil 51 is input to the information processing apparatus 200 as the prediction conditions.

[0057] The prediction unit 232 predicts the processing result of the plasma etching process on the substrate W from the prediction conditions.

[0058] FIG. 7 is a diagram for explaining the flow of predicting the processing result of the plasma etching process according to the embodiment.

[0059] The prediction unit 232 calculates the spatial distribution of the magnetic field in the plasma processing chamber 10 from the processing conditions set as prediction conditions using the magnetic field calculation model in the magnetic field calculation model data 224. For example, the prediction unit 232 calculates the spatial distribution of the magnetic field in the plasma processing chamber 10 from the set current values of each coil 51 set as prediction conditions using the arithmetic expression of the magnetic field calculation model. For example, similar to when calculating the correlation, the prediction unit 232 sets the radius r from the central axis in the plasma processing chamber 10 and the height z, and calculates the magnetic field at each position with a constant interval for the radius r and the height z to calculate the spatial distribution of the magnetic field. For example, the prediction unit 232 calculates the magnetic field at each of the 4000 points in the plasma processing chamber 10 from the set current values of each coil 51 for each processing condition using the arithmetic expression of the magnetic field calculation model. The magnetic field may be a value obtained by normalizing the calculated value.

[0060] The prediction unit 232 converts the calculated data of the spatial distribution of the magnetic field in the plasma processing chamber 10 into data of the scores of each principal component using each principal component of the magnetic field when calculating the correlation. For example, the prediction unit 232 converts the magnetic field data at each of the 4000 points in the plasma processing chamber 10 into data of the scores of the first to fifth principal components of the magnetic field.

[0061] The prediction unit 232 predicts the processing result of the plasma etching process on the substrate W from the spatial distribution value of the magnetic field in the plasma processing chamber 10 using the prediction model stored in the prediction model data 223. For example, the prediction unit 232 calculates the scores of each principal component of the etching rate from the scores of each principal component of the magnetic field using the regression equation stored in the prediction model data 223. For example, the prediction unit 232 calculates the scores of the first to fifth principal components of the etching rate.

[0062] The prediction unit 232 inverse-transforms the scores of the respective principal components of the calculated etching rate to convert them into data on the distribution of the etching rate. For example, the prediction unit 232 inverse-transforms the scores of the respective principal components of the etching rate using the respective principal components of the etching rate when calculating the correlation, and converts them into data on the distribution of the etching rate. For example, the prediction unit 232 converts the score data of the first to fifth principal components of the etching rate into the etching rate data at each of 26 points in the radial direction from the center of the substrate W.

[0063] The prediction unit 232 predicts the tilting distribution of the substrate W from the distribution of the etching rate of the substrate W. For example, the prediction unit 232 calculates a differential value obtained by differentiating the etching rate value of the substrate W at each position in the radial direction of the substrate W. For example, the prediction unit 232 calculates the difference in the etching rate between the position one inside in the radial direction and the etching rate for each of 26 points in the radial direction from the center of the substrate W. Tilting occurs at the part where the etching rate changes. Therefore, the differential value of the etching rate corresponds to the tilting angle.

[0064] The display control unit 233 performs display control to display the processing result of the plasma etching process predicted by the prediction unit 232 on the display unit 211. For example, the display control unit 233 performs display control to display the predicted distribution of the etching rate and the distribution of tilting on the display unit 211.

[0065] Note that the information processing apparatus 200 may output the data of the processing result of the plasma etching process predicted by the prediction unit 232 to another apparatus via the external I / F unit 210.

[0066] Next, an example of the prediction result by the information processing apparatus 200 will be described. First, an example of verifying the prediction result and the actual processing result for the etching rate will be described. FIG. 8 is a diagram showing an example of the verification result of the etching rate according to the embodiment. FIG. 8 verifies the prediction result and the actual processing result of the etching rate for each processing condition of the processing condition data 221 used for calculating the prediction model. The horizontal axis is the axis obtained by normalizing the actually measured actual etching rate. The vertical axis is the axis obtained by normalizing the predicted etching rate. In FIG. 8, for each processing condition of the processing condition data 221 used for calculating the prediction model, a point is plotted at a position where the horizontal axis is the actual etching rate and the vertical axis is the predicted etching rate. Further, FIG. 8 shows the result of obtaining the correlation between the actual etching rate and the predicted etching rate for each processing condition. The correlation coefficient R 2 is a high value of 0.9876. Therefore, the information processing apparatus 200 can predict the etching rate of each processing condition of the processing condition data 221 with high accuracy.

[0067] FIG. 9 is a diagram showing another example of the verification result of the etching rate according to the embodiment. FIG. 9 verifies the prediction result and the actual processing result of the etching rate for processing conditions other than the processing conditions of the processing condition data 221. The horizontal axis is the axis obtained by normalizing the actual etching rate. The vertical axis is the axis obtained by normalizing the predicted etching rate. In FIG. 9, for each processing condition, a point is plotted at a position where the horizontal axis is the actual etching rate and the horizontal axis is the predicted etching rate. FIG. 9 shows the result of obtaining the correlation between the actual etching rate and the predicted etching rate for each processing condition. The correlation coefficient R 2 is a high value of 0.9831. Therefore, the information processing apparatus 200 can also predict the etching rate with high accuracy for processing conditions other than the processing conditions of the processing condition data 221. From this, the information processing apparatus 200 can predict the etching rate with high accuracy.

[0068] Next, an example of verifying the prediction result and the actual processing result for tilting will be described. FIG. 10 is a diagram showing an example of the verification result of tilting according to the embodiment. In FIG. 10, the change in the tilting angle with respect to the distance R from the center of the substrate W is shown. The line L1 indicates the predicted tilting angle. The line L2 indicates the actually measured actual tilting angle. The line L1 and the line L2 generally have the same shape. From this, the information processing apparatus 200 can predict the tilting angle with high accuracy.

[0069] Next, the processing flow of the prediction method implemented by the information processing apparatus 200 according to the embodiment will be described. First, the processing flow of the calculation process for calculating the correlation will be described. FIG. 11 is a diagram for explaining an example of the processing order of the calculation process according to the embodiment. The calculation process shown in FIG. 11 is executed when the processing condition data 221 and the processing result data 222 are stored in the storage unit 213 and a predetermined processing start instruction is given. FIGS. 12A to 12F are diagrams showing an example of the data used in the calculation process according to the embodiment.

[0070] The calculation unit 231 calculates the spatial distribution of the magnetic field in the plasma processing chamber 10 from the set current values of the respective coils 51 using the magnetic field calculation model of the magnetic field calculation model data 224 for each of the plurality of processing conditions stored in the processing condition data 221 (step S10). In FIG. 12A, the set current values of the five coils 51, C1 to C5, are shown as processing conditions 1 to 20. For example, the calculation unit 231 calculates the magnetic field at each of the 4000 points in the plasma processing chamber 10 using the arithmetic expression of the magnetic field calculation model from the set current values of C1 to C5 for each of the processing conditions 1 to 20. FIG. 12B shows the magnetic field data at each of the 4000 points in the plasma processing chamber 10.

[0071] The calculation unit 231 performs principal component analysis on the data of the spatial distribution of the magnetic field in the plasma processing chamber 10 including all of a plurality of processing conditions, and calculates the principal components of the magnetic field (step S11). Then, for each processing condition, the calculation unit 231 converts the data of the spatial distribution of the magnetic field in the plasma processing chamber 10 into the data of the scores of the respective principal components of the magnetic field (step S12). For example, the calculation unit 231 performs principal component analysis on the magnetic field data of 4000 points for processing conditions 1 to 20, and calculates the first to fifth principal components of the magnetic field. Then, the calculation unit 231 converts the magnetic field data of 4000 points for processing conditions 1 to 20 into the data of the scores of the first to fifth principal components. FIG. 12C shows the data of the scores of the first to fifth principal components for processing conditions 1 to 20.

[0072] Further, the calculation unit 231 performs principal component analysis on the data of the distribution of the etching rate including all of a plurality of processing conditions stored in the processing result data 222, and calculates the principal components (step S13). Then, for each processing condition, the calculation unit 231 converts the data of the distribution of the etching rate into the data of the scores of the respective principal components of the etching rate (step S14). FIG. 12D shows the etching rates at substrate positions 1 to 26, which are 26 points in the radial direction from the center of the substrate W, for processing conditions 1 to 20. For example, the calculation unit 231 performs principal component analysis on the etching rate data at substrate positions 1 to 26 for processing conditions 1 to 20, and calculates the first to fifth principal components of the etching rate. Then, the calculation unit 231 performs principal component analysis on the etching rate data at substrate positions 1 to 26 for processing conditions 1 to 20, and calculates the first to fifth principal components of the etching rate. Then, the calculation unit 231 converts the etching rate data at substrate positions 1 to 26 for processing conditions 1 to 20 into the data of the scores of the first to fifth principal components. FIG. 12E shows the data of the scores of the first to fifth principal components for processing conditions 1 to 20.

[0073] The calculation unit 231 calculates the correlation between the spatial distribution value of the magnetic field in the plasma processing chamber 10 when the plasma etching process is performed on the substrate W disposed in the plasma processing chamber 10 and the processing result of the plasma etching process on the substrate W (step S15). For example, the calculation unit 231 calculates a regression equation indicating the correlation between the data of the scores of the main components of the magnetic field for each processing condition and the data of the scores of the main components of the etching rate. For example, as shown in FIG. 12F, the calculation unit 231 uses the data of the scores of the first to fifth main components of the magnetic field under processing conditions 1 to 20 as explanatory variables and the scores of the first to fifth main components of the etching rate under processing conditions 1 to 20 as the target variable to calculate a regression model representing the correlation.

[0074] The calculation unit 231 stores the calculated correlation data as a prediction model in the prediction model data 223. For example, the calculation unit 231 stores the calculated regression equation in the prediction model data 223 (step S16) and ends the process.

[0075] Note that the calculation process may be performed in the reverse order of steps S10 to S12 and steps S13 and S14, or may be executed in parallel.

[0076] Next, the flow of the prediction process for predicting the processing result of the plasma etching process on the substrate W will be described. FIG. 13 is a diagram for explaining an example of the processing order of the prediction process according to the embodiment. The prediction process shown in FIG. 13 is executed when the processing conditions set as the prediction conditions are input and a predetermined processing start instruction is given. FIGS. 14A to 14E are diagrams showing an example of the data used in the prediction process according to the embodiment.

[0077] The prediction unit 232 calculates the spatial distribution of the magnetic field in the plasma processing chamber 10 from the processing conditions set as the prediction conditions using the magnetic field calculation model of the magnetic field calculation model data 224 (step S20). The prediction unit 232 converts the calculated data of the spatial distribution of the magnetic field in the plasma processing chamber 10 into data of the scores of the respective principal components of the magnetic field using the respective principal components of the magnetic field when calculating the correlation (step S21). In FIG. 14A, as the processing conditions set as the prediction conditions, the set current values of the five coils 51 are shown as C1 to C5. For example, the prediction unit 232 calculates the magnetic field at each of the 4000 points in the plasma processing chamber 10 using the arithmetic expression of the magnetic field calculation model from the set current values of C1 to C5 of the processing conditions set as the prediction conditions. In FIG. 14B, the magnetic field data at each of the 4000 points in the plasma processing chamber 10 is shown. The prediction unit 232 converts the magnetic field data at 4000 points into data of the scores of the first to fifth principal components of the magnetic field using the first to fifth principal components of the magnetic field. In FIG. 14C, the data of the scores of the first to fifth principal components of the magnetic field is shown.

[0078] The prediction unit 232 predicts the processing result of the plasma etching process on the substrate W from the spatial distribution value of the magnetic field in the plasma processing chamber 10 using the prediction model stored in the prediction model data 223 (step S22). For example, the prediction unit 232 calculates the scores of the respective principal components of the etching rate from the scores of the respective principal components of the magnetic field using the regression formula stored in the prediction model data 223. For example, the prediction unit 232 calculates the data of the scores of the first to fifth principal components of the etching rate from the data of the scores of the first to fifth principal components of the magnetic field using the regression model representing the correlation. In FIG. 14D, the data of the scores of the first to fifth principal components of the etching rate is shown.

[0079] The prediction unit 232 converts the scores of the respective principal components of the calculated etching rate into data of the distribution of the etching rate by inverse transformation of the principal component analysis (step S23). For example, the prediction unit 232 performs inverse transformation of the principal component analysis of the etching rate calculated in step S13 on the scores of the first to fifth principal components of the etching rate, and calculates predicted values of the etching rate at substrate positions 1 to 26. FIG. 14E shows the predicted values of the etching rate at substrate positions 1 to 26.

[0080] The prediction unit 232 predicts the tilting distribution of the substrate W from the distribution of the etching rate of the substrate W (step S24), and ends the process. For example, the prediction unit 232 calculates, as the tilting distribution, a differential value obtained by differentiating the value of the etching rate of the substrate W at each position in the radial direction of the substrate W.

[0081] In this way, the information processing apparatus 200 can predict the processing result of the plasma etching process. For example, the information processing apparatus 200 can predict the distribution of the etching rate of the substrate W when the plasma processing apparatus 1 performs the plasma etching process on the substrate W under the prediction conditions. Further, the information processing apparatus 200 can predict the tilting distribution of the substrate W when the plasma processing apparatus 1 performs the plasma etching process on the substrate W under the prediction conditions.

[0082] In the above embodiment, the case of calculating the correlation between the data of the scores of the main components of the magnetic field for each processing condition and the data of the scores of the main components of the etching rate was described as an example. However, the present invention is not limited to this. The calculation unit 231 may calculate the correlation between the data of the spatial distribution of the magnetic field for each processing condition and the data of the distribution of the etching rate. For example, the calculation unit 231 may calculate the correlation between the magnetic field data at each of the 4000 points in the plasma processing chamber 10 for each processing condition and the etching rate data at each of the 26 points in the radial direction from the center of the substrate W, and calculate a regression equation. In this case, the spatial distribution of the magnetic field (4000 points) is used as an explanatory variable, and the etching rate (26 points) is used as a target variable. In this case, the prediction unit 232 can directly calculate the data of the distribution of the etching rate from the data of the spatial distribution of the magnetic field in the plasma processing chamber 10 using the calculated regression equation.

[0083] Also, in the above embodiment, the case of calculating the spatial distribution of the magnetic field in the plasma processing chamber 10 from the processing conditions using the magnetic field calculation model of the magnetic field calculation model data 224 in the information processing apparatus 200 was described as an example. However, the present invention is not limited to this. The data of the spatial distribution of the magnetic field in the plasma processing chamber 10 may be calculated by another device and transmitted to the information processing apparatus 200. The calculation unit 231 may calculate the correlation using the data of the spatial distribution of the magnetic field in the plasma processing chamber 10 received from another device.

[0084] Further, in the above-described embodiment, in the information processing apparatus 200, the case where principal component analysis is performed on the data of the spatial distribution of the magnetic field including all of the plurality of processing conditions and the data of the distribution of the etching rate has been described as an example. However, the present invention is not limited to this. The principal component analysis may be performed by another apparatus. For example, the data of the scores of the principal components of the magnetic field for each processing condition may be calculated by another apparatus and transmitted to the information processing apparatus 200. Further, the data of the scores of the principal components of the etching rate for each processing condition may be calculated by another apparatus and transmitted to the information processing apparatus 200. The calculation unit 231 may calculate the correlation using the data of the scores of the principal components of the magnetic field for each processing condition and the data of the scores of the principal components of the etching rate received from another apparatus.

[0085] Further, in the above-described embodiment, in the prediction, the case where the distribution of the etching rate is calculated and the distribution of the tilting is calculated from the distribution of the etching rate has been described as an example. However, the present invention is not limited to this. The prediction unit 232 may directly calculate the distribution of the tilting using the prediction model. In this case, for example, the data of the distribution of the tilting is stored in the processing condition data 221 as the processing result of the plasma etching process for each processing condition. The tilting can be obtained by measuring the inclination of the holes of the substrate W subjected to the plasma etching process by X-ray measurement technology. For example, the distribution of the inclination of the holes of the substrate W in the plane of the substrate is measured by an X-ray measurement apparatus, and the data of the distribution of the tilting of the substrate W is stored in the processing condition data 221. The calculation unit 231 calculates the correlation between the spatial distribution value of the magnetic field in the plasma processing chamber 10 when the plasma etching process is performed on the substrate W disposed in the plasma processing chamber 10 and the distribution of the tilting of the substrate W. Thereby, the prediction unit 232 can directly calculate the distribution of the tilting of the substrate W from the prediction conditions based on the calculated correlation.

[0086] In the above-described embodiment, the case where the processing result of the plasma etching process is predicted by an information processing apparatus 200 separate from the plasma processing system has been described as an example. However, the present invention is not limited to this. The plasma processing system may be configured to include the information processing apparatus 200. The plasma processing system may operate the information processing apparatus 200 together with the control unit 2. Further, the control unit 2 and the information processing apparatus 200 may be integrally configured. For example, the functions of the above-described calculation unit 231 and prediction unit 232 may be incorporated into the control unit 2. FIG. 15 is a diagram showing another example of the schematic configuration of the plasma processing system according to the embodiment. FIG. 15 shows a case where the control unit 2 and the information processing apparatus 200 are integrally configured, and the control unit 2 includes the information processing apparatus 200. In this case, the plasma processing system can predict the processing result of the plasma etching process in the control unit 2.

[0087] Also, the plasma etching process for the substrate W may have a plurality of steps. For example, the plasma etching process may be a cycle etching in which RF power is repeatedly applied in a pulsed manner. Further, the plasma etching process may sequentially perform a plurality of etching processes. The information processing apparatus 200 may collectively predict the processing results of the plurality of steps. Also, the information processing apparatus 200 may predict the processing result of each step and predict the final processing result by integrating the predicted processing results of each step.

[0088] Here, in the present embodiment, the spatial distribution value of the magnetic field is calculated from the set current value of the coil 51, and the correlation between the calculated spatial distribution value of the magnetic field and the processing result of the plasma etching process for the substrate W is calculated. The spatial distribution of the magnetic field can be calculated from the set current value of the coil 51. Therefore, it is conceivable to calculate the correlation between the set current value of the coil 51 and the processing result of the plasma etching process for the substrate W and perform prediction. However, the prediction error can be reduced by changing the explanatory variable of the relational expression showing the correlation from the set current value to the magnetic field.

[0089] FIG. 16 is a diagram showing an example of prediction error according to an embodiment. The horizontal axis shows the explanatory variables of the relational expression indicating the correlation relationship, including the case where the set current value of the coil 51 is used, the case where the spatial distribution of the magnetic field is used, and the case where the principal component of the spatial distribution of the magnetic field is used. The vertical axis shows the target variables of the relational expression indicating the correlation relationship, including the case where the etching rate is used and the case where the principal component of the etching rate is used. FIG. 16 shows the prediction error in the relational expression indicating the correlation relationship with the explanatory variable and the target variable respectively. The prediction error is shown after being normalized with the minimum value being 1. When the explanatory variable is the spatial distribution of the magnetic field or the principal component of the spatial distribution of the magnetic field and the target variable is the etching rate, the prediction error is the smallest and becomes 1, indicating that high accuracy is obtained. Also, even when the explanatory variable is the spatial distribution of the magnetic field or the principal component of the spatial distribution of the magnetic field and the target variable is the principal component of the etching rate, the prediction error is sufficiently small and high accuracy is obtained. On the other hand, when the explanatory variable is the set current value of the coil 51, the prediction error is about 1.16, which is a decrease of about 16%. The reason for this is considered as follows. The magnetic field directly affects the plasma in the plasma processing chamber 10. Therefore, it is considered that using the magnetic field directly for the target variable results in better accuracy than using the set current value of the coil 51 that indirectly calculates the magnetic field for the target variable.

[0090] As described above, the prediction method according to the embodiment includes a calculation step (steps S10 to S15) and a prediction step (steps S20 to S24). The calculation step calculates the correlation relationship between the spatial distribution value of the magnetic field in the plasma processing chamber 10 when plasma etching processing is performed on the substrate W disposed in the plasma processing chamber 10 and the processing result of the plasma etching processing on the substrate W. The prediction step predicts the processing result of the plasma etching processing on the substrate W from the spatial distribution value of the magnetic field in the plasma processing chamber 10 based on the calculated correlation relationship. Thereby, the prediction method according to the embodiment can predict the processing result of the plasma etching processing.

[0091] In addition, the spatial distribution value of the magnetic field is calculated from the set current value of the electromagnet 50 provided in the plasma processing chamber 10. Thereby, the prediction method according to the embodiment can predict the processing result of the plasma etching process from the set current value of the electromagnet 50.

[0092] In addition, the spatial distribution value of the magnetic field is the score of the principal component (principal component score) obtained by principal component analysis. Thereby, the prediction method according to the embodiment can reduce the data amount of the spatial distribution value of the magnetic field, and can reduce the calculation load when calculating the correlation relationship or predicting the processing result.

[0093] In addition, the number of principal components is less than or equal to the number of coils 51 of the electromagnet 50 provided in the plasma processing chamber 10. Thereby, the prediction method according to the embodiment can reduce the data amount of the spatial distribution value of the magnetic field.

[0094] In addition, the processing result is the distribution in the substrate plane of the inclination of the holes formed by the plasma etching process. Thereby, the prediction method according to the embodiment can predict the distribution in the substrate plane of the tilting.

[0095] In addition, the distribution in the substrate plane of the inclination of the holes was measured by X-ray measurement technology. Thereby, it is possible to measure the distribution in the substrate plane of the inclination of the holes even for the fine holes formed in the substrate W.

[0096] In addition, the processing result is the distribution in the substrate plane of the etching rate of the plasma etching process. The prediction step predicts the distribution in the substrate plane of the etching rate, and differentiates the predicted distribution in the substrate plane of the etching rate by the distance from the center of the substrate W to predict the distribution in the substrate plane of the inclination of the holes formed by the plasma etching process. Thereby, the prediction method according to the embodiment can predict the distribution in the substrate plane of the tilting even when using the distribution in the substrate plane of the etching rate as the processing result.

[0097] Further, the correlation is calculated using a multivariate analysis model. The multivariate analysis model is a multiple regression model or a Gaussian process regression model. Thereby, the prediction method according to the embodiment can accurately obtain the correlation between the spatial distribution value of the magnetic field in the plasma processing chamber 10 and the processing result.

[0098] As described above, the embodiments have been described. However, the embodiments disclosed this time should be considered to be illustrative in all respects and not restrictive. In fact, the above-described embodiments can be embodied in various forms. Further, the above-described embodiments may be omitted, replaced, or changed in various forms without departing from the scope and spirit of the claims.

[0099] For example, in the above embodiment, the case where plasma processing is performed on a semiconductor wafer as the substrate W has been described as an example, but it is not limited thereto. The substrate W can be any one.

[0100] Note that the embodiments disclosed this time should be considered to be illustrative in all respects and not restrictive. In fact, the above-described embodiments can be embodied in various forms. Further, the above embodiments may be omitted, replaced, or changed in various forms without departing from the scope and spirit of the appended claims.

Description of Reference Numerals

[0101] 1 Plasma processing apparatus 2 Control unit 10 Plasma processing chamber 50 Electromagnet 51, 51a~51e Coil 56 Electromagnet excitation circuit 60 Bulk region 61 Sheath region 62 Sheath surface 63 Hole 200 Information processing apparatus 211 Display unit 212 Input unit 213 Storage unit 214 Controller 221 Processing condition data 222 Processing result data 223 Prediction model data 224 Magnetic field calculation model data 231 Calculation unit 232 Prediction unit 233 Display control unit W substrate

Claims

1. A calculating step of calculating a correlation between a spatial distribution value of a magnetic field in the chamber when performing a plasma etching process on a substrate disposed in the chamber and a processing result of the plasma etching process on the substrate; A predicting step of predicting a processing result of the plasma etching process on the substrate from the spatial distribution value of the magnetic field in the chamber based on the calculated correlation; comprising; The spatial distribution value of the magnetic field is a principal component score of a principal component obtained by principal component analysis Prediction method.

2. A calculating step of calculating a correlation between a spatial distribution value of a magnetic field in the chamber when performing a plasma etching process on a substrate disposed in the chamber and a processing result of the plasma etching process on the substrate; A predicting step of predicting a processing result of the plasma etching process on the substrate from the spatial distribution value of the magnetic field in the chamber based on the calculated correlation; comprising; The processing result is a distribution in the substrate plane of the inclination of the holes formed by the plasma etching process, measured by X-ray measurement technology Prediction method.

3. A calculating step of calculating a correlation between a spatial distribution value of a magnetic field in the chamber when performing a plasma etching process on a substrate disposed in the chamber and a processing result of the plasma etching process on the substrate; A predicting step of predicting a processing result of the plasma etching process on the substrate from the spatial distribution value of the magnetic field in the chamber based on the calculated correlation; comprising; The correlation is calculated using a multivariate analysis model Prediction method.

4. The spatial distribution value of the magnetic field is calculated from the set current value of the electromagnet provided in the chamber The prediction method according to any one of Claims 1 to 3.

5. The spatial distribution value of the magnetic field is a principal component score of a principal component obtained by principal component analysis The prediction method according to Claim 2 or 3.

6. The number of the principal components is equal to or less than the number of coils of the electromagnet provided in the chamber The prediction method according to Claim 1 or 5.

7. The processing result is a distribution in the substrate plane of the inclination of the holes formed by the plasma etching process The prediction method according to Claim 1 or 3.

8. The distribution in the substrate plane of the inclination of the holes is measured by X-ray measurement technology The prediction method according to Claim 7.

9. The processing result is a distribution in the substrate plane of the etching rate of the plasma etching process, The prediction process predicts the distribution of the etching rate within the substrate surface, and by differentiating the predicted distribution of the etching rate within the substrate surface with respect to the distance from the center of the substrate, predicts the distribution within the substrate surface of the inclination of the holes formed by the plasma etching process. The prediction method according to claim 1 or 3.

10. The correlation is calculated using a multivariate analysis model. The prediction method according to claim 1 or 2.

11. The multivariate analysis model is a multiple regression model or a Gaussian process regression model. The prediction method according to claim 10.

12. The plasma etching process of the substrate has a plurality of steps. The prediction method according to any one of claims 1 to 11.

13. A calculation unit that calculates the correlation between the spatial distribution value of the magnetic field in the chamber when performing a plasma etching process on a substrate disposed in the chamber and the processing result of the plasma etching process on the substrate; A prediction unit that predicts the processing result of the plasma etching process from the spatial distribution value of the magnetic field in the chamber based on the calculated correlation, and has The spatial distribution value of the magnetic field is the principal component score of the principal component obtained by principal component analysis. Information processing apparatus.

14. A calculation unit that calculates the correlation between the spatial distribution value of the magnetic field in the chamber when performing a plasma etching process on a substrate disposed in the chamber and the processing result of the plasma etching process on the substrate; A prediction unit that predicts the processing result of the plasma etching process from the spatial distribution value of the magnetic field in the chamber based on the calculated correlation, and has The processing result is the distribution within the substrate surface of the inclination of the holes formed by the plasma etching process, which is the inclination of the holes measured by X-ray measurement technology. Information processing apparatus.

15. A calculation unit that calculates the correlation between the spatial distribution value of the magnetic field in the chamber when performing a plasma etching process on a substrate disposed in the chamber and the processing result of the plasma etching process on the substrate; A prediction unit that predicts the processing result of the plasma etching process from the spatial distribution value of the magnetic field in the chamber based on the calculated correlation, and has The correlation is calculated using a multivariate analysis model. Information processing apparatus.

Images