Substrate processing apparatus and monitoring method

Abstract

To provide a technology capable of suppressing influences of droplets and thereby monitoring an object to be monitored with higher accuracy.SOLUTION: A substrate processing device comprises a chamber 10, a substrate holding part 20, a nozzle 30, a camera 70, and a control part 9. The substrate holding part 20 holds a substrate W in the chamber 10. The nozzle 30 discharges processing liquid toward the substrate W held by the substrate holding part 20. The camera 70 images an imaging region including an object to be monitored in the chamber 10 to generate pickup image data. When the pickup image data includes droplets, the control part 9 monitors the object to be monitored using a region excluding at least a part of a droplet region indicating the droplets of the pickup image data.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to a substrate processing apparatus and a monitoring method. [Background technology]

[0002] Conventionally, in manufacturing processes for semiconductor devices and the like, various processing liquids such as pure water, photoresist liquid, and etching liquid are supplied to substrates to perform various substrate processing processes such as cleaning processing and resist coating processing. As an apparatus for performing substrate processing using these processing liquids, a substrate processing apparatus is widely used in which a substrate holder rotates a substrate in a horizontal position while a processing liquid is ejected from a nozzle onto the surface of the substrate.

[0003] In such substrate processing apparatuses, whether the nozzle position is appropriate is monitored. For example, in Patent Document 1, an imaging means such as a camera is provided to monitor the nozzle position. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-173148 Summary of the Invention [Problem to be solved by the invention]

[0005] In order to properly process a substrate, it is desirable to monitor more than just the nozzle.

[0006] For example, a substrate processing apparatus is provided with a guard for receiving processing liquid splashed from the periphery of a substrate. The guard has a cylindrical shape and surrounds the periphery of the substrate. The guard is provided so as to be able to rise and fall, and is lowered when the substrate is being loaded or unloaded. This makes it possible to avoid collision between the guard and a transport robot that loads or unloads the substrate into or out of the substrate processing apparatus. When the processing liquid is supplied to the surface of the substrate, the guard is raised. As the guard is raised, the upper peripheral edge of the guard is positioned above the substrate. Therefore, processing liquid splashed from the periphery of the substrate is received by the inner peripheral surface of the guard.

[0007] If an abnormality occurs and the guard cannot move to the appropriate position, it may not be possible to properly avoid a collision between the guard and the transport robot, or the guard may not be able to properly receive the processing liquid.

[0008] Therefore, it is conceivable that a camera captures an image of an imaging area including the guard, generates captured image data, and an image processing unit monitors the position of the guard based on the captured image data. However, if droplets of the processing liquid adhere to the outer surface of the guard, the accuracy of monitoring using the captured image data may decrease.

[0009] Furthermore, even if droplets adhere to the nozzles, there is a risk that the accuracy of nozzle position monitoring using captured image data will decrease.

[0010] Therefore, an object of the present disclosure is to provide a technology that can suppress the influence of droplets and monitor an object to be monitored with higher accuracy. [Means for solving the problem]

[0011] A first aspect is a substrate processing apparatus comprising a chamber, a substrate holding unit that holds a substrate within the chamber, a nozzle that ejects a processing liquid toward the substrate held by the substrate holding unit, a camera that captures an image of an image area including an object to be monitored within the chamber and generates captured image data, and a control unit that, when the captured image data includes droplets, monitors the object to be monitored using an area of ​​the captured image data excluding at least a portion of the droplet area that represents the droplets.

[0012] A second aspect is a substrate processing apparatus according to the first aspect, further comprising a memory unit that stores area data indicating a first area and a second area in the captured image data that correspond to the surfaces of different objects, and when the droplet is contained in the first area, the control unit monitors the monitored object using an area of ​​the captured image data excluding the outline area of ​​the droplet area, and when the droplet is contained in the second area, the control unit monitors the monitored object using an area of ​​the captured image data excluding the entire droplet area.

[0013] A third aspect is a substrate processing apparatus according to the first aspect, wherein the control unit monitors the object to be monitored using an area of ​​the captured image data excluding the outline area of ​​the droplet area for droplets adhering to a hydrophilic surface, and an area of ​​the captured image data excluding the entire droplet area for droplets adhering to a hydrophobic surface that has lower wettability than the hydrophilic surface.

[0014] A fourth aspect is a substrate processing apparatus according to the third aspect, further comprising a memory unit that stores area data indicating a first area and a second area corresponding to the hydrophilic surface and the hydrophobic surface, respectively, in the captured image data, and the control unit determines whether the surface to which the droplet is attached is the hydrophilic surface or the hydrophobic surface based on the area data.

[0015] A fifth aspect is the substrate processing apparatus according to the fourth aspect, wherein the control unit updates the area data based on a time-related value indicating the operating time of the substrate processing apparatus, the number of processed substrates, or elapsed time.

[0016] A sixth aspect is a substrate processing apparatus according to the third aspect, wherein the control unit determines whether the surface to which the droplets are attached is the hydrophilic surface or the hydrophobic surface based on the captured image data.

[0017] A seventh aspect is a substrate processing apparatus according to the sixth aspect, wherein the control unit calculates the size of the droplet area based on the captured image data, and determines that the surface is a hydrophilic surface when the size of the droplet area is equal to or greater than a threshold value, and determines that the surface is a hydrophobic surface when the size of the droplet is less than the threshold value.

[0018] An eighth aspect is the substrate processing apparatus according to the sixth or seventh aspect, wherein the control unit determines whether the surface is the hydrophilic surface or the hydrophobic surface using a trained model.

[0019] A ninth aspect is a substrate processing apparatus according to any one of the first to eighth aspects, further comprising a hydrophilic and transparent camera guard provided between the camera and the imaging area, wherein the control unit determines whether or not the droplets are attached to the camera guard based on the captured image data, and when the droplets are attached to the camera guard, monitors the monitored object using an area obtained by excluding from the captured image data the outline area of ​​the droplet area indicating the droplets attached to the camera guard.

[0020] A tenth aspect is a substrate processing apparatus according to any one of the first to eighth aspects, further comprising a hydrophobic and transparent camera guard provided between the camera and the imaging area, wherein the control unit determines whether or not the droplets are attached to the camera guard based on the captured image data, and when the droplets are attached to the camera guard, monitors the monitored object using an area obtained by excluding the entire droplet area representing the droplets attached to the camera guard from the captured image data.

[0021] An eleventh aspect is a substrate processing apparatus according to any one of the first to eighth aspects, further comprising a transparent camera guard provided between the camera and the imaging area, and a droplet removal unit that performs a removal operation to remove at least some of the droplets adhering to the camera guard, wherein when the droplets are included in the captured image data, the droplet removal unit performs the removal operation, and the control unit monitors the object to be monitored based on the captured image data captured by the camera after the removal operation.

[0022] A twelfth aspect is a monitoring method comprising an imaging step in which a camera captures an image of an imaging area including an object to be monitored within a chamber that contains a substrate holding part that holds a substrate and a nozzle that ejects a processing liquid toward the substrate held by the substrate holding part, and generates captured image data; a droplet determination step in which it is determined whether or not the captured image data contains droplets; and a monitoring step in which, when the captured image data contains the droplets, the object to be monitored is monitored using an area of ​​the captured image data excluding at least a portion of the droplet area that indicates the droplets. [Effects of the Invention]

[0023] According to the first, second and twelfth aspects, at least a part of the droplet area is not used, so that the object to be monitored can be monitored with higher accuracy.

[0024] According to the third aspect, a droplet on a hydrophobic surface with low wettability is positioned in a raised state, functioning as a lens. Therefore, visual distortion occurs in the image of the hydrophobic surface through the droplet. In the third aspect, the entire droplet area is removed, thereby avoiding a decrease in monitoring accuracy due to distortion.

[0025] On the other hand, droplets on a highly wettable hydrophilic surface are positioned in a thin, spread state. In the inner part of the droplet, which is inside the outline of the droplet in a planar view, the liquid surface is flat, so it hardly functions as a lens, and there is almost no visual distortion in the image of the hydrophilic surface through the inner part of the droplet. In the third aspect, the inner area of ​​the droplet is used, excluding the outline area, so monitoring can be performed based on more pixel values.

[0026] According to the fourth aspect, the wettability of the surface can be determined by a simple process.

[0027] According to the fifth aspect, the range of the droplet region to be removed can be determined appropriately in response to changes over time.

[0028] According to the sixth aspect, the wettability of the surface is determined based on the captured image data, so that the user does not need to set data relating to the wettability in advance.

[0029] According to the seventh aspect, the wettability can be determined with a relatively light processing load.

[0030] According to the eighth aspect, the wettability can be determined with high accuracy.

[0031] According to the ninth aspect, when a droplet adheres to the hydrophilic camera guard, the droplet is positioned in a thinly spread state. By using the inner area of ​​the droplet area, a larger number of pixels can be used, and the monitored object can be monitored with higher accuracy.

[0032] According to the tenth aspect, when a droplet adheres to a hydrophobic camera guard, the droplet is positioned in a thick, raised state. By using an area of ​​the captured image data excluding the entire droplet area, the influence of visual distortion due to the droplet area can be avoided, and the monitored object can be monitored with higher accuracy.

[0033] According to the eleventh aspect, when droplets adhere to the camera guard, the droplets are removed, so that the object to be monitored can be monitored with less influence of the droplets. [Brief explanation of the drawings]

[0034] [Figure 1] FIG. 1 is a plan view schematically showing an example of the configuration of a substrate processing apparatus. [Figure 2] FIG. 2 is a plan view schematically illustrating an example of the configuration of a processing unit according to the first embodiment. [Figure 3] FIG. 2 is a longitudinal sectional view schematically showing an example of the configuration of a processing unit according to the first embodiment. [Figure 4] FIG. 2 is a functional block diagram illustrating an example of an internal configuration of a control unit. [Figure 5] 1 is a flowchart showing an example of a flow of substrate processing. [Figure 6] FIG. 2 is a diagram schematically illustrating an example of a captured image generated by a camera capturing an image of an imaging area. [Figure 7] 10 is a flowchart illustrating an example of a monitoring process performed by a processing unit. [Figure 8] 10 is a flowchart showing a specific example of a monitoring process. [Figure 9] 10A and 10B are diagrams illustrating an example of a droplet removal process performed on a captured image and a reference image. [Figure 10] 10 is a cross-sectional view schematically illustrating an example of droplets on the upper surface of the spin base and the outer peripheral surface of the outer guard. FIG. [Figure 11] 10 is a flowchart showing a specific example of a droplet removing step according to the second embodiment. [Figure 12]10A and 10B are diagrams illustrating an example of a droplet removal process performed on a captured image and a reference image. [Figure 13] 10 is a flowchart illustrating an example of updating area data. [Figure 14] 10 is a flowchart illustrating an example of a method for determining a deletion range based on size. [Figure 15] 10 is a flowchart showing an example of a method for determining a deletion range using a trained model. [Figure 16] FIG. 10 is a longitudinal sectional view schematically showing an example of the configuration of a processing unit according to a third embodiment. [Figure 17] FIG. 2 is a diagram schematically illustrating an example of an image captured by a camera at a first camera position. [Figure 18] FIG. 10 is a diagram schematically illustrating an example of an image captured by a camera at a second camera position. [Figure 19] 10 is a flowchart showing a specific example of a droplet removing step according to the third embodiment. [Figure 20] FIG. 10 is a longitudinal sectional view schematically showing an example of the configuration of a processing unit according to a fourth embodiment. [Figure 21] 13 is a flowchart showing an example of an operation of a processing unit according to the fourth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0035] Hereinafter, embodiments will be described with reference to the accompanying drawings. Note that the drawings are schematic, and for the sake of convenience, components may be omitted or simplified as appropriate. Furthermore, the relative sizes and positions of components shown in the drawings are not necessarily accurately depicted and may be changed as appropriate.

[0036] In the following description, the same components are denoted by the same reference numerals, and their names and functions are also the same. Therefore, detailed descriptions of them may be omitted to avoid duplication.

[0037] Furthermore, in the following description, even if ordinal numbers such as "first" or "second" are used, these terms are used for convenience to facilitate understanding of the contents of the embodiments, and are not limited to the ordering that may result from these ordinal numbers.

[0038] When expressions indicating relative or absolute positional relationships (e.g., "in one direction," "along one direction," "parallel," "orthogonal," "center," "concentric," "coaxial," etc.) are used, unless otherwise specified, the expressions not only strictly represent the positional relationship but also represent a state in which there is a relative displacement in terms of angle or distance within a range in which tolerance or equivalent functionality is obtained. When expressions indicating an equal state (e.g., "identical," "equal," "homogeneous," etc.) are used, the expressions not only represent a state in which there is strict quantitative equality but also represent a state in which there is a difference in which tolerance or equivalent functionality is obtained, unless otherwise specified. When expressions indicating a shape (e.g., "rectangular shape" or "cylindrical shape," etc.) are used, the expressions not only represent a geometrically strict shape but also represent a shape with, for example, irregularities or chamfers within a range in which equivalent effects are obtained, unless otherwise specified. When the expressions "comprise," "include," "have," "includes," "includes," or "have" are used to describe one component, the expressions are not exclusive expressions that exclude the presence of other components. When the phrase "at least one of A, B, and C" is used, the phrase includes A only, B only, C only, any two of A, B, and C, and all of A, B, and C.

[0039] First Embodiment <Overall configuration of substrate processing equipment> FIG. 1 is a plan view schematically illustrating an example of the configuration of a substrate processing apparatus 100. The substrate processing apparatus 100 is a single-wafer processing apparatus that processes substrates W to be processed one by one. The substrate processing apparatus 100 performs liquid processing on the substrates W using a chemical solution and a rinse solution such as pure water, and then performs a drying process. The substrate W is, for example, a semiconductor substrate and has a disk shape. Examples of the chemical solution include a mixed solution (SC1) of ammonia and hydrogen peroxide, a mixed aqueous solution (SC2) of hydrochloric acid and hydrogen peroxide, or a DHF solution (dilute hydrofluoric acid). In the following description, the chemical solution, rinse solution, organic solvent, etc. are collectively referred to as the "processing solution." It should be noted that the "processing solution" includes not only chemical solutions used in cleaning processes, but also chemical solutions for removing unnecessary films and chemical solutions for etching.

[0040] The substrate processing apparatus 100 includes a plurality of processing units 1, a load port LP, an indexer robot 102, a main transport robot 103, and a control unit 9.

[0041] The load port LP is an interface unit for loading and unloading substrates W between the substrate processing apparatus 100 and the outside. A container (also called a carrier) containing a plurality of unprocessed substrates W is loaded into the load port LP from the outside. The load port LP can hold a plurality of carriers. Each substrate W is removed from the carrier by the substrate processing apparatus 100, processed as described below, and then stored back in the carrier. The carrier containing the processed substrates W is then unloaded from the load port LP to the outside.

[0042] The indexer robot 102 transports the substrates W between each carrier held on the load port LP and the main transport robot 103. The main transport robot 103 transports the substrates W between each processing unit 1 and the indexer robot 102.

[0043] Each processing unit 1 performs liquid processing and drying processing on one substrate W. The substrate processing apparatus 100 according to this embodiment is provided with 12 processing units 1 of similar configuration. Specifically, four towers, each including three processing units 1 stacked vertically, are arranged around the main transport robot 103. FIG. 1 shows a schematic diagram of one of the processing units 1 stacked in three tiers. The number of processing units 1 in the substrate processing apparatus 100 is not limited to 12 and may be changed as appropriate.

[0044] The main transport robot 103 is installed in the center of four towers in which processing units 1 are stacked. The main transport robot 103 carries the substrates W to be processed received from the indexer robot 102 into each processing unit 1. The main transport robot 103 also carries out processed substrates W from each processing unit 1 and hands them over to the indexer robot 102. The control unit 9 controls the operation of each component of the substrate processing apparatus 100.

[0045] Hereinafter, one of the twelve processing units 1 installed in the substrate processing apparatus 100 will be described.

[0046] <Processing unit> Fig. 2 is a plan view schematically showing an example of the configuration of the processing unit 1 according to the first embodiment. Fig. 3 is a vertical cross-sectional view schematically showing an example of the configuration of the processing unit 1 according to the first embodiment.

[0047] In the example of FIGS. 2 and 3, the processing unit 1 includes a substrate holder 20, a first nozzle 30, a second nozzle 60, a third nozzle 65, a guard unit 40, and a camera 70.

[0048] 2 and 3, the processing unit 1 also includes a chamber 10. The chamber 10 includes a sidewall 11 extending in the vertical direction, a ceiling wall 12 that closes the upper side of the space enclosed by the sidewall 11, and a floor wall 13 that closes the lower side. A processing space is formed in the space enclosed by the sidewall 11, the ceiling wall 12, and the floor wall 13. A loading / unloading port through which the main transport robot 103 loads and unloads the substrate W, and a shutter that opens and closes the loading / unloading port are provided in part of the sidewall 11 of the chamber 10 (all not shown). The chamber 10 houses a substrate holder 20, a first nozzle 30, a second nozzle 60, a third nozzle 65, and a guard unit 40.

[0049] 3, a fan filter unit (FFU) 14 is attached to the ceiling wall 12 of the chamber 10 to further purify the air in a clean room in which the substrate processing apparatus 100 is installed and supply the purified air to the processing space in the chamber 10. The fan filter unit 14 includes a fan and a filter (e.g., a HEPA (High Efficiency Particulate Air) filter) for taking in air from the clean room and sending it into the chamber 10, and forms a downflow of purified air in the processing space in the chamber 10. A punched plate with a large number of blow-out holes may be provided directly below the ceiling wall 12 to uniformly distribute the purified air supplied from the fan filter unit 14.

[0050] The substrate holder 20 holds the substrate W in a horizontal position (a position in which the normal is along the vertical direction) and rotates the substrate W around a rotation axis CX (see FIG. 3). The rotation axis CX is an axis that is along the vertical direction and passes through the center of the substrate W. The substrate holder 20 is also called a spin chuck. Note that FIG. 2 shows the substrate holder 20 in a state in which it is not holding a substrate W.

[0051] 2 and 3, the substrate holding unit 20 includes a disk-shaped spin base 21 that is arranged in a horizontal position. The outer diameter of the disk-shaped spin base 21 is slightly larger than the diameter of the circular substrate W held by the substrate holding unit 20 (see FIG. 3). Therefore, the spin base 21 has an upper surface 21a that faces the entire lower surface of the substrate W to be held in the vertical direction. Here, as an example, the upper surface 21a of the spin base 21 has high wettability. In other words, the upper surface 21a is a hydrophilic surface. The contact angle of the hydrophilic surface here is, for example, less than about 45 degrees.

[0052] 2 and 3, a plurality of chuck pins 26 (four in this embodiment) are erected on the peripheral edge of the upper surface 21a of the spin base 21. The plurality of chuck pins 26 are arranged at equal intervals along a circumference corresponding to the peripheral edge of the circular substrate W. Each chuck pin 26 is provided so as to be drivable between a holding position in contact with the peripheral edge of the substrate W and an open position spaced apart from the peripheral edge of the substrate W. The plurality of chuck pins 26 are driven in conjunction with each other by a link mechanism (not shown) housed in the spin base 21. The substrate holder 20 can hold the substrate W in a horizontal position close to the upper surface 21a above the spin base 21 by stopping the plurality of chuck pins 26 at their respective holding positions (see FIG. 3), and can release the substrate W from its holding by stopping the plurality of chuck pins 26 at their respective open positions.

[0053] 3, the upper end of a rotation shaft 24 extending along the rotation axis CX is connected to the lower surface of the spin base 21. A spin motor 22 that rotates the rotation shaft 24 is provided below the spin base 21. The spin motor 22 rotates the rotation shaft 24 about the rotation axis CX, thereby rotating the spin base 21 within a horizontal plane. As a result, the substrate W held by the chuck pins 26 also rotates about the rotation axis CX.

[0054] 3, a cylindrical cover member 23 is provided to surround the periphery of the spin motor 22 and the rotation shaft 24. The lower end of the cover member 23 is fixed to the floor wall 13 of the chamber 10, and the upper end reaches directly below the spin base 21. In the example of FIG. 3, a flange-shaped member 25 is provided at the upper end of the cover member 23, which extends outward from the cover member 23 almost horizontally and then bends downward.

[0055] The first nozzle 30 ejects a processing liquid toward the substrate W to supply the processing liquid to the substrate W. In the example of FIG. 2, the first nozzle 30 is attached to the tip of a nozzle arm 32. The nozzle arm 32 extends horizontally, and its base end is connected to a nozzle support column 33. The nozzle support column 33 extends vertically and is rotatable about a vertical axis by an arm drive motor (not shown). As the nozzle support column 33 rotates, the first nozzle 30 moves in an arc between a nozzle processing position and a nozzle standby position in a space vertically above the substrate holder 20, as indicated by arrow AR34 in FIG. 2. The nozzle processing position is a position where the first nozzle 30 ejects a processing liquid onto the substrate W, e.g., a position vertically opposite the center of the substrate W. The nozzle standby position is a position where the first nozzle 30 does not eject a processing liquid onto the substrate W, e.g., a position radially outward from the periphery of the substrate W. The radial direction here refers to the radial direction about the rotation axis CX. Figure 2 shows the first nozzle 30 positioned at the nozzle standby position, and Figure 3 shows the first nozzle 30 positioned at the nozzle operating position.

[0056] 3, the first nozzle 30 is connected to a processing liquid supply source 36 via a supply pipe 34. The processing liquid supply source 36 includes a tank that stores the processing liquid. A valve 35 is provided on the supply pipe 34. When the valve 35 is opened, the processing liquid is supplied from the processing liquid supply source 36 through the supply pipe 34 to the first nozzle 30, and is then ejected from an ejection port formed in the lower end surface of the first nozzle 30. The first nozzle 30 may be configured to be supplied with a plurality of types of processing liquid (including at least pure water).

[0057] The second nozzle 60 is attached to the tip of a nozzle arm 62, and the base end of the nozzle arm 62 is connected to a nozzle support column 63. A motor for driving the arm (not shown) rotates the nozzle support column 63, causing the second nozzle 60 to move in an arc in the space vertically above the substrate holding unit 20, as shown by arrow AR64. Similarly, the third nozzle 65 is attached to the tip of a nozzle arm 67, and the base end of the nozzle arm 67 is connected to a nozzle support column 68. A motor for driving the arm (not shown) rotates the nozzle support column 68, causing the third nozzle 65 to move in an arc in the space vertically above the substrate holding unit 20, as shown by arrow AR69.

[0058] Like the first nozzle 30, the second nozzle 60 and the third nozzle 65 are each connected to a processing liquid supply source (not shown) via a supply pipe (not shown). Each supply pipe is provided with a valve, and the supply / stop of the processing liquid is switched by opening and closing the valve. The number of nozzles provided in the processing unit 1 is not limited to three, and may be one or more.

[0059] During liquid processing, the processing unit 1 rotates the substrate W using the substrate holder 20 while ejecting the processing liquid from, for example, the first nozzle 30 toward the upper surface of the substrate W. The processing liquid that has landed on the upper surface of the substrate W spreads over the upper surface of the substrate W due to centrifugal force caused by the rotation and is scattered from the periphery of the substrate W. This liquid processing allows the upper surface of the substrate W to be treated in accordance with the type of processing liquid.

[0060] The guard section 40 is a member for receiving processing liquid splashed from the periphery of the substrate W. The guard section 40 has a cylindrical shape surrounding the substrate holding section 20 and includes, for example, multiple guards that can be raised and lowered independently of each other. The guards may also be called processing cups. In the example of FIG. 3, the multiple guards are an inner guard 41, a middle guard 42, and an outer guard 43. Each of the guards 41 to 43 surrounds the periphery of the substrate holding section 20 and has a shape that is approximately rotationally symmetrical with respect to the rotation axis CX.

[0061] In the example shown in FIG. 3 , the inner guard 41 integrally includes a bottom portion 44, an inner wall portion 45, an outer wall portion 46, a first guide portion 47, and a middle wall portion 48. The bottom portion 44 has an annular shape in a plan view. The inner wall portion 45 and the outer wall portion 46 have cylindrical shapes and are respectively provided on the inner and outer peripheral edges of the bottom portion 44. The first guide portion 47 has a cylindrical tubular portion 47a provided on the bottom portion 44 between the inner wall portion 45 and the outer wall portion 46 and extending vertically upward from the upper end of the tubular portion 47a and approaching the rotation axis CX as it extends vertically upward. The middle wall portion 48 has a cylindrical shape and is provided on the bottom portion 44 between the first guide portion 47 and the outer wall portion 46.

[0062] When the guards 41 to 43 are raised (see the imaginary lines in FIG. 3), the processing liquid splashed from the periphery of the substrate W is received by the inner peripheral surface of the first guide portion 47, flows down along the inner peripheral surface, and is received in the waste groove 49. The waste groove 49 is an annular groove formed by the inner wall portion 45, the first guide portion 47, and the bottom portion 44. A liquid exhaust mechanism (not shown) is connected to the waste groove 49 to discharge the processing liquid and to forcibly exhaust the air from the inside of the waste groove 49.

[0063] The middle guard 42 integrally includes a second guide portion 52 and a cylindrical processing liquid separation wall 53 connected to the second guide portion 52. The second guide portion 52 has a cylindrical tubular portion 52a and an inclined portion 52b that approaches the rotation axis CX as it extends vertically upward from the upper end of the tubular portion 52a. The inclined portion 52b is located vertically above the inclined portion 47b of the inner guard 41 and is arranged to overlap with the inclined portion 47b in the vertical direction. The tubular portion 52a is housed in an annular inner recovery groove 50. The inner recovery groove 50 is a groove formed by the first guide portion 47, the middle wall portion 48, and the bottom portion 44.

[0064] When only the guards 42 and 43 are raised, the processing liquid from the periphery of the substrate W is received by the inner peripheral surface of the second guide portion 52 , flows down along the inner peripheral surface, and is received in the inner recovery groove 50 .

[0065] The processing liquid separation wall 53 has a cylindrical shape, and its upper end is connected to the second guide part 52. The processing liquid separation wall 53 is housed in an annular outer recovery groove 51. The outer recovery groove 51 is a groove formed by the middle wall part 48, the outer wall part 46, and the bottom part 44.

[0066] The outer guard 43 is located outside the middle guard 42 and functions as a third guide section that guides the treatment liquid to the outer recovery groove 51. The outer guard 43 integrally includes a cylindrical portion 43a and an inclined portion 43b that approaches the rotation axis CX as it extends vertically upward from the upper end of the cylindrical portion 43a. The cylindrical portion 43a is housed within the outer recovery groove 51, and the inclined portion 43b is located vertically above the inclined portion 52b and is arranged to overlap the inclined portion 52b in the vertical direction.

[0067] When only the outer guard 43 is raised, the processing liquid from the periphery of the substrate W is received by the inner peripheral surface of the outer guard 43 , flows down along the inner peripheral surface, and is received in the outer recovery groove 51 .

[0068] The inner recovery groove 50 and the outer recovery groove 51 are connected to recovery mechanisms (both not shown) for recovering the processing liquid into a recovery tank provided outside the processing unit 1.

[0069] The inner guard 41, the middle guard 42, and the outer guard 43 are formed of a resin such as a fluorine-based resin. Here, as an example, the wettability of the surfaces of the inner guard 41, the middle guard 42, and the outer guard 43 is lower than the wettability of the upper surface 21a of the spin base 21. In other words, the surfaces of the guards 41 to 43 are hydrophobic. Here, a hydrophobic surface refers to a surface whose contact angle is greater than, for example, about 45 degrees. Note that the value of the contact angle that distinguishes between a hydrophobic surface and a hydrophilic surface is not necessarily limited to 45 degrees, and can be determined appropriately by the user.

[0070] The guards 41 to 43 can be raised and lowered by a guard lifting mechanism 55. The guard lifting mechanism 55 raises and lowers the guards 41 to 43 between their respective guard processing positions and guard standby positions so that the guards 41 to 43 do not collide with each other. The guard processing position is a position where the upper edge of the target guard to be raised and lowered is above the upper surface of the substrate W, and the guard standby position is a position where the upper edge of the target guard is below the upper surface 21a of the spin base 21. The upper edge here refers to the annular portion that forms the upper opening of the target guard. In the example of FIG. 3, the guards 41 to 43 are located at the guard standby position. The guard lifting mechanism 55 includes, for example, a ball screw mechanism and a motor or an air cylinder.

[0071] The partition plate 15 is provided around the guard portion 40 to divide the inner space of the chamber 10 into upper and lower portions. The partition plate 15 may have through-holes and cutouts (not shown) that penetrate in the thickness direction, and in this embodiment, through-holes are formed to allow the nozzle support columns 33, 63, and 68 to pass through. The outer peripheral edge of the partition plate 15 is connected to the side wall 11 of the chamber 10. The inner peripheral edge of the partition plate 15 that surrounds the guard portion 40 is formed into a circular shape with a diameter larger than the outer diameter of the outer guard 43. Therefore, the partition plate 15 does not obstruct the raising and lowering of the outer guard 43.

[0072] In the example of Figure 3, an exhaust duct 18 is provided in part of the side wall 11 of the chamber 10, near the floor wall 13. The exhaust duct 18 is connected to an exhaust mechanism (not shown). Of the clean air that flows down inside the chamber 10, the air that passes between the guard part 40 and the partition plate 15 is exhausted to the outside of the apparatus through the exhaust duct 18.

[0073] The camera 70 is used to monitor the state of an object to be monitored within the chamber 10. The object to be monitored includes, for example, at least one of the substrate holder 20, the first nozzle 30, the second nozzle 60, the third nozzle 65, and the guard unit 40. The camera 70 captures an image of an imaging area including the object to be monitored, generates captured image data (hereinafter simply referred to as a captured image), and outputs the captured image to the control unit 9. The control unit 9 monitors the state of the object to be monitored based on the captured image, as will be described in detail later.

[0074] The camera 70 includes a solid-state imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor), and an optical system such as a lens. In the example of Fig. 3, the camera 70 is installed at an imaging position vertically above the substrate W held by the substrate holder 20. In the example of Fig. 3, the imaging position is set vertically above the partition plate 15 and radially outward from the guard part 40. The radial direction here refers to the radial direction with respect to the rotation axis CX.

[0075] In the example of FIG. 3, a recessed portion (hereinafter referred to as a recessed wall portion 111) for accommodating the camera 70 is formed in the side wall 11 of the chamber 10. The recessed wall portion 111 has a shape that is recessed outward relative to the other portions of the side wall 11. The camera 70 is accommodated inside the recessed wall portion 111. In the example of FIG. 3, a transparent camera guard 72 is provided in front of the camera 70 in the imaging direction. The camera guard 72 is a transparent member that is highly translucent for the wavelength of light detected by the camera 70. Therefore, the camera 70 can image the imaging region within the processing space through the camera guard 72. In other words, the camera guard 72 is provided between the camera 70 and the imaging region. The transmittance of the camera guard 72 in the detection wavelength range of the camera 70 is, for example, 60% or more, preferably 80% or more. The camera guard 72 is formed of a transparent material such as quartz glass. 3, the camera guard 72 has a plate-like shape and, together with the recessed wall portion 111 of the side wall 11, forms a space for accommodating the camera 70. The provision of the camera guard 72 makes it possible to protect the camera 70 from the processing liquid and volatile components of the processing liquid in the processing space.

[0076] The imaging area of ​​the camera 70 includes, for example, a portion of the substrate holding part 20 and the guard part 40. In the example of Fig. 3, the camera 70 captures an image of the imaging area obliquely downward from the imaging position. In other words, the imaging direction of the camera 70 is inclined vertically downward from the horizontal direction.

[0077] 3, the illumination unit 71 is provided at a position vertically above the partition plate 15. As a specific example, the illumination unit 71 is also provided inside the recessed wall portion 111. If the inside of the chamber 10 is a darkroom, the control unit 9 may control the illumination unit 71 so that the illumination unit 71 illuminates the imaging area when the camera 70 captures an image. Illumination light from the illumination unit 71 passes through the camera guard 72 and is irradiated into the processing space.

[0078] The hardware configuration of the control unit 9 is the same as that of a general computer. That is, the control unit 9 is configured to include a data processing unit such as a CPU that performs various arithmetic processing, a non-temporary storage unit such as a ROM (Read Only Memory) that is a read-only memory that stores a basic program, and a temporary storage unit such as a RAM (Random Access Memory) that is a readable and writable memory that stores various information. When the CPU of the control unit 9 executes a predetermined processing program, the control unit 9 controls each operating mechanism of the substrate processing apparatus 100, and processing in the substrate processing apparatus 100 progresses. Note that the control unit 9 may be realized by a dedicated hardware circuit that does not require software to realize its functions.

[0079] 4 is a functional block diagram schematically showing an example of the internal configuration of the control unit 9. As shown in FIG. 4, the control unit 9 includes a process control unit 91 and a monitoring processing unit 92.

[0080] The process control unit 91 controls each component of the processing unit 1. More specifically, the process control unit 91 controls the spin motor 22, various valves such as the valve 35, arm drive motors that rotate each of the nozzle support columns 33, 63, and 68, the guard lifting mechanism 55, the fan filter unit 14, and the camera 70. The process control unit 91 controls these components in accordance with a predetermined procedure, thereby enabling the processing unit 1 to process the substrate W.

[0081] <An example of substrate processing flow> Here, an example of a specific flow of processing the substrate W will be briefly described. Fig. 5 is a flowchart showing an example of the flow of substrate processing. Initially, the guards 41 to 43 each stop at a guard standby position, and the nozzles 30, 60, 65 each stop at a nozzle standby position. Note that although the control unit 9 controls each component to perform a predetermined operation described below, the following description will focus on each component itself as the subject of the operation.

[0082] First, the main transport robot 103 loads an unprocessed substrate W into the processing unit 1, and the substrate holding part 20 holds the substrate W (step S1: loading and holding step). Initially, the guard part 40 is stopped at the guard standby position, so that collision between the hand of the main transport robot 103 and the guard part 40 can be avoided when the substrate W is loaded. When the substrate W is handed over to the substrate holding part 20, the multiple chuck pins 26 move to their respective holding positions, thereby holding the substrate W.

[0083] Next, the spin motor 22 starts rotating the substrate W (step S2: rotation start step). Specifically, the spin motor 22 rotates the spin base 21, thereby rotating the substrate W held by the substrate holder 20.

[0084] Next, the processing unit 1 performs various liquid treatments on the substrate W (step S3: liquid treatment step). For example, the processing unit 1 performs chemical liquid treatment. First, the guard lifting mechanism 55 raises one of the guards 41 to 43 that corresponds to the chemical liquid to the guard treatment position. The guard for the chemical liquid is not particularly limited, but may be, for example, the outer guard 43. In this case, the guard lifting mechanism 55 stops the inner guard 41 and the middle guard 42 at their respective guard standby positions, and raises the outer guard 43 to the guard treatment position.

[0085] Next, the processing unit 1 supplies the chemical liquid to the substrate W. Here, it is assumed that the first nozzle 30 supplies the processing liquid. Specifically, the arm drive motor moves the first nozzle 30 to the nozzle processing position, and the valve 35 opens to discharge the chemical liquid from the first nozzle 30 toward the substrate W. As a result, the chemical liquid spreads over the upper surface of the rotating substrate W and splashes from the periphery of the substrate W. At this time, the chemical liquid acts on the upper surface of the substrate W, and processing according to the chemical liquid (e.g., cleaning processing) is performed on the substrate W. The chemical liquid splashed from the periphery of the substrate W is received by the inner circumferential surface of the guard part 40 (e.g., outer guard 43). When the chemical liquid processing has been sufficiently performed, the processing unit 1 stops supplying the chemical liquid.

[0086] Next, the processing unit 1 performs a rinse process on the substrate W. The guard lifting mechanism 55 adjusts the lifted state of the guard part 40 as necessary. That is, if the guard for the rinse liquid is different from the guard for the chemical liquid, the guard lifting mechanism 55 moves the guard corresponding to the rinse liquid among the guards 41 to 43 to the guard processing position. The guard for the rinse liquid is not particularly limited, but may be the inner guard 41. In this case, the guard lifting mechanism 55 lifts the guards 41 to 43 to their respective guard processing positions.

[0087] Next, the first nozzle 30 ejects a rinse liquid toward the upper surface of the substrate W. The rinse liquid is, for example, pure water. The rinse liquid spreads over the upper surface of the rotating substrate W, washing away the chemical liquid on the substrate W, and splashes from the periphery of the substrate W. The processing liquid (mainly the rinse liquid) splashed from the periphery of the substrate W is received by the inner circumferential surface of the guard portion 40 (for example, the inner guard 41). When the rinsing process has been sufficiently performed, the processing unit 1 stops supplying the rinse liquid.

[0088] If necessary, the processing unit 1 may supply a volatile rinse liquid such as highly volatile isopropyl alcohol to the substrate W. If the guard for the volatile rinse liquid is different from the guard for the rinse liquid described above, the guard lifting mechanism 55 may move the guard corresponding to the volatile rinse liquid among the guards 41 to 43 to the guard processing position. When the rinse process is completed, the first nozzle 30 moves to the nozzle standby position.

[0089] Next, the processing unit 1 performs a drying process on the substrate W (step S4: drying step). For example, the spin motor 22 increases the rotation speed of the substrate W to dry the substrate W (so-called spin drying). Even during the drying process, the processing liquid splashed from the periphery of the substrate W is received by the inner peripheral surface of the guard part 40. When the drying process has been sufficiently completed, the spin motor 22 stops the rotation of the substrate W.

[0090] Next, the guard lifting mechanism 55 lowers the guard portion 40 to the guard standby position (step S5: guard lowering step). That is, the guard lifting mechanism 55 lowers the guards 41 to 43 to their respective guard standby positions.

[0091] Next, the substrate holder 20 releases its hold on the substrate W, and the main transport robot 103 removes the processed substrate W from the processing unit 1 (step S6: hold release and unloading process). When the substrate W is unloaded, the guard part 40 is stopped at the guard standby position, so that collision between the hand of the main transport robot 103 and the guard part 40 can be avoided.

[0092] As described above, the substrate W is processed by the appropriate operation of various components in the processing unit 1. For example, the substrate holder 20 holds or releases the substrate W. The first nozzle 30 moves between the nozzle processing position and the nozzle standby position, and ejects the processing liquid toward the substrate W at the nozzle processing position. The guards 41 to 43 of the guard section 40 move to height positions according to each process.

[0093] <Monitoring process> The above components operate properly to process the substrate W. Conversely, if at least one of the above components does not operate properly, the processing of the substrate W may be impaired. Therefore, the processing unit 1 monitors at least one of the above components as an object to be monitored, and monitors the state of the object to be monitored.

[0094] As is clear from the substrate processing operation described above, in the liquid processing step, the processing liquid is discharged toward the rotating substrate W. Therefore, the processing liquid splashes onto the substrate W. Although this processing liquid is mostly received by the guard portion 40, there is a possibility that the processing liquid will bounce off the guard portion 40 and adhere to other components, and there is also a possibility that the processing liquid will bounce off the upper surface of the substrate W and adhere to other components (for example, the outer peripheral surface of the outer guard 43). If droplets adhere, they will also be included in the captured image, and there is a risk that these droplets will reduce the accuracy of monitoring the object being monitored.

[0095] In the following description, the outer guard 43 is used as an example of a monitored object. FIG. 6 is a diagram schematically illustrating an example of a captured image generated by the camera 70 capturing an image of the imaging area. The captured image in FIG. 6 includes the entire top surface of the substrate W held by the substrate holder 20. In other words, the camera 70 is provided at a position where the entire substrate W is included in the imaging area. In the example of FIG. 6, the substrate holder 20 holds the substrate W, and the outer guard 43 is stopped at the guard standby position. Since the camera 70 captures an image of the imaging area obliquely downward, the substrate W, which is circular in plan view, has an elliptical shape in the captured image. Similarly, the upper periphery of the outer guard 43, which is circular in plan view, has a shape that follows an ellipse in the captured image. The example of FIG. 6 also illustrates a virtual ellipse E1 along which the upper periphery of the outer guard 43 follows.

[0096] Such a captured image can be obtained, for example, by the camera 70 capturing an image of the capture area with the outer guard 43 lowered to the guard standby position in the guard lowering process (step S5). If the outer guard 43 can be properly lowered to the guard standby position in the guard lowering process, it is possible to properly avoid a collision between the hand of the main transport robot 103 and the guard unit 40 in the subsequent holding release carry-out process (step S6). On the other hand, if the outer guard 43 cannot be lowered to the guard standby position due to an abnormality, a collision between the hand of the main transport robot 103 and the guard unit 40 may occur in the holding release carry-out process. Therefore, the monitoring processing unit 92 monitors the position of the outer guard 43 based on the captured image.

[0097] 6, droplets L1 are attached to the upper surface 21a of the spin base 21 and the outer peripheral surface of the outer guard 43. For example, in the liquid processing step (step S3) before the guard lowering step, processing liquid adheres to the upper surface 21a of the spin base 21 and the outer peripheral surface of the outer guard 43, and thus droplets L1 remain on the upper surface 21a of the spin base 21 and the outer peripheral surface of the outer guard 43 even during the guard lowering step. Here, since the upper surface 21a of the spin base 21 has high wettability, droplets L1 are located in a relatively thin, spread state on the upper surface 21a of the spin base 21. Here, since the outer peripheral surface of the outer guard 43 has lower wettability than the upper surface 21a, droplets L1 are located in a relatively thick, raised state on the outer peripheral surface of the outer guard 43.

[0098] If the liquid droplets L1 are present on or around the outer guard 43, which is the object to be monitored, the accuracy of monitoring based on the captured image containing the liquid droplets L1 may decrease.

[0099] Therefore, as will be described in detail later, when the captured image contains the droplet L1, the monitoring processing unit 92 generates removed image data by removing at least a portion of the droplet region RL1 representing the droplet L1 from the captured image, and monitors the state of the monitoring object based on the removed image data. In other words, as will be described in detail later, the monitoring processing unit 92 monitors the state of the monitoring object using the region of the captured image excluding at least a portion of the droplet region RL1.

[0100] In explaining this monitoring process, an example of a monitoring algorithm for the outer guard 43 when no droplet L1 is present will first be outlined. In the example of FIG. 6, a guard determination region R1 is set in the captured image. The guard determination region R1 is an area used to monitor the outer guard 43 and includes at least a portion of the outer guard 43. In the example of FIG. 6, the guard determination region R1 is set to an area including a portion of the upper periphery of the outer guard 43 when it is normally positioned at the guard standby position. In the example of FIG. 6, multiple guard determination regions R11 and R12 (two in the figure) are set as the guard determination region R1. Each of the guard determination regions R11 and R12 is set to include a portion of the upper periphery of the outer guard 43 below the major axis LA1 of the ellipse E1 in the captured image. Furthermore, the guard determination regions R11 and R12 are set on opposite sides of each other with respect to the minor axis SA1 of the ellipse E1.

[0101] The upper region of each of the guard determination regions R11 and R12 includes a portion of the upper surface 21a of the spin base 21, and the lower region of each of the guard determination regions R11 and R12 includes a portion of the outer peripheral surface of the outer guard 43. In the example of Fig. 6, the guard determination region R11 does not include the liquid droplet L1, and the guard determination region R12 includes the liquid droplet L1.

[0102] Here, a reference image M1 for determining the guard position is stored in advance in the storage unit 94. The reference image M1 is an image in which no droplets L1 are attached and the outer guard 43 is normally positioned at the guard standby position. Such a reference image M1 is generated, for example, based on an image captured by the camera 70 when no droplets L1 are attached and the outer guard 43 is normally positioned at the guard standby position. In FIG. 6, reference images M11 and M12 corresponding to the guard determination regions R11 and R12, respectively, are shown as the reference image M1. The reference image M11 is an image of the same region as the guard determination region R11, and the reference image M12 is an image of the same region as the guard determination region R12.

[0103] Here, we will focus on the guard determination region R11, which does not contain the droplet L1, and outline an example of a monitoring algorithm for the outer guard 43 when the droplet L1 is not present. When the outer guard 43 is positioned correctly at the guard standby position, the similarity between the guard determination region R11 and the reference image M11 is high (see FIG. 6). On the other hand, when the outer guard 43 is positioned higher than the guard standby position in the captured image, the similarity between the guard determination region R11 and the reference image M11 decreases. Conversely, when the similarity is high, it can be determined that the outer guard 43 is positioned correctly at the guard standby position, and when the similarity is low, it can be determined that an abnormality has occurred in the outer guard 43.

[0104] Therefore, when the captured image does not contain the droplet L1, the monitoring processor 92 calculates the similarity between the guard determination region R11 and the reference image M11, and the similarity between the guard determination region R12 and the reference image M12, as described below. When both similarities are equal to or greater than a predetermined guard threshold, the monitoring processor 92 determines that the outer guard 43 is normally positioned at the guard standby position, and when at least one of the similarities is less than the guard threshold, the monitoring processor 92 determines that an abnormality has occurred in the outer guard 43.

[0105] On the other hand, if the liquid droplet L1 is included in the captured image, the similarity may decrease even if the outer guard 43 is properly stopped at the guard standby position. For example, the liquid droplet L1 is included in the guard determination region R12 in FIG. 6. In this case, even if the outer guard 43 is properly positioned at the guard standby position, the similarity between the guard determination region R12 and the reference image M12 decreases. This is because the liquid droplet L1 is included in the guard determination region R12, but the liquid droplet L1 is not included in the reference image M12. In other words, this difference causes a decrease in the similarity.

[0106] Therefore, in this embodiment, when the captured image contains a droplet L1, the monitoring processing unit 92 monitors the state of the object to be monitored using an area of ​​the captured image excluding at least a portion of the droplet area RL1 that indicates the droplet L1, as described below.

[0107] 7 is a flowchart showing an example of monitoring processing by the processing unit 1. As illustrated in FIG. 7, the camera 70 captures an image of an imaging area including the outer guard 43, which is an example of an object to be monitored, to generate a captured image, and outputs the captured image to the control unit 9 (step S11: imaging step). Here, the imaging step is performed after the guard lowering step (step S5) is completed. That is, the camera 70 captures an image of the imaging area after the control unit 9 outputs a control signal to the guard lifting / lowering mechanism 55. If the guard lifting / lowering mechanism 55 can normally move the guards 41 to 43 to their respective guard standby positions, the captured image will include the outer guard 43 normally positioned at the guard standby position (see FIG. 6).

[0108] Next, the monitoring processing unit 92 determines whether or not the captured image obtained in the imaging step includes the droplet L1 (step S12: droplet determination step). Here, the monitoring processing unit 92 monitors the state of the outer guard 43 based on the guard determination areas R11, R12, and may therefore determine whether or not the droplet L1 is included in the guard determination areas R11, R12. Hereinafter, the monitoring processing unit 92 determines whether or not the droplet L1 exists in the guard determination areas R11, R12. The monitoring processing unit 92 may determine whether or not the droplet L1 exists by, for example, performing the image processing described below on the captured image.

[0109] First, the monitoring processor 92 performs edge detection processing such as the Canny method on the captured image to generate an edge image. This edge image is, for example, a binary image, where, for example, pixels that indicate edges have large pixel values ​​and pixels that do not indicate edges have small pixel values. If the captured image does not include the droplet L1, the edge image does not include the edge of the droplet L1, but includes the edge of an object such as the substrate W (hereinafter referred to as the background edge). On the other hand, if the captured image includes the droplet L1, the edge image includes both the edge of the droplet L1 and the background edge.

[0110] Next, the monitoring processing unit 92 obtains a difference image between the edge image and the edge background image. The edge background image is an edge image that does not include the edge of the droplet L1 but includes the background edge. The edge background image is set in advance and stored, for example, in the memory unit 94. Such an edge background image is obtained, for example, by performing edge detection on an image captured by the camera 70 when the substrate holder 20 holds the substrate W and the outer guard 43 is normally positioned at the guard standby position, without including the droplet L1. In the difference image between the edge image and the edge background image, the background edge is largely canceled out, leaving the edge of the droplet L1.

[0111] Since the edge of the droplet L1 forms a closed curve, the presence or absence of the droplet L1 is determined based on the presence or absence of a closed curve edge in the differential image. That is, the monitoring processor 92 determines whether or not an edge forming a closed curve exists in the differential image. Specifically, the monitoring processor 92 performs contour tracing on the differential image to label each edge and obtain the curve shape of the edge. The monitoring processor 92 determines whether or not an edge forming a closed curve exists, and if an edge forming a closed curve exists, it determines that the droplet L1 is included. If an edge forming a closed curve does not exist, it determines that the droplet L1 is not included. That is, the area surrounded by the closed curve edges is the droplet area RL1. When the monitoring processor 92 detects multiple closed curve edges, it determines that the area surrounded by each edge is the droplet area RL1.

[0112] Next, the monitoring processor 92 determines whether at least a portion of the droplet region RL1 is included in at least one of the guard determination regions R11, R12. When at least a portion of the droplet region RL1 is included in either the guard determination region R11, R12, the monitoring processor 92 determines that the droplet L1 is included in the guard determination region R1.

[0113] The monitoring processing unit 92 may determine the presence or absence of the droplet L1 in the captured image using an algorithm other than the above algorithm. For example, the monitoring processing unit 92 may use a trained model to determine whether the captured image contains the droplet L1. Such a trained model is generated by machine learning, such as deep learning. The trained model classifies the captured image into a category that includes the droplet L1 and a category that does not include the droplet L1. The trained model is generated by the learning model performing machine learning on a plurality of training image data that includes the droplet L1, a plurality of training image data that does not include the droplet L1, and a plurality of training data that includes the correct category (label) for the training image data.

[0114] Next, the monitoring processing unit 92 monitors the state of the outer guard 43 based on the captured image using an algorithm according to the result of the determination of the presence or absence of the liquid droplet L1 (step S13: monitoring step).

[0115] 8 is a flowchart showing a specific example of the monitoring process. As described above, the monitoring processor 92 determines whether or not the captured image (here, the guard determination region R1) contains the liquid droplet L1 (step S131). If the liquid droplet L1 is not contained, the monitoring processor 92 monitors the outer guard 43 by comparing the guard determination region R1 of the captured image with the reference image M1 (step S132).

[0116] Specifically, the monitoring processing unit 92 calculates the similarity between the guard determination region R11 and the reference image M11, and the similarity between the guard determination region R12 and the reference image M12, and compares each similarity with a predetermined guard threshold. The similarity is not particularly limited, and may be, for example, a known similarity such as the sum of squared differences of pixel values, the sum of absolute differences of pixel values, normalized cross-correlation, or zero-mean normalized cross-correlation. The guard threshold is set in advance by experiment or simulation and stored in, for example, the storage unit 94.

[0117] The monitoring processor 92 determines that the outer guard 43 is normally positioned at the guard standby position when both of the similarities are equal to or greater than the guard threshold value, and determines that an abnormality has occurred with the outer guard 43 when at least one of the similarities is less than the guard threshold value. When it determines that an abnormality has occurred, the process controller 91 may appropriately suspend the processing of the substrate W. For example, the main transport robot 103 may suspend the removal of the substrate W. This makes it possible to avoid a collision between the main transport robot 103 and the outer guard 43. The process controller 91 may also cause a notification unit, such as a display (not shown), to notify the abnormality. This allows an operator to recognize the abnormality.

[0118] On the other hand, if it is determined in step S131 that the droplet L1 is present, the monitoring processor 92 monitors the state of the outer guard 43 using an area of ​​the captured image excluding at least a portion of the droplet region RL1 representing the droplet L1. As a specific example, the monitoring processor 92 deletes the droplet region RL1 from the captured image to generate removed image data (hereinafter referred to as the removed image) (step S133: droplet deletion process). Deleting the area here includes setting the pixel value of each pixel within the area to a specified value. For example, the monitoring processor 92 sets the pixel values ​​of all pixels belonging to the droplet region RL1 in the captured image to zero.

[0119] Fig. 9 is a diagram showing an example of a droplet removal process performed on a captured image and a reference image. In the example of Fig. 6, the guard determination region R11 does not contain the droplet L1, but the guard determination region R12 contains the droplet L1. Therefore, in the example of Fig. 9, the guard determination region R12 and the reference image M12 are shown as targets for droplet removal.

[0120] The monitoring processor 92 deletes the droplet region RL1 from within the guard determination region R12 to generate a removed image DR12. In the example of FIG. 9, the deleted region is indicated by blackening in the removed image DR12. The monitoring processor 92 also deletes the same region as the droplet region RL1 from the reference image M12 to generate removed reference image data (hereinafter referred to as the removed reference image) DM12. In this removed reference image DM12, the pixel values ​​of the pixels in the same region as the droplet region RL1 are set to the specified value (e.g., zero).

[0121] In the example of FIG. 6, the guard determination region R11 does not include the liquid droplet L1, so the liquid droplet region is not removed from the guard determination region R11 and the reference image M11.

[0122] Next, the monitoring processor 92 monitors the position of the outer guard 43 based on the captured image after the deletion (step S134). More specifically, the monitoring processor 92 monitors the position of the outer guard 43 based on a comparison between the guard determination region R11 and the reference image M11 and a comparison between the removed image DR12 and the removed reference image DM12. For example, the monitoring processor 92 first calculates the similarity between the guard determination region R11 and the reference image M11 and the similarity between the removed image DR12 and the removed reference image DM12. Next, the monitoring processor 92 determines whether both similarities are equal to or greater than a predetermined guard threshold. If both similarities are equal to or greater than the guard threshold, the monitoring processor 92 determines that the outer guard 43 is normally positioned at the guard standby position. If at least one of the similarities is less than the guard threshold, the monitoring processor 92 determines that an abnormality has occurred with the outer guard 43.

[0123] As described above, when the captured image contains the liquid droplet L1, the monitoring processor 92 monitors the state of the monitored object using the captured image excluding the liquid droplet region RL1. In the example described above, the monitoring processor 92 monitors the outer guard 43 based on a comparison between a removed image DR12, in which the liquid droplet region RL1 is removed from the guard determination region R12, and a removed reference image DM12, in which the liquid droplet region RL1 is removed from the reference image M12. Because pixel values ​​within the liquid droplet region RL1 are not used in the comparison between the removed image DR12 and the removed reference image DM12, the liquid droplet L1 is less likely to affect the similarity, which is the comparison result. In other words, the monitoring processor 92 can suppress the influence of the liquid droplet and monitor the state of the monitored object with higher accuracy.

[0124] <Second embodiment> An example of the configuration of the substrate processing apparatus 100 according to the second embodiment is similar to that of the first embodiment. However, in the second embodiment, the control unit 9 changes the removal range of the droplet region RL1 depending on the wettability of the surface to which the droplet L1 is attached. Here, the upper surface 21a of the spin base 21 is a hydrophilic surface with high wettability, and the outer peripheral surface of the outer guard 43 is a hydrophobic surface with lower wettability than the upper surface 21a.

[0125] FIG. 10 is a cross-sectional view schematically illustrating an example of a droplet L1 on the upper surface 21a of the spin base 21 and the outer peripheral surface of the outer guard 43. Because the outer peripheral surface of the outer guard 43 has low wettability, the droplet L1 is positioned on the outer peripheral surface of the outer guard 43 in a thick, raised state due to surface tension. The droplet L1 is colorless and transparent. In this case, the raised droplet L1 functions as a lens. As a result, the image of the outer peripheral surface of the outer guard 43 viewed through the droplet L1 is distorted. Therefore, if the droplet region RL1 representing the droplet L1 attached to a surface with low wettability is used to monitor the outer guard 43, the monitoring accuracy may be reduced. Therefore, it is desirable to completely remove the droplet region RL1 corresponding to the surface with low wettability.

[0126] In contrast, the wettability of the top surface 21a of the spin base 21 is higher than that of the outer peripheral surface of the outer guard 43, so the droplet L1 spreads thinly on the top surface 21a, as illustrated in FIG. 10. Although the outline portion L1a of such a droplet L1 in a planar view can function as a lens, the liquid surface of the inner portion L1b inside the outline portion L1a is relatively flat, so the inner portion L1b does not easily function as a lens. Therefore, although distortion may occur in the image of the top surface 21a of the spin base 21 viewed through the outline portion L1a, there is almost no distortion in the image of the top surface 21a of the spin base 21 viewed through the inner portion L1b. Therefore, for the droplet region RL1 representing the droplet L1 attached to a highly wettable surface, it is desirable to delete only the outline region RL1a (see also FIG. 12).

[0127] Therefore, in the second embodiment, the control unit 9 varies the removal range of the droplet region RL1 depending on the wettability of the surface to which the droplet L1 is attached.

[0128] Here, as an example, region data is recorded in advance in the storage unit 94. The region data is data indicating a first region and a second region corresponding to the surfaces of different objects in the captured image. The first region is a region corresponding to a hydrophilic surface with high wettability, and the second region is a region corresponding to a hydrophobic surface with low wettability. As a more specific example, the first region includes the upper surface 21a of the spin base 21, and the second region includes the outer peripheral surface of the outer guard 43. The region data may be composed of data indicating a pixel group belonging to the first region and data indicating a pixel group belonging to the second region. Such region data may be set in advance by an operator. Hereinafter, the first region will also be referred to as a hydrophilic region, and the second region will also be referred to as a hydrophobic region.

[0129] An example of the monitoring process according to the second embodiment is similar to the flowcharts of Figures 7 and 8. However, a specific example of the droplet removal process in step S133 differs from that of the first embodiment. Figure 11 is a flowchart showing a specific example of the droplet removal process according to the second embodiment.

[0130] First, the monitoring processor 92 determines whether a certain droplet region RL1 is included in a hydrophilic region or a hydrophobic region (step S21). In other words, the monitoring processor 92 determines whether the surface to which the droplet L1 is attached is a hydrophilic surface or a hydrophobic surface. As a more specific example, the monitoring processor 92 reads region data from the storage unit 94 and makes a determination by comparing the droplet region RL1 with each of the hydrophilic and hydrophobic regions indicated by the region data. When the droplet region RL1 is included in a hydrophilic region, the monitoring processor 92 determines the outline region RL1a of the droplet region RL1 as the deletion range (step S22). Here, as an example, the deletion range of the droplet region RL1 included in the upper surface 21a of the spin base 21 is determined to be the outline region RL1a (see also FIG. 12). The width of the outline region RLa can be determined in advance, for example, by simulation or experiment. On the other hand, when the droplet region RL1 is included in a hydrophobic region, the monitoring processor 92 determines the entire droplet region RL1 as the removal range (step S23). Here, as an example, the removal range for the droplet region RL1 included in the outer peripheral surface of the outer guard 43 is determined to be the entire droplet region RL1 (see also FIG. 12).

[0131] Next, the monitoring processing unit 92 determines whether or not the removal ranges have been determined for all droplet regions RL1 included in the guard determination region R1 in the captured image (step S24).

[0132] If the removal ranges of all droplet regions RL1 have not been determined, the monitoring processing unit 92 performs steps S21 to S24 for the next droplet region RL1.

[0133] When the removal ranges of all droplet regions RL1 have been determined, the monitoring processing unit 92 removes the removal ranges of all droplet regions RL1 from the captured image to generate removed image data (step S25). The monitoring processing unit 92 also removes the same areas as the removal ranges of all droplet regions RL1 from the reference image M1.

[0134] Fig. 12 is a diagram showing an example of a droplet removal process performed on a captured image and a reference image. In the example of Fig. 6, the guard determination region R11 does not contain the droplet L1, but the guard determination region R12 contains the droplet L1. Therefore, in the example of Fig. 12, the guard determination region R12 and the reference image M12 are shown as targets for droplet removal.

[0135] Within the guard determination region R12, the top surface 21a of the spin base 21 corresponds to a hydrophilic region with high wettability, so the outline region RL1a of the droplet region RL1 is deleted in the hydrophilic region of the removed image DR12. Meanwhile, the inner region RL1b of the droplet region RL1 remains untouched. Although this inner region RL1b contains droplet L1, the droplet L1 in the inner region RL1b does not function well as a lens, so the image of the top surface 21a of the spin base 21 viewed through the droplet L1 is not distorted much, and the top surface 21a is reflected as is.

[0136] The outer peripheral surface of the outer guard 43 in the guard determination region R12 corresponds to a hydrophobic region with low wettability, and therefore the entire droplet region RL1 is removed from the hydrophobic region of the removed image DR12.

[0137] In the removal reference image DM12, an area identical to the outline area RL1a of the droplet area RL1 is removed from the hydrophilic area, and an area identical to the entire droplet area RL1 is removed from the hydrophobic area.

[0138] Next, similarly to the first embodiment, the monitoring processor 92 monitors the position of the outer guard 43 based on the captured image after removal (step S134). Specifically, the monitoring processor 92 monitors the position of the outer guard 43 by comparing the guard determination region R11 with the reference image M11 and by comparing the removed image DR12 with the removed reference image DM12.

[0139] As described above, for the droplet region RL1 indicating the droplet L1 adhering to the hydrophilic surface, the monitoring processor 92 monitors the outer guard 43 using the captured image (more specifically, the guard determination region R1) excluding the outline region RL1a. Conversely, the monitoring processor 92 also monitors the position of the outer guard 43 using the inner region RL1b of the droplet region RL1. In other words, the inner region RL1b, where the surface of the colorless and transparent droplet L1 is flat, reflects the outer surface of the outer guard 43 almost as it is. Therefore, the monitoring processor 92 also monitors the position of the outer guard 43 using the inner region RL1b. Therefore, the position of the outer guard 43 can be monitored based on more appropriate pixel values ​​within the guard determination region R1, thereby enabling more accurate monitoring of the position of the outer guard 43. More specifically, the similarity between the removed image DR12 and the removed reference image DM12 can be calculated by comparing more appropriate pixel values. This allows the similarity to be calculated more accurately, and ultimately enables more accurate monitoring of the position of the outer guard 43.

[0140] On the other hand, for the droplet region RL1 indicating the droplet L1 adhering to the hydrophobic surface with low wettability, the monitoring processor 92 monitors the position of the outer guard 43 using an area of ​​the captured image (more specifically, the guard determination region R1) excluding the entire droplet region RL1. This makes it possible to avoid a decrease in similarity due to the droplet region RL1, where the image of the outer peripheral surface of the outer guard 43 is distorted, and allows the similarity to be calculated with higher accuracy. Therefore, the position of the outer guard 43 can be monitored with higher accuracy.

[0141] Moreover, in the above example, the monitoring processor 92 determines the wettability of the surface based on the region data, which allows the monitoring processor 92 to determine the wettability of the surface with simpler processing.

[0142] <Changes over time> The wettability of the upper surface 21a of the spin base 21 and the wettability of the outer peripheral surface of the outer guard 43 may change over time. For example, the wettability may gradually change due to the adhesion of the processing liquid to the upper surface 21a of the spin base 21 and the outer peripheral surface of the outer guard 43. The wettability may increase or decrease depending on the type of processing liquid, the material of the upper surface 21a of the spin base 21, and the material of the outer peripheral surface of the outer guard 43.

[0143] Such a change in wettability over time can be measured in advance by experiment or simulation, and the monitoring processor 92 may update the region data in accordance with the change over time.

[0144] 13 is a flowchart showing an example of updating of area data. First, the monitoring processor 92 acquires a time-related value such as the operating time of the substrate processing apparatus 100 (step S31). The operating time here refers to the cumulative time that the substrate processing apparatus 100 has been operating. Such cumulative time is measured, for example, using a known timer circuit. The time-related value may include at least one of the elapsed time and the number of processed substrates W in addition to the operating time of the substrate processing apparatus 100. The elapsed time here refers to the time that has elapsed regardless of whether the substrate processing apparatus 100 is operating. The number of processed substrates W refers to the number of substrates W that have been processed by the substrate processing apparatus 100. For example, the controller 9 can measure the number of processed substrates W by incrementing the number of processed substrates W each time the indexer robot 102 takes out a substrate W.

[0145] Next, the monitoring processing unit 92 updates the region data based on the time-related value. Specifically, the monitoring processing unit 92 determines whether the time-related value is equal to or greater than a predetermined time threshold value (step S32). The time threshold value is set in advance, for example, by simulation or experiment, and stored in the storage unit 94. If the time-related value is less than the time threshold value, the monitoring processing unit 92 executes step S31 again.

[0146] When the aging-related value is equal to or greater than a predetermined aging threshold, the monitoring processor 92 updates the region data (step S33). As a more specific example, when the wettability of the outer peripheral surface of the outer guard 43 increases over time, the monitoring processor 92 is configured to update the region data as follows. That is, when the aging-related value is equal to or greater than the aging threshold, the monitoring processor 92 changes the region representing the outer peripheral surface of the outer guard 43 from a hydrophobic region to a hydrophilic region in the region data. On the other hand, when the wettability of the upper surface 21a of the spin base 21 decreases over time, the monitoring processor 92 is configured to update the region data as follows. That is, when the aging-related value is equal to or greater than the aging threshold, the monitoring processor 92 changes the region representing the upper surface 21a of the spin base 21 from a hydrophilic region to a hydrophobic region in the region data. Note that different values ​​may be used as the aging threshold depending on the surface of each object in the captured image.

[0147] As described above, the monitoring processor 92 updates the region data in accordance with the change over time in the wettability of the surface of the object included in the image capture region. This allows the monitoring processor 92 to appropriately determine the removal range of the droplet region RL1 in response to the change over time.

[0148] <Wettability determination> In the above example, the area data indicating the wettability of the surface of the object within the image capture area is set in advance and stored in the storage unit 94. However, this is not necessarily limited to this. The monitoring processing unit 92 may determine the level of wettability based on the captured image, as described below.

[0149] As can be seen from Figure 10, droplet L1 on a surface with low wettability is positioned in a thick, raised state. On a surface with low wettability, the spherical droplet L1 does not spread out much, and when a large amount of liquid is supplied to the surface, multiple droplets L1 are present in a fine, separated state. In other words, the size of droplet L1 in a planar view on a surface with low wettability is relatively small. On the other hand, droplet L1 on a surface with high wettability spreads out thinly and widely, so its size in a planar view is relatively large.

[0150] Therefore, the monitoring processing unit 92 may obtain the size of the droplet L1 based on the captured image and determine the wettability of the surface to which the droplet L1 is attached based on the size. In other words, the monitoring processing unit 92 may determine the removal range of the droplet region RL1 based on the size of the droplet L1.

[0151] 14 is a flowchart showing an example of a method for determining a deletion range based on size. First, the monitoring processor 92 determines the size of the droplet region RL1 based on the captured image (step S41). Specifically, the monitoring processor 92 determines the number of pixels that make up the droplet region RL1 as the size of the droplet region RL1.

[0152] Next, the monitoring processing unit 92 determines whether the size of the droplet region RL1 is equal to or larger than a predetermined wettability threshold (corresponding to a first threshold) (step S42). The wettability threshold is, for example, set in advance and stored in the storage unit 94.

[0153] On the other hand, when the size of the droplet region RL1 is equal to or larger than the wettability threshold, the monitoring processing unit 92 determines the deletion range of the droplet region RL1 to be the outline region RL1a (step S43). In other words, when the size is equal to or larger than the wettability threshold, the droplet region RL1 is considered to be within a highly wettable hydrophilic region, and therefore the deletion range is determined to be the outline region RL1a.

[0154] When the size of the droplet region RL1 is less than the wettability threshold, the monitoring processing unit 92 determines the removal range of the droplet region RL1 to be the entire droplet region RL1 (step S44). In other words, when the size is less than the wettability threshold, the droplet region RL1 is considered to be within a hydrophobic region with low wettability, so the removal range is determined to be the entire droplet region RL1.

[0155] This allows the monitoring processing unit 92 to automatically determine the removal range of the droplet region RL1 based on the captured image. Since the operator does not need to set the surface wettability in advance, it is possible to more easily set the region data in advance.

[0156] Since the position of each object in the captured image can be determined to some extent in advance, region data indicating the region of each object in the captured image may be set in advance. This region data sets the region of each object in the captured image, but does not include information about the wettability of that region. Explaining this based on the example of FIG. 6, the region data includes a region indicating the top surface 21a of the spin base 21 and a region indicating the outer peripheral surface of the outer guard 43. However, the region data does not include information about the wettability of these regions.

[0157] When the size of at least one of the multiple droplet regions RL1 on the surface of an object (e.g., the upper surface 21a of the spin base 21) indicated by the region data is equal to or greater than the wettability threshold, the monitoring processing unit 92 may determine the removal range of the multiple droplet regions RL1 on that surface to be the outline region RL1a.When the size of all of the multiple droplet regions RL1 on the surface of another object (e.g., the outer peripheral surface of the outer guard 43) indicated by the region data is less than the wettability threshold, the monitoring processing unit 92 may determine the removal range of the multiple droplet regions RL1 on that surface to be the entirety of each droplet region RL1.

[0158] In the above example, the monitoring processor 92 determines the wettability based on the size of the droplet region RL1, so the monitoring processor 92 can determine the wettability with a relatively light processing load.

[0159] However, the method for determining the deletion range is not necessarily limited to the above example. For example, the monitoring processing unit 92 may use a trained model to determine the wettability of the surface of each object based on the captured image. The trained model is generated by training the model using, for example, multiple training data sets having multiple captured images (training image data) including droplets L1 on the upper surface 21a of the spin base 21 and their labels (correct categories for wettability), and multiple training data sets having multiple captured images including droplets L1 on the outer peripheral surface of the outer guard 43 and their labels. By using the trained model, wettability can be determined with high accuracy.

[0160] FIG. 15 is a flowchart showing an example of a method for determining a deletion range using a trained model. The monitoring processor 92 performs classification processing using the trained model (step S51). For example, the monitoring processor 92 performs classification processing for each surface of an object in a captured image. For example, when a droplet region RL1 is included in an area corresponding to the upper surface 21a of the spin base 21, the monitoring processor 92 classifies the area into either a hydrophilic category or a hydrophobic category using the trained model. Similarly, when a droplet region RL1 is included in an area corresponding to the outer peripheral surface of the outer guard 43, the monitoring processor 92 classifies the area into either a hydrophilic category or a hydrophobic category using the trained model. In other words, as classification categories, categories indicating hydrophilicity and hydrophobicity are prepared for each of multiple surfaces (here, the upper surface 21a of the spin base 21 and the outer peripheral surface of the outer guard 43).

[0161] The monitoring processor 92 determines the category and determines the removal range of the droplet region RL1 according to the category (step S52). Specifically, for the droplet L1 adhering to a hydrophilic surface, the monitoring processor 92 determines the outline region RL1a of the droplet region RL1 as the removal range, and for the droplet L1 adhering to a hydrophobic surface, the monitoring processor 92 determines the entire droplet region RL1 as the removal range.

[0162] <Third embodiment> In the processing unit 1, droplets L1 may adhere to the surface of the camera guard 72. For example, volatile components of the processing liquid in the chamber 10 may cool and condense on the surface of the camera guard 72 (specifically, the surface on the processing space side), causing droplets L1 to adhere to the surface of the camera guard 72. Therefore, in the third embodiment, a decrease in the accuracy of the monitoring process due to droplets L1 on the camera guard 72 is suppressed.

[0163] 16 is a longitudinal cross-sectional view schematically illustrating an example of the configuration of a processing unit 1 according to the third embodiment. Hereinafter, the processing unit 1 according to the third embodiment will be referred to as processing unit 1A. Compared to the processing unit 1 according to the first and second embodiments, the processing unit 1A further includes a camera displacement unit 73.

[0164] The camera displacement unit 73 includes, for example, a motor, and displaces the camera 70 between a first camera position and a second camera position. For example, the camera displacement unit 73 may rotate the camera 70. In this case, the first camera position and the second camera position are expressed as angles around the rotation axis of the camera 70. The movable angle range of the camera 70 is set, for example, from several degrees to several tens of degrees. Here, as an example, the camera displacement unit 73 rotates the camera 70 around a horizontal rotation axis. By the camera displacement unit 73 rotating the camera 70, the imaging direction of the camera 70 rotates within a predetermined angle range around the rotation axis of the camera 70.

[0165] After capturing an image of the imaging area at the first camera position, the camera 70 also captures an image of the imaging area at the second camera position. Since the first camera position and the second camera position are different from each other, the imaging area at the first camera position and the imaging area at the second camera position are different from each other.

[0166] Fig. 17 is a diagram schematically illustrating an example of an image captured by the camera 70 at the first camera position, and Fig. 18 is a diagram schematically illustrating an example of an image captured by the camera 70 at the second camera position. Figs. 17 and 18 show images captured when a droplet L1 adheres to the surface of the camera guard 72.

[0167] The axis of rotation of the camera 70 extends horizontally, and the imaging direction at the second camera position is directed downward relative to the imaging direction at the first camera position. Therefore, each object in the captured image of FIG. 18 is translated upward relative to each object in the captured image of FIG. 17. However, the amount of translation depends on the distance between the camera 70 and the object. Specifically, the greater the distance, the greater the translation amount of the object. That is, the farther the object is from the camera 70, the greater the translation amount. As shown in FIG. 16, the distance between the camera 70 and the camera guard 72 is the shortest compared to the distance between the camera 70 and other objects in the processing space, and therefore the translation amount of the droplet L1 adhering to the camera guard 72 is the smallest. Specifically, although the positions of the substrate W, the substrate holder 20, and the outer guard 43 in the captured image change significantly between the images of FIG. 17 and FIG. 18, the change in the position of the droplet region RL1 in the captured image is relatively small.

[0168] Conversely, if the difference between the positions of the droplet L1 in the images captured at the first camera position and the second camera position is relatively small, it can be assumed that the droplet L1 is attached to the camera guard 72. On the other hand, if the difference between the positions of the droplet L1 in the images captured at the first camera position and the second camera position is relatively large, it can be assumed that the droplet L1 is attached to an object other than the camera guard 72.

[0169] An example of the monitoring process according to the third embodiment is similar to the flowcharts of Figures 7 and 8. However, in the imaging process of step S11, the camera 70 captures an image of the imaging area at each of the first camera position and the second camera position to generate a captured image. Also, a specific example of the droplet removal process of step S132 differs from that of the first embodiment. Figure 19 is a flowchart showing a specific example of the droplet removal process according to the third embodiment.

[0170] First, the monitoring processor 92 determines whether or not a droplet L1 is attached to the camera guard 72 based on the captured images (step S61). Specifically, the monitoring processor 92 determines whether or not a droplet L1 is attached to the camera guard 72 based on the difference in position between the droplet region RL1 in the image captured at the first camera position and the droplet region RL1 in the image captured at the second camera position. Here, the camera displacement unit 73 rotates the camera 70 around a horizontal rotation axis, so that the object in the captured image moves vertically. Therefore, the monitoring processor 92 determines the difference in vertical position between the droplet regions RL1 corresponding to the same droplet L1 in both captured images. The droplet region RL1 corresponding to the same droplet L1 in both captured images can be identified by, for example, a matching process. Template matching, for example, can be used as the matching process.

[0171] The monitoring processing unit 92 compares the position difference with a predetermined position threshold, and when the difference is less than the position threshold, determines that the droplet L1 is attached to the camera guard 72. The position threshold is set in advance, for example, by simulation or experiment, and is stored in the storage unit 94.

[0172] When the liquid droplet L1 is attached to the camera guard 72, the monitoring processing unit 92 determines whether the surface of the camera guard 72 is hydrophilic or hydrophobic (step S62). Here, as an example, guard data indicating the wettability of the surface of the camera guard 72 is stored in advance in the storage unit 94. The guard data includes data indicating whether the wettability of the surface of the camera guard 72 is high or low, that is, data indicating whether the surface of the camera guard 72 is hydrophilic or hydrophobic. The monitoring processing unit 92 reads the guard data from the storage unit 94 and determines whether the wettability of the surface of the camera guard 72 is high or low.

[0173] When the surface of the camera guard 72 is a hydrophilic surface, the monitoring processing unit 92 determines the contour area RL1a of the droplet area RL1 as the deletion area (step S63), and when the surface of the camera guard 72 is a hydrophobic surface, the monitoring processing unit 92 determines the entire droplet area RL1 as the deletion area (step S64).

[0174] In step S61, if the liquid droplet L1 is not attached to the camera guard 72, the monitoring processing unit 92 may determine the removal range of the liquid droplet region RL1 according to the region data, as in the second embodiment.

[0175] Next, the monitoring processing unit 92 monitors the position of the outer guard 43 based on a comparison between the removed image in which the removal range of the droplet region RL1 has been removed and the reference image, as in the second embodiment (step S134). Note that the monitoring process may use either an image captured at the first camera position or an image captured at the second camera position. An image corresponding to the captured image may be prepared as the reference image.

[0176] As described above, in the third embodiment, when the liquid droplet L1 is attached to the camera guard 72, the removal range of the liquid droplet region RL1 is determined according to the wettability of the camera guard 72. Therefore, the outer guard 43 can be monitored with more appropriate accuracy according to the wettability of the camera guard 72.

[0177] The monitoring processor 92 may update the guard data over time, similar to the region data in the second embodiment. However, if the wettability of the camera guard 72 changes little over time, the guard data is not necessarily required. For example, if the camera guard 72 is hydrophilic, the monitoring processor 92 may delete the outline region RL1a of the droplet region RL1 representing the droplet L1 adhering to the camera guard 72 from the captured image. In this case, the guard data is not read out, as a matter of course. Similarly, if the camera guard 72 is hydrophobic, the monitoring processor 92 may delete the entire droplet region RL1 representing the droplet L1 adhering to the camera guard 72 from the captured image. In this case, the guard data is not read out, as a matter of course.

[0178] <Fourth embodiment> 20 is a longitudinal cross-sectional view schematically showing an example of the configuration of a processing unit 1 according to the fourth embodiment. Hereinafter, the processing unit 1 according to the fourth embodiment will also be referred to as processing unit 1B. Compared to processing unit 1A, processing unit 1B further includes a droplet removal unit 74.

[0179] The droplet removal unit 74 performs a removal operation to remove the droplets L1 adhering to the surface of the camera guard 72. Note that "removal" here means that at least a portion of the droplets L1 on the camera guard 72 is removed, and it is not necessary that all of the droplets L1 are removed.

[0180] In the example of FIG. 20 , the droplet removal unit 74 includes a nozzle 741, a gas supply pipe 742, and a valve 743. The nozzle 741 is provided in the processing space of the chamber 10 and discharges gas toward the surface of the camera guard 72. The nozzle 741 is connected to a gas supply source 744 through the gas supply pipe 742. The gas supply source 744 has a tank for storing gas and supplies the gas to the gas supply pipe 742. The gas may be an inert gas containing at least one of a rare gas such as argon gas and nitrogen gas. The gas supply pipe 742 is provided with a valve 743. When the valve 743 is opened, gas is supplied from the gas supply source 744 through the gas supply pipe 742 to the nozzle 741 and discharged from the discharge port of the nozzle 741 toward the surface of the camera guard 72. When the gas is sprayed onto the surface of the camera guard 72, droplets L1 adhering to the camera guard 72 are blown off and removed from the camera guard 72. The flow rate of the gas is set to, for example, about 50 cc / min or more and 150 cc / min or less.

[0181] When the control unit 9 determines that the captured image contains the liquid droplet L1, it causes the liquid droplet removal unit 74 to perform a removal operation to remove the liquid droplet L1 from the camera guard 72.

[0182] 21 is a flowchart showing an example of the operation of the processing unit 1B according to the fourth embodiment. First, the camera 70 captures an image of the imaging area to generate a captured image (step S71). As in the third embodiment, the camera 70 may capture an image of the imaging area at each of the first camera position and the second camera position.

[0183] Next, the control unit 9 determines whether or not the captured image contains the liquid droplet L1 (step S72). The control unit 9 determines whether or not the liquid droplet L1 exists in the same manner as in the first embodiment.

[0184] When it is determined that the droplet L1 is included in the captured image, the droplet removal unit 74 performs a removal operation (step S73). That is, the valve 743 opens and gas is sprayed onto the surface of the camera guard 72. This blows away the droplet L1 that may be attached to the camera guard 72. In short, when the droplet L1 is included in the captured image, there is a possibility that the droplet L1 is attached to the camera guard 72, and therefore the droplet removal unit 74 operates.

[0185] Next, the control unit 9 determines whether steps S71 and S72 have been executed a predetermined number of times (step S74). If steps S71 and S72 have not yet been executed the predetermined number of times, the control unit 9 executes step S71 again. The predetermined number of times is set in advance, for example, by simulation or experiment, and is stored in the storage unit 94. The predetermined number of times may be 1. In this case, step S74 is unnecessary.

[0186] When the droplet L1 is removed by the operation of the droplet removal unit 74, the droplet L1 is no longer included in the captured image. Therefore, in step S72, it is determined that the droplet L1 is not included in the captured image. At this time, the monitoring processing unit 92 monitors the position of the outer guard 43 based on the captured image without further operating the droplet removal unit 74 (step S75). That is, the monitoring processing unit 92 monitors the position of the outer guard 43 based on the captured image after the removal operation. Here, since the droplet L1 is not included, the monitoring processing unit 92 monitors the position of the outer guard 43 by comparing the guard determination region R11 with the reference image M11 and comparing the guard determination region R12 with the reference image M12.

[0187] On the other hand, when steps S71 and S72 have been executed a predetermined number of times, there is a possibility that the liquid droplet L1 is still included in the latest captured image after the removal operation. However, since it is highly likely that the liquid droplet L1 has been removed from the surface of the camera guard 72 by the operation of the liquid droplet removal unit 74, it is highly likely that the liquid droplet L1 is attached to an object other than the camera guard 72, such as the upper surface 21a of the spin base 21 or the outer peripheral surface of the outer guard 43. For this reason, the monitoring processing unit 92 monitors the outer guard 43 based on the captured image after the removal operation, in the same manner as in the first or second embodiment (step S75).

[0188] Of course, there is a possibility that the outer guard 43 may be attached to the camera guard 72, so in step S75, the monitoring processing unit 92 may monitor the position of the outer guard 43 based on the captured image after the removal operation, as in the third embodiment.

[0189] As described above, when there is a high possibility that the liquid droplets L1 are attached to the camera guard 72, the liquid droplet removal unit 74 can remove the liquid droplets L1 from the camera guard 72. Therefore, in the subsequent monitoring process, the influence of the liquid droplets L1 by the camera guard 72 can be suppressed, and the outer guard 43 can be monitored with higher accuracy.

[0190] Alternatively, in step S71, the camera 70 may capture images of the imaging area at the first camera position and the second camera position, and in step S72, the control unit 9 may determine, based on both captured images, whether or not the liquid droplet L1 is attached to the camera guard 72. In this case, the liquid droplet removal unit 74 operates when the liquid droplet L1 is attached to the camera guard 72, so that unnecessary removal operations by the liquid droplet removal unit 74 can be avoided.

[0191] Furthermore, in the above-described specific example, the droplet removal unit 74 blows away the droplets L1 with gas, but this is not necessarily limited to this. For example, the droplet removal unit 74 may include a wiper body that extends along the surface of the camera guard 72, and a wiper drive unit that rotates the wiper body about its base end to swing the wiper body along the surface of the camera guard 72. The wiper drive unit includes, for example, a motor. This makes it possible to more reliably remove droplets adhering to the camera guard 72.

[0192] As described above, the substrate processing apparatus 100 and the monitoring method have been described in detail. However, the above description is merely illustrative in all respects and is not intended to be limiting. It is understood that countless variations not illustrated can be envisioned without departing from the scope of this disclosure. The configurations described in the above embodiments and variations can be combined or omitted as appropriate as long as they are not mutually inconsistent.

[0193] For example, the object to be monitored can be at least one of the substrate holder 20, the first nozzle 30, the second nozzle 60, the third nozzle 65, the inner guard 41, and the middle guard 42. In other words, any object within the chamber 10 can be used as the object to be monitored. [Explanation of symbols]

[0194] 1 Processing Unit 10 chambers 100 Substrate processing apparatus 20 Substrate holder (spin chuck) 30 nozzles (first nozzle) 43 Monitoring object (outer guard) 60 nozzle (second nozzle) 65 nozzle (third nozzle) 70 Camera 72 Camera Guard 74 Droplet removal section 9 Control Unit W substrate S11 Imaging process (step) S12 Droplet determination process (step) S13 Monitoring process (step)

Claims

1. A chamber; a substrate holder that holds a substrate in the chamber; a nozzle that ejects a processing liquid toward the substrate held by the substrate holding unit; a camera that captures an image of an imaging area including a monitoring target in the chamber and generates captured image data; a control unit that, when the captured image data includes droplets, monitors the monitoring object using an area of ​​the captured image data excluding at least a part of a droplet area that indicates the droplets; A substrate processing apparatus comprising:

2. The substrate processing apparatus according to claim 1 , a storage unit configured to store area data indicating a first area and a second area corresponding to surfaces of different objects in the captured image data; When the droplet is contained in the first region, the control unit monitors the object to be monitored using a region of the captured image data excluding the outline region of the droplet region, and when the droplet is contained in the second region, the control unit monitors the object to be monitored using a region of the captured image data excluding the entire droplet region.

3. The substrate processing apparatus according to claim 1 , The control unit monitors the object to be monitored by using the captured image data excluding the outline region of the droplet area for droplets adhering to a hydrophilic surface, and by using the captured image data excluding the entire droplet area for droplets adhering to a hydrophobic surface that has lower wettability than the hydrophilic surface.

4. 4. The substrate processing apparatus according to claim 3, a storage unit configured to store area data indicating a first area and a second area corresponding to the hydrophilic surface and the hydrophobic surface, respectively, in the captured image data; The control unit determines whether the surface to which the droplet is attached is the hydrophilic surface or the hydrophobic surface based on the area data.

5. 5. The substrate processing apparatus according to claim 4, The control unit updates the area data based on a time-related value indicating an operating time of the substrate processing apparatus, the number of processed substrates, or an elapsed time.

6. 4. The substrate processing apparatus according to claim 3, The control unit determines whether the surface to which the droplets are attached is the hydrophilic surface or the hydrophobic surface based on the captured image data.

7. 7. The substrate processing apparatus according to claim 6, The control unit calculates the size of the droplet region based on the captured image data, and determines that the surface is a hydrophilic surface when the size of the droplet region is equal to or greater than a threshold value, and determines that the surface is a hydrophobic surface when the size of the droplet is less than the threshold value.

8. 8. The substrate processing apparatus according to claim 6, wherein: The control unit determines whether the surface is the hydrophilic surface or the hydrophobic surface using a trained model.

9. 9. The substrate processing apparatus according to claim 1, a hydrophilic and transparent camera guard provided between the camera and the imaging area; The control unit determines whether or not the droplets are attached to the camera guard based on the captured image data, and when the droplets are attached to the camera guard, monitors the monitored object using an area obtained by excluding the outline area of ​​the droplet area indicating the droplets attached to the camera guard from the captured image data.

10. 9. The substrate processing apparatus according to claim 1, a hydrophobic and transparent camera guard disposed between the camera and the imaging area; The control unit determines whether or not the droplets are attached to the camera guard based on the captured image data, and when the droplets are attached to the camera guard, monitors the monitored object using an area obtained by excluding the entire droplet area indicating the droplets attached to the camera guard from the captured image data.

11. 9. The substrate processing apparatus according to claim 1, a transparent camera guard provided between the camera and the imaging area; a droplet removal unit that performs a removal operation to remove at least a part of the droplets attached to the camera guard; Furthermore, When the droplets are included in the captured image data, the droplet removal unit performs the removal operation, and the control unit monitors the monitored object based on the captured image data captured by the camera after the removal operation.

12. an imaging step of capturing an image of an imaging area including a monitoring target in a chamber accommodating a substrate holding unit that holds a substrate and a nozzle that discharges a processing liquid toward the substrate held by the substrate holding unit, with a camera, and generating captured image data; a droplet determination step of determining whether or not droplets are included in the captured image data; a monitoring step of monitoring the monitoring object using an area of ​​the captured image data excluding at least a part of a droplet area showing the droplet when the captured image data includes the droplet; A monitoring method comprising:

Images