Substrate processing apparatus and monitoring method

By using a camera in the substrate processing device to generate photographed image data and perform corresponding determination processes based on the environmental state, the problem of decreasing nozzle position monitoring accuracy when the substrate holding part does not hold the substrate is solved, and high-precision nozzle position monitoring is achieved.

CN118891702APending Publication Date: 2024-11-01SCREEN HOLDINGS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202380026667.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-03-18
Filing Date
2023-01-25
Publication Date
2024-11-01

AI Technical Summary

Technical Problem

When the conventional substrate processing device monitors the nozzle position, the accuracy of the nozzle position is reduced, especially when the substrate holding portion does not hold the substrate, resulting in a decrease in the accuracy of the nozzle position monitoring.

Method used

By setting a camera in the substrate processing device, shooting image data is generated, and corresponding determination process is performed according to the environmental state (whether the substrate exists), and matching processing is performed using different reference image data and threshold values ​​to monitor the nozzle position with high accuracy.

Benefits of technology

It realizes high-precision monitoring of nozzle positions under different environmental conditions, improves monitoring accuracy, and reduces false detection caused by environmental changes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118891702A_ABST
    Figure CN118891702A_ABST
Patent Text Reader

Abstract

The invention provides a technology capable of monitoring the state of a monitored object with high precision. A substrate processing apparatus is provided with a chamber (10), a substrate holding unit (20), a camera (70), and a control unit (9). The substrate holding unit (20) holds the substrate (W) in the chamber (10). A camera (70) captures an image of an imaging region including a monitored object in a chamber (10), and generates captured image data. The control unit (9) specifies an environmental state within the imaging area, monitors the state of the object to be monitored on the basis of the captured image data using a first determination process corresponding to a first environmental state when the environmental state is the first environmental state, and monitors the state of the object to be monitored on the basis of the captured image data using a second determination process corresponding to the second environmental state when the environmental state is a second environmental state different from the first environmental state. The state of the object to be monitored is monitored on the basis of the captured image data using a second determination process that corresponds to the second environment state and is different from the first determination process.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to a substrate processing device and a monitoring method. Background Art

[0002] In the manufacturing process of semiconductor devices, various processing liquids such as pure water, photoresist and etching liquid are supplied to the substrate to perform various substrate processing such as cleaning processing and resist coating processing. As a device for performing substrate processing using these processing liquids, a substrate processing device is widely used, in which a substrate holding part rotates the substrate in a horizontal posture and sprays the processing liquid from a nozzle onto the surface of the substrate. The nozzle sprays the processing liquid at a processing position opposite to the center of the upper surface of the substrate in the vertical direction, for example. The processing liquid that lands on the center of the substrate is spread on the surface of the substrate by the centrifugal force generated by the rotation of the substrate. The substrate is processed by the processing liquid acting on the surface of the substrate.

[0003] In such a substrate processing apparatus, the position of the nozzle is monitored to determine whether it is appropriate. For example, in Patent Document 1, an imaging mechanism such as a camera is provided to monitor the position of the nozzle.

[0004] In Patent Document 1, a camera is disposed above a substrate holding portion. The camera captures a capture area including a substrate held by the substrate holding portion and a nozzle to generate a captured image. In Patent Document 1, a reference image including a nozzle is pre-set, and the position of the nozzle is detected by matching the captured image captured by the camera with the reference image.

[0005] Prior art literature:

[0006] Patent Literature

[0007] Patent Document 1: Japanese Patent Application Publication No. 2015-173148 Summary of the invention

[0008] Problem that the invention aims to solve

[0009] In Patent Document 1, the position of the nozzle is monitored during substrate processing of the substrate. During the substrate processing, the substrate is of course held by the substrate holding portion. The captured image at this time includes the nozzle and the substrate. Specifically, the captured image includes the nozzle, and the background area around the nozzle includes the substrate.

[0010] However, there is a case where the processing liquid is ejected from the nozzle when the substrate holding part does not hold the substrate. For example, in order to clean various components in the substrate processing device, there is a case where the processing liquid for cleaning is ejected from the nozzle when the substrate holding part does not hold the substrate. During this cleaning process, the position of the nozzle can be monitored. However, since the substrate holding part does not hold the substrate, the nozzle is included in the captured image, but the substrate is not included. In this case, for example, the substrate holding part is included in the background area around the nozzle in the captured image.

[0011] The reference image used in the matching process includes the nozzle, which is the monitored object. When the background area around the nozzle in the reference image includes the substrate, the accuracy of the matching process between the captured image captured when the substrate holding portion holds the substrate and the reference image is high. However, the accuracy of the matching process between the captured image captured when the substrate holding portion does not hold the substrate and the reference image is low. This is because the background area is different between the captured image and the reference image.

[0012] Similarly, when the background region of the reference image does not include the substrate, the accuracy of the matching process between the captured image captured in a state where the substrate is held by the substrate holding portion and the reference image is reduced.

[0013] As described above, if the position of the nozzle is monitored in the same process in a state where the substrate holding portion holds the substrate and in a state where the substrate is not held, the accuracy may be reduced.

[0014] To explain more generally, the monitoring accuracy decreases depending on the environmental state (here, whether the substrate holding portion is holding the substrate) in the imaging region including the monitoring object (for example, the nozzle).

[0015] Therefore, an object of the present disclosure is to provide a technology that can monitor the state of a monitoring object with high accuracy.

[0016] Technical solutions to the problem

[0017] The first method is a substrate processing device, which includes: a chamber; a substrate holding unit that holds a substrate in the above-mentioned chamber; a camera that captures a shooting area in the above-mentioned chamber that includes a monitored object and generates captured image data; and a control unit that determines the environmental state in the above-mentioned shooting area, and when the above-mentioned environmental state is a first environmental state, monitors the state of the above-mentioned monitored object based on the above-mentioned captured image data by a first judgment process corresponding to the above-mentioned first environmental state, and when the above-mentioned environmental state is a second environmental state different from the above-mentioned first environmental state, monitors the above-mentioned state of the above-mentioned monitored object based on the above-mentioned captured image data by a second judgment process corresponding to the above-mentioned second environmental state and different from the above-mentioned first judgment process.

[0018] A second aspect is the substrate processing apparatus according to the first aspect, wherein the control unit specifies the environmental state based on the captured image data.

[0019] The third mode is a substrate processing device as in the first or second mode, wherein the device further comprises a storage unit recording a plurality of reference image data corresponding to the above-mentioned environmental state; the above-mentioned control unit, when the above-mentioned environmental state is the above-mentioned first environmental state, monitors the above-mentioned state of the above-mentioned monitored object based on the comparison between the above-mentioned captured image data and the first reference image data corresponding to the above-mentioned first environmental state as the above-mentioned first determination process, and when the above-mentioned environmental state is the above-mentioned second environmental state, monitors the above-mentioned state of the above-mentioned monitored object based on the comparison between the above-mentioned captured image data and the second reference image data corresponding to the above-mentioned second environmental state as the above-mentioned second determination process.

[0020] The fourth mode is a substrate processing device as described in the third mode, wherein the first environmental state includes a state in which a specified object exists in the above-mentioned shooting area; the second environmental state includes a state in which the above-mentioned object does not exist in the above-mentioned shooting area; the first reference image data is an image including the above-mentioned object and the above-mentioned monitored object; and the second reference image data does not include the above-mentioned object but includes the image of the above-mentioned monitored object.

[0021] A fifth aspect is the substrate processing apparatus according to any one of the first to fourth aspects, wherein an algorithm of the first determination process and an algorithm of the second determination process are different from each other.

[0022] Mode 6 is a substrate processing device as described in any one of modes 1 to 5, wherein the threshold used in the first determination process to monitor the above-mentioned state of the above-mentioned monitored object is different from the threshold used in the second determination process to monitor the above-mentioned state of the above-mentioned monitored object.

[0023] The seventh mode is a substrate processing device as in the sixth mode, wherein the device further comprises a storage unit for recording reference image data; the first environmental state includes a state in which a prescribed object exists in the shooting area; the second environmental state includes a state in which the object does not exist in the shooting area; the reference image data is an image that does not include the object but includes the monitored object; when the environmental state is the first environmental state, the control unit compares the similarity between the captured image data and the reference image data with a first threshold value as the first determination process to monitor the state of the monitored object, and when the environmental state is the second environmental state, the control unit compares the similarity between the captured image data and the reference image data with a second threshold value that is less than the first threshold value as the second determination process to monitor the state of the monitored object.

[0024] The 8th mode is a substrate processing device such as the 4th or 7th mode, wherein the device further comprises a nozzle which supplies a processing liquid to the substrate from a nozzle processing position which is higher than the substrate held by the substrate holding portion; the object includes smoke originating from the processing liquid which is generated higher than the substrate.

[0025] The 9th mode is a substrate processing device as described in any one of the 1st to 8th modes, wherein the first environmental state includes a state in which a specified object exists in the above-mentioned shooting area; the second environmental state includes a state in which the above-mentioned object does not exist in the above-mentioned shooting area; in the above-mentioned control unit, as the above-mentioned first judgment process, the above-mentioned captured image data is input into a first learned model, and as the above-mentioned second judgment process, the above-mentioned captured image data is input into a second learned model; the above-mentioned first learned model is a learned model generated based on a plurality of learning data including the above-mentioned monitored object and the above-mentioned object, and classifies the above-mentioned captured image data into any one of a normal category indicating normality and an abnormal category indicating abnormality; the above-mentioned second learned model is a learned model generated based on a plurality of learning data including the above-mentioned monitored object but not including the above-mentioned object, and classifies the above-mentioned captured image data into any one of the above-mentioned normal category and the above-mentioned abnormal category.

[0026] The 10th embodiment is a substrate processing device as described in any one of the 1st to 9th embodiments, wherein the monitored object includes at least any one of a chuck pin of the substrate holding portion, a nozzle for supplying a processing liquid to the substrate held by the substrate holding portion, and a cylindrical protective member for catching the processing liquid scattered from the periphery of the substrate held by the substrate holding portion.

[0027] The 11th mode is a substrate processing device as in the 5th mode, wherein the device further comprises a nozzle which supplies a processing liquid to the substrate from a nozzle processing position which is above the substrate held by the substrate holding portion; the first environmental state includes a pattern substrate state in which a pattern is formed on the upper surface of the substrate held by the substrate holding portion; the second environmental state includes a uniform substrate state in which no pattern is formed on the upper surface of the substrate held by the substrate holding portion; when the environmental state is the uniform substrate state, the control portion calculates, as the first judgment process, an index representing a deviation of pixel values ​​in a spray judgment area directly below the nozzle in the captured image data, and determines the presence or absence of droplets of the processing liquid falling from the nozzle based on a comparison between the index and a threshold value, and when the environmental state is the pattern substrate state, the captured image data is input into a learned model as the second judgment process to determine the presence or absence of the droplets.

[0028] The 12th mode is a substrate processing device as in the 5th mode, wherein the device further comprises a nozzle for supplying a processing liquid to the substrate held by the substrate holding portion; the first environmental state includes a smoke state in which smoke originating from the processing liquid is generated above the substrate held by the substrate holding portion; the second environmental state includes a non-smoke state in which the smoke is not generated; when the environmental state is the smoke state, the control portion, as the first determination process, performs contrast emphasis processing on the captured image data to generate emphasized image data, and monitors the state of the monitored object based on the emphasized image data, and when the environmental state is the non-smoke state, the control portion, as the second determination process, does not perform the contrast emphasis processing, but monitors the state of the monitored object based on the captured image data.

[0029] The 13th method is a monitoring method, which comprises: an environmental state determining step, determining the environmental state of a shooting area including a monitoring object in a chamber of a substrate holding portion that stores and holds a substrate; a shooting step, shooting the shooting area by a camera to generate shot image data; and a monitoring step, which, when the above-mentioned environmental state is a first environmental state, monitors the state of the above-mentioned monitoring object based on the above-mentioned shot image data as a first judgment process corresponding to the above-mentioned first environmental state, and when the above-mentioned environmental state is a second environmental state different from the above-mentioned first environmental state, monitors the above-mentioned state of the above-mentioned monitoring object based on the above-mentioned shot image data as a second judgment process corresponding to the above-mentioned second environmental state and different from the above-mentioned first judgment process.

[0030] Effects of the Invention

[0031] According to the first and thirteenth aspects, since the state of the monitoring object is monitored by a determination process according to the surrounding environmental state, the state of the monitoring object can be monitored with high accuracy.

[0032] According to the second aspect, since the environmental state is specified based on the captured image data, the environmental state can be specified with high accuracy.

[0033] According to the third aspect, since the state of the monitoring object is monitored based on the reference image data and the captured image data according to the environmental state, the state of the monitoring object can be monitored with high accuracy.

[0034] According to the fourth aspect, when an object exists in the photographing area, the object is included in the photographing image data. At this time, the control unit compares the photographing image data with the first reference image data including the object. In the comparison result, since the influence of the object is eliminated, the control unit can monitor the state of the monitoring object with higher accuracy by comparing the state of the monitoring object in the photographing image data with the state of the monitoring object in the first reference image data.

[0035] On the other hand, when there is no object in the photographed area, the photographed image data also does not include the object. In this case, the control unit compares the photographed image data with the second reference image data that does not include the object. In the comparison result, since the influence of the object is not included, the control unit can monitor the state of the monitored object with higher accuracy by comparing the monitored object in the photographed image data with the monitored object in the second reference image data.

[0036] According to the fifth aspect, since an algorithm corresponding to the environmental state is used, the control unit can monitor the state of the monitoring object with high accuracy.

[0037] According to the seventh aspect, when the object exists, the first threshold value compared with the similarity is large. Therefore, the state of the monitored object can be monitored with higher accuracy. On the other hand, when the object does not exist, the second threshold value compared with the similarity is small. Therefore, the false detection of abnormalities caused by the decrease in the similarity caused by the presence or absence of the object between the captured image and the reference image can be suppressed.

[0038] According to the eighth aspect, the state of the monitoring object can be appropriately monitored according to the presence or absence of smoke.

[0039] According to the ninth aspect, since a learned model corresponding to the environmental state is used, the state of the monitored object can be monitored with higher accuracy.

[0040] According to the tenth aspect, the state of at least one of the chuck pin, the nozzle, and the guard can be appropriately monitored.

[0041] According to the eleventh aspect, when a pattern is formed on the substrate, the presence or absence of droplets (dripping) is determined based on the comparison between the pointer indicating the deviation of the discharge determination area and the threshold value. Therefore, the control unit can determine the presence or absence of droplets with a light processing load and high accuracy.

[0042] On the other hand, when a pattern is formed on the substrate, the pointer of the discharge determination area becomes high even if no droplets are generated.

[0043] In the eleventh aspect, when a pattern is formed on the substrate, the presence or absence of a droplet is determined using the learned model. Therefore, even when a pattern is formed on the substrate, the control unit can determine the presence or absence of a droplet with high accuracy.

[0044] According to the twelfth aspect, when smoke is generated, the state of the monitoring object is monitored using enhanced image data. Therefore, the influence of contrast reduction due to smoke can be suppressed, and the state of the monitoring object can be monitored with higher accuracy.

[0045] On the other hand, when smoke is not generated, contrast enhancement processing is not performed. Therefore, the control unit can monitor the state of the monitoring object with a relatively light processing load. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a plan view schematically showing an example of the structure of a substrate processing apparatus.

[0047] Figure 2 It is a plan view schematically showing an example of the configuration of the processing unit according to the first embodiment.

[0048] Figure 3 This is a longitudinal sectional view schematically showing an example of the configuration of the processing unit according to the first embodiment.

[0049] Figure 4 This is a functional block diagram schematically showing an example of the internal configuration of the control unit.

[0050] Figure 5 This is a flowchart showing an example of the flow of substrate processing.

[0051] Figure 6 This is a diagram schematically showing an example of an image captured by a camera.

[0052] Figure 7 This is a diagram schematically showing an example of an image captured by a camera.

[0053] Figure 8 This is a flowchart showing an example of a flowchart of monitoring processing of a processing unit.

[0054] Fig. 9 This is a flowchart showing a specific example of the monitoring process.

[0055] Fig.10 This is a diagram schematically showing an example of a captured image when droplets of the processing liquid fall from the discharge port of the first nozzle.

[0056] Fig.11 This is a diagram schematically showing an example of a captured image when droplets of the processing liquid fall from the discharge port of the first nozzle.

[0057] Fig.12 This is a flowchart showing a specific example of the monitoring process.

[0058] Fig.13 This is a diagram schematically showing an example of an image captured by a camera.

[0059] Fig.14 This is a diagram schematically showing an example of an image captured when the processing liquid is scattered from the periphery of the substrate.

[0060] Fig.15This is a flowchart showing a specific example of the monitoring process.

[0061] Fig.16 This is a diagram schematically showing an example of an image captured when smoke is generated.

[0062] Fig.17 This is a flowchart showing a specific example of the monitoring process.

[0063] Fig.18 This is a diagram schematically showing an example of the configuration of a batch processing unit according to the second embodiment.

[0064] Fig.19 This is a flowchart showing a specific example of the monitoring process according to the second embodiment.

[0065] Fig. 20 This is a flowchart showing a specific example of the monitoring process according to the third embodiment. DETAILED DESCRIPTION

[0066] Below, please refer to the attached Figure 1 The following description will be given in the context of the embodiments. In addition, the drawings are schematic diagrams, and the configurations are appropriately omitted or simplified for the sake of convenience. In addition, the size and position of the configurations shown in the drawings may not be accurately described and may be appropriately changed.

[0067] In the following description, the same components are denoted by the same reference numerals and shown in the drawings, and their names and functions are also assumed to be the same. Therefore, their detailed description may be omitted to avoid duplication.

[0068] In the following description, even if serial numbers such as "1st" or "2nd" are used, these terms are used for convenience in order to facilitate understanding of the contents of the implementation mode and are not limited to the order that can be generated by these serial numbers.

[0069] When using expressions that indicate relative or absolute positional relationships (e.g., "in a direction," "along a direction," "parallel," "orthogonal," "center," "concentric," "coaxial," etc.), the expressions, unless otherwise specified, not only strictly indicate the positional relationship, but also indicate the state of relative displacement of angles or distances within a tolerance or a range in which the same degree of function can be obtained. When using expressions that indicate an equal state (e.g., "same," "equal," "homogeneous," etc.), the expressions, unless otherwise specified, not only indicate a state of quantitatively strict equality, but also indicate a state of difference with a tolerance or a range in which the same degree of function can be obtained. When using expressions that indicate a shape (e.g., "quadrilateral" or "cylindrical shape," etc.), the expressions, unless otherwise specified, not only strictly indicate the shape geometrically, but also indicate a shape with, for example, concave-convex or chamfered corners within a range in which the same degree of effect can be obtained. When using an expression that indicates "provides," "equipped," "equipped," "includes," or "has" a constituent element, the expression is not an exclusive expression that excludes the existence of other constituent elements. When the expression "at least any one of A, B, and C" is used, the expression includes only A, only B, only C, any two of A, B, and C, and all of A, B, and C.

[0070] <First Embodiment>

[0071] <Overall Structure of Substrate Processing Apparatus>

[0072] Figure 1 1 is a top view schematically showing an example of the structure of the substrate processing device 100. The substrate processing device 100 is a single-wafer processing device that processes the substrates W as the processing object piece by piece. The substrate processing device 100 performs a drying process after performing a liquid treatment on the substrate W using a chemical solution and a rinsing liquid such as pure water. The substrate W is, for example, a semiconductor substrate and has a circular plate shape. As the above-mentioned chemical solution, for example, a mixed solution of ammonia and hydrogen peroxide water (SC1), a mixed aqueous solution of hydrochloric acid and hydrogen peroxide water (SC2), or DHF liquid (dilute hydrofluoric acid) is used. In the following description, chemical solutions, rinsing liquids, and organic solvents are collectively referred to as "processing liquids". In addition, not only cleaning treatments, but also chemical solutions for removing excess films, or chemical solutions for etching, etc. are included in the "processing liquid".

[0073] The substrate processing apparatus 100 includes a plurality of processing units 1 , a load port LP, a carrier robot 102 , a main transfer robot 103 , and a control unit 9 .

[0074] The loading port LP is an interface for loading and unloading substrates W between the substrate processing apparatus 100 and the outside. In the loading port LP, a storage container (also called a carrier) storing a plurality of unprocessed substrates W is loaded from the outside. The loading port LP can hold a plurality of carriers. As described later, each substrate W is taken out from the carrier by the substrate processing apparatus 100, processed, and stored again in the carrier. The carrier storing the processed plurality of substrates W is unloaded from the loading port LP to the outside.

[0075] The transfer robot 102 transfers the substrate W between each carrier held at the load port LP and the main transfer robot 103 . The main transfer robot 103 transfers the substrate W between each processing unit 1 and the transfer robot 102 .

[0076] The processing unit 1 performs liquid processing and drying processing on one substrate W. In the substrate processing apparatus 100 of this embodiment, 12 processing units 1 having the same structure are arranged. Specifically, four towers each including three processing units 1 stacked in the vertical direction are arranged to surround the main transfer robot 103 . Figure 1 , one of the three-layered processing units 1 is schematically shown. In addition, the number of processing units 1 in the substrate processing apparatus 100 is not limited to 12, and can be changed appropriately.

[0077] The main transport robot 103 is installed in the center of the four towers on which the processing units 1 are stacked. The main transport robot 103 carries the substrate W to be processed received from the carrier robot 102 into each processing unit 1. In addition, the main transport robot 103 carries out the processed substrate W from each processing unit 1 and transfers it to the carrier robot 102. The control unit 9 controls the operation of each component of the substrate processing apparatus 100.

[0078] Hereinafter, one of the twelve processing units 1 mounted in the substrate processing apparatus 100 will be described.

[0079] <Processing Unit>

[0080] Figure 2 It is a plan view schematically showing an example of the configuration of the processing unit 1 according to the first embodiment. Figure 3 It is a longitudinal sectional view schematically showing an example of the structure of the processing unit 1 according to the first embodiment.

[0081] exist Figure 2 and Figure 3 In the example of FIG. 1 , the processing unit 1 includes a substrate holding portion 20 , a first nozzle 30 , a second nozzle 60 , a third nozzle 65 , a guard portion 40 , and a camera 70 .

[0082] exist Figure 2 and Figure 3In the example of , the processing unit 1 also includes a chamber 10. The chamber 10 includes a side wall 11 along the vertical direction, a top wall 12 that closes the upper side of the space surrounded by the side wall 11, and a bottom wall 13 that closes the lower side. A processing space is formed in the space surrounded by the side wall 11, the top wall 12, and the bottom wall 13. In a part of the side wall 11 of the chamber 10, a loading and unloading port for the main transport robot 103 to load and unload the substrate W and a baffle that opens and closes the loading and unloading port are provided (both are omitted in the figure). The chamber 10 accommodates the substrate holding part 20, the first nozzle 30, the second nozzle 60, the third nozzle 65, and the protection part 40.

[0083] exist Figure 3 In the example, a fan filter unit (FFU) 14 is installed on the top wall 12 of the chamber 10, and the fan filter unit 14 is used to further purify the air in the clean room where the substrate processing device 100 is installed and supply it to the processing space in the chamber 10. The fan filter unit 14 includes a fan and a filter (such as a HEPA (High Efficiency Particulate Air) filter) for extracting the air in the clean room and sending it to the chamber 10, forming a downflow of clean air in the processing space in the chamber 10. In order to evenly disperse the clean air supplied from the fan filter unit 14, a punching plate with a plurality of blowing holes may be provided directly below the top wall 12.

[0084] The substrate holding unit 20 holds the substrate W in a horizontal posture (a posture in which the normal line is along the vertical direction) and rotates the substrate W around the rotation axis CX (refer to FIG. Figure 3 ). The rotation axis CX is an axis along the vertical direction and passes through the center of the substrate W. The substrate holding portion 20 is also called a rotation chuck. In addition, Figure 2 The substrate holding portion 20 is shown in the middle in a state where no substrate is held.

[0085] exist Figure 2 and Figure 3 In the example of FIG. 1 , the substrate holding portion 20 includes a disk-shaped rotating base 21 disposed in a horizontal position. The outer diameter of the disk-shaped rotating base 21 is slightly larger than the diameter of the circular substrate W held by the substrate holding portion 20 (see FIG. 1 ). Figure 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.

[0086] exist Figure 2 and Figure 3In the example, a plurality of (4 in the present embodiment) chuck pins 26 are vertically provided on the peripheral portion of the upper surface 21a of the rotating base 21. The plurality of chuck pins 26 are arranged at equal intervals along a circle corresponding to the periphery of the circular substrate W. Each chuck pin 26 is configured to be drivable between a holding position abutting against the periphery of the substrate W and an open position away from the periphery of the substrate W. The plurality of chuck pins 26 are driven in conjunction with a linkage mechanism (not shown) housed in the rotating base 21. The substrate holding portion 20 can hold the substrate W in a horizontal posture close to the upper surface 21a above the rotating base 21 by stopping the plurality of chuck pins 26 at each holding position (see Figure 3 ), and the substrate W can be released from being held by stopping the plurality of chuck pins 26 at respective open positions.

[0087] exist Figure 3 In the example of FIG. 1 , the upper end of a rotating shaft 24 extending along a rotating axis CX is connected to the lower surface of the rotating base 21. A rotating motor 22 for rotating the rotating shaft 24 is provided below the rotating base 21. The rotating motor 22 rotates the rotating base 21 in a horizontal plane by rotating the rotating shaft 24 around the rotating axis CX. As a result, the substrate W held by the chuck pins 26 also rotates around the rotating axis CX.

[0088] exist Figure 3 In the example of FIG. 2 , a cylindrical cover member 23 is provided to surround the rotary motor 22 and the rotary shaft 24. The lower end of the cover member 23 is fixed to the bottom wall 13 of the chamber 10, and the upper end reaches directly below the rotary base 21. Figure 3 In the example, at the upper end of the cover member 23, a flange-shaped member 25 is provided which protrudes substantially horizontally outward from the cover member 23 and further bends and extends downward.

[0089] The first nozzle 30 discharges the processing liquid toward the substrate W, thereby supplying the processing liquid to the substrate W. Figure 2 In the example of FIG. 1 , the first nozzle 30 is mounted on the front end 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 in the vertical direction and is arranged to be rotatable around an axis in the vertical direction by an arm drive motor (not shown). Figure 2 As shown by the arrow AR34 in FIG. 1 , the first nozzle 30 moves in an arc shape between the nozzle processing position and the nozzle standby position in a space vertically above the substrate holding portion 20. The nozzle processing position is the position of the first nozzle 30 when it sprays the processing liquid onto the substrate W, for example, a position vertically opposite to the center of the substrate W. The nozzle standby position is the position of the first nozzle 30 when it does not spray the processing liquid onto the substrate W, for example, a position radially outward of the periphery of the substrate W. The radial direction mentioned here is the radial direction with respect to the rotation axis CX. Figure 2The first nozzle 30 is shown in the nozzle standby position. Figure 3 The first nozzle 30 located at the nozzle processing position is shown in the middle.

[0090] like Figure 3 As shown in the example, the first nozzle 30 is connected to a treatment liquid supply source 36 via a supply pipe 34. The treatment liquid supply source 36 includes a tank for storing the treatment liquid. A valve 35 is provided in the supply pipe 34. When the valve 35 is opened, the treatment liquid is supplied from the treatment liquid supply source 36 to the first nozzle 30 through the supply pipe 34, and is ejected from the ejection port formed on the lower end surface of the first nozzle 30. In addition, the first nozzle 30 may also be configured to supply a plurality of treatment liquids (including at least pure water).

[0091] The second nozzle 60 is mounted on the front end of a nozzle arm 62, and the base end of the nozzle arm 62 is connected to a nozzle support column 63. The motor for arm driving (not shown) rotates the nozzle support column 63, whereby the second nozzle 60 moves in an arc shape in a space vertically above the substrate holding portion 20 as indicated by an arrow AR64. Similarly, the third nozzle 65 is mounted on the front end of a nozzle arm 67, and the base end of the nozzle arm 67 is connected to a nozzle support column 68. The motor for arm driving (not shown) rotates the nozzle support column 68, whereby the third nozzle 65 moves in an arc shape in a space vertically above the substrate holding portion 20 as indicated by an arrow AR69.

[0092] The second nozzle 60 and the third nozzle 65 are each connected to a treatment liquid supply source (not shown) via a supply pipe (not shown) similarly to the first nozzle 30. A valve is provided in each supply pipe, and the supply / stop of the treatment liquid is switched by opening and closing the valve. In addition, the number of nozzles provided in the treatment unit 1 is not limited to three, and may be one or more.

[0093] During the liquid treatment, the processing unit 1 rotates the substrate W through the substrate holding portion 20, and sprays the processing liquid from the first nozzle 30 toward the upper surface of the substrate W. The processing liquid landed on the upper surface of the substrate W is spread on the upper surface of the substrate W by the centrifugal force generated by the rotation, and scatters from the periphery of the substrate W. Through this liquid treatment, the upper surface of the substrate W can be treated according to the type of the processing liquid.

[0094] The protection part 40 is a member for catching the processing liquid scattered from the periphery of the substrate W. The protection part 40 has a cylindrical shape surrounding the substrate holding part 20, and, for example, includes a plurality of protection members that can be raised and lowered independently of each other. The protection member can also be called a processing cup. Figure 3 In the example of FIG. 1 , an inner guard 41 , a middle guard 42 , and an outer guard 43 are shown as a plurality of guards. Each of the guards 41 to 43 surrounds the substrate holding portion 20 and has a shape that is substantially rotationally symmetrical with respect to the rotation axis CX.

[0095] exist Figure 3 In the example of, the inner guard 41 integrally includes a bottom 44, an inner wall portion 45, an outer wall portion 46, a first guide portion 47 and a middle wall portion 48. The bottom 44 has a circular ring shape in a plan view. The inner wall portion 45 and the outer wall portion 46 have a cylindrical shape and are respectively provided on the inner periphery and the outer periphery of the bottom 44. The first guide portion 47 has a cylindrical barrel portion 47a provided on the bottom 44 between the inner wall portion 45 and the outer wall portion 46, and an inclined portion 47b approaching the rotation axis CX as it moves from the upper end of the barrel portion 47a toward the vertical upper side. The middle wall portion 48 has a cylindrical shape and is provided on the bottom 44 between the first guide portion 47 and the outer wall portion 46.

[0096] In the state where the guards 41 to 43 are raised (refer to Figure 3 The processing liquid scattered 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 by 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 44. The waste groove 49 is connected to a liquid exhaust mechanism (not shown) for exhausting the processing liquid and forcibly exhausting the waste groove 49.

[0097] The middle guard 42 integrally includes a second guide portion 52 and a cylindrical treatment liquid separation wall 53 connected to the second guide portion 52. The second guide portion 52 has a cylindrical barrel portion 52a and an inclined portion 52b that approaches the rotation axis CX as it moves from the upper end of the barrel portion 52a toward the vertical upper side. The inclined portion 52b is arranged to be located vertically above the inclined portion 47b of the inner guard 41 and is stacked with the inclined portion 47b in the vertical direction. The barrel portion 52a is accommodated in the 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.

[0098] 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 by the inner recovery tank 50 .

[0099] The process liquid separation wall 53 has a cylindrical shape, and its upper end is connected to the second guide portion 52. The process liquid separation wall 53 is accommodated in the annular outer recovery groove 51. The outer recovery groove 51 is a groove formed by the middle wall portion 48, the outer wall portion 46, and the bottom portion 44.

[0100] The outer protection member 43 is located outside the middle protection member 42 and has a function as a third guide portion for guiding the processing liquid to the outer recovery tank 51. The outer protection member 43 integrally includes a cylindrical cylindrical portion 43a and an inclined portion 43b that approaches the rotation axis CX as it moves from the upper end of the cylindrical portion 43a toward the vertical upper side. The cylindrical portion 43a is accommodated in the outer recovery tank 51, and the inclined portion 43b is arranged to be located vertically above the inclined portion 52b and to be stacked with the inclined portion 52b in the vertical direction.

[0101] 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 by the outer recovery tank 51 .

[0102] The inner recovery tank 50 and the outer recovery tank 51 are connected to a recovery mechanism (both not shown) for recovering the processing liquid to a recovery tank provided outside the processing unit 1 .

[0103] The protective members 41 to 43 can be raised and lowered by a protective member lifting mechanism 55. The protective member lifting mechanism 55 lifts the protective members 41 to 43 between respective protective member processing positions and protective member standby positions in a manner that prevents the protective members 41 to 43 from colliding with each other. The protective member processing position is a position where the upper peripheral edge of the target protective member to be lifted is above the upper surface of the substrate W, and the protective member standby position is a position where the upper peripheral edge of the target protective member is below the upper surface 21a of the rotating base 21. The upper peripheral edge mentioned here is the annular portion of the target protective member that forms an upper end opening. Figure 3 In the example of , 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.

[0104] The partition plate 15 is provided to divide the inner space of the chamber 10 into upper and lower parts around the protection part 40. A through hole and a notch (not shown) penetrating in the thickness direction may be formed in the partition plate 15. In the present embodiment, through holes are formed for respectively passing the nozzle support column 33, the nozzle support column 63, and the nozzle support column 68. The outer peripheral end of the partition plate 15 is connected to the side wall 11 of the chamber 10. In addition, the inner peripheral edge of the partition plate 15 surrounding the protection part 40 is formed into a circular shape with a diameter larger than the outer diameter of the outer protection part 43. Therefore, the partition plate 15 does not hinder the lifting and lowering of the outer protection part 43.

[0105] exist Figure 3 In the example of FIG. 1 , an exhaust pipe 18 is provided at a part of the side wall 11 of the chamber 10 and near the bottom wall 13. The exhaust pipe 18 is connected to an exhaust mechanism (not shown). The clean air flowing down in the chamber 10 passes through the guard 40 and the partition plate 15 and is discharged from the exhaust pipe 18 to the outside of the device.

[0106] The camera 70 is used to monitor the state of the monitoring object in the chamber 10. The monitoring object includes, for example, at least one of the substrate holding portion 20, the first nozzle 30, the second nozzle 60, the third nozzle 65, and the protection portion 40. The camera 70 captures a captured area including the monitoring object, generates captured image data (hereinafter referred to as a captured image), and outputs the captured image to the control unit 9. As described in detail later, the control unit 9 monitors the state of the monitoring object based on the captured image.

[0107] The camera 70 includes, for example, 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. Figure 3 In the example of , the camera 70 is set at a photographing position vertically above the substrate W held by the substrate holding portion 20. Figure 3 In the example of , the imaging position is set vertically above the partition plate 15 and radially outward relative to the guard portion 40. The radial direction mentioned here is the radial direction about the rotation axis CX.

[0108] exist Figure 3 In the example of FIG. 1 , the side wall 11 of the chamber 10 is formed with a concave portion (hereinafter referred to as the concave wall portion 11) for accommodating the camera 70. The concave wall portion 111 has a shape that is concave outward relative to other portions of the side wall 11. The camera 70 is accommodated inside the concave wall portion 111. Figure 3 In the example, a transparent member 72 is provided in front of the camera 70 in the shooting direction. The transparent member 72 has a high light transmittance to the wavelength of light detected by the camera 70. Therefore, the camera 70 can shoot the shooting area in the processing space through the transparent member 72. The transmittance of the transparent member 72 in the detection wavelength range of the camera 70 is, for example, 60% or more, preferably 80% or more. The transparent member 72 is formed of a transparent material such as quartz glass. Figure 3 In the example of FIG. 1 , the transparent member 72 has a plate-like shape and forms a storage space for the camera 70 together with the concave wall portion 111 of the side wall 11. By providing the transparent member 72, the camera 70 can be protected from the processing liquid in the processing space and the volatile components of the processing liquid.

[0109] The imaging area of ​​the camera 70 includes, for example, a portion of the substrate holding portion 20 and the shielding portion 40. Figure 3 In the example of , the camera 70 shoots the shooting area obliquely downward from the shooting position. In other words, the shooting direction of the camera 70 is inclined from the horizontal direction toward the vertical downward direction.

[0110] exist Figure 3In the example, the lighting unit 71 is provided at a position vertically above the partition plate 15. As a specific example, the lighting unit 71 is also provided inside the concave wall portion 111. When the chamber 10 is a dark room, the control unit 9 can control the lighting unit 71 so that the lighting unit 71 illuminates the photographing area when the camera 70 takes pictures. The illumination light from the lighting unit 71 is irradiated into the processing space through the transparent member 72.

[0111] The hardware structure of the control unit 9 is the same as that of a general computer. That is, the control unit 9 is configured as a data processing unit including a CPU (Central Processing Unit) that performs various calculations, a non-temporary storage unit including a ROM (Read Only Memory) that is a dedicated read-only memory for storing basic processes, and a temporary storage unit including a RAM (Random Access Memory) that is a readable and writable memory for storing various information. The CPU of the control unit 9 executes a predetermined processing process, and the control unit 9 controls each action mechanism of the substrate processing apparatus 100 to perform processing in the substrate processing apparatus 100. In addition, the control unit 9 can also be implemented by a dedicated hardware circuit that does not require software to implement the function.

[0112] Figure 4 9 is a functional block diagram schematically showing an example of the internal structure of the control unit 9. Figure 4 As shown, the control unit 9 includes an environment state identification unit 91 , a monitoring processing unit 92 , and a processing control unit 93 .

[0113] The process control unit 93 controls each component of the process unit 1. More specifically, the process control unit 93 controls the rotary motor 22, various valves such as the valve 35, a motor for driving the arm that rotates 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 93 controls these components according to a predetermined process, whereby the process unit 1 can process the substrate W.

[0114] <An Example of a Substrate Processing Flow>

[0115] Here, an example of a specific flow of processing on the substrate W will be briefly described. Figure 5 1 is a flowchart showing an example of the process of substrate processing. Initially, the guards 41 to 43 are respectively stopped at the guard standby position, and the nozzles 30, 60, and 65 are respectively stopped at the nozzle standby position. In addition, the control unit 9 controls each component to perform the prescribed action described later, but the following description uses each component itself as the main body of the action.

[0116] First, the main transport robot 103 carries an unprocessed substrate W into the processing unit 1, and the substrate holding part 20 holds the substrate W (step S1: carrying-in holding process). Since the initial protection part 40 stops at the protection member standby position, the hand of the main transport robot 103 can be prevented from colliding with the protection part 40 when the substrate W is carried in. After the substrate W is transferred to the substrate holding part 20, the plurality of chuck pins 26 move to each holding position, thereby holding the substrate W by the plurality of chuck pins 26.

[0117] Next, the rotary motor 22 starts rotating the substrate W (step S2 : rotation start step). Specifically, the rotary motor 22 rotates the spin base 21 to rotate the substrate W held by the substrate holding portion 20 .

[0118] Next, the processing unit 1 performs various liquid treatments on the substrate W (step S3: liquid treatment process). For example, the processing unit 1 performs liquid chemical treatment. First, the shield lifting mechanism 55 raises the shield corresponding to the liquid chemical among the shields 41 to 43 to the shield processing position. The shield for the liquid chemical is not particularly limited, and may be, for example, the outer shield 43. In this case, the shield lifting mechanism 55 stops the inner shield 41 and the middle shield 42 at the respective shield standby positions, and raises the outer shield 43 to the shield processing position.

[0119] Next, the processing unit 1 supplies the chemical liquid to the substrate W. Here, the processing liquid is supplied from the first nozzle 30. Specifically, the motor for arm driving moves the first nozzle 30 to the nozzle processing position, and the valve 35 opens to allow the chemical liquid to be ejected from the first nozzle 30 to the substrate W. As a result, the chemical liquid spreads on the upper surface of the rotating substrate W and scatters from the periphery of the substrate W. At this time, the chemical liquid acts on the upper surface of the substrate W, and performs a treatment corresponding to the chemical liquid (for example, a cleaning treatment) on the substrate W. The chemical liquid scattered from the periphery of the substrate W is received by the inner circumferential surface of the protection part 40 (for example, the outer protection part 43). After the chemical liquid treatment is fully performed, the processing unit 1 stops the supply of the chemical liquid.

[0120] Next, the processing unit 1 performs a rinse process on the substrate W. The shield lifting mechanism 55 adjusts the lifting state of the shield 40 as needed. That is, when the shield for the rinse liquid is different from the shield for the chemical solution, the shield lifting mechanism 55 moves the shield corresponding to the rinse liquid among the shields 41 to 43 to the shield processing position. The shield for the rinse liquid is not particularly limited, and may be the inner shield 41. In this case, the shield lifting mechanism 55 raises the shields 41 to 43 to the respective shield processing positions.

[0121] Next, the first nozzle 30 sprays the rinsing liquid onto the upper surface of the substrate W. The rinsing liquid is, for example, pure water. The first rinsing liquid spreads on the upper surface of the rotating substrate W to wash away the chemical solution on the substrate W, and scatters from the periphery of the substrate W. The processing liquid (mainly the rinsing liquid) scattering from the periphery of the substrate W is received by the inner peripheral surface of the protection part 40 (for example, the inner protection part 41). After the rinsing process is fully performed, the processing unit 1 stops supplying the rinsing liquid.

[0122] The processing unit 1 can supply a volatile rinsing liquid such as isopropyl alcohol having high volatility to the substrate W as needed. In addition, when the guard for the volatile rinsing liquid is different from the guard for the above-mentioned rinsing liquid, the guard lifting mechanism 55 can move the guard corresponding to the volatile rinsing liquid among the guards 41 to 43 to the guard processing position. After the rinsing process is completed, the first nozzle 30 moves to the nozzle standby position.

[0123] Next, the processing unit 1 performs a drying process on the substrate W (step S4: drying process). For example, the rotary motor 22 increases the rotation speed of the substrate W to dry the substrate W (so-called spin drying). During the drying process, the processing liquid scattered from the periphery of the substrate W is also received by the inner peripheral surface of the protection part 40. After the drying process is fully performed, the rotary motor 22 stops the rotation of the substrate W.

[0124] 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 the respective guard standby positions.

[0125] Next, the substrate holding part 20 releases the holding of the substrate W, and the main transport robot 103 takes out the processed substrate W from the processing unit 1 (step S6: holding release and unloading process). Since the protection part 40 stops at the protection member standby position when the substrate W is unloaded, the hand of the main transport robot 103 can be prevented from colliding with the protection part 40.

[0126] As described above, the substrate W is processed by appropriately operating various components in the processing unit 1. For example, the substrate holding portion 20 holds the substrate W or releases the holding. In addition, the first nozzle 30 moves between the nozzle processing position and the nozzle standby position, and sprays the processing liquid onto the substrate W at the nozzle processing position. The respective guards 41 to 43 of the guard portion 40 move to height positions corresponding to each process.

[0127] <Monitoring Process>

[0128] If these components do not operate properly, processing of the substrate W becomes inappropriate. Therefore, in the present embodiment, the processing unit 1 monitors at least one of the above components as a monitoring object.

[0129] <Nozzle Position Monitoring>

[0130] For example, if the first nozzle 30 cannot be moved to the nozzle processing position due to an abnormality in the arm driving motor or the like, the substrate W is not properly processed. Therefore, first, a case where the processing unit 1 monitors the position of the first nozzle 30 will be described.

[0131] In the above example, the first nozzle 30 moves to the nozzle processing position (step S3 ) while the substrate holding portion 20 holds the substrate W. However, the first nozzle 30 may also move to the nozzle processing position while the substrate holding portion 20 does not hold the substrate W.

[0132] For example, when the processing unit 1 processes a plurality of substrates W, impurities may accumulate in various components in the chamber 10. For example, impurities in the processing liquid may precipitate and accumulate on the inner peripheral surface of the protection portion 40. Therefore, a chamber cleaning process for cleaning the inside of the chamber 10 is appropriately performed.

[0133] In the chamber cleaning process, the first nozzle 30 can move to the nozzle processing position and spray the cleaning liquid (e.g., pure water) in a state where the substrate holding part 20 does not hold the substrate W. When the rotary motor 22 rotates the spin base 21, the cleaning liquid landed on the upper surface 21a of the spin base 21 spreads and scatters from the periphery of the spin base 21, and collides with the inner peripheral surface of the guard 40. Thus, the inner peripheral surface of the guard 40 can be cleaned with the cleaning liquid.

[0134] When cleaning the guard 40, if the first nozzle 30 cannot be moved to the nozzle processing position due to an abnormality in the arm driving motor, etc., the guard 40 cannot be properly cleaned. Therefore, the processing unit 1 may monitor the position of the first nozzle 30 during the cleaning process.

[0135] In addition, a preparation process (also referred to as a pre-process) may be performed before the liquid processing step (step S3) on the substrate W. In the pre-process, the first nozzle 30 may eject the processing liquid from the nozzle processing position when the substrate holding portion 20 is not holding the substrate W. In this case, the processing unit 1 may monitor the position of the first nozzle 30.

[0136] Furthermore, during maintenance, the first nozzle 30 may be moved to the nozzle processing position in a state where the substrate holding portion 20 does not hold the substrate W. In this case, the processing unit 1 may monitor the position of the first nozzle 30 .

[0137] Figure 6 and Figure 7 70 is a diagram schematically showing an example of an image captured by the camera 70. Figure 6 and Figure 7In the example of FIG. 4 , the entire upper periphery of the outer guard 43 is included in the captured image. That is, the camera 70 is set so that the entire upper periphery of the outer guard 43 is included in the captured area. Here, since the camera 70 captures the captured area obliquely downward, the upper periphery of the outer guard 43, which is circular in plan view, has an elliptical shape in the captured image.

[0138] exist Figure 6 In the captured image of , the substrate holding portion 20 holds the substrate W, and the first nozzle 30 is located at the nozzle processing position. Figure 6 The captured image can be obtained, for example, by capturing the captured image area with the camera 70 in a state where the first nozzle 30 has not yet ejected the processing liquid in the liquid processing step (step S3).

[0139] exist Figure 7 In the captured image of , the substrate holding portion 20 does not hold the substrate W, and the first nozzle 30 is located at the nozzle processing position. Figure 7 The captured image can be obtained by, for example, capturing the captured area with the camera 70 in any of the chamber cleaning process, pre-processing, and maintenance, when the first nozzle 30 has not yet ejected the processing liquid.

[0140] since Figure 6 and Figure 7 It can be seen that the background area around the front end portion of the first nozzle 30 in the captured image is different depending on the presence or absence of the substrate W. Specifically, when the substrate W is present, the background area includes the upper surface of the substrate W, and when the substrate W is not present, the background area includes the upper surface 21a of the rotating base 21 instead of the substrate W.

[0141] In this way, the environmental state in the chamber 10 is not always the same, but can change. The environmental state described here can be expressed by the presence, position and shape of objects in the chamber 10 other than the monitoring object (here, the first nozzle 30). In the above example, the environmental state includes a substrate-existing state (equivalent to the first environmental state) in which the substrate W exists in the chamber 10, and a substrate-free state (equivalent to the second environmental state) in which the substrate W does not exist in the chamber 10. Here, the substrate-existing state is a state in which the substrate W exists in the substrate holding portion 20, and the substrate-free state is a state in which the substrate W does not exist in the substrate holding portion 20.

[0142] In the present embodiment, the control unit 9 monitors the state of the monitoring object based on the captured image in a determination process according to the environmental state. Figure 8 This is a flowchart showing an example of a flowchart of monitoring processing by the processing unit 1 .

[0143] First, the environmental state determination unit 91 of the control unit 9 determines the environmental state (step S11: environmental state determination step). Specifically, the environmental state determination unit 91 determines whether the environmental state is a substrate-present state or a substrate-absent state. This determination is performed, for example, as follows.

[0144] The environmental state determination unit 91 may receive data indicating whether the substrate W exists from the process control unit 93. For example, the process control unit 93 may control various components of the substrate processing apparatus 100, and when the main transport robot 103 carries the substrate W into the process unit 1, the environmental state determination unit 91 is given data indicating that the substrate W exists in the chamber 10, and when the main transport robot 103 carries the substrate W out of the process unit 1, the environmental state determination unit 91 is given data indicating that the substrate W does not exist in the chamber 10. Based on these data, the environmental state determination unit 91 may determine whether the environmental state is a state in which the substrate exists or a state in which the substrate does not exist.

[0145] Alternatively, a sensor for detecting the substrate W may be provided in the chamber 10. The environmental state determination unit 91 may determine whether the environmental state is a state in which a substrate is present or a state in which a substrate is absent based on the detection result of the sensor.

[0146] Next, the camera 70 captures the captured area to generate a captured image, and outputs the captured image to the control unit 9 (step S12: capturing step). When the capturing step is performed in the liquid processing step, as described above, the captured image can be obtained. Figure 6 In addition, when the imaging process is performed during any of the chamber cleaning process, pre-processing, and maintenance, as described above, an image can be obtained. Figure 7 The captured image.

[0147] In addition, the environmental state determination unit 91 may also determine the environmental state based on the image captured by the camera 70. In this case, the environmental state determination process is performed after the capturing process. Figure 6 and Figure 7 As shown in the example, the substrate determination area R1 can also be set in the captured image. Figure 6 The captured image includes at least a portion of the substrate W. The position and size of the substrate determination area R1 are not particularly limited. Figure 6In the example, it is an area corresponding to the central part of the substrate W. The pixel values ​​in the substrate determination area R1 are different depending on the presence or absence of the substrate W. Therefore, the environmental state determination unit 91 can determine the presence or absence of the substrate W based on the pixel values ​​in the substrate determination area R1. For example, the environmental state determination unit 91 can determine that there is a substrate W when the statistical value (such as the average value) of the pixel values ​​in the substrate determination area R1 is within a specified range. Alternatively, the substrate determination area R1 of the captured image when there is no substrate W can be set as a reference image and pre-stored in the storage unit 94. The environmental state determination unit 91 compares the reference image with the substrate determination area R1 to determine the presence or absence of the substrate W. The storage unit 94 is, for example, a non-volatile memory.

[0148] Next, the monitoring processing unit 92 monitors the state of the monitoring object based on the captured image captured by the camera 70 in a determination process corresponding to the environmental state determined by the environmental state determination unit 91 (step S13: monitoring process). That is, when the environmental state is the first environmental state (here, the substrate-existing state), the monitoring processing unit 92 uses the first determination process corresponding to the first environmental state. On the other hand, when the environmental state is the second environmental state different from the first environmental state (here, the substrate-free state), the monitoring processing unit 92 uses the second determination process corresponding to the second environmental state and different from the first determination process.

[0149] Fig. 9 1 is a flowchart showing a specific example of the monitoring process. First, the monitoring processing unit 92 determines whether the substrate W is present in the captured image (step S21 ). The monitoring processing unit 92 can recognize the presence or absence of the substrate W based on the environmental state determined by the environmental state determination unit 91 .

[0150] When the substrate W is present, that is, when the environmental state is the substrate present state, the monitoring processing unit 92 reads the first reference image data (hereinafter referred to as the reference image) M11 from the storage unit 94 (step S22). Figure 6 As illustrated, the first reference image M11 is an image having a size smaller than that of the captured image. The first reference image M11 includes the front end portion of the first nozzle 30, and the substrate W is included in the background area around the front end portion. Such a first reference image M11 can be obtained, for example, in the following manner. That is, in a state where the substrate holding portion 20 holds the substrate W and the first nozzle 30 is located at the nozzle processing position, the camera 70 captures the captured area to generate a captured image. Furthermore, the control unit 9 generates the first reference image M11 by cutting out a portion of the area including the front end portion of the first nozzle 30 from the captured image. The first reference image M11 is pre-stored in the storage unit 94. The storage unit 94 is, for example, a non-volatile, non-temporary memory.

[0151] Next, the monitoring processing unit 92 monitors the position of the first nozzle 30 by comparing the captured image from the camera 70 and the read reference image (here, the first reference image M11) (step S23). More specifically, first, the monitoring processing unit 92 detects the position of the first nozzle 30 by matching the captured image with the first reference image M11. The matching process includes, for example, template matching. As a specific example, the monitoring processing unit 92 scans the first reference image M11 in the captured image, and detects the position with the highest similarity between the first reference image M11 and each partial area in the captured image as the position of the first nozzle 30. The similarity is not particularly limited, and for example, it can be a well-known similarity such as the sum of squared differences in pixel values, the sum of absolute differences in pixel values, normalized cross correlation, and zero-mean normalized cross correlation.

[0152] The monitoring processing unit 92 can determine whether the detection position of the first nozzle 30 is within the prescribed position range. The monitoring processing unit 92 can determine that the position of the first nozzle 30 is normal when the detection position is within the prescribed position range, and determine that an abnormality related to the position of the first nozzle 30 occurs when the detection position is outside the prescribed position range.

[0153] On the other hand, when there is no substrate W, that is, when the environmental state is a substrate-free state, the monitoring processing unit 92 reads the second reference image M12 from the storage unit 94 (step S24). Figure 7 As illustrated, the second reference image M12 is also an image having a smaller size than the captured image. The second reference image includes the front end portion of the first nozzle 30, and includes the upper surface 21a of the rotating base 21 instead of the substrate W in the background area around the front end portion. Such a second reference image M12 can be obtained, for example, in the following manner. That is, when the substrate holding portion 20 does not hold the substrate W and the first nozzle 30 is located at the nozzle processing position, the camera 70 captures the captured area to generate a captured image. In addition, the control unit 9 generates the second reference image M12 by cutting out a portion of the area including the front end portion of the first nozzle 30 from the captured image. The second reference image M12 is pre-stored in the storage unit 94. That is, a plurality of reference images corresponding to the environmental state (here, the first reference image M11 and the second reference image M12) are pre-stored in the storage unit 94.

[0154] Next, the monitoring processing unit 92 monitors the position of the first nozzle 30 by comparing the captured image from the camera 70 with the read reference image (here, the second reference image M12) (step S23). More specifically, the monitoring processing unit 92 detects the position of the first nozzle 30 by matching the captured image with the second reference image M12. The monitoring processing unit 92 can determine that the position of the first nozzle 30 is normal when the detected position of the first nozzle 30 is within the prescribed position range, and determine that an abnormality related to the position of the first nozzle 30 has occurred when the detected position is outside the prescribed position range.

[0155] As described above, the monitoring processing unit 92 monitors the state of the monitoring object (here, the first nozzle 30) based on the comparison between the captured image and the reference image corresponding to the environmental state. Specifically, when the environmental state is the substrate-existing state, that is, when the substrate W exists in the captured area, the first reference image M11 is used. In the substrate-existing state, the substrate W is also included in the background area of ​​the captured image, and the substrate W is also included in the background area of ​​the first reference image M11. Therefore, the similarity between each partial area of ​​the captured image and the first reference image M11 is not easily affected by the substrate W in the background area.

[0156] For comparison, the case where the second reference image M12 is used when the environment state is a substrate-present state is described. Since the background region of the second reference image M12 includes the upper surface 21a of the rotating base 21, even if the region representing the first nozzle 30 is completely consistent with the second reference image M12 in the partial region, the similarity between each partial region of the captured image and the second reference image M12 will be affected by the difference in the background region. That is, in the matching process between the captured image and the second reference image M12, the difference in the background region may become a factor of error in position detection.

[0157] On the other hand, by using the first reference image M11 when the environmental state is the substrate-present state, the similarity is less likely to be affected by the background region. Therefore, the monitoring processing unit 92 can detect the position of the first nozzle 30 with higher accuracy.

[0158] Similarly, when the environmental state is the substrate-free state, the monitoring processing unit 92 can detect the position of the first nozzle 30 with higher accuracy by performing the matching process between the captured image and the second reference image M12 .

[0159] As described above, in this embodiment, when the processing unit 1 monitors a predetermined state of the monitored object (here, the position of the first nozzle 30), the control unit 9 uses a determination process corresponding to the environmental state in the shooting area. In other words, when the control unit 9 detects a certain abnormality related to the monitored object, the determination process is different according to the environmental state. Thus, regardless of whether the environmental state is the first environmental state or the second environmental state, the control unit 9 can monitor the state of the monitored object with higher accuracy.

[0160] In the above example, the presence or absence of the substrate W has been described, but the present invention is not necessarily limited to this. In short, the environmental state identification unit 91 and the monitoring processing unit 92 only need to operate as follows.

[0161] That is, the environmental state determination unit 91 determines the presence or absence of an object (here, the substrate W) around the monitoring object (here, the first nozzle 30) in the imaging area to determine the environmental state. That is, the environmental state determination unit 91 determines whether the environmental state is a state with an object or a state without an object. When the environmental state is a state with an object, the monitoring processing unit 92 reads out a first reference image (here, the first reference image M11) including the object and the monitoring object from the storage unit 94, and monitors the state of the monitoring object by comparing the first reference image with the image captured by the camera 70. In addition, when the environmental state is a state without an object, the monitoring processing unit 92 reads out a second reference image (here, the second reference image M12) including the monitoring object but not the object from the storage unit 94, and monitors the state of the monitoring object by comparing the second reference image with the image captured by the camera 70. Thus, the monitoring processing unit 92 can monitor the state of the monitoring object with high accuracy in both the state with an object and the state without an object.

[0162] <Determination of environmental status>

[0163] In the above example, the environmental state determination unit 91 determines the environmental state based on the data from the process control unit 93, the detection results from the separately provided sensor, or the captured image from the camera 70. In this way, the environmental state determination unit 91 can use the data of the process control unit 93, but the reliability is not necessarily high. This is because even if the process control unit 93 controls various components of the substrate processing apparatus 100, there are cases where various components cannot operate normally due to abnormalities. In this case, the reliability of the data from the process control unit 93 is reduced.

[0164] In this regard, when using the detection results of the sensor or the captured images of the camera 70, the environmental state determination unit 91 can directly confirm the environmental state, thereby being able to determine the environmental state with higher accuracy. In addition, since when using the captured images, a sensor different from the camera 70 is not required, the manufacturing cost of the processing unit 1 can also be avoided from increasing.

[0165] The environmental state determination unit 91 may also determine the environmental state using a learned model. The learned model is, for example, a model (algorithm) generated by a machine learning algorithm such as deep learning. The learned model classifies the input captured image into any one of the following two first environmental categories and second environmental categories. The first environmental category is a category corresponding to the first environmental state, and in the above example, it is a category indicating that a substrate W exists in the substrate holding unit 20. The second environmental category is a category corresponding to the second environmental state, and in the above example, it is a category indicating that a substrate W does not exist in the substrate holding unit 20. Such a learned model is generated, for example, by learning in the learning model to establish teacher data corresponding to the correct category (label) for a plurality of learning data.

[0166] <Nozzle discharge monitoring>

[0167] Next, a case where the processing unit 1 monitors the ejection state of the first nozzle 30 is described. Droplets of the processing liquid may sometimes fall from the ejection outlet of the first nozzle 30 (so-called dripping). For example, when the ejection of the processing liquid from the first nozzle 30 is stopped, droplets of the processing liquid may fall from the first nozzle 30. When such droplets fall on the upper surface of the substrate W, an undesirable situation may occur. Therefore, here, the control unit 9 monitors the ejection state of the processing liquid from the first nozzle 30 based on the captured image.

[0168] Fig.10 This is a diagram schematically showing an example of a captured image when a droplet L1 of the processing liquid falls from the discharge port of the first nozzle 30 . Fig.10 In the captured image of , a plurality of droplets L1 are included just below the lower end of the first nozzle 30 located at the nozzle processing position. Fig.10 In the example of FIG. 1 , the ejection determination area R2 is also shown. The ejection determination area R2 is located directly below the lower end of the first nozzle 30 in the captured image, and is set to include the processing liquid ejected from the first nozzle 30. The ejection determination area R2 is set to be larger than the droplet L1. Fig.10 As shown in the example, the discharge determination area R2 also includes the upper surface of the substrate W. Fig.10 In the example, the upper surface of the substrate W is almost uniform.

[0169] Since the pixel value in the discharge determination region R2 when the droplet L1 is generated is different from the pixel value in the discharge determination region R2 when the droplet L1 is not generated, the presence or absence of the droplet L1 can be determined based on the pixel value in the discharge determination region R2.

[0170] For example, since the pixel values ​​in the ejection determination area R2 when the droplet L1 is not generated are values ​​corresponding to the almost uniform upper surface of the substrate W, they are substantially uniform. That is, the deviation of the pixel values ​​in the ejection determination area R2 is small. On the other hand, the deviation of the pixel values ​​in the ejection determination area R2 when the droplet L1 is generated becomes large.

[0171] However, there are cases where various patterns of metals, semiconductors, insulators, etc., and circuit patterns are formed on the upper surface of the substrate W. When light is incident on the upper surface of such a substrate W, the light is reflected according to the pattern on the upper surface of the substrate W. Therefore, in the brightness distribution on the upper surface of the substrate W, the deviation of the brightness value becomes large.

[0172] Fig.11 1 is a diagram schematically showing an example of a captured image when a droplet L1 of the processing liquid falls from the discharge port of the first nozzle 30. Fig.11 In the captured image, a pattern is formed on the upper surface of the substrate W. Fig.11 In the case where a plurality of patterns are formed on the upper surface of the substrate W, even if a plurality of droplets L1 are not generated, the deviation of the pixel value in the ejection determination area R2 becomes larger. This is because the light is reflected according to the pattern on the upper surface of the substrate W, and the deviation of the brightness value on the upper surface of the substrate W becomes larger. Fig.11 In the example, the state of light reflection is schematically represented by a rectangular block with oblique hatching.

[0173] As described above, among the substrates W carried into the processing unit 1, there are pattern substrates having a plurality of fine patterns formed on their upper surfaces and uniform substrates having a uniform upper surface compared to the pattern substrates. In other words, the environmental state includes a pattern substrate state (equivalent to the first environmental state) in which a plurality of patterns are formed on the upper surface of the substrate W, and a uniform substrate state (equivalent to the second environmental state) in which almost no pattern is formed on the upper surface of the substrate W.

[0174] When the environmental state is a uniform substrate state, the upper surface of the substrate W is uniform. Therefore, if the droplet L1 is not generated, the deviation of the pixel value in the ejection determination area R2 is small. On the other hand, if the droplet L1 is generated, the deviation becomes large. Therefore, as long as an index representing the deviation (hereinafter referred to as the deviation index) is calculated, the presence or absence of the droplet L1 can be determined based on the deviation index.

[0175] On the other hand, when the environmental state is the pattern substrate state, even if the droplet L1 is not generated, the variation of the pixel value in the discharge determination area R2 is large. Therefore, in the determination based on the variation index, the determination accuracy is reduced.

[0176] Therefore, the monitoring processing unit 92 makes the determination algorithm different according to the pattern substrate state and the uniform substrate state in the monitoring process of the discharge state of the first nozzle 30 .

[0177] An example of monitoring processing for the discharge state of the first nozzle 30 Figure 8 The flowchart of is the same. First, in step S11, the environmental state determination unit 91 determines whether the environmental state is a pattern substrate state or a uniform substrate state. As a specific example, the environmental state determination unit 91 can receive substrate data indicating the presence or absence of a pattern on the substrate W from the processing control unit 93. The processing control unit 93 can obtain the substrate data, for example, through an input from a device on the upstream side of the substrate processing device 100 or an operator. The processing control unit 93 can assign the substrate data to the environmental state determination unit 91 when controlling the main transport robot 103 to move the substrate W into the processing unit 1. The environmental state determination unit 91 can determine whether the environmental state is a pattern substrate state or a uniform substrate state based on the substrate data.

[0178] Alternatively, a sensor for detecting the presence or absence of a pattern on the substrate W may be provided in the chamber 10. The environmental state determination unit 91 may determine whether the environmental state is a patterned substrate state or a uniform substrate state based on data from the sensor.

[0179] Alternatively, the environmental state determination unit 91 may also determine the presence or absence of a pattern on the substrate W based on the captured image captured by the camera 70. For example, when the substrate holding unit 20 autonomously transfers the robot 103 to receive the substrate W, that is, in the holding and carrying process (step S1), the camera 70 captures the captured area. The environmental state determination unit 91 receives the captured image from the camera 70 and calculates a deviation index within the captured image, for example, a substrate determination area R21. The substrate determination area R21 is set to an area including the upper surface of the substrate W held by the substrate holding unit 20. If the deviation index of the substrate determination area R21 is large, the substrate W is a pattern substrate, and if the deviation index of the substrate determination area R21 is small, the substrate W is a uniform substrate.

[0180] Therefore, the environmental state determination unit 91 compares the deviation index with a predetermined pattern threshold. The pattern threshold is preset, for example, by simulation or experiment. When the deviation index is above the pattern threshold, the environmental state determination unit 91 determines that a pattern is formed in the substrate W. In other words, the environmental state determination unit 91 determines that the environmental state is a pattern substrate state. On the other hand, when the deviation index does not reach the pattern threshold, the environmental state determination unit 91 determines that a pattern is not formed in the substrate W. In other words, the environmental state determination unit 91 determines that the environmental state is a uniform substrate state. In addition, the substrate determination area R1 may be used instead of the substrate determination area R21.

[0181] Next, in step S12, the camera 70 captures the captured area during the liquid processing step (step S3) to generate a captured image, and outputs the captured image to the control unit 9. The camera 70 can repeatedly capture the captured area at a predetermined time interval during the liquid processing step. Thus, the ejection state of the first nozzle 30 can be monitored during all periods of the liquid processing step.

[0182] Next, in step S13, the monitoring processing unit 92 monitors the state of the monitoring object based on the captured image in a determination process corresponding to the environmental state determined by the environmental state determination unit 91. That is, the monitoring processing unit 92 determines the discharge state of the first nozzle 30 based on the captured image captured in the liquid processing step. Fig.12 This is a flowchart showing a specific example of the monitoring process.

[0183] First, the monitoring processing unit 92 determines whether a pattern is formed on the upper surface of the substrate W in the discharge determination region R2 (step S31 ). The monitoring processing unit 92 can recognize the presence or absence of a pattern based on the environmental state determined by the environmental state determination unit 91 .

[0184] When no pattern is formed on the substrate W, that is, when the environmental state is a uniform substrate state, the monitoring processing unit 92 monitors the discharge state of the first nozzle 30 by comparing the deviation index with a predetermined deviation threshold value (step S32 ).

[0185] First, the monitoring processing unit 92 calculates the captured image (reference Fig.10 ) is a deviation index of the pixel value in the ejection determination area R2. The deviation index may be, for example, a standard deviation. When the environmental state is a uniform substrate state, if no droplets L1 are generated, the deviation index becomes smaller, and if droplets are generated, the deviation index becomes larger.

[0186] Therefore, the monitoring processing unit 92 compares the deviation index with a specified deviation threshold. The deviation threshold is preset, for example, by simulation or experiment. When the deviation index is greater than the deviation threshold, the monitoring processing unit 92 determines that the droplet L1 is generated. That is, the monitoring processing unit 92 determines that an abnormality related to the ejection state (here, dripping) has occurred. On the other hand, when the deviation index is less than the deviation threshold, the monitoring processing unit 92 determines that the droplet L1 is not generated. That is, the monitoring processing unit 92 determines that the ejection state is normal.

[0187] On the other hand, when a pattern is formed on the substrate W, that is, when the environmental state is the pattern substrate state, the monitoring processing unit 92 monitors the discharge state of the first nozzle 30 based on the learned model (step S33 ).

[0188] The learned model is, for example, a model (algorithm) generated based on a machine learning algorithm such as deep learning. The learned model classifies the input captured image into one of the following two categories: the first category and the second category. The first category is a category indicating that no droplet L1 is generated, and the second category is a category indicating that droplet L1 is generated. Such a learned model is generated, for example, by learning in the learning model to establish teacher data corresponding to the correct category (label) for a plurality of learning data.

[0189] The monitoring processing unit 92 generates images (reference Fig.11 ) is input to the learned model. The monitoring processing unit 92 classifies the captured image using the learned model to determine whether or not there is a droplet L1.

[0190] As described above, when the uniform upper surface of the substrate W is included in the ejection determination area R2 of the captured image, the monitoring processing unit 92 monitors the ejection state of the first nozzle 30 by comparing the deviation index with the deviation threshold. Therefore, the monitoring processing unit 92 can more simply process the monitoring ejection state. Specifically, the monitoring processing unit 92 can more simply process the determination of the presence or absence of the droplet L1. Therefore, the load of the control unit 9 can be reduced. Moreover, in the uniform substrate state, the determination accuracy using the comparison of the deviation index with the deviation threshold is higher than the determination accuracy when the learned model is used.

[0191] On the other hand, when the upper surface of the substrate W on which a pattern is formed is included in the ejection determination area R2 of the captured image, the monitoring processing unit 92 monitors the ejection state of the first nozzle 30 based on the learned model. Therefore, even when a pattern is formed on the upper surface of the substrate W, the monitoring processing unit 92 can monitor the ejection state with higher accuracy.

[0192] <Protective parts monitoring>

[0193] Next, the processing unit 1 will be described as monitoring the guard 40. As described above, the lifting state of the guard 40 varies in each process. Hereinafter, as an example, the processing unit 1 will be described as monitoring the height position of the outer guard 43 when only the outer guard 43 is located at the guard processing position.

[0194] Fig.13 70 is a diagram schematically showing an example of an image captured by the camera 70. Fig.13 In the captured image, only the outer protective member 43 is located at the protective member processing position.

[0195] exist Fig.13 , a guard determination region R3 for monitoring processing is also shown. The guard determination region R3 is a region for determining the position of the outer guard 43. The guard determination region R3 is a region including at least a portion of the outer guard 43 when it is normally located at the guard processing position. Fig.13 In the example, the guard determination region R3 is set to include a portion of the upper peripheral edge of the outer guard 43. More specifically, the guard determination region R3 is set to include a portion of the upper portion of the elliptical upper peripheral edge of the outer guard 43 in the captured image.

[0196] Here, a reference image M3 is set in advance. The reference image M3 is an image of the same area as the guard determination area R3 and is generated based on a normal imaging area captured by the camera 70 when the outer guard 43 is normally stopped at the guard processing position. The reference image M3 is stored in advance in the storage unit 94 .

[0197] If the similarity between the guard determination area R3 of the captured image and the reference image M3 is high, it is considered that the outer guard 43 is normally located at the guard processing position. Therefore, as described in detail below, the monitoring processing unit 92 calculates the similarity between the guard determination area R3 and the reference image M3, and compares the similarity with a predetermined guard threshold (equivalent to the threshold). If the similarity is higher than the guard threshold, it is determined that the outer guard 43 is normally located at the guard processing position.

[0198] However, if the camera 70 captures the captured area at a time point when the processing unit 1 has not yet supplied the processing liquid to the substrate W, the captured image does not include the processing liquid. Therefore, the guard determination area R3 also does not include the processing liquid.

[0199] On the other hand, when the processing unit 1 supplies the processing liquid to the rotating substrate W, the processing liquid scatters from the periphery of the substrate W, and the scattered processing liquid adheres to the inner peripheral surface of the shield 40 . Fig.14 1 is a diagram schematically showing an example of an image captured when the processing liquid is scattered from the periphery of the substrate W. Fig.14In the captured image of , a columnar processing liquid is ejected from the first nozzle 30 , and the processing liquid spreads on the upper surface of the substrate W and scatters from the periphery of the substrate W. A part of the scattered processing liquid is also included in the guard determination region R3 .

[0200] As described above, there are cases where the processing liquid is supplied to the substrate W and the processing liquid is scattered from the periphery of the substrate W, and there are cases where the processing liquid is not supplied to the substrate W and the processing liquid is not scattered from the substrate W. In other words, the environmental state includes a liquid state (equivalent to the first environmental state) in which the processing liquid is scattered from the substrate W, and a liquid-free state (equivalent to the second environmental state) in which the processing liquid is not present. In the liquid state, the processing liquid collides with the inner peripheral surface of the outer shield 43, and in the liquid-free state, the processing liquid does not collide with the outer shield 43.

[0201] In the case where the treatment liquid is included in the guard determination area R3, even if the outer guard 43 is normally located at the guard processing position, the similarity between the guard determination area R3 and the reference image M3 may decrease. This is because the treatment liquid is included in the guard determination area R3 of the captured image, while the treatment liquid is not included in the reference image M3. In this case, even if the outer guard 43 is normally located at the guard processing position, the similarity may be lower than the guard threshold. If the similarity is lower than the guard threshold, the processing unit 1 will mistakenly detect the abnormality of the outer guard 43.

[0202] Therefore, in the monitoring process of the outer guard 43 , the monitoring processing unit 92 sets the guard threshold value to a different value depending on the state where liquid is present and the state where liquid is absent.

[0203] An example of monitoring processing of the height position of the outer guard 43 is Figure 8 The flowchart of is the same. That is, in step S11, the environmental state determination unit 91 determines whether the environmental state is a state with liquid or a state without liquid. As a specific example, the environmental state determination unit 91 can also determine the environmental state based on data from the processing control unit 93. For example, the processing control unit 93 can also give the environmental state determination unit 91 data indicating that the first nozzle 30 sprays the processing liquid at the nozzle processing position. When the environmental state determination unit 91 receives the data, it can determine that the environmental state is a state with liquid, and when the data is not received, it can determine that the environmental state is a state without liquid.

[0204] Alternatively, the environmental state determination unit 91 may also determine the environmental state based on the captured image from the camera 70. In this case, step S11 is executed after step S12 (shooting process). For example, the environmental state determination unit 91 may determine whether the processing liquid is ejected based on the pixel value in the ejection determination area R2 of the captured image. Since the pixel value in the ejection determination area R2 when the processing liquid in the form of a liquid column is ejected from the first nozzle 30 is different from the pixel value in the ejection determination area R2 when the processing liquid is not ejected from the first nozzle 30, the environmental state determination unit 91 may determine whether the processing liquid in the form of a liquid column is ejected based on the pixel value in the ejection determination area R2. For example, the environmental state determination unit 91 may determine that the processing liquid in the form of a liquid column is ejected from the first nozzle 30 when the statistical value (e.g., the sum) of the pixel values ​​in the ejection determination area R2 is within a specified liquid column range. In other words, the environmental state determination unit 91 may determine that the environmental state is a liquid state. When the statistical value (for example, the total) is outside a predetermined liquid column range, the environmental state determination unit 91 may determine that the processing liquid is not ejected from the first nozzle 30. In other words, the environmental state determination unit 91 may determine that the environmental state is a liquid-free state.

[0205] In step S12, the camera 70 captures the captured area to generate a captured image, and outputs the captured image to the control unit 9. Here, in the liquid processing step (step S3) in which the outer shield 43 is located at the shield processing position, the camera 70 can continuously capture the captured area. Thus, the height position of the outer shield 43 can be monitored throughout the liquid processing step.

[0206] In the liquid treatment process, first, the process control unit 93 outputs a control signal for moving the outer guard 43 to the guard treatment position to the guard lifting mechanism 55. The guard lifting mechanism 55 moves the outer guard 43 to the guard treatment position based on the control signal. Then, at a second time point later than the first time point after a sufficient time for the outer guard 43 to stay at the guard position, the process control unit 93 opens the valve 35 to eject the treatment liquid from the first nozzle 30.

[0207] If the guard lifting mechanism 55 operates normally, the captured image obtained by the camera 70 capturing the captured area after the first time point includes the outer guard 43 located at the guard handling position. The following describes the case where the camera 70 captures the captured area after the first time point.

[0208] Next, in step S13 , the monitoring processing unit 92 monitors the height position of the outer guard 43 based on the captured image in a determination process according to the environmental state specified by the environmental state specifying unit 91 . Fig.15 This is a flowchart showing a specific example of the monitoring process.

[0209] First, the monitoring processing unit 92 determines whether the protection member determination area R3 contains the processing liquid (step S41 ). The monitoring processing unit 92 can recognize the presence or absence of the processing liquid based on the environmental state determined by the environmental state determination unit 91 .

[0210] When there is no processing liquid, that is, when the environment is in a liquid-free state, the monitoring processing unit 92 sets a first guard threshold (equivalent to the first threshold) as a guard threshold for monitoring the outer guard 43 described later (step S42). The first guard threshold is a relatively large value, for example, set in advance.

[0211] Next, the monitoring processing unit 92 calculates the similarity between the guard determination area R3 of the captured image and the reference image M3, and monitors the position of the outer guard 43 by comparing the similarity with the guard threshold (here, the first guard threshold) (step S43). The similarity is not particularly limited, and for example, it can be a well-known similarity such as the sum of squares of pixel value differences, the sum of absolute values ​​of pixel value differences, normalized cross-correlation, and zero-mean normalized cross-correlation. If the similarity between the guard determination area R3 and the reference image M3 is high, it is considered that the outer guard 43 is normally stopped at the guard processing position.

[0212] The monitoring processing unit 92 determines that the outer guard 43 is normally located at the guard handling position when the similarity is equal to or greater than the guard threshold, and determines that an abnormality has occurred in the outer guard 43 when the similarity is less than the guard threshold.

[0213] On the other hand, when the process liquid is present, that is, when the environment is in the liquid state, the monitoring processing unit 92 sets a second guard threshold (equivalent to the second threshold) as the guard threshold (step S44). The second guard threshold is smaller than the first guard threshold and is set in advance, for example.

[0214] Next, the monitoring processing unit 92 monitors the position of the outer guard 43 by comparing the similarity between the guard determination area R3 of the captured image and the reference image M3 with the guard threshold (here, the second guard threshold) (step S43). The monitoring processing unit 92 determines that the outer guard 43 is normally located at the guard processing position when the similarity is greater than the guard threshold, and determines that an abnormality has occurred in the outer guard 43 when the similarity is less than the guard threshold.

[0215] As described above, when the processing liquid is not included in the guard determination area R3 of the captured image, a larger first guard threshold is used as the guard threshold. Therefore, the monitoring processing unit 92 can detect an abnormality of the outer guard 43 with higher accuracy. That is, when there is no processing liquid, which is a factor of similarity reduction, a larger first guard threshold is used as the guard threshold, thereby more strictly monitoring the height position of the outer guard 43. In this way, even a slight abnormality can be detected.

[0216] On the other hand, when the processing liquid is included in the guard determination region R3 of the captured image, the second guard threshold smaller than the first guard threshold is used as the guard threshold. Therefore, erroneous detection of abnormality due to the processing liquid, which is a factor of reduced similarity, can be suppressed.

[0217] In the above example, the outer protection member 43 is monitored, but the same is true when the monitored object is the chuck pin 26. Fig.13 and Fig.14 As shown in the example, the captured image includes the chuck pin 26. Fig.13 and Fig.14 In the captured image of , the chuck pins 26 are located at the holding position and abut against the peripheral edge of the substrate W. When the chuck pins 26 are not located at the holding position due to an abnormality, the substrate holding unit 20 cannot hold the substrate W appropriately.

[0218] exist Fig.13 and Fig.14 The pin determination area R31 is also shown in the captured image. The pin determination area R31 is set to an area including at least a portion of the chuck pin 26 normally located at the holding position. Fig.13 Although only one pin determination region R31 is shown in FIG. 1 , in reality, the pin determination regions R31 are set corresponding to all the chuck pins 26 .

[0219] Here, a reference image M31 is set in advance. The reference image M31 is an image of the same region as the pin determination region R31 and is generated based on a normal imaging region imaged by the camera 70 when the chuck pin 26 is normally stopped at the holding position. The reference image M31 is stored in advance in the storage unit 94 .

[0220] If the similarity between the pin determination area R31 of the captured image and the reference image M31 is high, it is considered that the chuck pin 26 is normally located at the holding position. Therefore, the monitoring processing unit 92 calculates the similarity between the pin determination area R31 and the reference image M31, and compares the similarity with the pin threshold. The monitoring processing unit 92 determines that the chuck pin 26 is located at the holding position when the similarity is greater than the pin threshold, and determines that an abnormality has occurred in the chuck pin 26 when the similarity is less than the pin threshold.

[0221] However, when the processing unit 1 does not supply the processing liquid to the substrate W, the processing liquid does not collide with the chuck pins 26. Fig.13 In the example, the processing liquid is not included in the pin determination area R31.

[0222] On the other hand, when the processing unit 1 supplies the processing liquid to the substrate W, the processing liquid may collide with the chuck pins 26. Specifically, the processing liquid flows radially outward on the upper surface of the substrate W, and a part of the processing liquid collide with the chuck pins 26. Fig.14In the example of , the processing liquid is included in the pin determination region R31. In this case, even if the chuck pin 26 is normally located at the holding position, the similarity is reduced.

[0223] Therefore, the monitoring processing unit 92 can set the pin threshold value according to the presence or absence of the processing liquid in the pin determination area R31, similarly to the outer protection member 43. More specifically, the monitoring processing unit 92 sets a larger first pin threshold value (equivalent to the first threshold value) as the pin threshold value when there is no processing liquid, and sets a second pin threshold value (equivalent to the second threshold value) smaller than the first pin threshold value as the pin threshold value when there is processing liquid.

[0224] <Presence or absence of smoke>

[0225] Next, a situation in which smoke originating from the processing liquid is generated is described. For example, there is a situation in which the first nozzle 30 sprays a mixed liquid (SPM liquid) of sulfuric acid and hydrogen peroxide water as the processing liquid. The temperature of the SPM liquid is set to 150°C to 200°C, for example. The SPM liquid can, for example, remove the resist formed on the upper surface of the substrate W. After the resist is sufficiently removed, the processing unit 1 stops the supply of sulfuric acid. Since hydrogen peroxide water is still supplied after the supply of sulfuric acid is stopped, the hydrogen peroxide water pushes the sulfuric acid in the first nozzle 30 out and discharges it. As a result, in various subsequent processes, the possibility of sulfuric acid accidentally falling from the first nozzle 30 can be reduced.

[0226] When hydrogen peroxide solution is supplied after the supply of sulfuric acid is stopped, the proportion of hydrogen peroxide solution on the upper surface of the substrate W increases. Therefore, a large amount of hydrogen peroxide solution reacts with sulfuric acid to generate an atmosphere containing a large amount of fine particles called fumes. Fig.16 FIG. 1 is a diagram schematically showing an example of an image captured when smoke is generated. Fig.16 In the example of , the captured image includes smoke around the first nozzle 30 .

[0227] As described above, there are cases where smoke is not generated and cases where smoke is generated in the space above the substrate W in the chamber 10. That is, the environmental state includes a smoke state (corresponding to the first environmental state) where smoke is generated and a non-smoke state (corresponding to the second environmental state) where smoke is not generated.

[0228] Also, when smoke is generated, Fig.16 As can be understood, the contrast in the captured image is reduced. When the contrast is reduced, the monitoring accuracy related to various monitoring objects may be reduced.

[0229] Therefore, the monitoring processing unit 92 makes the determination algorithm different depending on whether there is smoke or no smoke in the monitoring process on the monitoring object.

[0230] An example of monitoring processing Figure 8That is, in step S11, the environment state determination unit 91 determines whether the environment state is a smoke state or a smoke-free state. As a specific example, the environment state determination unit 91 can determine the environment state based on the captured image captured by the camera 70. In this case, step S11 is executed after step S12 (photographing process).

[0231] For example, the environmental state determination unit 91 calculates the contrast of the captured image and determines whether the contrast is within a specified smoke range. The environmental state determination unit 91 determines that smoke is generated when the contrast is within the specified smoke range, and determines that smoke is not generated when the contrast is outside the specified smoke range. The smoke range is pre-set, for example, by simulation or experiment.

[0232] In addition, the environmental state determination unit 91 may calculate the contrast of only a portion of the captured image where smoke is likely to be generated. Alternatively, a reference image when smoke is not generated may be pre-stored in the storage unit 94, and the environmental state determination unit 91 may determine the environmental state by comparing the captured image with the reference image.

[0233] In step S12, the camera 70 captures the captured area to generate a captured image, and outputs the captured image to the control unit 9. Here, during the liquid processing step (step S3), the camera 70 can continuously capture the captured area. Thus, the monitored object can be monitored throughout the liquid processing step.

[0234] Next, in step S13 , the monitoring processing unit 92 monitors the state of the monitoring target based on the captured image in a determination process according to the environmental state specified by the environmental state specifying unit 91 . Fig.17 This is a flowchart showing a specific example of the monitoring process.

[0235] First, the monitoring processing unit 92 determines whether smoke is generated (step S51 ). The monitoring processing unit 92 can recognize the presence or absence of smoke based on the environmental state specified by the environmental state specifying unit 91 .

[0236] When smoke is generated, that is, when the environment state is a smoke state, the monitoring processing unit 92 performs contrast enhancement processing to increase the contrast of the captured image, and generates enhanced image data (hereinafter referred to as enhanced image) (step S52). The contrast enhancement processing includes, for example, well-known processing such as histogram equalization. In the enhanced image, for example, various objects such as the first nozzle 30, the processing liquid ejected from the first nozzle 30, the guard 40, and the chuck pin 26 can be more clearly recognized.

[0237] Next, the monitoring processing unit 92 monitors the state of the monitoring object based on the emphasized image (step S53). For example, the monitoring processing unit 92 may monitor the discharge state of the first nozzle 30 based on the discharge determination area R2 of the emphasized image, or may monitor the height position of the outer guard 43 based on the guard determination area R3 of the emphasized image, or may monitor the position of the chuck pin 26 based on the pin determination area R31 of the emphasized image.

[0238] On the other hand, when smoke is not generated, that is, when the environmental state is a smoke-free state, the monitoring processing unit 92 does not perform contrast enhancement processing on the captured image, but monitors the state of the monitored object based on the captured image (step S54). For example, the monitoring processing unit 92 may monitor the ejection state of the first nozzle 30 based on the ejection determination area R2 of the captured image, or may monitor the height position of the outer guard 43 based on the guard determination area R3 of the captured image, or may monitor the position of the chuck pin 26 based on the pin determination area R31 of the captured image.

[0239] As described above, when smoke is generated, the monitoring processing unit 92 monitors the monitoring object based on the contrast-enhanced image. Therefore, the monitoring processing unit 92 can monitor the state of the monitoring object with higher accuracy. On the other hand, when smoke is not generated, the monitoring processing unit 92 monitors the state of the monitoring object based on the captured image. Therefore, the monitoring processing unit 92 does not need to perform contrast-enhanced processing, and the load of the control unit 9 can be reduced.

[0240] In the above example, the monitoring processing unit 92 changes whether to perform contrast enhancement processing according to the presence or absence of smoke, but it is not necessarily limited to this. For example, the monitoring processing unit 92 may set the threshold to a larger first threshold in the presence of smoke, and set the threshold to a smaller second threshold in the absence of smoke. Alternatively, a first reference image containing smoke and a normal monitoring object and a second reference image containing no smoke but a normal monitoring object may be pre-stored in the storage unit 94. The monitoring processing unit 92 may monitor the state of the monitoring object by comparing the captured image with the first reference image in the presence of smoke, and monitor the state of the monitoring object by comparing the captured image with the second reference image in the absence of smoke.

[0241] <Second Embodiment>

[0242] Fig.181 is a diagram schematically showing an example of the structure of a substrate processing apparatus 100A according to the second embodiment. The substrate processing apparatus 100A includes a processing unit 1A. Although not shown in the figure, the substrate processing apparatus 100A includes various structures such as a loading port for carrying in and out a conveyor storing a plurality of substrates W, and a substrate conveying unit (not shown) for conveying a plurality of substrates W between the loading port and the processing unit 1A. In addition, the substrate processing apparatus 100A may also include a plurality of processing units 1A.

[0243] The processing unit 1A includes a processing tank 15A, a lifting unit 20A, a liquid supply unit 30A, a liquid discharge unit 40A, and a camera 70A.

[0244] exist Fig.18 In the example of , a chamber 10A is also provided. Fig.18 In the example of the present invention, the chamber 10A has a box-like shape that is opened vertically upward. An openable and closable cover may be provided at the upper end of the chamber 10A.

[0245] The processing tank 15A is provided in the chamber 10A, and has a box-like shape that is opened vertically upward. The processing tank 15A stores a processing liquid.

[0246] The liquid supply unit 30A supplies the processing liquid to the processing tank 15A. Fig.18 In the example of , the liquid supply unit 30A includes a nozzle 31A, a liquid supply pipe 32A and a valve 33A. The nozzle 31A is provided at the lower side in the processing tank 15A. The downstream end of the liquid supply pipe 32A is connected to the nozzle 31A, and the upstream end of the liquid supply pipe 32A is connected to the processing liquid supply source 34A. The processing liquid supply source 34A has a tank (not shown) for storing the processing liquid.

[0247] The valve 33A is provided on the liquid supply pipe 32A. When the valve 33A is opened, the processing liquid is supplied from the processing liquid supply source 34A to the nozzle 31A through the liquid supply pipe 32A, and is ejected from the ejection port of the nozzle 31A to the processing tank 15A. When the valve 33A is closed, the supply of the processing liquid to the processing tank 15A ends.

[0248] The lifting unit 20A (equivalent to the substrate holding unit) holds the substrate W and lifts the held substrate W. The lifting unit 20A can hold a plurality of substrates W. For example, the lifting unit 20A holds a plurality of substrates W in a state where the plurality of substrates W are arranged at intervals in the thickness direction of the substrate W. Fig.18In the example of FIG. 1 , the lifting unit 20A includes a connecting plate 21A and a plurality of supporting members 22A. The connecting plate 21A is arranged with its thickness direction along the horizontal direction. The plurality of supporting members 22A have a strip shape extending along the thickness direction of the connecting plate 21A, and one end thereof is connected to the connecting plate 21A. A plurality of grooves (not shown) for inserting a plurality of substrates W are formed in each supporting member 22A. By inserting the substrate W into the groove of the supporting member 22A, the supporting member 22A supports the substrate W in an upright posture.

[0249] The lifting unit 20A has a lifting mechanism (not shown) to lift the plurality of substrates W between a processing position inside the processing tank 15A and a lifting position vertically above the processing tank 15A. The lifting mechanism has, for example, a ball screw mechanism and a motor to lift the connecting plate 21A. As a result, the plurality of substrates W supported by the supporting member 22A are also lifted. The lifting unit 20A lowers the plurality of substrates to the processing position, thereby allowing the plurality of substrates W to be immersed in the processing liquid.

[0250] The drain section 40A discharges the treatment liquid from the treatment tank 15A to the outside. The drain section 40A includes a drain pipe 41A and a valve 42A. The upstream end of the drain pipe 41A is connected to, for example, the bottom of the treatment tank 15A, and the downstream end of the drain pipe 41A is connected to the outside. The valve 42A is provided on the drain pipe 41A. If the valve 42A is opened, the treatment liquid is supplied to the outside from the treatment tank 15A through the drain pipe 41A. If the valve 42A is closed, the discharge of the treatment liquid ends.

[0251] The processing liquid is supplied to the processing tank 15A by the liquid supply unit 30A, and the processing liquid is stored in the processing tank 15A, and the processing liquid is discharged from the processing tank 15A by the liquid discharge unit 40A, and the processing tank 15A becomes empty. In addition, the empty mentioned here refers to a state in which at least a part of the bottom of the processing tank 15A is not covered by the processing liquid and is exposed.

[0252] As described above, the environmental state in the chamber 10A includes a storage state in which the processing liquid is stored in the processing tank 15A and an empty state in which the processing tank 15A is empty.

[0253] The camera 70A is disposed vertically above the processing tank 15A and captures a capture area including the interior (specifically, the bottom) of the processing tank 15A. Fig.18 In the example of , the camera 70A is disposed above the chamber 10A. Fig.18 In the example, the camera 70A is disposed directly above the processing tank 15A, and the camera 70A is disposed in such a manner that its photographing direction is along a vertical downward direction.

[0254] exist Fig.18In the example of , an illumination unit 71A is also provided. The illumination unit 71A is also provided vertically above the processing tank 15A. The illumination unit 71A illuminates the imaging area of ​​the camera 70A.

[0255] In such a processing unit 1A, the control unit 9 can also monitor various components in the chamber 10A as monitoring objects based on the captured images from the camera 70A. As a specific example, the monitoring object includes the bottom of the processing tank 15A. Sometimes, fragments of the substrate W remain at the bottom of the processing tank 15A. That is, when a defect (i.e., a break) occurs in the plurality of substrates W held by the lifting unit 20A, the fragments fall to the bottom of the processing tank 15A.

[0256] Here, after the lifting unit 20A lifts the substrate W from the processing tank 15A and transfers the substrate W to a substrate transfer unit (not shown), the camera 70A captures an image of the captured area. The control unit 9 determines whether there are fragments of the substrate W in the bottom of the processing tank 15A based on the captured image.

[0257] However, in the storage state where the processing liquid is stored in the processing tank 15A, it is difficult to visually recognize the bottom of the processing tank 15A. This is because light is reflected by the liquid surface of the processing liquid stored in the processing tank 15A. Therefore, it is also difficult to visually recognize the fragments of the substrate W remaining at the bottom of the processing tank 15A. On the other hand, in the empty state where the processing tank 15A is not stored with the processing liquid, it is easy to visually recognize the bottom of the processing tank 15A.

[0258] Therefore, in the monitoring process of the bottom of the processing tank 15A, the monitoring processing unit 92 sets the threshold value to a different value depending on the storage state and the empty state.

[0259] An example of monitoring processing of the bottom of the processing tank 15A Figure 8 The flowchart of is the same. That is, in step S11, the environmental state determination unit 91 determines whether the environmental state is a storage state or an empty state. As a specific example, the environmental state determination unit 91 can also determine the environmental state based on data from the processing control unit 93. For example, when the liquid supply unit 30A is made to supply the processing liquid, the processing control unit 93 can give the environmental state determination unit 91 data indicating the storage state, and when the liquid discharge unit 40A is made to discharge the processing liquid and the processing tank 15A is set to be empty, the data indicating the empty state is output to the environmental state determination unit 91.

[0260] Alternatively, a sensor for detecting the presence or absence of the processing liquid in the processing tank 15A may be provided in the chamber 10A. The environmental state determination unit 91 may determine the environmental state based on the detection result of the sensor.

[0261] Alternatively, the environmental state determination unit 91 may also determine the environmental state based on the captured images taken by the camera 70. In this case, step S11 is executed after step S12. When a processing liquid is stored in the processing tank 15A, the plurality of captured images captured in a time series may be different from each other due to the fluctuation of the liquid level of the processing liquid. On the other hand, if the processing tank 15A is empty, the plurality of captured images captured in a time series are ideally consistent with each other. Therefore, the environmental state determination unit 91 can calculate the inter-frame difference of the captured images captured in a time series, and determine the environmental state based on the inter-frame difference. For example, when the sum of the inter-frame differences is greater than a specified liquid threshold, the environmental state determination unit 91 determines that a processing liquid is stored in the processing tank 15A. In other words, the environmental state determination unit 91 determines that the environmental state is a storage state. On the other hand, when the sum is less than the liquid threshold, the environmental state determination unit 91 determines that the processing liquid is not stored in the processing tank 15A. In other words, the environmental state determination unit 91 determines that the environmental state is an empty state. The liquid threshold value is preset, for example, through simulation or experiment.

[0262] In step S12, the camera 70A captures the captured area to generate a captured image, and outputs the captured image to the control unit 9. Here, the camera 70A captures the captured area including the bottom of the processing tank 15A in a state where the lifting unit 20A does not hold a plurality of substrates W.

[0263] Next, in step S13 , the monitoring processing unit 92 determines whether or not there are fragments of the substrate W in the processing tank 15A based on the captured image in a determination process according to the environmental state determined by the environmental state determination unit 91 . Fig.19 This is a flowchart showing a specific example of the monitoring process according to the second embodiment.

[0264] First, the monitoring processing unit 92 determines whether the processing liquid is stored in the processing tank 15A (step S61 ). The monitoring processing unit 92 can recognize the presence or absence of the processing liquid based on the environmental state determined by the environmental state determination unit 91 .

[0265] When there is no processing liquid, that is, when the environment is in an empty state, the monitoring processing unit 92 sets a first debris threshold as a debris threshold for monitoring the presence of debris of the substrate W described later (step S42). The first debris threshold is a relatively large value, for example, set in advance.

[0266] Next, the monitoring processing unit 92 calculates the similarity between the captured image and the reference image for monitoring the debris. The reference image for monitoring the debris mentioned here is an image of the bottom of the processing tank 15A in which the processing tank 15A is empty and does not contain the debris of the substrate W. The reference image is generated based on a normal captured image captured by the camera 70 in a state in which the processing tank 15A is empty and no debris of the substrate W remains inside the processing tank 15A.

[0267] The monitoring processing unit 92 compares the similarity with a debris threshold (here, the first debris threshold) to determine whether there is debris on the substrate W (step S63). If the similarity between the captured image and the reference image for debris monitoring is high, it is considered that no debris on the substrate W remains.

[0268] The monitoring processing unit 92 determines that no fragments remain when the similarity is equal to or greater than the fragment threshold, and determines that fragments remain when the similarity is less than the fragment threshold.

[0269] On the other hand, when the processing liquid is present, that is, when the environmental state is the storage state, the monitoring processing unit 92 sets the second fragmentation threshold as the fragmentation threshold (step S62). The second fragmentation threshold is smaller than the first fragmentation threshold and is set in advance, for example.

[0270] Next, the monitoring processing unit 92 determines whether there is debris on the substrate W by comparing the similarity between the captured image and the reference image for debris monitoring and the debris threshold (here, the second debris threshold) (step S63). The monitoring processing unit 92 determines that there is no debris left when the similarity is greater than the predetermined debris threshold, and determines that debris has occurred when the similarity is less than the debris threshold.

[0271] As described above, when the processing liquid is not stored in the processing tank 15A, a larger first fragmentation threshold is used as the fragmentation threshold. Therefore, the monitoring processing unit 92 can detect fragmentation (abnormality) with higher accuracy. That is, when the processing liquid, which is the cause of the decrease in similarity, is not stored, a larger first fragmentation threshold is used as the fragmentation threshold, thereby more strictly determining the presence or absence of fragmentation. In this way, even tiny fragments can be detected.

[0272] On the other hand, when the processing liquid is not stored in the processing tank 15A, the second debris threshold value lower than the first debris threshold value is used as the debris threshold value. Therefore, it is possible to suppress erroneous detection of debris caused by liquid surface reflection of the processing liquid.

[0273] <Third Embodiment>

[0274] In the third embodiment, the monitoring processing unit 92 uses a first learned model corresponding to a first environmental state and a second learned model corresponding to a second environmental state according to the environmental state. The first learned model is a learned model generated using a machine learning algorithm such as deep learning, and is generated based on first learning data captured in the first environmental state. When monitoring the position of the first nozzle 30, the first learning data captured in a substrate-containing state (first environmental state) is used. Specifically, a plurality of first learning data captured when the first nozzle 30 is normally located at the nozzle processing position in a substrate-containing state and its label (normal) are used as teacher data, and a plurality of first learning data captured when the first nozzle 30 is not located at the nozzle processing position in a substrate-containing state and its label (abnormal) are used as teacher data, and learning is performed in the learning model, thereby generating the first learned model. The first learned model classifies the captured image into either a normal category indicating normality or an abnormal category indicating abnormality.

[0275] The second learned model is a learned model generated using a machine learning algorithm such as deep learning, and is generated based on learning data captured in the second environmental state. When monitoring the position of the first nozzle 30, the second hand data captured in the substrate-free state (second environmental state) is used. Specifically, teacher data including a plurality of second learning data captured when the first nozzle 30 is normally located at the nozzle processing position in the substrate-free state and its label (normal), and teacher data including a plurality of second learning data captured when the first nozzle 30 is not located at the nozzle processing position in the substrate-free state and its label (abnormal) are used to learn in the learning model, thereby generating the second learned model. The second learned model classifies the captured image into either a normal category or an abnormal category.

[0276] Flowchart of monitoring processing in the third embodiment Figure 8 However, the monitoring processing unit 92 varies the learned model according to the environmental state. Fig. 20 This is a flowchart showing an example of the monitoring process according to the third embodiment.

[0277] First, the monitoring processing unit 92 determines whether the substrate W is present in the captured image (step S71 ). The monitoring processing unit 92 can recognize the presence or absence of the substrate W based on the environmental state identified by the environmental state identification unit 91 .

[0278] When there is a substrate W, that is, when the environmental state is a substrate-present state, the monitoring processing unit 92 uses the first learned model to monitor the position of the first nozzle 30 (step S72). More specifically, the monitoring processing unit 92 inputs the captured image to the first learned model, and the first learned model classifies the captured image into either a normal category or an abnormal category.

[0279] When there is no substrate W, that is, when the environmental state is a substrate-free state, the monitoring processing unit 92 uses the second learned model to monitor the position of the first nozzle 30 (step S73). More specifically, the monitoring processing unit 92 inputs the captured image to the second learned model, and the second learned model classifies the captured image into either a normal category or an abnormal category.

[0280] As described above, according to the third embodiment, in the state where the substrate is present, the first learned model generated based on the learning data including the substrate W is used. Since the captured image in the state where the substrate is present includes the substrate W, the first learned model learned based on the first learning data including the substrate W can classify the captured image with high accuracy. In other words, the monitoring processing unit 92 can monitor the position of the first nozzle 30 with higher accuracy.

[0281] In addition, in the state without a substrate, the second learned model generated based on the learning data not including the substrate W is used. Since the captured image does not include the substrate W in the state without a substrate, the second learned model generated based on the second learning data not including the substrate W can classify the captured image with high accuracy. In other words, the monitoring processing unit 92 can monitor the position of the first nozzle 30 with higher accuracy.

[0282] In addition, in the above example, the presence or absence of the substrate W has been described, but it is not necessarily limited to this. For example, as described in the first or second embodiment, the first learned model and the second learned model corresponding to the presence or absence of the processing liquid can be prepared, and the first learned model and the second learned model can be used according to the environmental state. In short, as long as the first learned model generated based on the first learning data that includes an object around the monitored object in the shooting area and the second learned model generated based on the second learning data that does not include an object around the monitored object are prepared, the first learned model and the second learned model can be used according to the environmental state (the state with the object and the state without the object).

[0283] <Other embodiments>

[0284] <Reference Image>

[0285] In the above, in the specific example of monitoring processing using the reference image corresponding to the environmental state, as an example of the first environmental state and the second environmental state, a substrate-existing state (equivalent to an object-existing state) and a substrate-free state (equivalent to an object-free state) are respectively adopted (also refer to Figure 6 and Figure 7 ). However, it is not necessarily limited thereto.

[0286] For example, the already described liquid state (equivalent to the state with an object) and liquid-free state (equivalent to the state without an object) may be used as the first environmental state and the second environmental state. That is, the object in the state with an object and the state without an object may be a processing liquid. As the monitoring object at this time, for example, the protective part 40, the chuck pin 26 or the processing tank 15A may be used. In the case where the protective part 40 is the monitoring object, it is sufficient to pre-set a first reference image in which the protective part 40 stops at a normal position in the liquid state and a second reference image in which the protective part 40 stops at a normal position in the liquid-free state, and use either the first reference image or the second reference image according to the environmental state. The monitoring process when the chuck pin 26 is the monitoring object is also the same. When the processing tank 15A is the monitoring object, it is sufficient to pre-set a first reference image showing that the processing tank 15A is normal in a liquid state where the processing liquid is stored, and a second reference image showing that the processing tank 15A is normal in a liquid-free state where the processing liquid is not stored. Depending on the environmental conditions, either the first reference image or the second reference image can be used.

[0287] In addition, the aforementioned state with smoke (equivalent to the state with an object) and state without smoke (equivalent to the state without an object) may be used as the first environmental state and the second environmental state. That is, the object in the state with an object and the state without an object may be smoke originating from the processing liquid generated above the substrate W. As the monitoring object at this time, for example, the protective part 40 or the chuck pin 26 may be used. In the case where the protective part 40 is the monitoring object, it is sufficient to pre-set a first reference image in which the protective part 40 is in a normal position in the state with smoke and a second reference image in which the protective part 40 is in a normal position in the state without smoke, and use either the first reference image or the second reference image according to the environmental state. The monitoring process when the chuck pin 26 is the monitoring object is the same.

[0288] <Threshold>

[0289] In the above example, in the monitoring process using the threshold value corresponding to the environmental state, as an example of the first environmental state and the second environmental state, the liquid state (equivalent to the object state) and the liquid-free state (equivalent to the object-free state) are used for explanation respectively (see also Fig.13 and Fig.14 ). However, it is not necessarily limited thereto.

[0290] For example, the substrate-presence state (equivalent to the object-presence state) and substrate-absence state (equivalent to the object-absence state) described above may be used as the first environmental state and the second environmental state. That is, the object in the object-presence state and the object-absence state may be the substrate W in the substrate holding portion 20. As the monitoring object in this case, for example, the first nozzle 30 may be used. Specifically, a reference image including the first nozzle 30 in the substrate-presence state is pre-set, and the position of the first nozzle 30 is calculated by template matching. Furthermore, when the environmental state is the substrate-presence state, when the difference between the calculated position of the first nozzle 30 and the target position is greater than the first threshold value, it may be determined that an abnormality related to the first nozzle 30 has occurred, and when the environmental state is the substrate-absence state, when the difference is greater than the second threshold value, it may be determined that the abnormality has occurred.

[0291] In addition, the pattern substrate state (equivalent to the state with an object) and the uniform substrate state (equivalent to the state without an object) described above may also be used as the first environmental state and the second environmental state. That is, the object in the state with an object and the state without an object may be a pattern in the substrate W. As the monitoring object at this time, for example, the first nozzle 30 may be used. Specifically, a reference image including the first nozzle 30 in the uniform substrate state is pre-set, and the position of the first nozzle 30 is calculated by template matching. Furthermore, when the environmental state is the uniform substrate state, when the difference between the calculated position of the first nozzle 30 and the target position is above a higher first threshold value, it may be determined that an abnormality has occurred, and when the environmental state is the pattern substrate state, when the difference is above a lower second threshold value, it may be determined that an abnormality has occurred.

[0292] In addition, the aforementioned smoke plate state (equivalent to the state with an object) and the state without smoke (equivalent to the state without an object) may be used as the first environmental state and the second environmental state. That is, the object in the state with an object and the state without an object may be smoke. As the monitoring object at this time, for example, the first nozzle 30 or the protective part 40 may be used. When the monitoring object is the first nozzle 30, the same as described above. When the protective part 40 is the monitoring object, a reference image of the protective part 40 normally positioned in the state without smoke may be pre-set. When the environmental state is the state without smoke, when the similarity between the captured image and the reference image is less than the higher first threshold value, it is determined that an abnormality related to the protective part 40 has occurred. When the environmental state is the state with smoke, when the similarity is less than the lower second threshold value, it is determined that the abnormality has occurred.

[0293] In addition, the above-mentioned liquid state (equivalent to the state with an object) and liquid-free state (equivalent to the state without an object) may be used as the first environmental state and the second environmental state. As the monitoring object at this time, for example, the processing tank 15A may be used. In this case, a reference image containing a normal processing tank 15A in the liquid-free state is pre-set. When the environmental state is the liquid-free state, when the similarity between the captured image and the reference image is less than the higher first threshold value, it is determined that an abnormality related to the processing tank 15A has occurred. When the environmental state is the liquid state, when the similarity is less than the lower second threshold value, it is determined that the abnormality has occurred.

[0294] <Machine Learning>

[0295] In the monitoring process using the learned model corresponding to the environmental state, the first environmental state and the second environmental state are not limited to the above example. For example, the smoke state (equivalent to the object state) and the non-smog state (equivalent to the object state) described above can also be used as the first environmental state and the second environmental state. In this case, as the monitoring object, for example, the protection unit 40 can be used. In this case, a learned model generated based on a plurality of teacher data in the non-smog state and a learned model generated based on a plurality of teacher data in the smoke state are used. When the environmental state is a smoke state, the captured image can be input into the learned model corresponding to the smoke state to determine whether there is an abnormality related to the protection unit 40. When the environmental state is a non-smog state, the captured image can be input into the learned model corresponding to the non-smog state to determine whether there is an abnormality related to the protection unit 40.

[0296] In addition, the liquid state (equivalent to the state with an object) and the liquid-free state (equivalent to the state without an object) described above can also be used as the first environmental state and the second environmental state. In this case, as the monitoring object, for example, the protective part 40, the chuck pin 26 or the processing tank 15A can be used. Specifically, a learned model generated based on a plurality of teacher data in a state without a processing liquid and a learned model generated based on a plurality of teacher data in a state with a processing liquid are used. When the environmental state is a liquid state, the captured image can be input into the learned model corresponding to the liquid state to determine the presence or absence of an abnormality related to the protective part 40, the chuck pin 26 or the processing tank 15A. When the environmental state is a liquid-free state, the captured image can be input into the learned model corresponding to the liquid-free state to determine the presence or absence of the abnormality.

[0297] As described above, although the substrate processing apparatus 100 and the monitoring method have been described in detail, the above description is illustrative in all aspects and is not limited thereto. It should be understood that numerous variations that are not exemplified can be conceived without departing from the scope of the disclosure. The various configurations described in the above embodiments and various variations can be appropriately combined or omitted as long as they do not contradict each other.

[0298] [Description of Reference Numerals]

[0299] 10.10A: Chamber

[0300] 100: Substrate processing device

[0301] 20: Substrate holding part

[0302] 20A: Substrate holding part (lifting part)

[0303] 26: Chuck pin

[0304] 30: Nozzle (No. 1)

[0305] 60: Nozzle (No. 2 nozzle)

[0306] 68: Nozzle (No. 3)

[0307] 41: Protective parts (inner protective parts)

[0308] 42: Protective parts (middle protective parts)

[0309] 43: Protective parts (external protective parts)

[0310] 70, 70A: Camera

[0311] 9. 9A: Camera

[0312] 94: Storage

[0313] S11: Environmental status determination process (step)

[0314] S12: Photographing process (step)

[0315] S13: Monitoring process (step)

[0316] W: substrate

Claims

1. A substrate processing device, wherein: have: Chamber; a substrate holding portion for holding the substrate in the chamber; a camera that captures a capture area in the chamber that includes the monitored object and generates captured image data; and A control unit that determines the environmental state within the above-mentioned shooting area, and when the above-mentioned environmental state is a first environmental state, monitors the state of the above-mentioned monitored object based on the above-mentioned captured image data by a first judgment process corresponding to the above-mentioned first environmental state, and when the above-mentioned environmental state is a second environmental state different from the above-mentioned first environmental state, monitors the above-mentioned state of the above-mentioned monitored object based on the above-mentioned captured image data by a second judgment process corresponding to the above-mentioned second environmental state and different from the above-mentioned first judgment process.

2. The substrate processing apparatus according to claim 1, wherein: The control unit determines the environmental state based on the captured image data.

3. The substrate processing apparatus according to claim 1 or 2, wherein: The device further comprises: a storage unit storing a plurality of reference image data corresponding to the environmental state; and In the control unit, when the environmental state is the first environmental state, as the first determination process, the state of the monitored object is monitored based on the comparison between the captured image data and the first reference image data corresponding to the first environmental state. In the control unit, when the environmental state is the second environmental state, the state of the monitored object is monitored based on comparison between the captured image data and second reference image data corresponding to the second environmental state as the second determination process.

4. The substrate processing apparatus according to claim 3, wherein: The first environmental state includes a state in which a predetermined object exists in the shooting area; The second environmental state includes a state where the object does not exist in the shooting area; The first reference image data is an image including the object and the monitored object; The second reference image data is an image that does not include the object but includes the monitoring target object.

5. The substrate processing apparatus according to any one of claims 1 to 4, wherein: The algorithm of the first determination process and the algorithm of the second determination process are different from each other.

6. The substrate processing apparatus according to any one of claims 1 to 5, wherein: The threshold value used in the first determination process to monitor the state of the monitoring object is different from the threshold value used in the second determination process to monitor the state of the monitoring object.

7. The substrate processing apparatus according to claim 6, wherein: The device further comprises: a storage unit storing reference image data; The first environmental state includes a state in which a predetermined object exists in the shooting area; The second environmental state includes a state where the object does not exist in the shooting area; The reference image data is an image that does not include the object but includes the monitored object; In the control unit, when the environmental state is the first environmental state, as the first determination process, the similarity between the captured image data and the reference image data is compared with a first threshold value to monitor the state of the monitored object. In the control unit, when the environmental state is the second environmental state, as the second determination process, the similarity between the captured image data and the reference image data is compared with a second threshold value that is smaller than the first threshold value to monitor the state of the monitored object.

8. The substrate processing apparatus according to claim 4 or 7, wherein: The device further comprises: a nozzle that supplies a processing liquid to the substrate from a nozzle processing position above the substrate held by the substrate holding portion; The object includes mist derived from the processing liquid generated above the substrate.

9. The substrate processing apparatus according to any one of claims 1 to 8, wherein: The first environmental state includes a state in which a predetermined object exists in the shooting area; The second environmental state includes a state where the object does not exist in the shooting area; In the control unit, as the first determination process, the captured image data is input into the first learned model, and as the second determination process, the captured image data is input into the second learned model; The first learned model is a learned model generated based on a plurality of learning data including the monitored object and the object, and classifies the captured image data into either a normal category indicating normality or an abnormal category indicating abnormality; The second learned model is a learned model generated based on a plurality of learning data that does not include the object but includes the monitoring target object, and classifies the captured image data into any one of the normal category and the abnormal category.

10. The substrate processing apparatus according to any one of claims 1 to 9, wherein: The monitored object includes at least any one of a chuck pin of the substrate holding portion, a nozzle for supplying a processing liquid to the substrate held by the substrate holding portion, and a cylindrical shield for catching the processing liquid scattered from the periphery of the substrate held by the substrate holding portion.

11. The substrate processing apparatus according to claim 5, wherein: The device further comprises: a nozzle that supplies a processing liquid to the substrate from a nozzle processing position above the substrate held by the substrate holding portion; The first environmental state includes a pattern substrate state in which a pattern is formed on the upper surface of the substrate held by the substrate holding portion; The second environmental state includes a uniform substrate state in which no pattern is formed on the upper surface of the substrate held by the substrate holding portion; In the control unit, when the environmental state is the uniform substrate state, as the first determination process, an index representing a deviation of pixel values ​​in a discharge determination area located directly below the nozzle in the captured image data is calculated, and based on a comparison between the index and a threshold value, it is determined whether or not there are droplets of the processing liquid falling from the nozzle. In the control unit, when the environmental state is the pattern substrate state, as the second determination process, the captured image data is input to a learned model to determine the presence or absence of the droplets.

12. The substrate processing apparatus according to claim 5, wherein: The device further comprises: a nozzle for supplying a processing liquid to the substrate held by the substrate holding portion; The first environmental state includes a smoke-existing state in which smoke originating from the processing liquid is generated above the substrate held by the substrate holding portion; The second environmental state includes a smoke-free state where the smoke is not generated; In the control unit, when the environmental state is the smoky state, as the first determination process, contrast enhancement processing is performed on the captured image data to generate enhanced image data, and the state of the monitored object is monitored based on the enhanced image data. In the control unit, when the environmental state is the non-smog state, the state of the monitoring object is monitored based on the captured image data without performing the contrast enhancement process as the second determination process.

13. A monitoring method, wherein: have: An environmental state determining step of determining an environmental state in a photographing area including a monitoring object in a chamber of a substrate holding portion that stores and holds the substrate; A photographing step, in which a camera photographs the photographing area to generate photographing image data; and A monitoring process, when the above-mentioned environmental state is a first environmental state, a first judgment process corresponding to the above-mentioned first environmental state is used to monitor the state of the above-mentioned monitored object based on the above-mentioned captured image data; when the above-mentioned environmental state is a second environmental state different from the above-mentioned first environmental state, a second judgment process corresponding to the above-mentioned second environmental state and different from the above-mentioned first judgment process is used to monitor the above-mentioned state of the above-mentioned monitored object based on the above-mentioned captured image data.