Method for controlling a plating apparatus and a plating apparatus

Abstract

In a plating apparatus equipped with multiple plating modules, it is required to form a high-quality plating film by performing the plating process using the appropriate plating module. [Solution] A method for controlling a plating apparatus having a plurality of plating modules is provided, comprising the steps of: acquiring plating film thickness measurement data for a plurality of substrates plated by the plurality of plating modules; determining the quality of each of the plurality of plating modules based on the plating film thickness measurement data; and controlling the plating process in the plating apparatus based on the quality of each of the plating modules.

Description

Technical Field

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

Background Art

[0002] In semiconductor manufacturing apparatuses such as plating apparatuses, various types of substrates are processed from the previous process to the subsequent process. As the process moves to the subsequent process, the manufacturing cost of the substrate accumulates and becomes expensive. Also, depending on the product, there are cases where a substrate that is originally expensive is processed. The more expensive the substrate is, generally, a higher-performance process is required. Also, if scrap occurs due to equipment trouble or the like, the amount of damage becomes larger.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a plating apparatus including a plurality of plating modules, it is required to form a high-quality plating film by performing plating processing using an appropriate plating module.

Means for Solving the Problems

[0005] According to one embodiment, there is provided a method for controlling a plating apparatus including a plurality of plating modules, the method including: obtaining plating film thickness measurement data for a plurality of substrates plated by the plurality of plating modules; determining the goodness of each plating module in the plurality of plating modules based on the plating film thickness measurement data; and controlling a plating process in the plating apparatus based on the goodness of each plating module. [Brief explanation of the drawing]

[0006] [Figure 1] This is an overall configuration diagram of a plating apparatus according to one embodiment of the present invention. [Figure 2] This is a schematic side cross-sectional view of one plating module of a plating unit in one embodiment of the present invention. [Figure 3] This is a diagram illustrating the configuration of an exemplary system for implementing a method relating to one embodiment of the present invention. [Figure 4] This is a flowchart showing the operation of a system for carrying out a method according to one embodiment of the present invention. [Figure 5] This figure shows the configuration of an exemplary learning model used in implementing the method according to this embodiment. [Figure 6] This is a flowchart showing the operation of a system for carrying out a method according to another embodiment of the present invention. [Figure 7] This is an example of a database for storing the quality rating of each substrate type and each plating module in one embodiment of the present invention. [Figure 8] This is a flowchart showing the operation of a system for carrying out yet another embodiment of the present invention. [Figure 9] This figure shows the configuration of an exemplary learning model used in implementing the method according to this embodiment. [Modes for carrying out the 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 100 according to one embodiment of the present invention. The plating apparatus 100 includes a load / unload unit 110 for loading a substrate into a substrate holder (not shown) or unloading a substrate from a substrate holder, and a processing unit 120 for processing the substrate. The processing unit 120 further includes a pre-processing / post-processing unit 120A for pre-processing and post-processing the substrate, and a plating processing unit 120B for performing plating on the substrate.

[0009] The load / unload unit 110 includes a handling stage 26, a substrate transport device 27, a fixing station 29, and a cleaning unit 50a. As an example, in this embodiment, the load / unload unit 110 has two handling stages 26: a loading handling stage 26A for handling substrates before processing, and an unloading handling stage 26B for handling substrates after processing. In this embodiment, the loading handling stage 26A and the unloading handling stage 26B have the same configuration and are arranged 180° apart from each other. Note that the handling stages 26 are not limited to those provided with loading and unloading handling stages 26A and 26B, and may be used without distinction between loading and unloading. Also, in this embodiment, the load / unload unit 110 has two fixing stations 29. The two fixing stations 29 have the same mechanism, and the one that is not in use (not handling substrates) is used. Furthermore, depending on the available space in the plating apparatus 100, one or more of the handling stage 26 and fixing station 29 may be provided.

[0010] 26 (a loading handling stage 26A) receives substrates from multiple (three in Figure 1 as an example) cassette tables 25 via a robot 24. Each cassette table 25 is equipped with a cassette 25a in which the substrates are stored. The cassette is, for example, a FOUP. The handling stage 26 is configured to adjust (align) the position and orientation of the placed substrates. Between the handling stage 26 and the fixing station 29 is a substrate transport device 27 that transports the substrates between them. The substrate transport device 27 is configured to transport the substrates between the handling stage 26, the fixing station 29, and the cleaning unit 50a. A stocker 30 for storing substrate holders is also provided near the fixing station 29.

[0011] The cleaning unit 50a has a spin rinse dryer 50 that cleans the substrate after plating and dries it by high-speed rotation. The substrate transport device 27 is configured to transport the substrate after plating to the spin rinse dryer 50 and remove the cleaned and dried substrate from the spin rinse dryer 50. The cleaned and dried substrate is then passed by the substrate transport device 27 to the handling stage 26 (handling stage 26B for unloading) and returned to the cassette 25a via the robot 24.

[0012] The pre-treatment / post-treatment unit 120A includes a pre-wet tank 32, a pre-soak tank 33, a pre-rinse tank 34, a blow tank 35, and a rinse tank 36. In the pre-wet tank 32, the substrate is immersed in pure water. In the pre-soak tank 33, 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 pre-rinse tank 34, the substrate after pre-soaking is washed with a cleaning solution (pure water, etc.) along with the substrate holder. In the blow tank 35, the substrate is drained of the liquid after washing. In the rinse tank 36, the substrate after plating is washed with a cleaning solution along with the substrate holder. Note that the configuration of this pre-treatment / post-treatment unit 120A is just one example, and plating The pre-processing / post-processing unit 120A of the apparatus 100 is not limited to this configuration, and other configurations can be adopted.

[0013] The plating unit 120B is configured, for example, by housing multiple plating tanks 39 inside an overflow tank 38. Each plating tank 39 houses one substrate inside and is configured to immerse the substrate in a plating solution held inside to apply a plating such as copper plating to the substrate surface.

[0014] The plating apparatus 100 has a transporter 37, for example, employing a linear motor system, which is located to the side of the pre-treatment / post-treatment unit 120A and the plating unit 120B and transports the substrate holder together with the substrate. This transporter 37 is configured to transport the substrate holder between the fixing station 29, the stocker 30, the pre-wet tank 32, the pre-soak tank 33, the pre-rinse tank 34, the blow tank 35, the rinse tank 36, and the plating tank 39.

[0015] The plating apparatus 100 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 100 and analyzing various data related to the plating process in the plating apparatus 100. The film thickness measuring unit 300 may be built into or attached to the plating apparatus 100 as part of the plating apparatus 100, as shown in Figure 1, or it may be located away from the plating apparatus 100 as a separate, independent device. Similarly, the control unit 400 may be built into or attached to the plating apparatus 100 as part of the plating apparatus 100, as shown in Figure 1, or it may be located away from the plating apparatus 100 as a separate, independent device, and may be connected to the plating apparatus 100 and the film thickness measuring unit 300 in a communicative manner via a network such as a LAN (Local Area Network) or the Internet.

[0016] An example of a series of plating processes by this plating apparatus 100 will be described. First, a substrate is taken out one by one from the cassette 25a mounted on the cassette table 25 by the robot 24, and the substrate is transported to the handling stage 26 (the handling stage 26A for loading). The handling stage 26 aligns the position and orientation of the transported substrate to a predetermined position and orientation. The substrate whose position and orientation have been adjusted by this handling stage 26 is transported to the fixing station 29 by the substrate transport device 27.

[0017] On the other hand, the substrate holder stored in the stocker 30 is transported to the fixing station 29 by the transporter 37 and horizontally placed on the fixing station 29. Then, the substrate transported by the substrate transport device 27 is placed on the substrate holder in this state, and the substrate and the substrate holder are connected.

[0018] Next, the substrate holder holding the substrate is gripped by the transporter 37 and stored in the pre-wet tank 32. Next, the substrate holder holding the substrate processed in the pre-wet tank 32 is transported to the pre-soak tank 33 by the transporter 37, and the oxide film on the substrate is etched in the pre-soak tank 33. Subsequently, the substrate holder holding this substrate is transported to the pre-rinse tank 34, and the surface of the substrate is washed with pure water stored in this pre-rinse tank 34.

[0019] The substrate holder holding the substrate after the washing is completed is transported from the pre-rinse tank 34 to the plating processing unit 120B by the transporter 37 and stored in the plating tank 39 filled with the plating solution. The transporter 37 sequentially repeats the above procedure and stores the substrate holder holding the substrate in each plating tank 39 of the plating processing unit 120B.

[0020] In each plating tank 39, plating is performed on the surface of the substrate by applying a plating voltage between the anode (not shown) in the plating tank 39 and the substrate.

[0021] [[ID=,19]] After the plating is complete, the substrate holder holding the plated substrate is grasped by the transporter 37 and transported to the rinsing tank 36, where it is immersed in the pure water contained in the rinsing tank 36 to wash the surface of the substrate with pure water. Next, the substrate holder is transported by the transporter 37 to the blow tank 35, where any water droplets adhering to the substrate holder are removed by blowing air or the like. After that, the substrate holder is transported by the transporter 37 to the fixing station 29.

[0022] At the fixing station 29, the processed substrates are removed from the substrate holder by the substrate transport device 27 and transported to the spin rinse dryer 50 of the cleaning unit 50a. The spin rinse dryer 50 cleans the plated substrates and dries them by high-speed rotation. The dried substrates are then passed by the substrate transport device 27 to the handling stage 26 (handling stage 26B for unloading) and returned to the cassette 25a via the robot 24.

[0023] Subsequently, the film thickness of the plating film formed on the substrate is measured in the film thickness measurement unit 300. The plating film thickness measurement data is provided to the control unit 400 for analysis.

[0024] Figure 2 is a schematic side cross-sectional view of one plating module 200 in the plating processing unit 120B described above. As shown in the figure, the plating module 200 includes an anode holder 220 configured to hold an anode 221, a substrate holder 240 configured to hold a substrate W, a plating tank 39 containing a plating solution Q containing additives, and an overflow tank 38 that receives and discharges the plating solution Q that overflows from the plating tank 39. The plating tank 39 and the overflow tank 38 are separated by a partition wall 255. The anode holder 220 and the substrate holder 240 are housed inside the plating tank 39. As mentioned above, the substrate holder 240 holding the substrate W is transported by a transporter 37 (see Figure 1) and housed in the plating tank 39.

[0025] Although Figure 2 shows one plating module 200, as mentioned above, the plating processing unit 120B of the plating apparatus 100 may be equipped with multiple plating modules 200 having the same configuration as shown in Figure 2.

[0026] 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 240. The power supply contact 242 of the substrate holder 240 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.

[0027] The anode holder 220, which holds the anode 221, and the substrate holder 240, which holds the substrate W, are immersed in the plating solution Q in the plating tank 39, 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 39, 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.

[0028] The anode holder 220 adjusts the electric field between the anode 221 and the substrate W. The anode mask 225 is provided. 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 240). That is, the anode mask 225 is positioned between the anode 221 and the substrate holder 240. 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.

[0029] The plating module 200 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 240 (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.

[0030] A paddle (not shown) may be provided between the regulation plate 230 and the substrate holder 240 for stirring the plating solution Q near the plating surface W1 of the substrate W. The paddle is a substantially rod-shaped member and stirs the plating solution Q by moving horizontally along the plating surface W1 of the substrate W.

[0031] The plating tank 39 has a plating solution supply port 256 for supplying the plating solution Q into the tank. The overflow tank 38 has a plating solution outlet 257 for discharging the plating solution Q that has overflowed from the plating tank 39. The plating solution supply port 256 is located at the bottom of the plating tank 39, and the plating solution outlet 257 is located at the bottom of the overflow tank 38.

[0032] When the plating solution Q is supplied to the plating tank 39 from the plating solution supply port 256, the plating solution Q overflows from the plating tank 39 and flows over the partition wall 255 into the overflow tank 38. The plating solution Q that flows into the overflow tank 38 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 39 via the plating solution supply port 256 by the plating solution circulation device 258. The plating solution circulation device 258 may also be equipped with a plating solution analyzer 259 for measuring the temperature of the plating solution Q, the flow rate (amount supplied per unit time from the plating solution supply port 256 to the plating tank 39), the concentration of each chemical component contained in the plating solution Q, etc.

[0033] Figure 3 is a diagram of an exemplary system 10 for implementing a method according to one embodiment of the present invention. The system 10 comprises a plating apparatus 100, a film thickness measuring unit 300, and a control unit 400. The plating apparatus 100 is the plating apparatus described with reference to Figure 1. The plating apparatus 100, 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 500 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 100 as part of the configuration of the plating apparatus 100, as shown in Figure 1 above. The control unit 400 comprises a processor 420 and a memory 440. The memory 440 stores a program 460 (computer executable instructions) for implementing a method according to one embodiment of the present invention. The processor 420 reads the program 460 from the memory 440 and executes it. This realizes the method according to one embodiment of the present invention.

[0034] <First Embodiment> Figure 4 shows the operation of system 10 for carrying out a method according to one embodiment of the present invention. This is a flowchart. The processing of each step in the flowchart of Figure 4 is performed by the processor 420 of the control unit 400 in the system 10. The method according to the embodiment of Figure 4 starts in step 402 while the plating apparatus 100 is in operation.

[0035] First, in step 402, the processor 420 acquires plating film thickness measurement data for multiple substrates that have been plated by multiple plating modules 200 in the plating apparatus 100. For example, a large number of substrates are processed in the plating apparatus 100. Each substrate is plated by one of the multiple plating modules 200 according to a predetermined recipe. For example, one group of substrates is plated by the first plating module of the multiple plating modules 200, and another group of substrates is plated by the second plating module of the multiple plating modules 200. The same applies to the third plating module, the fourth plating module, and so on. After being plated by one of the plating modules 200 in the plating apparatus 100, each substrate is sent to the film thickness measurement unit 300, where the film thickness of the plating film formed by the plating process is measured. The film thickness measurement may include, for example, measuring the film thickness of the plating film at a number of measurement points on the plated surface W1 of each substrate, preferably at a number of measurement points covering the entire plated surface W1. The data obtained from the film thickness measurement of each substrate by the film thickness measurement unit 300 (hereinafter also referred to as plating film thickness measurement data, or simply film thickness measurement data) is sent to the control unit 400 and acquired by the processor 420. For each plating module 200 of the plating apparatus 100, plating film thickness measurement data is acquired for one or more substrates processed by each plating module 200. The plating film thickness measurement data may be temporarily or permanently stored in the memory 440 of the control unit 400.

[0036] Next, in step 404, the processor 420 determines the quality of each of the multiple plating modules 200 of the plating apparatus 100 based on the plating film thickness measurement data acquired in step 402. The quality of a plating module 200 is an indicator of how capable it is to form a high-quality plating film. The quality of the plating film may be, but is not limited to, the difference between the target film thickness value of the plating film and the actual film thickness value of the formed plating film (i.e., whether it is possible to form a plating film that matches the target film thickness value) or the uniformity of the plating film within the substrate surface (i.e., whether it is possible to form a flat plating film). As described above, in step 402, plating film thickness measurement data is acquired for each of the multiple plating modules 200 of the plating apparatus 100, and in step 404, the processor 420 uses the plating film thickness measurement data for each plating module 200 to determine the quality of each plating module 200.

[0037] The quality of the plating module 200 may be determined, for example, based on a statistical analysis of the plating film thickness measurement data. The processor 420 can calculate one or more statistical values ​​of various kinds from the plating film thickness measurement data and determine the quality of each plating module 200 based on the calculated statistical values. The statistical values ​​may be, but are not limited to, the average value of the in-plane uniformity of the plating film thickness across multiple substrates, or the average value of the error of the plating film thickness from the target film thickness value across multiple substrates. For example, for each plating module 200, the processor 420 can calculate the in-plane uniformity of the plating film thickness for each substrate processed by the plating module 200 from the respective plating film thickness measurement data, and calculate the average value of the in-plane uniformity of the plating film thickness for each of these substrates. For each plating module 200, the processor 420 determines the quality of the plating module 200 based on the average value of the in-plane uniformity of the plating film thickness calculated in this way, and / or based on the average value of the error of the plating film thickness from the target film thickness value calculated similarly. Instead of the average values ​​described above, statistical values ​​such as the maximum value, minimum value, or variance may be used. Quality is, for example, These can be given as numerical values ​​between 0 and 100, or as signs such as A, B, and C. Appropriate methods can be used to convert or assign the calculated statistical values ​​(e.g., the mean) to these scores, and the details will not be explained here.

[0038] In another embodiment, the quality of the plating module 200 may be determined using a machine learning-trained model. Figure 5 shows the configuration of an exemplary machine learning model 480 used in implementing the method according to this embodiment. For example, the machine learning model 480 may be constructed within the control unit 400 by the processor 420 reading and executing a program 460 stored in the memory 440 of the control unit 400. The machine learning model 480 is configured to determine the quality of each plating module 200 in the plating apparatus 100. The machine learning model 480 is trained using a large amount of training data so that it can correctly determine the quality of the plating module 200.

[0039] As shown in Figure 5, the exemplary learning model 480 is comprised of a neural network 487 comprising an input layer 482 having multiple input nodes 481, one or more intermediate layers 484 each having multiple nodes 483, and an output layer 486 having one or more output nodes 485. Each node is connected to multiple nodes in adjacent layers to the layer to which it belongs, with an intensity characterized by weighting parameters. One or more types of data correlated with the quality of the plating module 200 are input to the multiple input nodes 481 of the input layer 482. An estimated value for the quality of the plating module 200 is output from the output node 485 of the output layer 486, depending on the data input to the input nodes 481. The weighting parameters between each node of the neural network 487 are adjusted so that this estimated value matches a predetermined ground truth label. The parameter adjustment of the neural network 487 is repeated using many sets of training data. This trains the learning model 480.

[0040] The input node 481 of the learning model 480 receives, as data correlated with the quality of the plating module 200, at least a target value for the plating film thickness and plating film thickness measurement data for a substrate actually plated by the plating module 200. The target value for the plating film thickness (hereinafter referred to as the target film thickness value) may include, for example, a target value for the plating film thickness at a predetermined reference point on the substrate, a target value for the average plating film thickness across the substrate surface, or a target value for the uniformity of the plating film thickness across the substrate surface. For example, after such a target film thickness value is set in advance by the operator of the plating apparatus 100, a substrate is actually plated in one of the plating modules 200 of the plating apparatus 100, and plating film thickness measurement data for that substrate is obtained from the film thickness measurement unit 300. Furthermore, this plating film thickness measurement data is evaluated by the operator of the plating apparatus 100, and a correct label for quality is created by the operator for the plating module 200 that processed the substrate. The learning model 480 is trained using these target film thickness values, plating film thickness measurement data, and correct label as a set of training data. Specifically, the target film thickness value and plating film thickness measurement data are input to the input node 481, and the weighting parameters between nodes of the neural network 487 are adjusted based on the estimated quality value output from the output node 485 and the correct label. By performing similar parameter adjustments using a large number of training data sets, a learning model 480 capable of accurately determining the quality of the plating module 200 is completed.

[0041] In this embodiment, in step 404, the plating film thickness measurement data acquired in step 402 and the corresponding target film thickness value are input to the input node 481 of the trained learning model 480. In response to this input, the output node 485 of the trained learning model 480 outputs an estimated value of the quality of the plating module 200. In this way, the trained learning model 480 estimates the quality of multiple plating modules 200 in the plating apparatus 100. A quality assessment is made for each of them.

[0042] In addition to the film thickness target value and plating film thickness measurement data described above, the input node 481 of the learning model 480 may also receive additional data that correlates with the quality of the plating module 200. Such additional data may include, for example, one or more of the following: substrate information relating to the characteristics of the substrate, module information relating to the plating process of the plating module 200, and analysis results relating to the components of the plating solution Q used in the plating module 200.

[0043] The additional data, specifically substrate information, may include, for example, the size, shape, and material of the substrate, the thickness and material of the seed layer formed on the substrate surface, the thickness of the resist film provided on the substrate, and the size, shape, arrangement, aperture area, and aperture ratio of the openings in the resist film. The substrate information may also be an identifier that classifies the type of substrate according to each of these items (e.g., substrate type A, substrate type B, etc.). The quality or characteristics of the plating film formed on the substrate by the plating module 200 are influenced by these various characteristics of the substrate. Therefore, by using such substrate information as input to the learning model 480, the accuracy of the judgment of the quality of the plating module 200 output from the learning model 480 can be improved. In particular, the quality of the plating module 200 can be judged more accurately depending on the type of substrate.

[0044] Furthermore, the module information among the additional data may include, for example, dimensions or arrangement information of various elements in the plating tank 39 of the plating module 200 (e.g., the distance between each element of the anode 221, anode mask 225, regulation plate 230, and substrate W, and the error from the design value), the temperature of the plating solution Q in the plating tank 39, the temperature distribution of the plating solution Q (temperature differences depending on the location in the plating tank 39), the temporal stability of the temperature of the plating solution Q, the flow rate of the plating solution Q, and its temporal stability, etc. The temperature and flow rate of the plating solution Q can be obtained from the plating solution analyzer 259. The quality or characteristics of the plating film formed on the substrate by the plating module 200 are affected by such individual differences in the plating module 200. Therefore, by using such module information as input to the learning model 480, the accuracy of the judgment of the quality of the plating module 200 output from the learning model 480 can be improved. In particular, the quality of each plating module in the multiple plating modules 200 provided by the plating apparatus 100 can be judged more accurately.

[0045] The analysis results regarding the components of the plating solution Q, among the additional data, are obtained from the plating solution analyzer 259. The plating solution Q contains, for example, an accelerator and / or inhibitor as additives. The accelerator is a component that promotes the deposition of plating, and the inhibitor is a component that suppresses the deposition of plating. The concentrations of such accelerators and inhibitors affect the local or global uniformity of the plating film formed on the substrate. Therefore, by using the analysis results of the components of such plating solution Q as input to the learning model 480, the accuracy of the judgment of the quality of the plating module 200 output from the learning model 480 can be improved.

[0046] Furthermore, recipe data and process logs may be used as additional data to the input node 481 of the learning model 480. Recipe data includes, for example, the set value of the plating current to be applied to the substrate, the set value of the energizing time to the substrate, the set value of the aperture size of the anode mask 225 and the regulation plate 230, etc. Process logs include, for example, log data of the plating current actually supplied to the substrate during the process, logs of the actual energizing time to the substrate during the process, etc. By using this data as input to the learning model 480, the accuracy of determining the quality of the plating module 200 can be further improved.

[0047] Returning to Figure 4, in step 406, the processor 420 performs the actual plating process. A setting screen for specifying row conditions is displayed on the user interface (e.g., display) of the control unit 400. The execution conditions for the plating process include specifying the quality of the plating module to be used in the plating process. For example, among the many substrates to be plated by the plating apparatus 100, there may be "critical substrates" that require particularly careful handling compared to other substrates. Critical substrates need to be plated by the plating module 200 so that a high-quality plating film (e.g., high in-plane uniformity of film thickness) is formed. When plating such critical substrates, the administrator / operator of the plating apparatus 100 specifies from the user interface (input means) that the critical substrate should be plated with a plating module that is of high quality (i.e., expected to be able to form a high-quality plating film) among the multiple plating modules 200. For example, if the quality of the plating module 200 is classified into three levels: "A" (high quality), "B" (medium quality), and "C" (relatively low quality), the manager / operator of the plating apparatus 100 would designate a plating module 200 with quality "A" for plating critical substrates. Furthermore, when plating ordinary substrates that are not critical, a quality "B" or "C" module may be designated.

[0048] Next, in step 408, the processor 420 controls the plating apparatus 100 to execute the plating process according to the execution conditions specified in step 406. Specifically, the processor 420 selects a plating module from among the multiple plating modules 200 of the plating apparatus 100 that matches the quality level specified in step 406, and controls the plating apparatus 100 to execute the plating process using the selected plating module 200. For example, if a quality level of "A" is specified in step 406, a plating module 200 with a quality level of "A" is selected, and the substrate is plated using that plating module 200.

[0049] Thus, according to this embodiment, the quality of each of the multiple plating modules 200 of the plating apparatus 100 is determined, and the quality of the plating module to be used for the substrate plating process is specified, thereby enabling the substrate plating process to be carried out using a plating module 200 with an appropriate quality. As a result, a plating film of appropriate quality can be formed for each substrate, reducing the occurrence of process defects and enabling efficient operation of the plating apparatus 100.

[0050] Furthermore, in steps 406 and 408 described above, the execution conditions for the plating process may include additional execution conditions other than the quality of the plating module 200. For example, the setting screen displayed on the control unit 400 in step 406 may include one or more of the following as additional execution conditions for the plating process: specifying the processing priority for the substrate to be processed, specifying the substrate transport speed, specifying the priority for retrieving the substrate in the event of an error, and specifying the operating conditions when the process is restarted after an error occurs. For example, the specification of the substrate processing priority may allow selection from "priority" to process the substrate earlier than other substrates, "delay" to process the substrate after other substrates, or "no specification" to process the substrate in the normal order. Also, the specification of the substrate transport speed may allow selection from, for example, "normal" and "slow". Furthermore, the priority for recovering the substrate in the event of an error may be specified as follows: "Priority," which recovers the substrate from the plating apparatus 100 to the cassette 25a mounted on the cassette table 25 earlier than other substrates; "Delay," which recovers the substrate after other substrates; or "No specification." Additionally, the operating conditions when the process is restarted may be specified as follows: for example, which process to restart from when the process is restarted (for example, restarting from the cleaning process or restarting from the plating process). In step 408, the plating process may be executed according to these specified conditions.

[0051] <Second Embodiment> Figure 6 is a flowchart showing the operation of System 10 for carrying out a method according to another embodiment of the present invention. The processing of each step in the flowchart of Figure 6 is performed by the processor 420 of the control unit 400 in System 10. The method according to the embodiment of Figure 6 is started in step 602 while the plating apparatus 100 is in operation.

[0052] In step 602, the processor 420 acquires plating thickness measurement data for multiple substrates plated by multiple plating modules 200 in the plating apparatus 100. In the subsequent step 604, the processor 420 determines the quality of each plating module in the multiple plating modules 200 of the plating apparatus 100 based on the plating thickness measurement data acquired in step 602. The processes in steps 602 and 604 are the same as steps 402 and 404 in the flowchart of Figure 4 (first embodiment) described above, and redundant explanations are omitted.

[0053] Next, in step 606, the processor 420 creates a database that stores the quality scores for each substrate type and each plating module based on the quality scores obtained in step 604. As can be understood from the description of steps 402 and 404 above with respect to the first embodiment, in step 604, for each plating module 200 of the plating apparatus 100, a quality score determination result for the plating module 200 is obtained for each of the numerous substrate types plated by the plating module 200. In step 606, a database is created from the quality score determination results for each plating module 200 for each substrate type.

[0054] Figure 7 shows an example of the database created in step 606. In this example, the quality of the plating modules is represented by "A", "B", or "C". According to this exemplary database, for example, for a substrate of "Substrate Type 1", the quality of the first plating module among the multiple plating modules 200 is "B", the quality of the second plating module is "A", the quality of the third plating module is "B", and so on. Therefore, when plating a substrate of "Substrate Type 1", it can be seen that using the second plating module makes it possible to form the highest quality (for example, the one with the best in-plane uniformity) plating film.

[0055] Next, in step 608, the processor 420 accepts the specification of the substrate type. For example, the administrator / operator of the plating apparatus 100 inputs recipe information through the interface screen of the control unit 400 to instruct various process conditions when plating a substrate in the plating apparatus 100. As part of this recipe information, the specification of the substrate type of the substrate to be plated (for example, "Substrate Type 1") may be input.

[0056] Next, in step 610, the processor 420 selects a plating module suitable for the substrate type from the database based on the substrate type specified in step 608. Referring to the example database in Figure 7 above, for example, if "substrate type 1" is specified in step 608, the processor 420 selects the second plating module, which is a plating module 200 having a quality rating of "A" for the substrate of "substrate type 1", as the plating module to be used to plate the substrate of "substrate type 1". Alternatively, for example, if "substrate type 2" is specified in step 608, and it is predetermined that the process in the plating apparatus 100 does not require special care for the substrate of "substrate type 2", and that normal care is sufficient, the processor 420 may select a plating module with a quality rating of "B" instead of "A" (for example, the first plating module) as the plating module to be used to plate the substrate of "substrate type 2". It is also acceptable to always select a plating module with a quality rating of "A" for the substrate.

[0057] Next, in step 612, the processor 420 controls the plating apparatus 100 to perform a plating process on a substrate of the substrate type specified in step 608 using the plating module selected in step 610. This ensures that the substrate is plated using the plating module 200 appropriate for the substrate type.

[0058] Thus, according to this embodiment, by using a database that stores the quality level of each plating module 200 of the plating apparatus 100 for each substrate type, the substrate can be plated using a plating module 200 with an appropriate quality level for each substrate type. Therefore, a plating film of appropriate quality can always be formed on any substrate type, and by using a plating module that is not of the highest quality depending on the substrate type, the plating apparatus 100 can be operated even more efficiently.

[0059] <Third Embodiment> Figure 8 is a flowchart showing the operation of system 10 for carrying out a method according to yet another embodiment of the present invention. The processing of each step in the flowchart of Figure 8 is performed by the processor 420 of the control unit 400 in system 10. The method according to the embodiment of Figure 8 is started in step 802 before the process starts in the plating apparatus 100.

[0060] First, in step 802, the processor 420 determines a predicted score regarding the quality of the plating film thickness formed when the plating process is performed under predetermined plating process conditions, based on those conditions. The determination of the predicted score (hereinafter referred to as the process predicted score) is performed using a learning model that has been trained by machine learning to output a process predicted score when predetermined plating process conditions are input.

[0061] Figure 9 shows the configuration of an exemplary learning model 490 used in carrying out the method according to this embodiment. For example, the learning model 490 may be constructed within the control unit 400 by the processor 420 reading and executing a program 460 stored in the memory 440 of the control unit 400. The learning model 490 is configured to determine a process prediction score regarding the quality of the plating film thickness formed under predetermined plating process conditions. The learning model 490 is trained using a large amount of training data so that it can correctly determine the process prediction score.

[0062] As shown in Figure 9, the learning model 490 is composed of a neural network 497 comprising an input layer 492 having multiple input nodes 491, an intermediate layer 494 consisting of one or more layers, each having multiple nodes 493, and an output layer 496 having one or more output nodes 495. Each node is connected to multiple nodes in the layer to which it belongs, with an intensity characterized by a weighting parameter.

[0063] The input node 491 of the learning model 490 receives predetermined plating process conditions for plating a substrate with the plating module 200 of the plating apparatus 100. These predetermined plating process conditions include a target film thickness, substrate information, module information, the concentrations of each component of the plating solution, and recipe data. Some of these may be omitted. These—the target film thickness, substrate information, module information, the concentrations of each component of the plating solution, and recipe data—have already been described in relation to the learning model 480 in the first embodiment, so a redundant explanation will not be repeated here. The output node 495 of the learning model 490 outputs a score (process prediction score) related to the quality of the plating film thickness expected to be formed on the substrate when the plating process is performed using the plating process conditions input to the input node 491. The learning model 490 is trained by adjusting the weighting parameters between each node of the neural network 497 so that the predicted score matches a predetermined correct label. The correct labels are prepared in advance by actually performing plating on a substrate under the plating process conditions in question. In other words, the correct labels are created using data from actual plating processes performed in the past. For example, the manager of the plating apparatus 100 can create a correct label indicating the quality of the plating film by evaluating the plating film thickness measurement data obtained when plating is actually performed under the plating process conditions in question. The learning model 490 is trained using a large number of training data sets consisting of various plating process conditions and their corresponding correct labels. This completes the learning model 490, which is capable of accurately determining the process prediction score.

[0064] In step 802, various plating process conditions are input to the input node 491 of the trained learning model 490, and in response to this input, the output node 495 of the trained learning model 490 outputs a process prediction score corresponding to the input plating process conditions. If the value of the process prediction score obtained from the learning model 490 is not satisfactory, step 802 may be repeated by changing the plating process conditions input to the learning model 490 until a satisfactory process prediction score is obtained.

[0065] Returning to Figure 8, in step 804, the processor 420 selects a plating module to be used in the substrate plating process from among the multiple plating modules 200 of the plating apparatus 100, based on the process prediction score obtained in step 802. For example, in step 802 above, by using various substrate information and module information as plating process conditions input to the learning model 490, a process prediction score can be obtained for each substrate type of substrate to be plated and for each plating module 200 in the plating apparatus 100. In step 804, the processor 420 may, for example, select the plating module with the highest process prediction score for each substrate type as the plating module to be used in the plating process for that substrate type. Using this selected plating module, it is expected that the highest quality plating film (for example, with good in-plane uniformity of film thickness) can be obtained.

[0066] Next, in step 806, the processor 420 controls the plating apparatus 100 to perform a plating process on the substrate using the plating module selected in step 804. This ensures that the substrate is plated using the plating module 200, which is expected to produce a high-quality plating film.

[0067] Thus, according to this embodiment, by selecting the plating module 200 based on the expected quality (process expected score) of the plating film obtained in the plating process, the substrate can be plated using the optimal plating module 200. Therefore, a high-quality plating film can be formed on the substrate in the plating apparatus 100.

[0068] In the first to third embodiments described above, since the quality and process prediction scores for each plating module may change moment by moment, instead of configuring the learning models 480 and 490 as simple input / output neural networks 487 and 497 as shown in Figures 5 and 9, a recurrent neural network may be adopted in which the quality and process prediction scores output from the output layers 486 and 496 are input back into the input layers 482 and 492. By using such a recurrent neural network, it is possible to estimate the quality and process prediction scores of the plating modules more accurately by reflecting the state at previous time points.

[0069] The embodiments of the present invention have been described above based on several examples, but the above-mentioned The embodiments described herein are for the purpose of facilitating understanding of the present invention and do not limit it. The present invention can be modified and improved without departing from its spirit, and of course, the present invention includes its equivalents. Furthermore, any combination or omission of the components described in the claims and specification is possible to the extent that at least some of the above-described problems can be solved or at least some of the effects can be achieved. [Explanation of symbols]

[0070] 10 Systems 100 Plating equipment 200 plated modules 300 Film Thickness Measurement Unit 400 control units 420 processors 440 memory 460 programs 480 Learning Models 481 Input Nodes 482 Input Layers 483 nodes 484 Middle Class 485 Output Nodes 486 Output Layers 487 Neural Networks 490 Learning Models 491 Input Nodes 492 Input Layer 493 nodes 494 Middle Class 495 Output Nodes 496 Output Layer 497 Neural Networks 500 Networks

Claims

1. A control method for a plating apparatus comprising multiple plating modules, The steps include: acquiring plating thickness measurement data for multiple substrates that have been plated by the multiple plating modules; A step of determining the quality of each plating module in the plurality of plating modules based on the plating thickness measurement data, A step of controlling the plating process in the plating apparatus based on the quality of each of the plating modules, A method for controlling a plating apparatus, including the control of a plating apparatus.

2. The method according to claim 1, wherein the step of determining the quality includes determining the quality of each plating module using a learning model trained by machine learning to output the quality of the plating module when a target value for the plating thickness and measurement data of the plating thickness on a plated substrate are input.

3. The method according to claim 2, wherein the learning model is configured to receive at least one of the following as input parameters: (i) substrate information relating to the characteristics of the substrate, (ii) module information relating to the plating process of the plating module, and (iii) analysis results relating to the components of the plating solution used in the plating module.

4. The method according to claim 1, wherein the step of determining the quality includes calculating statistical values ​​from the plating film thickness measurement data and determining the quality of each plating module based on the statistical values.

5. The method according to any one of claims 1 to 4, wherein the control step includes control to select a plating module to be used in the plating process from the plurality of plating modules.

6. The aforementioned control step is, The steps include creating a database to store the quality scores for each substrate type and each plating module based on the quality scores obtained by the above determination, Steps include specifying the board type, The steps include selecting a plating module suitable for the substrate type from the database based on the specified substrate type, The steps include controlling the process to perform a plating process on a substrate of the specified substrate type using the selected plating module, The method according to claim 5, including the method described in claim 5.

7. The method according to claim 6, wherein control is performed to use only high-quality plated modules.

8. The method according to claim 6, wherein control is performed to use only high-quality plating modules for substrates of the first substrate type, and only low-quality plating modules for substrates of the second substrate type.

9. The aforementioned control step is, A step of displaying a settings screen for specifying the execution conditions of a plating process, wherein the execution conditions include specifying the quality level of the plating module used in the plating process. The steps include: executing a plating process according to the specified execution conditions; The method according to any one of claims 1 to 4, including the method described in any one of claims 1 to 4.

10. The method according to claim 9, wherein the execution conditions further include at least one of the following: (i) specifying the processing priority for the substrate to be processed, (ii) specifying the transport speed of the substrate, (iii) specifying the priority for retrieving the substrate when an error occurs, and (iv) specifying the operating conditions when the process is restarted after an error occurs.

11. A control method for a plating apparatus comprising multiple plating modules, A step of determining a predicted score regarding the quality of the plating film thickness formed when a plating process is performed under predetermined plating process conditions, wherein the determination is performed using a learning model trained by machine learning to output the predicted score when the predetermined plating process conditions are input. A step of controlling the selection of a plating module to be used in the plating process based on the predicted score obtained by the above determination, A method for controlling a plating apparatus, including the control of a plating apparatus.

12. A plating apparatus comprising multiple plating modules and a control unit, The control unit is The plating thickness measurement data is obtained for multiple substrates that have been plated by the multiple plating modules described above. Based on the aforementioned plating thickness measurement data, the quality of each plating module in the plurality of plating modules is determined. The plating process in the plating apparatus is controlled based on the quality of each of the aforementioned plating modules. A plating apparatus configured as follows.

13. The control unit is equipped with a machine learning-trained learning model that, upon inputting a target value for the plating thickness and measurement data of the plating thickness on a plated substrate, outputs the quality rating of the plating module. The control unit uses the learning model to determine the quality of each plating module. The plating apparatus according to claim 12.

14. A plating apparatus comprising multiple plating modules and a control unit, The control unit is Based on predetermined plating process conditions, the predicted score regarding the quality of the plating film thickness formed when the plating process is performed under those conditions is determined. Based on the predicted score obtained by the above determination, the selection of the plating module to be used in the plating process is controlled. It is configured in such a way, The control unit includes a learning model trained by machine learning to output the predicted score when the predetermined plating process conditions are input. The control unit uses the learning model to determine the predicted score from the predetermined plating process conditions. Plating equipment.

Images