JP2021174959A - Substrate processing apparatus, substrate processing method, method for generating data for learning, learning method, learning device, method for creating learned model, and learned model - Google Patents

Abstract

To appropriately eliminate static electricity on a substrate to be processed.SOLUTION: A substrate processing apparatus (100) comprises a substrate holding unit (120), an electrification distribution measuring unit (130), a static eliminating unit (140), a substrate information acquisition unit (22a), a static elimination processing condition information acquisition unit (22b), and a control unit (22). The substrate information acquisition unit (22a) acquires substrate information including electrification distribution information indicating the distribution of electrification on a substrate to be processed. The static elimination processing condition information acquisition unit (22b) acquires, based on the substrate information, a static elimination processing condition for the substrate to be processed from a learned model. The control unit (22) controls the substrate holding unit (120) and the static eliminating unit (140) to eliminate static electricity on the substrate to be processed based on the static elimination processing condition information acquired by the static elimination processing condition information acquisition unit (22b).SELECTED DRAWING: Figure 4

Description

The present invention relates to a substrate processing apparatus, a substrate processing method, a learning data generation method, a learning method, a learning apparatus, a trained model generation method, and a trained model.

A substrate processing apparatus for processing a substrate is suitably used for manufacturing a semiconductor substrate or the like. If the substrate is charged during processing in the substrate processing apparatus, particles may reattach to the substrate or the substrate may be damaged by electric discharge. Therefore, it has been studied to suppress the charging of the substrate (see Patent Document 1).

In the substrate processing method of Patent Document 1, when a liquid containing pure water having a relatively high specific resistance is supplied to the substrate, the liquid is first supplied while rotating the substrate at a relatively high rotation speed, and then the liquid is relatively supplied later. The liquid is supplied while rotating the substrate at a low rotation speed. As a result, the rate of increase in the surface potential of the substrate is suppressed.

Japanese Unexamined Patent Publication No. 2014-203906

However, the substrate processing method of Patent Document 1 can suppress the charge of the substrate when it is treated with a liquid containing pure water, but cannot eliminate the charged substrate. For example, a substrate that has been ion-implanted or dry-etched may be charged, and if a treatment liquid is supplied to such a substrate, particles may reattach to the substrate or the substrate may be damaged by electric discharge. .. Further, when static elimination of the substrate according to the recipe, the charge status of the substrate varies greatly due to minute differences between the substrates, so that the static elimination treatment may not be appropriate.

The present invention has been made in view of the above problems, and an object of the present invention is a substrate processing apparatus capable of appropriately eliminating static electricity from a substrate to be processed, a substrate processing method, a learning data generation method, a learning method, a learning apparatus, and learned. The purpose is to provide a model generation method and a trained model.

According to one aspect of the present invention, the substrate processing apparatus has a substrate holding unit that rotatably holds the substrate to be processed, a charge distribution measuring unit that measures the charge distribution of the substrate to be processed, and static elimination of the substrate to be processed. A static elimination unit to be processed, a substrate information acquisition unit that acquires substrate information including charge distribution information indicating the charge distribution of the processing target substrate, and static elimination processing conditions of the processing target substrate from a learned model based on the substrate information. Based on the static elimination processing condition information acquisition unit that acquires the static elimination processing condition information indicating, and the static elimination processing condition information acquired by the static elimination processing condition information acquisition unit, the substrate holding unit so as to eliminate static electricity on the processing target substrate. And a control unit that controls the static elimination unit. The trained model includes substrate information including charge distribution information indicating the charge distribution of the learning target substrate, static elimination processing condition information indicating the conditions for static elimination processing of the learning target substrate, and the result of static elimination processing of the learning target substrate. It is constructed by machine learning the learning data associated with the processing result information shown.

In certain embodiments, the substrate processing apparatus further comprises a storage unit that stores the trained model.

In certain embodiments, for each of the processing target substrate and the learning target substrate, the substrate information further includes information indicating the film type or film thickness of the substrate.

In a certain embodiment, the static elimination liquid is supplied to each of the processing target substrate and the learning target substrate.

In a certain embodiment, for each of the processing target substrate and the learning target substrate, the static elimination processing condition information includes the concentration of the static elimination liquid, the temperature of the static elimination liquid, the supply amount of the static elimination liquid, and the discharge pattern of the static elimination liquid. , And information indicating any of the rotational speeds of the substrate when supplying the static elimination liquid.

In a certain embodiment, the processing target substrate and the learning target substrate are each irradiated with ultraviolet rays.

According to another aspect of the present invention, the substrate processing method includes a step of holding the substrate to be processed rotatably, a step of acquiring substrate information including charge distribution information indicating the charge distribution of the substrate to be processed, and the above-mentioned step. Based on the board information, a step of acquiring static elimination processing condition information indicating the static elimination processing conditions of the processing target substrate from the trained model and a step of static elimination of the processing target substrate according to the static elimination processing conditions of the static elimination processing condition information. Include. In the step of acquiring the static elimination processing condition information, the trained model includes substrate information including charge distribution information indicating the charging distribution of the learning target substrate, and static elimination processing condition information indicating the conditions for static elimination processing of the learning target substrate. , It is constructed by machine learning the learning data associated with the processing result information indicating the result of static elimination processing of the learning target substrate.

According to still another aspect of the present invention, the method of generating the learning data obtains the charging distribution information indicating the charging distribution of the learning target substrate from the time series data output from the substrate processing apparatus that processes the learning target substrate. The board processing apparatus includes a step of acquiring board information including, a step of acquiring static elimination processing condition information indicating a condition for statically eliminating the learning target substrate in the board processing apparatus from the time series data, and a step of acquiring static elimination processing condition information indicating the condition of static elimination of the learning target substrate from the time series data. In the step of acquiring the processing result information indicating the result of static elimination of the learning target substrate, the substrate information, the static elimination processing condition information, and the processing result information of the learning target substrate are associated and stored in the storage unit as learning data. Including the steps to be taken.

According to still another aspect of the present invention, the learning method includes a step of acquiring the learning data generated according to the learning data generation method described above, and inputting the learning data into the learning program. It includes a step of machine learning the training data.

According to still another aspect of the present invention, the learning device inputs a storage unit that stores the learning data generated according to the learning data generation method described above, and the learning data into the learning program. It is provided with a learning unit for machine learning the learning data.

According to still another aspect of the present invention, the trained model generation method includes a step of acquiring the training data generated according to the training data generation method described above, and machine learning of the training data. It includes steps to generate a trained model constructed by letting it.

According to yet another aspect of the present invention, the trained model is constructed by machine learning the training data generated according to the training data generation method described above.

According to still another aspect of the present invention, the substrate processing apparatus includes a substrate holding unit that rotatably holds the substrate, a charge distribution measuring unit that measures the charge distribution of the substrate, and a static elimination unit that eliminates static electricity from the substrate. , A storage unit that stores a conversion table in which board information including charge distribution information and static elimination processing condition information indicating static elimination processing conditions are associated with each other, and substrate information including charge distribution information indicating the charge distribution of the substrate. The board information acquisition unit to be acquired, the static elimination processing condition information acquisition unit that acquires static elimination processing condition information indicating the static elimination processing conditions of the substrate based on the substrate information, and the static elimination processing condition information acquisition. Based on the static elimination processing condition information acquired in the unit, the substrate holding unit and a control unit that controls the static elimination unit are provided so as to eliminate static electricity on the substrate.

According to the present invention, the substrate to be processed can be appropriately statically eliminated.

It is a schematic diagram of the board processing learning system provided with the board processing apparatus of this embodiment. It is a schematic diagram of the board processing system provided with the board processing apparatus of this embodiment. It is a schematic diagram of the substrate processing apparatus of this embodiment. It is a block diagram of the board processing system provided with the board processing apparatus of this embodiment. (A) is a flow chart of the substrate processing method of this embodiment, and (b) is a flow chart of static elimination processing in the substrate processing method of this embodiment. It is a figure which shows the charge distribution of the substrate measured by the substrate processing apparatus of this embodiment. (A) to (d) are schematic views showing the static elimination process in the substrate processing apparatus of this embodiment. It is a block diagram of the substrate processing apparatus and learning data generation apparatus of this embodiment. It is a flow figure which shows the learning data generation method of this embodiment. It is a block diagram of the learning data generation apparatus and learning apparatus of this embodiment. It is a flow chart which shows the learning method of this embodiment and the generation method of a trained model. It is a figure which shows the learning data input to the learning device of this embodiment. It is a figure which shows the learning data input to the learning device of this embodiment. (A) is a diagram showing the charge distribution of the substrate to be processed measured by the substrate processing apparatus of the present embodiment, and (b) shows the static elimination treatment conditions acquired based on the charge distribution of the substrate to be processed. It is a figure. It is a figure which shows the learning data input to the learning device of this embodiment. It is a schematic diagram of the substrate processing apparatus of this embodiment. It is a figure which shows the learning data input to the learning device of this embodiment. It is a schematic diagram of the substrate processing apparatus of this embodiment. It is a figure which shows the learning data input to the learning device of this embodiment. It is a schematic diagram of the substrate processing apparatus of this embodiment. It is a figure which shows the learning data input to the learning device of this embodiment. (A) is a schematic view of a substrate holding portion in the substrate processing apparatus of this embodiment, and (b) to (d) are schematic top views of the substrate holding portion. It is a figure which shows the learning data input to the learning device of this embodiment. It is a block diagram of the substrate processing apparatus of this embodiment. It is a figure which shows the conversion table in the substrate processing apparatus of this embodiment.

Hereinafter, a substrate processing apparatus, a substrate processing method, a learning data generation method, a learning method, a learning apparatus, a trained model generation method, and an embodiment of the trained model will be described with reference to the drawings. .. In the drawings, the same or corresponding parts are designated by the same reference numerals and the description is not repeated. Further, in the specification of the present application, in order to facilitate understanding of the invention, the X direction, the Y direction and the Z direction which are orthogonal to each other may be described. Typically, the X and Y directions are parallel to the horizontal direction and the Z direction is parallel to the vertical direction.

First, the substrate processing learning system 200 including the substrate processing apparatus 100 of the present embodiment will be described with reference to FIG. First, the substrate processing learning system 200 will be described with reference to FIG.

FIG. 1 is a schematic view of a substrate processing learning system 200. As shown in FIG. 1, the board processing learning system 200 includes a board processing device 100, a board processing device 100L, a learning data generation device 300, and a learning device 400.

The substrate processing apparatus 100 processes the substrate to be processed. Here, the substrate processing apparatus 100 eliminates static electricity from the substrate to be processed. The substrate processing apparatus 100 may perform processing other than static elimination on the processing target substrate. The substrate processing apparatus 100 is a single-wafer type that processes the substrates to be processed one by one. Typically, the substrate to be processed has a substantially disk shape.

The substrate processing device 100L processes the learning target substrate. Here, the substrate processing device 100L eliminates static electricity from the learning target substrate. The substrate processing apparatus 100L may perform processing other than static elimination on the learning target substrate. The configuration of the learning target substrate is the same as the configuration of the processing target substrate. The substrate processing apparatus 100L is a single-wafer type that processes the substrates to be processed one by one. Typically, the substrate to be processed has a substantially disk shape. The configuration of the substrate processing apparatus 100L is the same as the configuration of the substrate processing apparatus 100. The substrate processing device 100L may be the same as the substrate processing device 100. For example, the same substrate processing apparatus may process the learning target substrate in the past, and then process the processing target substrate. Alternatively, the substrate processing apparatus 100L may be another product having the same configuration as the substrate processing apparatus 100.

In the following description of the present specification, the learning target substrate may be described as "learning target substrate WL", and the processing target substrate may be described as "processing target substrate Wp". When it is not necessary to distinguish between the learning target substrate WL and the processing target substrate Wp, the learning target substrate WL and the processing target substrate Wp may be described as "board W".

The substrate W includes, for example, a semiconductor wafer, a substrate for a liquid crystal display device, a substrate for a plasma display, a substrate for a field emission display (FED), a substrate for an optical disk, a substrate for a magnetic disk, a substrate for a magneto-optical disk, and a photomask. Substrates, ceramic substrates, or solar cell substrates.

The board processing device 100L outputs time series data TDL. The time-series data TDL is data showing the time change of the physical quantity in the substrate processing apparatus 100L. The time series data TDL shows the time change of the physical quantity (value) changed in time series over a predetermined period. For example, the time-series data TDL is data indicating the time change of the physical quantity for the processing performed on the learning target substrate by the substrate processing apparatus 100L. Alternatively, the time-series data TDL is data indicating a time change of a physical quantity regarding the characteristics of the learning target substrate processed by the substrate processing apparatus 100L.

The value shown in the time series data TDL may be a value directly measured by the measuring device. Alternatively, the value shown in the time series data TDL may be a value obtained by arithmetically processing a value directly measured by the measuring device. Alternatively, the value shown in the time series data TDL may be a calculation of the value measured by a plurality of measuring instruments.

The learning data generation device 300 generates the learning data LD based on at least a part of the time series data TDL or the time series data TDL. The learning data generation device 300 outputs the learning data LD. The learning data LD includes the board information of the learning target board WL, the static elimination processing condition information indicating the processing conditions of the static elimination processing performed on the learning target board WL, and the static elimination processing performed on the learning target board WL. Includes processing result information indicating the result of. Further, the substrate information of the learning target substrate WL includes the charging distribution information indicating the charging distribution of the learning target substrate WL measured before the learning target substrate WL is subjected to the static elimination processing.

The learning device 400 generates a trained model LM by machine learning the learning data LD. The learning device 400 outputs the trained model LM.

The board processing apparatus 100 outputs the time series data TD. The time-series data TD is data indicating a time change of a physical quantity in the substrate processing apparatus 100. The time series data TD shows the time change of the physical quantity (value) changed in time series over a predetermined period. For example, the time-series data TD is data indicating the time change of the physical quantity of the processing performed on the processing target substrate by the substrate processing apparatus 100. Alternatively, the time-series data TD is data indicating a time change of a physical quantity regarding the characteristics of the substrate to be processed processed by the substrate processing apparatus 100.

The value shown in the time series data TD may be a value directly measured by the measuring device. Alternatively, the value shown in the time series data TD may be a value obtained by arithmetically processing a value directly measured by the measuring device. Alternatively, the value shown in the time series data TD may be a calculation of the value measured by a plurality of measuring instruments.

The object used by the substrate processing apparatus 100 corresponds to the object used by the substrate processing apparatus 100L. Therefore, the configuration of the object used by the substrate processing apparatus 100 is the same as the configuration of the object used by the substrate processing apparatus 100L. Further, in the time series data TD, the physical quantity of the object used by the substrate processing apparatus 100 corresponds to the physical quantity of the object used by the substrate processing apparatus 100L. Therefore, the physical quantity of the object used by the substrate processing apparatus 100L is the same as the physical quantity of the object used by the substrate processing apparatus 100.

From the time series data TD, the board information Cp of the process target board Wp is generated. The substrate information Cp of the processing target substrate Wp corresponds to the substrate information of the learning target substrate WL. The substrate information Cp of the processing target substrate Wp includes charge distribution information indicating the charging distribution of the processing target substrate Wp measured before the processing target substrate Wp is statically eliminated.

From the trained model LM, the static elimination processing condition information Rp indicating the static elimination processing conditions suitable for the processing target substrate Wp in the substrate processing apparatus 100 is output based on the substrate information Cp of the processing target substrate Wp.

As described above with reference to FIG. 1, according to the present embodiment, the learning device 400 performs machine learning. Therefore, it is possible to generate a highly accurate trained model LM from time-series data TDL, which is extremely complicated and has a huge number of analysis targets. Further, the substrate information Cp including the charge distribution information from the time series data TD is input to the trained model LM, and the static elimination processing condition information Rp indicating the static elimination processing condition is output from the trained model LM. Therefore, static elimination processing can be performed according to the processing target substrate Wp.

Next, the substrate processing system 10 including the substrate processing apparatus 100 of the present embodiment will be described with reference to FIG. FIG. 2 is a schematic plan view of the substrate processing system 10.

The substrate processing system 10 processes the substrate W. The substrate processing system 10 includes a plurality of substrate processing devices 100. The substrate processing apparatus 100 processes the substrate W so as to perform at least one of etching, surface treatment, character imparting, treatment film formation, removal of at least a part of the film, and cleaning of the substrate W.

As shown in FIG. 2, in addition to the plurality of substrate processing devices 100, the substrate processing system 10 includes a fluid cabinet 32, a fluid box 34, a plurality of load port LPs, an indexer robot IR, and a center robot CR. , The control device 20 is provided. The control device 20 controls the load port LP, the indexer robot IR, and the center robot CR.

Each of the load port LPs accommodates a plurality of substrates W in a laminated manner. The indexer robot IR conveys the substrate W between the load port LP and the center robot CR. An installation table (path) on which the substrate W is temporarily placed is provided between the indexer robot IR and the center robot CR, and an installation table (path) is provided between the indexer robot IR and the center robot CR via the installation table. The device configuration may be such that the substrate W is indirectly delivered. The center robot CR conveys the substrate W between the indexer robot IR and the substrate processing apparatus 100. Each of the substrate processing devices 100 discharges a liquid onto the substrate W to process the substrate W. Liquids include static eliminators, chemicals and / or rinses. Alternatively, the liquid may contain other treatment liquids. The fluid cabinet 32 houses the liquid. The fluid cabinet 32 may contain gas.

Specifically, the plurality of substrate processing devices 100 form a plurality of tower TWs (four tower TWs in FIG. 2) arranged so as to surround the center robot CR in a plan view. Each tower TW includes a plurality of substrate processing devices 100 (three substrate processing devices 100 in FIG. 1) stacked one above the other. Each of the fluid boxes 34 corresponds to a plurality of tower TWs. The liquid in the fluid cabinet 32 is supplied to all the substrate processing devices 100 included in the tower TW corresponding to the fluid box 34 via one of the fluid boxes 34. Further, the gas in the fluid cabinet 32 is supplied to all the substrate processing devices 100 included in the tower TW corresponding to the fluid box 34 via any of the fluid boxes 34.

The control device 20 controls various operations of the substrate processing system 10. The control device 20 includes a control unit 22 and a storage unit 24. The control unit 22 has a processor. The control unit 22 has, for example, a central processing unit (CPU). Alternatively, the control unit 22 may have a general-purpose arithmetic unit.

The storage unit 24 stores data and computer programs. The data includes recipe data. The recipe data includes information indicating a plurality of recipes. Each of the plurality of recipes defines the processing content and processing procedure of the substrate W.

The storage unit 24 includes a main storage device and an auxiliary storage device. The main storage device is, for example, a semiconductor memory. Auxiliary storage is, for example, a semiconductor memory and / or a hard disk drive. The storage unit 24 may include removable media. The control unit 22 executes the computer program stored in the storage unit 24 to execute the board processing operation.

Although FIG. 2 shows that the substrate processing system 10 is provided with one control device 20, each substrate processing device 100 may be provided with a control device 20. However, in that case, it is preferable that the board processing system 10 includes a plurality of board processing devices 100 and another control device that controls devices other than the board processing device 100.

A computer program for which a procedure has been determined in advance is stored in the storage unit 24. The substrate processing apparatus 100 operates according to a procedure defined in a computer program.

Next, the substrate processing apparatus 100 of this embodiment will be described with reference to FIG. FIG. 3 is a schematic view of the substrate processing apparatus 100 of the present embodiment. Although the configuration of the substrate processing device 100 will be described here, the substrate processing device 100L also has the same configuration as the substrate processing device 100.

The substrate processing apparatus 100 processes the substrate W. The substrate processing device 100 includes a chamber 110, a substrate holding unit 120, a charge distribution measuring unit 130, a static elimination unit 140, a chemical solution supply unit 150, and a rinse solution supply unit 160. The chamber 110 houses the substrate W. The substrate holding unit 120 holds the substrate W. The substrate holding unit 120 rotatably holds the substrate W. The charge distribution measuring unit 130 measures the distribution of the amount of charge charged on the substrate W or the potential distribution of the upper surface Wa of the substrate W. The static elimination unit 140 eliminates static electricity from the substrate W. In FIG. 3, the static elimination unit 140 supplies a static elimination liquid to the substrate W to eliminate static electricity on the substrate W.

The chamber 110 has a substantially box shape having an internal space. The chamber 110 houses the substrate W. Here, the substrate processing apparatus 100 is a single-wafer type that processes the substrate W one by one, and the chamber 110 accommodates the substrate W one by one. The substrate W is housed in the chamber 110 and processed in the chamber 110. The chamber 110 houses at least a part of each of the substrate holding unit 120, the charge distribution measuring unit 130, the static elimination unit 140, the chemical solution supply unit 150, and the rinse solution supply unit 160.

The substrate holding unit 120 holds the substrate W. The substrate holding portion 120 holds the substrate W horizontally so that the upper surface Wa of the substrate W faces upward and the back surface (lower surface) Wb of the substrate W faces vertically downward. Further, the substrate holding unit 120 rotates the substrate W while holding the substrate W.

For example, the substrate holding portion 120 may be a sandwiching type that sandwiches an end portion of the substrate W. Alternatively, the substrate holding unit 120 may have an arbitrary mechanism for holding the substrate W from the back surface Wb. For example, the substrate holding portion 120 may be of a vacuum type. In this case, the substrate holding portion 120 holds the substrate W horizontally by adsorbing the central portion of the back surface Wb of the substrate W, which is a non-device forming surface, to the upper surface. Alternatively, the substrate holding portion 120 may combine a holding type and a vacuum type in which a plurality of chuck pins are brought into contact with the peripheral end surface of the substrate W.

For example, the substrate holding portion 120 includes a spin base 121, a chuck member 122, a shaft 123, and an electric motor 124. The chuck member 122 is provided on the spin base 121. The chuck member 122 chucks the substrate W. Typically, the spin base 121 is provided with a plurality of chuck members 122.

The shaft 123 is a hollow shaft. The shaft 123 extends in the vertical direction along the rotation axis Ax. A spin base 121 is coupled to the upper end of the shaft 123. The back surface of the substrate W is in contact with the spin base 121, and the substrate W is placed above the spin base 121.

The spin base 121 has a disk shape and horizontally supports the substrate W. The shaft 123 extends downward from the central portion of the spin base 121. The electric motor 124 applies a rotational force to the shaft 123. The electric motor 124 rotates the substrate W and the spin base 121 around the rotation shaft Ax by rotating the shaft 123 in the rotation direction. Here, the direction of rotation is counterclockwise.

The charge distribution measuring unit 130 measures the charge distribution of the substrate W. The charge distribution measuring unit 130 measures the amount of charge on the surface of the substrate W. For example, the charge distribution measuring unit 130 includes a non-contact type surface electrometer. The charge distribution measuring unit 130 may be a vibration capacitance type electrometer.

The static elimination unit 140 eliminates static electricity from the substrate. Here, the static elimination unit 140 supplies the static elimination liquid to the substrate W. By supplying the static elimination liquid to the substrate W by the static elimination unit 140, it is possible to suppress the generation of electric discharge on the substrate W even when the substrate W is in a charged state.

The static eliminator is preferably a liquid having a relatively low specific resistance. In one example, a liquid having a lower specific resistance than the chemical solution is used as the static elimination liquid.

For example, carbonated water is preferably used as the static eliminator. Alternatively, water may be used as the static elimination liquid. Alternatively, SC1 (ammonia hydrogen peroxide solution mixture), SC2 (hydrochloric acid hydrogen peroxide solution mixture), or the like may be used as the static elimination solution. By using a liquid having a relatively low specific resistance as the static eliminator, the charge on the substrate W can be smoothly removed while suppressing the discharge generated in the substrate W.

The static elimination unit 140 includes a nozzle 142, a pipe 144, and a valve 146. The nozzle 142 faces the upper surface Wa of the substrate W and discharges the static elimination liquid toward the upper surface Wa of the substrate W. The pipe 144 is coupled to the nozzle 142. The nozzle 142 is provided at the tip of the pipe 144. The static elimination liquid is supplied to the pipe 144 from the supply source. The valve 146 is provided in the pipe 144. The valve 146 opens and closes the flow path in the pipe 144.

The static elimination unit 140 further includes a nozzle moving unit 148. The nozzle moving unit 148 moves the nozzle 142 between the discharge position and the retracted position. When the nozzle 142 is in the discharge position, the nozzle 142 is located above the substrate W. When the nozzle 142 is in the discharge position, the nozzle 142 discharges the static elimination liquid toward the upper surface Wa of the substrate W. When the nozzle 142 is in the retracted position, the nozzle 142 is located radially outside the substrate W with respect to the substrate W.

The nozzle moving portion 148 includes an arm 148a, a rotating shaft 148b, and a moving mechanism 148c. The arm 148a extends along a substantially horizontal direction. A nozzle 142 is attached to the tip of the arm 148a. The arm 148a is coupled to the rotation shaft 148b. The rotation shaft 148b extends along a substantially vertical direction. The moving mechanism 148c rotates the rotation shaft 148b around a rotation axis along a substantially vertical direction, and rotates the arm 148a along a substantially horizontal plane. As a result, the nozzle 142 moves along a substantially horizontal plane. For example, the moving mechanism 148c includes an arm swing motor that rotates the rotating shaft 148b around the rotating axis. The arm swing motor is, for example, a servo motor. Further, the moving mechanism 148c raises and lowers the rotation shaft 148b along a substantially vertical direction to raise and lower the arm 148a. As a result, the nozzle 142 moves along a substantially vertical direction. For example, the moving mechanism 148c includes a ball screw mechanism and an arm elevating motor that applies a driving force to the ball screw mechanism. The arm elevating motor is, for example, a servo motor.

The chemical solution supply unit 150 supplies the chemical solution to the substrate W. As a result, the substrate W is treated with the chemical solution.

As the chemical solution, a liquid having a relatively high specific resistance may be used. For example, the chemical solution contains hydrofluoric acid (hydrogen fluoride water: HF). Alternatively, the chemical solution is sulfuric acid, acetic acid, nitric acid, hydrochloric acid, citric acid, buffered fluoric acid (BHF), dilute fluoric acid (DHF), ammonia water, dilute ammonia water, hydrogen peroxide solution, organic alkali (for example, TMAH: It may be a solution containing at least one of a tetramethylammonium hydrochloride, etc.), a surfactant, and a corrosion inhibitor. Further, the chemical solution may be a mixed solution in which the above solutions are mixed. For example, examples of the chemical solution in which these are mixed include SPM (mixed solution of hydrogen sulfate solution), SC1 (mixed solution of aqueous ammonia hydrogen peroxide solution), SC2 (mixed solution of mixed solution of hydrochloric acid hydrogen peroxide solution) and the like.

The chemical supply unit 150 includes a nozzle 152, a pipe 154, and a valve 156. The nozzle 152 faces the upper surface Wa of the substrate W and discharges the chemical solution toward the upper surface Wa of the substrate W. The pipe 154 is coupled to the nozzle 152. The nozzle 152 is provided at the tip of the pipe 154. The chemical solution is supplied to the pipe 154 from the supply source. The valve 156 is provided in the pipe 154. The valve 156 opens and closes the flow path in the pipe 154.

The rinse liquid supply unit 160 supplies the rinse liquid to the substrate W. The rinse liquid supplied from the rinse liquid supply unit 160 is deionized water (DIW), carbonated water, electrolytic ionized water, ozone water, ammonia water, hydrochloric acid water having a diluted concentration (for example, about 10 ppm to 100 ppm). Alternatively, it may contain any of reduced water (hydrogen water).

The rinse liquid supply unit 160 includes a nozzle 162, a pipe 164, and a valve 166. The nozzle 162 faces the upper surface Wa of the substrate W and discharges the rinse liquid toward the upper surface Wa of the substrate W. The pipe 164 is coupled to the nozzle 162. The nozzle 162 is provided at the tip of the pipe 164. Rinse liquid is supplied to the pipe 164 from the supply source. The valve 166 is provided in the pipe 164. The valve 166 opens and closes the flow path in the pipe 164.

The substrate processing apparatus 100 further includes a cup 180. The cup 180 collects the liquid scattered from the substrate W. The cup 180 can rise vertically upward to the side of the substrate W. Further, the cup 180 may descend vertically downward from the side of the substrate W.

The control device 20 controls various operations of the substrate processing device 100. The control unit 22 controls the substrate holding unit 120, the charge distribution measuring unit 130, the static elimination unit 140, the chemical solution supply unit 150, the rinsing solution supply unit 160 and / or the cup 180. In one example, the control unit 22 controls the electric motor 124, valves 146, 156, 166, moving mechanism 148c and / or cup 180.

In the substrate processing apparatus 100 of the present embodiment, the substrate W can be subjected to static elimination treatment, chemical solution treatment, and rinsing treatment.

Next, the substrate processing apparatus 100 of the present embodiment will be described with reference to FIGS. 1 to 4. FIG. 4 is a block diagram of the substrate processing system 10 including the substrate processing apparatus 100.

As shown in FIG. 4, the control device 20 controls various operations of the substrate processing system 10. The control device 20 controls the indexer robot IR, the center robot CR, the substrate holding unit 120, the charge distribution measuring unit 130, the static elimination unit 140, the chemical solution supply unit 150, the rinse solution supply unit 160, and the cup 180. Specifically, the control device 20 sends control signals to the indexer robot IR, the center robot CR, the substrate holding unit 120, the charge distribution measuring unit 130, the static elimination unit 140, the chemical liquid supply unit 150, the rinse liquid supply unit 160, and the cup 180. The indexer robot IR, the center robot CR, the substrate holding unit 120, the charge distribution measuring unit 130, the static elimination unit 140, the chemical liquid supply unit 150, the rinsing liquid supply unit 160, and the cup 180 are controlled by transmitting.

Specifically, the control unit 22 controls the indexer robot IR and delivers the substrate W by the indexer robot IR.

The control unit 22 controls the center robot CR and delivers the substrate W by the center robot CR. For example, the center robot CR receives the unprocessed substrate W and carries the substrate W into one of the plurality of chambers 110. Further, the center robot CR receives the processed substrate W from the chamber 110 and carries out the substrate W.

The control unit 22 controls the substrate holding unit 120 to control the start of rotation of the substrate W, the change of the rotation speed, and the stop of the rotation of the substrate W. For example, the control unit 22 can control the substrate holding unit 120 to change the rotation speed of the substrate holding unit 120. Specifically, the control unit 22 can change the rotation speed of the substrate W by changing the rotation speed of the electric motor 124 of the substrate holding unit 120.

The control unit 22 controls the charge distribution measurement unit 130 to measure the charge distribution of the substrate W.

The control unit 22 controls the valve 146 of the static elimination unit 140, the valve 156 of the chemical solution supply unit 150, and the valve 166 of the rinse solution supply unit 160 to change the state of the valves 146, 156, and 166 into an open state and a closed state. You can switch. Specifically, the control unit 22 controls the valves 146, 156, and 166 to open the valves 146, 156, and 166, so that the pipes 144, 154, and 164 are directed toward the nozzles 142, 152, and 162. It is possible to pass the static eliminator, the chemical solution, and the rinse solution that flow inside. Further, the control unit 22 controls the valve 146 of the static elimination unit 140, the valve 156 of the chemical liquid supply unit 150, and the valve 166 of the rinse liquid supply unit 160 to close the valves 146, 156, and 166, thereby closing the nozzle. The static elimination liquid, the chemical liquid, and the rinsing liquid flowing in the pipes 144, 154, and 164 toward 142, 152, and 162 can be stopped.

Further, the control unit 22 controls the moving mechanism 148c to move the arm 148a in the horizontal direction and / or the vertical direction. As a result, the control unit 22 can move the nozzle 142 attached to the tip of the arm 148a on the upper surface Wa of the substrate W. Further, the control unit 22 can move the nozzle 142 attached to the tip of the arm 148a between the discharge position and the retracted position. The substrate processing device 100 of this embodiment is suitably used for forming a semiconductor device.

In the substrate processing apparatus 100 of the present embodiment, the storage unit 24 stores the learned model LM and the control program PG. The substrate processing apparatus 100 operates according to the procedure defined in the control program PG.

Further, the control unit 22 includes a substrate information acquisition unit 22a and a static elimination processing condition information acquisition unit 22b. The substrate information acquisition unit 22a acquires the substrate information of the processing target substrate Wp from the charge distribution measurement unit 130. The substrate information includes charge distribution information. The substrate information acquisition unit 22a may acquire information other than the charge distribution information as the substrate information from the storage unit 24.

The trained model LM generates static elimination processing condition information based on the substrate information. Typically, when the board information is input to the trained model LM, the static elimination processing condition information corresponding to the board information is output. In one example, when the charge distribution information is input to the trained model LM, the static elimination processing condition information corresponding to the charge distribution information is output.

The static elimination processing condition information acquisition unit 22b acquires static elimination processing condition information from the trained model LM. The static elimination processing condition information acquisition unit 22b acquires static elimination processing condition information corresponding to the substrate information of the processing target substrate Wp from the trained model LM.

The control unit 22 controls the substrate holding unit 120 and the static elimination unit 140 according to the static elimination processing conditions shown in the static elimination processing condition information.

The substrate processing system 10 preferably further includes a display unit 42, an input unit 44, and a communication unit 46.

The display unit 42 displays an image. The display unit 42 is, for example, a liquid crystal display or an organic electroluminescence display.

The input unit 44 is an input device for inputting various information to the control unit 22. For example, the input unit 44 is a keyboard and a pointing device, or a touch panel.

The communication unit 46 is connected to the network and communicates with an external device. In this embodiment, the network includes, for example, the Internet, a LAN (Local Area Network), a public switched telephone network, and a short-range wireless network. The communication unit 46 is a communication device, for example, a network interface controller.

Further, the substrate processing system 10 preferably further includes a sensor 50. Typically, a plurality of sensors 50 detect the state of each part of the substrate processing system 10. For example, at least a part of the sensor 50 detects the state of each part of the substrate processing apparatus 100.

The storage unit 24 stores the output result from the sensor 50 and the control parameters by the control program as time series data. Typically, the time series data is stored separately for each substrate W.

The sensor 50 detects the physical quantity of the object used by the substrate processing apparatus 100 in the period from the start of the processing of the substrate W to the end of the processing for each processing of one substrate W, and controls a detection signal indicating the physical quantity. Output to 22. Then, the control unit 22 associates the physical quantity indicated by the detection signal output from the sensor 50 in the period from the start of the processing of the substrate W to the end of the processing with the time for each processing of one substrate W and time-series data. It is stored in the storage unit 24 as a TD.

The control unit 22 acquires the time-series data TD from the sensor 50 and stores the time-series data TD in the storage unit 24. In this case, the control unit 22 stores the time-series data TD in the storage unit 24 in association with the lot identification information, the board identification information, the processing order information, and the lot interval information. The lot identification information is information for identifying a lot (for example, a lot number). Lot indicates the processing unit of the substrate W. One lot is composed of a predetermined number of substrates W. The board identification information is information for identifying the board W. The processing order information is information indicating the processing order for a predetermined number of substrates W constituting one lot. The lot interval information is information indicating a time interval from the end of processing for a lot to the start of processing for the next lot.

Next, a substrate processing method by the substrate processing apparatus 100 of the present embodiment will be described with reference to FIGS. 1 to 5. FIG. 5A is a flow chart of a substrate processing method in the substrate processing apparatus 100 of the present embodiment, and FIG. 5B is a flow chart of static elimination processing in the substrate processing method of the present embodiment.

As shown in FIG. 5A, in step S10, the processing target substrate Wp is carried into the substrate processing apparatus 100. The carried-in processing target substrate Wp is mounted on the substrate holding portion 120. Typically, the processing target substrate Wp is carried into the substrate processing apparatus 100 by the center robot CR.

In step S20, the substrate Wp to be processed is statically eliminated. The static elimination unit 140 eliminates static electricity from the substrate Wp to be processed. Specifically, the static elimination liquid is discharged from the nozzle 142 of the static elimination unit 140 to the upper surface Wa of the processing target substrate Wp. The static eliminator covers the upper surface Wa of the substrate Wp to be processed. As a result, the substrate W is statically eliminated with the static elimination liquid. When the substrate Wp to be processed is statically eliminated, the substrate W is rotated by the substrate holding unit 120. The rotation of the processing target substrate Wp may be continued until immediately before the processing target substrate Wp is carried out.

In step S30, the substrate Wp to be processed is treated with a chemical solution. The chemical solution supply unit 150 supplies the chemical solution to the substrate Wp to be processed. The chemical solution is discharged from the nozzle 152 of the chemical solution supply unit 150 to the upper surface Wa of the substrate Wp to be processed. The chemical solution covers the upper surface Wa of the substrate Wp to be treated. As a result, the substrate Wp to be processed is treated with the chemical solution.

In step S40, the substrate Wp to be processed is rinsed with a rinsing liquid. The rinse liquid supply unit 160 supplies the rinse liquid to the substrate Wp to be processed. The rinse liquid is discharged from the nozzle 162 of the rinse liquid supply unit 160 to the upper surface Wa of the substrate Wp to be processed. The rinse liquid covers the upper surface Wa of the substrate Wp to be processed. As a result, the substrate Wp to be processed is treated with the rinsing liquid.

In step S50, the processing target substrate Wp is separated from the substrate holding unit 120 and the processing target substrate Wp is carried out. Typically, the processing target substrate Wp is carried out from the substrate processing apparatus 100 by the center robot CR. As described above, the substrate Wp to be processed can be subjected to static elimination treatment and chemical solution treatment. The specific resistance of the chemical solution used for the chemical solution treatment may be relatively high. In this case, it is preferable to perform the static elimination treatment before the chemical treatment. As a result, even when the processing target substrate Wp is charged and carried in, it is possible to suppress the generation of electric discharge in the processing target substrate Wp in the chemical treatment. However, the substrate W may be charged by the chemical treatment. In this case, the static elimination treatment may be performed after the chemical treatment.

In the substrate processing apparatus 100 of the present embodiment, as shown in FIG. 5B, the substrate Wp to be processed is statically eliminated.

In step S22, the board information of the process target board Wp is acquired. The board information acquisition unit 22a acquires the board information of the process target board Wp. The substrate information includes charge distribution information indicating the charge distribution of the substrate Wp to be processed. For example, the control unit 22 controls the charge distribution measurement unit 130, so that the charge distribution measurement unit 130 measures the charge distribution of the substrate Wp to be processed. The control unit 22 may acquire substrate information other than charge distribution information. For example, the control unit 22 may acquire the board information of the processing target board Wp from the storage unit 24.

In step S24, the board information of the process target board Wp is input to the trained model LM. Although the details will be described later, the trained model LM has the substrate information of the learning target substrate WL, the static elimination processing condition information indicating the processing conditions of the static elimination processing performed on the learning target substrate WL, and the learning target substrate WL. It is constructed from learning data including processing result information indicating the result of the static elimination processing performed. The trained model LM outputs the static elimination processing condition information Rp corresponding to the board information of the processing target board Wp.

In step S26, the static elimination processing condition information is acquired from the trained model LM. The static elimination processing condition information acquisition unit 22b acquires static elimination processing condition information corresponding to the board information from the learned model LM.

In step S28, the substrate holding unit 120 and the static elimination unit 140 execute the static elimination processing of the processing target substrate Wp according to the static elimination processing condition information. In the substrate processing apparatus 100 shown in FIG. 3, the static elimination unit 140 supplies the static elimination liquid to the processing target substrate Wp according to the static elimination processing condition information. As described above, the substrate Wp to be processed can be statically eliminated.

According to the present embodiment, static elimination processing condition information corresponding to the substrate information including the charge distribution information of the processing target substrate Wp is acquired from the trained model LM constructed by machine learning, and is shown in the static elimination processing condition information. The static elimination process is executed according to the static elimination process conditions. The charge distribution of the substrate Wp to be processed varies greatly depending on the characteristics of the substrate Wp to be processed and a slight difference in the treatment before static elimination. However, according to the present embodiment, the charge distribution of the substrate Wp to be processed varies depending on the charge state of the substrate Wp to be processed. The static elimination process can be executed properly.

Next, the charged state of the substrate W in the substrate processing method of the present embodiment will be described with reference to FIG. FIG. 6 is a schematic view showing the charge distribution of the substrate W. FIG. 6A shows the charge distribution of the substrate measured by the charge distribution measuring unit 130. Here, the potential of the substrate W is divided into eight stages and shown for each region.

In the substrate W, the region R1 indicates the region having the lowest potential in the substrate W, and the region R2 indicates the region having the lowest potential next to the region R1 in the substrate W. Regions R3 to R7 indicate regions having lower potentials in order in the substrate W. The region R8 indicates the region having the highest potential in the substrate W.

In FIG. 6, the region having the lowest potential of the substrate W is located at the upper end portion of the substrate W and from the center to the left side of the substrate W. In FIG. 6, the potential of the substrate W tends to be low on the upper side and high on the lower side. However, the charge distribution of the substrate W shown in FIG. 6 is merely an example, and the charge distribution of the substrate W varies greatly depending on the type and thickness of the substrate W and the slight difference in the treatment prior to the substrate W.

Next, the static elimination treatment in the substrate processing method of the present embodiment will be described with reference to FIGS. 1 to 7. 7 (a) to 7 (d) are schematic views of the static elimination process in the substrate processing method of the present embodiment.

As shown in FIG. 7A, the potential of the substrate Wp to be processed differs depending on the position. FIG. 7A shows the distribution of the charge Q for each position on the processing target substrate Wp. In FIG. 7A, it is shown that the larger the charge Q is, the larger the charge amount is at the position of the processing target substrate Wp, and the smaller the charge Q is, the smaller the charge amount is at the position of the processing target substrate Wp. ing. In FIG. 7A, there is a region where the potential is relatively high at the left end and the center of the substrate Wp to be processed, while the potential is relatively low at the right end of the substrate Wp to be processed. The charge distribution measuring unit 130 measures the charge distribution of the substrate Wp to be processed.

As shown in FIG. 7B, static elimination of the processing target substrate Wp is started. The static elimination unit 140 discharges the static elimination liquid to a region of the processing target substrate Wp where the potential is relatively low. Here, the nozzle 142 of the static elimination unit 140 is located above the right end of the processing target substrate Wp, and the static elimination liquid is discharged to the right end of the processing target substrate Wp. In the region of the processing target substrate Wp where the discharge of the static elimination liquid is started, if the potential of the processing target substrate Wp is high, discharge may occur, but if the potential is low, the generation of discharge can be suppressed.

After that, as shown in FIG. 7C, the nozzle 142 of the static elimination unit 140 is scanned against the processing target substrate Wp. Here, the region of the processing target substrate Wp where the static elimination liquid is discharged from the nozzle 142 of the static elimination unit 140 is scanned so as to be directed from the end portion of the processing target substrate Wp toward the center. In this way, the nozzle 142 of the static elimination unit 140 is scanned against the processing target substrate Wp. The static elimination liquid removes the charge on the substrate Wp to be processed.

As shown in FIG. 7D, by performing the static elimination treatment on the processing target substrate Wp, the electric charge Q of the processing target substrate Wp can be removed, and the charge amount of the processing target substrate Wp can be reduced. By eliminating static electricity from the processing target substrate Wp as described above, it is possible to suppress the generation of electric discharge in the processing target substrate Wp.

In the description with reference to FIGS. 6 and 7, the potential of the substrate W is positive with respect to the ground, and the supply of the static elimination liquid is started in the region of the substrate W where the potential is low. However, when the substrate W has a negative charge with respect to the ground, the static elimination liquid is started to be supplied to the region of the substrate W where the potential is farthest from the ground.

As described above with reference to FIG. 1, the trained model LM is generated from the training data LD, and the learning data LD is generated from the time series data TDL of the substrate processing apparatus 100L.

Next, the generation of the learning data LD will be described with reference to FIG. FIG. 8 is a block diagram of a substrate processing system 10L provided with a substrate processing apparatus 100L and a learning data generation apparatus 300. Here, the learning data generation device 300 is communicably connected to the substrate processing device 100L. In the board processing system 10L provided with the board processing device 100L of FIG. 8, the control unit 22L does not have the board information acquisition unit 22a and the static elimination processing condition information acquisition unit 22b, and the storage unit 24L stores the learned model LM. It is the same as the block diagram of the substrate processing system 10 shown in FIG. 4, except that the test recipe TR is stored without the above, and duplicate description is omitted in order to avoid duplication.

The board processing system 10L includes a plurality of board processing devices 100L, an indexer robot IRL, a center robot CRL, a control device 20L, a display unit 42L, an input unit 44L, a communication unit 46L, and a sensor 50L. The board processing device 100L, the indexer robot IRL, the center robot CRL, the control device 20L, the display unit 42L, the input unit 44L, and the communication unit 46L are the board processing device 100 and the indexer robot IR of the board processing system 10 shown in FIG. , Center robot CR, control device 20, display unit 42, input unit 44, and communication unit 46.

The substrate processing device 100L includes a substrate holding unit 120L, a charge distribution measuring unit 130L, a static elimination unit 140L, a chemical solution supply unit 150L, a rinsing solution supply unit 160L, and a cup 180L. The chamber 110L, the substrate holding unit 120L, the charge distribution measuring unit 130L, the static elimination unit 140L, the chemical solution supply unit 150L, the rinsing solution supply unit 160L and the cup 180L are the substrate holding unit 120 and the charging distribution measuring unit shown in FIGS. 3 and 4. It is preferable to have the same configurations as 130, the static elimination unit 140, the chemical solution supply unit 150, the rinse solution supply unit 160, and the cup 180.

The control device 20L has a control unit 22L and a storage unit 24L. The storage unit 24L stores the control program PGL. The substrate processing apparatus 100L operates according to the procedure specified in the control program PGL.

Further, the storage unit 24L stores a plurality of test recipes TR. The plurality of test recipes TR include recipes having different static elimination processing conditions. Therefore, when the control unit 22L processes the learning target substrate WL according to the test recipe TR, different static elimination processing is performed on the different learning target substrate WL.

The storage unit 24L stores the time-series data TDL of the learning target substrate WL. The time-series data TDL is data showing the time change of the physical quantity in the substrate processing apparatus 100L. The time series data TDL shows a plurality of physical quantities detected by the sensor 50L. The time-series data TDL includes charge distribution information of the learning target substrate WL measured by the charge distribution measuring unit 130L, static elimination processing condition information indicating the conditions for static elimination processing of the learning target substrate WL, and static elimination processing of the learning target substrate WL. Contains processing result information that indicates the result.

The learning data generation device 300 is communicably connected to the substrate processing device 100L. The learning data generation device 300 communicates at least a part of the time series data of the board processing device 100L.

The learning data generation device 300 includes a control device 320, a display unit 342, an input unit 344, and a communication unit 346. The learning data generation device 300 can communicate with the control device 20L of the plurality of board processing devices 100L via the communication unit 346. The display unit 342, the input unit 344, and the communication unit 346 have the same configurations as the display unit 42, the input unit 44, and the communication unit 46.

The control device 320 includes a control unit 322 and a storage unit 324. The storage unit 324 stores the control program PG3. The learning data generation device 300 operates according to the procedure defined in the control program PG3.

The control unit 322 receives at least a part of the time series data TDL from the substrate processing device 100L, and stores the received time series data TDL in the storage unit 324. The storage unit 324 stores at least a part of the time series data TDL of the learning target substrate WL. The time-series data TDL is transmitted from the substrate processing device 100L to the learning data generation device 300 via the communication unit 46L and the communication unit 346. The control unit 322 stores at least a part of the transmitted time series data TDL in the storage unit 324. The time-series data TDL stored in the storage unit 324 includes board information, static elimination processing condition information, and processing result information of the time-series data TDL.

The control unit 322 acquires the substrate information including the charge distribution information of the learning target substrate WL, the static elimination processing condition information, and the processing result information from the time series data TDL of the storage unit 324. Further, the control unit 322 collectively generates the learning data LD by collecting the board information, the static elimination processing condition information, and the processing result information of the learning target board WL, and the storage unit 324 stores the learning data LD.

Next, a method of generating learning data of the present embodiment will be described with reference to FIGS. 8 and 9. FIG. 9 is a flow chart of a method for generating learning data according to the present embodiment. The learning data is generated in the learning data generation device 300.

As shown in FIG. 9, in step S110, the time series data TDL of the learning target substrate WL is acquired. Typically, the learning data generation device 300 receives at least a part of the time series data TDL of the learning target board WL from the board processing device 100L. The storage unit 324 stores the received time series data TDL.

In step S112, the board information is extracted from the time series data TDL of the learning target board WL stored in the storage unit 324. The substrate information includes charge distribution information of the learning target substrate WL. The control unit 322 acquires the board information of the learning target board WL from the time series data TDL of the storage unit 324.

In step S114, the static elimination processing condition information of the learning target substrate WL is extracted from the time series data TDL of the learning target substrate WL stored in the storage unit 324. The control unit 322 acquires the static elimination processing condition information of the learning target substrate WL from the time series data TDL of the storage unit 324.

In step S116, the processing result information of the learning target substrate WL is extracted from the time series data TDL of the learning target substrate WL stored in the storage unit 324. The control unit 322 acquires the processing result information of the learning target board WL from the time series data TDL of the storage unit 324.

In step S118, the board information of the learning target board WL, the static elimination processing condition information, and the processing result information are associated and generated as the learning data LD, and the storage unit 324 stores the learning data LD for each of the plurality of learning target board WLs. do.

In the present embodiment, the generated learning data includes board information, static elimination processing condition information, and processing result information associated with each other for each learning target board WL. Such learning data is suitably used for learning processing.

In FIG. 8, the learning data generation device 300 is communicably connected to one substrate processing device 100L, but the present embodiment is not limited to this. The learning data generation device 300 may be communicably connected to a plurality of board processing devices 100L.

Further, in the description with reference to FIGS. 8 and 9, the time-series data TDL generated by the board processing device 100L was transmitted to the learning data generation device 300 via the communication unit 46L and the communication unit 346. The form is not limited to this. The control device 320 of the learning data generation device 300 is incorporated in the control device 20 of the board processing system 10 including the board processing device 100L, and the time series data TDL is not transferred to the network in the board processing system 10. The learning data LD may be generated from the time series data TDL.

Next, the generation of the trained model LM of the present embodiment will be described with reference to FIG. FIG. 10 is a schematic diagram of the learning data generation device 300 and the learning device 400 of the present embodiment. The learning data generation device 300 and the learning device 400 can communicate with each other.

The learning device 400 is communicably connected to the learning data generation device 300. The learning device 400 receives the learning data LD from the learning data generation device 300. The learning device 400 performs machine learning based on the learning data LD and generates a trained model LM.

The learning device 400 includes a control device 420, a display unit 442, an input unit 444, and a communication unit 446. The display unit 442, the input unit 444, and the communication unit 446 have the same configurations as the display unit 42, the input unit 44, and the communication unit 46 of the board processing system 10 shown in FIG.

The control device 420 includes a control unit 422 and a storage unit 424. The storage unit 424 stores the control program PG4. The learning device 400 operates according to the procedure defined in the control program PG4.

The storage unit 424 stores the learning data LD. The learning data LD is transmitted from the learning data generation device 300 to the learning device 400 via the communication unit 346 and the communication unit 446. The control unit 422 stores the transmitted learning data LD in the storage unit 424. In the learning data LD stored in the storage unit 424, the board information, the static elimination processing condition information, and the processing result information of the time series data TDL are associated with each other.

The storage unit 424 stores the learning program LPG. The learning program LPG is a program for finding a certain rule from a plurality of learning data LDs and executing a machine learning algorithm for generating a learned model LM expressing the found rule. The control unit 422 generates a trained model LM by adjusting the parameters of the inference program by machine learning the learning data LD by executing the learning program LPG of the storage unit 424.

The machine learning algorithm is not particularly limited as long as it is supervised learning, and is, for example, a decision tree, a nearest neighbor method, a naive Bayes classifier, a support vector machine, or a neural network. Therefore, the trained model LM includes a decision tree, the nearest neighbor method, a naive Bayes classifier, a support vector machine, or a neural network. The error backpropagation method may be used in machine learning to generate the trained model LM.

For example, a neural network includes an input layer, a single or multiple intermediate layers, and an output layer. Specifically, the neural network is a deep neural network (DNN: Deep Neural Network), a recurrent neural network (RNN: Recurrent Neural Network), or a convolutional neural network (CNN: Convolutional Neural Network). conduct. For example, a deep neural network includes an input layer, a plurality of intermediate layers, and an output layer.

The control unit 422 includes an acquisition unit 422a and a learning unit 422b. The acquisition unit 422a acquires the learning data LD from the storage unit 424. The learning unit 422b machine-learns the learning data LD by executing the learning program LPG of the storage unit 424, and generates a learned model LM from the learning data LD.

The learning unit 422b machine-learns a plurality of learning data LDs based on the learning program LPG. As a result, a certain rule is found from the plurality of training data LDs, and the trained model LM is generated. That is, the trained model LM is constructed by machine learning the learning data LD. The storage unit 424 stores the trained model LM.

Typically, the trained model LM is transferred to the control device 20 in the substrate processing system 10, and the storage unit 24 stores the trained model LM. In this case, as described above with reference to FIG. 4, the storage unit 24 of the control device 20 in the board processing system 10 stores the learned model LM, and the static elimination processing condition information acquisition unit 22b learns the storage unit 24. Obtain the static elimination processing conditions from the completed model LM.

However, this embodiment is not limited to this. The storage unit 24 does not store the learned model LM, and the static elimination processing condition information acquisition unit 22b may acquire the static elimination processing conditions from the outside of the substrate processing system 10. For example, the static elimination processing condition information acquisition unit 22b transmits the board information of the processing target board Wp to the learned model LM of the learning device 400 via the communication unit 46 and the communication unit 446, and transmits the board information of the processing target board Wp via the communication unit 446 and the communication unit 46. The static elimination processing condition information output in the trained model LM may be received from the learning device 400.

Next, a learning method and a learning model generation method in the learning device 400 of the present embodiment will be described with reference to FIGS. 1 to 11. FIG. 11 is a flow chart of the learning method and the learned model of the present embodiment. The learning of the learning data LD and the generation of the trained model LM are performed in the learning device 400.

As shown in FIG. 11, in step S122, the acquisition unit 422a of the learning device 400 acquires a plurality of learning data LDs from the storage unit 424. In the learning data LD, the board information, the static elimination processing condition information, and the processing result information of the time series data TDL are associated with each other.

Next, in step S124, the learning unit 422b machine-learns a plurality of learning data LDs based on the learning program LPG.

Next, in step S126, the learning unit 422b determines whether or not the machine learning of the learning data LD is completed. Whether or not to end machine learning is determined according to predetermined conditions. For example, machine learning ends when a predetermined number or more of learning data LDs are machine-learned.

If the machine learning is not completed (No in step S126), the process returns to step S122. In that case, machine learning is repeated. On the other hand, if the machine learning is not completed (Yes in step S126), the process proceeds to step S128.

In step S128, the learning unit 422b outputs a model (one or more functions) to which the latest plurality of parameters (coefficients), that is, a plurality of learned parameters (coefficients) are applied, as a trained model LM. The storage unit 424 stores the trained model LM.

As described above, the learning method is completed, and the trained model LM is generated. According to this embodiment, the trained model LM can be generated by machine learning the learning data LD.

In FIG. 10, the learning device 400 is communicably connected to one learning data generation device 300, but the present embodiment is not limited to this. The learning device 400 may be communicably connected to a plurality of learning data generation devices 300.

Further, in the description with reference to FIGS. 10 and 11, the learning data LD generated by the learning data generation device 300 is transmitted to the learning device 400 via the communication unit 346 and the communication unit 446. Is not limited to this. The control device 420 of the learning device 400 is incorporated in the control device 320 of the learning data generation device 300, and the learning data LD is not transferred to the network, and the learning data is stored in the learning data generation device 300. A trained model LM may be generated from the LD.

Further, in the description with reference to FIGS. 8 to 11, the time-series data TDL generated by the board processing device 100L is transmitted to the learning data generation device 300 via the communication unit 46L and the communication unit 346 to generate the learning data. The learning data LD generated by the device 300 is transmitted to the learning device 400 via the communication unit 346 and the communication unit 446, but the present embodiment is not limited to this. The control device 320 of the learning data generation device 300 and the control device 420 of the learning device 400 are incorporated in the control device 20 of the board processing system 10L, and the time-series data TDL and the learning data LD are transferred to the network. Instead, the trained model LM may be generated from the time-series data TDL in the substrate processing system 10L via the learning data LD.

Next, an example of the learning data LD will be described with reference to FIG. FIG. 12 is a diagram showing an example of the learning data LD.

FIG. 12 shows the substrate information of the learning target substrate WL, the static elimination processing conditions of the learning target substrate WL, and the static elimination processing result of the learning target substrate WL. Here, the substrate information is charge distribution information indicating the charge distribution of the learning target substrate WL. The charge distribution information is generated by measuring the learning target substrate WL by the charge distribution measuring unit 130L before static elimination processing of the learning target substrate WL. The static elimination processing condition information indicates, for example, the concentration of the static elimination liquid, the temperature of the static elimination liquid, the supply amount of the static elimination liquid, the discharge pattern of the static elimination liquid, and the rotation speed of the learning target substrate WL when supplying the static elimination liquid. The processing result shows the result of the learning target substrate WL after the static elimination processing. In FIG. 12, the learning data LD includes the learning data LD1 to the learning data LD1000.

The learning data LD1 shows board information, static elimination processing conditions, and processing results of a certain learning target substrate WL1. Here, in the learning data LD1, the substrate information indicates the charge distribution of the learning target substrate WL1. Further, Lp1 indicates the conditions of the static elimination processing performed on the learning target substrate WL1.

The processing result information indicates the processing result of the static elimination processing for the learning target substrate WL1. The processing result may be determined by whether or not a discharge has occurred in the learning target substrate WL1. Alternatively, the processing result may be determined by whether or not an abnormality in the characteristics is found in the learning target substrate WL1. In the learning data LD1, the result of the learning target substrate that had been statically eliminated was good, so it is shown as 〇.

The learning data LD2 to LD1000 are generated corresponding to the learning target substrates WL2 to WL1000. As shown in the learning data LD2 to LD1000, typically, the charge distribution of the learning target substrate WL is different for each substrate. The static elimination processing conditions performed on the learning target substrate WL may be the same or different. The static elimination processing result changes according to the charge distribution of the learning target substrate WL and the processing conditions.

In the learning data LD shown in FIG. 12, the number of data is 1000, but the present embodiment is not limited to this. The number of data may be less than 1000 and may be greater than 1000. However, it is preferable that the number of data is as large as possible.

In the above description with reference to FIG. 12, when the processing result is good, it is indicated by ◯, when the processing result is not good, it is indicated by ×, and the processing results of the learning data LD1 to LD1000 are binarized. However, the present embodiment is not limited to this. The processing result may be classified into a plurality of values of 3 or more. Alternatively, the processing result may be classified into any value between the minimum value and the maximum value. For example, the processing result may be quantified in consideration of the usage amount (supply amount) of the static elimination liquid, the time required for the static elimination treatment, and the like, in addition to the characteristics of the learning target substrate WL.

In the learning data LD, the static elimination processing condition preferably includes a plurality of items. For example, the static elimination processing conditions may include the concentration, temperature, supply amount of the static elimination liquid, the discharge pattern of the static elimination liquid with respect to the learning target substrate, and the rotation speed of the substrate holding portion 120 at the time of static elimination.

Next, the learning data LD used in the learning method of the present embodiment will be described with reference to FIG. FIG. 13 is a diagram showing an example of the learning data LD.

As shown in FIG. 13, the learning data LD includes the learning data LD1 to LD1000. The learning data LD shows the board information of the learning target board WL, the static elimination processing conditions of the learning target board WL, and the processing result information of the learning target board WL. Here, the static elimination processing conditions include the concentration of the static elimination solution, the temperature of the static elimination solution, the supply amount of the static elimination solution, the discharge pattern of the static elimination solution to the learning target substrate, and the rotation speed of the learning target substrate when supplying the static elimination solution. ..

The concentration of the static eliminator indicates the concentration of the static eliminator used for the learning target substrate WL. The temperature of the static eliminator and the temperature of the static eliminator used for the learning target substrate WL are shown. The supply amount of the static elimination liquid indicates the supply amount of the static elimination liquid used for the learning target substrate WL. The discharge pattern of the static elimination liquid to the learning target substrate indicates a path (moving path of the nozzle 142) for discharging the static elimination liquid to the learning target substrate WL. The rotation speed of the learning target substrate indicates the rotation speed of the learning target substrate WL when supplying the static elimination liquid. Further, in the learning data LD, when the result of the static elimination processed learning target substrate is good, it is indicated by "◯", and when the result of the static elimination processed learning target substrate is not good, it is indicated by "x".

In the learning data LD1, Lc1 indicates the concentration of the static elimination liquid used for the learning target substrate WL1, and Lt1 indicates the temperature of the static elimination liquid used for the learning target substrate WL1. Further, Ls1 indicates the supply amount of the static elimination liquid used for the learning target substrate WL1, Le1 indicates the discharge pattern of the static elimination liquid for the learning target substrate WL1, and Lv1 indicates the static elimination liquid for the learning target substrate WL1. The rotation speed of the learning target substrate WL1 when supplying the liquid is shown. In the learning data LD1, the processing result of the learning target substrate that has been subjected to the static elimination processing is good, so the processing result is “◯”.

The same applies to the learning data LD2 to LD1000. As shown in the learning data LD2 to LD1000, typically, the charge distribution of the learning target substrate WL is different for each substrate. The static elimination processing conditions performed on the learning target substrate WL may be the same or different. For example, at least a part of a plurality of items of the static elimination processing condition may be the same or different. Alternatively, all of the plurality of items of the static elimination processing condition may be the same or different. The static elimination treatment result varies depending on the charge distribution of the learning target substrate WL and the static elimination treatment conditions.

Next, the static elimination process in the substrate processing apparatus 100 of the present embodiment will be described with reference to FIGS. 1 to 14. FIG. 14A shows the charge distribution of the substrate Wp to be processed, and FIG. 14B shows the static elimination processing condition information Rp generated in the trained model LM.

As shown in FIG. 14A, the substrate Wp to be processed has a charge distribution. The charge distribution of the substrate Wp to be processed is measured by the charge distribution measuring unit 130. When the control unit 22 inputs the charge distribution information indicating the charge distribution of the processing target substrate Wp into the trained model LM, the trained model LM generates the static elimination processing condition information Rp corresponding to the charge distribution information.

FIG. 14B is a diagram showing static elimination processing condition information Rp. The static elimination processing condition information Rp includes the concentration of the static elimination liquid, the temperature of the static elimination liquid, the supply amount of the static elimination liquid, the discharge pattern of the static elimination liquid to the learning target substrate, and the rotation speed of the processing target substrate when the static elimination liquid is supplied. ..

In the static elimination treatment condition information Rp, Rc indicates the concentration of the static elimination liquid used for the processing target substrate Wp, and Rt indicates the temperature of the static elimination liquid used for the treatment target substrate Wp. Further, Rs indicates the supply amount of the static elimination liquid used for the processing target substrate Wp, Re indicates the discharge pattern of the static elimination liquid used for the processing target substrate Wp, and Rv indicates the treatment target substrate Wp. On the other hand, the rotation speed of the processing target substrate Wp when supplying the static elimination liquid is shown.

In the description with reference to FIGS. 13 and 14, the static elimination treatment conditions are 5 of the static elimination liquid concentration, the static elimination liquid temperature, the static elimination liquid supply amount, the static elimination liquid discharge pattern, and the rotation speed of the substrate to be processed. It has one item, but the present embodiment is not limited to this. The static elimination processing condition may have any one or more of these five items. Alternatively, the static elimination processing condition may be a combination of any one or more of these five items and another item. Alternatively, the static elimination processing conditions may have one or more items different from these five items.

In the above description with reference to FIGS. 12 to 14, the substrate information of the learning target substrate WL is the charging distribution information indicating the charging distribution of the learning target substrate WL, but the present embodiment is not limited to this. .. The substrate information of the learning target substrate WL may include information other than the charge distribution information.

Next, the learning data LD used in the learning method of the present embodiment will be described with reference to FIG. FIG. 15 is a diagram showing an example of the learning data LD. Note that the learning data LD of FIG. 15 refers to FIG. 13 except that the substrate information includes information indicating the film thickness and film type of the learning target substrate WL in addition to the charge distribution of the learning target substrate WL. It is the same as the above-mentioned learning data LD, and duplicate description is omitted in order to avoid duplication.

As shown in FIG. 15, the learning data LD includes learning data LD1 to LD1000. The learning data LD shows the board information of the learning target board WL, the static elimination processing conditions of the learning target board WL, and the processing result information of the learning target board WL. Here, the substrate information of the learning target substrate WL includes the charge distribution of the learning target substrate WL, the film thickness of the learning target substrate WL, and the film type.

Further, the static elimination treatment conditions include the concentration of the static elimination liquid, the temperature of the static elimination liquid, the supply amount of the static elimination liquid, the discharge pattern of the static elimination liquid to the learning target substrate, and the rotation speed of the learning target substrate when the static elimination liquid is supplied. In FIG. 15, Lc indicates the concentration of the static elimination liquid used for the learning target substrate WL, and Lt indicates the temperature of the static elimination liquid used for the learning target substrate WL. Further, Ls indicates the supply amount of the static elimination liquid used for the learning target substrate WL, and Le indicates the discharge pattern of the static elimination liquid for the learning target substrate WL. Further, Lv indicates the rotation speed of the learning target substrate WL when supplying the static elimination liquid to the learning target substrate WL.

The film thickness of the substrate WL to be learned indicates the thickness of the film existing on the surface. The film thickness of the learning target substrate WL may indicate the thickness of two or more films existing on the surface.

The film type of the substrate WL to be learned indicates the type of film existing on the surface (upper surface Wa). For example, in the film type of the substrate WL to be learned, the film existing on the surface is a silicon oxide film, a silicon nitride film, or a mixture thereof. When the film thickness of the substrate WL to be learned indicates the thickness of two or more films existing on the surface, the film type may indicate the types of two or more films to be studied.

In the learning data LD1, Ld1 indicates the thickness of the film existing on the surface of the learning target substrate WL1. Further, Lk1 indicates the type of film existing on the surface of the learning target substrate WL1.

The same applies to the learning data LD2 to LD1000. As shown in the learning data LD2 to LD1000, typically, the charge distribution of the learning target substrate WL is different for each substrate. Further, even if the charge distribution of the learning target substrate WL is substantially the same, the degree of static elimination treatment varies greatly depending on the film thickness and / or the film type on the surface of the learning target substrate WL. Therefore, the substrate information preferably includes the film thickness and / or the film type in addition to the charge distribution. The substrate information may have a combination of one item of the film thickness and the film type and the other item. Alternatively, the substrate information may have one or more items other than the film thickness and the film type.

In the substrate processing apparatus 100 shown in FIG. 3, the static elimination unit 140 supplies the static elimination liquid in a predetermined state from the supply source to the substrate W, but the present embodiment is not limited to this. The concentration of the static eliminator may be changed as appropriate. Further, in the substrate processing apparatus 100 shown in FIG. 3, the static elimination unit 140 supplies the static elimination liquid to the upper surface Wa of the substrate W, but the present embodiment is not limited to this. The static eliminator may be supplied not only to the upper surface Wa of the substrate W but also to the back surface Wb of the substrate W.

Next, the substrate processing apparatus 100 of this embodiment will be described with reference to FIG. FIG. 16 is a schematic view of the substrate processing apparatus 100 of the present embodiment. The substrate processing apparatus 100 of FIG. 16 includes the substrate processing apparatus 100 described above with reference to FIG. 3, except that the static elimination unit 140 further includes a mixing unit 149, a nozzle 149a, a pipe 149b, and a valve 149c. The same applies, and duplicate descriptions are omitted to avoid redundancy.

In the substrate processing apparatus 100 of the present embodiment shown in FIG. 16, the static elimination unit 140 further includes a mixing unit 149, a nozzle 149a, a pipe 149b, and a valve 149c in addition to the nozzle 142, the pipe 144, and the valve 146. The mixing unit 149 is connected to the source. Here, pure water and carbon dioxide are supplied from the supply source to the mixing unit 149.

The mixing unit 149 produces carbonated water as a static elimination liquid by mixing pure water and carbon dioxide. The mixing ratio of pure water and carbon dioxide is changed according to the instruction from the control unit 22. Therefore, the concentration of the static elimination liquid can be changed by the mixing unit 149. The mixing unit 149 is connected to the pipe 144.

The nozzle 149a faces the back surface Wb of the substrate W and discharges the static elimination liquid toward the back surface Wb of the substrate W. The pipe 149b is coupled to the nozzle 149a. The pipe 149b penetrates the hollow hole of the shaft 123 of the substrate holding portion 120. The nozzle 149a is provided at the tip of the pipe 149b. The pipe 149b communicates the position between the valve 146 and the mixing unit 149 in the pipe 144 and the nozzle 149a. The static elimination liquid is supplied to the pipe 149b from the mixing unit 149. The valve 149c is provided in the pipe 149b. The valve 149c opens and closes the flow path in the pipe 149b.

According to the present embodiment, since the concentration of the static elimination liquid can be changed by the mixing unit 149, the static elimination unit 140 can supply the static elimination liquid having a different concentration to the substrate W. Further, the static elimination unit 140 can supply the static elimination liquid not only to the upper surface Wa of the substrate W but also to the back surface Wb.

Typically, since the back surface Wb of the substrate W is a non-device forming surface, discharging on the back surface Wb may have almost no effect on the characteristics of the substrate. In this case, it is preferable that the substrate processing apparatus 100 supplies the static elimination liquid to the back surface Wb of the substrate W before supplying the static elimination liquid to the upper surface Wa of the substrate W.

Next, the learning data LD used in the learning method of the present embodiment will be described with reference to FIG. FIG. 17 is a diagram showing an example of the learning data LD. The learning data LD of FIG. 17 is suitably used for generating the trained model LM of the substrate processing apparatus 100 shown in FIG. The learning data LD of FIG. 17 is the same as the learning data LD described above with reference to FIG. 13, except that the static elimination processing condition has two values for at least one item of one learning data. Therefore, duplicate descriptions are omitted to avoid redundancy.

As shown in FIG. 17, the learning data LD includes learning data LD1 to LD1000. The static elimination treatment conditions include the concentration of the static elimination liquid, the temperature of the static elimination liquid, the supply amount of the static elimination liquid, the discharge pattern of the static elimination liquid to the learning target substrate, and the rotation speed of the learning target substrate when the static elimination liquid is supplied. In FIG. 17, Lc indicates the concentration of the static elimination liquid used for the learning target substrate WL, and Lt indicates the temperature of the static elimination liquid used for the learning target substrate WL. Further, Ls indicates the supply amount of the static elimination liquid used for the learning target substrate WL, and Le indicates the discharge pattern and discharge timing of the static elimination liquid for the learning target substrate WL. Further, Lv indicates the rotation speed of the learning target substrate WL when supplying the static elimination liquid to the learning target substrate WL.

In FIG. 17, there are two values for the items of the concentration Lc of the static elimination liquid, the supply amount Ls, and the discharge pattern Le of the static elimination liquid of one learning data.

In the substrate processing apparatus 100 shown in FIG. 16, the concentration of the static elimination liquid can be changed by the mixing unit 149. Therefore, in the learning data LD1, Lcu1 indicates the concentration of the static elimination liquid supplied from the nozzle 142 to the upper surface Wa of the learning target substrate WL, and Lcd1 is supplied from the nozzle 149a to the back surface Wb of the learning target substrate WL. Indicates the concentration of the static eliminator.

Further, in the learning data LD1, Lsu1 indicates the amount of the static elimination liquid supplied from the nozzle 142 to the upper surface Wa of the learning target substrate WL, and Lsd1 is supplied from the nozzle 149a to the back surface Wb of the learning target substrate WL. Indicates the amount of static eliminator supplied. Further, Leu1 indicates the discharge pattern and discharge timing of the static elimination liquid from the nozzle 142 with respect to the upper surface Wa of the learning target substrate WL, and Red1 indicates the discharge timing of the static elimination liquid from the nozzle 149a with respect to the back surface Wb of the learning target substrate WL. ..

The same applies to the learning data LD2 to LD1000. As shown in the learning data LD2 to LD1000, typically, the charge distribution of the learning target substrate WL is different for each substrate. Further, with respect to the learning target substrate WL, the result of the static elimination processing of the learning target substrate WL greatly varies depending on the concentration, the supply amount, the discharge pattern and the discharge timing of the static elimination liquid supplied from the nozzle 142 and the nozzle 149a. Therefore, it is preferable that the learning data LD has an item that greatly contributes to the fluctuation of the result of the static elimination processing of the learning target substrate WL.

In the above description, the static elimination unit 140 supplies the so-called static elimination liquid, but in the present embodiment, the static elimination unit 140 is not limited to the one that supplies the so-called static elimination liquid. For example, the static elimination unit 140 may supply a treatment liquid other than the static elimination liquid. The static elimination unit 140 may supply the processing liquid so that the processing target substrate Wp does not generate an electric discharge.

In the substrate processing apparatus 100 described above, the static elimination unit 140 supplies the static elimination liquid to the substrate W, but the present embodiment is not limited to this. The static elimination unit 140 may supply the static elimination body to the chamber 110 toward the substrate W.

Next, the substrate processing apparatus 100 of the present embodiment will be described with reference to FIG. FIG. 18 is a schematic view of the substrate processing apparatus 100 of the present embodiment. The substrate processing apparatus 100 of FIG. 18 is the same as the substrate processing apparatus 100 described above with reference to FIG. 3, except that the static elimination unit 140 supplies the static elimination body toward the substrate W, and is redundant. Duplicate description is omitted to avoid it.

In the substrate processing apparatus 100 of the present embodiment shown in FIG. 18, the static elimination unit 140 supplies the static elimination body to the substrate W. The static eliminator is, for example, a high humidity gas. The static eliminator may be generated by adding water vapor to the inert gas.

The static elimination unit 140 includes a nozzle 142, a pipe 144, and a valve 146. One end of the pipe 144 is connected to the nozzle 142, and the other end of the pipe 144 is connected to the supply source of the static eliminator. An electric removing body is supplied to the pipe 144 from the supply source. The valve 146 is provided in the pipe 144. The valve 146 opens and closes the flow path in the pipe 144.

The electrostatic body may be supplied before the chemical treatment. Alternatively, the electrostatic body may be supplied during the chemical treatment. According to this embodiment, the static elimination body can easily suppress the charging of the substrate.

Next, the learning data LD used in the learning method of the present embodiment will be described with reference to FIG. FIG. 19 is a diagram showing an example of the learning data LD. The learning data LD of FIG. 19 is suitably used for generating the trained model LM of the substrate processing apparatus 100 shown in FIG. The learning data LD of FIG. 19 is the same as the learning data LD described above with reference to FIG. 13 except that the discharge pattern Le is omitted, and duplicate descriptions are omitted in order to avoid redundancy. do.

As shown in FIG. 19, the learning data LD includes learning data LD1 to LD1000. The static elimination treatment conditions include the humidity of the static elimination body, the temperature of the static elimination body, the supply amount of the static elimination body, and the rotation speed of the learning target substrate when supplying the static elimination body. In FIG. 19, Lc indicates the humidity of the static eliminator used for the learning target substrate WL, and Lt indicates the temperature of the static eliminator used for the learning target substrate WL. Further, Ls indicates the supply amount of the static elimination body used for the learning target substrate WL, and Lv indicates the rotation speed of the learning target substrate WL when supplying the static elimination body to the learning target substrate WL. show.

The same applies to the learning data LD2 to LD1000. As shown in the learning data LD2 to LD1000, typically, the charge distribution of the learning target substrate WL is different for each substrate. It is preferable that the learning data LD has an item that greatly contributes to the fluctuation of the result of the static elimination processing of the learning target substrate WL. The static eliminator may be used in combination with the static eliminator in order to efficiently remove the static electricity from the substrate W.

In the substrate processing apparatus 100 described above, the static elimination unit 140 supplies the static elimination liquid or the static elimination body to the substrate W, but the present embodiment is not limited to this. The static elimination unit 140 may use ultraviolet rays to eliminate static electricity from the substrate W.

Next, the substrate processing apparatus 100 of the present embodiment will be described with reference to FIG. FIG. 20 is a schematic view of the substrate processing apparatus 100 of the present embodiment. The substrate processing apparatus 100 of FIG. 20 is the same as the substrate processing apparatus 100 described above with reference to FIG. 3, except that the static elimination unit 140 uses ultraviolet rays to eliminate static electricity on the substrate W, in order to avoid redundancy. The description duplicated in is omitted.

In the substrate processing apparatus 100 of the present embodiment shown in FIG. 20, the static elimination unit 140 irradiates ultraviolet rays to eliminate static electricity on the substrate W.

The static elimination unit 140 has a light source 140U and a light source moving unit 148U. The light source 140U irradiates ultraviolet rays. For example, the light source 140U includes an excimer lamp. In one example, the light source 140U has a quartz tube charged with a discharge gas and a pair of electrodes arranged within the quartz tube.

The light source moving unit 148U moves the light source 140U between the irradiation position and the retracted position. When the light source 140U is in the irradiation position, the light source 140U is located above the substrate W. When the light source 140U is in the irradiation position, the light source 140U irradiates ultraviolet rays toward the upper surface Wa of the substrate W. When the light source 140U is in the retracted position, the light source 140U is located outside the substrate W in the radial direction.

The light source moving unit 148U includes an arm 148a, a rotating shaft 148b, and a moving mechanism 148c. The arm 148a extends along a substantially horizontal direction. A light source 140U is attached to the tip of the arm 148a. The arm 148a is coupled to the rotation shaft 148b. The rotation shaft 148b extends along a substantially vertical direction. The moving mechanism 148c rotates the rotation shaft 148b around a rotation axis along a substantially vertical direction, and rotates the arm 148a along a substantially horizontal plane. As a result, the light source 140U moves along a substantially horizontal plane. For example, the moving mechanism 148c includes an arm swing motor that rotates the rotating shaft 148b around the rotating axis. The arm swing motor is, for example, a servo motor.

Next, the learning data LD used in the learning method of the present embodiment will be described with reference to FIG. FIG. 21 is a diagram showing an example of the learning data LD. The learning data LD of FIG. 21 is suitably used for generating the trained model LM of the substrate processing apparatus 100 shown in FIG. The learning data LD of FIG. 21 is the same as the learning data LD described above with reference to FIG. 13, except that the concentration Lc, the temperature Lt, and the discharge pattern Le are omitted, in order to avoid redundancy. The description duplicated in is omitted.

As shown in FIG. 21, the learning data LD includes learning data LD1 to LD1000. The static elimination processing conditions include the irradiation intensity from the light source and the rotation speed of the learning target substrate when irradiating ultraviolet rays. In FIG. 17, Ls1 indicates the irradiation intensity from the light source used for the learning target substrate WL1, and Lv1 indicates the rotation speed of the learning target substrate WL1 when irradiating ultraviolet rays.

The same applies to the learning data LD2 to LD1000. As shown in the learning data LD2 to LD1000, typically, the charge distribution of the learning target substrate WL is different for each substrate. It is preferable that the learning data LD has an item that greatly contributes to the fluctuation of the result of the static elimination processing of the learning target substrate WL.

In the substrate processing apparatus 100 described above, the static elimination unit 140 applies the static elimination liquid, the static elimination body, or ultraviolet rays to the substrate W, but the present embodiment is not limited to this. The substrate W may be statically eliminated by the substrate holding unit 120 functioning as the static elimination unit 140.

Next, the substrate processing apparatus 100 of the present embodiment will be described with reference to FIG. 22 (a) is a schematic view of the substrate processing apparatus 100 of the present embodiment, and FIG. 22 (b) is a schematic plan view of the substrate holding portion 120 of the substrate processing apparatus 100 of the present embodiment. The substrate processing apparatus 100 of FIG. 22 is the same as the substrate processing apparatus 100 described above except that the substrate holding unit 120 eliminates static electricity from the substrate W, and duplicate description is omitted in order to avoid redundancy.

In the substrate processing apparatus 100 of the present embodiment shown in FIG. 22, the substrate holding portion 120 includes a spin base 121, a chuck member 122, a shaft 123, and an electric motor 124. The chuck member 122 is provided on the spin base 121. The chuck member 122 chucks the substrate W. The spin base 121 is provided with six chuck members 122 (that is, chuck members 122a to 122f).

Here, the chuck member 122 abuts on the end portion of the upper surface Wa of the substrate W to chuck the substrate W. The chuck member 122 is individually driven so as to rotate in the circumferential direction by a drive mechanism housed in the spin base 121. Here, when the chuck member 122 rotates in the counterclockwise direction, the chuck member 122 chucks the substrate W. On the contrary, when the chuck member 122 rotates in the clockwise direction, the substrate W is detached from the chuck member 122.

In the substrate processing apparatus 100 of the present embodiment, the chuck member 122 is formed of a conductive material. Further, inside the spin base 121, wiring 121L separated for each chuck member 122 is provided, and on the shaft 123, wiring 123L connected to a plurality of wirings 121L of the spin base 121 is provided. One end of the wiring 123L is connected to the ground of the substrate processing device 100.

Therefore, when the chuck member 122 rotates and comes into contact with the end portion of the upper surface Wa of the substrate W, the substrate W can be statically eliminated. Therefore, the substrate holding unit 120 functions as the static elimination unit 140. Further, when a specific chuck member 122 among the six chuck members 122a to 122f is rotated and brought into contact with the substrate W, the electric charge in the specific region of the substrate W is preferentially moved to the outside of the substrate processing apparatus 100. can. Further, after static elimination, the chuck member 122 can chuck the substrate W by rotating the remaining chuck member 122 to bring it into contact with the substrate W.

22 (c) and 22 (d) are schematic plan views of the substrate holding portion 120 in the substrate processing apparatus 100 of the present embodiment. FIG. 22C also shows the charge distribution of the substrate W measured by the charge distribution measuring unit 130. As shown in FIG. 22 (c), there is a portion of the substrate W having a low potential at the end of the upper right region. In that case, the chuck member 122a located near the end of the upper right region of the substrate W is rotated to bring it into contact with the substrate W, while the other chuck members 122b to 122f are not rotated. In this case, the electric charge of the substrate W gently flows from the upper right region end of the substrate W to the ground through the wirings 121L and 123L connected to the chuck member 122a and the chuck member 122a. It is possible to suppress the generation of electric discharge when chucking.

Further, as shown in FIG. 22D, in another substrate W, there are two low potential portions of the substrate W, the end portion of the diagonally upper right region and the end portion of the diagonally lower right region. In that case, while the chuck members 122a and 122c located near the end of the diagonally upper right region and the end of the diagonally lower right region of the substrate W are rotated and brought into contact with the substrate W, the other chuck members 122b and 122d ~ 122f is not rotated. In this case, the electric charge of the substrate W is transferred from the end of the diagonally upper right region and the end of the diagonally lower right region of the substrate W to the ground via the wirings 121L and 123L connected to the chuck members 122a and 122c and the chuck members 122a and 122c. Since the flow is gentle, it is possible to suppress the generation of electric discharge when the chuck member 122 chucks the substrate W.

Next, the learning data LD used in the learning method of the present embodiment will be described with reference to FIG. 23. FIG. 23 is a diagram showing an example of the learning data LD. The learning data LD of FIG. 23 is suitably used for generating the trained model LM of the substrate processing apparatus 100 shown in FIG. The learning data LD of FIG. 23 is the same as the learning data LD described above with reference to FIG. 13 except that the static elimination processing condition has the rotation start pattern Lr, and is duplicated in order to avoid redundancy. The description is omitted.

As shown in FIG. 23, the learning data LD includes the learning data LD1 to LD1000. The static elimination processing condition includes a chuck rotation start pattern.

The learning data LD1 shows board information, static elimination processing conditions, and processing results of a certain learning target substrate WL1. Here, in the learning data LD1, the substrate information indicates the charge distribution of the learning target substrate WL1. Further, Lr1 indicates a pattern of a chuck member that is first rotated when chucking the learning target substrate WL1.

The same applies to the learning data LD2 to LD1000. As shown in the learning data LD2 to LD1000, typically, the charge distribution of the learning target substrate WL is different for each substrate. It is preferable that the learning data LD has an item that greatly contributes to the fluctuation of the result of the static elimination processing of the learning target substrate WL.

In the above description with reference to FIGS. 1 to 23, the storage unit 24 of the board processing device 100 or the storage unit 424 of the learning device 400 stores the learned model LM constructed by machine learning. The embodiment is not limited to this. The storage unit 24 of the board processing device 100 or the storage unit 424 of the learning device 400 may store the conversion table instead of the trained model LM.

Next, the substrate processing apparatus 100 of this embodiment will be described with reference to FIG. 24. The substrate processing apparatus 100 of FIG. 24 has the same configuration as the substrate processing apparatus 100 described above with reference to FIG. 4, except that the storage unit 24 stores the conversion table CT instead of the trained model LM. It has, and duplicate description is omitted to avoid redundancy.

As shown in FIG. 24, in the substrate processing apparatus 100, the storage unit 24 stores the conversion table CT. The conversion table CT associates the substrate information of the processing target substrate Wp with the static elimination processing processing conditions. The substrate information of the substrate Wp to be processed includes, for example, the lowest potential value and the lowest potential position of the substrate W. The conversion table CT is created based on the board information of the learning target board WL, the static elimination processing processing condition information, and the processing result information.

The substrate information acquisition unit 22a identifies the lowest potential of the processing target substrate Wp and its position from the charging distribution of the processing target substrate Wp measured by the charge distribution measuring unit 130.

The static elimination processing condition information acquisition unit 22b acquires static elimination processing condition information from the board information based on the conversion table CT. Typically, the static elimination processing condition information acquisition unit 22b extracts the value corresponding to the substrate information from the conversion table CT, and based on the relationship between the substrate information associated with the conversion table CT and the static elimination processing processing condition information, Acquires static elimination processing condition information. In this way, the static elimination processing condition information acquisition unit 22b acquires the static elimination processing condition information corresponding to the board information by using the conversion table CT.

After that, the control unit 22 controls the substrate holding unit 120 and the static elimination unit 140 according to the static elimination processing conditions shown in the static elimination processing condition information.

FIG. 25 is a diagram showing an example of the conversion table CT. As shown in FIG. 25, the conversion table CT shows the substrate information of the substrate Wp to be processed and the static elimination processing conditions. Here, in the conversion table CT, the substrate information indicates information regarding the charge distribution of the substrate Wp to be processed. Here, the information regarding the charge distribution of the substrate Wp to be processed includes the lowest potential position and the lowest potential value of the substrate Wp to be processed. The lowest potential position of the processing target substrate Wp is represented by the xy coordinates of the processing target substrate Wp. The static elimination processing condition information indicates the conditions of static elimination processing to be performed on the processing target substrate Wp.

The conversion table CT1 shows a certain substrate information and the corresponding static elimination processing conditions. Here, in the conversion table CT1, the substrate information includes the lowest potential position and the lowest potential value of the substrate Wp to be processed. (X1, y1) indicate the lowest potential position of a certain processing target substrate Wp. C1 indicates the lowest potential value of a certain processing target substrate Wp. Rp1 indicates the conditions for static elimination processing to be performed on the processing target substrate Wp. Therefore, if the lowest potential position of the substrate Wp to be processed is (x1, y1) and the lowest potential value is C1, the substrate processing apparatus 100 performs the static elimination processing under the static elimination processing conditions indicated by Rp1. ..

The same applies to the conversion tables CD2 to CD1000. Typically, at least one of the lowest potential position and the lowest potential value is different for the conversion tables CT1 to CD1000.

If the minimum potential value of the substrate Wp to be processed and its position measured by the charge distribution measuring unit 130 do not match the values shown in the conversion table, the static elimination processing conditions of the substrate Wp to be processed are shown in the conversion table CT. It may be determined by linear interpolation of the values of the static elimination processing conditions. Alternatively, the static elimination processing conditions of the processing target substrate Wp may be determined by interpolating the values of the static elimination processing conditions shown in the conversion table CT with a polynomial.

The embodiments of the present invention have been described above with reference to the drawings. However, the present invention is not limited to the above-described embodiment, and can be implemented in various aspects without departing from the gist thereof. In addition, various inventions can be formed by appropriately combining the plurality of components disclosed in the above embodiments. For example, some components may be removed from all the components shown in the embodiments. In addition, components across different embodiments may be combined as appropriate. In order to make the drawings easier to understand, each component is schematically shown, and the thickness, length, number, spacing, etc. of each component shown are actual for the convenience of drawing creation. May be different. Further, the material, shape, dimensions, etc. of each component shown in the above embodiment are merely examples, and are not particularly limited, and various changes can be made without substantially deviating from the effects of the present invention. be.

The present invention is suitably used for a substrate processing apparatus, a substrate processing method, a learning data generation method, a learning method, a learning apparatus, a trained model generation method, and a trained model.

10 Board processing system 20 Control device 22 Control unit 22a Board information acquisition unit 22b Static elimination processing condition information acquisition unit 24 Storage unit LM learned model 100 Board processing device 130 Charge distribution measurement unit 140 Chemical solution supply unit 150 Rinse solution supply unit 200 Board processing Learning system 300 Learning data generator 400 Learning device

Claims (13)

A substrate holding unit that rotatably holds the substrate to be processed,
A charge distribution measuring unit that measures the charge distribution of the substrate to be processed, and a charge distribution measuring unit.
A static elimination unit that eliminates static electricity from the substrate to be processed, and
A substrate information acquisition unit that acquires substrate information including charge distribution information indicating the charge distribution of the substrate to be processed, and a substrate information acquisition unit.
Based on the board information, a static elimination processing condition information acquisition unit that acquires static elimination processing condition information indicating the static elimination processing conditions of the processing target board from the trained model, and a static elimination processing condition information acquisition unit.
Based on the static elimination processing condition information acquired by the static elimination processing condition information acquisition unit, the substrate holding unit and a control unit that controls the static elimination unit so as to eliminate static electricity on the processing target substrate are provided.
The trained model includes substrate information including charge distribution information indicating the charge distribution of the learning target substrate, static elimination processing condition information indicating the conditions for static elimination processing of the learning target substrate, and the result of static elimination processing of the learning target substrate. A board processing device constructed by machine learning the learning data associated with the processing result information shown. The substrate processing apparatus according to claim 1, further comprising a storage unit for storing the trained model. The substrate processing apparatus according to claim 1 or 2, wherein the substrate information for each of the processing target substrate and the learning target substrate further includes information indicating the film type or film thickness of the substrate. The substrate processing apparatus according to any one of claims 1 to 3, wherein a static elimination liquid is supplied to each of the processing target substrate and the learning target substrate. For each of the processing target substrate and the learning target substrate, the static elimination treatment condition information includes the concentration of the static elimination liquid, the temperature of the static elimination liquid, the supply amount of the static elimination liquid, the discharge pattern of the static elimination liquid, and the static elimination. The substrate processing apparatus according to claim 4, which includes information indicating any of the rotational speeds of the substrate when supplying the liquid. The substrate processing apparatus according to any one of claims 1 to 3, wherein the processing target substrate and the learning target substrate are each irradiated with ultraviolet rays. Steps to hold the substrate to be processed rotatably,
A step of acquiring substrate information including charge distribution information indicating the charge distribution of the substrate to be processed, and
A step of acquiring static elimination processing condition information indicating the static elimination processing condition of the processing target substrate from the trained model based on the substrate information, and
A substrate processing method including a step of statically eliminating a substrate to be processed according to the static elimination processing conditions of the static elimination processing condition information.
In the step of acquiring the static elimination processing condition information, the trained model includes substrate information including charge distribution information indicating the charging distribution of the learning target substrate, and static elimination processing condition information indicating the conditions for static elimination processing of the learning target substrate. , A substrate processing method constructed by machine learning learning data associated with processing result information indicating the result of static elimination processing of the learning target substrate. A step of acquiring substrate information including charge distribution information indicating the charge distribution of the learning target substrate from time series data output from a substrate processing apparatus that processes the learning target substrate.
From the time-series data, a step of acquiring static elimination processing condition information indicating a condition for statically eliminating the learning target substrate in the substrate processing apparatus, and a step of acquiring static elimination processing condition information.
From the time-series data, a step of acquiring processing result information indicating the result of static elimination of the learning target substrate in the substrate processing apparatus, and a step of acquiring the processing result information.
A method for generating learning data, which includes a step of associating the board information, the static elimination processing condition information, and the processing result information with the learning target substrate and storing the learning data in a storage unit. The step of acquiring the learning data generated according to the method of generating the learning data according to claim 8, and the step of acquiring the learning data.
A learning method including a step of inputting the learning data into a learning program and machine learning the learning data. A storage unit that stores the learning data generated according to the method for generating the learning data according to claim 8.
A learning device including a learning unit that inputs the learning data into a learning program and machine-learns the learning data. The step of acquiring the learning data generated according to the method of generating the learning data according to claim 8, and the step of acquiring the learning data.
A method for generating a trained model, which includes a step of generating a trained model constructed by machine learning the training data. A trained model constructed by machine learning the learning data generated according to the learning data generation method according to claim 8. A board holding part that holds the board rotatably,
A charge distribution measuring unit that measures the charge distribution of the substrate,
A static eliminator that eliminates static electricity from the substrate,
A storage unit that stores a conversion table in which substrate information including charge distribution information and static elimination processing condition information indicating static elimination processing conditions are associated with each other.
A substrate information acquisition unit that acquires substrate information including charge distribution information indicating the charge distribution of the substrate, and a substrate information acquisition unit.
A static elimination processing condition information acquisition unit that acquires static elimination processing condition information indicating the static elimination processing conditions of the substrate using the conversion table based on the substrate information.
A substrate processing apparatus including a substrate holding unit and a control unit that controls the static elimination unit so as to eliminate static electricity on the substrate based on the static elimination processing condition information acquired by the static elimination processing condition information acquisition unit.

Images