Substrate processing apparatus and substrate processing method

Abstract

To provide a wafer processing device capable of improving uniformity of processing between a plurality of wafers.SOLUTION: A wafer processing device 100 comprises a plurality of processing units 220, a carrier mechanism 210 and a control unit CNT. The plurality of processing units 220 respectively processes a plurality of processing target wafers Wx. The carrier mechanism 210 performs carry-in and carry-out of the processing target wafer Wx with respect to the processing unit 220. The control unit CNT controls the plurality of processing units 220 and the carrier mechanism 210. The control unit CNT controls one or more processing units 220 and the carrier mechanism 210 in such a manner that each of the processing target wafers Wx is processed by the one or more processing units 220 selected from among the plurality of processing units 220 on the basis of processing results of a plurality of wafers Wp by the plurality of processing units 220.SELECTED DRAWING: Figure 8

Description

Technical Field

[0001] The present invention relates to a substrate processing apparatus, a substrate processing method, a selection apparatus, a selection method, a learning model generation method, and a learning model.

Background Art

[0002] The substrate processing apparatus described in Patent Document 1 includes a carrier holding unit that holds a carrier for accommodating a substrate, a plurality of processing units that process the substrate, a substrate transfer unit that transfers the substrate between the carrier and the processing units, and a computer. The computer classifies the plurality of processing units into a plurality of groups, and selects one of the plurality of groups when determining the processing unit to process the substrate. Further, the computer selects one processing unit belonging to the selected group and controls the substrate transfer unit to carry the substrate into the selected processing unit. As a result, the variation in the usage frequency of the plurality of processing units can be reduced.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the substrate processing apparatus described in Patent Document 1 only focuses on the variation in the usage frequency of the processing units.

[0005] On the other hand, the inventor of the present application focused on the possibility that the processing characteristics vary among the plurality of processing units. And the inventor of the present application has conducted intensive research to improve the uniformity of processing among a plurality of substrates even when the processing characteristics vary.

[0006] An object of the present invention is to provide a substrate processing apparatus, a substrate processing method, a selection apparatus, a selection method, a learning model generation method, and a learning model capable of improving the uniformity of processing between a plurality of substrates.

Means for Solving the Problems

[0007] According to an aspect of the present invention, a substrate processing apparatus includes a plurality of processing units, a transfer mechanism, and a control unit. The plurality of processing units each process a plurality of substrates to be processed. The transfer mechanism carries in and out the substrates to be processed with respect to the processing units. The control unit controls the plurality of processing units and the transfer mechanism. The control unit controls the one or more processing units and the transfer mechanism so that each of the substrates to be processed is processed by one or more processing units selected from among the plurality of processing units based on the processing results of the plurality of substrates by each of the plurality of processing units. The control unit includes a first selection unit. The first selection unit selects, from among the plurality of processing units, the one or more processing units to be used for processing each of the substrates to be processed based on a plurality of pieces of processing result information each indicating the processing result of the plurality of substrates by the plurality of processing units. Each of the plurality of pieces of processing result information includes at least one of the contact angle of the processing liquid on the surface of the substrate, a numerical value based on the contact angle, the heat treatment China temperature on the surface of the substrate, a numerical value based on the temperature, the line width of the pattern on the surface of the substrate, a numerical value based on the line width, the number of collapses of the pattern on the surface of the substrate, a numerical value based on the number of collapses, and the cut width of the edge of the substrate.

[0008] In the substrate processing apparatus of the present invention, the first selection unit selects, from among the plurality of processing units, the one or more processing units to be used for processing each of the substrates to be processed with priority orders of use based on the plurality of pieces of processing result information.

[0009] The substrate processing apparatus of the present invention further includes a measurement unit. The measurement unit measures the contact angle, the temperature, the line width, the number of collapses, or the cut width.

[0010] In the substrate processing apparatus of the present invention, the first selection unit determines a processing unit to be unused from among the plurality of processing units based on the plurality of processing result information.

[0011] In the substrate processing apparatus of the present invention, the control unit further includes an analysis unit and an adjustment unit. The analysis unit analyzes the processing result information indicating the processing result of the substrate by the processing unit to be unused. The adjustment unit adjusts the processing unit to be unused based on the analysis result of the processing result information, and returns the processing unit to be unused to a processing unit to be used.

[0012] According to another aspect of the present invention, a substrate processing method is executed by a substrate processing apparatus including a plurality of processing units that respectively process a plurality of substrates to be processed, and a transfer mechanism that transfers the substrates to be processed into and out of the processing units. The substrate processing method includes a step of selecting one or more processing units to be used for processing each of the substrates to be processed from among the plurality of processing units based on a plurality of processing result information respectively indicating the processing results of the plurality of substrates by the plurality of processing units, a step of controlling the one or more processing units and the transfer mechanism so that each of the substrates to be processed is processed by the one or more processing units selected based on the plurality of processing result information from among the plurality of processing units, and a step of processing the substrates to be processed. Each of the plurality of processing result information indicates at least one of a contact angle of a processing liquid on the surface of the substrate, a numerical value based on the contact angle, a temperature of a heat treatment on the surface of the substrate, a numerical value based on the temperature, a line width of a pattern on the surface of the substrate, a numerical value based on the line width, a number of collapses of a pattern on the surface of the substrate, a numerical value based on the number of collapses, and a cut width of an edge of the substrate. China of the temperature, a numerical value based on the temperature, a line width of a pattern on the surface of the substrate, a numerical value based on the line width, a number of collapses of a pattern on the surface of the substrate, a numerical value based on the number of collapses, and a cut width of an edge of the substrate.

[0013] In the method for processing a substrate according to the present invention, in the step of selecting the processing unit, based on the plurality of processing result information, one or more processing units to be used for processing each of the substrates to be processed are selected from among the plurality of processing units, with priority orders for use.

[0014] The method for processing a substrate according to the present invention further includes a step of measuring the contact angle, the temperature, the line width, the number of collapses, or the cut width.

[0015] In the method for processing a substrate according to the present invention, in the step of selecting the processing unit, based on the plurality of processing result information, a processing unit not to be used is determined from among the plurality of processing units.

[0016] The method for processing a substrate according to the present invention further includes a step of analyzing the processing result information indicating the processing result of the substrate by the processing unit not to be used, and a step of adjusting the processing unit not to be used and returning the processing unit not to be used to a processing unit to be used, based on the analysis result of the processing result information.

Effects of the Invention

[0017] According to the present invention, it is possible to provide a substrate processing apparatus, a substrate processing method, a selection apparatus, a selection method, a learning model generation method, and a learning model that can improve the uniformity of processing among a plurality of substrates.

Brief Description of the Drawings

[0018]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

Figure 23

Figure 24

Figure 25

Figure 26

Figure 27

Figure 28

Figure 29

Modes for Carrying Out the Invention

[0019] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the drawings, the same or corresponding parts are denoted by the same reference numerals and description thereof will not be repeated. In the embodiments of the present invention, the X-axis, Y-axis, and Z-axis are orthogonal to each other, the X-axis and Y-axis are parallel in the horizontal direction, and the Z-axis is parallel in the vertical direction.

[0020] (Embodiment 1) With reference to FIGS. 1 to 7, a substrate processing apparatus 100 according to Embodiment 1 of the present invention will be described. The substrate processing apparatus 100 processes a plurality of substrates W in parallel. The substrate W is, for example, a semiconductor wafer, a substrate for a liquid crystal display device, a substrate for a plasma display, a substrate for a field emission display (FED), a substrate for an optical disk, a substrate for a magnetic disk, a substrate for a magneto-optical disk, a substrate for a photomask, a ceramic substrate, or a substrate for a solar cell. The substrate W is, for example, substantially disk-shaped. In the following description of Embodiment 1, the substrate W is a semiconductor substrate.

[0021] First, with reference to FIG. 1, the substrate processing apparatus 100 will be described. FIG. 1 is a plan view showing the substrate processing apparatus 100 according to Embodiment 1. As shown in FIG. 1, the substrate processing apparatus 100 includes an indexer block 11, a first processing block 12, a second processing block 13, a cleaning and drying processing block 14A, a loading / unloading block 14B, and a control device CM. The cleaning and drying processing block 14A and the loading / unloading block 14B constitute an interface block 14. An exposure apparatus 15 is arranged adjacent to the loading / unloading block 14B. In the exposure apparatus 15, the substrate W is subjected to an exposure process by the immersion method.

[0022] The control device CM controls the indexer block 11, the first processing block 12, the second processing block 13, and the interface block 14. The control device CM is, for example, a computer.

[0023] The indexer block 11 includes a plurality of carrier placement units 111 and a transfer unit 112. A carrier 113 for storing a plurality of substrates W in multiple stages is placed on each carrier placement unit 111. In Embodiment 1, a FOUP (front opening unified pod) is adopted as the carrier 113, but it is not limited thereto. For example, a SMIF (Standard Mechanical Inter Face) pod or an OC (open cassette) that exposes the stored substrate W to the outside air may be used.

[0024] A transfer mechanism 115 is provided in the transfer unit 112. The transfer mechanism 115 has a hand 116 for holding the substrate W. The transfer mechanism 115 transfers the substrate W while holding the substrate W with the hand 116. Further, as shown in FIG. 5 described later, an opening 117 for transferring the substrate W between the carrier 113 and the transfer mechanism 115 is formed in the transfer unit 112.

[0025] The first processing block 12 includes a coating processing unit 121, a transfer unit 122, and a heat treatment unit 123. The heat treatment unit 123 includes a plurality of plates 5. The substrate W is placed on the plate 5. The coating processing unit 121 and the heat treatment unit 123 face each other with the transfer unit 122 interposed therebetween. A substrate placement unit PASS1 on which the substrate W is placed and substrate placement units PASS2 to PASS4 (see FIG. 5) described later are provided between the transfer unit 122 and the indexer block 11. A transfer mechanism 127 for transferring the substrate W and a transfer mechanism 128 (see FIG. 5) described later are provided in the transfer unit 122.

[0026] The second processing block 13 includes a development processing unit 131, a transport unit 132, and a heat treatment unit 133. The heat treatment unit 133 includes a plurality of plates 5. The substrate W is placed on the plate 5. The development processing unit 131 and the heat treatment unit 133 are provided to face each other with the transport unit 132 interposed therebetween. Between the transport unit 132 and the transport unit 122, a substrate placement unit PASS5 on which the substrate W is placed and substrate placement units PASS6 to PASS8 (see FIG. 5) described later are provided. In the transport unit 132, a transport mechanism 137 for transporting the substrate W and a transport mechanism 138 (see FIG. 5) described later are provided. Inside the second processing block 13, a packing 145 is provided between the heat treatment unit 133 and the interface block 14.

[0027] The cleaning and drying processing block 14A includes cleaning and drying processing units 161, 162, and a transport unit 163. The cleaning and drying processing units 161, 162 face each other with the transport unit 163 interposed therebetween. In the transport unit 163, transport mechanisms 141, 142 are provided.

[0028] Between the transport unit 163 and the transport unit 132, a placement and buffer unit P-BF1 and a placement and buffer unit P-BF2 (see FIG. 5) described later are provided. The placement and buffer units P-BF1, P-BF2 can accommodate a plurality of substrates W.

[0029] Also, between the transport mechanisms 141, 142, substrate placement units PASS11, PASS12 and a placement and cooling unit P-CP (see FIG. 5) described later are provided so as to be adjacent to the loading / unloading block 14B. The placement and cooling unit P-CP has a function of cooling the substrate W (for example, a cooling plate). In the placement and cooling unit P-CP, the substrate W is cooled to a temperature suitable for the exposure process. Therefore, the placement and cooling unit P-CP functions as a cooling processing unit. Hereinafter, the placement and cooling unit P-CP may be described as a processing unit P-CP or a cooling processing unit P-CP.

[0030] A transfer mechanism 146 is provided in the loading / unloading block 14B. The transfer mechanism 146 transfers the substrate W into and out of the exposure apparatus 15. The transfer mechanism 146 has hands H7 and H8 for holding the substrate W. The exposure apparatus 15 is provided with a substrate loading section 15a for loading the substrate W and a substrate unloading section 15b for unloading the substrate W.

[0031] Next, with reference to FIG. 2, the coating processing section 121 and the developing processing section 131 in FIG. 1 will be described. FIG. 2 is a view of the coating processing section 121, the developing processing section 131, and the cleaning and drying processing section 161 in FIG. 1 as seen from the direction D1 in FIG. 1.

[0032] As shown in FIG. 2, coating processing chambers 21, 22, 23, and 24 are hierarchically provided in the coating processing section 121. Anti-reflection film coating processing units AR

[11] and AR

[12] are provided in the coating processing chamber 21. Anti-reflection film coating processing units AR

[21] and AR

[22] are provided in the coating processing chamber 23. Resist film coating processing units RT

[11] and RT

[12] are provided in the coating processing chamber 22. Resist film coating processing units RT

[21] and RT

[22] are provided in the coating processing chamber 24.

[0033] Hereinafter, the anti-reflection film coating processing units AR

[11] , AR

[12] , AR

[21] , and AR

[22] may be collectively referred to as the processing unit AR or the anti-reflection film coating processing unit AR. Also, the resist film coating processing units RT

[11] , RT

[12] , RT

[21] , and RT

[22] may be collectively referred to as the processing unit RT or the resist film coating processing unit RT.

[0034] Each of the processing units RT and AR includes a spin chuck 25 for holding the substrate W and a cup 27 provided so as to cover the periphery of the spin chuck 25. The spin chuck 25 is rotationally driven by a driving device (for example, an electric motor) not shown.

[0035] Further, as shown in FIG. 1, the coating processing chamber 24 where the processing unit RT is disposed is provided with a plurality of nozzles 28 for discharging the processing liquid and a nozzle transfer mechanism 29. The nozzle transfer mechanism 29 transfers the nozzles 28.

[0036] In the coating processing chamber 24, any one of the plurality of nozzles 28 is moved above the substrate W by the nozzle transfer mechanism 29. Then, the processing liquid is discharged from the nozzle 28, and the processing liquid is applied onto the substrate W. When the processing liquid is supplied from the nozzle 28 to the substrate W, the spin chuck 25 is rotated by a driving device (not shown). As a result, the substrate W is rotated.

[0037] Each of the coating processing chambers 23, 22, 21 (FIG. 2) is also provided with a plurality of nozzles 28 and a nozzle transfer mechanism 29, similar to the coating processing chamber 24.

[0038] The nozzles 28 and the nozzle transfer mechanism 29 of the coating processing chambers 24 and 22 constitute a part of the processing unit RT. The nozzles 28 and the nozzle transfer mechanism 29 of the coating processing chambers 23 and 21 constitute a part of the processing unit AR.

[0039] In Embodiment 1, in the coating processing chambers 24 and 22 where the processing unit RT is disposed, the processing liquid for the resist film is supplied from the nozzles 28 to the substrate W. Therefore, the nozzles 28 of the coating processing chambers 24 and 22 constitute a part of the processing unit RT.

[0040] Also, in the coating processing chambers 23 and 21 where the processing unit AR is disposed, the processing liquid for the antireflection film is supplied from the nozzles 28 to the substrate W. Therefore, the nozzles 28 of the coating processing chambers 23 and 21 constitute a part of the processing unit AR.

[0041] As shown in FIG. 2, the development processing unit 131 is provided with development processing chambers 31, 32, 33, and 34 in a hierarchical manner. In the development processing chamber 31, development processing units DV

[12] , DV

[14] , and DV

[16] are provided. In the development processing chamber 32, development processing units DV

[11] , DV

[13] , and DV

[15] are provided. In the development processing chamber 33, development processing units DV

[22] , DV

[24] , and DV

[26] are provided. In the development processing chamber 34, development processing units DV

[21] , DV

[23] , and DV

[25] are provided.

[0042] Hereinafter, the development processing units DV

[11] to DV

[16] , DV

[21] to DV

[26] may be collectively referred to as the processing unit DV or the development processing unit DV.

[0043] Similar to the processing units RT and AR, the processing unit DV includes a spin chuck 35 and a cup 37. As shown in FIG. 1, the processing unit DV also includes two nozzles 38 for discharging the developer and a moving mechanism 39. The moving mechanism 39 moves the nozzle 38 in the X direction.

[0044] In the processing unit DV, first, while one nozzle 38 moves in the X direction, the developer is supplied to each substrate W. Then, while the other nozzle 38 moves in the X direction, the developer is supplied to each substrate W. When the developer is supplied from the nozzle 38 to the substrate W, the spin chuck 35 is rotated by a driving device (not shown). As a result, the substrate W is rotated.

[0045] In Embodiment 1, when the developer is supplied to the substrate W in the processing unit DV, the resist cover film on the substrate W is removed and the development processing of the substrate W is performed. Also, in Embodiment 1, different developers are discharged from the two nozzles 38. Therefore, two types of developers can be supplied to each substrate W.

[0046] As shown in FIG. 2, the cleaning and drying processing section 161 is provided with a plurality (four in this example) of cleaning and drying processing units SD1. In the cleaning and drying processing unit SD1, the cleaning and drying processing of the substrate W before the exposure processing is performed.

[0047] Further, above the processing units AR and RT in the coating processing chambers 21 to 24, an air supply unit 41 for supplying clean air whose temperature and humidity are adjusted in the coating processing chambers 21 to 24 is provided. Also, above the processing unit DV in the development processing chambers 31 to 34, an air supply unit 47 for supplying clean air whose temperature and humidity are adjusted in the development processing chambers 31 to 34 is provided.

[0048] Further, below the processing units AR and RT in the coating processing chambers 21 to 24, an exhaust unit 42 for exhausting the atmosphere in the cup 27 is provided. Also, below the processing unit DV in the development processing chambers 31 to 34, an exhaust unit 48 for exhausting the atmosphere in the cup 37 is provided.

[0049] As shown in FIGS. 1 and 2, a fluid box section 50 is provided in the coating processing section 121 so as to be adjacent to the development processing section 131. Similarly, a fluid box section 60 is provided in the development processing section 131 so as to be adjacent to the cleaning and drying processing block 14A. In the fluid box section 50 and the fluid box section 60, fluid-related devices such as conduits, joints, valves, flow meters, regulators, pumps, and temperature controllers related to the supply of chemical solutions to the processing units AR, RT, and DV and the drainage and exhaust from the processing units AR, RT, and DV are housed.

[0050] Next, with reference to FIG. 3, the heat treatment sections 123 and 133 and the cleaning and drying processing section 162 in FIG. 1 will be described. FIG. 3 is a view of the heat treatment sections 123 and 133 and the cleaning and drying processing section 162 as seen from the direction D1 in FIG. 1.

[0051] As shown in FIG. 3, the heat treatment unit 123 has an upper heat treatment unit 301 provided above and a lower heat treatment unit 302 provided below. In the lower heat treatment unit 302, adhesion strengthening treatment units PAHP

[11] to PAHP

[14] , a plurality of heat treatment units PHP

[15] to PHP

[22] , and a plurality of cooling treatment units CP

[11] to CP

[13] are provided. In the upper heat treatment unit 301, adhesion strengthening treatment units PAHP

[51] to PAHP

[54] , a plurality of heat treatment units PHP

[55] to PHP

[62] , and a plurality of cooling treatment units CP

[21] to CP

[23] are provided.

[0052] Further, the heat treatment unit 133 has an upper heat treatment unit 303 provided above and a lower heat treatment unit 304 provided below. In the lower heat treatment unit 304, a plurality of heat treatment units PHP

[23] to PHP

[34] , a plurality of cooling treatment units CP

[14] , CP

[15] , and an edge exposure treatment unit EEW[1] are provided. In the upper heat treatment unit 303, a plurality of heat treatment units PHP

[63] to PHP

[74] , a plurality of cooling treatment units CP

[24] , CP

[25] , and an edge exposure treatment unit EEW[2] are provided.

[0053] Hereinafter, the heat treatment units PHP

[15] to PHP

[34] , PHP

[55] to PHP

[74] may be collectively referred to as the treatment unit PHP or the heat treatment unit PHP. The adhesion strengthening treatment units PAHP

[11] to PAHP

[14] , PAHP

[51] to PAHP

[54] may be collectively referred to as the treatment unit PAHP or the adhesion strengthening treatment unit PAHP. The cooling treatment units CP

[11] to CP

[15] , CP

[21] to CP

[25] may be collectively referred to as the treatment unit CP or the cooling treatment unit CP. The edge exposure treatment units EEW[1], EEW[2] may be collectively referred to as the treatment unit EEW or the edge exposure treatment unit EEW.

[0054] In the heat treatment unit PHP, heat treatment and cooling treatment of the substrate W are performed. In the heat treatment unit PHP, heat treatment and cooling treatment of the substrate W are continuously performed. For example, the heat treatment unit PHP includes two plates 5 (FIG. 1). Then, the substrate W is placed on one plate 5, and heat treatment is performed on the substrate W. Also, the substrate W is placed on the other plate 5, and cooling treatment of the substrate W is performed.

[0055] In the adhesion strengthening treatment unit PAHP, an adhesion strengthening treatment for improving the adhesion between the substrate W and the antireflection film is performed. Specifically, in the adhesion strengthening treatment unit PAHP, an adhesion strengthening agent such as HMDS (hexamethyldisilazane) is applied to the substrate W, and heat treatment is performed on the substrate W. Applying an adhesion strengthening agent to the substrate W corresponds to performing a hydrophobization treatment on the substrate W. In addition, after the heat treatment of the substrate W, cooling treatment of the substrate W is performed. For example, the adhesion strengthening treatment unit PAHP includes two plates 5 (FIG. 1). Then, the substrate W is placed on one plate 5, and the adhesion strengthening agent is applied and heat treatment is performed on the substrate W. Also, the substrate W is placed on the other plate 5, and cooling treatment of the substrate W is performed.

[0056] In the cooling treatment unit CP, cooling treatment of the substrate W is performed. For example, the cooling treatment unit CP includes one or two plates (not shown). Then, the substrate W is placed on the plate, and cooling treatment of the substrate W is performed.

[0057] In the edge exposure treatment unit EEW, exposure treatment is performed on the peripheral portion of the substrate W. For example, the edge exposure treatment unit EEW includes one plate 5 (FIG. 1). Then, the substrate W is placed on the plate 5, and exposure treatment is performed on the peripheral portion of the substrate W.

[0058] Hereinafter, the heat treatment unit PHP, the adhesion strengthening treatment unit PAHP, the cooling treatment unit CP, the edge exposure treatment unit EEW, the coating treatment unit AR for the antireflection film, the coating treatment unit RT for the resist film, the development treatment unit DV, the mounting and cooling unit P-CP, and the substrate mounting parts PASS6 and PASS8 described later that can function as the cooling treatment unit are collectively referred to as the processing unit 220 (FIG. 5 described later).

[0059] Also, as shown in FIG. 3, the cleaning and drying treatment section 162 is provided with a plurality (five in this example) of cleaning and drying treatment units SD2. In the cleaning and drying treatment unit SD2, the substrate W after the exposure treatment is cleaned and dried.

[0060] Next, with reference to FIGS. 4 and 5, the coating treatment section 121, the transfer section 122, and the heat treatment section 123 in FIG. 1 will be described. FIG. 4 is a view of the coating treatment section 121, the transfer section 122, and the heat treatment section 123 as seen from the direction D2 in FIG. 1. FIG. 5 is a view of the transfer sections 122, 132, and 163 as seen from the direction D1 in FIG. 1.

[0061] As shown in FIGS. 4 and 5, the transfer section 122 has an upper transfer chamber 125 and a lower transfer chamber 126. The transfer section 132 has an upper transfer chamber 135 and a lower transfer chamber 136.

[0062] A transfer mechanism 127 is provided in the upper transfer chamber 125, and a transfer mechanism 128 is provided in the lower transfer chamber 126. Also, a transfer mechanism 137 is provided in the upper transfer chamber 135, and a transfer mechanism 138 is provided in the lower transfer chamber 136.

[0063] As shown in FIG. 4, the coating treatment chambers 23 and 24 and the upper heat treatment section 301 face each other with the upper transfer chamber 125 interposed therebetween, and the coating treatment chambers 21 and 22 and the lower heat treatment section 302 face each other with the lower transfer chamber 126 interposed therebetween. Similarly, the development treatment chambers 33 and 34 (FIG. 2) and the upper heat treatment section 303 (FIG. 3) face each other with the upper transfer chamber 135 (FIG. 5) interposed therebetween, and the development treatment chambers 31 and 32 (FIG. 2) and the lower heat treatment section 304 (FIG. 3) face each other with the lower transfer chamber 136 (FIG. 5) interposed therebetween.

[0064] As shown in FIG. 5, between the transport unit 112 and the upper transport chamber 125, substrate placement units PASS1 and PASS2 are provided, and between the transport unit 112 and the lower transport chamber 126, substrate placement units PASS3 and PASS4 are provided. For example, a placement and buffer unit may be provided between the transport unit 112 and the upper transport chamber 125. The placement and buffer unit is configured to enable the loading and unloading of the substrate W by the transport mechanisms 115 and 127. For example, a placement and buffer unit may be provided between the transport unit 112 and the lower transport chamber 126. The placement and buffer unit is configured to enable the loading and unloading of the substrate W by the transport mechanisms 115 and 128.

[0065] Between the upper transport chamber 125 and the upper transport chamber 135, substrate placement units PASS5 and PASS6 are provided, and between the lower transport chamber 126 and the lower transport chamber 136, substrate placement units PASS7 and PASS8 are provided. For example, a plurality of substrate placement units PASS6 (for example, three substrate placement units PASS6) may be provided vertically, or a plurality of substrate placement units PASS8 (for example, three substrate placement units PASS8) may be provided vertically. For example, a placement and buffer unit may be provided between the upper transport chamber 125 and the upper transport chamber 135. The placement and buffer unit is configured to enable the loading and unloading of the substrate W by the transport mechanisms 127 and 137. For example, a placement and buffer unit may be provided between the lower transport chamber 126 and the lower transport chamber 136. The placement and buffer unit is configured to enable the loading and unloading of the substrate W by the transport mechanisms 128 and 138.

[0066] Between the upper transport chamber 135 and the transport unit 163, a placement and buffer unit P-BF1 is provided, and between the lower transport chamber 136 and the transport unit 163, a placement and buffer unit P-BF2 is provided. Also, between the upper transport chamber 135 and the transport unit 163, a substrate placement unit PASS9 is provided. Further, between the lower transport chamber 136 and the transport unit 163, a substrate placement unit PASS10 is provided.

[0067] Adjacent to the loading and unloading block 14B in the transport unit 163, substrate placement units PASS11, PASS12, and a plurality of placement and cooling units P-CP are provided.

[0068] The placement / buffer section P-BF1 and the substrate placement section PASS9 are configured to allow the transfer mechanism 137 and the transfer mechanisms 141, 142 (FIG. 1) to load and unload the substrate W. The placement / buffer section P-BF2 and the substrate placement section PASS10 are configured to allow the transfer mechanism 138 and the transfer mechanisms 141, 142 (FIG. 1) to load and unload the substrate W. The substrate placement sections PASS11, PASS12 and the placement / cooling section P-CP are configured to allow the transfer mechanism 141, 142 (FIG. 1) and the transfer mechanism 146 to load and unload the substrate W.

[0069] The transport mechanisms 141, 142 (FIG. 1) can transfer the substrate W to and from the placement / buffer sections P-BF1, P-BF2, the substrate placement sections PASS9 to PASS12, and the placement / cooling section P-CP. The transport mechanism 146 can transfer the substrate W to and from the substrate placement sections PASS11, PASS12, the placement / cooling section P-CP, the substrate carry-in section 15a (FIG. 1), and the substrate carry-out section 15b (FIG. 1).

[0070] 5, only one substrate platform PASS11 is provided, but multiple substrate platform PASS11 (e.g., two substrate platform PASS11) may be provided above and below. Also, multiple substrate platform PASS12 (e.g., two substrate platform PASS12) may be provided above and below. In this case, the substrate platform PASS11 and PASS12 may be used as buffer sections for temporarily placing the substrate W.

[0071] In the first embodiment, substrates W to be transported from the indexer block 11 to the first processing block 12 are placed on the substrate placement parts PASS1 and PASS3, and substrates W to be transported from the first processing block 12 to the indexer block 11 are placed on the substrate placement parts PASS2 and PASS4. The transport mechanism 115 can use a hand 116 to transfer the substrates W to and from the carrier 113 and the substrate placement parts PASS1 to PASS4.

[0072] Further, on the substrate rest parts PASS5, PASS6, PASS7, and PASS8, a substrate W to be transported from the first processing block 12 to the second processing block 13 is placed, or a substrate W to be transported from the second processing block 13 to the first processing block 12 is placed. In the first embodiment, each of the substrate rest parts PASS6 and PASS8 has a function of cooling the substrate W (e.g., a cooling plate). Thus, the substrate rest parts PASS6 and PASS8 function as cooling processing units. Hereinafter, the substrate rest part PASS6 may be referred to as a processing unit PASS6 or a cooling processing unit PASS6. Further, the substrate rest part PASS8 may be referred to as a processing unit PASS8 or a cooling processing unit PASS8.

[0073] The placement / buffer section P-BF1 receives a substrate W to be transported from the upper transport chamber 135 of the second processing block 13 to the cleaning / drying processing block 14A, and the substrate placement section PASS9 receives a substrate W to be transported from the cleaning / drying processing block 14A to the upper transport chamber 135. The placement / buffer section P-BF2 receives a substrate W to be transported from the lower transport chamber 136 of the second processing block 13 to the cleaning / drying processing block 14A, and the substrate placement section PASS10 receives a substrate W to be transported from the cleaning / drying processing block 14A to the lower transport chamber 136.

[0074] The placement and cooling section P-CP holds the substrate W to be transported from the cleaning and drying processing block 14A to the load-unloading block 14B, the substrate placement section PASS11 holds the substrate W to be transported from the cleaning and drying processing block 14A to the load-unloading block 14B, and the substrate placement section PASS12 holds the substrate W to be transported from the load-unloading block 14B to the cleaning and drying processing block 14A.

[0075] In the upper transfer chamber 125, an air supply unit 43 is provided above the transfer mechanism 127, and in the lower transfer chamber 126, an air supply unit 43 is provided above the transfer mechanism 128. In the upper transfer chamber 135, an air supply unit 43 is provided above the transfer mechanism 137, and in the lower transfer chamber 136, an air supply unit 43 is provided above the transfer mechanism 138. The air supply unit 43 is supplied with air whose temperature and humidity are adjusted by a temperature control device (not shown).

[0076] Also, in the upper transfer chamber 125, an exhaust unit 44 for exhausting the upper transfer chamber 125 is provided below the transfer mechanism 127, and in the lower transfer chamber 126, an exhaust unit 44 for exhausting the lower transfer chamber 126 is provided below the transfer mechanism 128.

[0077] Similarly, in the upper transfer chamber 135, an exhaust unit 44 for exhausting the upper transfer chamber 135 is provided below the transfer mechanism 137, and in the lower transfer chamber 136, an exhaust unit 44 for exhausting the lower transfer chamber 136 is provided below the transfer mechanism 138.

[0078] As a result, the atmospheres of the upper transfer chambers 125 and 135 and the lower transfer chambers 126 and 136 are maintained in an appropriate temperature, humidity, and clean state.

[0079] An air supply unit 45 is provided at the upper part inside the transfer section 163 of the cleaning and drying processing block 14A. An air supply unit 46 is provided at the upper part inside the loading and unloading block 14B. The air supply units 45 and 46 are supplied with air whose temperature and humidity are adjusted by a temperature control device (not shown). As a result, the atmospheres inside the cleaning and drying processing block 14A and the loading and unloading block 14B are maintained in an appropriate temperature, humidity, and clean state.

[0080] Continuing to refer to FIG. 5, the transport mechanism 127 will be described. The transport mechanism 127 includes long guide rails 311 and 312. The guide rail 311 is fixed to the transport unit 112 side so as to extend in the vertical direction within the upper transport chamber 125. The guide rail 312 is fixed to the upper transport chamber 135 side so as to extend in the vertical direction within the upper transport chamber 125.

[0081] A long guide rail 313 is provided between the guide rail 311 and the guide rail 312. The guide rail 313 is attached to the guide rails 311 and 312 so as to be vertically movable. A moving member 314 is attached to the guide rail 313. The moving member 314 is provided so as to be movable in the longitudinal direction of the guide rail 313.

[0082] A long rotating member 315 is rotatably provided on the upper surface of the moving member 314. A hand H1 and a hand H2 for holding the substrate W are attached to the rotating member 315. The hands H1 and H2 are provided so as to be movable in the longitudinal direction of the rotating member 315.

[0083] With the above configuration, the transport mechanism 127 can freely move in the X direction and the Z direction within the upper transport chamber 125. Further, the transport mechanism 127 can transfer the substrate W to and from the coating processing chambers 24 and 23 (FIG. 2), the substrate placement portions PASS1, PASS2, PASS5, and PASS6 (FIG. 5), and the upper heat treatment unit 301 (FIG. 3) using the hands H1 and H2.

[0084] As shown in FIG. 5, the transport mechanisms 128, 137, and 138 have the same configuration as the transport mechanism 127.

[0085] Therefore, the transport mechanism 128 can freely move in the X direction and the Z direction within the lower transport chamber 126. Further, the transport mechanism 128 can transfer the substrate W to and from the coating processing chambers 22 and 21 (FIG. 2), the substrate placement portions PASS3, PASS4, PASS7, and PASS8 (FIG. 5), and the lower heat treatment unit 302 (FIG. 3) using the hands H1 and H2.

[0086] Further, the transfer mechanism 137 can move freely in the X and Z directions within the upper transfer chamber 135. Also, the transfer mechanism 137 can transfer the substrate W to and from the development processing chambers 34, 33 (Fig. 2), the substrate placement units PASS5, PASS6 (Fig. 5), the placement and buffer unit P-BF1 (Fig. 5), the substrate placement unit PASS9 (Fig. 5), and the upper heat treatment unit 303 (Fig. 3) using the hands H1, H2.

[0087] Further, the transfer mechanism 138 can move freely in the X and Z directions within the lower transfer chamber 136. Also, the transfer mechanism 138 can transfer the substrate W to and from the development processing chambers 32, 31 (Fig. 2), the substrate placement units PASS7, PASS8 (Fig. 5), the placement and buffer unit P-BF2 (Fig. 5), the substrate placement unit PASS10 (Fig. 5), and the lower heat treatment unit 304 (Fig. 3) using the hands H1, H2.

[0088] Hereinafter, the transfer mechanisms 115, 127, 128, 137, 138, 141, 142, 146 may be collectively referred to as the transfer mechanism 210.

[0089] Next, with reference to Figs. 6 and 7, the processing of the substrate W transported from the carrier 113 of the substrate processing apparatus 100 to the exposure apparatus 15, and the processing of the substrate W transported from the exposure apparatus 15 to the carrier 113 of the substrate processing apparatus 100 will be described.

[0090] Fig. 6 is a flowchart showing the processing of a single substrate W in the forward path from the substrate processing apparatus 100 to the exposure apparatus 15. Fig. 7 is a flowchart showing the processing of a single substrate W in the return path from the exposure apparatus 15 to the substrate processing apparatus 100.

[0091] In order to perform the adhesion strengthening process of step S1 shown in Fig. 6, the transfer mechanisms 115, 128 in Fig. 5 carry out the substrate W from the carrier 113 and carry it into the processing unit PAHP in Fig. 3 (for example, the processing unit PAHP

[11] ).

[0092] Then, in step S1, the processing unit PAHP (e.g., processing unit PAHP

[11] ) performs an adhesion strengthening process on the substrate W. That is, the processing unit PAHP applies an adhesion strengthening agent to the substrate W and heats the substrate W. Then, the processing unit PAHP cools the substrate W.

[0093] Next, in step S2, the processing unit AR in FIG. 2 (e.g., processing unit AR

[11] ) performs an antireflection film forming process on the substrate W. That is, the processing unit AR applies a processing liquid for the antireflection film to the substrate W on which the adhesion strengthening process has been performed to form an antireflection film on the substrate W.

[0094] Next, in step S3, the processing unit PHP in FIG. 3 (e.g., processing unit PHP

[15] ) performs a first heat treatment on the substrate W. That is, the processing unit PHP heats the substrate W on which the antireflection film has been formed.

[0095] Next, in step S4, the processing unit CP (e.g., processing unit CP

[11] ) performs a first cooling process on the substrate W. That is, the processing unit CP cools the substrate W after the first heat treatment.

[0096] Next, in step S5, the processing unit RT in FIG. 2 (e.g., processing unit RT

[11] ) performs a resist film forming process on the substrate W. That is, the processing unit RT applies a processing liquid for the resist film to the substrate W after the first cooling process to form a resist film on the substrate W. The resist film is formed on the antireflection film.

[0097] Next, in step S6, the processing unit PHP in FIG. 3 (e.g., processing unit PHP

[19] ) performs a second heat treatment on the substrate W. That is, the processing unit PHP heats the substrate W on which the resist film has been formed.

[0098] Next, in step S7, the processing unit PASS8 in FIG. 5 performs a second cooling process on the substrate W. That is, the processing unit PASS8 cools the substrate W after the second heat treatment. Note that in step S7, the processing unit CP (for example, the processing unit CP

[13] ) may perform the second cooling process on the substrate W.

[0099] Next, in step S8, the processing unit EEW in FIG. 3 (for example, the processing unit EEW[1]) performs an edge exposure process on the substrate W. That is, the processing unit EEW performs an exposure process on the peripheral portion of the substrate W after the second cooling process.

[0100] Next, in step S9, the processing unit P-CP in FIG. 5 cools the substrate W. That is, the processing unit P-CP cools the substrate W after the edge exposure process.

[0101] Next, in step S10, the exposure apparatus 15 in FIG. 1 performs an exposure process on the substrate W. That is, the exposure apparatus 15 exposes the substrate W after the cooling process, that is, the substrate W on which the resist film is formed.

[0102] Next, as shown in FIG. 7, in step S11, the processing unit PHP in FIG. 3 (for example, the processing unit PHP

[31] ) performs a third heat treatment on the substrate W. That is, the processing unit PHP heats the substrate W after the exposure process.

[0103] Next, in step S12, the processing unit CP (for example, the processing unit CP

[14] ) performs a third cooling process on the substrate W. That is, the processing unit PHP cools the substrate W after the third heat treatment.

[0104] Next, in step S13, the processing unit DV in FIG. 2 (for example, the processing unit DV

[15] ) performs a development process on the substrate W. That is, the processing unit DV supplies a developing solution to the substrate W after the third cooling and develops the substrate W.

[0105] Next, in step S14, the processing unit PHP in FIG. 3 (for example, the processing unit PHP

[27] ) performs a fourth heat treatment on the substrate W. That is, the processing unit PHP heats the substrate W after the development process.

[0106] Next, in step S15, the processing unit CP (for example, the processing unit CP

[15] ) performs a fourth cooling treatment on the substrate W. That is, the processing unit CP cools the substrate W after the fourth heat treatment.

[0107] Then, the transfer mechanisms 138, 128, and 115 in FIG. 5 unload the substrate W from the processing unit CP that has performed the fourth cooling treatment in step S15 and load the substrate W into the carrier 113.

[0108] Note that the processing unit PHP that performs the first heat treatment in step S3, the processing unit PHP that performs the second heat treatment in step S6, the processing unit PHP that performs the third heat treatment in step S11, and the processing unit PHP that performs the fourth heat treatment in step S14 are different from each other.

[0109] Also, the processing unit CP that performs the first cooling treatment in step S4, the processing unit PASS8 that performs the second cooling treatment in step S7, the processing unit CP that performs the third cooling treatment in step S12, and the processing unit CP that performs the fourth cooling treatment in step S15 are different from each other.

[0110] Here, among steps S1 to S15, a series of steps S1 to S9, S11 to S15 excluding step S10 are described as a series of steps SQ. In Embodiment 1, the substrate processing apparatus 100 executes a plurality of series of steps SQ in parallel for each of the plurality of substrates W. Each of steps S1 to S9, S11 to S15 corresponds to an example of a "processing step".

[0111] Specifically, the series of steps SQ includes a plurality of steps S1 to S9, S11 to S15 that are sequentially executed. That is, the series of steps SQ includes a plurality of steps S1 to S9, S11 to S15 with different processing contents.

[0112] Next, referring to FIGS. 6 to 8, the substrate processing apparatus 100 will be described. FIG. 8 is a block diagram showing the control device CM and a plurality of processing units 220 controlled by the control device CM.

[0113] As shown in FIG. 8, the control device CM controls a plurality of processing units 220. And, as shown in FIGS. 6 to 8, the plurality of processing units 220 execute a plurality of series of processes SQ in parallel.

[0114] Specifically, the plurality of processing units 220 include two or more processing units 220 that perform the same processing content on the substrate W among the plurality of series of processes SQ. "The processing content is the same" means that the processing functions and processing conditions are the same. For example, one of the processes S1 to S9, S11 to S15 shown in FIGS. 6 and 7 is described as "process SP". In this case, the process SP is executed in parallel by two or more processing units 220. In this case, the processing content of two or more processing units 220 that execute the same process SP in parallel is the same. For example, the plurality of processing units 220 include two or more processing units 220 that respectively execute two or more processes S1 included in the plurality of series of processes SQ.

[0115] As shown in FIG. 8, the control device CM controls each transfer mechanism 210. And each transfer mechanism 210 carries the substrate W into and out of each processing unit 220. And the plurality of processing units 220 each process a plurality of substrates W.

[0116] The substrate processing apparatus 100 may include one or more measurement units 200. In this case, for example, the measurement unit 200 is arranged in the transfer unit 112, the transfer unit 122 (upper transfer chamber 125, lower transfer chamber 126), the transfer unit 132 (upper transfer chamber 135, lower transfer chamber 136), the transfer unit 163, the loading / unloading block 14B, the coating processing unit 121 (coating processing chambers 21 to 24), the developing processing unit 131 (developing processing chambers 31 to 34), the processing unit PAHP, the processing unit PHP, the processing unit CP, or the processing unit EEW.

[0117] Further, the single or plural measurement units 200 may not form part of the substrate processing apparatus 100. That is, the single or plural measurement units 200 may be arranged outside the substrate processing apparatus 100.

[0118] The measurement unit 200 measures the state of the substrate W after being processed by the processing unit 220. For example, the measurement unit 200 measures the state at a plurality of measurement points on the surface of the substrate W after being processed by the processing unit 220. The measurement unit 200 transmits measurement data ME2 indicating the measurement result of the state of the substrate W to the control device CM. For example, the measurement data ME2 includes a plurality of measurement values indicating the state of each of the plurality of measurement points on the surface of the substrate W. The measurement unit 200 includes, for example, a sensor that measures the state of the substrate W and a transmitter that transmits the measurement data ME2 to the control device CM. According to Embodiment 1, by providing the substrate processing apparatus 100 with the measurement unit 200, the measurement data ME2 can be easily acquired.

[0119] For example, one or more measurement units 200 measure the state of the substrate W after being processed by the processing unit 220 for each of one or more processes selected from the processes S1 to S9 and S11 to S15 shown in FIGS. 6 and 7.

[0120] For example, one of the plurality of measurement units 200 measures the contact angle of the processing liquid on the surface of the substrate W and transmits measurement data ME2 indicating the contact angle to the control device CM. For example, the measurement unit 200 measures the contact angle of the processing liquid at a plurality of measurement points on the surface of the substrate W. The measurement unit 200 measures the contact angle by, for example, the θ / 2 method, the tangent method, or the droplet method. For example, the measurement unit 200 measures the contact angle of the processing liquid on the surface of the substrate W after the adhesion strengthening process in step S1 of FIG. 6.

[0121] For example, one of the plurality of measurement units 200 measures the film thickness of the film formed on the substrate W, and transmits measurement data ME2 indicating the film thickness to the control device CM. For example, the measurement unit 200 measures the film thickness at a plurality of measurement points on the surface of the substrate W. The measurement unit 200 measures the film thickness, for example, by spectroscopic interference. For example, the measurement unit 200 measures the film thickness of the resist film on the substrate W after the resist film formation process in step S5 of FIG. 6.

[0122] For example, one of the plurality of measurement units 200 measures the temperature during the heat treatment of the substrate W, and transmits measurement data ME2 indicating the temperature to the control device CM. For example, the measurement unit 200 measures the temperature during the heat treatment at a plurality of measurement points on the substrate W. The measurement unit 200 measures the temperature, for example, using the substrate W with a built-in temperature sensor. For example, the measurement unit 200 measures the temperature of the substrate W during the third heat treatment (during the heat treatment after exposure) in step S11 of FIG. 7.

[0123] For example, one of the plurality of measurement units 200 measures the line width (CD: Critical Dimension) of the pattern on the surface of the substrate W, and transmits measurement data ME2 indicating the line width to the control device CM. For example, the measurement unit 200 measures the line width of the pattern at a plurality of measurement points on the surface of the substrate W. The "line width of the pattern" measured by the measurement unit 200 is, for example, the "line width of the resist pattern". The measurement unit 200 is, for example, a CD-SEM or a CD-AFM. For example, the measurement unit 200 measures the line width of the resist pattern on the surface of the substrate W after the development process in step S13 of FIG. 7.

[0124] For example, one of the plurality of measurement units 200 measures the number of particles on the surface of the substrate W, and transmits measurement data ME2 indicating the number of particles to the control device CM. For example, the measurement unit 200 measures the number of particles at a plurality of measurement points on the surface of the substrate W.

[0125] For example, one of the plurality of measurement units 200 measures the number of collapses of the pattern on the surface of the substrate W, and transmits measurement data ME2 indicating the number of collapses to the control device CM. For example, the measurement unit 200 measures the number of collapses of the pattern at a plurality of measurement points on the surface of the substrate W.

[0126] For example, one of the plurality of measurement units 200 measures the cut width of the edge of the substrate W, and transmits measurement data ME2 indicating the cut width to the control device CM. For example, the measurement unit 200 measures the cut width of the edge of the substrate W at a plurality of measurement points along the circumferential direction.

[0127] The control device CM includes a control unit CNT, a storage unit MEM, an input unit IN, a display unit DP, and a communication unit TR.

[0128] The control unit CNT controls the plurality of processing units 220 and each transfer mechanism 210. Specifically, the control unit CNT controls the one or more processing units 220 and each transfer mechanism 210 so that each of the processing target substrates Wx is processed by one or more processing units 220 selected based on the processing results of the plurality of substrates Wp by each of the plurality of processing units 220. Therefore, according to Embodiment 1, even if the processing characteristics by the plurality of processing units 220 vary, a processing unit 220 with good processing results can be selected and used. As a result, the uniformity of processing among the plurality of processing target substrates Wx can be improved.

[0129] "The processing results of the plurality of substrates Wp by each of the plurality of processing units 220" indicates the processing results of the substrate Wp in the past before processing the processing target substrate Wx. The processing target substrate Wx is the substrate W to be processed in a series of processes SQ. Each of the processes S1 to S9, S11 to S15 included in the series of processes SQ corresponds to an example of "a process of processing a processing target substrate".

[0130] In this specification, when there is no need to distinguish between the substrate Wp that has been processed in the past and the substrate Wx to be processed, the substrate Wp and the substrate Wx to be processed are simply described as "substrate W".

[0131] The control unit CNT includes processors such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The storage unit MEM includes a storage device and stores data and computer programs. The storage unit MEM includes, for example, a main storage device such as a semiconductor memory, and an auxiliary storage device such as a semiconductor memory and a hard disk drive. The storage unit MEM may include a removable medium such as an optical disk. The storage unit MEM is, for example, a non-transitory computer-readable storage medium.

[0132] The processor of the control unit CNT executes a computer program stored in the storage device of the storage unit MEM to control the storage unit MEM, the input unit IN, the display unit DP, the communication unit TR, each measurement unit 200, each transfer mechanism 210, and each processing unit 220.

[0133] The communication unit TR is connected to a network and communicates with an external device. The network includes, for example, the Internet, a LAN (Local Area Network), a public telephone network, and a short-range wireless network. The communication unit TR is a communication device and is, for example, a network interface controller.

[0134] The input unit IN is an input device for inputting various information to the control unit CNT. For example, the input unit IN is a keyboard and a pointing device, or a touch panel.

[0135] The display unit DP displays an image. The display unit DP is, for example, a liquid crystal display or an organic electroluminescence display.

[0136] Specifically, the control unit CNT functions as a preprocessing unit CN1, an acquisition unit CN2, a first selection unit CN3, an analysis unit CN4, an adjustment unit CN5, a second selection unit CN6, a substrate path determination unit CN7, and a substrate processing control unit CN8 by executing a control program ME1. That is, the control unit CNT includes a preprocessing unit CN1, an acquisition unit CN2, a first selection unit CN3, an analysis unit CN4, an adjustment unit CN5, a second selection unit CN6, a substrate path determination unit CN7, and a substrate processing control unit CN8. The first selection unit CN3 corresponds to an example of the "selection unit". The storage unit MEM stores the control program ME1.

[0137] The acquisition unit CN2 acquires measurement data ME2 from each measurement unit 200. When the measurement unit 200 is arranged outside the substrate processing apparatus 100, the acquisition unit CN2 acquires the measurement data ME2 from the measurement unit 200 via the communication unit TR.

[0138] The storage unit MEM stores a plurality of measurement data ME2 respectively acquired from a plurality of measurement units 200.

[0139] The preprocessing unit CN1 processes the measurement data ME2 to calculate processing result information ME3. The processing result information ME3 is generated for each substrate W and indicates the processing result of the substrate W by the processing unit 220. The preprocessing unit CN1 processes each measurement data ME2 for each processing unit 220 to calculate the processing result information ME3. The storage unit MEM stores the processing result information ME3. Hereinafter, the processing by the preprocessing unit CN1 may be described as "preprocessing".

[0140] For example, the preprocessing unit CN1 executes statistical processing on a plurality of measurement values indicating the states of a plurality of measurement points on the surface of the substrate W, and calculates a numerical value indicating the state of the substrate W for each substrate W. The "numerical value indicating the state of the substrate W" obtained by the statistical processing is the processing result information ME3. In this case, for example, the preprocessing unit CN1 calculates the average value of a plurality of measurement values for the substrate W. The "average value" is an example of the "numerical value indicating the state of the substrate W" obtained by the statistical processing and is the processing result information ME3.

[0141] Further, for example, the preprocessing unit CN1 calculates a numerical value indicating the variation in a plurality of measurement values for the substrate W. The "numerical value indicating the variation" is an example of the "numerical value indicating the state of the substrate W" by statistical processing, and is the processing result information ME3. The numerical value indicating the variation is, for example, the difference value between the maximum value and the minimum value of the plurality of measurement values, the standard deviation σ of the plurality of measurement values, a numerical value based on the standard deviation σ, the variance σ of the plurality of measurement values 2 , or a numerical value based on the variance σ 2 is a numerical value based on. The numerical value based on the standard deviation σ is, for example, the 3σ value.

[0142] Furthermore, for example, the preprocessing unit CN1 normalizes a plurality of measurement values for the substrate W to make the plurality of measurement values dimensionless. The "plurality of normalized measurement values" is an example of the "numerical value indicating the state of the substrate W" by statistical processing, and is the processing result information ME3.

[0143] The preprocessing unit CN1 can calculate a plurality of types of processing result information ME3 from the same measurement data ME2. The plurality of types of processing result information ME3 are, for example, the average value, the difference value between the maximum value and the minimum value, the standard deviation σ, a numerical value based on the standard deviation σ, the variance σ 2 , and 2 are two or more numerical values among the numerical values based on.

[0144] Also, the measurement data ME2 itself may be the processing result information ME3. For example, the processing result information ME3 is the map data indicated by the measurement data ME2. The map data indicates the distribution of a plurality of measurement values indicating the respective states of a plurality of measurement points on the surface of the substrate W, or the distribution of a plurality of measurement values indicating the respective states of a plurality of measurement points of the substrate W.

[0145] For example, the processing result information ME3 includes the contact angle θ with respect to the processing liquid on the surface of the substrate W, a numerical value based on the contact angle θ, the film thickness t of the film formed on the substrate W, a numerical value based on the film thickness t, and the heat treatment on the surface of the substrate W ChinaThe temperature T, a numerical value based on the temperature T, the line width W1 of the pattern on the surface of the substrate W, a numerical value based on the line width W1, the number of particles NM1 on the surface of the substrate W, a numerical value based on the number of particles NM1, the number of collapses NM2 of the pattern on the surface of the substrate W, a numerical value based on the number of collapses NM2, and the cut width W2 of the edge of the substrate W are shown. Therefore, according to Embodiment 1, the processing result information ME3 can accurately indicate the state of the surface of the substrate W.

[0146] Specifically, the processing result information ME3 is, for example, contact angle map data, film thickness map data, temperature map data, pattern line width map data, particle map data, or collapse map data. The contact angle map data indicates the distribution of the contact angle θ with respect to the processing liquid on the surface of the substrate W. The film thickness map data indicates the distribution of the film thickness t of the substrate W. The temperature map data indicates the distribution of the temperature T of the substrate W. The pattern line width map data indicates the distribution of the line width W1 of the pattern on the surface of the substrate W. The particle map data indicates the distribution of the number of particles NM1 on the surface of the substrate W. The collapse map data indicates the distribution of the number of collapses NM2 of the pattern on the surface of the substrate W.

[0147] The "numerical value based on the contact angle θ" as the processing result information ME3 is, for example, a numerical value or a normalized value obtained by performing statistical processing on a plurality of contact angles θ at each of a plurality of measurement points on the surface of the substrate W. The "numerical value based on the film thickness t" as the processing result information ME3 is, for example, a numerical value or a normalized value obtained by performing statistical processing on a plurality of film thicknesses t at each of a plurality of measurement points on the surface of the substrate W. The "numerical value based on the temperature T" as the processing result information ME3 is, for example, a numerical value or a normalized value obtained by performing statistical processing on a plurality of temperatures T at each of a plurality of measurement points on the surface of the substrate W. The "numerical value based on the line width W1" as the processing result information ME3 is, for example, a numerical value or a normalized value obtained by performing statistical processing on a plurality of line widths W1 at each of a plurality of measurement points on the surface of the substrate W. The "numerical value based on the particle number NM1" as the processing result information ME3 is, for example, a numerical value or a normalized value obtained by performing statistical processing on the particle number NM1 at each measurement point on the surface of the substrate W. The "numerical value based on the collapse number NM2" as the processing result information ME3 is, for example, a numerical value or a normalized value obtained by performing statistical processing on the collapse number NM2 at each measurement point on the surface of the substrate W. In these cases, the "numerical value" is, for example, an average value or a numerical value indicating variation.

[0148] The processing result information ME3 may be stored in an external device of the substrate processing apparatus 100. In this case, the acquisition unit CN2 acquires, via the communication unit TR and the network, the processing result information ME3 indicating the processing result of the substrate W by each of the plurality of processing units 220 from the external device, and stores the processing result information ME3 in the storage unit MEM. The external device is, for example, a server or a storage device.

[0149] Further, the acquisition unit CN2 acquires the processing result information ME3 from the storage unit MEM, and causes the first selection unit CN3 to select one or more processing units 220 to be used for processing each of the substrates Wx to be processed.

[0150] The first selection unit CN3 has at least one analysis algorithm. In Embodiment 1, the first selection unit CN3 has a plurality of analysis algorithms. The analysis algorithm is an algorithm for analyzing the processing result information ME3 when selecting one or more processing units 220 to be used for processing each of the substrates Wx to be processed. The analysis algorithm is prepared, for example, for each type of processing result information ME3. For example, the analysis algorithm indicates the type of processing result information ME3 to be analyzed and the analysis method of the processing result information ME3. The analysis method includes the selection conditions of the processing unit 220. The analysis algorithm is incorporated into the control program ME1, for example.

[0151] Based on a plurality of pieces of processing result information ME3 respectively indicating the processing results of a plurality of substrates Wp by a plurality of processing units 220, the first selection unit CN3 selects one or more processing units 220 to be used for processing each of the substrates Wx to be processed from among the plurality of processing units 220, and generates selection result information ME4 indicating the selection result. Therefore, according to Embodiment 1, a processing unit 220 with good processing results can be selected, and the quality of the substrate Wx to be processed after processing can be improved. The control device CM can be regarded as a "selection device".

[0152] For example, the selection result information ME4 indicates one or more processing units 220 to be used for processing each of the substrates Wx to be processed among the plurality of processing units 220.

[0153] Based on a plurality of pieces of processing result information ME3 respectively indicating the processing results of a plurality of substrates Wp by a plurality of processing units 220, it is preferable that the first selection unit CN3 selects two or more processing units 220 to be used for processing each of the substrates Wx to be processed from among the plurality of processing units 220. This is because the throughput of the processing of the substrate W can be improved.

[0154] Further, the first selection unit CN3 sets the processing units 220 that have not been selected among the plurality of processing units 220 as the processing units 220 not to be used. In other words, the first selection unit CN3 determines the processing units 220 not to be used from among the plurality of processing units 220 based on a plurality of pieces of processing result information ME3 respectively corresponding to the plurality of processing units 220. In this case, the selection result information ME4 includes not only information indicating one or more processing units 220 used to process each of the substrates Wx to be processed, but also information indicating the processing units 220 not to be used. According to Embodiment 1, by determining the processing units 220 not to be used, it is possible to suppress a decrease in the uniformity of processing among a plurality of substrates W caused by the processing units 220 with poor processing characteristics.

[0155] The first selection unit CN3 may select, with a priority order of use, one or more processing units 220 used to process each of the substrates Wx to be processed from among the plurality of processing units 220 based on a plurality of pieces of processing result information ME3 respectively indicating the processing results of a plurality of substrates Wp by the plurality of processing units 220. Therefore, according to Embodiment 1, by increasing the usage frequency of the processing units 220 with a higher priority order, the quality of the processed substrate Wx can be further improved.

[0156] For example, the first selection unit CN3 assigns a higher priority order to the processing unit 220 as the quality of the processed substrate Wp indicated by the processing result information ME3 is higher.

[0157] For example, the first selection unit CN3 selects all or some of the processing units 220 with a priority order of use based on a plurality of pieces of processing result information ME3 respectively corresponding to the plurality of processing units 220. In this case, the selection result information ME4 includes information indicating the priority order of use. Even in this case, the selection result information ME4 may include information indicating the processing units 220 not to be used.

[0158] For example, the first selection unit CN3 compares the processing result information ME3 with a threshold value, and based on the comparison result, selects one or more processing units 220 to be used for processing each of the substrates Wx to be processed. The "threshold value" is, for example, a specification value required for the substrate processing apparatus 100.

[0159] For example, for the processing result information ME3 (for example, a value indicating variation) indicating that the smaller the numerical value, the better the quality, the first selection unit CN3 increases the priority of the processing unit 220 corresponding to the processing result information ME3 as the processing result information ME3 indicates a smaller numerical value. Also, for example, for the processing result information ME3 indicating that the larger the numerical value, the better the quality, the first selection unit CN3 increases the priority of the processing unit 220 corresponding to the processing result information ME3 as the processing result information ME3 indicates a larger numerical value.

[0160] For example, the first selection unit CN3 determines whether the numerical value (for example, the average value) indicated by the processing result information ME3 is within a predetermined range, and based on the determination result, selects one or more processing units 220 to be used for processing each of the substrates Wx to be processed. The predetermined range includes a reference value. In this case, for example, when the numerical value indicated by the processing result information ME3 is within the predetermined range, the first selection unit CN3 selects the processing unit 220 corresponding to the processing result information ME3 as a target to be used, and when the numerical value indicated by the processing result information ME3 is outside the predetermined range, sets the processing unit 220 corresponding to the processing result information ME3 as a non-use target. Also, for example, the first selection unit CN3 increases the priority of the processing unit 220 corresponding to the processing result information ME3 as the numerical value indicated by the processing result information ME3 is closer to the reference value. The "predetermined range" is, for example, the range indicated by the specifications required for the substrate processing apparatus 100. The "reference value" is, for example, the median value of the predetermined range.

[0161] The first selection unit CN3 generates selection result information ME4 for each analysis algorithm based on each processing result information ME3 prepared for each analysis algorithm. The storage unit MEM stores each selection result information ME4.

[0162] The first selection unit CN3 sets the processing target substrate Wx to be processed by the processing unit 220 with a priority lower than the predetermined priority as the target of quality inspection based on the selection result information ME4. Therefore, according to Embodiment 1, the quality inspection time can be shortened as compared with the case where all the processing target substrates Wx are set as the targets of quality inspection. In addition, by setting only the processing target substrate Wx processed by the processing unit 220 with a relatively low priority as the target of quality inspection, quality inspection can be performed efficiently.

[0163] The predetermined priority is the priority of use. For example, it may be a priority one higher than the lowest priority, or may be a priority N ranks higher than the lowest priority. N represents an integer of 2 or more.

[0164] Specifically, the first selection unit CN3 determines, based on the selection result information ME4, the processing unit 220 from among the plurality of processing units 220 for which the processed substrate W is to be the target of quality inspection.

[0165] For example, the first selection unit CN3 generates inspection target information ME5 indicating the processing unit 220 with a priority lower than the predetermined priority based on the selection result information ME4. That is, the inspection target information ME5 indicates the processing unit 220 for which the processed substrate W is to be the target of quality inspection.

[0166] The first selection unit CN3 may determine, by assigning a quality inspection priority, the processing unit 220 from among the plurality of processing units 220 for which the processed substrate W is to be the target of quality inspection. In this case, the first selection unit CN3 increases the quality inspection priority as the use priority is lower. In this case, for example, the inspection target information ME5 includes information indicating the quality inspection priority.

[0167] The plurality of processing units 220 includes a predetermined number of processing units 220. The predetermined number is a number of 2 or more. And, the first selection unit CN3 may select one or more processing units 220 to be used for processing each of the substrates to be processed Wx from among the predetermined number of processing units 220 based on the predetermined number of pieces of processing result information ME3 respectively indicating the processing results of the predetermined number of substrates Wp by the predetermined number of processing units 220. In this case, the second selection unit CN6 selects whether to use one or more processing units 220 selected from the predetermined number of processing units 220, or to use all of the predetermined number of processing units 220.

[0168] That is, when it is selected to use one or more processing units 220 selected from the predetermined number of processing units 220, the quality of the processed substrate W (processing quality) is prioritized. On the other hand, when it is selected to use all of the predetermined number of processing units 220, the throughput (processing speed) of the processing of the substrate W is prioritized. Therefore, according to Embodiment 1, it is possible to select whether to prioritize the quality of the processed substrate W or to prioritize the throughput of the processing of the substrate W according to the user's request. As a result, the convenience for the user can be improved.

[0169] The storage unit MEM stores priority information ME6 in the case of prioritizing the throughput of the processing of the substrate W. The priority information ME6 indicates the priority of use for all of the predetermined number of processing units 220. The priority information ME6 indicates, for example, consecutive numbers assigned to all of the predetermined number of processing units 220.

[0170] Next, with reference to FIGS. 9 and 10, the substrate processing method according to Embodiment 1 will be described. FIG. 9 is a flowchart showing the substrate processing method according to Embodiment 1. The substrate processing method is executed by the substrate processing apparatus 100. Specifically, the control unit CNT shown in FIG. 8 executes the substrate processing method. As shown in FIG. 9, the substrate processing method includes steps S31 to S36.

[0171] In step S31, the control unit CNT selects one or more processing units 220 to be used for processing each of the substrates Wx to be processed from among a predetermined number of processing units 220, and generates selection result information ME4 indicating the selection result. In Embodiment 1, the predetermined number of processing units 220 are two or more processing units 220 having the same processing content.

[0172] Next, in step S32, the second selection unit CN6 of the control unit CNT selects whether to perform throughput-priority processing or quality-priority processing of the processed substrate W for each substrate W.

[0173] If it is selected to perform throughput-priority processing in step S32, the process proceeds to step S33.

[0174] In step S33, the substrate path determination unit CN7 of the control unit CNT determines a plurality of transfer paths for each of the plurality of substrates W so as to use all of the predetermined number of processing units 220 in parallel. In this case, the substrate path determination unit CN7 determines each transfer path so that the higher the priority of the processing unit 220, the higher the usage frequency, based on the usage priority indicated by the priority information ME6, for example. Specifically, the substrate path determination unit CN7 determines each transfer path so as to use not only the predetermined number of processing units 220 but also two or more other processing units 220 in parallel. Each transfer path includes a plurality of processing units 220 that respectively execute steps S1 to S9, S11 to S15 shown in FIGS. 6 and 7.

[0175] Next, in step S34, the substrate processing control unit CN8 of the control unit CNT controls each transfer mechanism 210 and each processing unit 220 to transfer and process each substrate W according to each transfer path determined in step S33. As a result, all of the predetermined number of processing units 220 process the substrate W in parallel, and two or more other processing units 220 process the substrate W in parallel. When the processing of the desired number of substrates W is completed, the process ends.

[0176] On the other hand, when it is selected to perform quality-priority processing in step S32, the process proceeds to step S35.

[0177] In step S35, based on the selection result information ME4, the substrate path determination unit CN7 determines the respective transport paths of a plurality of substrates W so as to use in parallel each processing unit 220 selected from a predetermined number of processing units 220. In this case, for example, based on the priority of use indicated by the selection result information ME4, the substrate path determination unit CN7 determines each transport path such that the higher the priority of the processing unit 220, the higher the usage frequency. Specifically, the substrate path determination unit CN7 determines each transport path so as to use in parallel not only each processing unit 220 selected from a predetermined number of processing units 220 but also two or more other processing units 220. Each transport path includes a plurality of processing units 220 that respectively execute steps S1 to S9 and S11 to S15 shown in FIGS. 6 and 7.

[0178] Next, in step S36, the substrate processing control unit CN8 controls each transport mechanism 210 and each processing unit 220 so as to transport and process each substrate W according to each transport path determined in step S35. As a result, each processing unit 220 selected from a predetermined number of processing units 220 processes the substrate W in parallel, and two or more other processing units 220 process the substrate W in parallel. When the processing of the desired number of substrates W is completed, the process ends.

[0179] FIG. 10 is a flowchart showing the processing of step S31 shown in FIG. 9. As shown in FIG. 10, the processing of step S31 includes steps S51 to S61. The processing of step S31 corresponds to an example of the "selection method".

[0180] In step S51, the preprocessing unit CN1 of the control unit CNT processes a plurality of measurement data ME2 to generate a plurality of processing result information ME3.

[0181] Next, in step S52, the acquisition unit CN2 acquires two or more pieces of processing result information ME3 respectively indicating the processing results of two or more substrates Wp by two or more processing units 220 with the same processing content.

[0182] Next, in step S53, based on two or more pieces of processing result information ME3 respectively indicating the processing results of two or more substrates Wp by two or more processing units 220 with the same processing content, the first selection unit CN3 selects one or more processing units 220 to be used for processing each of the substrates Wx to be processed from among two or more processing units 220 (specifically, a predetermined number of processing units 220). Therefore, according to Embodiment 1, a processing unit 220 with good processing results can be selected from among two or more processing units 220 with the same processing content, and the quality of the substrate Wx to be processed after processing can be improved.

[0183] Specifically, the first selection unit CN3 analyzes the processing result information ME3 by an analysis algorithm, selects one or more processing units 220 to be used for processing each of the substrates Wx to be processed from among two or more processing units 220 with the same processing content, and generates selection result information ME4.

[0184] Next, in step S54, the first selection unit CN3 determines whether the selection result information ME4 includes information indicating the processing units 220 not to be used.

[0185] If a negative determination is made in step S54, the process proceeds to step S59.

[0186] On the other hand, if an affirmative determination is made in step S54, the process proceeds to step S55.

[0187] In step S55, the first selection unit CN3 determines whether a request to adjust the processing units 220 not to be used has been received.

[0188] If a negative determination is made in step S55, the process proceeds to step S59.

[0189] On the one hand, if an affirmative determination is made in step S55, the process proceeds to step S56.

[0190] In step S56, the analysis unit CN4 analyzes the processing result information ME3 indicating the processing result of the substrate Wp by the processing unit 220 not to be used.

[0191] Next, in step S57, the adjustment unit CN5 adjusts the processing unit 220 not to be used based on the analysis result of the processing result information ME3 by the analysis unit CN4, and returns the processing unit 220 not to be used to the processing unit 220 to be used. Therefore, according to Embodiment 1, in the case of quality priority, the number of available processing units 220 can be increased. As a result, while improving the quality of the processed substrate Wx after processing, the throughput of the processing of the processed substrate Wx can be improved.

[0192] Next, in step S58, the first selection unit CN3 updates the selection result information ME4 so that the processing unit 220 restored by the adjustment unit CN5 is selected to process the substrate Wx to be processed.

[0193] Next, in step S59, the first selection unit CN3 sets the substrate Wx to be processed, which is processed by the processing unit 220 having a lower priority than the predetermined priority, as the object of quality inspection based on the selection result information ME4.

[0194] Next, in step S60, the first selection unit CN3 notifies the selection result information ME4. For example, the first selection unit CN3 causes the display unit DP to display the selection result information ME4. For example, the first selection unit CN3 transmits the selection result information ME4 to an external device via the communication unit TR. The external device is, for example, the terminal device of the administrator of the substrate processing apparatus 100.

[0195] Next, in step S61, the first selection unit CN3 determines whether or not the processing based on all the analysis algorithms has been completed.

[0196] If a negative determination is made in step S61, the process proceeds to step S52. In step S52, acquisition unit CN2 acquires each piece of processing result information ME3 corresponding to an analysis algorithm different from the previous analysis algorithm. In step S53, first selection unit CN3 analyzes the processing result information ME3 using an analysis algorithm different from the previous analysis algorithm, and selects one or more processing units 220 to be used to process each of the processing target substrates Wx from among two or more processing units 220 having the same processing content.

[0197] On the other hand, if an affirmative determination is made in step S61, the process returns to the main routine of FIG. 9 and proceeds to step S32.

[0198] As described above with reference to FIG. 10, according to Embodiment 1, first selection unit CN3 analyzes each corresponding piece of processing result information ME3 using a plurality of different analysis algorithms, and for each analysis algorithm, selects one or more processing units 220 to be used to process each of the processing target substrates Wx from among two or more processing units 220 having the same processing content. Therefore, first selection unit CN3 generates selection result information ME4 for each analysis algorithm. As a result, according to Embodiment 1, among the plurality of pieces of selection result information ME4, the processing unit 220 to be used can be selected based on the selection result information ME4 desired by the user.

[0199] When a plurality of pieces of selection result information ME4 are stored in storage unit MEM, substrate path determination unit CN7 determines the conveyance path of each substrate W based on, for example, one piece of selection result information ME4 among the plurality of pieces of selection result information ME4.

[0200] Note that the "processing content" in the "two or more processing units 220 having the same processing content" may be the processing content in any of steps S1 to S9, S11 to S15 constituting the series of steps SQ in FIGS. 6 and 7, for example.

[0201] Next, with reference to FIG. 11, the selection result information ME4 will be described while giving a specific example. Also, as two or more processing units 220 having the same processing content, ten processing units PAHP will be taken as an example. The processing unit PAHP performs an adhesion strengthening process (step S1 in FIG. 1) on the substrate W. For convenience of explanation, identification information U1 to U10 is assigned to each of the ten processing units PAHP.

[0202] FIG. 11 is a diagram showing an example of the processing result information ME3, the priority information ME6, the selection result information ME4, and the inspection target information ME5.

[0203] In FIG. 11, as a first example of the processing result information ME3, the average value of the contact angle (degrees) on the surface of the substrate W is shown. Hereinafter, the average value of the contact angle may be referred to as the average contact angle. Further, as a second example of the processing result information ME3, the difference value between the maximum value and the minimum value of the contact angle (degrees) on the surface of the substrate W is shown. Further, as a third example of the processing result information ME3, the 3σ value calculated from the distribution of the contact angle (degrees) on the surface of the substrate W is shown. In the first to third examples, the contact angle indicates the contact angle with respect to the processing liquid for the antireflection film.

[0204] Also, as an example of the priority information ME6 in the case of throughput priority, priority information A1 is shown.

[0205] In the case of throughput priority, all ten processing units U1 to U10 are used. And the priority information A1 in the case of throughput priority indicates the processing units U1 to U10 in descending order of the priority of use. Therefore, for example, when processing 25 substrates W, the number of substrates W processed by each of the processing units U1 to U5 is 3, and the number of substrates W processed by each of the processing units U6 to U10 is 2.

[0206] Also, as an example of the selection result information ME4 in the case of quality priority, selection result information A2 is shown.

[0207] In the selection result information A2 in the case of quality priority, all 10 processing units U1 to U10 are selected. And in the selection result information A2, based on the 3σ value, the priority of use is determined. Specifically, in the selection result information A2, the smaller the 3σ value, the higher the priority is assigned to the processing units U1 to U10. That is, the selection result information A2 shows the processing units U5, U6, U2, U3, U7, U4, U8, U1, U9, U10 in descending order of the priority of use.

[0208] Therefore, for example, when processing 25 substrates W, the number of substrates W processed by each of the processing units U5, U6, U2, U3, U7 with smaller 3σ values is 3, and the number of substrates W processed by each of the processing units U8, U1, U9, U10 with larger 3σ values is 2.

[0209] Also, the selection result information A3 is shown as an example of the selection result information ME4 in the case of quality priority.

[0210] In the selection result information A3 in the case of quality priority, the processing units U8, U5, U9, U1, U5, U2 that have processed the substrates W with the average contact angle within a predetermined range are selected. In the example of FIG. 11, the predetermined range is "59 ± 0.5". "59" is the reference value.

[0211] And in the selection result information A3, based on the average contact angle, the priority of use is determined. Specifically, in the selection result information A3, the closer the average contact angle is to "59", the higher the priority is assigned to the processing units U8, U5, U9, U1, U5, U2. That is, the selection result information A3 shows the processing units U8, U5, U9, U1, U5, U2 in descending order of the priority of use.

[0212] Therefore, for example, when processing 25 substrates W, in the order of the average contact angle being closer to the reference value "59", the number of substrates W processed by the processing unit U8 is 5, and the number of substrates W processed by each of the processing units U5, U9, U1, U5, U2 is 4.

[0213] On the other hand, in the selection result information A3, the processing units U10, U7, U3, and U4 that have processed the substrate W with an average contact angle outside the predetermined range are not selected and are set as non-use targets. In FIG. 11, being a non-use target is indicated by the character "NU".

[0214] Also, the inspection target information ME5 indicates that the substrate W processed by the processing unit U2 is set as the target of quality inspection. That is, the inspection target information ME5 indicates the processing unit U2 for which the substrate W after processing becomes the target of quality inspection. In the example of FIG. 11, the inspection target information ME5 sets, in relation to the selection result information A3, the processing unit U2 that has processed the substrate W with the average contact angle being the most deviated from the reference value "59" as the processing unit U2 for processing the substrate W that is the target of quality inspection. That is, in the inspection target information ME5, among the processing units U8, U5, U9, U1, U5, and U2 selected as use targets in the selection result information A3, the substrate W processed by the processing unit U2 with the lowest usage priority is set as the target of quality inspection.

[0215] (Embodiment 2) With reference to FIGS. 12 to 19, the substrate processing apparatus 100 according to Embodiment 2 of the present invention will be described. Embodiment 2 is mainly different from Embodiment 1 in that the substrate processing apparatus 100 according to Embodiment 2 performs machine learning. The configuration of the substrate processing apparatus 100 according to Embodiment 2 is the same as the configuration of the substrate processing apparatus 100 according to Embodiment 1 described with reference to FIGS. 1 to 7. Hereinafter, the points in which Embodiment 2 is different from Embodiment 1 will be mainly described.

[0216] First, with reference to FIG. 12, the substrate processing apparatus 100 according to Embodiment 2 will be described. FIG. 12 is a block diagram showing the control device CM of the substrate processing apparatus 100 according to Embodiment 2. As shown in FIG. 12, the control unit CNT further includes a learning unit CN9. Also, the storage unit MEM further stores a learning program ME7, a plurality of learning data ME8, and a learning model ME9.

[0217] The learning model ME9 is constructed by performing machine learning (e.g., supervised machine learning) on a plurality of learning data ME8. The learning model ME9 is, for example, a trained model.

[0218] Each of the plurality of learning data ME8 includes processing result information (hereinafter referred to as "processing result information F1") indicating the processing result of a substrate to be learned (hereinafter referred to as "substrate to be learned Wn") by the processing unit 220, and evaluation information (hereinafter referred to as "evaluation information TV1") indicating an evaluation of the processing result of the substrate to be learned Wn indicated by the processing result information F1.

[0219] The plurality of processing result information F1 respectively included in the plurality of learning data ME8 indicates the processing results by two or more processing units 220 having the same processing content. Also, the processing result information F1 is an explanatory variable. That is, the processing result information F1 is a feature amount. The configuration of the processing result information F1 is the same as the configuration of the processing result information ME3. The evaluation information TV1 is an objective variable. That is, the evaluation information TV1 is a label.

[0220] The evaluation information TV1 indicates, for example, the processing result of the substrate to be learned Wn as either "normal" or "abnormal". The evaluation information TV1 may indicate, for example, the processing result of the substrate to be learned Wn in multiple stages. The evaluation information TV1 can also be regarded as information indicating an evaluation of the processing result information F1.

[0221] The learning program ME7 is a program for executing a machine learning algorithm for finding a certain rule from among the plurality of learning data ME8 and generating a learning model ME9 that represents the found rule.

[0222] In Embodiment 1, the machine learning algorithm is supervised learning, for example, a decision tree, a nearest neighbor method, a naive Bayes classifier, a support vector machine, or a neural network. Therefore, the learning model ME9 includes a decision tree, a nearest neighbor method, a naive Bayes classifier, a support vector machine, or a neural network. In the machine learning for generating the learning model ME9, the error backpropagation method may be used.

[0223] For example, a neural network includes an input layer, one or more intermediate layers, and an output layer. Specifically, the neural network is a deep neural network (DNN), a recurrent neural network (RNN), or a convolutional neural network (CNN), and performs deep learning. For example, a deep neural network includes an input layer, a plurality of intermediate layers, and an output layer.

[0224] The learning unit CN9 performs machine learning on a plurality of learning data ME8 based on the learning program ME7. As a result, a certain rule is found from among the plurality of learning data ME8, and the learning model ME9 is generated.

[0225] Specifically, the learning unit CN9 finds a certain rule between the processing result information F1 and the evaluation information TV1 included in the learning data ME8, and generates the learning model ME9.

[0226] More specifically, the learning unit CN9 calculates a plurality of learned parameters by performing machine learning on a plurality of learning data ME8 based on the learning program ME7, and generates a learning model ME9 including one or more functions to which the plurality of learned parameters are applied. The learned parameters are parameters (coefficients) obtained based on the results of machine learning using the plurality of learning data ME8.

[0227] The learning model ME9 takes the processing result information ME3 indicating the processing result of the substrate Wp by the processing unit 220 as input information, and outputs evaluation information (hereinafter referred to as "evaluation information OT1") indicating an evaluation of the processing result of the substrate Wp as output information. That is, the learning model ME9 evaluates the substrate Wp after being processed by the processing unit 220. The configuration of the evaluation information OT1 is the same as the configuration of the evaluation information TV1.

[0228] The first selection unit CN3 inputs each of two or more pieces of processing result information ME3 indicating the processing results of two or more substrates Wp to the learning model ME9 as input information, and acquires, from the learning model ME9, the evaluation information OT1 indicating the evaluation of the processing result of each of the two or more substrates Wp as output information. The "processing results of two or more substrates Wp" in this case indicates the processing results of two or more substrates Wp by two or more processing units 220 with the same processing content.

[0229] Then, based on the two or more pieces of evaluation information OT1 acquired from the learning model ME9, the first selection unit CN3 selects one or more processing units 220 to be used for processing each of the processing target substrates Wx from among the two or more processing units 220 with the same processing content. Therefore, according to Embodiment 2, by using the learning model ME9 that has learned a plurality of pieces of learning data ME8 each including a plurality of pieces of processing result information F1, the processing unit 220 to be used can be selected quickly and with high accuracy.

[0230] Next, with reference to FIGS. 13 and 14, the substrate processing method according to Embodiment 2 will be described. The substrate processing method according to Embodiment 2 is the same as the substrate processing method according to Embodiment 1 described with reference to FIG. 9. Hereinafter, the points where the substrate processing method according to Embodiment 2 differs from the substrate processing method of Embodiment 1 will be mainly described.

[0231] FIG. 13 is a flowchart showing step S31 of FIG. 9 in Embodiment 2. As shown in FIG. 13, the processing of step S31 according to Embodiment 2 includes steps S81 to S94.

[0232] The processing of steps S81 to S91 is the same as the processing of steps S51 to S61 described with reference to FIG. 10, respectively. However, in step S83, the processing shown in FIG. 14 may be performed.

[0233] FIG. 14 is a flowchart showing an example of the processing of step S83 in FIG. 13. As shown in FIG. 14, the processing of step S83 includes steps S111 to S114.

[0234] In step S111, the first selection unit CN3 inputs, as input information, the processing result information ME3 indicating the processing result of the substrate Wp to the learning model ME9.

[0235] Next, in step S112, the first selection unit CN3 acquires, as output information, the evaluation information OT1 indicating the evaluation of the processing result of the substrate Wp from the learning model ME9.

[0236] Next, in step S113, the first selection unit CN3 selects, based on the evaluation information OT1, one or more processing units 220 to be used for processing each of the processing target substrates Wx from among two or more processing units 220 having the same processing content. For example, the first selection unit CN3 selects, as a target for use, the processing unit 220 that has processed the substrate Wp for which the evaluation information OT1 indicates "normal", and sets the processing unit 220 that has processed the substrate Wp for which the evaluation information OT1 indicates "abnormal" as a non-use target.

[0237] Next, in step S114, the first selection unit CN3 determines whether processing has been completed for all the processing result information ME3.

[0238] If a negative determination is made in step S114, the processing proceeds to step S111.

[0239] On the other hand, if an affirmative determination is made in step S114, the first selection unit CN3 outputs the selection result information ME4, and the processing returns to the routine shown in FIG. 13 and proceeds to step S84.

[0240] As shown in FIG. 13, in step S92, the first selection unit CN3 selects one or more processing units 220 to be used for processing each of a plurality of processing target substrates Wx based on a plurality of different selection result information ME4 respectively obtained by different plurality of analysis algorithms. For example, the first selection unit CN3 processes a plurality of different selection result information ME4 respectively obtained by different plurality of analysis algorithms by an AND condition to generate new selection result information ME4.

[0241] Next, in step S93, the first selection unit CN3 sets, as an object of quality inspection, a processing target substrate Wx to be processed by a processing unit 220 having a lower priority than a predetermined priority based on the selection result information ME4 generated in step S92. This point is the same as that in step S89.

[0242] Next, in step S94, the first selection unit CN3 notifies the selection result information ME4 generated in step S92. This point is the same as that in step S90. After the completion of step S94, the process returns to the main routine of FIG. 9 and proceeds to step S32.

[0243] Note that the “processing content” in “two or more processing units 220 having the same processing content” may be the processing content in any of steps S1 to S9 and S11 to S15 constituting a series of steps SQ in FIGS. 6 and 7.

[0244] Next, with reference to FIGS. 12 and 15, the learning unit CN9 will be described. FIG. 15 is a flowchart showing a learning method executed by the learning unit CN9. As shown in FIG. 15, the learning method includes steps S131 to S134.

[0245] In step S131, the learning unit CN9 acquires learning data ME8.

[0246] Next, in step S132, the learning unit CN9 performs machine learning on the learning data ME8 based on a learning program ME7.

[0247] Next, in step S133, the learning unit CN9 determines whether or not the learning end condition is satisfied. The learning end condition is a condition predetermined for ending the machine learning. The learning end condition is, for example, that the number of iterations has reached a specified number of times.

[0248] If the determination in step S133 is negative, the process proceeds to step S131. As a result, the machine learning is repeated.

[0249] On the other hand, if the determination in step S133 is positive, the process proceeds to step S134.

[0250] In step S134, the learning unit CN9 outputs, as the learning model ME9, a model (one or more functions) to which a plurality of latest parameters (coefficients), that is, a plurality of learned parameters (coefficients) are applied. Then, the storage unit MEM stores the learning model ME9.

[0251] As described above, by the learning unit CN9 executing steps S131 to S134, the learning model ME9 is generated. The learning method corresponds to an example of the "learning model generation method". The control device CM can be regarded as a "learning device".

[0252] In the repeatedly executed step S131, each of the plurality of learning data ME8 includes processing result information F1 indicating the processing result of the learning target substrate Wn and evaluation information TV1 indicating the evaluation of the processing result of the learning target substrate Wn. The processing result information F1 included in each learning data ME8 is one of two or more pieces of processing result information F1 respectively indicating the processing results of two or more learning target substrates Wn by two or more processing units 220 having the same processing content. The learning model ME9 is a program that inputs, as input information, each of two or more pieces of processing result information ME3 respectively indicating the processing results of two or more substrates Wp by two or more processing units 220 having the same processing content, and outputs, as output information, evaluation information OT1 indicating the evaluation of the processing result of each of the two or more substrates Wp.

[0253] In other words, the learning model ME9 causes the control device CM to function so as to evaluate the processing result of the substrate Wp. The control device CM is an example of a "computer". Specifically, the learning model ME9 causes the control device CM to function so as to input each of two or more pieces of input information and output each of two or more pieces of output information. The two or more pieces of input information are two or more pieces of processing result information ME3 respectively indicating the processing results of two or more substrates Wp by two or more processing units 220 with the same processing content. The two or more pieces of output information are two or more pieces of evaluation information OT1 respectively indicating the evaluation of the processing results of two or more substrates Wp.

[0254] Next, with reference to FIGS. 16 to 19, the selection result information ME4 will be described with specific examples. Also, as in the case of FIG. 11, as two or more processing units 220 with the same processing content, ten processing units PAHP that execute the adhesion strengthening process (step S1 in FIG. 6) will be taken as an example. Also, for the sake of convenience of explanation, identification information U1 to U10 is assigned to each of the ten processing units PAHP.

[0255] FIG. 16 is a diagram showing an example of the processing result information ME3, the priority information ME6, the selection result information ME4, and the inspection target information ME5. FIG. 17 is a diagram showing the contact angle map data M1 to M10 according to the second embodiment.

[0256] As shown in FIG. 16, in the second embodiment, as an example of the processing result information ME3, the contact angle map data M1 to M10 is shown. The contact angles represented by the contact angle map data M1 to M10 indicate the contact angles with respect to the processing liquid for the antireflection film.

[0257] Specifically, as shown in FIGS. 17 to 19, the contact angle map data M1 to M10 respectively correspond to the processing units U1 to U10. For example, the contact angle map data M1 shows the distribution of the contact angles on the surface of the substrate W processed by the processing unit U1.

[0258] In the contact angle map data M1 to M10, the contact angle is the smallest in region G1 and the largest in region G5. The contact angle increases in the order of region G1, region G2, region G3, region G4, and region G5 from region G1 toward region G5. Region G1 is indicated by dense diagonal lines slanting upward to the right. Region G2 is indicated by sparse diagonal lines slanting downward to the right. Region G3 is indicated by sparse diagonal lines slanting upward to the right. Region G4 is indicated by crossed diagonal lines. Region G5 is indicated by dots. In FIGS. 17 to 19, regions G1 to G5 are described to make the drawings easy to understand, but actually, in the contact angle map data M1 to M10, the distribution of the contact angle is shown by gradation.

[0259] Returning to FIG. 16, selection result information B2 is shown as an example of the selection result information ME4 in the case of quality priority.

[0260] In the selection result information B2 in the case of quality priority, based on the evaluation information OT1 obtained by inputting the contact angle map data M1 to M10 into the learning model ME9, the processing units U2, U3, U4, U5, U6, and U7 are selected. In FIG. 16, "○" indicates that the processing units U2, U3, U4, U5, U6, and U7 are selected. Specifically, in the selection result information B2, the processing units U2, U3, U4, U5, U6, and U7 that have processed the substrate Wp for which the evaluation information OT1 indicates "normal" are selected.

[0261] Therefore, for example, when processing 25 substrates W, the number of substrates W processed by the processing unit U2 is 5, and the number of substrates W processed by each of the processing units U3, U4, U5, U6, and U7 is 4.

[0262] On the other hand, in the selection result information B2, the processing units U1, U8, U9, and U10 that have processed the substrate Wp for which the evaluation information OT1 indicates "abnormal" are not selected and are set as non-use targets. In FIG. 16, being a non-use target is indicated by the character "NU".

[0263] Also, the priority information B1 in the case of throughput priority is the same as the priority information A1 in the case of throughput priority shown in FIG. 11.

[0264] Furthermore, the selection result information B3 in the case of quality priority is the same as the selection result information A3 in the case of quality priority shown in FIG. 11.

[0265] Furthermore, selection result information B4 is shown as an example of the selection result information ME4 in the case of quality priority.

[0266] In the selection result information B4 in the case of quality priority, for each of the processing units U1 to U10, the result of processing the selection result information B2 and the selection result information B3 under the AND condition is shown. For example, in the processing unit U1, when taking the AND condition for "not use target: NU" of the selection result information B2 and "use target: priority 4" of the selection result information B3, the result of the processing under the AND condition is "not use target: NU" in the selection result information B4. That is, if one or both of the selection result information B2 and the selection result information B3 indicate "not use target: NU", the result of the processing under the AND condition becomes "not use target: NU". On the other hand, if both the selection result information B2 and the selection result information B3 indicate "use target", that is, if both the selection result information B2 and the selection result information B3 indicate "selected", the result of the processing under the AND condition is "use target", that is, "selected" in the selection result information B4. In this case, in the selection result information B4, the priority of the selection result information B3 is adopted. This is because the selection result information B2 does not include priority.

[0267] In the selection result information B4, the processing units U6, U5, and U2 are selected. In the selection result information B4, the priority of use is determined based on the priority of the selection result information B3 that is the target of the processing under the AND condition. Specifically, in the selection result information B4, according to the priority of the selection result information B3, the processing units U6, U5, and U2 are shown in descending order of the priority of use.

[0268] Therefore, for example, when processing 25 substrates W, the number of substrates W processed by the processing unit U6 is 9, and the number of substrates W processed by each of the processing units U5 and U2 is 8.

[0269] On the other hand, in the selection result information B4, the processing units U1, U3, U4, U7 to U10, whose processing results by the AND condition indicate "not target for use", are not selected and are set as not target for use. In FIG. 16, that it is not target for use is indicated by the character "NU".

[0270] (Embodiment 3) With reference to FIGS. 12 and 20 to 28, the substrate processing apparatus 100 according to Embodiment 3 of the present invention will be described. In Embodiment 3, Embodiment 3 is mainly different from Embodiments 1 and 2 in that one or more processing units 220 are selected based on the processing result information ME3 by the processing units 220 with different processing contents. The configuration of the control device CM of the substrate processing apparatus 100 according to Embodiment 3 is the same as the configuration of the control device CM of the substrate processing apparatus 100 according to Embodiment 2 described with reference to FIG. 12. Therefore, in the description of Embodiment 3, FIG. 12 will be appropriately referred to. Hereinafter, the points in which Embodiment 3 is different from Embodiments 1 and 2 will be mainly described.

[0271] First, with reference to FIGS. 6, 7, 12, and 20, the substrate processing apparatus 100 according to Embodiment 3 will be described. FIG. 20 is a diagram showing the storage unit MEM and the control unit CNT of the substrate processing apparatus 100 according to Embodiment 3. FIG. 20 mainly shows the parts in which the substrate processing apparatus 100 according to Embodiment 3 is different from the substrate processing apparatus 100 in FIG. 12.

[0272] As shown in FIGS. 6, 7, and 12, a plurality of processing units 220 execute a plurality of series of processes SQ in parallel. Each of the plurality of series of processes SQ includes a plurality of processes S1 to S9, S11 to S15 whose processing contents executed on the substrate W are different. And the plurality of processing units 220 include two or more processing units 220 that sequentially execute a plurality of processes S1 to S9, S11 to S15 whose processing contents executed on the substrate W are different. "The processing contents are different" means that at least one of the processing functions and processing conditions is different. Also, in Embodiment 3, similar to Embodiment 1, the plurality of processing units 220 include two or more processing units 220 whose processing contents executed on the substrate W are the same among the plurality of series of processes SQ.

[0273] As shown in FIG. 20, in the substrate processing apparatus 100 according to Embodiment 3, the storage unit MEM stores a plurality of sets of processing result information ME30 instead of the plurality of processing result information ME3 in FIG. 12. The plurality of sets of processing result information ME30 are respectively obtained in a plurality of series of processes SQ. Each of the plurality of sets of processing result information ME30 includes two or more pieces of processing result information ME3 respectively indicating the processing results of the substrate Wp by two or more processing units 220 with different processing contents. That is, each of the plurality of sets of processing result information ME30 includes two or more pieces of processing result information ME3 respectively indicating the processing results in two or more processes among the processes S1 to S9, S11 to S15 included in the series of processes SQ.

[0274] In the following description, a case where each of the plurality of sets of processing result information ME30 includes the processing result information DA1, the processing result information DA2, the processing result information DA3, and the processing result information DA4 will be exemplified as appropriate. Also, as selection targets by the first selection unit CN3, the processing units 220 from which the processing result information DA1 to DA3 are respectively obtained will be exemplified as appropriate.

[0275] The processing result information DA1 indicates the processing result of the substrate Wp by the processing unit 220 that executed the adhesion strengthening process in step S1 (FIG. 6). For example, the processing result information DA1 is contact angle map data after the adhesion strengthening process.

[0276] The processing result information DA2 indicates the processing result of the substrate Wp by the processing unit 220 that executed the resist film formation process in step S5 (Fig. 6). For example, the processing result information DA2 is resist film thickness map data after the resist film formation process.

[0277] The processing result information DA3 indicates the processing result of the substrate Wp by the processing unit 220 that executed the third heat treatment (post-exposure heat treatment) in step S11 (Fig. 7). For example, the processing result information DA3 is temperature map data after the third heat treatment.

[0278] The processing result information DA4 indicates the processing result of the substrate Wp by the processing unit 220 that executed the development process in step S13 (Fig. 7). For example, the processing result information DA4 is resist pattern line width map data after the development process.

[0279] As shown in Figs. 12 and 20, based on the processing result information set ME30, the first selection unit CN3 selects one or more processing units 220 to be used for processing the processing target substrate Wx from among two or more processing units 220 with different processing contents, and generates selection result information ME4 indicating the selection result. Therefore, according to Embodiment 3, a processing unit 220 with good processing results can be selected, and the quality of the processed processing target substrate Wx can be improved.

[0280] For example, the selection result information ME4 indicates one or more processing units 220 to be used for processing each of the processing target substrates Wx among two or more processing units 220 with different processing contents.

[0281] In the following description, two or more pieces of processing result information ME3 included in the processing result information set ME30 are normalized by the preprocessing unit CN1 (Fig. 12) and are dimensionless quantities.

[0282] In the substrate processing apparatus 100 according to Embodiment 3, the storage unit MEM stores, instead of the learning program ME7, a plurality of learning data ME8, and the learning model ME9 in FIG. 12, a first learning program 71, a second learning program 72, a plurality of third learning programs 73, a plurality of first learning data 81, a plurality of second learning data 82, a plurality of third learning data 83, a first learning model 91, a second learning model 92, and a plurality of third learning models 93. Each of the first learning program 71, the second learning program 72, and the third learning program 73 corresponds to an example of a "learning program". Each of the first learning data 81, the second learning data 82, and the third learning data 83 corresponds to an example of "learning data". Each of the first learning model 91, the second learning model 92, and the third learning model 93 corresponds to an example of a "learning model".

[0283] Also, in the substrate processing apparatus 100 according to Embodiment 3, the control unit CNT includes, instead of the learning unit CN9 in FIG. 12, a first learning unit 61, a second learning unit 62, and a plurality of third learning units 63. Each of the first learning unit 61, the second learning unit 62, and the third learning unit 63 corresponds to an example of a "learning unit".

[0284] The first learning model 91 is constructed by performing machine learning (for example, supervised machine learning) on a plurality of first learning data 81. The first learning model 91 is, for example, a trained model.

[0285] Each of the plurality of first learning data 81 includes processing result information F1 indicating the processing result of the learning target substrate Wn by the processing unit 220, and evaluation information TV1 indicating the evaluation of the processing result of the learning target substrate Wn indicated by the processing result information F1. The plurality of processing result information F1 respectively included in the plurality of first learning data 81 indicates the processing results by two or more processing units 220 with the same processing content. In addition, the configuration of the first learning data 81 is the same as the configuration of the learning data ME8 in FIG. 12.

[0286] In this case, for example, the processing result information F1 is processing result information indicating the processing result of the learning target substrate Wn obtained in a predetermined process (hereinafter referred to as "predetermined process ST") among the processes S1 to S9 and S11 to S15.

[0287] In Embodiment 3, the predetermined process ST is process S13. Therefore, the configuration of the processing result information F1 is the same as the configuration of the processing result information DA4. The processing result information F1 has been normalized by the preprocessing unit CN1 (FIG. 12) and is a dimensionless quantity. The predetermined process ST corresponds to an example of the "predetermined processing process".

[0288] For example, the predetermined process ST is not particularly limited as long as it is a process S2 to S9 or S11 to S15 among the processes S1 to S9 and S11 to S15 included in the series of processes SQ and is after the first-stage process S1. For example, the predetermined process ST is a process after the exposure process of process S10.

[0289] The first learning program 71 is a program for executing a machine learning algorithm for finding a certain rule from a plurality of first learning data 81 and generating a first learning model 91 expressing the found rule. In addition, the configuration of the first learning program 71 is the same as the configuration of the learning program ME7 in FIG. 12.

[0290] The first learning unit 61 performs machine learning on a plurality of first learning data 81 based on the first learning program 71 and generates the first learning model 91. In addition, the configuration of the first learning unit 61 is the same as the configuration of the learning unit CN9 in FIG. 12.

[0291] The first learning model 91 takes, as input information, the processing result information DA4 indicating the processing result of the substrate Wp by the processing unit 220, and outputs, as output information, the evaluation information OT1 indicating the evaluation of the processing result of the substrate Wp. The evaluation information OT1 indicates, for example, the processing result of the substrate Wp as either "normal" or "abnormal". That is, the first learning model 91 evaluates the substrate W after being processed by the processing unit 220. The evaluation information OT1 can also be regarded as information indicating the evaluation of the processing result information DA4. In addition, the configuration of the first learning model 91 is the same as the configuration of the learning model ME9 in FIG. 12.

[0292] The first selection unit CN3 inputs, as input information, each of two or more pieces of processing result information DA4 respectively indicating the processing results of two or more substrates Wp to the first learning model 91, and acquires, as output information, the evaluation information OT1 indicating the evaluation of the processing result of each of the two or more substrates Wp from the first learning model 91. The "processing results of two or more substrates Wp" in this case indicates the processing results of two or more substrates Wp by two or more processing units 220 with the same processing content. The two or more pieces of processing result information DA4 are respectively included in two or more sets of processing result information ME30.

[0293] That is, for each of the plurality of sets of processing result information ME30, the first selection unit CN3 inputs the processing result information DA4 as input information to the first learning model 91, and acquires the evaluation information OT1 as output information from the first learning model 91.

[0294] Note that the processing result information F1 included in the first learning data 81 and the processing result information DA4 input to the first learning model 91 may be information before normalization.

[0295] The second learning model 92 is constructed by performing machine learning (for example, unsupervised machine learning) on a plurality of second learning data 82. The second learning model 92 is, for example, a trained model.

[0296] Each of the plurality of second learning data 82 includes a processing result information set (hereinafter referred to as "processing result information set FS"). The processing result information set FS includes two or more processing result information (hereinafter referred to as "processing result information F2") respectively indicating the processing results of the learning target substrate Wn by two or more processing units 220 with different processing contents.

[0297] Also, the processing result information F2 is an explanatory variable. That is, the processing result information F2 is a feature quantity. The configuration of the processing result information set FS is the same as the configuration of the processing result information set ME30. That is, the configurations of the two or more processing result information F2 included in the processing result information set FS are respectively the same as the configurations of the two or more processing result information ME3 included in the processing result information set ME30. The two or more processing result information F2 included in the processing result information set FS are normalized by the preprocessing unit CN1 (FIG. 12) and are dimensionless quantities.

[0298] In Embodiment 3, the processing result information set FS includes four pieces of processing result information F2. Specifically, the processing result information set FS includes processing result information DB1 indicating the processing result of the learning target substrate Wn in step S1, processing result information DB2 indicating the processing result of the learning target substrate Wn in step S5, processing result information DB3 indicating the processing result of the learning target substrate Wn in step S11, and processing result information DB4 indicating the processing result of the learning target substrate Wn in step S13. The configuration of the processing result information DB1 is the same as the configuration of the processing result information DA1, and the configuration of the processing result information DB2 is the same as the configuration of the processing result information DA2. Also, the configuration of the processing result information DB3 is the same as the configuration of the processing result information DA3, and the configuration of the processing result information DB4 is the same as the configuration of the processing result information DA4.

[0299] The second learning program 72 is a program for executing a machine learning algorithm for finding a certain rule from each processing result information F2 of the plurality of second learning data 82 and generating a second learning model 92 expressing the found rule.

[0300] In Embodiment 3, the machine learning algorithm is unsupervised learning, for example, k-means method, k-medoids method, hierarchical clustering, self-organizing map, fuzzy c-means method, Gaussian mixture model, or neural network.

[0301] The second learning unit 62 performs machine learning on a plurality of second learning data 82 based on the second learning program 72. As a result, a certain rule is found from each processing result information F2 of the plurality of second learning data 82, and a second learning model 92 is generated.

[0302] Specifically, the second learning unit 62 calculates a plurality of learned parameters by performing machine learning on a plurality of second learning data 82 based on the second learning program 72, and generates a second learning model 92 including one or more functions to which the plurality of learned parameters are applied. The learned parameter is a parameter (coefficient) obtained based on the result of machine learning using a plurality of second learning data 82.

[0303] The second learning model 92 inputs each of two or more pieces of processing result information DA1 to DA4 included in the processing result information set ME30 as input information, clusters the two or more pieces of processing result information DA1 to DA4, and outputs first clustering information indicating the result of the clustering as output information. Clustering is to find information with similarity or correlation and group the information with similarity or correlation. Therefore, by clustering, information with similarity or correlation is classified into one cluster. The first clustering information indicates each cluster into which each of the processing result information DA1 to DA4 is classified. The first clustering information corresponds to an example of "clustering information".

[0304] The first selection unit CN3 inputs each of two or more pieces of processing result information DA1 to DA4 included in the processing result information set ME30 as input information to the second learning model 92, and acquires first clustering information from the second learning model 92. The "two or more pieces of processing result information DA1 to DA4" in this case indicate the processing results of the substrate Wp by each of two or more processing units 220 with different processing contents.

[0305] Then, based on the first clustering information acquired from the second learning model 92, the first selection unit CN3 selects one or more processing units 220 to be used for processing the processing target substrate Wx from among two or more processing units 220 with different processing contents. Therefore, according to Embodiment 3, by using the second learning model 92 that has learned a plurality of second learning data 82 including the processing result information DB1 to DB4, the processing unit 220 to be used can be selected quickly and with high accuracy.

[0306] For example, the user labels each cluster generated by the second learning model 92 via the input unit IN with "normal" indicating that the processing result is normal or "abnormal" indicating that the processing result is abnormal.

[0307] Then, for example, the first selection unit CN3 selects, as the processing unit 220 to be used for processing the processing target substrate Wx, the processing unit 220 from which the processing result information classified into the cluster labeled with "normal" among the processing result information DA1 to DA4 is obtained. On the other hand, for example, the first selection unit CN3 sets the processing unit 220 from which the processing result information classified into the cluster labeled with "abnormal" among the processing result information DA1 to DA4 is obtained as the processing unit 220 not to be used.

[0308] In particular, in Embodiment 3, the first selection unit CN3 determines, based on the first clustering information, whether the processing result information DA1 to DA3 obtained in the steps S1, S5, and S11, which are executed before a predetermined step S13 among the plurality of steps S1, S5, S11, and S13 with different processing contents, belong to the same cluster as the processing result information DA4 obtained in the predetermined step S13. Based on the determination result, one or more processing units 220 to be used for processing the processing target substrate Wx are selected from among the two or more processing units 220. In other words, the first selection unit CN3 selects the processing unit 220 to be used for processing the processing target substrate Wx based on the cluster to which the processing result information DA4 obtained in a predetermined step S13, which is a downstream step among the plurality of steps S1, S5, S11, and S13, belongs. Therefore, according to Embodiment 3, it is possible to identify the upstream step that caused the processing result indicated by the processing result information DA4 among the plurality of steps S1, S5, S11, and S13 and select the processing unit 220 to be used for processing the processing target substrate Wx. The predetermined step S13 corresponds to an example of the "predetermined processing step".

[0309] For example, in the first analysis algorithm AG1, the first selection unit CN3 selects, as the processing unit 220 to be used for processing the processing target substrate Wx, the processing unit 220 in which the processing result information belonging to a cluster different from the processing result information DA4 indicated as "abnormal" by the evaluation information OT1 acquired from the first learning model 91 is obtained among the processing result information DA1 to DA3. That is, among the processing result information DA1 to DA3, the processing unit 220 in which the processing result information having no correlation or a small correlation with the processing result information DA4 indicated as "abnormal" by the evaluation information OT1 is obtained is selected.

[0310] Also, in the first analysis algorithm AG1, when the processing result information DA4 is indicated as "normal" by the evaluation information OT1 acquired from the first learning model 91, the first selection unit CN3 selects all the processing units 220 in which the processing result information DA1 to DA3 is obtained as the processing unit 220 to be used for processing the processing target substrate Wx.

[0311] Furthermore, in the first analysis algorithm AG1, the first selection unit CN3 sets the processing unit 220 that has obtained the processing result information belonging to the same cluster as the processing result information DA4 indicated as "abnormal" by the evaluation information OT1 obtained from the first learning model 91 among the processing result information DA1 to DA3 as the processing unit 220 not to be used. That is, among the processing result information DA1 to DA3, the processing unit 220 that has obtained the processing result information correlated with the processing result information DA4 indicated as "abnormal" by the evaluation information OT1 is set as the object not to be used.

[0312] Also, for example, in order to execute the second analysis algorithm AG2, the user labels, via the input unit IN, at least one of the plurality of clusters generated by the second learning model 92 with "specificity" indicating that the processing result is specific. Whether the processing result is specific or not is determined experimentally and / or empirically.

[0313] The second analysis algorithm AG2 is the same as the first analysis algorithm AG1. However, even when the processing result information DA4 is indicated as "normal" by the evaluation information OT1 obtained from the first learning model 91, under certain conditions, the processing unit 220 not to be used is set.

[0314] That is, in the second analysis algorithm AG2, the first selection unit CN3 sets the processing result information belonging to a cluster different from the processing result information DA4 indicated as "normal" by the evaluation information OT1 obtained from the first learning model 91 among the processing result information DA1 to DA3 and belonging to the cluster labeled with "specificity" as the processing unit 220 not to be used.

[0315] Note that, for example, the selection targets by the first selection unit CN3 are two or more processing units 220 that execute processes other than a predetermined process ST (for example, process S13) among the plurality of processing units 220 from which the plurality of pieces of processing result information ME3 included in the processing result information set ME30 can be obtained respectively. However, the selection targets by the first selection unit CN3 may be all of the plurality of processing units 220 from which the plurality of pieces of processing result information ME3 included in the processing result information set ME30 can be obtained respectively. In this case, for example, when the processing result information DA4 belongs to a "normal" cluster, the first selection unit CN3 selects the processing unit 220 from which the processing result information DA4 is obtained as the processing unit 220 to be used for processing the processing target substrate Wx. On the other hand, for example, when the processing result information DA4 belongs to an "abnormal" cluster, the first selection unit CN3 sets the processing unit 220 from which the processing result information DA4 is obtained as the processing unit 220 not to be used.

[0316] Here, for each of the plurality of processing result information sets ME30, the first selection unit CN3 inputs each of the processing result information DA1 to DA4 as input information to the second learning model 92, and acquires the first clustering information from the second learning model 92. Then, for each of the plurality of processing result information sets ME30, the first selection unit CN3 selects one or more processing units 220 to be used for processing the processing target substrate Wx based on the first clustering information, and generates selection result information ME4. That is, for each of the plurality of series of processes SQ, the first selection unit CN3 selects one or more processing units 220 to be used for processing the processing target substrate Wx based on the first clustering information, and generates selection result information ME4. That is, a plurality of selection result information ME4 are generated corresponding to the plurality of series of processes SQ respectively.

[0317] Then, the first selection unit CN3 may assign priorities to the plurality of selection result information ME4. The priority in this case is the priority of use for one set when one or more processing units 220 selected by the selection result information ME4 are regarded as one set.

[0318] For example, in the first analysis algorithm AG1 and the second analysis algorithm AG2, when the processing result information DA4 is shown to be "abnormal" by the evaluation information OT1 obtained from the first learning model 91 in the first selection unit CN3, and at least one of the processing result information of DA1 to DA3 belongs to the same cluster as the processing result information DA4, the lowest priority is assigned to the selection result information ME4 based on the processing result information DA1 to DA4.

[0319] For example, in the first analysis algorithm AG1, when the processing result information DA4 is shown to be "normal" by the evaluation information OT1 obtained from the first learning model 91 in the first selection unit CN3, and at least one of the processing result information of DA1 to DA3 belongs to the same cluster as the processing result information DA4, a lower priority is assigned to the selection result information ME4 based on the processing result information DA1 to DA4 than when all of the processing result information of DA1 to DA3 belongs to a cluster different from the processing result information DA4.

[0320] For example, in the second analysis algorithm AG2, when the processing result information DA4 is shown to be "normal" by the evaluation information OT1 obtained from the first learning model 91 in the first selection unit CN3, and at least one of the processing result information of DA1 to DA3 belongs to a cluster labeled with "specificity", a lower priority is assigned to the selection result information ME4 based on the processing result information DA1 to DA4 than when all of the processing result information of DA1 to DA3 does not belong to a cluster labeled with "specificity".

[0321] Also, for example, the first selection unit CN3 sets the processing target substrate Wx to be processed by a set of one or more processing units 220 selected by the selection result information ME4 with a priority lower than a predetermined priority as the target of quality inspection. In this case, the first selection unit CN3 may determine the set of processing units 220 by assigning priorities for quality inspection.

[0322] Furthermore, in Embodiment 3, in the first clustering information, when the processing result information (for example, processing result information DA1) obtained in a process (for example, process S1) executed before a predetermined process S13 included in a series of processes SQ belongs to the same cluster as the processing result information DA4 obtained in the predetermined process S13, the first selection unit CN3 determines whether there is a correlation between the processing result information (for example, processing result information DA1) obtained in a process (for example, process S1) executed before and the processing result information (for example, processing result information DA1) obtained in a process (for example, process S1) with the same processing content (for example, a process S1 of another series of processes SQ). Then, based on the determination result, the first selection unit CN3 selects one or more processing units 220 to be used for processing the processing target substrate Wx from among two or more processing units 220 with the same processing content. Therefore, according to Embodiment 3, it is possible to select a processing unit 220 with good processing results from among two or more processing units 220 with the same processing content, and improve the quality of the processed processing target substrate Wx.

[0323] For example, when the processing result information DA4 is shown to be "abnormal" by the evaluation information OT1 obtained from the first learning model 91, and in the first clustering information, the processing result information DA1 by the process S1 executed before the predetermined process S13 belongs to the same cluster as the processing result information DA4 by the predetermined process S13, when the first selection unit CN3 determines that there is a correlation between another processing result information DA1 by the process S1 with the same processing content as the process S1 executed before and the processing result information DA1 by the process S1 executed before, the first selection unit CN3 sets the processing unit 220 where the other processing result information DA1 by the process S1 with the same processing content is obtained as a processing unit 220 not to be used. Therefore, according to Embodiment 3, it is possible to set a processing unit 220 with poor processing results as not to be used from among two or more processing units 220 with the same processing content, and improve the quality of the processed processing target substrate Wx as a whole for the substrate processing apparatus 100.

[0324] In this specification, setting the processing unit 220 that is not the target of use (that is, determining the processing unit 220 that is not the target of use) is synonymous with selecting the processing unit 220 other than the target of non - use.

[0325] In particular, in Embodiment 3, the first selection unit CN3 uses the third learning model 93 to select one or more processing units 220 based on the correlation.

[0326] The storage unit MEM stores a plurality of third learning models 93 corresponding to a plurality of processes S1 to S9, S11 to S15 with different processing contents in a series of processes SQ. In Embodiment 3, as an example, the storage unit MEM stores a plurality of third learning models 93 corresponding to a plurality of processes S1, S5, and S11, respectively.

[0327] The third learning model 93, a plurality of third learning data 83, and the third learning unit 63 corresponding to the process S1 will be described. The configurations of the third learning model 93, the third learning data 83, and the third learning unit 63 corresponding to the processes S5 and S11 are the same as the configurations of the third learning model 93, the third learning data 83, and the third learning unit 63 corresponding to the process S1, and the description thereof will be omitted.

[0328] The third learning model 93 is constructed by performing machine learning (for example, unsupervised machine learning) on a plurality of third learning data 83. The third learning model 93 is, for example, a learned model.

[0329] Each of the plurality of third learning data 83 includes processing result information (hereinafter referred to as "processing result information F3") indicating the processing result of the learning target substrate Wn by the processing unit 220 that executes the process S1. The plurality of pieces of processing result information F3 are obtained in two or more processes S1 with the same processing content among a plurality of series of processes SQ.

[0330] Further, the processing result information F3 is an explanatory variable. That is, the processing result information F3 is a feature amount. The configuration of the processing result information F3 is the same as that of the processing result information DA1 obtained in step S1. The processing result information F2 is normalized by the preprocessing unit CN1 (FIG. 12) and is a dimensionless quantity.

[0331] The third learning program 73 is a program for executing a machine learning algorithm for finding a certain rule from a plurality of third learning data 83 and generating a third learning model 93 that represents the found rule. The machine learning algorithm of the third learning program 73 is the same as the machine learning algorithm of the second learning program 72.

[0332] The third learning unit 63 performs machine learning on a plurality of third learning data 83 based on the third learning program 73. As a result, a certain rule is found from the plurality of third learning data 83, and the third learning model 93 is generated.

[0333] Specifically, the third learning unit 63 calculates a plurality of learned parameters by performing machine learning on a plurality of third learning data 83 based on the third learning program 73, and generates a third learning model 93 including one or more functions to which the plurality of learned parameters are applied. The learned parameter is a parameter (coefficient) obtained based on the result of machine learning using a plurality of third learning data 83.

[0334] The third learning model 93 inputs, as input information, two or more pieces of processing result information DA1 respectively obtained in two or more steps S1 having the same processing content among a plurality of series of steps SQ, clusters the two or more pieces of processing result information DA1, and outputs, as output information, second clustering information indicating the result of the clustering. The second clustering information indicates each cluster to which each of the two or more pieces of processing result information DA1 is classified.

[0335] The first selection unit CN3 selects, as follows, a processing unit 220 to be used for processing the substrate to be processed Wx from two or more processing units 220 having the same processing content among a plurality of series of processes SQ.

[0336] That is, the first selection unit CN3 refers to the first clustering information obtained from the second learning model 92 for the processing result information set ME30, and among the processing result information DA1 to DA3 obtained in steps S1, S5, and S11 executed before a predetermined step S13 in the series of steps SQ, identifies the processing result information belonging to the same cluster as the processing result information DA4 obtained in the predetermined step S13. Hereinafter, for simplicity, the case where the identified processing result information is the processing result information DA1 obtained in step S1 will be exemplified.

[0337] Then, the first selection unit CN3 selects the third learning model 93 corresponding to the step S1 in which the identified processing result information DA1 is obtained.

[0338] Furthermore, the first selection unit CN3 inputs the identified processing result information DA1 and the processing result information DA1 obtained in other steps S1 having the same processing content among a plurality of series of processes SQ as input information to the selected third learning model 93, and obtains second clustering information indicating the clustering result for the plurality of processing result information DA1.

[0339] In addition, the first selection unit CN3 refers to the second clustering information and determines whether there is other processing result information DA1 belonging to the same cluster as the identified processing result information DA1.

[0340] Then, based on the determination result, the first selection unit CN3 selects a processing unit 220 to be used for processing the substrate to be processed Wx from two or more processing units 220 that execute other steps S1 having the same processing content among a plurality of series of processes SQ.

[0341] For example, when the processing result information DA4 is shown to be "abnormal" by the evaluation information OT1 obtained from the first learning model 91, the first selection unit CN3 sets the processing unit 220 that executes another process S1 in which other processing result information DA1 belonging to the same cluster as the specified processing result information DA1 is obtained as a target not to be used.

[0342] Note that the processing result information F3 included in the third learning data 83 and the processing result information DA1 input to the third learning model 93 may be information before normalization.

[0343] Also, as shown in FIG. 12, in Embodiment 3 as well, similar to Embodiment 2, the storage unit MEM stores priority information ME6 for throughput priority. Here, a plurality of processing units 220 that execute processes S1, S5, and S11 included in the series of processes SQ are set as one set. In this case, there are a plurality of sets corresponding to the plurality of series of processes SQ. And the priority information ME6 of Embodiment 3 indicates the priority of use for the plurality of sets. The number of all the processing units 220 constituting the plurality of sets is a predetermined number. That is, in the priority information ME6, all of the predetermined number of processing units 220 are selected. For example, the priority information ME6 indicates a serial number assigned to the plurality of sets.

[0344] Next, with reference to FIGS. 9 and 21 to 24, the substrate processing method according to Embodiment 3 will be described. The substrate processing method according to Embodiment 3 is the same as the substrate processing method according to Embodiment 1 described with reference to FIG. 9. Hereinafter, the points in which the substrate processing method according to Embodiment 3 differs from the substrate processing method of Embodiment 1 will be mainly described.

[0345] FIGS. 21 and 22 are flowcharts showing the process S31 of FIG. 9 in Embodiment 3. As shown in FIGS. 21 and 22, the process of the process S31 according to Embodiment 3 includes processes S151 to S166.

[0346] In process S151, the preprocessing unit CN1 in FIG. 12 processes a plurality of measurement data ME2 to generate a plurality of sets of processing result information ME30.

[0347] Next, in step S152, the acquisition unit CN2 in FIG. 12 acquires a processing result information set ME30 by two or more processing units 220 with different processing contents in a series of steps SQ.

[0348] Next, in step S153, the first selection unit CN3 in FIG. 12 selects, based on the processing result information set ME30 by two or more processing units 220 with different processing contents, one or more processing units 220 to be used for processing each of the processing target substrates Wx from among two or more processing units 220 (specifically, a predetermined number of processing units 220).

[0349] Specifically, the first selection unit CN3 analyzes the processing result information set ME30 by an analysis algorithm, selects one or more processing units 220 to be used for processing each of the processing target substrates Wx from among two or more processing units 220 with different processing contents, and generates selection result information ME4.

[0350] FIG. 23 is a flowchart showing an example of the processing in step S153 of FIG. 21. As shown in FIG. 23, the processing in step S153 includes steps S181 to S185.

[0351] In step S181, the first selection unit CN3 inputs, as input information, the processing result information DA4 obtained in a predetermined step S13 (FIG. 20) among the processing result information DA1 to DA4 included in the processing result information set ME30 to the first learning model 91.

[0352] Next, in step S182, the first selection unit CN3 acquires, as output information, evaluation information OT1 indicating an evaluation of the processing result of the substrate Wp in a predetermined step S13 from the first learning model 91.

[0353] Next, in step S183, the first selection unit CN3 inputs the processing result information DA1 to DA4 included in the processing result information set ME30 to the second learning model 92 as input information.

[0354] Next, in step S184, the first selection unit CN3 acquires, as output information, first clustering information indicating the clustering result of the processing result information DA1 to DA4 from the second learning model 92.

[0355] Next, in step S185, based on the evaluation information OT1 and the first clustering information, the first selection unit CN3 selects, from among two or more processing units 220 whose processing contents are different in the series of steps SQ, that is, from among two or more processing units 220 that execute steps S1, S5, and S11 (FIG. 20) included in the series of steps SQ, one or more processing units 220 to be used for processing each of the processing target substrates Wx, and generates selection result information ME4. Then, the process returns to the routine shown in FIG. 21 and proceeds to step S154.

[0356] Steps S154 to S158 shown in FIG. 21 are the same as steps S54 to S58 shown in FIG. 10, respectively, and the description thereof is omitted.

[0357] In step S159, the first selection unit CN3 determines whether or not the processing in steps S152 to S158 has been completed for all of the plurality of sets of processing result information ME30 respectively corresponding to the plurality of series of steps SQ.

[0358] If a negative determination is made in step S159, the process proceeds to step S152.

[0359] On the other hand, if an affirmative determination is made in step S159, the process proceeds to step S160.

[0360] In step S160, the first selection unit CN3 assigns priorities to the plurality of selection result information ME4 respectively generated corresponding to the plurality of sets of processing result information ME30.

[0361] Next, in step S161, the first selection unit CN3 determines whether or not the processing based on all the analysis algorithms has been completed.

[0362] If a negative determination is made in step S161, the process proceeds to step S152. Then, in step S153 after step S152, the first selection unit CN3 analyzes the processing result information set ME30 using an analysis algorithm different from the previous analysis algorithm to select a processing unit 220.

[0363] On the other hand, if an affirmative determination is made in step S161, the process proceeds to step S162 in FIG. 22.

[0364] As shown in FIG. 22, in step S162, the first selection unit CN3 selects, from among two or more processing units 220, one or more processing units 220 to be used for processing the processing target substrate Wx based on the correlation relationship of two or more pieces of processing result information ME3 by two or more processing units 220 having the same processing content.

[0365] FIG. 24 is a flowchart showing an example of the process of step S162 in FIG. 22. As shown in FIG. 24, the process of step S162 includes steps S201 to S204.

[0366] In step S201, the first selection unit CN3 refers to the first clustering information and specifies, from among the processing result information DA1 to DA3 obtained in steps S1, S5, and S11 (FIG. 20) before a predetermined step S13 (FIG. 20), the processing result information belonging to the same cluster as the processing result information DA4 obtained in the predetermined step S13. Hereinafter, for simplicity, the case where the specified processing result information is the processing result information DA1 obtained in step S1 will be exemplified.

[0367] Next, in step S202, the first selection unit CN3 selects, from among a plurality of third learning models 93, the third learning model 93 corresponding to the step S1 from which the processing result information DA1 specified in step S201 was obtained.

[0368] Next, in step S203, the first selection unit CN3 inputs, as input information, a plurality of pieces of processing result information DA1 obtained in step S1, where the processing contents are the same among a plurality of sets of processes SQ, with respect to the third learning model 93 selected in step S202, and acquires second clustering information.

[0369] Next, in step S205, based on the second clustering information, the first selection unit CN3 selects a processing unit 220 to be used for processing the substrate to be processed Wx from two or more processing units 220 that execute step S1, where the processing contents are the same among a plurality of sets of processes SQ. Then, the process returns to the routine shown in FIG. 22 and proceeds to step S163.

[0370] As shown in FIG. 22, in step S163, the first selection unit CN3 updates each selection result information ME4 based on the result of step S162.

[0371] Next, in step S164, the first selection unit CN3 updates the priority order assigned to each selection result information ME4 based on the result of step S162.

[0372] Next, in step S165, the first selection unit CN3 determines a processing unit 220 for which the processed substrate W becomes the object of quality inspection based on each selection result information ME4.

[0373] Next, in step S166, the first selection unit CN3 notifies each selection result information ME4. This is the same as step S60 in FIG. 10. Then, the process returns to the main routine in FIG. 9 and proceeds to step S32.

[0374] Note that the "two or more processing units 220 with different processing contents" are not particularly limited. For example, two or more processing units 220 that execute two or more of steps S1 to S9 and S11 to S15 constituting the sets of processes SQ in FIGS. 6 and 7 may be used.

[0375] Next, with reference to FIG. 15, the first learning method by the first learning unit 61, the second learning method by the second learning unit 62, and the third learning method by the third learning unit 63 will be described.

[0376] The first learning method by the first learning unit 61 is the same as the learning method by the learning unit CN9 described with reference to FIG. 15. That is, in the description of FIG. 15, the learning method is read as the first learning method, the learning unit CN9 is read as the first learning unit 61, the learning data ME8 is read as the first learning data 81, the learning program ME7 is read as the first learning program 71, and the learning model ME9 is read as the first learning model 91.

[0377] The second learning method by the second learning unit 62 is the same as the learning method by the learning unit CN9 described with reference to FIG. 15. That is, in the description of FIG. 15, the learning method is read as the second learning method, the learning unit CN9 is read as the second learning unit 62, the learning data ME8 is read as the second learning data 82, the learning program ME7 is read as the second learning program 72, and the learning model ME9 is read as the second learning model 92.

[0378] In particular, each of the plurality of second learning data 82 includes two or more pieces of processing result information F2 respectively indicating the processing results of the learning target substrate Wn by two or more processing units 220 with different processing contents. The second learning model 92 inputs each of two or more pieces of processing result information DA1 to DA4 respectively indicating the processing results of the substrate Wp by two or more processing units 220 with different processing contents as input information, clusters the two or more pieces of processing result information DA1 to DA4, and outputs the first clustering information indicating the clustering result as output information.

[0379] In other words, the second learning model 92 causes the control device CM to function so as to cluster the processing result information DA1 to DA4 indicating the processing results of the substrate Wp. Specifically, the second learning model 92 causes the control device CM to function so as to input input information and output output information. The input information is two or more pieces of processing result information DA1 to DA4 respectively indicating the processing results of the substrate Wp by two or more processing units 220 with different processing contents. The output information is first clustering information indicating the result of clustering of two or more pieces of processing result information DA1 to DA4.

[0380] The third learning method by the third learning unit 63 is the same as the learning method by the learning unit CN9 described with reference to FIG. 15. That is, in the description of FIG. 15, the learning method is read as the third learning method, the learning unit CN9 is read as the third learning unit 63, the learning data ME8 is read as the third learning data 83, the learning program ME7 is read as the third learning program 73, and the learning model ME9 is read as the third learning model 93. Further, the third learning method by the third learning unit 63 is the same as the second learning method by the second learning unit 62 in that clustering is executed.

[0381] Next, with reference to FIGS. 25 to 28, the selection result information ME4 will be described with specific examples. Further, as two or more processing units 220 with different processing contents in the series of steps SQ, the processing unit PAHP

[11] in FIG. 3, the processing unit RT

[11] in FIG. 2, the processing unit PHP

[31] in FIG. 3, and the processing unit DV

[11] in FIG. 2 are taken as examples. As two or more other processing units 220 with different processing contents in another series of steps SQ, the processing unit PAHP

[12] , the processing unit RT

[12] , the processing unit PHP

[32] , and the processing unit DV

[12] are taken as examples. Further, as still two or more other processing units 220 with different processing contents in still another series of steps SQ, the processing unit PAHP

[13] , the processing unit RT

[11] , the processing unit PHP

[33] , and the processing unit DV

[13] are taken as examples.

[0382] That is, examples of the selection targets by the first selection unit CN3 include the processing units PAHP

[11] , RT

[11] , PHP

[31] , PAHP

[12] , RT

[12] , PHP

[32] , PAHP

[13] , RT

[11] , and PHP

[33] .

[0383] FIG. 25 is a diagram showing an example of the processing result information set ME30, the priority information ME6, the selection result information ME4, and the inspection target information ME5 according to Embodiment 3. In FIG. 25, the unused target is indicated by "NU".

[0384] As shown in FIG. 25, in Embodiment 3, as an example of the processing result information set ME30, the processing result information sets ME30a, ME30b, and ME30c are shown.

[0385] The processing result information set ME30a includes the contact angle map data M10, the film thickness map data M11, the temperature map data M12, and the pattern line width map data M13. The map data M10, M11, M12, and M13 respectively show the processing results of the substrate Wp after processing by the processing units PAHP

[11] , RT

[11] , PHP

[31] , and DV

[11] .

[0386] The processing result information set ME30b includes the contact angle map data M20, the film thickness map data M21, the temperature map data M22, and the pattern line width map data M23. The map data M20, M21, M22, and M23 respectively show the processing results of the substrate Wp after processing by the processing units PAHP

[12] , RT

[12] , PHP

[32] , and DV

[12] .

[0387] The processing result information set ME30c includes the contact angle map data M30, the film thickness map data M31, the temperature map data M32, and the pattern line width map data M33. The map data M30, M31, M32, and M33 respectively show the processing results of the substrate Wp after processing by the processing units PAHP

[13] , RT

[11] , PHP

[33] , and DV

[13] .

[0388] The contact angles represented by the contact angle map data M10, M20, and M30 indicate the processing result of the substrate Wp after the adhesion strengthening process in step S1, and indicate the contact angle with respect to the processing liquid for the antireflection film.

[0389] The film thickness represented by the film thickness map data M11, M21, and M31 indicates the processing result of the substrate Wp after the resist film formation process in step S5, and indicates the film thickness of the resist film.

[0390] The temperature represented by the temperature map data M12, M22, and M32 indicates the processing result of the substrate Wp after the third heat treatment in step S11 (after the heat treatment after exposure), and indicates the temperature of the substrate Wp.

[0391] The line width indicated by the pattern line width map data M13, M23, and M33 indicates the processing result of the substrate Wp after the development process in step S13, and indicates the line width of the resist pattern.

[0392] FIG. 26 is a diagram showing the contact angle map data M10, the film thickness map data M11, the temperature map data M12, and the pattern line width map data M13, which constitute the processing result information set ME30a of FIG. 25.

[0393] FIG. 27 is a diagram showing the contact angle map data M20, the film thickness map data M21, the temperature map data M22, and the pattern line width map data M23, which constitute the processing result information set ME30b of FIG. 25.

[0394] FIG. 28 is a diagram showing the contact angle map data M30, the film thickness map data M31, the temperature map data M32, and the pattern line width map data M33, which constitute the processing result information set ME30c of FIG. 25.

[0395] In FIGS. 26 to 28, for easy understanding, the map data M10 to M13, M20 to M23, and M30 to M33 before normalization by the pretreatment unit CN1 are shown.

[0396] In FIGS. 26 to 28, region G1 is indicated by dense diagonal lines slanting upward to the right. Region G2 is indicated by sparse diagonal lines slanting downward to the right. Region G3 is indicated by sparse diagonal lines slanting upward to the right. Region G4 is indicated by crossed diagonal lines. Region G5 is indicated by dots. Region G6 is indicated by dense diagonal lines slanting downward to the right. In FIGS. 26 to 28, region G1, region G2, region G3, region G4, region G5, and region G6 are described for easy understanding of the drawing. However, actually, in the contact angle map data M10, M20, and M30, the distribution of the contact angle is shown by gradation. Similarly, actually, the film thickness of the film thickness map data M11, M21, and M31, the temperature of the temperature map data M12, M22, and M32, and the line width of the pattern line width map data M13, M23, and M33 are also shown by gradation.

[0397] In the contact angle map data M10, M20, and M30, the contact angle is the smallest in region G1 and the largest in region G6. The contact angle increases in the order of regions G1, G2, G3, G4, G5, and G6 from region G1 toward region G6. Similarly, for the film thickness map data M11, M21, and M31, the film thickness increases in the order of regions G1, G2, G3, G4, G5, and G6 from region G1 toward region G6. Similarly, for the temperature map data M12, M22, and M32, the temperature increases in the order of regions G1, G2, G3, G4, G5, and G6 from region G1 toward region G6. Similarly, for the pattern line width map data M13, M23, and M33, the line width increases in the order of regions G1, G2, G3, G4, G5, and G6 from region G1 toward region G6.

[0398] Returning to FIG. 25, priority information C1 is shown as an example of the priority information ME6 in the case of throughput priority.

[0399] In the case of throughput priority, all the processing units to be selected, PAHP

[11] , RT

[11] , PHP

[31] , PAHP

[12] , RT

[12] , PHP

[32] , PAHP

[13] , RT

[11] , PHP

[33] , are used. And the priority information C1 indicates the sets of processing units PAHP

[11] , RT

[11] , PHP

[31] ; the sets of processing units PAHP

[12] , RT

[12] , PHP

[32] ; and the sets of processing units PAHP

[13] , RT

[11] , PHP

[33] in the order of decreasing priority of use.

[0400] Also, as an example of the selection result information ME4 in the case of quality priority, selection result information C2 is shown. The selection result information C2 is obtained based on the above-described first analysis algorithm AG1.

[0401] Regarding the selection result information C2, the pattern line width map data M13 of the processing result information set ME30a is indicated as "abnormal" by the evaluation information OT1 of the first learning model 91.

[0402] Also, as shown in FIG. 26, the temperature map data M12 is correlated with the pattern line width map data M13. In the example of FIG. 26, the temperature map data M12 has a negative correlation with the pattern line width map data M13. Therefore, the first clustering information by the second learning model 92 indicates that the temperature map data M12 belongs to the same cluster as the pattern line width map data M13. In this case, it can be estimated that the cause of the "abnormality" of the pattern line width map data M13 lies in the temperature map data M12. In other words, it can be estimated that the cause of the "abnormality" of the pattern line width map data M13 lies in the processing unit PHP

[31] from which the temperature map data M12 was obtained.

[0403] Therefore, as shown in FIG. 25, with respect to the processing result information set ME30a, in the selection result information C2, the first selection unit CN3 sets the processing unit PHP

[31] from which the temperature map data M12 was obtained as a non-use target, and selects the processing unit PAHP

[11] from which the contact angle map data M10 was obtained and the processing unit RT

[11] from which the film thickness map data M11 was obtained as the processing units for processing the substrate Wx to be processed.

[0404] Also, with respect to the selection result information C2, the pattern line width map data M23 of the processing result information set ME30b is indicated as "normal" by the evaluation information OT1 of the first learning model 91.

[0405] Furthermore, as shown in FIG. 27, none of the contact angle map data M20, the film thickness map data M21, and the temperature map data M22 has a correlation with the pattern line width map data M13. Therefore, the first clustering information by the second learning model 92 indicates that the contact angle map data M20, the film thickness map data M21, and the temperature map data M22 belong to a cluster different from the pattern line width map data M13.

[0406] And, as shown in FIG. 25, with respect to the processing result information set ME30b, in the selection result information C2, the first selection unit CN3 selects all the processing units PAHP

[12] , RT

[12] , and PHP

[32] as the processing units for processing the substrate Wx to be processed.

[0407] Furthermore, with respect to the selection result information C2, the pattern line width map data M33 of the processing result information set ME30c is indicated as "normal" by the evaluation information OT1 of the first learning model 91.

[0408] Also, as shown in FIG. 28, the film thickness map data M31 is correlated with the pattern line width map data M33. Therefore, the first clustering information by the second learning model 92 indicates that the film thickness map data M31 belongs to the same cluster as the pattern line width map data M33. In this case, it can be estimated that the distribution of the film thickness of the film thickness map data M31 has affected the distribution of the line width of the pattern line width map data M33. In other words, it can be estimated that the processing unit RT

[11] from which the film thickness map data M31 was obtained has affected the distribution of the line width of the pattern line width map data M33.

[0409] And, as shown in FIG. 25, regarding the processing result information set ME30c, in the selection result information C2, the first selection unit CN3 has selected all the processing units PAHP

[13] , RT

[11] , and PHP

[33] as the processing units for processing the processing target substrate Wx.

[0410] Also, according to the first analysis algorithm AG1, in the selection result information C2, the lowest priority is assigned to the set of the processing units PAHP

[11] and RT

[11] selected based on the processing result information set ME30a. Also, according to the first analysis algorithm AG1, a lower priority is assigned to the set of the processing units PAHP

[13] , RT

[11] , and PHP

[33] selected based on the processing result information set ME30c than to the set of the processing units PAHP

[12] , RT

[12] , and PHP

[32] selected based on the processing result information set ME30b. This is because in the processing result information set ME30c, the film thickness map data M31 belongs to the same cluster as the pattern line width map data M33.

[0411] Also, the selection result information C3 is shown as an example of the selection result information ME4 in the case of quality priority. The selection result information C3 is obtained based on the second analysis algorithm AG2 described above.

[0412] Regarding the selection result information C3, the pattern line width map data M13 of the processing result information set ME30a is indicated as "abnormal" by the evaluation information OT1 of the first learning model 91. In addition, the selection result information C3 obtained from the processing result information set ME30a is the same as the selection result information C2 obtained from the processing result information set ME30a.

[0413] Also, regarding the selection result information C3, the pattern line width map data M23 of the processing result information set ME30b is indicated as "normal" by the evaluation information OT1 of the first learning model 91.

[0414] And, as shown in FIG. 27, the contact angle map data M20 has specificity. Therefore, the first clustering information by the second learning model 92 indicates that the contact angle map data M20 belongs to the cluster labeled with "specificity". The processing unit PAHP

[12] that obtained the contact angle map data M20 having specificity can be estimated to highly likely affect the line width of the resist pattern in the future.

[0415] Therefore, as shown in FIG. 25, regarding the processing result information set ME30b, in the selection result information C3, the first selection unit CN3 sets the processing unit PAHP

[12] where the contact angle map data M20 was obtained as a non-use target, and selects the processing unit RT

[12] where the film thickness map data M21 was obtained and the processing unit PHP

[32] where the temperature map data M22 was obtained as the processing units for processing the processing target substrate Wx.

[0416] Furthermore, regarding the selection result information C3, the pattern line width map data M33 of the processing result information set ME30c is indicated as "normal" by the evaluation information OT1 of the first learning model 91.

[0417] And, regarding the processing result information set ME30c, in the selection result information C3, the first selection unit CN3 selects all the processing units PAHP

[13] , RT

[11] , PHP

[33] as the processing units for processing the processing target substrate Wx.

[0418] Also, according to the second analysis algorithm AG2, in the selection result information C3, the lowest priority is assigned to the pair of processing units PAHP

[11] and RT

[11] selected based on the processing result information set ME30a. Also, according to the second analysis algorithm AG2, the pair of processing units RT

[12] and PHP

[32] selected based on the processing result information set ME30b is assigned a lower priority than the pair of processing units PAHP

[13] , RT

[11] , and PHP

[33] selected based on the processing result information set ME30c. This is because the contact angle map data M20 of the processing result information set ME30b belongs to the cluster labeled with "specificity".

[0419] Note that the first selection unit CN3 may update the selection result information C2 by replacing at least one of the processing units PAHP

[12] , RT

[12] , and PHP

[32] selected in the selection result information C2 with another processing unit 220 having the same processing content with respect to, for example, the processing result information set ME30b. In this case, the other processing unit 220 has a better processing result of the substrate Wp than the processing unit to be replaced.

[0420] (Embodiment 4) Referring to FIG. 29, the substrate processing system SYS according to Embodiment 4 of the present invention will be described. Embodiment 4 is mainly different from Embodiment 1 in that the substrate processing system SYS according to Embodiment 4 has a selection device 400 for selecting a processing unit 220 outside the substrate processing device 100A. Hereinafter, the differences between Embodiment 4 and Embodiment 1 will be mainly described.

[0421] FIG. 29 is a diagram showing a substrate processing system SYS according to Embodiment 4 of the present invention. As shown in FIG. 29, the substrate processing system SYS includes a substrate processing apparatus 100A and a selection apparatus 400. The substrate processing apparatus 100A and the selection apparatus 400 communicate with each other via a network NW. The network NW includes, for example, the Internet, a LAN (Local Area Network), a public telephone network, and a short-range wireless network.

[0422] The configuration of the substrate processing apparatus 100A is the same as that of the substrate processing apparatus 100 according to Embodiment 1 described with reference to FIGS. 1 to 8. However, the substrate processing apparatus 100A does not include, for example, the acquisition unit CN2 and the first selection unit CN3 in FIG. 8. Further, the substrate processing apparatus 100A may not include the preprocessing unit CN1 in FIG. 8. Further, the substrate processing apparatus 100A may not store the measurement data ME2 and the processing result information ME3.

[0423] The selection apparatus 400 selects one or more processing units 220 from a plurality of processing units 220 that respectively process a plurality of substrates to be processed Wx. Specifically, the selection apparatus 400 includes a control unit 401, a storage unit 402, an input unit 403, a display unit 404, and a communication unit 405. The configurations of the control unit 401, the storage unit 402, the input unit 403, the display unit 404, and the communication unit 405 are the same as those of the control unit CNT, the storage unit MEM, the input unit IN, the display unit DP, and the communication unit TR in FIG. 8, respectively, and the description thereof will be omitted as appropriate.

[0424] The control unit 401 includes the acquisition unit CN2 and the first selection unit CN3 in FIG. 8.

[0425] The acquisition unit CN2 of the control unit 401 acquires a plurality of pieces of processing result information ME3 respectively indicating the processing results of a plurality of substrates Wp by a plurality of processing units 220. For example, the acquisition unit CN2 may acquire the processing result information ME3 from the substrate processing apparatus 100A via the communication unit 405 and the network NW, and store it in the storage unit 402. For example, the acquisition unit CN2 may acquire measurement data ME2 from the measurement unit 200 outside the substrate processing apparatus 100A and / or the measurement unit 200 inside the substrate processing apparatus 100A via the communication unit 405 and the network NW, and store the measurement data ME2 in the storage unit 402 as the processing result information ME3.

[0426] Note that the control unit 401 may include the preprocessing unit CN1 in FIG. 8. In this case, for example, the acquisition unit CN2 acquires the measurement data ME2 from the measurement unit 200 outside the substrate processing apparatus 100A and / or the measurement unit 200 inside the substrate processing apparatus 100A via the communication unit 405 and the network NW. Then, the preprocessing unit CN1 of the control unit 401 processes the measurement data ME2 to generate the processing result information ME3.

[0427] The first selection unit CN3 of the control unit 401 selects one or more processing units 220 to be used for processing each of the processing target substrates Wx from among the plurality of processing units 220 based on the plurality of pieces of processing result information ME3, and generates selection result information ME4. Then, the communication unit 405 transmits the selection result information ME4 to the substrate processing apparatus 100A via the network NW.

[0428] Therefore, the control unit CNT of the substrate processing apparatus 100A can control each processing unit 220 and each transfer mechanism 210 so that the processing target substrate Wx is processed by the processing unit 220 selected by the selection result information ME4. As a result, according to the fourth embodiment, even if the processing characteristics by the plurality of processing units 220 vary, the processing unit 220 with good processing results can be selected and used. Therefore, the uniformity of processing among the plurality of processing target substrates Wx can be improved.

[0429] In addition, the first selection unit CN3 generates inspection target information ME5 and transmits the inspection target information ME5 to the substrate processing apparatus 100A via the communication unit 405 and the network NW.

[0430] In addition, the acquisition unit CN2, the first selection unit CN3, and the preprocessing unit CN1 of the control unit 401 according to Embodiment 4 operate in the same manner as the acquisition unit CN2, the first selection unit CN3, and the preprocessing unit CN1 of the control unit CNT according to Embodiment 1, respectively. In addition, in Embodiment 4, it has the same effects as Embodiment 1.

[0431] (First Modification Example) With reference to FIG. 29, a substrate processing system SYS according to a first modification example of Embodiment 4 of the present invention will be described. The first modification example is mainly different from Embodiment 2 in that the substrate processing system SYS according to the first modification example has a selection device 400 that selects the processing unit 220 outside the substrate processing apparatus 100A. Hereinafter, the points in which the first modification example is different from Embodiment 2 and Embodiment 4 will be mainly described.

[0432] The configuration of the substrate processing apparatus 100A according to the first modification example is the same as the configuration of the substrate processing apparatus 100 according to Embodiment 2 described with reference to FIGS. 1 to 7 and FIG. 12. However, the substrate processing apparatus 100A does not include, for example, the acquisition unit CN2, the first selection unit CN3, and the learning unit CN9 in FIG. 12. Further, the substrate processing apparatus 100A may not include the preprocessing unit CN1 in FIG. 12. Further, the substrate processing apparatus 100A does not store the learning program ME7 and the learning data ME8 in FIG. 12. Furthermore, the substrate processing apparatus 100A may not store the measurement data ME2 and the processing result information ME3 in FIG. 12.

[0433] The control unit 401 according to the first modification example includes the acquisition unit CN2, the first selection unit CN3, and the learning unit CN9 in FIG. 12. Further, the control unit 401 may include the preprocessing unit CN1 in FIG. 12. Furthermore, the storage unit 402 stores the learning program ME7, the learning data ME8, and the learning model ME9 in FIG. 12. Also, the storage unit 402 stores the measurement data ME2 and the processing result information ME3 in FIG. 12, which is the same as in the fourth embodiment in this regard.

[0434] The first selection unit CN3 of the control unit 401 according to the first modification example selects one or more processing units 220 to be used for processing each of the processing target substrates Wx from among the plurality of processing units 220 based on a plurality of pieces of processing result information ME3, and generates selection result information ME4. Then, the communication unit 405 transmits the selection result information ME4 to the substrate processing apparatus 100A via the network NW.

[0435] As a result, in the first modification example, as in the fourth embodiment, in the substrate processing apparatus 100A, the uniformity of processing among the plurality of processing target substrates Wx can be improved.

[0436] In addition, the acquisition unit CN2, the first selection unit CN3, the learning unit CN9, and the preprocessing unit CN1 of the control unit 401 according to the first modification example operate in the same manner as the acquisition unit CN2, the first selection unit CN3, the learning unit CN9, and the preprocessing unit CN1 of the control unit CNT according to the second embodiment, respectively. In addition, in the first modification example, it has the same effects as in the second embodiment. Note that the selection device 400 can also be regarded as a "learning device".

[0437] Also, the communication unit 405 may transmit the learning model ME9 to the substrate processing apparatus 100A via the network NW. Note that the learning model ME9 may be stored in a removable medium and the learning model ME9 may be provided to the substrate processing apparatus 100A from the removable medium.

[0438] (Second Modification Example) Referring to FIG. 29, a substrate processing system SYS according to a second modification of Embodiment 4 of the present invention will be described. The second modification is mainly different from Embodiment 3 in that the substrate processing system SYS according to the second modification has a selection device 400 for selecting a processing unit 220 outside the substrate processing apparatus 100A. Hereinafter, the points in which the second modification is different from Embodiments 3 and 4 will be mainly described.

[0439] The configuration of the substrate processing apparatus 100A according to the second modification is the same as the configuration of the substrate processing apparatus 100 according to Embodiment 3 described with reference to FIGS. 1 to 7, 12, and 20. However, the substrate processing apparatus 100A does not include, for example, the acquisition unit CN2, the first selection unit CN3, and the learning unit CN9 in FIG. 12, or does not include the first learning unit 61, the second learning unit 62, and the third learning unit 63 in FIG. 20. Further, the substrate processing apparatus 100A may not include the preprocessing unit CN1 in FIG. 12. Further, the substrate processing apparatus 100A does not store the learning program ME7 and the learning data ME8 in FIG. 12, or does not store the first learning program 71, the second learning program 72, the third learning program 73, the first learning data 81, the second learning data 82, and the third learning data 83 in FIG. 20. Furthermore, the substrate processing apparatus 100A may not store the measurement data ME2 and the processing result information ME3 in FIG. 12, or may not store the processing result information set ME30 in FIG. 20.

[0440] The control unit 401 according to the second modification includes the acquisition unit CN2, the first selection unit CN3 in FIG. 12, the first learning unit 61, the second learning unit 62, and the third learning unit 63 in FIG. 20. Further, the control unit 401 may include the preprocessing unit CN1 in FIG. 12. Furthermore, the storage unit 402 stores the first learning program 71, the second learning program 72, the third learning program 73, the first learning data 81, the second learning data 82, the third learning data 83, the first learning model 91, the second learning model 92, and the third learning model 93 in FIG. 20. Further, the storage unit 402 stores the measurement data ME2 in FIG. 12 and the processing result information set ME30 in FIG. 20, which is the same as in Embodiment 4.

[0441] The first selection unit CN3 of the control unit 401 according to the second modification example selects one or more processing units 220 to be used for processing each of the processing target substrates Wx from among the plurality of processing units 220 based on the plurality of processing result information ME3, and generates selection result information ME4. Then, the communication unit 405 transmits the selection result information ME4 to the substrate processing apparatus 100A via the network NW.

[0442] As a result, in the second modification example, as in the fourth embodiment, in the substrate processing apparatus 100A, the uniformity of processing among the plurality of processing target substrates Wx can be improved.

[0443] In addition, the acquisition unit CN2, the first selection unit CN3, the first learning unit 61, the second learning unit 62, the third learning unit 63, and the preprocessing unit CN1 of the control unit 401 according to the second modification example each operate in the same manner as the acquisition unit CN2, the first selection unit CN3, the first learning unit 61, the second learning unit 62, the third learning unit 63, and the preprocessing unit CN1 of the control unit CNT according to the third embodiment. In addition, in the second modification example, it has the same effects as the third embodiment. Note that the selection device 400 can also be regarded as a "learning device".

[0444] Further, the communication unit 405 may transmit the first learning model 91, the second learning model 92, and the third learning model 93 to the substrate processing apparatus 100A via the network NW. Note that the first learning model 91, the second learning model 92, and the third learning model 93 may be stored in a removable medium, and the first learning model 91, the second learning model 92, and the third learning model 93 may be provided to the substrate processing apparatus 100A from the removable medium.

[0445] The embodiments of the present invention have been described above with reference to the drawings. However, the present invention is not limited to the above embodiments, and can be implemented in various forms without departing from the gist thereof. In addition, the plurality of components disclosed in the above embodiments can be modified as appropriate. For example, a component among all the components shown in a certain embodiment may be added to the components of another embodiment, or some of the components among all the components shown in a certain embodiment may be deleted from the embodiment.

[0446] In addition, for the purpose of facilitating the understanding of the invention, the drawings schematically show each component mainly. The thickness, length, number, interval, etc. of each illustrated component may be different from the actual ones for convenience in drawing creation. In addition, the configuration of each component shown in the above embodiment is an example and is not particularly limited. Needless to say, various changes can be made without substantially departing from the effects of the present invention.

Industrial Applicability

[0447] The present invention relates to a substrate processing apparatus, a substrate processing method, a selection apparatus, a selection method, a learning model generation method, and a learning model, and has industrial applicability.

Explanation of Reference Numerals

[0448] 61 First learning unit (learning unit) 62 Second learning unit (learning unit) 63 Third learning unit (learning unit) 91 First learning model (learning model) 92 Second learning model (learning model) 93 Third learning model (learning model) 100, 100A Substrate processing apparatus 200 Measurement unit 220 Processing unit 210 Conveying mechanism 400 Selection apparatus 401 Control unit 402 Storage unit AR, RT, DV, PAHP, PHP, CP, EEW processing unit CNT control unit CN1 preprocessing section CN2 acquisition section CN3 first selection section (selection section) CN4 analysis section CN5 adjustment section CN6 second selection section CN7 substrate path determination section CN8 substrate processing control section CN9 learning section MEM memory unit ME9 learning model

Claims

1. A plurality of processing units that each process a plurality of substrates to be processed, a transfer mechanism that transfers the substrates to be processed into and out of the processing units, and a control unit that controls the plurality of processing units and the transfer mechanism. The control unit controls the one or more processing units and the transfer mechanism so as to process each of the substrates to be processed by one or more processing units selected from among the plurality of processing units based on the processing results of a plurality of substrates by each of the plurality of processing units. The control unit includes a first selection unit that selects, from among the plurality of processing units, the one or more processing units to be used for processing each of the substrates to be processed based on a plurality of pieces of processing result information respectively indicating the processing results of the plurality of substrates by the plurality of processing units. Each of the plurality of pieces of processing result information indicates at least one of a contact angle of a processing liquid on the surface of the substrate, a numerical value based on the contact angle, and a cut width of an edge of the substrate. A substrate processing apparatus.

2. The first selection unit selects, from among the plurality of processing units, the one or more processing units to be used for processing each of the substrates to be processed with a priority order of use based on the plurality of pieces of processing result information. The substrate processing apparatus according to Claim 1.

3. Each of the plurality of pieces of processing result information further indicates at least one of a temperature during heat treatment on the surface of the substrate, a numerical value based on the temperature, a line width of a pattern on the surface of the substrate, a numerical value based on the line width, a number of collapses of a pattern on the surface of the substrate, and a numerical value based on the number of collapses. The substrate processing apparatus according to Claim 1 or 2.

4. The substrate processing apparatus according to Claim 3, further comprising a measurement unit that measures the contact angle, the temperature, the line width, the number of collapses, or the cut width.

5. The first selection unit determines, from among the plurality of processing units, a processing unit not to be used based on the plurality of pieces of processing result information. The substrate processing apparatus according to any one of Claims 1 to 4.

6. The control unit includes an analysis unit that analyzes the processing result information indicating the processing result of the substrate by the processing unit not to be used. ​ An adjustment unit that adjusts the processing unit not to be used based on the analysis result of the processing result information and returns the processing unit not to be used to the processing unit to be used The substrate processing apparatus according to claim 5, further comprising

7. A plurality of processing units that process a plurality of substrates to be processed respectively, A transfer mechanism that transfers the substrates to be processed into and out of the processing unit, A control unit that controls the plurality of processing units and the transfer mechanism Comprising The control unit controls the one or more processing units and the transfer mechanism so that each of the substrates to be processed is processed by one or more processing units selected based on the processing results of a plurality of substrates by each of the plurality of processing units among the plurality of processing units. The control unit selects, from among the plurality of processing units, one or more processing units to be used for processing each of the substrates to be processed based on a plurality of pieces of processing result information respectively indicating the processing results of the plurality of substrates by the plurality of processing units, and determines, from among the plurality of processing units, a processing unit not to be used based on the plurality of pieces of processing result information, a first selection unit; An analysis unit that analyzes the processing result information indicating the processing result of the substrate by the processing unit not to be used; Based on the analysis result of the processing result information, an adjustment unit that adjusts the processing unit not to be used and returns the processing unit not to be used to the processing unit to be used, Each of the plurality of pieces of processing result information indicates at least one of a contact angle with respect to a processing liquid on the surface of the substrate, a numerical value based on the contact angle, a temperature during heat treatment on the surface of the substrate, a numerical value based on the temperature, a line width of a pattern on the surface of the substrate, a numerical value based on the line width, a number of collapses of the pattern on the surface of the substrate, a numerical value based on the number of collapses, and a cut width of an edge of the substrate. Substrate processing apparatus.

8. A substrate processing method executed by a substrate processing apparatus including a plurality of processing units that process a plurality of substrates to be processed respectively and a transfer mechanism that transfers the substrates to be processed into and out of the processing unit, A step of selecting, from among the plurality of processing units, one or more processing units to be used for processing each of the substrates to be processed based on a plurality of pieces of processing result information respectively indicating the processing results of the plurality of substrates by the plurality of processing units; A step of controlling the one or more processing units and the transfer mechanism so that each of the substrates to be processed is processed by the one or more processing units selected based on the plurality of pieces of processing result information from among the plurality of processing units; A step of processing the substrate to be processed; including; Each of the plurality of pieces of processing result information indicates at least one of a contact angle of a processing liquid on the surface of the substrate, a numerical value based on the contact angle, and a cut width of an edge of the substrate. A substrate processing method.

9. In the step of selecting the processing unit, based on the plurality of pieces of processing result information, the one or more processing units to be used for processing each of the substrates to be processed are selected from among the plurality of processing units with a priority order of use. The substrate processing method according to claim 8.

10. Each of the plurality of pieces of processing result information further indicates at least one of a temperature during heat treatment on the surface of the substrate, a numerical value based on the temperature, a line width of a pattern on the surface of the substrate, a numerical value based on the line width, a number of collapses of a pattern on the surface of the substrate, and a numerical value based on the number of collapses. The substrate processing method according to claim 8 or 9.

11. The substrate processing method according to claim 10, further including a step of measuring the contact angle, the temperature, the line width, the number of collapses, or the cut width.

12. In the step of selecting the processing unit, based on the plurality of pieces of processing result information, a processing unit not to be used is determined from among the plurality of processing units. The substrate processing method according to any one of claims 8 to 11.

13. A step of analyzing the processing result information indicating the processing result of the substrate by the processing unit not to be used; Based on the analysis result of the processing result information, adjusting the processing unit not to be used and returning the processing unit not to be used to a processing unit to be used. The substrate processing method according to claim 12, further including.

Images