JP7177628B2 - SUBSTRATE PROCESSING METHOD, SUBSTRATE PROCESSING APPARATUS, AND SUBSTRATE PROCESSING SYSTEM - Google Patents

Description

The present invention relates to a substrate processing method, a substrate processing apparatus, and a substrate processing system.

2. Description of the Related Art Conventionally, there has been proposed a substrate processing apparatus that processes substrates by sequentially supplying different processing liquids to the substrates. This substrate processing apparatus includes a substrate holding portion that holds a substrate in a horizontal position, a rotation mechanism that rotates the substrate holding portion to rotate the substrate in a horizontal plane, a first ejection nozzle that ejects a processing liquid from above the substrate, and and a second ejection nozzle. The first ejection nozzle and the second ejection nozzle each eject the processing liquid from near the center of the substrate in plan view.

When the first processing liquid is discharged from the first discharge nozzle toward the substrate, the first processing liquid lands near the center of the substrate, receives centrifugal force due to rotation of the substrate, and spreads on the substrate. scattered from the perimeter. As the first treatment liquid, SC1 liquid (mixed liquid of ammonia water, hydrogen peroxide water and water), SC2 liquid (mixed liquid of hydrochloric acid, hydrogen peroxide water and water), DHF liquid (dilute hydrofluoric acid), etc. are used. be done. Thereby, the substrate can be processed according to the first processing liquid.

Next, a treatment with a second treatment liquid is performed. That is, the nozzles that eject the treatment liquid are switched from the first ejection nozzles to the second ejection nozzles. Specifically, ejection of the first treatment liquid from the first ejection nozzles is stopped, and ejection of the second treatment liquid from the second ejection nozzles is started. The second processing liquid lands near the center of the substrate, spreads on the substrate due to the centrifugal force accompanying the rotation of the substrate, and scatters from the periphery of the substrate. Pure water, for example, can be used as the second treatment liquid. Thereby, the first processing liquid can be washed away from the substrate.

Techniques have also been proposed in which a camera is used to monitor the discharge state of the processing liquid from the discharge nozzles (for example, Patent Documents 1 and 2). In Patent Documents 1 and 2, an imaging region including the tip of the ejection nozzle is imaged by a camera, and based on the image captured by the camera, it is determined whether or not the treatment liquid is being ejected from the ejection nozzle.

JP 2017-29883 A JP 2015-173148 A

When switching the nozzles that eject the treatment liquid from the first ejection nozzles to the second ejection nozzles, the ejection of the treatment liquid from the first ejection nozzles is stopped and the ejection of the treatment liquid from the second ejection nozzles is started. timing difference is important.

For example, the later the ejection start timing of the processing liquid from the second ejection nozzles relative to the ejection stop timing of the first ejection nozzles, the easier it is for the surface of the substrate to partially dry (liquid dripping). If the surface of the substrate dries out, defects (eg adhesion of particles) can occur.

In order to avoid drying of the substrate, ejection from the second ejection nozzle should be started before the ejection stop timing of the first ejection nozzle. For example, while the ejection of the first treatment liquid is stopped, the ejection amount of the first treatment liquid decreases with the lapse of time and eventually reaches zero. By starting the ejection of the second treatment liquid while the ejection of the first treatment liquid is stopped, the treatment liquid can be continuously supplied onto the substrate, and the possibility of drying the substrate can be reduced.

However, if the ejection start timing of the second ejection nozzle is too early, ejection of the second treatment liquid is started while a sufficient amount of the first treatment liquid is still ejected. In this case, the total amount of processing liquid supplied to the substrate increases, and the processing liquid rebounds on the substrate (liquid splash). The occurrence of such liquid splash is not preferable.

Therefore, it is desirable to adjust the timing difference so that splashes and drips do not occur.

In addition, the timing difference described above may affect the quality of substrate processing. In this case, it is desirable to adjust the timing difference so that the processing result is good.

SUMMARY OF THE INVENTION Accordingly, an object of the present application is to provide a substrate processing method, a substrate processing apparatus, and a substrate processing system capable of switching from the first nozzle to the second nozzle with a desired timing difference.

A first aspect of a substrate processing method is a substrate processing method, wherein a first step of holding a substrate, and an imaging region including the tip of a first nozzle and the tip of a second nozzle are imaged by a camera. a second step of generating a captured image; a third step of starting ejection of the treatment liquid from the first nozzle onto the substrate; stopping ejection of the treatment liquid from the first nozzle; and a start timing for starting ejection of the treatment liquid from the second nozzle and from the first nozzle in the fourth step based on the image processing of the captured image. determining whether or not the timing difference is outside a predetermined range; determining whether the timing difference is outside the predetermined range; a sixth step of adjusting at least one of the start timing and the stop timing so that the timing difference is within the predetermined range when determined ; calculating a statistic based on pixel values in a first ejection determination region extending in the ejection direction of the first nozzle from the tip of the first nozzle in each frame of specifying the stop timing based on the comparison, calculating the statistic based on pixel values in a second ejection determination region extending from the tip of the second nozzle in each frame in the ejection direction of the second nozzle; The start timing is specified based on a comparison between the statistic and the threshold value, and the statistic is a value reflecting the ejection state of the treatment liquid from each of the first nozzle and the second nozzle .

A second aspect of the substrate processing method is the substrate processing method according to the first aspect, wherein the stop timing is adjusted without adjusting the start timing.

A third aspect of the substrate processing method is the substrate processing method according to the first or second aspect, comprising: a frame in which the statistic of pixel values in the first ejection determination region is greater than the threshold; The stop timing is specified based on a frame subsequent to the frame in which the statistic of the first ejection determination region is smaller than the threshold value, and the statistic of the pixel value of the second ejection determination region is The start timing is specified based on a frame smaller than the threshold and a frame next to the frame in which the statistic of the first ejection determination region is larger than the threshold.

A fourth aspect of the substrate processing method is the substrate processing method according to the third aspect, wherein, in the sixth step, graphs showing temporal changes in the statistics for the first nozzle and the second nozzle are provided. The target timing is displayed on a user interface, and when an input for the target timing, which is at least one of the start timing and the stop timing, is made to the user interface, the target timing is adjusted according to the input.
A fifth aspect of the substrate processing method is the substrate processing method according to any one of the first to fourth aspects, wherein the statistic of the first ejection determination region is the number of pixels of the first ejection determination region. The statistic of the second ejection determination area is the integral value or standard deviation of the pixel values of the second ejection determination area.

A sixth aspect of the substrate processing method is a substrate processing method, wherein a first step of holding the substrate, and an imaging region including the tip of the first nozzle and the tip of the second nozzle are imaged by a camera. a second step of generating a captured image; a third step of starting ejection of the treatment liquid from the first nozzle onto the substrate; stopping ejection of the treatment liquid from the first nozzle; and a start timing for starting ejection of the treatment liquid from the second nozzle and from the first nozzle in the fourth step based on the image processing of the captured image. determining whether or not the timing difference is outside a predetermined range; determining whether the timing difference is outside the predetermined range; a sixth step of adjusting at least one of the start timing and the stop timing so that the timing difference is within the predetermined range when determined , and machine learning is completed in the fifth step each frame included in the captured image is classified into discharge/stop of the treatment liquid for each of the first nozzle and the second nozzle, and the timing difference is obtained based on the classification result. .

A seventh aspect of the substrate processing method is the substrate processing method according to the sixth aspect, wherein a frame classified as ejection for the first nozzle and a frame next to the frame classified as ejection for the first nozzle The stop timing is specified based on the frame classified as stop, and the frame classified as stop for the second nozzle and the frame next to the frame classified as discharge for the second nozzle. and specifying the start timing based on the substrate processing method.

An eighth aspect of the substrate processing method is the substrate processing method according to the sixth aspect, wherein the stop timing is after the start timing, and both the first nozzle and the second nozzle supply the processing liquid. The timing difference is determined based on the number of frames classified as fired and the time between the frames.

A ninth aspect of the substrate processing method is the substrate processing method according to any one of the sixth to eighth aspects, wherein in the sixth step, when it is determined that the timing difference is outside a predetermined range and notify the worker to that effect.

A tenth aspect of the substrate processing method is a substrate processing method, wherein a first step of holding the substrate, and an imaging region including the tip of the first nozzle and the tip of the second nozzle are imaged by a camera. a second step of generating a captured image; a third step of starting ejection of the treatment liquid from the first nozzle onto the substrate; stopping ejection of the treatment liquid from the first nozzle; and a start timing for starting ejection of the treatment liquid from the second nozzle and from the first nozzle in the fourth step based on the image processing of the captured image. determining whether or not the timing difference is outside a predetermined range; determining whether the timing difference is outside the predetermined range; and a sixth step of adjusting at least one of the start timing and the stop timing so that the timing difference is within the predetermined range when determined, wherein the stop timing is after the start timing. and determining whether or not there is splashing of the treatment liquid on the substrate based on the image processing of the captured image, and when it is determined that the liquid splashing is occurring, the start timing and a seventh step of adjusting at least one of the start timing and the stop timing so as to reduce a timing difference between the start timing and the stop timing.

An eleventh aspect of the substrate processing method is the substrate processing method according to the tenth aspect, wherein in the seventh step, each frame of the captured image is subjected to the liquid splash using a machine-learned classifier. classified as with or without

A twelfth aspect of the substrate processing method is the substrate processing method according to the eleventh aspect, wherein, in the seventh step, of each frame of the captured image, near the first nozzle and the second nozzle, A liquid splash determination region is cut out, and the classifier is used to classify the liquid splash determination region into presence/absence of liquid splash.

A thirteenth aspect of the substrate processing method is the substrate processing method according to any one of the sixth to eighth, eleventh, and twelfth aspects, wherein the type of the substrate, the type of the processing liquid, the type of the first selecting one of a plurality of machine-learned classifiers according to at least one of the positions of the nozzle and the second nozzle and the flow rate of the processing liquid, and based on the selected classifier to classify each frame included in the captured image.

A fourteenth aspect of the substrate processing method is the substrate processing method according to the thirteenth aspect, wherein the type of the substrate, the type of the processing liquid, the positions of the first nozzle and the second nozzle, and the One of the plurality of classifiers is selected according to the input to the input section when at least one of the flow rates of the treatment liquid is input to the input section.

A first aspect of a substrate processing apparatus has a substrate holder that holds a substrate, a first nozzle that discharges a processing liquid onto the substrate, and a second nozzle that discharges the processing liquid onto the substrate. a processing liquid supply unit; a camera that captures an image of an imaging region including the tip of the first nozzle and the tip of the second nozzle to generate a captured image; After starting the ejection of the processing liquid from the nozzles onto the substrate, the ejection of the processing liquid from the second nozzle onto the substrate is started, and the ejection of the processing liquid from the first nozzle onto the substrate is stopped. to control the treatment liquid supply unit in such a manner as to start the ejection of the treatment liquid from the second nozzle and to stop the ejection of the treatment liquid from the first nozzle based on the image processing of the captured image. At least one of the start timing and the stop timing is obtained so that the timing difference is within the predetermined range when it is determined that the timing difference is outside the predetermined range. When obtaining the timing difference, the control unit adjusts one of pixels in a first ejection determination region extending from the tip of the first nozzle in the ejection direction of the first nozzle in each frame of the captured image. A statistic is calculated based on the value, the stop timing is specified based on a comparison between the statistic and a preset threshold value, and the ejection direction of the second nozzle is determined from the tip of the second nozzle in each frame. calculating the statistic based on the pixel values in the second ejection determination region extending to the It is a value that reflects the ejection state of the treatment liquid from each of the second nozzles .

A second aspect of the substrate processing apparatus has a substrate holder that holds a substrate, a first nozzle that discharges a processing liquid onto the substrate, and a second nozzle that discharges the processing liquid onto the substrate. a processing liquid supply unit; a camera that captures an image of an imaging region including the tip of the first nozzle and the tip of the second nozzle to generate a captured image; After starting the ejection of the processing liquid from the nozzles onto the substrate, the ejection of the processing liquid from the second nozzle onto the substrate is started, and the ejection of the processing liquid from the first nozzle onto the substrate is stopped. to control the treatment liquid supply unit in such a manner as to start the ejection of the treatment liquid from the second nozzle and to stop the ejection of the treatment liquid from the first nozzle based on the image processing of the captured image. At least one of the start timing and the stop timing is obtained so that the timing difference is within the predetermined range when it is determined that the timing difference is outside the predetermined range. Adjusting one, the control unit uses a machine-learned classifier to indicate the discharge/stop state of the treatment liquid for each frame included in the captured image for the first nozzle and the second nozzle. It is classified into categories, and the timing difference is obtained based on the classification result.

A third aspect of the substrate processing apparatus is the substrate processing apparatus according to the second aspect, wherein the controller controls the type of the substrate, the type of the processing liquid, and the type of the first nozzle and the second nozzle. One of a plurality of machine-learned classifiers corresponding to at least one of the position and the flow rate of the treatment liquid is selected, and is included in the captured image based on the selected classifier. Classify each frame.

A fourth aspect of the substrate processing apparatus is the substrate processing apparatus according to the third aspect, wherein the type of the substrate, the type of the processing liquid, the positions of the first nozzle and the second nozzle, and the An input unit for receiving at least one of the flow rates of the treatment liquid is provided, and the control unit selects one of the plurality of classifiers according to the input to the input unit.

A first aspect of a substrate processing system includes a substrate processing apparatus and a server that communicates with the substrate processing apparatus. and a second nozzle for ejecting the treatment liquid onto the substrate, and an imaging region including the tip of the first nozzle and the tip of the second nozzle. a camera for generating a captured image; after starting to discharge the processing liquid from the first nozzle to the substrate, discharging the processing liquid to the substrate from the second nozzle; a control unit that controls the processing liquid supply unit to stop discharging the processing liquid from the substrate processing apparatus and the server using a machine-learned classifier, the captured image are classified into categories indicating the discharge/stop state of the treatment liquid for the first nozzle and the second nozzle, and the discharge of the treatment liquid from the second nozzle is determined based on the classification result. A timing difference between a start timing for starting the ejection of the treatment liquid from the first nozzle and a timing difference for stopping the ejection of the treatment liquid from the first nozzle is obtained. At least one of the start timing and the stop timing is adjusted so that the timing difference is within the predetermined range.

According to the first aspect of the substrate processing method and the first aspect of the substrate processing apparatus, the timing difference between the start timing and the stop timing is obtained based on the image processing of the captured image, so that the timing difference can be obtained with high accuracy. can be done. Therefore, the timing difference can be adjusted within a predetermined range with high accuracy.

As a result, for example, it is possible to substantially avoid the occurrence of splashing of the processing liquid on the substrate and drying of the substrate in which the substrate is partially dried. Moreover, since the pixel values of the first ejection determination region and the second ejection determination region are used, the processing can be lightened compared to the case where image processing is performed on the entire captured image.

According to the second aspect of the substrate processing method, the timing difference can be within a predetermined range without changing the length of the processing period during which the processing liquid is supplied from the first nozzle.

According to the third and fifth aspects of the substrate processing method, the start timing and stop timing can be identified by simple processing.

According to the fourth aspect of the substrate processing method, the operator can visually recognize the time change of the statistic and adjust the timing difference based on the time change.

According to the sixth aspect of the substrate processing method, the second aspect of the substrate processing apparatus, and the first aspect of the substrate processing system, the timing difference can be determined with high accuracy by machine learning.

According to the seventh aspect of the substrate processing method, it is possible to appropriately identify the timing difference.

According to the eighth aspect of the substrate processing method, the timing difference can be specified appropriately.

According to the ninth aspect of the substrate processing method, the operator can recognize that the timing difference is outside the predetermined range.

According to the tenth aspect of the substrate processing method, the timing difference can be adjusted so as to reduce the occurrence of liquid splash.

According to the eleventh aspect of the substrate processing method, the presence or absence of liquid splash can be determined with high accuracy.

According to the twelfth aspect of the substrate processing method, the classification accuracy can be improved.

According to the thirteenth aspect of the substrate processing method and the third aspect of the substrate processing apparatus, each frame can be classified with high accuracy.

According to the fourteenth aspect of the substrate processing method and the fourth aspect of the substrate processing apparatus, the operator can input information to the input section.

It is a figure which shows a schematic example of a structure of a substrate processing apparatus. FIG. 2 is a plan view showing a schematic example of the configuration of a processing unit; FIG. 2 is a plan view showing a schematic example of the configuration of a processing unit; 4 is a flow chart showing an example of the operation of a control unit; FIG. 2 schematically shows an example of a frame generated by a camera; FIG. 2 schematically shows an example of a frame generated by a camera; FIG. 2 schematically shows an example of a frame generated by a camera; FIG. 2 schematically shows an example of a frame generated by a camera; 6 is a flowchart showing a specific example of monitoring processing; 4 is a graph schematically showing an example of luminance distribution within an ejection determination region; 4 is a graph schematically showing an example of luminance distribution within an ejection determination region; 7 is a graph schematically showing an example of temporal change in the statistic of pixel values in the ejection determination region; 7 is a graph schematically showing an example of temporal change in the statistic of pixel values in the ejection determination region; 3 is a functional block diagram schematically showing an example of the internal configuration of a control unit; FIG. 6 is a flowchart showing a specific example of monitoring processing; FIG. 4 is a diagram schematically showing an example of multiple frames of a captured image; 3 is a functional block diagram schematically showing an example of the internal configuration of a control unit; FIG. It is a figure which shows an example of an input screen roughly. 1 is a functional block diagram schematically showing an example of a substrate processing apparatus and a server; FIG. 1 is a diagram schematically showing an example of a deep learning model; FIG. FIG. 2 schematically shows an example of a frame generated by a camera; 7 is a graph schematically showing an example of temporal changes in the statistic of pixel values in the liquid splash determination region; 6 is a flowchart showing a specific example of monitoring processing; FIG. 2 is a plan view showing a schematic example of the configuration of a processing unit; FIG. 2 schematically shows an example of a frame generated by a camera;

Embodiments will be described below with reference to the attached drawings. It should be noted that the drawings are shown schematically, and for the convenience of explanation, the configuration may be omitted or simplified as appropriate. Also, the mutual relationship of sizes and positions of the configurations shown in the drawings are not necessarily described accurately, and may be changed as appropriate.

In addition, in the description given below, the same components are denoted by the same reference numerals, and their names and functions are also the same. Therefore, a detailed description thereof may be omitted to avoid duplication.

First embodiment.
<Overview of substrate processing equipment>
FIG. 1 is a diagram showing the overall configuration of a substrate processing apparatus 100. As shown in FIG. The substrate processing apparatus 100 is an apparatus that processes the substrate W by supplying a processing liquid to the substrate W. As shown in FIG. The substrate W is, for example, a semiconductor substrate. This substrate W has a substantially disk shape.

This substrate processing apparatus 100 can supply at least two kinds of processing liquids to the substrate W in sequence. For example, the substrate processing apparatus 100 can perform a cleaning process by supplying a rinse liquid to the substrate W after supplying the substrate W with a chemical solution for cleaning. The chemical solutions typically include SC1 solution (mixture of ammonia water, hydrogen peroxide solution and water), SC2 solution (hydrochloric acid, hydrogen peroxide solution and water mixture), and DHF solution (dilute hydrofluoric acid). etc. are used. Pure water, for example, is used as the rinsing liquid. In this specification, the chemical liquid and the rinse liquid are collectively referred to as "treatment liquid". In addition to the cleaning process, the "processing liquid" includes a coating liquid such as a photoresist liquid for a film forming process, a chemical liquid for removing unnecessary films, a chemical liquid for etching, and the like.

A substrate processing apparatus 100 includes an indexer 102 , a plurality of processing units 1 and a main transfer robot 103 . The indexer 102 has a function of loading unprocessed substrates W received from outside the apparatus into the apparatus, and unloading processed substrates W that have undergone cleaning processing from the apparatus. The indexer 102 mounts a plurality of carriers and has a transfer robot (not shown). As a carrier, adopt a FOUP (front opening unified pod) or SMIF (Standard Mechanical Interface) pod that stores the substrate W in a sealed space, or an OC (open cassette) that exposes the substrate W to the outside while stored. can be done. The transfer robot transfers the substrate W between the carrier and the main transfer robot 103 .

Twelve processing units 1 are arranged in the substrate processing apparatus 100 . The detailed arrangement configuration is such that four towers in which three processing units 1 are stacked are arranged so as to surround the main transfer robot 103 . In other words, the four processing units 1 arranged around the main transfer robot 103 are stacked in three layers, and FIG. 1 shows one of them. The number of processing units 1 mounted on the substrate processing apparatus 100 is not limited to twelve, and may be, for example, eight or four.

The main transfer robot 103 is installed in the center of four towers in which the processing units 1 are stacked. The main transport robot 103 loads unprocessed substrates W received from the indexer 102 into the respective processing units 1 and unloads the processed substrates W from the respective processing units 1 to deliver them to the indexer 102 .

Next, the processing unit 1 will be explained. One of the 12 processing units 1 mounted on the substrate processing apparatus 100 will be described below, but the other processing units 1 are also the same. FIG. 2 is a plan view of the processing unit 1. FIG. 3 is a longitudinal sectional view of the processing unit 1. FIG. 2 shows a state in which the substrate W is not held by the substrate holding portion 20, and FIG. 3 shows a state in which the substrate W is held by the substrate holding portion 20. As shown in FIG.

In the chamber 10, the processing unit 1 includes, as main elements, a substrate holding part 20 that holds the substrate W in a horizontal posture (a posture in which the normal line of the substrate W is along the vertical direction), and a substrate held by the substrate holding part 20. Three processing liquid supply units 30, 60, 65 for supplying the processing liquid to the upper surface of W, a processing cup 40 surrounding the substrate holding unit 20, and a camera 70 for imaging the space above the substrate holding unit 20. Prepare. A partition plate 15 is provided around the processing cup 40 in the chamber 10 to partition the inner space of the chamber 10 into upper and lower parts.

The chamber 10 includes side walls 11 extending in the vertical direction, a ceiling wall 12 that closes the upper side of the space surrounded by the side walls 11, and a floor wall 13 that closes the lower side. A space surrounded by the side walls 11, the ceiling wall 12, and the floor wall 13 serves as a processing space for the substrates W. As shown in FIG. A loading/unloading port for loading/unloading the substrate W by the main transfer robot 103 into/from the chamber 10 and a shutter for opening/closing the loading/unloading port are provided on a part of the side wall 11 of the chamber 10 (both are shown in the figure). omit).

A fan filter unit (FFU) 14 is attached to the ceiling wall 12 of the chamber 10 for further purifying the air in the clean room in which the substrate processing apparatus 100 is installed and supplying it to the processing space in the chamber 10 . . The fan filter unit 14 is equipped with a fan and a filter (for example, a HEPA filter) for taking in air in the clean room and sending it out into the chamber 10 , and forms clean air downflow in the processing space inside the chamber 10 . In order to uniformly disperse the clean air supplied from the fan filter unit 14 , a punching plate having a large number of blowout holes may be provided immediately below the ceiling wall 12 .

The substrate holder 20 is, for example, a spin chuck. The substrate holding unit 20 includes a disk-shaped spin base 21 fixed in a horizontal posture to the upper end of a rotating shaft 24 extending along the vertical direction. A spin motor 22 that rotates a rotating shaft 24 is provided below the spin base 21 . The spin motor 22 rotates the spin base 21 in the horizontal plane via the rotation shaft 24 . A tubular cover member 23 is provided to surround the spin motor 22 and the rotating shaft 24 .

The outer diameter of the disk-shaped spin base 21 is slightly larger than the diameter of the circular substrate W held by the substrate holder 20 . Therefore, the spin base 21 has a holding surface 21a facing the entire lower surface of the substrate W to be held.

A plurality of (four in this embodiment) chuck pins 26 are erected on the periphery of the holding surface 21 a of the spin base 21 . The plurality of chuck pins 26 are spaced evenly along the circumference corresponding to the outer circumference of the circular substrate W (in the case of four chuck pins 26 as in this embodiment, they are spaced at 90° intervals). ) are placed. A plurality of chuck pins 26 are interlocked and driven by a link mechanism (not shown) housed in the spin base 21 . The substrate holding unit 20 holds the substrate W in a horizontal position above the spin base 21 and close to the holding surface 21a by holding the substrate W with each of the plurality of chuck pins 26 in contact with the outer peripheral edge of the substrate W. (see FIG. 3), and each of the plurality of chuck pins 26 can be separated from the outer peripheral edge of the substrate W to release the grip.

In a state where the substrate holding unit 20 holds the substrate W by gripping with a plurality of chuck pins 26, the spin motor 22 rotates the rotation shaft 24, thereby rotating the rotation axis CX along the vertical direction passing through the center of the substrate W. substrate W can be rotated.

The processing liquid supply unit 30 is configured by attaching a discharge nozzle 31 to the tip of a nozzle arm 32 (see FIG. 2). The base end side of the nozzle arm 32 is fixedly connected to the nozzle base 33 . The nozzle base 33 is rotatable about a vertical axis by a motor (not shown). As the nozzle base 33 rotates, the discharge nozzle 31 moves between the processing position above the substrate holder 20 and the waiting position outside the processing cup 40 as indicated by the arrow AR34 in FIG. Moves in an arc along the horizontal direction.

The processing liquid supply unit 30 is configured to supply a plurality of types of processing liquids. Specifically, the treatment liquid supply unit 30 has a plurality of ejection nozzles 31 . Two ejection nozzles 31 a and 31 b are shown as the ejection nozzle 31 in the examples of FIGS. 2 and 3 . The ejection nozzles 31 a and 31 b are fixed to a nozzle base 33 via a nozzle arm 32 . Therefore, the ejection nozzles 31a and 31b move in synchronization with each other. The ejection nozzles 31a and 31b are provided adjacent to each other in the horizontal plane.

As illustrated in FIG. 3, the discharge nozzle 31a is connected to a processing liquid supply source 37a through a pipe 34a, and the discharge nozzle 31b is connected to a processing liquid supply source 37b through a pipe 34b. On-off valves 35a and 35b are provided in the middle of the pipes 34a and 34b, respectively. By opening the on-off valve 35a, the processing liquid Lq1 from the processing liquid supply source 37a flows inside the pipe 34a and is discharged from the discharge nozzle 31a. Lq2 flows inside the pipe 34b and is discharged from the discharge nozzle 31b. The SC1 liquid, for example, is discharged from the discharge nozzle 31a, and pure water, for example, is discharged from the discharge nozzle 31b. The processing liquids Lq1 and Lq2 ejected while the ejection nozzles 31a and 31b are stopped at the processing positions land on the upper surface of the substrate W held by the substrate holder 20. FIG.

Suck-back valves 36a and 36b may be provided in the middle of the pipes 34a and 34b, respectively. The suck back valve 36a draws in the processing liquid Lq1 from the tip of the discharge nozzle 31a by sucking the processing liquid Lq1 in the pipe 34a when the discharge of the processing liquid Lq1 is stopped. This makes it difficult for the treatment liquid Lq1 to drop as a relatively large lump (droplet) from the tip of the ejection nozzle 31a when the ejection is stopped. The same applies to the suck back valve 36b.

The processing unit 1 of the present embodiment is further provided with two processing liquid supply units 60 and 65 in addition to the processing liquid supply unit 30 described above. The processing liquid supply units 60 and 65 of this embodiment have the same configuration as the processing liquid supply unit 30 described above. That is, the treatment liquid supply unit 60 is configured by attaching a discharge nozzle 61 to the tip of a nozzle arm 62, and the discharge nozzle 61 is connected to an arrow AR64 by a nozzle base 63 connected to the base end of the nozzle arm 62. , moves in an arc between the processing position above the substrate holding part 20 and the standby position outside the processing cup 40. As shown in FIG. Similarly, the treatment liquid supply unit 65 is configured by attaching a discharge nozzle 66 to the tip of a nozzle arm 67 , and the discharge nozzle 66 is moved by a nozzle base 68 connected to the base end of the nozzle arm 67 . , move in an arc between the processing position above the substrate holder 20 and the standby position outside the processing cup 40 . The processing liquid supply units 60 and 65 may also be configured to supply a plurality of types of processing liquid, or may be configured to supply a single processing liquid.

The processing liquid supply units 60 and 65 discharge the processing liquid onto the upper surface of the substrate W held by the substrate holding unit 20 with the discharge nozzles 61 and 66 positioned at the processing positions. At least one of the processing liquid supply units 60 and 65 mixes a cleaning liquid such as pure water with a pressurized gas to generate droplets, and jets a mixed fluid of the droplets and the gas onto the substrate W. A two-fluid nozzle may be used. Further, the number of processing liquid supply units provided in the processing unit 1 is not limited to three, and may be one or more. However, in the present embodiment, since it is assumed that the two treatment liquids are sequentially switched and ejected, two or more ejection nozzles are provided as a whole. Each of the discharge nozzles of the processing liquid supply units 60 and 65 is also connected to the processing liquid supply source through a pipe in the same manner as the processing liquid supply unit 30, and an on-off valve is provided in the middle of the pipe, and a suckback valve is provided in the middle of the pipe. may be provided. Processing using the processing liquid supply unit 30 will be representatively described below.

The processing cup 40 is provided so as to surround the substrate holder 20 . The processing cup 40 has an inner cup 41 , a middle cup 42 and an outer cup 43 . The inner cup 41, the middle cup 42 and the outer cup 43 are provided so as to be able to move up and down. When the inner cup 41 , the middle cup 42 and the outer cup 43 are raised, the processing liquid scattered from the peripheral edge of the substrate W hits the inner peripheral surface of the inner cup 41 and drops. The dropped treatment liquid is appropriately recovered by a first recovery mechanism (not shown). In a state where the inner cup 41 is lowered and the middle cup 42 and the outer cup 43 are raised, the processing liquid scattered from the peripheral edge of the substrate W hits the inner peripheral surface of the middle cup 42 and falls. The dropped treatment liquid is appropriately recovered by a second recovery mechanism (not shown). In a state where the inner cup 41 and the middle cup 42 are lowered and the outer cup 43 is raised, the processing liquid scattered from the peripheral edge of the substrate W hits the inner peripheral surface of the outer cup 43 and falls. The dropped treatment liquid is appropriately recovered by a third recovery mechanism (not shown). According to this, different processing liquids can be recovered appropriately.

The partition plate 15 is provided around the processing cup 40 so as to vertically partition the inner space of the chamber 10 . The partition plate 15 may be a single plate-like member surrounding the processing cup 40, or may be a plurality of plate-like members joined together. Further, the partition plate 15 may be formed with a through hole or a notch that penetrates in the thickness direction. A through hole (not shown) is formed for passing a support shaft for support.

The outer peripheral edge of the partition plate 15 is connected to the side wall 11 of the chamber 10 . Further, the edge portion of the partition plate 15 surrounding the processing cup 40 is formed in a circular shape with a diameter larger than the outer diameter of the outer cup 43 . Therefore, the partition plate 15 does not hinder the lifting of the outer cup 43 .

Also, an exhaust duct 18 is provided in the vicinity of the floor wall 13 at a portion of the side wall 11 of the chamber 10 . The exhaust duct 18 is communicatively connected to an exhaust mechanism (not shown). Of the clean air supplied from the fan filter unit 14 and flowing down inside the chamber 10 , the air that has passed between the processing cup 40 and the partition plate 15 is discharged from the exhaust duct 18 to the outside of the apparatus.

The camera 70 is installed inside the chamber 10 above the partition plate 15 . The camera 70 includes, for example, an imaging device (such as a CCD (Charge Coupled Device)) and an optical system such as an electronic shutter and a lens. The discharge nozzle 31 of the processing liquid supply unit 30 is moved by the nozzle base 33 to a processing position above the substrate W held by the substrate holding unit 20 (a solid line position in FIG. 3) and a standby position outside the processing cup 40 ( dotted line position in FIG. 3). The processing position is a position where the processing liquid is discharged from the processing liquid supply unit 30 onto the upper surface of the substrate W held by the substrate holding unit 20 to perform the cleaning process. The standby position is a position where the treatment liquid supply unit 30 stops discharging the treatment liquid and waits when the treatment liquid supply unit 30 does not perform the cleaning process. A standby pod that accommodates the ejection nozzles 31 of the processing liquid supply unit 30 may be provided at the standby position.

The camera 70 is installed so that its imaging area includes at least the tip of the ejection nozzle 31 at the processing position. More specifically, the camera 70 is installed such that the tip of the ejection nozzle 31 and the treatment liquid ejected from the tip are included in the imaging area. In the present embodiment, as shown in FIG. 3, a camera 70 is installed at a position that captures an image of the discharge nozzle 31 at the processing position from above the front. Therefore, the camera 70 can capture an imaging area including the tip of the ejection nozzle 31 at the processing position. Similarly, the camera 70 can also image an imaging region including the tips of the ejection nozzles 61 and 66 of the treatment liquid supply units 60 and 65 at the treatment position. When the camera 70 is installed at the position shown in FIG. 2, the discharge nozzles 31 and 66 of the processing liquid supply units 30 and 65 move laterally within the imaging field of the camera 70. Although it is possible to appropriately image the movement in the vicinity, the ejection nozzle 61 of the processing liquid supply unit 60 moves in the depth direction within the imaging field of the camera 70. It may not be possible to take an image immediately. In such a case, a camera dedicated to the treatment liquid supply section 60 may be provided separately from the camera 70 .

Further, as shown in FIG. 3, an illumination unit 71 is provided inside the chamber 10 and above the partition plate 15 . Since the chamber 10 is normally a dark room, when the camera 70 takes an image, the illumination unit 71 irradiates the discharge nozzles 31, 61, 66 of the processing liquid supply units 30, 60, 65 near the processing position with light. A captured image generated by the camera 70 is output to the control unit 9 .

The control unit 9 controls various components of the substrate processing apparatus 100 to proceed with the processing of the substrate W. FIG. Also, the control unit 9 performs image processing on the captured image generated by the camera 70 . By this image processing, the control unit 9 obtains the timing difference between the start timing and the stop timing of ejection of the treatment liquid from each ejection nozzle. This image processing will be described in detail later.

The hardware configuration of the control unit 9 is similar to that of a general computer. That is, the control unit 9 stores a CPU that performs various arithmetic processes, a ROM that is a read-only memory that stores basic programs, a RAM that is a readable and writable memory that stores various information, control software, data, and the like. It is configured with a magnetic disk or the like to store. Each operation mechanism of the substrate processing apparatus 100 is controlled by the control unit 9 by the CPU of the control unit 9 executing a predetermined processing program, and processing in the substrate processing apparatus 100 proceeds. Further, image processing is performed by the CPU of the control unit 9 executing a predetermined processing program. Part or all of the functions of the control unit 9 may be realized by dedicated hardware.

User interface 90 includes a display and an input. The display is, for example, a liquid crystal display or an organic EL (Electro Luminescence) display. The input unit is, for example, a touch panel, mouse or keyboard. This user interface 90 is connected to the control section 9 . The display displays a display image based on the display signal from the control section 9 . This display image includes, for example, an image captured by the camera 70 . The input unit outputs input information input by the user to the control unit 9 . The control unit 9 can control various configurations according to input information.

<Operation of the control unit>
FIG. 4 is a flow chart showing an example of the operation of the control section 9. As shown in FIG. Here, as an example, processing using the processing liquid supply unit 30 will be described. First, in step S<b>1 , the main transfer robot 103 transfers the substrate W onto the substrate holder 20 . The substrate holding part 20 holds the substrate W that has been transported.

Next, in step S2, the control unit 9 rotates the nozzle base 33 to move the ejection nozzles 31a and 31b to the processing positions. The tip of the ejection nozzle 31a and the tip of the ejection nozzle 31b are included in the imaging area of the camera 70 when the ejection nozzles 31a and 31b are stopped at the processing position.

Next, in step S3, the control unit 9 controls the camera 70 to start imaging. Accordingly, the camera 70 can more reliably capture images of the tip of the ejection nozzle 31a and the tip of the ejection nozzle 31b. The camera 70 captures an image of the imaging area at a predetermined frame rate (for example, 60 frames/second), and sequentially outputs each frame of the generated captured image to the control unit 9 . Note that the imaging by the camera 70 may be started when the ejection nozzles 31a and 31b start moving in step S2.

FIG. 5 is a diagram schematically showing an example of a frame IM1 of a captured image generated by camera 70. As shown in FIG. In the frame IM1 illustrated in FIG. 5, the tip of the ejection nozzle 31a and the tip of the ejection nozzle 31b are shown, and part of the substrate W is also shown. In the frame IM1, the treatment liquid Lq1 has not yet been ejected from the ejection nozzle 31a, and similarly, the treatment liquid Lq2 has not yet been ejected from the ejection nozzle 31b.

Next, in step S4, the controller 9 starts ejection from the ejection nozzle 31a. Specifically, the controller 9 outputs an open signal to the on-off valve 35a. The on-off valve 35a performs an opening operation based on this open signal to open the pipe 34a. As a result, the processing liquid from the processing liquid supply source 37a is discharged from the discharge nozzle 31a and supplied to the upper surface of the substrate W. As shown in FIG. Note that there is a delay time from the output of the open signal to the actual ejection of the treatment liquid Lq1. This delay time depends on various factors such as the movement speed of the valve element due to the opening operation of the on-off valve 35a, the length of the pipe 34a, and the pressure loss.

Further, the control unit 9 rotates the spin motor 22 to rotate the substrate W immediately before step S4.

FIG. 6 is a diagram schematically showing an example of a frame IM2 of a captured image generated by camera 70. As shown in FIG. In the frame IM2 illustrated in FIG. 6, the treatment liquid Lq1 is ejected from the ejection nozzle 31a, and the treatment liquid Lq2 is not ejected from the ejection nozzle 31b. The processing liquid Lq1 ejected from the ejection nozzle 31a is a so-called continuous flow, and in the region from the tip of the ejection nozzle 31a to the upper surface of the substrate W, has a liquid column shape extending along the vertical direction. This processing liquid Lq1 lands on the approximate center of the substrate W and spreads on the upper surface of the substrate W under the centrifugal force accompanying the rotation of the substrate W. As shown in FIG. Then, it scatters from the periphery of the substrate W. As a result, the processing liquid Lq1 acts on the entire upper surface of the substrate W, and processing based on the processing liquid Lq1 is performed.

For example, when a predetermined period of time has passed since step S4, the control unit 9 switches the nozzle for ejecting the treatment liquid from the ejection nozzle 31a to the ejection nozzle 31b in step S5. That is, the control unit 9 stops ejection of the treatment liquid Lq1 from the ejection nozzle 31a and starts ejection of the treatment liquid Lq2 from the ejection nozzle 31b. That is, the controller 9 transmits a close signal to the on-off valve 35a and an open signal to the on-off valve 35b. As a specific example, the control unit 9 outputs an open signal to the on-off valve 35b when the elapsed time from step S4 reaches the first reference time, and the elapsed time from step S4 reaches the second reference time. Then, a close signal is output to the on-off valve 35a. For example, the second reference time can be set longer than the first reference time.

The on-off valve 35b performs an opening operation based on the open signal to open the pipe 34b. As a result, the processing liquid Lq2 from the processing liquid supply source 37b is ejected from the ejection nozzle 31b and lands on the upper surface of the substrate W. As shown in FIG. Note that there is a delay time from when the open signal is output to when the treatment liquid Lq2 is actually discharged. This delay time depends on various factors such as the movement speed of the valve element due to the opening operation of the on-off valve 35b, the length of the pipe 34b, and the pressure loss.

The on-off valve 35a performs a closing operation based on the close signal to close the pipe 34a. If the suck-back valve 36a is provided, the controller 9 sends a suction signal to the suck-back valve 36a. The suck-back valve 36a performs a suction operation based on this suction signal to suck the processing liquid in the pipe 34a. The closing operation of the on-off valve 35a and the sucking operation of the suck-back valve 36a are executed in parallel with each other. As a result, the treatment liquid Lq1 on the tip side of the ejection nozzle 31a is pulled back, and the ejection of the treatment liquid Lq1 is appropriately stopped. Note that there is a delay time from when the close signal is output to when the discharge of the treatment liquid Lq1 is actually stopped. This delay time depends on various factors such as the movement speed of the valve body due to the closing operation of the on-off valve 35a, the movement speed of the suckback valve 36a, the pipe length of the pipe 34a, and the pressure loss.

7 and 8 schematically show an example of a captured image frame produced by the camera 70. FIG. Frames IM3 and IM4 exemplified in FIGS. 7 and 8, respectively, indicate frames when switching from the ejection nozzle 31a to the ejection nozzle 31b. The frame IM3 is a frame during which the on-off valves 35a and 35b are performing the closing operation and the opening operation, respectively. Therefore, in the frame IM3, the treatment liquids Lq1 and Lq2 are ejected from both the ejection nozzles 31a and 31b, respectively. However, the width of the treatment liquid Lq1 ejected from the ejection nozzles 31a is narrower than that of the frame IM2. This is because the closing operation of the on-off valve 35a reduces the flow rate of the treatment liquid Lq1. In the frame IM3, the on-off valve 35b is not yet completely opened, so the width of the treatment liquid Lq2 ejected from the ejection nozzle 31b is also narrow.

The frame IM4 is a frame in which the on-off valve 35a is closed and the on-off valve 35b is open. Therefore, in the frame IM4, the treatment liquid Lq1 is not ejected from the ejection nozzle 31a, and the treatment liquid Lq2 is ejected from the ejection nozzle 31b. The processing liquid Lq2 ejected from the ejection nozzle 31b is also a continuous flow, and in the region from the tip of the ejection nozzle 31b to the upper surface of the substrate W, it has a liquid column shape extending along the vertical direction. This processing liquid Lq2 lands on the approximate center of the substrate W and spreads on the upper surface of the substrate W under the centrifugal force accompanying the rotation of the substrate W. As shown in FIG. Then, it scatters from the periphery of the substrate W. As a result, the processing liquid Lq2 acts on the entire upper surface of the substrate W, and processing based on the processing liquid Lq2 is performed.

After a predetermined period of time has passed since step S5, in step S6, the control unit 9 stops the ejection of the treatment liquid Lq2 from the ejection nozzle 31b. As a specific example, the control unit 9 transmits a close signal to the on-off valve 35b when the elapsed time from outputting the open signal to the on-off valve 35b reaches the third reference time. The on-off valve 35b closes the pipe 34b by performing a closing operation based on this closing signal. If the suck-back valve 36b is provided, a suction signal is transmitted to the suck-back valve 36b. As a result, the suck-back valve 36b performs a suction operation in parallel with the closing operation of the on-off valve 35a to suck the processing liquid Lq2 in the pipe 34b. As a result, the ejection of the treatment liquid Lq2 from the ejection nozzle 31b is stopped appropriately. Also in this case, there is a delay time from the output of the signal to the actual end of ejection of the treatment liquid Lq2.

The controller 9 may stop the rotation of the substrate W by stopping the rotation of the spin motor 22 after step S6. Alternatively, the control unit 9 increases the rotational speed of the spin motor 22 so that the processing liquid Lq2 on the substrate W is scattered from the peripheral edge of the substrate W by the rotational force to dry the substrate W. Rotation may be stopped.

Next, in step S7, the control section 9 terminates the imaging by the camera 70. FIG. Next, in step S8, the controller 9 controls the nozzle base 33 to move the discharge nozzles 31a and 31b to the standby position.

A series of processes using the treatment liquids Lq1 and Lq2 can be sequentially performed by the above operation.

Further, as illustrated in FIG. 4, the control unit 9 performs monitoring processing in step S10 in parallel with steps S4 to S6 in order to monitor the discharge/stop timing of the treatment liquid. This monitoring process monitors whether or not the timing difference between the start timing tb for starting ejection of the treatment liquid Lq2 from the ejection nozzle 31b in step S5 and the stop timing ta for stopping ejection of the treatment liquid Lq1 from the ejection nozzle 31a is appropriate. It is a process to

FIG. 9 is a flowchart showing an example of a specific operation of monitoring processing. First, the control unit 9 performs image processing on the captured image generated by the camera 70 to specify the start timing tb of the ejection nozzle 31b and the stop timing ta of the ejection nozzle 31a (step S11).

First, the start timing tb of the discharge nozzle 31b will be described. When a frame is input from the camera 70, the controller 9 cuts out the ejection determination region Rb1 from the frame. The ejection determination area Rb1 here is an area extending from the tip of the ejection nozzle 31b in the ejection direction of the treatment liquid Lq2 in each frame of the captured image (see also FIGS. 5 to 8). Here, since the treatment liquid Lq2 extends vertically downward, the ejection determination region Rb1 has an elongated shape (for example, a rectangular shape) extending in the vertical direction of the captured image. The width of the ejection determination region Rb1 in the horizontal direction is set wider than the width of the treatment liquid Lq2, and the length of the ejection determination region Rb1 in the vertical direction is such that the ejection determination region Rb1 does not include the landing position of the treatment liquid Lq2. is set to

Now, the pixel value in the ejection determination region Rb1 when the treatment liquid Lq2 is not ejected from the ejection nozzle 31b differs from the pixel value in the ejection determination region Rb1 when the treatment liquid Lq2 is ejected from the ejection nozzle 31b. . 10 and 11 are diagrams schematically showing an example of the luminance distribution in the horizontal direction within the ejection determination region Rb1. FIG. 10 illustrates the luminance distribution when the treatment liquid Lq2 is not ejected, and FIG. 11 illustrates the luminance distribution when the treatment liquid Lq2 is ejected.

When the treatment liquid Lq2 is being ejected, the liquid column portion of the treatment liquid Lq2 is reflected in the ejection determination region Rb1. When the illumination light is incident from the same direction as the imaging direction of the camera 70, the surface of the liquid column of the treatment liquid Lq2 appears to shine brightly. Therefore, as illustrated in FIG. 11, the brightness corresponding to this liquid column portion is higher than the surroundings. Specifically, the luminance distribution has an upward convex shape in the liquid column portion. In other words, the luminance distribution has characteristics resulting from the liquid column shape of the treatment liquid Lq2.

On the other hand, when the treatment liquid Lq2 is not ejected, the liquid column shape of the treatment liquid Lq2 is not reflected in the ejection determination region Rb1. Therefore, as exemplified in FIG. 10, the luminance distribution naturally does not have the characteristic attributed to the liquid column shape of the treatment liquid Lq2. Although the luminance fluctuates according to the irregular reflection due to the pattern on the upper surface of the substrate W or the reflection of the internal parts of the chamber 10, it has a relatively uniform distribution.

By the way, the camera 70 may be of a type that generates a grayscale captured image, or may be a type of camera that generates a color captured image. In the former case, it can be said that the pixel value of the captured image indicates the luminance value. A camera that generates a grayscale captured image will be described below as an example, but in the case of a color image, the brightness value is calculated from the pixel value and used.

Based on the pixel values in the ejection determination region Rb1, the control unit 9 determines whether or not the treatment liquid Lq2 is being ejected from the ejection nozzles 31b. Specifically, the control unit 9 calculates a statistic A2 of pixel values in the ejection determination region Rb1. The statistic A2 is a value that reflects the ejection state of the treatment liquid Lq2 from the ejection nozzles 31b, and is, for example, the total sum (integrated value) of the pixel values in the ejection determination region Rb1. This is because the sum of the pixel values when the treatment liquid Lq2 is ejected is greater than the sum of the pixel values when the treatment liquid Lq2 is not ejected.

As the statistic A2, the variance of the pixel values may be used instead of the sum of the pixel values. This is because, as shown in FIGS. 10 and 11, the luminance distribution when the treatment liquid Lq2 is ejected varies more than the luminance distribution when the treatment liquid Lq2 is not ejected. Standard deviation, for example, can be used as the variance. Further, it is possible to adopt dispersion for all pixel values in the ejection determination region Rb1.

On the other hand, since the treatment liquid Lq2 has a liquid column shape along the vertical direction, variations in the luminance distribution in the vertical direction in the ejection determination region Rb1 are small. Therefore, it is also possible to cut out pixels arranged in a row along the horizontal direction and adopt the dispersion of the pixel values of the plurality of pixels. Alternatively, the pixel values aligned in the vertical direction may be integrated for each column to calculate the integrated pixel value, and the variance of the obtained integrated pixel value for each column may be employed.

As an example of determination, a threshold th1 is set for the statistic A2, and when the statistic A2 is equal to or greater than the threshold th1, it can be determined that the treatment liquid Lq2 is being ejected from the ejection nozzle 31b, and the statistic A2 is greater than the threshold th1. When it is small, it can be determined that the treatment liquid Lq2 is not ejected from the ejection nozzle 31b. This threshold th1 can be set in advance through experiments, simulations, or the like.

FIG. 12 is a graph showing an example of temporal changes in the statistic A2 in steps S4 to S6 of FIG. In FIG. 12, the horizontal axis indicates the frame number of the captured image generated by the camera 70, and the vertical axis indicates the statistic. Since the frame number increases with the passage of time, it can be said that the horizontal axis indicates time. A statistic A2 for the ejection determination region Rb1 is indicated by a dashed line, and a statistic A1 for the ejection determination region Ra1, which will be described later, is indicated by a solid line.

In FIG. 12, the statistic A2 is initially smaller than the threshold th1. This is because the ejection nozzle 31b does not eject the treatment liquid Lq2 at the beginning of the process (see step S4 in FIG. 4). When the ejection nozzles are switched in step S5, the statistic A2 increases and exceeds the threshold th1. That is, the statistic A2 transitions from a state smaller than the threshold th1 to a state larger than the threshold th1. The timing at which the statistic A2 exceeds the threshold th1 corresponds to the start timing tb. Therefore, the start timing tb can be specified based on the change in the statistic A2. A detailed description is given below.

The control unit 9 calculates the statistic A2 for each frame, and determines for each frame whether or not the statistic A2 is greater than the threshold th1. Then, the control unit 9 stores the determination result in the storage medium. The control unit 9 determines that the statistic A2 exceeds the threshold th1 when the statistic A2 is smaller than the threshold th1 in the previous frame and greater than the threshold th1 in the current frame.

The control unit 9 specifies the start timing tb based on the previous frame and the current frame. That is, the control unit 9 determines the start timing based on the previous frame in which the statistic A2 is smaller than the threshold th1 and the current frame, which is the next frame of the current frame and in which the statistic A2 is larger than the threshold th1. Identify tb. For example, the control unit 9 may specify the generation timing of the previous frame as the start timing tb, or may specify the generation timing of the current frame as the start timing tb, or may specify the generation timing of the previous frame and the current frame as the start timing tb. An average of the timings may be specified as the start timing tb.

Next, the stop timing ta of the discharge nozzle 31a will be described. When the frame is input, the controller 9 cuts out the ejection determination region Ra1 from the frame. The ejection determination area Ra1 here is an area extending in the ejection direction of the treatment liquid Lq1 from the tip of the ejection nozzle 31a in each frame of the captured image (see also FIGS. 5 to 8). Here, since the treatment liquid Lq1 extends vertically downward, the ejection determination area Ra1 has an elongated shape (for example, a rectangular shape) extending in the vertical direction of the captured image. The width of the ejection determination region Ra1 in the horizontal direction is set wider than the width of the treatment liquid Lq1, and the length of the ejection determination region Rb1 in the vertical direction is such that the ejection determination region Rb1 does not include the landing position of the treatment liquid Lq1. is set to

Similar to the ejection determination region Rb1, the luminance distribution in the ejection determination region Ra1 differs depending on whether or not the treatment liquid Lq1 is ejected. Therefore, the control unit 9 determines whether or not the treatment liquid Lq1 is to be ejected, based on the pixel values of the ejection determination area Ra1, in the same manner as the ejection determination of the treatment liquid Lq2. More specifically, the controller 9 calculates a statistic A1 of pixel values in the ejection determination region Ra1. The statistic A1 is similar to the statistic A2, and is a value that reflects the ejection state of the treatment liquid Lq2 from the ejection nozzles 31a.

When the statistic A1 is large, it can be determined that the treatment liquid Lq1 is ejected from the ejection nozzle 31a, and when the statistic A1 is small, it can be determined that the treatment liquid Lq1 is not ejected from the ejection nozzle 31a. Therefore, a threshold is set for the statistic A1 used for these determinations. Here, the threshold th1 for the statistic A2 is used as the threshold for the statistic A1. A value different from the threshold th1 may be adopted as the threshold for the statistic A1.

As illustrated in FIG. 12, the statistic A1 is initially larger than the threshold th1. This is because the treatment liquid Lq1 is discharged from the beginning of the treatment (see step S4 in FIG. 4). Then, when the ejection nozzles are switched in step S5, the statistic A1 decreases and falls below the threshold th1. The timing at which the statistic A1 falls below the threshold th1 corresponds to the stop timing ta. Therefore, the stop timing ta can be specified based on the change in the statistic A1. A detailed description is given below.

The control unit 9 calculates the statistic A1 for each frame, and determines for each frame whether or not the statistic A1 is greater than the threshold th1. Then, the control unit 9 stores the determination result in the storage medium. The control unit 9 determines that the statistic A1 is below the threshold th1 when the statistic A1 is larger than the threshold th1 in the previous frame and is smaller than the threshold th1 in the current frame.

Then, the control unit 9 specifies the stop timing ta based on the previous frame and the current frame. That is, the control unit 9 determines the stop timing based on the previous frame in which the statistic A1 is larger than the threshold th1 and the current frame, which is the next frame of the current frame and in which the statistic A2 is smaller than the threshold th1. Identify ta. For example, the control unit 9 may specify the generation timing of the previous frame as the stop timing ta, or may specify the generation timing of the current frame as the stop timing ta, or may specify the generation timing of the previous frame and the current frame as the stop timing ta. An average of the timings may be specified as the stop timing ta.

Next, in step S12, the controller 9 calculates the timing difference between the start timing tb and the stop timing ta. Specifically, the control unit 9 subtracts the start timing tb from the stop timing ta to calculate the timing difference.

Next, in step S13, the control section 9 determines whether or not this timing difference is outside a predetermined range. The predetermined range may be set in advance and stored in a storage medium, for example. The lower and upper limits of the predetermined range have positive values, for example.

When the timing difference is out of the predetermined range, the controller 9 performs error notification processing in step S14. For example, the controller 9 causes the display of the user interface 90 to display an error. Alternatively, when a sound output unit such as a buzzer or speaker is provided, the control unit 9 may cause the sound output unit to output an error. The display and sound output section of the user interface 90 are examples of the notification section. In short, the control section 9 causes this reporting section to report the error. Such notification allows the operator to recognize that the timing difference is outside the predetermined range.

Next, in step S15, the controller 9 adjusts at least one of the start timing tb and the stop timing ta so that the timing difference is within a predetermined range.

When the timing difference is greater than the upper limit of the predetermined range, the controller 9 updates the start timing tb of the discharge nozzle 31b to a later timing, for example, in order to reduce the timing difference and keep it within the predetermined range. As a more specific example, the control unit 9 updates the second reference time that defines the timing of opening the on-off valve 35b to a longer value so that the timing difference is within a predetermined range, and updates the second reference time after updating. 2. Store the reference time in a storage medium. According to this, the timing of outputting the open signal to the on-off valve 35b is delayed when switching in step S5 from the next time onward, so the start timing tb is delayed. Therefore, the timing difference in step S5 (step S5 for the next substrate) after the next time can be reduced to be within a predetermined range.

According to this, the ejection stop timing ta of the treatment liquid Lq1 is not changed, so the length of the treatment period for the treatment liquid Lq1 is not changed. Therefore, the treatment with the treatment liquid Lq1 can be performed appropriately.

Alternatively, the control unit 9 may update the stop timing ta of the discharge nozzle 31a to an earlier timing. As a more specific example, the control unit 9 updates the first reference time that defines the timing of closing the on-off valve 35a to a shorter value so that the timing difference is within a predetermined range, 1. Store the reference time in a storage medium. According to this, the timing of outputting the close signal to the on-off valve 35a is advanced when switching in step S5 from the next time onward, so the stop timing ta is advanced. Therefore, the timing difference in step S5 from the next time onward can be reduced to be within a predetermined range.

Also, both the start timing tb and the stop timing ta may be adjusted to reduce the timing difference.

Now, when the timing difference is larger than the upper limit value of the predetermined range, the overlap period during which both the treatment liquids Lq1 and Lq2 are ejected is long. That is, the total amount of processing liquid discharged onto the substrate W temporarily increases. As a result, for example, the processing liquid Lq2 collides with the processing liquid Lq1 on the substrate W, and part of the processing liquid splashes on the substrate W, which can cause liquid splashing. In the first embodiment, when the timing difference is greater than the upper limit of the predetermined range, the timing difference in step S5 from the next time onward can be kept within the predetermined range. Therefore, by adopting a value that does not cause liquid splashing as the upper limit value of the predetermined range, it is possible to substantially avoid the occurrence of liquid splashing.

On the other hand, when the timing difference is smaller than the lower limit of the predetermined range, the controller 9 updates the start timing tb of the discharge nozzle 31b to an earlier timing, for example, in order to increase the timing difference and keep it within the predetermined range. . As a more specific example, the control unit 9 updates the second reference time that defines the timing of opening the on-off valve 35b to a shorter value so that the timing difference is within a predetermined range, and A second reference time is stored in the storage medium. As a result, the timing difference in step S5 from the next time onward can be increased to be within a predetermined range.

According to this, the ejection stop timing ta of the treatment liquid Lq1 is not changed, so the length of the treatment period for the treatment liquid Lq1 is not changed. Therefore, the treatment with the treatment liquid Lq1 can be performed appropriately.

Alternatively, the control unit 9 may update the stop timing ta of the discharge nozzle 31a to a later timing. As a more specific example, the control unit 9 updates the first reference time, which defines the timing of closing the on-off valve 35a, to a longer value so that the timing difference is within a predetermined range, and updates the updated first reference time. 1. Store the reference time in a storage medium. This also makes it possible to increase the timing difference in step S5 from the next time onwards so that it falls within the predetermined range.

Moreover, both the start timing tb and the stop timing ta may be adjusted to increase the timing difference.

Now, when the timing difference is smaller than the lower limit of the predetermined range, the overlap period during which both the treatment liquids Lq1 and Lq2 are ejected becomes short. In other words, the ejection of the treatment liquid Lq2 is started while the ejection of the treatment liquid Lq1 is almost stopped. Since the substrate W is rotating, the processing liquid Lq1 supplied to the upper surface of the substrate W moves toward the peripheral edge of the substrate W due to the centrifugal force. Therefore, if the discharge amount of the treatment liquid Lq1 decreases while the treatment liquid Lq2 is not being discharged, the amount of the treatment liquid Lq1 on the upper surface of the substrate W decreases and the substrate W can be partially dried (liquid dryness). In particular, the upper surface of the substrate W may be partially dried in the vicinity of the liquid landing position of the treatment liquid Lq1. Such drying may cause defects (eg, adhesion of particles, etc.) to the upper surface of the substrate W, which is not preferable. In the first embodiment, even when the timing difference is smaller than the lower limit value of the predetermined range, the timing difference in step S5 after the next time can be kept within the predetermined range. Therefore, by setting the lower limit of the predetermined range to a value that does not cause partial drying of the substrate W, the occurrence of partial drying of the substrate W can be substantially avoided.

As described above, according to the first embodiment, when the timing difference is outside the predetermined range, it is adjusted within the predetermined range. Therefore, it is possible to substantially avoid the occurrence of troubles (liquid splashing and liquid drying) due to the timing difference being out of the predetermined range.

Further, according to the first embodiment, the start timing tb of the ejection nozzle 31b and the stop timing ta of the ejection nozzle 31a are specified by the image processing of the captured image from the camera 70 . That is, since the start timing tb and the stop timing ta can be specified based on the actual ejection states of the treatment liquids Lq1 and Lq2, the specification accuracy can be improved. Further, since the timing difference is calculated based on the timing specified with high accuracy, the calculation accuracy of the timing difference is also high. Therefore, the timing difference can be kept within a predetermined range with higher accuracy.

Moreover, since the pixel values of the ejection determination regions Ra1 and Rb1 are used, the processing can be lightened compared to the case where the image processing is performed on the entire captured image.

Further, the timing difference can be obtained based on the comparison between the statistical amount and the threshold th1, so the processing is simple.

In the above example, the upper limit value of the predetermined range is set to a value that does not cause liquid splashing, and the lower limit value is set to a value that does not cause liquid drying. However, depending on other factors, the upper limit value may be set to a smaller value, and the lower limit value may be set to a larger value. For example, this timing difference may affect the quality of the processing result for the substrate W. FIG. In this case, the upper limit and lower limit of the predetermined range of the timing difference may be set through experiments, simulations, or the like so that the processing result is good.

The delay time for ejection control may differ for each processing unit 1 due to manufacturing variations of the plurality of processing units 1 or the like. However, the timing difference can be adjusted within a predetermined range for each processing unit 1 by the control section 9 performing the above operation for each processing unit 1 . Conventionally, in order to adjust the start timing tb and the stop timing ta for each processing unit 1 , the recipe information of the substrate W has been changed for each processing unit 1 . This made management of recipe information complicated. In the first embodiment, even if common recipe information is employed, processing can be performed with optimal timing differences for each processing unit 1, and stable processing performance can be achieved.

Further, in the above example, the ejection of the treatment liquid Lq1 from the ejection nozzle 31a is stopped after the ejection of the treatment liquid Lq2 from the ejection nozzle 31b is started. FIG. 13 is a graph showing another example of temporal changes in statistics. In the example of FIG. 13, the start timing tb of the ejection nozzle 31b appears after the stop timing ta of the ejection nozzle 31a, and the timing difference is relatively large. Even in such a case, the amount of the processing liquid Lq1 on the upper surface of the substrate W decreases before the processing liquid Lq2 is discharged, so the substrate W can be partially dried.

In this case, the timing difference obtained by subtracting the start timing tb from the stop timing ta in step S12 has a negative value. Therefore, this timing difference is smaller than the lower limit value of the predetermined range, and in step S13, the control unit 9 determines that the timing difference is outside the predetermined range. Therefore, in step S15, the controller 9 adjusts at least one of the start timing tb and the stop timing ta so that the timing difference is within a predetermined range. Therefore, the timing difference can be kept within a predetermined range in step S5 from the next time onward.

Further, the above description can be grasped as the operation when processing the substrate W, or can be grasped as the operation during initial setting performed when the substrate processing apparatus 100 is installed. That is, if a temporary timing is set at the time of initial setting and the substrate W is actually processed, an appropriate timing is set when the temporary timing is inappropriate.

<User interface>
In the above example, the controller 9 determined whether the timing difference was outside the predetermined range. However, the operator may make the determination. A specific description will be given below.

The control unit 9 causes the display of the user interface 90 to display a graph showing temporal changes in the statistics A1 and A2. It is desirable that the control unit 9 also display the threshold th1 on the graph. Specifically, the control unit 9 displays the graph shown in FIG. 12 or 13 on the display. Thereby, the operator can visually recognize the temporal change of the statistics A1 and A2, and can determine the magnitude of the timing difference.

The input unit of the user interface 90 receives input for adjusting the input for adjusting the start timing tb and the stop timing ta. For example, when the operator determines that the timing difference is greater than the upper limit of the predetermined range, the operator performs at least one of an input to delay the start timing tb and an input to advance the stop timing ta to the input unit. . The input section outputs the input information to the control section 9 . The control unit 9 adjusts at least one of the start timing tb and the stop timing ta according to the input information. The same applies when the operator determines that the timing difference is smaller than the lower limit of the predetermined range.

As described above, the operator can visually recognize the time change of the statistics A1 and A2 and adjust the timing difference based on the time change.

<Machine learning>
In the above example, the control unit 9 obtains the timing difference between the start timing tb and the stop timing ta based on the statistic of pixel values, but this is not necessarily the case. The control unit 9 may obtain the timing difference between the start timing tb and the stop timing ta by machine learning in the monitoring process.

FIG. 14 is a diagram schematically showing an example of the internal configuration of the control section 9. As shown in FIG. The control unit 9 has a classifier 91 and a machine learning unit 92 . Each frame of the captured image from the camera 70 is sequentially input to the classifier 91 . The classifier 91 classifies each input frame into the following four categories C1 to C4 regarding discharge/stop of the discharge nozzles 31a and 31b. Categories may also be called classes.

Four categories C1 to C4 are categories indicating the ejection states shown in FIGS. 5 to 8, respectively. More specifically, category C1 indicates a state in which both of the ejection nozzles 31a and 31b do not eject the treatment liquid (FIG. 5), and category C2 indicates a state in which only the ejection nozzle 31a ejects the treatment liquid. Category C3 is a category indicating a state in which both the ejection nozzles 31a and 31b are ejecting the processing liquid (FIG. 7). Category C4 is a category indicating the state in which the ejection nozzle 31b is a category indicating a state in which the treatment liquid is being discharged (FIG. 8).

This classifier 91 is generated by the machine learning section 92 using a plurality of teacher data. In other words, it can be said that this classifier 91 is a machine-learned classifier. The machine learning unit 92 uses, for example, a neighborhood method, a support vector machine, a random forest, or a neural network (including deep learning) as a machine learning algorithm.

The teacher data includes learning data and a label indicating which category the learning data belongs to. The learning data are frames of captured images captured by the camera 70 and are generated in advance. A correct category is given as a label to each learning data. This assignment can be performed by the operator, for example, by operating the user interface 90 . The machine learning unit 92 performs machine learning based on these teacher data to generate the classifier 91 .

As an example, the classifier 91 that classifies frames by the neighborhood method will be described. The classifier 91 includes a feature vector extraction unit 911, a determination unit 912, and a storage medium in which a determination database 913 is stored. Each frame of the captured image from the camera 70 is sequentially input to the feature vector extraction unit 911 . A feature vector extraction unit 911 extracts the feature vector of the frame according to a predetermined algorithm. This feature vector is a vector that easily indicates the feature amount corresponding to the ejection state of the ejection nozzles 31a and 31b. A known algorithm can be adopted as the algorithm. Feature vector extraction section 911 outputs the feature vector to determination section 912 .

A determination database 913 stores a plurality of feature vectors (hereinafter referred to as reference vectors) generated from a plurality of teacher data by the machine learning unit 92, and the reference vectors are classified into categories C1 to C4. there is Specifically, the machine learning unit 92 applies the same algorithm as the feature vector extraction unit 911 to multiple teacher data to generate multiple reference vectors. Then, the machine learning unit 92 assigns a teacher data label (correct category) to the reference vector.

A determination unit 912 classifies frames based on the feature vector input from the feature vector extraction unit 911 and a plurality of reference vectors stored in the determination database 913 . For example, the determining unit 912 may identify a reference vector whose feature vectors are closest, and classify frames into the category of the identified reference vector (nearest neighbor method). As a result, the determination unit 912 can classify the frame input to the classifier 91 (feature vector extraction unit 911) into one of the categories C1 to C4.

The control unit 9 classifies each frame by the classifier 91, and based on the classification result, obtains the timing difference between the start timing tb of the ejection nozzle 31b and the stop timing ta of the ejection nozzle 31a.

FIG. 15 is a flow chart showing an example of the operation of the control section 9 in the monitoring process. In step S40, the control unit 9 specifies the start timing tb and the stop timing ta by machine learning as image processing.

FIG. 16 is a diagram schematically showing an example of a plurality of frames F of a captured image. In the example of FIG. 16, frames F are arranged in chronological order. The reason why the reference numerals of the frames are changed here is for convenience of explanation, and the frame F is of the same kind as the frames IM1 to IM4 described above.

As illustrated in FIG. 16, at the initial stage of operation of the substrate processing apparatus 100, neither of the ejection nozzles 31a and 31b ejects the processing liquid. Therefore, the frames F[1] to F[k] illustrated in FIG. 16 are classified by the classifier 91 into the category C1.

Then, when the treatment liquid Lq1 is ejected from the ejection nozzle 31a (step S4), the following frames F[k+1] to F[m] are classified by the classifier 91 into category C2, as illustrated in FIG.

Next, the nozzle for ejecting the treatment liquid is switched from the ejection nozzle 31a to the ejection nozzle 31b (step S5). That is, the treatment liquid Lq2 is ejected from the ejection nozzle 31b. Therefore, as illustrated in FIG. 16, the subsequent frames F[m+1] to F[n] are classified by the classifier 91 into category C3. Next, ejection of the treatment liquid Lq1 from the ejection nozzle 31a is stopped. Therefore, as exemplified in FIG. 16, the frames after the subsequent frame F[n+1], which are the frames until the discharge of the treatment liquid Lq2 from the discharge nozzle 31b is completed, are classified by the classifier 91 into the category C4. be.

The control unit 9 specifies the start timing tb and the stop timing ta based on the result of classification of each frame, as described in detail below.

That is, the control unit 9 controls the m-th frame F[m] classified as stopped (category C2) for the ejection nozzle 31b and the (m+1)-th frame next to the frame F[m]. The start timing tb of the ejection nozzle 31b is specified based on the frame F[m+1] classified as ejection (category C3) for 31b. For example, the control unit 9 may specify the generation timing of the frame F[m] as the start timing tb, may specify the generation timing of the frame F[m+1] as the start timing tb, or may specify the generation timing of the frame F[m] as the start timing tb. ], F[m+1] may be specified as the start timing tb.

Similarly, the control unit 9 controls the n-th frame F[n] classified as ejection (category C3) for the ejection nozzle 31a and the (n+1)-th frame next to the frame F[n]. The stop timing ta of the discharge nozzle 31a is specified based on the frame F[n+1] classified as stop (category C4) for the nozzle 31a. For example, the control unit 9 may specify the generation timing of the frame F[n] as the stop timing ta, may specify the generation timing of the frame F[n+1] as the stop timing ta, or may specify the generation timing of the frame F[n] as the stop timing ta. ], F[n+1] may be specified as the stop timing ta.

As described above, the controller 9 can determine (classify) the ejection states of the ejection nozzles 31a and 31b by machine learning. Therefore, each frame can be classified with high accuracy. As a result, the timing difference between the stop timing ta and the start timing tb can be obtained with high accuracy.

Steps S41 to S44 after specifying the stop timing ta and the start timing tb are the same as steps S12 to S15 in the first embodiment, respectively.

Note that when ejection from the ejection nozzle 31b starts before ejection from the ejection nozzle 31a stops, the overlap period during which both the treatment liquids Lq1 and Lq2 are ejected corresponds to the timing difference. Therefore, in this case, the control unit 9 may calculate the timing difference based on the number of frames classified into category C3. For example, the control unit 9 may calculate the timing difference by multiplying the time between frames by the number of frames.

<Input to classifier>
In the above example, the input data to the classifier 91 is the entire area of each frame F of the captured image, but it is not necessarily limited to this. For example, the control unit 9 may cut out images representing the ejection determination regions Ra<b>1 and Rb<b>1 from the frame F and input the images to the classifier 91 . In this case, as learning data input to the machine learning unit 92, images representing the ejection determination regions Ra1 and Rb1 are employed.

According to this, the classifier 91 can classify by removing the influence of the region with low relevance to the discharge state, so that the classification accuracy can be improved. As a result, it is possible to improve the accuracy of specifying the start timing tb and the stop timing ta. Further, using the ejection determination regions Ra1 and Rb1 makes it possible to lighten the processing as compared with the case where the processing by the classifier 91 is performed on the entire frame of the captured image.

Note that the classifier 91 may classify the ejection state for each image of the ejection determination regions Ra1 and Rb2. That is, the classifier 91 may classify the image into the following two categories Ca1 and Ca2 based on the image of the ejection determination area Ra1. That is, category Ca1 indicates a state in which the ejection nozzle 31a does not eject the treatment liquid Lq1, and category Ca2 indicates a state in which the ejection nozzle 31a ejects the treatment liquid Lq1. Similarly, the classifier 91 may classify the image of the ejection determination region Rb2 into the following two categories Cb1 and Cb2. That is, category Ca2 indicates a state in which the ejection nozzle 31a is ejecting the treatment liquid Lq2. Category Cb1 indicates a state in which the ejection nozzle 31b does not eject the treatment liquid Lq2, and category Cb2 indicates a state in which the ejection nozzle 31b ejects the treatment liquid Lq2.

The control unit 9 sets the start timing tb of the discharge nozzle 31b based on the frame containing the image classified into the category Cb1 and the frame containing the image next to the image classified into the category Cb2. can be specified. The same applies to the stop timing ta of the discharge nozzle 31a.

As the input data to the classifier 91, for example, a pixel value group of pixels arranged horizontally in each of the ejection determination regions Ra1 and Rb1 may be used. This is because, as shown in FIGS. 10 and 11, the pixel value groups of the pixels arranged in the horizontal direction change depending on whether or not the treatment liquid is discharged. Alternatively, the input data of the classifier 91 may be an integral value group including, for each row, an integral value that is the sum of pixel values aligned in the vertical direction in each of the ejection determination regions Ra1 and Rb1.

<Multiple classifiers>
FIG. 17 is a functional block diagram schematically showing an example of the internal configuration of the control section 9. As shown in FIG. The controller 9 is the same as in FIG. 14 except that it has a plurality of classifiers 91 . These multiple classifiers 91 are also generated by the machine learning unit 92 .

For example, the machine learning unit 92 generates a plurality of classifiers 91 for each type of treatment liquids Lq1 and Lq2. In the example of FIG. 17, three classifiers 91A to 91C are shown as the plurality of classifiers 91. In FIG. Classifiers 91A-91C are classifiers generated using different teacher data.

For example, each frame of captured images obtained by performing processing using certain types of processing liquids Lq1 and Lq2 is adopted as learning data. The machine learning unit 92 generates the classifier 91A based on teacher data including the learning data. As a result, the classifier 91A for the set of types of the treatment liquids Lq1 and Lq2 (hereinafter referred to as the first set) can be generated. Similarly, the machine learning unit 92 generates a classifier 91B for the second set based on teacher data using a second set of treatment liquids Lq1 and Lq2 different from the first set, and A classifier 91C for the third set is generated based on teacher data using the third set of treatment liquids Lq1 and Lq2, which are different in type from the two sets.

In the example of FIG. 17, the feature vector extraction unit 911 and the determination unit 912 are commonly provided in the classifiers 91A to 91C, and the classifiers 91A to 91C are distinguished by the determination database 913. FIG. In short, the machine learning unit 92 generates the classifiers 91A to 91C by generating the judgment databases 913A to 913C for the first to third sets, respectively. In the determination database 913A, reference vectors and their correct categories are recorded when the first set of treatment liquids Lq1 and Lq2 are used. The same applies to the determination databases 913B and 913C.

The user interface 90 is connected to the determination unit 912 . The operator inputs the types of treatment liquids Lq1 and Lq2 to the user interface 90. FIG. FIG. 18 is a diagram showing an example of an input screen 90a displayed on the display of the user interface 90. As shown in FIG. A table 901 relating to the treatment liquids Lq1 and Lq2 is displayed on the input screen 90a. This table 901 shows the type of processing liquid, the flow rate, the rotation speed of the substrate W, and the processing time. Various information in the table 901 can be changed by the operator's input to the input unit. For example, by clicking (or touching) the relevant portion of the table 901, the information of the relevant portion can be input. For example, by clicking, a plurality of pieces of information are displayed in a pull-down format in the relevant portion, and the worker can input information by selecting one of them.

On the input screen 90a illustrated in FIG. 18, soft keys 902 for selecting the type of substrate W are also displayed. The operator can select soft key 902 by clicking or touching soft key 902 . Types of the substrate W include, for example, a silicon (Si) substrate and a silicon carbide (SiC) substrate. In addition, the determination database can be selected depending on whether or not a film is formed on the upper surface of the substrate W, or the type of film formed on the upper surface of the substrate W (for example, SiO ₂ , SiN, TiN, etc.). good.

An input screen 90a illustrated in FIG. 18 also shows an area 903 in which a captured image generated by the camera 70 is displayed. Thereby, the operator can visually recognize the captured image of the camera 70 .

The user interface 90 outputs input information (such as the types of the treatment liquids Lq1 and Lq2) input by the operator to the determination unit 912 .

Feature vector extraction section 911 extracts the feature vector of the input frame and outputs the feature vector to determination section 912 . The determination unit 912 selects the determination database 913 according to the types of the treatment liquids Lq1 and Lq2 to be processed. The determination unit 912 classifies frames using the input feature vector and the selected reference vector of the determination database 913 .

According to this, the frames are classified using the classifier 91 corresponding to the types of the treatment liquids Lq1 and Lq2, so that the frame classification accuracy can be improved. As a result, it is possible to improve the calculation accuracy of the timing difference.

Although the classifier 91 is generated for each type of the processing liquids Lq1 and Lq2 in the above example, the classifier 91 may be generated for each type of substrate W or for each flow rate of the processing liquids Lq1 and Lq2. . Also, for example, the positions of the ejection nozzles in the image captured by the camera 70 may be different. For example, in a captured image, the positional relationship of the ejection nozzles 31 of the treatment liquid supply section 30 and the positional relationship of the ejection nozzles 66 of the treatment liquid supply section 65 may be different. In this case, the classifier 91 may be generated for each ejection nozzle position. Moreover, these may be combined. For example, the classifier 91 may be generated according to the type of set of processing liquids Lq1 and Lq2 and the type of substrate W. FIG. For example, if there are N types of pairs of processing liquids Lq1 and Lq2 and M types of substrates W, (N×M) classifiers 91 may be generated according to the combinations. .

The user interface 90 inputs information necessary for selecting the classifier 91 (at least one of the types of the processing liquids Lq1 and Lq2, the type of the substrate W, the flow rate of the processing liquids Lq1 and Lq2, and the position of the discharge nozzle). The input information may be received and output to the control unit 9 .

Also, the information necessary for selecting the classifier 91 does not necessarily have to be input by the operator. For example, substrate information about the substrate W may be transmitted from the upstream side of the substrate processing apparatus 100 to the control unit 9, and such information may be included in the substrate information. In this case, the control unit 9 may select the classifier 91 based on the information in the substrate information.

<server>
In the above example, the control unit 9 provided in the substrate processing apparatus 100 generated the classifier 91 by machine learning, and the classifier 91 classified the frames. However, at least part of the machine learning function by the control unit 9 may be provided in the server.

FIG. 19 is a functional block diagram schematically showing an example of the electrical configuration of the substrate processing system; A substrate processing system includes a substrate processing apparatus 100 and a server 200 . As illustrated in FIG. 19 , the control unit 9 of the substrate processing apparatus 100 communicates with the server 200 via the communication unit 93 . The communication unit 93 is a communication interface and can communicate with the server 200 by wire or wirelessly.

In the example of FIG. 19, the server 200 includes a machine learning section 210 and a storage medium storing a determination database 220. In the example of FIG. The machine learning section 210 has the same function as the machine learning section 92, and can generate the determination database 220 based on the teacher data. Decision database 220 is similar to decision database 913 .

The determination unit 912 transmits a request signal requesting the determination database 220 to the server 200 via the communication unit 93 . Server 200 transmits determination database 220 to communication unit 93 in response to the request signal. This allows the determination unit 912 to use the determination database 220 stored in the server 200 . Note that in this case, the machine learning unit 92 and the determination database 913 are not necessarily required.

Further, although the determination unit 912 is provided in the control unit 9 of the substrate processing apparatus 100 in the above example, the determination unit 912 may be provided in the server 200 . In this case, feature vector extraction unit 911 transmits the feature vector to server 200 via communication unit 93 . Server 200 classifies frames based on the received feature vector and determination database 220 and transmits the classification result to communication section 93 . The communication section 93 outputs this classification result to the control section 9 .

Further, although the feature vector extraction unit 911 is provided in the control unit 9 of the substrate processing apparatus 100 in the above example, the feature vector extraction unit 911 may be provided in the server 200 . That is, the classifier 91 itself may be provided in the server 200 . In this case, the control unit 9 transmits the captured image frame generated by the camera 70 to the server 200 via the communication unit 93 . Server 200 extracts a feature vector from the frame, classifies the frame using the extracted feature vector and determination database 220 , and transmits the classification result to communication section 93 . The communication section 93 outputs this classification result to the control section 9 .

According to the aspect described above, since the determination processing function is provided in the server 200, common determination can be performed for a plurality of substrate processing units.

The machine learning unit 210 of the server 200 generates the determination database 220 for at least one of the types of the treatment liquids Lq1 and Lq2, the type of the substrate W, the flow rates of the treatment liquids Lq1 and Lq2, and the positions of the ejection nozzles 31a and 31b. You may In this case, the control section 9 may transmit information designating the determination database 220 to be used to the server 200 via the communication section 93 .

In short, the substrate processing apparatus 100 and the server 200 as a whole should exhibit the function of classifying each frame included in the captured image into each category using a machine-learned classifier and obtaining the timing difference based on the classification result. Just do it.

<Deep learning>
Deep learning may be employed as machine learning. FIG. 20 shows a model of neural network (including deep learning) NN1. This model has an input layer, an intermediate layer (hidden layer), and an output layer. Each layer has a plurality of nodes (artificial neurons), and each node receives the weighted output data of the nodes in the preceding layer. That is, each node receives a multiplication result obtained by multiplying the output of the preceding node by each weighting factor. Each node outputs, for example, the result of a known function. The number of intermediate layers is not limited to one and can be set arbitrarily.

The machine learning unit 92 determines weighting coefficients used for weighting between nodes by performing learning based on teacher data. This weighting factor is stored as a decision database. Thereby, the machine learning unit 92 can substantially generate the classifier 91 .

A frame F generated by the camera 70 is input to the input layer. The classifier 91 uses each weighting coefficient stored in the determination database to perform arithmetic processing from the input layer to the output layer via the intermediate layer based on the frame F, so that the frame F falls under each of the categories C1 to C4. Calculate the probability. Classifier 91 then classifies the frame into the most probable category.

As described above, frames can be classified by a neural network. In the neural network, the classifier 91 automatically generates feature quantities, so the designer does not need to determine feature vectors.

A plurality of classifiers 91 may be generated in the neural network as well. For example, the machine learning unit 92 may perform machine learning using teacher data for each type of treatment liquids Lq1 and Lq2 to generate a determination database (weighting coefficient) for each type.

The classifier 91 identifies the types of the treatment liquids Lq1 and Lq2 according to input information from the user interface 90, and classifies the frame F using a determination database corresponding to the type. As a result, classification accuracy can be improved.

Of course, the classifier 91 may be generated for at least one of the types of the substrate W, the flow rates of the processing liquids Lq1 and Lq2, and the positions of the discharge nozzles 31a and 31b, without being limited to the types of the processing liquids Lq1 and Lq2.

Second embodiment.
An example of the configuration of the substrate processing apparatus 100 according to the second embodiment is the same as that of the first embodiment, and an example of its operation is shown in FIG. However, a specific example of monitoring processing differs from that of the first embodiment. In the second embodiment, the control unit 9 performs image processing on the captured image captured by the camera 70 to detect the liquid splash that occurs when the ejection nozzle 31a is switched to the ejection nozzle 31b. do. That is, in the monitoring process, it is monitored whether or not liquid splashing occurs.

FIG. 21 is a diagram showing an example of a captured image frame generated by the camera 70. As shown in FIG. In a frame IM5 illustrated in FIG. 21, the treatment liquids Lq1 and Lq2 are ejected from the ejection nozzles 31a and 31b, respectively, and the liquid splashes. This liquid splash occurs in the vicinity of the ejection nozzles 31a and 31b.

Since the area where the liquid splash occurs is known in advance, the liquid splash determination area R2 can be set in the captured image in order to detect the liquid splash. Specifically, the liquid splash determination region R2 is set in the vicinity of the ejection nozzles 31a and 31b in each frame of the captured image. The liquid splash determination region R2 is set in a region within the region in which the substrate W is reflected and which does not overlap with the ejection determination regions Ra1 and Rb1. In the example of FIG. 21, the liquid splash determination region R2 has determination regions R21 and R22, which are set near the ejection nozzles 31a and 31b. More specifically, the determination regions R21 and R22 are located on opposite sides of the set of ejection nozzles 31a and 31b in the horizontal direction of the captured image. In the example of FIG. 21, the determination regions R21 and R22 have rectangular shapes.

When the liquid splash is reflected in the determination areas R21 and R22, the reflection of the illumination light on the liquid splash increases the average luminance value in the determination areas R21 and R22, and the luminance distribution varies greatly. become. Conversely, it is possible to determine whether or not liquid splash occurs based on the sum or dispersion (for example, standard deviation) of the pixel values in the determination regions R21 and R22. Therefore, the control unit 9 sets a statistic B1 that is the sum or variance (eg, standard deviation) of the pixel values in the determination region R21 and a statistic B2 that is the sum or variance (eg, standard deviation) of the pixel values in the determination region R22. calculate. When the statistical amounts B1 and B2 of the pixel values in the determination regions R21 and R22 become large, it can be determined that the liquid splash occurs.

FIG. 22 is a graph showing an example of temporal changes in statistics B1 and B2. The example of FIG. 22 shows the statistics B1 and B2 when the liquid splash occurs in step S5. As illustrated in FIG. 22, when liquid splash occurs, the statistics B1 and B2 increase and exceed the threshold th2. Conversely, when at least one of the statistic B1 and the statistic B2 is greater than the threshold th2, it can be determined that the liquid splash is occurring. Such a threshold th2 can be set in advance by experiment, simulation, or the like.

<Operation of Control Unit 9>
An example of the operation of the control section 9 is the same as the flowchart in FIG. However, the specific contents of the monitoring process in step S10 are different. In the second embodiment, this monitoring process is a process of monitoring whether or not liquid splashing occurs based on the captured image generated by the camera 70 .

23 is a flowchart illustrating an example of the operation of monitoring processing according to the second embodiment; FIG. First, in step S30, the control unit 9 initializes the value nn to 1. Next, in step S31, the control unit 9 determines whether or not liquid splash occurs based on the nn-th frame F[nn]. Specifically, the control unit 9 calculates statistics B1 and B2 of pixel values in the determination regions R21 and R22 of the frame F[nn].

Next, the control unit 9 determines whether or not at least one of the statistics B1 and B2 is equal to or greater than the threshold th2. When both of the statistics B1 and B2 are less than the threshold value th2, it is determined that the liquid splash has not occurred, and in step S32, the control unit 9 adds 1 to the value nn to update it. Step S31 is executed for the value nn. That is, when both of the statistics B1 and B2 are less than the threshold value th2, it is determined that the liquid splash has not occurred, and the determination of step S31 is performed for the next frame.

On the other hand, when at least one of the statistics B1 and B2 is equal to or greater than the threshold value th2, the controller 9 performs error notification processing in step S33. For example, the controller 9 causes the display of the user interface 90 to display an error. Alternatively, when a sound output unit such as a buzzer or speaker is provided, the control unit 9 may cause the sound output unit to output an error. Such notification allows the operator to recognize that liquid splashing has occurred.

Next, in step S34, the controller 9 adjusts either the start timing tb or the stop timing ta. That is, when at least one of the statistics B1 and B2 is equal to or greater than the threshold th2, it is determined that the liquid splash is detected, and the controller 9 adjusts the timing difference. Specifically, at least one of the start timing tb and the stop timing ta is adjusted so that the timing difference becomes small.

The amount of reduction in the timing difference may be predetermined. That is, in step S34, the control unit 9 may reduce the timing difference by a predetermined reduction amount. Then, the control unit 9 performs the operation of FIG. 4 again. At this time, when the liquid splash is detected again in step S31, the timing difference is reduced again by the reduction amount in step S34. By repeating this series of operations, the timing difference is adjusted to a value that does not cause liquid splashing.

As described above, in the second embodiment, when the occurrence of liquid splash is detected, the timing difference is adjusted so that the liquid splash does not occur. Thereby, it is possible to avoid or suppress the occurrence of liquid splash in subsequent processes.

<Machine learning>
In the above example, the controller 9 detects the liquid splash based on the statistics B1 and B2 of the pixel values, but this is not necessarily the case. The control unit 9 may detect the liquid splash by machine learning.

An example of the internal configuration of the control unit 9 is the same as that shown in FIG. However, in the second embodiment, the classifier 91 classifies each frame input from the camera 70 into the following two categories C11 and C12. That is, category C11 is a category indicating a state in which no liquid splash occurs, and category C12 is a category indicating a state in which liquid splash occurs.

Frames of captured images captured by the camera 70 are used as learning data, and teacher data is generated by assigning a correct category to the learning data as a label. A machine learning unit 92 generates a judgment database 913 based on the teacher data.

A flowchart showing an example of the operation of the control unit 9 in this monitoring process is the same as that shown in FIG. However, in step S31, the control unit 9 determines whether liquid splash is detected based on the classification result of the classifier 91 for the frame F[nn]. Specifically, the control unit 9 determines that the liquid splash is not detected when the frame F[nn] is classified into the category C11, and determines that the frame F[nn] is classified into the category C12. Then, it is determined that the liquid splash is detected.

As described above, the classifier 91 generated by machine learning classifies the frame F[nn] into category C11 or category C12. Therefore, frames can be classified with high classification accuracy. As a result, the liquid splash can be detected with high detection accuracy.

Also in the second embodiment, a plurality of classifiers 91 may be generated as in the first embodiment, and part or all of the classifiers 91 and the machine learning unit 92 are provided in the server 200. may

Modification.
In the above example, the two discharge nozzles 31a and 31b provided vertically above the substrate W are used for processing. However, it is not necessarily limited to this. FIG. 24 is a diagram showing an example of the configuration of the processing unit 1A. The processing unit 1A is the same as the processing unit 1 except for the presence or absence of the processing liquid supply section 80. FIG. The processing liquid supply unit 80 has an ejection nozzle 81 , and the ejection nozzle 81 is provided on the side of the substrate W and at a position higher than the upper surface of the substrate W. As shown in FIG. The ejection nozzle 81 ejects the processing liquid Lq3 along a substantially horizontal direction so that the processing liquid lands on the upper surface of the substrate W. As shown in FIG. The treatment liquid Lq3 is discharged from the tip of the discharge nozzle 81 in an arc shape and lands on the upper surface of the substrate W near the center thereof. The discharge nozzle 81 is connected to a processing liquid supply source 84 via a pipe 82 . An on-off valve 83 is provided in the middle of the pipe 82 . By opening the on-off valve 83 , the processing liquid Lq 3 from the processing liquid supply source 84 flows inside the pipe 82 and is discharged from the discharge nozzle 81 .

In such a processing unit 1A, the processing liquid is supplied to the substrate W in order using the ejection nozzle (for example, the ejection nozzle 31a) located above the substrate W and the ejection nozzle 81 located to the side of the substrate W. Sometimes. Here, the substrate W is processed with the treatment liquid Lq1 from the ejection nozzle 31a, then the nozzle for ejecting the treatment liquid is switched from the ejection nozzle 31a to the ejection nozzle 81, and the treatment liquid Lq3 from the ejection nozzle 81 is applied to the substrate W. A case of processing will be described.

The camera 70 is provided at a position where the tips of the ejection nozzles 31a, 31b, and 81 are included in the imaging area. Each frame of the captured image generated by the camera 70 is sequentially output to the control unit 9 .

FIG. 25 is a diagram schematically showing an example of a frame IM6 of a captured image generated by camera 70. As shown in FIG. In frame IM6, ejection nozzles 31a and 81 eject treatment liquids Lq1 and Lq3, respectively. In other words, the frame IM6 is a frame at the timing when both of the ejection nozzles 31a and 81 eject the processing liquid when the ejection nozzles 31a and 81 are switched.

Liquid splashing occurs on the substrate W in this frame IM6. This liquid splash is also caused by both of the discharge nozzles 31a and 81 discharging the treatment liquids Lq1 and Lq3, respectively. Since the processing liquid Lq3 from the discharge nozzle 81 is discharged from the side of the substrate W toward the vicinity of the center of the substrate W, the liquid splash occurs on the opposite side of the center of the substrate W from the discharge nozzle 81. Cheap.

An ejection determination region Rc1 is set in the frame IM6. The ejection determination region Rc1 is provided on the ejection path of the treatment liquid Lq3 from the tip of the ejection nozzle 81 to the liquid landing position on the substrate W, and extends in the direction in which the treatment liquid Lq3 extends from the tip of the ejection nozzle 81, for example. ing. The ejection determination region Rc1 has, for example, a rectangular shape.

The control unit 9 determines whether or not the treatment liquid Lq3 is ejected from the ejection nozzles 81 based on the size of the statistic of the pixel values in the ejection determination region Rc1, similarly to the ejection nozzles 31a and 31b. Identify timing. As the statistic here, the sum or variance of the pixel values in the ejection determination region Rc1 can be used. Further, since the ejection nozzle 81 ejects the treatment liquid Lq3 in the horizontal direction, variations in the luminance distribution in the horizontal direction are small, and the characteristics of the treatment liquid Lq3 appear in the luminance distribution in the vertical direction. Therefore, as the statistic, the variance of pixels arranged in a row in the vertical direction may be used. Alternatively, the pixel values of the pixels arranged in the horizontal direction may be integrated for each row, and the variance of the integration value for each row may be adopted.

Further, similarly to the first embodiment, the control unit 9 also specifies the stop timing of the ejection nozzles 31a.

The controller 9 calculates the timing difference between the start timing of the ejection nozzle 81 and the stop timing of the ejection nozzle 31a. For example, the timing difference is calculated by subtracting the start timing from the stop timing. Then, the control unit 9 determines whether or not the timing difference is outside a predetermined range. When the timing difference is outside the predetermined range, the controller 9 adjusts either the stop timing of the ejection nozzle 31a or the stop timing of the ejection nozzle 81 so that the timing difference is within the predetermined range.

As described above, also in the processing unit 1A, the timing difference between the stop timing of the ejection nozzle 31a and the start timing of the ejection nozzle 81 can be adjusted.

As in the second embodiment, whether or not the treatment liquid Lq3 is discharged from the discharge nozzle 81 may be determined by a machine-learned classifier.

Further, in the example of FIG. 25, a liquid splash determination region R3 is provided. This liquid splash determination region R3 is provided in a region in which the substrate W is reflected and on the opposite side of the center of the substrate W from the ejection nozzles 81 . The liquid splash determination region R3 has, for example, a rectangular shape.

Similarly to the liquid splash determination region R2, the control unit 9 determines the presence or absence of liquid splash based on the magnitude of the statistic of the pixel values in the liquid splash determination region R3. As the statistic here, the sum or variance of the pixel values in the ejection determination region Rc1 can be used. Then, when the liquid splash occurs, the controller 9 adjusts the timing difference between the start timing of the ejection nozzle 81 and the stop timing of the ejection nozzle 31a so that the liquid splash does not occur.

Also, the presence or absence of liquid splash may be determined by a machine-learned classifier, as in the fourth embodiment.

Although the embodiment of the present substrate processing apparatus has been described above, it is possible to make various modifications other than those described above without departing from the gist of the embodiment. The various embodiments and modifications described above can be implemented in appropriate combinations. For example, both the first embodiment and the second embodiment may be implemented to both monitor timing differences and monitor liquid splashes.

Also, as the substrate W, a semiconductor substrate was used in the description, but the substrate W is not limited to this. For example, substrates such as photomask glass substrates, liquid crystal display glass substrates, plasma display glass substrates, FED (Field Emission Display) substrates, optical disk substrates, magnetic disk substrates, or magneto-optical disk substrates may be used. good.

Furthermore, the present embodiment can be applied to any apparatus that performs a predetermined process by discharging a processing liquid from a movable nozzle onto a substrate. For example, in addition to the single-wafer cleaning processing apparatus of the above embodiment, a spin coating apparatus (spin coater) that applies resist by discharging a photoresist solution from a nozzle onto a rotating substrate, and a substrate with a film formed on its surface. The technique according to the present embodiment may be applied to a device that discharges a film removing liquid from a nozzle onto the edge of the substrate, or a device that discharges an etchant from a nozzle onto the surface of the substrate.

20 substrate holding part 30, 60, 65 treatment liquid supply part 31a first nozzle (ejection nozzle)
31b second nozzle (ejection nozzle)
70 camera 90 user interface 91, 91A to 91C classifier 100 substrate processing apparatus W substrate

Claims (19)

A substrate processing method comprising:
a first step of holding the substrate;
a second step of generating a captured image by starting imaging of an imaging region including the tip of the first nozzle and the tip of the second nozzle with a camera;
a third step of starting to discharge the treatment liquid from the first nozzle to the substrate;
a fourth step of stopping ejection of the treatment liquid from the first nozzle and starting ejection of the treatment liquid from the second nozzle;
A timing difference between a start timing for starting ejection of the treatment liquid from the second nozzle and a stop timing for stopping ejection of the treatment liquid from the first nozzle in the fourth step, based on the image processing of the captured image. a fifth step of obtaining
determining whether or not the timing difference is outside a predetermined range; and when it is determined that the timing difference is outside the predetermined range, the timing difference is within the predetermined range. A sixth step of adjusting at least one of the timing and the stop timing ;
In the fifth step,
A statistic is calculated based on pixel values in a first ejection determination region extending in the ejection direction of the first nozzle from the tip of the first nozzle in each frame of the captured image, and the statistic is set in advance. Identifying the stop timing based on comparison with a threshold;
calculating the statistic based on pixel values in a second ejection determination region extending in the ejection direction of the second nozzle from the tip of the second nozzle in each frame, and comparing the statistic with the threshold; to identify the start timing,
The substrate processing method , wherein the statistic is a value reflecting the discharge state of the processing liquid from each of the first nozzle and the second nozzle . The substrate processing method according to claim 1,
A substrate processing method, wherein the stop timing is adjusted without adjusting the start timing. The substrate processing method according to claim 1 or 2 ,
a frame in which the statistic of the pixel values of the first ejection determination region is greater than the threshold; and a frame next to the frame in which the statistic of the first ejection determination region is less than the threshold. Identify the stop timing based on
a frame in which the statistic of the pixel values of the second ejection determination region is smaller than the threshold, and a frame next to the frame in which the statistic of the first ejection determination region is greater than the threshold. A substrate processing method, wherein the start timing is specified based on. The substrate processing method according to claim 3 ,
In the sixth step,
displaying on a user interface a graph showing changes over time in the statistics for the first nozzle and the second nozzle;
A substrate processing method, wherein when an input for target timing, which is at least one of the start timing and the stop timing, is input to the user interface, the target timing is adjusted according to the input. The substrate processing method according to any one of claims 1 to 4,
the statistic of the first ejection determination area is an integral value or a standard deviation of pixel values of the first ejection determination area;
The substrate processing method, wherein the statistic of the second ejection determination area is an integral value or a standard deviation of pixel values of the second ejection determination area. A substrate processing method comprising:
a first step of holding the substrate;
a second step of generating a captured image by starting imaging of an imaging region including the tip of the first nozzle and the tip of the second nozzle with a camera;
a third step of starting to discharge the treatment liquid from the first nozzle to the substrate;
a fourth step of stopping ejection of the treatment liquid from the first nozzle and starting ejection of the treatment liquid from the second nozzle;
A timing difference between a start timing for starting ejection of the treatment liquid from the second nozzle and a stop timing for stopping ejection of the treatment liquid from the first nozzle in the fourth step, based on the image processing of the captured image. a fifth step of obtaining
determining whether or not the timing difference is outside a predetermined range; and when it is determined that the timing difference is outside the predetermined range, the timing difference is within the predetermined range. a sixth step of adjusting at least one of the timing and the stop timing;
with
In the fifth step,
Using a machine-learned classifier, each frame included in the captured image is classified into discharge/stop of treatment liquid for each of the first nozzle and the second nozzle, and the timing is based on the classification result. Substrate processing method to find the difference. The substrate processing method according to claim 6,
specifying the stop timing based on a frame classified as ejection for the first nozzle and a frame next to the frame classified as stop for the first nozzle;
The substrate processing method, wherein the start timing is specified based on a frame classified as stop for the second nozzle and a frame next to the frame classified as discharge for the second nozzle. The substrate processing method according to claim 6,
The stop timing is after the start timing,
A method of processing a substrate, wherein the timing difference is determined based on the number of frames in which both the first nozzle and the second nozzle are classified to eject processing liquid and the time between the frames. The substrate processing method according to any one of claims 6 to 8,
The substrate processing method, wherein, in the sixth step, when it is determined that the timing difference is outside a predetermined range, the operator is notified of the fact. A substrate processing method comprising:
a first step of holding the substrate;
a second step of generating a captured image by starting imaging of an imaging region including the tip of the first nozzle and the tip of the second nozzle with a camera;
a third step of starting to discharge the treatment liquid from the first nozzle to the substrate;
a fourth step of stopping ejection of the treatment liquid from the first nozzle and starting ejection of the treatment liquid from the second nozzle;
A timing difference between a start timing for starting ejection of the treatment liquid from the second nozzle and a stop timing for stopping ejection of the treatment liquid from the first nozzle in the fourth step, based on the image processing of the captured image. a fifth step of obtaining
determining whether or not the timing difference is outside a predetermined range; and when it is determined that the timing difference is outside the predetermined range, the timing difference is within the predetermined range. a sixth step of adjusting at least one of the timing and the stop timing;
with
The stop timing is after the start timing,
Based on the image processing of the captured image, it is determined whether or not the treatment liquid splashes on the substrate, and when it is determined that the liquid splash occurs, the start timing and the stop are determined. the substrate processing method, further comprising a seventh step of adjusting at least one of the start timing and the stop timing so as to reduce a timing difference therebetween. The substrate processing method according to claim 10,
The substrate processing method, wherein in the seventh step, each frame of the captured image is classified into presence/absence of the liquid splash using a machine-learned classifier. The substrate processing method according to claim 11,
In the seventh step, a liquid splash determination region near the first nozzle and the second nozzle is cut out from each frame of the captured image, and the liquid splash determination region is determined using the classifier. A substrate processing method classified into with/without splash. The substrate processing method according to any one of claims 6 to 8, claims 11 and 12,
Among a plurality of machine-learned classifiers according to at least one of the type of the substrate, the type of the processing liquid, the positions of the first nozzle and the second nozzle, and the flow rate of the processing liquid choose one from
A substrate processing method for classifying each frame included in the captured image based on the selected classifier. The substrate processing method according to claim 13,
When at least one of the type of the substrate, the type of the processing liquid, the positions of the first nozzle and the second nozzle, and the flow rate of the processing liquid is input to the input section, selecting one of the plurality of classifiers according to the input of . a substrate holder that holds the substrate;
a processing liquid supply unit having a first nozzle for discharging a processing liquid onto the substrate and a second nozzle for discharging the processing liquid onto the substrate;
a camera that captures an imaging region including the tip of the first nozzle and the tip of the second nozzle to generate a captured image;
and a control unit,
The control unit
After starting to discharge the processing liquid from the first nozzle to the substrate, discharging the processing liquid to the substrate from the second nozzle is started, and discharging the processing liquid to the substrate from the first nozzle. controlling the processing liquid supply unit to stop
A timing difference between a start timing for starting ejection of the treatment liquid from the second nozzle and a stop timing for stopping ejection of the treatment liquid from the first nozzle is obtained based on the image processing of the captured image, and the timing is calculated. adjusting at least one of the start timing and the stop timing so that the timing difference is within the predetermined range when it is determined that the difference is outside the predetermined range ;
When obtaining the timing difference, the control unit performs statistics based on pixel values within a first ejection determination region extending in the ejection direction of the first nozzle from the tip of the first nozzle in each frame of the captured image. calculating the amount and identifying the stop timing based on a comparison of the statistic with a preset threshold;
calculating the statistic based on pixel values in a second ejection determination region extending in the ejection direction of the second nozzle from the tip of the second nozzle in each frame, and comparing the statistic with the threshold; to identify the start timing,
The substrate processing apparatus , wherein the statistic is a value that reflects the discharge state of the processing liquid from each of the first nozzle and the second nozzle . a substrate holder that holds the substrate;
a processing liquid supply unit having a first nozzle for discharging a processing liquid onto the substrate and a second nozzle for discharging the processing liquid onto the substrate;
a camera that captures an imaging region including the tip of the first nozzle and the tip of the second nozzle to generate a captured image;
control unit and
with
The control unit
After starting to discharge the processing liquid from the first nozzle to the substrate, discharging the processing liquid to the substrate from the second nozzle is started, and discharging the processing liquid to the substrate from the first nozzle. controlling the processing liquid supply unit to stop
A timing difference between a start timing for starting ejection of the treatment liquid from the second nozzle and a stop timing for stopping ejection of the treatment liquid from the first nozzle is obtained based on the image processing of the captured image, and the timing is calculated. adjusting at least one of the start timing and the stop timing so that the timing difference is within the predetermined range when it is determined that the difference is outside the predetermined range;
The control unit uses a machine-learned classifier to classify each frame included in the captured image into a category indicating a discharge/stop state of the treatment liquid for the first nozzle and the second nozzle, A substrate processing apparatus that obtains the timing difference based on the classification result. 17. The substrate processing apparatus according to claim 16,
The control unit
Among a plurality of machine-learned classifiers according to at least one of the type of the substrate, the type of the processing liquid, the positions of the first nozzle and the second nozzle, and the flow rate of the processing liquid choose one from
A substrate processing apparatus that classifies each frame included in the captured image based on the selected classifier. The substrate processing apparatus according to claim 17,
an input unit for inputting at least one of the type of the substrate, the type of the processing liquid, the positions of the first nozzle and the second nozzle, and the flow rate of the processing liquid;
The substrate processing apparatus, wherein the control unit selects one of the plurality of classifiers according to an input to the input unit. having a substrate processing apparatus and a server communicating with the substrate processing apparatus;
The substrate processing apparatus is
a substrate holder that holds the substrate;
a processing liquid supply unit having a first nozzle for discharging a processing liquid onto the substrate and a second nozzle for discharging the processing liquid onto the substrate;
a camera that captures an imaging region including the tip of the first nozzle and the tip of the second nozzle to generate a captured image;
After starting to discharge the processing liquid from the first nozzle to the substrate, discharging the processing liquid to the substrate from the second nozzle is started, and discharging the processing liquid to the substrate from the first nozzle. a control unit that controls the processing liquid supply unit to stop
The substrate processing apparatus and the server use a machine-learned classifier to categorize each frame included in the captured image into a category indicating the discharge/stop state of the processing liquid for the first nozzle and the second nozzle. classify, and based on the result of the classification, obtain a timing difference between a start timing for starting ejection of the treatment liquid from the second nozzle and a stop timing for stopping ejection of the treatment liquid from the first nozzle;
When the control unit determines that the timing difference is outside the predetermined range, the control unit adjusts at least one of the start timing and the stop timing so that the timing difference is within the predetermined range. Substrate processing system.

Images