Plating device and plating device diagnosis method

Abstract

In the present invention, the operation status of a plating device is accurately ascertained.　Provided is a plating device for forming a plating film on a substrate, said plating device comprising: a substrate holder configured to hold the substrate; a plating tank configured to accommodate a plating solution together with the substrate holder; an anode disposed in the plating tank so as to face the substrate held by the substrate holder; a film thickness measurement unit configured to measure the film thickness of the plating film formed on the substrate at points on the substrate; and a control unit for controlling the plating device. The control unit includes: an imaging sub-unit configured to generate, on the basis of a film thickness measurement value at each of the points on the substrate, an image map representing a film thickness distribution on the substrate; a machine learning model trained to output an estimated status related to a plating process of the plating device when the image map is input; and a diagnosis sub-unit configured to diagnose the plating device on the basis of the estimated status output from the machine learning model.

Description

Plating apparatus and method for diagnosing plating apparatus

[0001] The present invention relates to a plating apparatus and a method for diagnosing a plating apparatus.

[0002] The plating apparatus includes a substrate holder that holds a substrate, a plating bath that stores a plating solution, and an anode disposed in the plating bath so as to face the substrate held by the substrate holder. In the plating apparatus, technological development has been carried out to improve the film thickness flatness of the plating formed on the substrate (see, for example, Patent Document 1).

[0003] Japanese Patent No. 7373684

[0004] In order to improve the film thickness flatness of the plating formed on the substrate, it is required to accurately grasp the operating status of the plating apparatus as a prerequisite.

[0005] According to one embodiment, there is provided a plating apparatus for forming a plating film on a substrate, the plating apparatus including: a substrate holder configured to hold the substrate; a plating bath configured to store a plating solution together with the substrate holder; an anode disposed in the plating bath so as to face the substrate held by the substrate holder; a film thickness measurement unit configured to measure the film thickness at each point on the substrate of the plating film formed on the substrate; a control unit for controlling the plating apparatus, the control unit including: an imaging subunit configured to generate an image map representing the film thickness distribution on the substrate based on the film thickness measurement values at each point on the substrate; a machine learning model trained to output an estimated status related to the plating process of the plating apparatus when the image map is input; and a diagnosis subunit configured to perform a diagnosis on the plating apparatus based on the estimated status output from the machine learning model.

[0006] This is an overall configuration diagram of a plating apparatus according to one embodiment of the present invention. This is a schematic side cross-sectional view of a plating module. This is a partial schematic cross-sectional view of a substrate holder that holds a substrate. This is an overall plan view of a substrate held by a substrate holder. This is a schematic diagram showing bumps formed on a substrate using a plating apparatus according to one embodiment of the present invention. This is a schematic diagram showing an example of the arrangement of bumps formed on a substrate. This is a configuration diagram of an exemplary system for implementing a method according to one embodiment of the present invention. This is an exemplary functional block diagram of a control unit according to one embodiment of the present invention. This is an exemplary functional block diagram of a system including a control unit according to one embodiment of the present invention. This is an exemplary functional block diagram of a system including a control unit according to one embodiment of the present invention. This is a diagram showing an example of an image map. This is a configuration diagram of an exemplary machine learning model according to one embodiment of the present invention.

[0007] Embodiments of the present invention will be described below with reference to the drawings. In the drawings described below, the same or corresponding components are denoted by the same reference numerals, and redundant descriptions are omitted.

[0008] Figure 1 is an overall configuration diagram of a plating apparatus 10 according to one embodiment of the present invention. As shown in Figure 1, the plating apparatus 10 includes two cassette tables 102, an aligner 104 that aligns the positions of orientation flats and notches on the substrate in a predetermined direction, and a spin rinse dryer 106 that dries the substrate after plating by rotating it at high speed. The cassette tables 102 are mounted on cassettes 100 containing substrates such as semiconductor wafers. Near the spin rinse dryer 106, a load / unload station 120 is provided where a substrate holder 30 is placed to load and unload the substrate. In the center of these units 102, 104, 106, and 120, a transport robot 122 is positioned to transport substrates between these units.

[0009] The load / unload station 120 is equipped with a flat mounting plate 152 that can slide laterally along the rail 150. Two substrate holders 30 are placed horizontally in parallel on this mounting plate 152. After a substrate is transferred between one substrate holder 30 and the transport robot 122, the mounting plate 152 slides laterally, and the substrate is transferred between the other substrate holder 30 and the transport robot 122.

[0010] The plating apparatus 10 further includes a stocker 124, a pre-wet module 126, a pre-soak module 128, a first rinse module 130a, a blow module 132, a second rinse module 130b, and a plating module 110. The stocker 124 stores and temporarily holds the substrate holder 30. In the pre-wet module 126, the substrate is immersed in pure water. In the pre-soak module 128, the oxide film on the surface of conductive layers such as seed layers formed on the surface of the substrate is etched off. In the first rinse module 130a, the substrate after pre-soaking is washed together with the substrate holder 30 in a cleaning solution (pure water, etc.). In the blow module 132, the liquid is removed from the substrate after washing. In the second rinse module 130b, the plated substrate is washed together with the substrate holder 30 in a cleaning solution. The load / unload station 120, stocker 124, pre-wet module 126, pre-soak module 128, first rinse module 130a, blow module 132, second rinse module 130b, and plating module 110 are arranged in this order.

[0011] The plating module 110 is configured, for example, by housing a plurality of plating tanks 114 inside an overflow tank 136. In the example shown in Figure 1, the plating module 110 has eight plating tanks 114. Each plating tank 114 is configured to house one substrate inside and immerse the substrate in the plating solution held inside to apply a plating such as copper plating to the surface of the substrate.

[0012] The plating apparatus 10 has a transport device 140, for example, employing a linear motor system, that is located to the side of each of these devices and transports the substrate holder 30 together with the substrate between these devices. This transport device 140 has a first transport device 142 and a second transport device 144. The first transport device 142 is configured to transport the substrate between the load / unload station 120, the stocker 124, the pre-wet module 126, the pre-soak module 128, the first rinse module 130a, and the blow module 132. The second transport device 144 is configured to transport the substrate between the first rinse module 130a, the second rinse module 130b, the blow module 132, and the plating module 110. The plating apparatus 10 may also consist only of the first transport device 142 without the second transport device 144.

[0013] On both sides of the overflow tank 136 are a paddle drive unit 160 and a paddle driven unit 162, which are located inside each plating tank 114 and drive paddles that act as stirring rods to agitate the plating solution inside the plating tank 114.

[0014] The plating apparatus 10 further includes a film thickness measuring unit 300 for measuring the film thickness of the plating film formed on the substrate, and a control unit 400 for performing various controls on each part of the plating apparatus 10 and analyzing various data related to the plating process in the plating apparatus 10. The film thickness measuring unit 300 may be built into or attached to the plating apparatus 10 as part of the plating apparatus 10, as shown in Figure 1, or it may be located away from the plating apparatus 10 as a separate, independent device. Similarly, the control unit 400 may be built into or attached to the plating apparatus 10 as part of the plating apparatus 10, as shown in Figure 1, or it may be located away from the plating apparatus 10 as a separate, independent device, and may be connected to the plating apparatus 10 and the film thickness measuring unit 300 in a manner that allows communication via a network such as a LAN (Local Area Network) or the Internet.

[0015] An example of a series of plating processes using this plating apparatus 10 will be described. First, a transport robot 122 takes one substrate from a cassette 100 mounted on a cassette table 102 and transports the substrate to an aligner 104. The aligner 104 aligns the positions of orientation flats and notches to a predetermined direction. The substrate, whose orientation has been aligned by the aligner 104, is then transported by the transport robot 122 to the load / unload station 120.

[0016] At the load / unload station 120, the two substrate holders 30 that were housed in the stocker 124 are simultaneously grasped by the first transport device 142 of the transport device 140 and transported to the load / unload station 120. The two substrate holders 30 are then simultaneously placed horizontally on the mounting plate 152 of the load / unload station 120. In this state, the transport robot 122 transports substrates to each substrate holder 30 and holds the transported substrates in the substrate holders 30.

[0017] Next, the substrate holders 30 holding the substrates are simultaneously gripped by the first transport device 142 of the transport device 140 and stored in the pre-wet module 126. Then, the substrate holders 30 holding the substrates processed in the pre-wet module 126 are transported by the first transport device 142 to the pre-soak module 128, where the oxide film on the substrates is etched. Subsequently, the substrate holders 30 holding these substrates are transported to the first rinse module 130a, where the surface of the substrates is washed with pure water stored in the first rinse module 130a.

[0018] The substrate holder 30, which holds the substrate after rinsing, is transported from the first rinsing module 130a to the plating module 110 by the second transport device 144 and placed in the plating tank 114 filled with plating solution. The second transport device 144 repeats the above procedure sequentially, placing the substrate holders 30 holding the substrates into each of the plating tanks 114 of the plating module 110 one after another.

[0019] In each plating tank 114, a plating current is supplied between the anode (not shown) inside the plating tank 114 and the substrate, and at the same time, the paddle drive unit 160 and the paddle driven unit 162 move the paddle back and forth parallel to the surface of the substrate, thereby plating the surface of the substrate.

[0020] After the plating is complete, the substrate holders 30 holding the plated substrates are simultaneously grasped by the second transport device 144 and transported to the second rinse module 130b, where they are immersed in the pure water contained in the second rinse module 130b to wash the surface of the substrates with pure water. Next, the substrate holders 30 are transported to the blow module 132 by the second transport device 144, where any water droplets adhering to the substrate holders 30 are removed by blowing air or the like. After that, the substrate holders 30 are transported to the load / unload station 120 by the first transport device 142.

[0021] At the load / unload station 120, the processed substrates are removed from the substrate holder 30 by the transport robot 122 and transported to the spin rinse dryer 106. The spin rinse dryer 106 dries the plated substrates by rotating them at high speed. The dried substrates are returned to the cassette 100 by the transport robot 122.

[0022] Subsequently, the film thickness measurement unit 300 measures the film thickness of the plating film formed on the substrate. The plating film thickness measurement data is provided to the control unit 400 for analysis.

[0023] Figure 2 is a schematic side cross-sectional view of the plating module 110 described above. As shown in the figure, the plating module 110 includes an anode holder 220 configured to hold an anode 221, a substrate holder 30 configured to hold a substrate W, a plating tank 114 containing a plating solution Q containing additives, and an overflow tank 136 that receives and discharges the plating solution Q that overflows from the plating tank 114. The plating tank 114 and the overflow tank 136 are separated by a partition wall 255. The anode holder 220 and the substrate holder 30 are housed inside the plating tank 114. As mentioned above, the substrate holder 30 holding the substrate W is transported by the second transport device 144 (see Figure 1) and housed in the plating tank 114.

[0024] Although only one plating tank 114 is shown in Figure 2, as mentioned above, the plating module 110 may have multiple plating tanks 114 with the same configuration as shown in Figure 2.

[0025] The anode 221 is electrically connected to the positive terminal 271 of the power supply 270 via an electrical terminal 223 provided on the anode holder 220. The substrate W is electrically connected to the negative terminal 272 of the power supply 270 via a power supply contact 242 and an electrical terminal 243 provided on the substrate holder 30. The power supply contact 242 of the substrate holder 30 is in contact with the peripheral edge of the substrate W. The power supply 270 is configured to supply plating current between the anode 221 connected to the positive terminal 271 and the substrate W connected to the negative terminal 272, and to measure the applied voltage between the positive terminal 271 and the negative terminal 272.

[0026] The anode holder 220, which holds the anode 221, and the substrate holder 30, which holds the substrate W, are immersed in the plating solution Q in the plating tank 114, and are positioned opposite each other so that the anode 221 and the plated surface W1 of the substrate W are substantially parallel. While the anode 221 and the substrate W are immersed in the plating solution Q in the plating tank 114, a plating current is supplied from the power supply 270. As a result, metal ions in the plating solution Q are reduced on the plated surface W1 of the substrate W, and a film is formed on the plated surface W1.

[0027] The anode holder 220 has an anode mask 225 for adjusting the electric field between the anode 221 and the substrate W. The anode mask 225 is a substantially plate-shaped member made of, for example, a dielectric material, and is provided on the front surface of the anode holder 220 (the surface facing the substrate holder 30). That is, the anode mask 225 is positioned between the anode 221 and the substrate holder 30. The anode mask 225 has a first opening 225a in its approximate center through which the current flowing between the anode 221 and the substrate W passes. The diameter of the opening 225a is preferably smaller than the diameter of the anode 221. The anode mask 225 may be configured to allow adjustment of the diameter of the opening 225a.

[0028] The plating module 110 further includes a regulation plate 230 for adjusting the electric field between the anode 221 and the substrate W. The regulation plate 230 is a substantially plate-shaped member made of, for example, a dielectric material, and is placed between the anode mask 225 and the substrate holder 30 (substrate W). The regulation plate 230 has a second opening 230a through which the current flowing between the anode 221 and the substrate W passes. The diameter of the opening 230a is preferably smaller than the diameter of the substrate W. The regulation plate 230 may be configured to allow adjustment of the diameter of the opening 230a.

[0029] Between the regulation plate 230 and the substrate holder 30, a paddle 235 is provided for stirring the plating solution Q near the plating surface W1 of the substrate W. The paddle 235 is a substantially rod-shaped member and is provided in the plating tank 114 so as to face vertically. One end of the paddle 235 is fixed to a paddle drive device 236. The operation of the paddle drive device 236 is controlled by a controller (not shown), and the paddle 235 is moved horizontally along the plating surface W1 of the substrate W by the paddle drive device 236. This stirs the plating solution Q.

[0030] The plating tank 114 has a plating solution supply port 256 for supplying the plating solution Q into the tank. The overflow tank 136 has a plating solution outlet 257 for discharging the plating solution Q that has overflowed from the plating tank 114. The plating solution supply port 256 is located at the bottom of the plating tank 114, and the plating solution outlet 257 is located at the bottom of the overflow tank 136.

[0031] When the plating solution Q is supplied to the plating tank 114 from the plating solution supply port 256, the plating solution Q overflows from the plating tank 114, passes over the partition wall 255, and flows into the overflow tank 136. The plating solution Q that flows into the overflow tank 136 is discharged from the plating solution outlet 257, and impurities are removed by a filter or the like in the plating solution circulation device 258. The plating solution Q from which impurities have been removed is supplied to the plating tank 114 via the plating solution supply port 256 by the plating solution circulation device 258.

[0032] Figure 3 is a schematic cross-sectional view of a substrate holder 30 holding a substrate W. Figure 4 is an overall plan view of the substrate W held by the substrate holder 30. As shown in Figure 3, a seed layer 301 is pre-formed on the surface of the substrate W, and a photoresist layer 302 is formed on the seed layer 301. The photoresist layer 302 has an opening 302a in the area where a plating film is to be formed. The substrate holder 30 includes a power supply contact 242 and a sealing member 241. The power supply contact 242 is a member made of a conductive material and electrically contacts the outer edge 62 of the substrate W. The sealing member 241 is made of a material such as resin and mechanically contacts the substrate W on the inner circumference side of the substrate W than the power supply contact 242. The sealing member 241 mechanically holds the substrate W and prevents the plating solution Q from penetrating the outer edge 62 of the substrate W and exposing the power supply contact 242 to the plating solution Q. As shown in Figure 4, the substrate holder 30 has a plurality of power supply contacts 242 along the outer circumference of the substrate W. In the example in Figure 4, the substrate holder 30 has 12 power supply contacts 242 arranged to be in contact with the outer edge 62 of the substrate W at equal intervals. Each power supply contact 242 is connected to the negative terminal 272 of the power supply 270 via electrical wiring (not shown) built into the substrate holder 30 (see Figure 2), and plating current flows to the substrate W through these power supply contacts 242.

[0033] Figure 5 is a schematic diagram showing bumps formed on a substrate W using a plating apparatus 10 according to one embodiment of the present invention. In the example of Figure 5 and the example of Figure 6 shown below, the mode in which the plating film is formed as bumps (or pads) which are cylindrical metal structures is described, but the present invention is not limited to the example of forming bumps on a substrate, and the mode in which a uniform plating film is formed on the entire surface of the substrate or a wide area of ​​the substrate surface is also included in the present invention. Note that Figure 5 shows only a part of the substrate W. Referring to Figure 5, a thin metal seed layer 501 is formed in advance on the surface of the substrate W, and during plating, this seed layer 501 (i.e., the surface of the substrate W) is supplied with power via the power supply contact 242 of the substrate holder 30. A photoresist layer 502 is formed on the seed layer 501, and the photoresist layer 502 has a circular opening 502a in the part where the bumps are to be formed. The substrate W on which the photoresist layer 502 is formed in this way is held in the substrate holder 30 and immersed in the plating solution Q in the plating tank 114 to perform plating. During plating, the portion of the substrate W surface other than the circular opening 502a of the photoresist layer 502 is shielded from the plating solution Q by the photoresist layer 502. As a result, the plating film grows only on the bottom surface of the opening 502a of the photoresist layer 502, forming bumps 503 on the substrate W. The photoresist layer 502 is removed after the plating process (see Figure 5, right).

[0034] Figure 6 is a schematic diagram showing an example of the arrangement of bumps formed on a substrate W. In this example, multiple vertical lines 602 and multiple horizontal lines 604 are provided on the substrate W as bump-free regions. Numerous bumps 503 are formed at predetermined intervals in the areas of each of these lines 602 and 604 other than the bump-free regions. The bumps 503 are present across the entire surface of the substrate W. In the plating process, it is required to eliminate or suppress variations in the height BH (see Figure 5) of each of these numerous bumps 503, that is, to form a plating film with a uniform film thickness distribution on the substrate W.

[0035] Figure 7 is a configuration diagram of an exemplary system 700 for implementing a method according to one embodiment of the present invention. The system 700 comprises a plating apparatus 10, a film thickness measuring unit 300, and a control unit 400. The plating apparatus 10, the film thickness measuring unit 300, and the control unit 400 are connected to each other so as to be able to communicate with each other via a network 710 such as a LAN (Local Area Network) or the Internet. Alternatively, the film thickness measuring unit 300 and the control unit 400 may be incorporated into the plating apparatus 10 as part of the configuration of the plating apparatus 10, as shown in Figure 1 above. The control unit 400 comprises a processor 402 and a memory 404. The memory 404 stores a program 406 for implementing a method according to one embodiment of the present invention. The processor 402 reads the program 406 from the memory 404 and executes it. This realizes the method according to one embodiment of the present invention.

[0036] Figure 8A is an exemplary functional block diagram of a control unit 400 according to one embodiment of the present invention. As shown in Figure 8A, the control unit 400 comprises an imaging subunit 410, a machine learning model 420, a diagnostic subunit 430, and a computation subunit 440. The functions of the imaging subunit 410, the machine learning model 420, the diagnostic subunit 430, and the computation subunit 440 are realized by the processor 402 reading and executing the corresponding programs 406 from the memory 404.

[0037] The imaging subunit 410 is configured to generate an image map representing the film thickness distribution on the substrate W based on the film thickness measurements at each point on the substrate W obtained from the film thickness measurement unit 300. For example, when a plating film is formed on the substrate W in the plating apparatus 10 and the plating process is completed, the substrate W is transported to the film thickness measurement unit 300. The film thickness measurement unit 300 measures the film thickness of the plating film at a number of measurement points on the substrate W and supplies the data set of measurement values ​​to the imaging subunit 410. The measurement points on the substrate W may be arranged at appropriate intervals, and the more measurement points there are, the higher the resolution image map that can be generated. In an embodiment in which bumps (see Figures 5 and 6) are formed on the substrate W, as an example, the measurement points may be set at the position of each bump (i.e., the film thickness measurement unit 300 measures the height BH of each bump). The imaging subunit 410 can generate an image map based on the film thickness measurements at a number of measurement points on the substrate W supplied from the film thickness measurement unit 300 in this way. The generation of the image map may include, for example, converting the film thickness values ​​to color values ​​(RGB values) or lightness values ​​according to a predetermined conversion formula or rule. Figure 9 shows an example of a generated image map.

[0038] The machine learning model 420 is configured to receive an image map generated by the imaging subunit 410 as input and to output an estimated status related to the plating process of the plating apparatus 10. The machine learning model 420 is pre-trained with a large set of training data, including various operating statuses of the plating apparatus 10 when it is plating a substrate, and image maps corresponding to each of those operating statuses. For example, the machine learning model 420 estimates the quality of power supply at a plurality of power supply contacts 242 of the substrate holder 30 based on an image map representing the film thickness distribution on the substrate W. In another example, the machine learning model 420 estimates the state of the aperture 225a of the anode mask 225 based on an image map representing the film thickness distribution on the substrate W. The machine learning model 420 may be configured to estimate both the quality of power supply at a plurality of power supply contacts 242 of the substrate holder 30 and the state of the aperture 225a of the anode mask 225 based on an image map representing the film thickness distribution on the substrate W. Furthermore, the machine learning model 420 may be configured to estimate any status of the plating apparatus 10 related to the thickness of the plating film on the substrate W, other than the quality of power supply to the power supply contact 242 and the state of the aperture 225a of the anode mask 225, based on an image map representing the film thickness distribution on the substrate W.

[0039] The diagnostic subunit 430 is configured to diagnose the plating apparatus 10 based on the estimated status output from the machine learning model 420 (for example, an estimate regarding the quality of power supply at the multiple power supply contacts 242 of the substrate holder 30). For example, based on the estimated status, the diagnostic subunit 430 determines that a problem such as a power supply failure has occurred at a specific power supply contact among the multiple power supply contacts 242. The diagnostic subunit 430 may also be configured to monitor the estimated status output from the machine learning model 420 over time and predict the occurrence of a failure or abnormality in the plating apparatus 10 based on its change over time.

[0040] The calculation subunit 440 is configured to simulate the film thickness at each point on the substrate W according to predetermined simulation conditions. The calculation subunit 440 is used to create training data for the machine learning model 420 through simulation. By using the calculation subunit 440, even if the amount of training data obtained by actually performing plating on the substrate W with the plating apparatus 10 is small, a variety of training data can be generated through simulation, and the effort required to collect a sufficient amount of training data necessary to train the machine learning model 420 can be reduced.

[0041] Figure 10 is a diagram illustrating the configuration of an exemplary machine learning model 420 according to one embodiment of the present invention. The machine learning model 420 is composed of a neural network comprising an input layer 422 having a plurality of input nodes 421, a hidden layer (intermediate layer) 424 consisting of one or more layers, each having a plurality of nodes 423, and an output layer 426 having a plurality of output nodes 425. Each node is connected to a plurality of nodes in the layer to which it belongs, with an intensity characterized by a weighting parameter. The input layer 422 receives an image map representing the film thickness distribution on the substrate W, generated by an imaging subunit 410. The output layer 426 outputs the estimated status of the plating apparatus 10. The weighting parameters between each node of the neural network are adjusted so that this estimated status matches the status of the plating apparatus 10 in the training data. The parameter adjustment of the neural network is performed repeatedly using a large number of sets of training data. This trains the machine learning model 420.

[0042] The training data for training the machine learning model 420 includes first training data based on actual plating processes on substrates W. That is, the first training data is collected by actually performing plating processes on multiple substrates in the plating apparatus 10. More specifically, plating is performed on one substrate by the plating apparatus 10. The operating status of the plating apparatus 10 is acquired during the plating process. The operating status of the plating apparatus 10 may be, for example, a status related to the quality of power supply at multiple power supply contacts 242 of the substrate holder 30. The operating status of the plating apparatus 10 may also include a status related to the state of the opening 225a of the anode mask 225 in the anode holder 220. Furthermore, the operating status of the plating apparatus 10 may include any other status of the plating apparatus 10 related to the thickness of the plating film on the substrate W. Once the plating process on one substrate is completed, the thickness measurement unit 300 measures the thickness of the film on that substrate, and an image map is generated by the imaging subunit 410 from the thickness measurement results. For this single substrate, the operating status of the plating apparatus 10 acquired during the plating process and the image map obtained from the imaging subunit 410 constitute one set of first training data. By repeating the same procedure for multiple substrates, multiple sets of first training data are collected. The process conditions for the plating process performed on multiple substrates may vary considerably. This makes it possible to create a wide variety of sets of first training data.

[0043] In addition to the first teacher data described above, the teacher data for training the machine learning model 420 may include second teacher data based on simulation. Specifically, the second teacher data is created based on the simulation results by the calculation subunit 440. The calculation subunit 440 calculates the plating film thickness at each point on the substrate according to predetermined simulation conditions that specify the operating status of the plating apparatus 10 (for example, the power supply amount from each power supply contact 242 of the substrate holder 30, the size of the opening 225a of the anode mask 225, etc.). An image map is generated in the imaging subunit 410 from the film thickness values calculated by the calculation subunit 440. The operating status of the plating apparatus 10 used in the simulation and the image map generated by the imaging subunit 410 from the simulation results constitute one set of second teacher data. By repeating the simulation while varying the simulation conditions, a plurality of sets of second teacher data are collected.

[0044] Thus, the machine learning model 420 is trained using teacher data including the first teacher data and the second teacher data. When an image map generated from the film thickness measurement value of the plated substrate is input to the trained machine learning model 420, the trained machine learning model 420 can estimate the status of the plating apparatus 10 when the plating process was performed on the substrate. For example, the trained machine learning model 420 can estimate whether the power supply is normal at the plurality of power supply contacts 242 of the substrate holder 30 when the plating apparatus 10 plated the substrate. Also, based on this estimation result, the diagnosis subunit 430 can determine, for example, that there is a problem such as a power supply failure in a specific power supply contact among the plurality of power supply contacts 242. Note that the estimation of the status of the plating apparatus 10 (i.e., the estimated status output from the machine learning model 420) may be based on one image map obtained from one plated substrate, or may be based on a plurality of image maps from a plurality of substrates plated in the same one of the plurality of plating tanks 114.

[0045] The machine learning model 420 may be further trained using additional training data. The additional training data may be, for example, features extracted from an image map. For example, as a feature, it may be possible to identify from the image map whether the film thickness distribution as a whole is concave or convex. Also, as a feature, the center position of the concave or convex surface when the film thickness distribution as a whole is concave or convex may be extracted from the image map. Furthermore, as a feature, the location of locally low or high areas in the film thickness distribution may be extracted from the image map. The additional training data may also include statistical data (e.g., average, maximum, minimum values ​​of film thickness, etc.) calculated from film thickness measurements obtained from the film thickness measurement unit 300 or film thickness values ​​calculated by the calculation subunit 440. The machine learning model 420 is configured so that these features and / or statistical data are input to the input layer 422. By configuring the machine learning model 420 in this way, the accuracy of the estimated status of the plating apparatus 10 output from the machine learning model 420 can be further improved.

[0046] The machine learning model 420 may be configured to output further setting parameters that suggest optimal process conditions in the plating apparatus 10. For example, in addition to outputting an estimated status regarding the quality of power supply to a particular power supply contact among the plurality of power supply contacts 242 of the substrate holder 30 when the power supply amount to that contact is reduced, the machine learning model 420 may also output setting parameters for the plating apparatus 10 that enable a better plating process. Such setting parameters may include, for example, an instruction to increase the power supply amount from the power supply contact 242 whose power supply amount is reduced. Alternatively, the setting parameters may include an instruction to adjust the opening 225a of the anode mask 225 so that the electric field in the plating solution Q increases around the power supply contact 242 whose power supply amount is reduced.

[0047] Note that the functional blocks of the control unit 400 shown in FIG. 8A are merely examples and do not limit the present invention. For example, as shown in FIG. 8B, the control unit 400 may include only the machine learning model 420 and the diagnosis sub-unit 430. The machine learning model 420 may receive an image map as an input from two imaging sub-units 410 (the imaging sub-unit 410 provided corresponding to the film thickness measurement unit 300 and the imaging sub-unit 410 provided corresponding to the calculation sub-unit 440) arranged outside the plating apparatus 10. Also, as shown in FIG. 8C, only the calculation sub-unit 440 and the imaging sub-unit 410 corresponding to the calculation sub-unit 440 may be arranged outside the plating apparatus 10. Further, as shown in FIG. 8D, the control unit 400 may include the imaging sub-unit 410, the machine learning model 420, and the diagnosis sub-unit 430, and the film thickness measurement unit 300 and the calculation sub-unit 440 may be arranged outside the plating apparatus 10. Note that in FIGS. 8B to 8D, the functions of each unit / sub-unit / model are the same as those in FIG. 8A.

[0048] As described above, embodiments of the present invention have been described based on several examples. However, the above-described embodiments of the invention are for facilitating understanding of the present invention and do not limit the present invention. The present invention can be changed and improved without departing from its gist, and it is a matter of course that equivalents of the present invention are included. Also, within the range capable of solving at least a part of the above-described problems or within the range achieving at least a part of the effects, any combination or omission of the constituent elements described in the claims and the specification is possible.

[0049] 10 Plating apparatus 300 Film thickness measurement unit 400 Control unit 402 Processor 404 Memory 406 Program 410 Imaging sub-unit 420 Machine learning model 430 Diagnosis sub-unit 440 Calculation sub-unit 700 System 710 Network

Claims

1. A plating apparatus for forming a plating film on a substrate, comprising: a substrate holder configured to hold the substrate; a plating tank configured to contain a plating solution together with the substrate holder; an anode disposed in the plating tank so as to face the substrate held by the substrate holder; and a control unit for controlling the plating apparatus, wherein the control unit comprises: a machine learning model trained to output an estimated status related to the plating process of the plating apparatus when an image map representing the film thickness distribution of the plating film formed on the substrate is input; and a diagnostic subunit configured to perform a diagnosis of the plating apparatus based on the estimated status output from the machine learning model.

2. A plating apparatus for forming a plating film on a substrate, comprising: a substrate holder configured to hold the substrate; a plating tank configured to contain a plating solution together with the substrate holder; an anode disposed in the plating tank so as to face the substrate held by the substrate holder; and a control unit for controlling the plating apparatus, wherein the control unit comprises: an imaging subunit configured to generate an image map representing the film thickness distribution on the substrate based on film thickness measurements at each point on the substrate of the plating film formed on the substrate; a machine learning model trained to output an estimated status related to the plating process of the plating apparatus when the image map is input; and a diagnostic subunit configured to perform a diagnosis of the plating apparatus based on the estimated status output from the machine learning model.

3. A plating apparatus for forming a plating film on a substrate, comprising: a substrate holder configured to hold the substrate; a plating tank configured to contain a plating solution together with the substrate holder; an anode disposed in the plating tank so as to face the substrate held by the substrate holder; a film thickness measuring unit configured to measure the film thickness of the plating film formed on the substrate at each point on the substrate; and a control unit for controlling the plating apparatus, wherein the control unit comprises: an imaging subunit configured to generate an image map representing the film thickness distribution on the substrate based on the film thickness measurement values ​​at each point on the substrate; a machine learning model trained to output an estimated status related to the plating process of the plating apparatus when the image map is input; and a diagnostic subunit configured to perform a diagnosis of the plating apparatus based on the estimated status output from the machine learning model.

4. The plating apparatus according to any one of claims 1 to 3, wherein the substrate holder comprises a plurality of power supply contacts for supplying power to the substrate, and the estimated status of the plating apparatus is related to the quality of power supply at the plurality of power supply contacts of the substrate holder.

5. The plating apparatus according to claim 4, further comprising an anode mask positioned near the anode, having an opening for adjusting the electric field in the plating solution within the plating tank, wherein the estimated status of the plating apparatus is related to the state of the opening of the anode mask.

6. The plating apparatus according to any one of claims 1 to 3, wherein the machine learning model is trained using first training data based on actual plating processes on the substrate, the first training data includes the actual operating status of the plating apparatus during the plating process and the image map generated based on the film thickness measurement of the plated substrate.

7. The plating apparatus according to claim 6, wherein the control unit further comprises a calculation subunit configured to simulate film thickness values ​​at each point on the substrate according to predetermined simulation conditions, the imaging subunit further configured to generate an image map based on the film thickness values ​​from the calculation subunit, and the machine learning model is further trained using second training data based on the simulation, the second training data including the operating status of the plating apparatus assumed in the simulation and the image map generated based on the simulated film thickness values.

8. The plating apparatus according to claim 7, wherein the first and second training data further include features extracted from the image map.

9. The plating apparatus according to claim 8, wherein the feature quantity includes at least one of the following: (i) whether the film thickness distribution is concave or convex as a whole; (ii) if the film thickness distribution is concave or convex as a whole, the central position of the concave or convex; and (iii) the position of a locally low or high area in the film thickness distribution.

10. The plating apparatus according to claim 7, wherein the first and second training data further include statistical data calculated from the film thickness measurement or the simulated film thickness value.

11. The plating apparatus according to any one of claims 1 to 3, wherein the diagnostic subunit is further configured to predict the occurrence of a failure or abnormality in the plating apparatus based on the time change of the estimated status output from the machine learning model.

12. The plating apparatus according to claim 11, wherein the plating apparatus comprises a plurality of plating tanks, and the estimated status is the output from the machine learning model to the image maps obtained from each of a plurality of substrates processed in the same plating tank among the plurality of plating tanks.

13. The plating apparatus according to any one of claims 1 to 3, wherein the machine learning model is trained to further output setting parameters of the plating apparatus that suggest optimal process conditions in the plating apparatus.

14. A method for diagnosing a plating apparatus that forms a plating film on a substrate, comprising: a step of obtaining a measurement of the film thickness at each point on the substrate of the plating film formed on the substrate from a film thickness measuring unit; a step of generating an image map representing the film thickness distribution on the substrate based on the measurement of the film thickness at each point on the substrate; a step of obtaining an estimated status of the plating apparatus from the image map using a machine learning model, wherein the machine learning model is trained to output the estimated status related to the plating process of the plating apparatus when the image map is input; and a step of performing a diagnosis of the plating apparatus based on the estimated status from the machine learning model.

15. The method for diagnosing a plating apparatus according to claim 14, wherein the plating apparatus comprises a plurality of plating tanks, and the estimated status is the output from the machine learning model to the image maps obtained from a plurality of substrates processed in the same plating tank among the plurality of plating tanks.

Images