Semiconductor manufacturing equipment management system and method thereof

Abstract

A management system and method for semiconductor manufacturing equipment that determines recipes according to changes over time in the semiconductor manufacturing equipment are provided. [Solution] A semiconductor manufacturing management system that determines a recipe for a film formation process in semiconductor manufacturing equipment that forms a SiC film on a SiC substrate by epitaxial growth includes one or more storage devices and one or more processors. The semiconductor manufacturing equipment has a means for monitoring by-products that adhere to an injector that flows a material gas and cause inner diameter fluctuations, and determines the recipe for the next film formation process and maintenance for cleaning the by-products using a machine learning model as an estimation model.

Description

Technical Field

[0001] The present invention relates to a management system and method for semiconductor manufacturing equipment.

Background Art

[0002] For example, in addition to high breakdown voltage, low on-resistance and low switching loss are required for semiconductor power devices. However, the current mainstream silicon (Si) power devices are approaching their theoretical performance limits. Silicon carbide (SiC) has an approximately one-order-of-magnitude higher breakdown electric field strength compared to Si. Therefore, by making the drift layer for holding the breakdown voltage about 1 / 10 thinner and increasing the impurity concentration by about 100 times, the element resistance can be theoretically reduced by more than three orders of magnitude. In addition, since SiC has an approximately three-fold larger bandgap than Si, it can also operate at high temperatures. SiC semiconductor devices are expected to have performance superior to Si semiconductor devices, and the development of semiconductor manufacturing equipment for SiC is underway.

[0003] One of the semiconductor manufacturing equipment for SiC is the SiC epitaxial growth equipment. The epitaxial growth of SiC is a technique for depositing a SiC film on an off-cut SiC substrate. Generally, since the SiC substrate has a high donor concentration, it is necessary to adjust the donor concentration and film thickness according to the application of the breakdown voltage used, and epitaxial growth is performed for fabricating SiC devices. The requirements for epitaxial growth technology include, for example, the enlargement of epitaxial growth accompanying the enlargement of the substrate diameter, ensuring the uniformity of the donor concentration, ensuring the uniformity of the epitaxial film thickness, high-speed growth, reduction of crystal defects, etc.

[0004] In order to accurately meet all of these requirements, an apparatus equipped with a large number of control parameters (input parameters) is required. Accordingly, in order to fully extract the performance of the semiconductor manufacturing equipment, it is necessary to determine control parameters ranging from several to several tens of types. Therefore, as the performance of the equipment improves, the equipment structure becomes more complex, and it is becoming increasingly difficult to find a combination of control parameters that can obtain a desired film formation result. This causes a lengthening of the device development period and an increase in development costs.

[0005] Furthermore, in a SiC epitaxial growth apparatus, during SiC epitaxial growth, by-products derived from the source gas firmly adhere to members other than the SiC substrate (inner wall and susceptor). These by-products are exposed to high temperatures during epitaxial growth and evaporate, causing changes in the epitaxial results over time. In other CVD apparatuses, it is easy to remove by-products such as through gas cleaning, but in the case of SiC, an effective gas cleaning method has not been established at present. For this reason, maintenance such as frequently opening the chamber is required to remove by-products, which increases the development cost.

[0006] Therefore, in order to reduce the development cost, there is a need for a function or device that can semi-automatically search for optimal control parameters considering changes over time, easily extract the performance of the apparatus, and further notify the maintenance timing. As methods for modifying the process recipe considering changes over time, there are the methods of Patent Document 1 and Patent Document 2.

[0007] As a document disclosing means for correcting the deviation of the film formation result due to changes over time, for example, Patent Document 1 can be cited. Patent Document 1 discloses a method for correcting the film thickness deviation. Specifically, it discloses the following: "The control device is a control device that controls the operation of a substrate processing device that forms a film on a substrate by atomic layer deposition, and includes a recipe storage unit that stores film formation conditions corresponding to the type of the film, a model storage unit that stores a process model representing the influence of the film formation conditions on the characteristics of the film, a log storage unit that stores measured values of the film formation conditions during film formation, a measurement result of the characteristics of the film formed under the film formation conditions stored in the recipe storage unit, the process model stored in the model storage unit, and the measured values of the film formation conditions stored in the log storage unit, and a control unit that calculates film formation conditions that satisfy the target characteristics of the film" (abstract).

[0008] As a document disclosing means for correcting differences caused by assembly and dimensional variations between devices and chambers, that is, mechanical differences, and changes over time, for example, Patent Document 2 can be cited. Patent Document 2 discloses the following matters. "In a semiconductor manufacturing apparatus including a plurality of semiconductor manufacturing apparatuses and a control apparatus for controlling each of these semiconductor manufacturing apparatuses, and controlling the plurality of semiconductor manufacturing apparatuses according to one supplied recipe to manufacture a common semiconductor device, based on difference data between the performance of the apparatus when the recipe was used and the apparatus performance obtained by using a semiconductor manufacturing apparatus scheduled to be used among the plurality of semiconductor manufacturing apparatuses, referring to recipe correction data stored in advance to calculate a recipe correction amount, correcting the supplied recipe based on the calculated recipe correction amount, and supplying it to the semiconductor manufacturing apparatus scheduled to be used hereafter." (Summary).

Prior Art Documents

Patent Documents

[0009]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0010] However, in the method of Patent Document 1, the trigger for correcting the recipe is film formation exceeding the allowable value, and depending on the deviation amount, the next process cannot proceed. That is, it involves a risk of failure and can cause an increase in development costs. Also, when increasing the items to be corrected, it is necessary to newly create a correlation model corresponding to the number of input parameters of the apparatus, and a large amount of man-hours is required for creating the correlation model.

[0011] Also in the method of Patent Document 2, as a means for correcting the machine difference and the change over time, it is necessary to prepare in advance the correlation data of the output results for each input parameter. When increasing the items to be corrected, it is necessary to newly create a correlation model corresponding to the number of input parameters of the apparatus, and a large amount of man-hours is required for creating the correlation model. Further, for correction, it is necessary to perform processing according to a recipe for constructing performance history data after maintenance in advance, which may cause an increase in development costs.

Means for Solving the Problems

[0012] Among the inventions disclosed in the present application, the outlines of typical ones will be briefly described as follows. One aspect of the present invention is a management system for determining a recipe of a semiconductor manufacturing apparatus, including one or more storage devices and one or more processors. The one or more storage devices store history information of past processes of the semiconductor manufacturing apparatus. The one or more processors acquire a target value of a specific target in a next process by the semiconductor manufacturing apparatus, and based on the history information and the target value, determine a recipe of the next process of the semiconductor manufacturing apparatus using one or more functions including an estimation model. An input of the estimation model includes a recipe candidate of the next process of the semiconductor manufacturing apparatus, and an output of the estimation model includes an estimated value of the specific target.

Effects of the Invention

[0013] According to one aspect of the present invention, a recipe corresponding to a change over time of a semiconductor manufacturing apparatus can be determined.

[0014] Problems, configurations, and effects other than those described above will be clarified by the description of the following embodiments.

Brief Description of the Drawings

[0015]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18A

Figure 18B

Figure 18C

Figure 19

Figure 20

Figure 21

Figure 22

Figure 23

Figure 24

Figure 25

Figure 26

Figure 27

Figure 28

Figure 29

Figure 30

Figure 31

Figure 32

Figure 33

Figure 34

Figure 35

Figure 36

Figure 37

Embodiments for Carrying Out the Invention

[0016] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following embodiments, for convenience, when necessary, they will be divided and described in a plurality of sections or embodiments. However, unless otherwise specified, they are not independent of each other, and one is related to a modification example, details, supplementary explanation, etc. of part or all of the other.

[0017] Also, in the following embodiments, when referring to the number of elements, etc. (including the number, numerical value, quantity, range, etc.), unless otherwise specified or clearly limited to a specific number in principle, it is not limited to that specific number, and it may be more than or less than the specific number. Further, in the following embodiments, the constituent elements (including element steps, etc.) are not necessarily essential, unless otherwise specified or clearly considered essential in principle. <Overview>

[0018] This embodiment explains the derivation of an appropriate recipe considering changes over time in a semiconductor manufacturing apparatus. The semiconductor manufacturing management system autonomously estimates changes over time in a chamber from history information of past processes of semiconductor manufacturing, and derives an appropriate recipe (processing conditions of a semiconductor device) suitable for the device situation.

[0019] In this embodiment, since the change over time is estimated from the process history information, film formation for confirming the change over time is unnecessary, and the man-hour can be reduced. Further, in this embodiment, by constructing a machine learning model based on the process history information, it is not necessary to prepare correlation data for each parameter constituting the recipe. Furthermore, in this embodiment, since an appropriate recipe considering the change over time can be derived, the number of maintenance times can be reduced.

[0020] As described above, the semiconductor manufacturing management system of this embodiment determines an appropriate recipe for the next process by a machine learning model (estimation model). The input of the estimation model includes the recipe, and the output includes an estimated value of a value obtained as a result of the process by the semiconductor manufacturing apparatus (estimated value of a specific target).

[0021] Hereinafter, an example of a film formation process will be described. An example of the film formation process is, for example, epitaxial film formation of Si or SiC. The input in the film formation process (estimation model) includes the recipe, and the output includes an estimated value of the characteristics of the generated film. The characteristics of the film include, for example, the film thickness or the impurity concentration profile. In the example described below, the film thickness is used as the output. Note that the features of this embodiment can be applied to semiconductor manufacturing processes other than the film formation process.

[0022] <Embodiment 1> For the sake of simplicity of explanation, an example in which the recipes of the repeatedly executed film formation processes are the same will be described. FIG. 1 shows the estimation of the film thickness of the Nth film formation process according to the comparative example. The estimation model of the comparative example estimates the film thickness from the recipe without referring to the process history information. That is, the input of the estimation model is only the recipe of each film formation process. When there is a change over time in the film forming apparatus, the film thickness (output) fluctuates even when the same recipe A (input A) is used. Therefore, the estimation model of the comparative example cannot accurately estimate the film thickness based on the Nth process. That is, the comparative example cannot estimate the input A that results in the target A (film thickness A).

[0023] Figure 2 shows the estimation of the film thickness in the Nth film formation process according to this embodiment. First, by adding the process history information to the training data and using machine learning suitable for time series analysis (for example, RNN (Recurrent Neural Network), LSTM (Long-Short Term Memory), etc.), an estimation model is constructed. Further, using an optimal solution search method, an input (input A) is predicted such that the estimation model outputs a value close to the target A of the Nth process. Here, the process history information is, for example, the number of processed sheets, the number of processing times, etc.

[0024] Next, consider an example where the output (film thickness) remains constant while there are changes over time. Due to the influence of changes over time, the input (recipe) for obtaining a constant output (film thickness) changes. If the amount of output variation due to changes over time is considered as a function of the input, it is considered that accurate prediction cannot be achieved even by using the number of processed sheets or the number of processing times as process history information.

[0025] Therefore, by using the recipe history as process history information, it becomes possible to autonomously learn the feature amount of changes over time. Figure 3 shows an example of the training data 31 used for constructing the estimation model after predicting the input for which the output becomes X at the Nth time. Figure 4 shows the relationship between the processing order and the output (film thickness) in the training data 31, and Figure 5 shows the relationship between the processing order and one of the input parameters (gas flow rate) in the training data 31.

[0026] The training data used for constructing the estimation model for predicting the input for which the output becomes X at the Nth time is the data obtained by removing the Nth record from the training data 31 shown in Figure 3. The training data 31 shows the recipe in semiconductor manufacturing, which is the input of the estimation model, the film thickness, concentration, in-plane distribution of each, and recipe record information. The recipe history information of each record shows the time series of the recipes in all past processes (after chamber maintenance). Note that all past processes may be all processes after chamber maintenance. The recipe history information "-" of the first record (No. 1 in the table) indicates that there is no process (recipe) shown as history before the process of that record.

[0027] FIG. 6 schematically shows a method for estimating an appropriate input (recipe) using an estimation model. The estimation model 23 outputs an output value 42 for an input value 41. The input value 41 and the output value 42 are represented by vectors, for example. This method searches for an input value 41 such that the error between the target value (also simply referred to as the target value) 35 of a specific target in the semiconductor manufacturing apparatus and the output value (estimated value) 42 is within an allowable range.

[0028] The input value 41 includes the input value (recipe candidate) for the semiconductor manufacturing apparatus in the next process. By changing the recipe candidate in the input value 41, a recipe (input value 41) that obtains an output value 42 within the allowable range is searched for. This method further adds the input value 41 to the training data 31 together with the recipe history information. This method further updates the estimation model 23 using the updated training data 31.

[0029] In actual semiconductor manufacturing, the same target is not always set every time. Therefore, as shown in FIG. 7, the combination of the input value and the output value of the estimation model can change for each process. By applying the recipe history information as the process history information, it is possible to autonomously capture the feature amount accompanying the change over time, and to construct an accurate estimation model including the change over time.

[0030] Hereinafter, a more specific configuration example in the present embodiment will be described. FIG. 8 schematically shows a configuration example of a semiconductor manufacturing management system. In the example of FIG. 8, the semiconductor manufacturing management system 100 is configured by one computer. The semiconductor manufacturing management system 100 includes a processor 110, a memory 120, an auxiliary storage device 130, a network (NW) interface 140, an I / O interface 145, an input device 151, and an output device 152. The above components are connected to each other by a bus. The memory 120, the auxiliary storage device 130, or a combination thereof is a storage device.

[0031] The memory 120 is composed of, for example, a semiconductor memory, and is mainly used to temporarily hold programs and data. The programs stored in the memory 120 include, in addition to an operating system (not shown), an integrated management program 121, a device control program 122, an estimation model program 123, a recipe search program 124, and an analysis and evaluation program 125.

[0032] The integrated management program 121 manages other programs and mediates communication between them. The device control program 122 controls a semiconductor manufacturing apparatus (for example, a chamber). The estimation model program 123 is a model that takes a semiconductor manufacturing recipe as an input and outputs an estimated value of a target object (for example, film characteristics in film formation) in semiconductor manufacturing, and a model of any appropriate method such as a neural network, a support vector machine, or a kernel is used. The recipe search program 124 searches for an appropriate recipe to achieve the target value of the target object in semiconductor manufacturing by the estimation model program 123. The analysis and evaluation program 125 analyzes and evaluates the measured value of the target object in semiconductor manufacturing.

[0033] The processor 110 executes various processes according to the programs stored in the memory 120. By operating the processor 110 according to the programs, various functional units are realized. For example, the processor 110 functions as an integrated management unit, a device control unit, an estimation model, a recipe search unit, and an analysis and evaluation unit according to each of the above programs.

[0034] The auxiliary storage device 130 stores a training data database 131. The training data database 131 stores data for training the estimation model. The auxiliary storage device 130 is composed of, for example, a large-capacity storage device such as a hard disk drive or a solid state drive, and is used to hold programs and data for a long period of time.

[0035] For convenience of explanation, programs 121 to 125 are stored in the memory 120, and the training data database 131 is stored in the auxiliary storage device 130. However, the storage location of the data of the semiconductor manufacturing management system 100 is not limited. For example, the programs and data stored in the auxiliary storage device 130 are loaded into the memory 120 at startup or when needed, and the processor 110 executes the programs, whereby various processes of the semiconductor manufacturing management system 100 are executed. Therefore, the processes executed by the functional units hereinafter are processes by the processor 110 or the semiconductor manufacturing management system 100 according to the programs.

[0036] The network interface 140 is an interface for connection to a network. The semiconductor manufacturing management system 100 communicates with other devices within the system or devices related to the system via the network interface 140. The input device 151 is a hardware device for a user to input instructions, information, etc., and includes, for example, a keyboard and a pointing device. The output device 152 is a hardware device for indicating various images for input / output, and is, for example, a display device.

[0037] The semiconductor manufacturing management system 100 includes one or more processors and one or more computing devices. Each processor can include a single or multiple arithmetic units or processing cores. The processor can be implemented, for example, as a central processing unit, a microprocessor, a microcomputer, a microcontroller, a digital signal processor, a state machine, a logic circuit, a graphics processing unit, a chip on system, and / or any device that operates signals based on control instructions.

[0038] The functions of the semiconductor manufacturing management system 100 may be implemented by distributed processing by a computer system including a plurality of computers. The plurality of computers communicate with each other via a network and execute processes in cooperation. FIGS. 9 and 10 schematically show other logical configuration examples of the semiconductor manufacturing management system.

[0039] In the example of FIG. 9, the integrated management unit 21, the device control unit 22, the estimation model 23, the recipe search unit 24, and the analysis and evaluation unit 25 communicate with each other via the network (NW) 200. For example, the integrated management unit 21, the device control unit 22, the estimation model 23, the recipe search unit 24, and the analysis and evaluation unit 25 are each realized by a program installed in a different computer. Through distributed processing by multiple computers, rapid processing is realized.

[0040] In the example of FIG. 10, the integrated management unit 21, the device control unit 22, and the analysis and evaluation unit 25 are installed in one computer. The estimation model 23 and the recipe search unit 24 are installed on the cloud. As will be described later, since the processing by the recipe search unit 24 has the highest load, by installing the recipe search unit 24 on the cloud, rapid processing is realized. Also, the recipe search unit 24 can be shared among multiple semiconductor manufacturing management systems.

[0041] FIG. 11 shows an example of the training data 31 for updating the estimation model 23 stored in the training data database 131. The training data 31 includes input data 311 input to the estimation model 23 and output data 312 which is the target data of the output from the estimation model 23.

[0042] In the example of FIG. 11, each record of the input data 311 indicates the input value for one film formation process input to the estimation model 23 in the training of the estimation model 23. The input value is composed of a plurality of variable values (variable parameter values) that make up the film formation recipe. In the example of FIG. 11, the input value is composed of the processing time, the processing temperature, the processing pressure, the gas flow rates of three different types of gases, and the carrier gas flow rate, and is represented as a vector. Each input value is the recipe in the actually performed film formation.

[0043] FIG. 11 shows SiH as three different types of gases 4 , C 3 H 8 , N 2Although Si is exemplified, other source gases containing Si, other source gases containing C, and other gases containing dopants (impurities) can be used. Other examples of other source gases containing Si are SiH 4 , SiClH 3 . The carrier gas is, for example, H 2 . In addition to these gases, the input value may include an assist gas (e.g., HCl).

[0044] Each record of the output data 312 indicates a target value for the output value output from the estimation model 23 for one film formation process in the training of the estimation model 23. The output value is composed of a plurality of variable values indicating the characteristics of the formed film and is represented as a vector. In the example of FIG. 11, the output value is composed of the film thickness, impurity concentration, and crystal defect density. Each output value is an actually measured value of the result of the actually performed film formation process.

[0045] The records with the same process number in the input data 311 and the output data 312 are associated with each other. In the example of FIG. 11, the history information is not explicitly shown. The recipe history information of each record is the recipe of past processes (records) arranged in the order of processing.

[0046] FIG. 12 shows an example of the target value 35 for the next film formation process. The target value 35 indicates the target value for the next process. In this example, it indicates the target value of the characteristics of the film obtained by the next film formation process. The elements of the target value 35 are the same as the elements of the output value of the estimation model 23. The recipe search unit 24 searches for an input value that gives an output value of the estimation model 23 close to the target value 35.

[0047] FIG. 13 shows an example of the optimal input value (recipe) 36 determined by the recipe search unit 24. The recipe search unit 24 sequentially inputs input values to the estimation model 23 and searches for an input value whose error between the output value and the target value 35 is within the allowable range as the optimal input value (recipe) 36.

[0048] Referring to FIGS. 14 and 15, the processing of the semiconductor manufacturing management system 100 will be described. FIG. 14 is a logical configuration diagram for explaining the processing of the semiconductor manufacturing management system 100. The recipe search unit 24 includes a model configuration unit 241, a recipe estimation unit 242, and a convergence determination unit 243. The user includes a target value and an error tolerance in the input data 51 from the input device 151 in order to obtain the optimal recipe for the next processing. When the user performs an analysis of the object to be processed obtained by the actual processing, the user further inputs the analysis evaluation result as the input data 51 from the input device 151. In the example of the film forming process, the analysis evaluation result is the output data of the training data 31 described with reference to FIG. 11. The analysis evaluation result is stored in the training data database 131.

[0049] The semiconductor manufacturing management system 100 outputs the optimal recipe for the next processing as the output data 52 from the output device 152. Further, when the semiconductor manufacturing management system 100 performs an analysis of the object to be processed obtained by the actual processing, the analysis evaluation result is further output from the output device 152 as the output data 52.

[0050] FIG. 15 shows a flowchart of the processing executed by the semiconductor manufacturing management system 100. First, the integrated management unit 21 acquires the target value and the error tolerance as the input data 51 from the input device 151 (S101). The integrated management unit 21 passes the target value and the error tolerance to the recipe estimation unit 242.

[0051] The recipe estimation unit 242 uses the estimation model 23 to derive a recipe that realizes a value close to the target value and estimates the processing result (S102). For example, the recipe estimation unit 242 determines an input value including the recipe closest to the target value using a random search method or an annealing method. The output value of the estimation model 23 for the input value is the estimated processing result.

[0052] The input value includes the recipe for the current process and the past recipe history. The recipe estimation unit 242 searches for an input value for which the output value is within the allowable range among input values with a common recipe history and a different recipe for the current process. Each parameter value of the recipe has constraints (upper and lower limit values) specific to the semiconductor manufacturing apparatus. The candidate recipe is selected from within the range of the said constraints. For example, they are the upper and lower limit values of the processing temperature and the upper and lower limit values of the pressure. Additionally, conditions under which the target film formation clearly does not occur may be used as the lower limit value. For example, the processing temperature is set to a temperature at which epitaxial growth of SiC occurs, such as 1000 °C or higher.

[0053] Next, the convergence determination unit 243 acquires the estimated processing result from the recipe estimation unit 242, and determines whether the error between the estimated processing result and the target value is within the error tolerance range specified by the user (S103). If the estimated processing result is not within the error tolerance range from the target value (S103: NO), the convergence determination unit 243 prompts the user to re-enter the target value and the error tolerance range at the output device 152 via the integrated management unit 21. The flow returns to step S101. Note that the user can perform the process even if the optimal recipe does not satisfy the allowable range. This is the same in other embodiments.

[0054] If the estimated processing result is within the error tolerance range from the target value (S103: YES), the apparatus control unit 22 causes the process execution unit 27 of the processing chamber to execute the process (film formation process in this example) with the determined optimal recipe, and further stores the optimal recipe in the training data database 131 (S104).

[0055] For example, the apparatus control unit 22 acquires the optimal recipe determined by the recipe estimation unit 242 via the integrated management unit 21. The apparatus control unit 22 designates the optimal recipe, instructs the process execution unit 27 to execute the process, and adds the optimal recipe to the input data 311 of the training data 31 via the integrated management unit 21. The process execution unit 27 executes the process according to the designated optimal recipe.

[0056] The analysis and evaluation unit 25 analyzes and evaluates the processing result by the process execution unit 27 (S105). For example, the analysis and evaluation unit 25 controls an analysis and evaluation device (analysis and evaluation chamber) for accommodating and analyzing and evaluating the object to be processed (the substrate formed with a film in this example), and executes the analysis and evaluation of the object to be processed. In this example, the analysis and evaluation unit 25 analyzes and evaluates the characteristics of the formed film. The analysis and evaluation unit 25 stores the analysis and evaluation result in the training data database 131 in association with the corresponding optimal recipe via the integrated management unit 21 (S106).

[0057] Note that the integrated management unit 21 may obtain the analysis and evaluation result from the user via the input device 151. The integrated management unit 21 stores the analysis and evaluation result obtained from the user in the training data database 131 in association with the corresponding optimal recipe. The model configuration unit 241 updates the estimation model 23 using the updated training data database 131 (S107).

[0058] The analysis and evaluation unit 25 compares the target value based on the allowable error with the analysis and evaluation result (S108). When the analysis and evaluation result is within the allowable error range from the target value (S108: YES), the analysis and evaluation unit 25 presents the comparison result to the user via the integrated management unit 21 and ends this flow. When the analysis and evaluation result is not within the allowable error range from the target value (S108: NO), the analysis and evaluation unit 25 presents the comparison result to the user via the integrated management unit 21 and asks the user whether redeposition is necessary. When redeposition is necessary, the integrated management unit 21 instructs the recipe estimation unit 242 to execute step S102. When redeposition is not necessary, this flow ends.

[0059] As described above, semiconductor manufacturing in this embodiment uses a semiconductor manufacturing apparatus and an analysis and evaluation apparatus. These apparatuses may be clustered, enabling efficient semiconductor manufacturing. FIG. 16 shows a configuration example of a cluster apparatus 400. The cluster apparatus 400 includes a plurality of chambers. Specifically, the cluster apparatus 400 includes a substrate analysis chamber 401, a cleaning chamber 402, an analysis and evaluation chamber 403, a processing chamber 404, a regeneration chamber 405, and a load lock chamber and transfer chamber 406.

[0060] The substrate analysis chamber 401 is a chamber for analyzing and evaluating a substrate and can be used to acquire the substrate information described in Embodiment 3. The substrate analysis chamber 401 can be used, for example, to measure the substrate shape such as warpage, edge shape, and plate thickness, or to evaluate dislocations, stacking defects, surface roughness (such as Ra), etc. using X-rays, PL light, laser light, a microscope, etc. The analysis and evaluation chamber 403 is a chamber for analyzing and evaluating the substrate processed in the processing chamber 404. The regeneration chamber 405 is a chamber for regenerating the substrate processed in the processing chamber 404. In the process described with reference to FIGS. 14 and 15, the process execution unit 27 is, for example, the processing chamber 404. The analysis and evaluation unit 25 or the user executes the analysis and evaluation of the substrate processed by the analysis and evaluation chamber 403.

[0061] FIG. 17 shows a configuration example of a SiC epitaxial cluster apparatus 450. The SiC epitaxial cluster apparatus 450 includes a substrate analysis chamber 451, an epi analysis chamber 452, a defect analysis chamber 453, an epi growth chamber 454, a CMP (Chemical Mechanical Polishing) chamber 455, and a load lock chamber and transfer chamber 456.

[0062] The epitaxial growth chamber 454 is an example of a processing chamber, and grows a SiC film epitaxially on a substrate. The epi-analysis chamber 452 is an example of an analysis and evaluation chamber, and is used to analyze and evaluate the film thickness and impurity concentration (dopant concentration) of the epi-film (i.e., SiC film) formed in the epitaxial growth chamber 454. The defect analysis chamber 453 is an example of an analysis and evaluation chamber, and is used to analyze and evaluate the defects of the epi-film formed in the epitaxial growth chamber 454 using X-rays, PL light, laser light, and a microscope. The CMP chamber 455 is an example of the regeneration chamber 405, and is used to reuse the substrate when the formed epi-film does not have desired characteristics.

[0063] In the process described with reference to FIGS. 14 and 15, the process execution unit 27 is, for example, the epitaxial growth chamber 454. The analysis and evaluation unit 25 or the user executes the analysis and evaluation of the SiC film formed by the epi-analysis chamber 452 and the defect analysis chamber 453 to obtain the values of the film thickness, impurity concentration, and crystal defect density. When the SiC film does not have desired characteristics, for example, the apparatus control unit 22 or the user removes the SiC film from the substrate in the CMP chamber 455 and grows the SiC film epitaxially on the substrate again.

[0064] The determination of an appropriate recipe according to this embodiment can be applied to various semiconductor processes (apparatuses). For example, it can be applied to a lithography apparatus, a film forming apparatus, a pattern processing apparatus, an ion implantation apparatus, a cleaning apparatus, etc. The lithography apparatus includes, for example, an exposure apparatus, an electron beam lithography apparatus, and an X-ray lithography apparatus. The film forming apparatus includes, for example, a CVD (Chemical Vapor Deposition) apparatus, a PVD (Physical Vapor Deposition) apparatus, an evaporation apparatus, a sputtering apparatus, and a thermal oxidation apparatus.

[0065] The pattern processing apparatus includes, for example, a wet etching apparatus, a dry etching apparatus, an electron beam processing apparatus, and a laser processing apparatus. The ion implantation apparatus includes, for example, a plasma doping apparatus and an ion beam doping apparatus. The cleaning apparatus includes, for example, a liquid cleaning apparatus and an ultrasonic cleaning apparatus.

[0066] In the optimization of the aperture size in an exposure apparatus, examples of the input elements of the estimation model are exposure amount, resist thickness, resist type, etc., and examples of the output elements are aperture size, deviation amount of design size, resist collapse, etc. In the optimization of the film formation process of a CVD apparatus, examples of the input elements are gas flow rate, process temperature, applied bias, pressure, etc., and examples of the output elements are film stress, density, in-furnace particles, etc.

[0067] In the optimization of the gate insulating film process of MOS and IGBT in a CVD / thermal oxidation apparatus, examples of the input elements are gas flow rate, process temperature, in-furnace pressure, etc., and examples of the output elements are interface state density, dielectric breakdown characteristics, channel mobility, PBTI & NBTI characteristics, etc. In the optimization of the concentration profile in an ion implantation apparatus, examples of the input elements are implantation energy, dose amount, etc., and examples of the output elements are peak concentration position, tail shape in the depth direction, etc.

[0068] In the optimization of the etching shape in a pattern processing apparatus, examples of the input elements are gas flow rate, applied bias, etc., and examples of the output elements are trench shape (taper angle, sub-trench, roughness of trench bottom), etc. In the optimization of the cleaning process in a cleaning apparatus, examples of the input elements are chemical solution type, chemical solution concentration, processing temperature, etc., and examples of the output elements are particles, metal contamination, etching rate, actual concentration, etc. In an example of the optimization of contact resistance in a laser annealing apparatus, examples of the input elements are wavelength, laser intensity, step, etc., and an example of the output element is resistance value.

[0069] As described above, based on the history information of past processes of the semiconductor manufacturing apparatus and the specified target values, this embodiment determines the recipe for the next process of the semiconductor manufacturing apparatus using one or more functions including the estimation model 23. The one or more functions in this embodiment are composed of the estimation model 23. The input of the estimation model 23 further includes the recipe history of the semiconductor manufacturing apparatus.

[0070] As described above, in this embodiment, by using a machine learning method that uses past history information in a semiconductor manufacturing apparatus, it is possible to autonomously capture feature amounts accompanying changes over time, and to construct an accurate estimation model including changes over time. In addition, since an optimal recipe considering changes over time can be derived, the number of maintenance operations can be reduced. Further, since a machine learning model is formed based on history information, it is not necessary to prepare correlation data.

[0071] <Embodiment 2> Embodiment 2 determines the necessity of maintenance of a semiconductor manufacturing apparatus. Thereby, the number of maintenance operations can be reduced. For example, when the estimation result by the optimal recipe found by search is not within the allowable range from the target value, the semiconductor manufacturing management system 100 determines that maintenance is necessary.

[0072] FIGS. 18A, 18B, and 18C are graphs showing examples of changes over time in the output by an estimation model. In each graph, the horizontal axis indicates the gas flow rate as an input to the estimation model, and the vertical axis indicates the concentration distribution as the output of the estimation model. In each graph, the solid line function curve 501 indicates the relationship between the input value and the output value of the estimation model. The semiconductor manufacturing apparatus has a settable range in the input value. Also, an allowable range based on the target value for the output value is set. In each graph, the dashed rectangle 502 indicates a region that satisfies both the settable range and the allowable range.

[0073] FIG. 18A shows a graph in a state where the change over time is small. An appropriate gas flow rate that realizes an output within the allowable range exists within the settable range. Thus, when the influence of the change over time is small, there exists an optimal value of the input that satisfies the target value, and an optimal recipe can be searched for. FIGS. 18B and 18C show graphs of the estimation model affected by the change over time. The function curve 501 of the estimation model is expected to shift in the vertical, horizontal, left, and right directions.

[0074] As shown in FIG. 18B, when the function curve 501 is greatly shifted upward, its extreme value also falls outside the allowable range. As shown in FIG. 18C, when the function curve 501 is greatly shifted to the right, the input value corresponding to the output value within the allowable range is outside the settable range. That is, if, even after searching for the optimal recipe, a recipe whose output value falls within the allowable range based on the target value cannot be found, it should be determined that maintenance of the semiconductor manufacturing apparatus is necessary.

[0075] In this embodiment, an estimation model is configured by including maintenance information in the training data. The estimation model enables determination of the necessity for maintenance and derivation of the optimal recipe. FIG. 19 is a conceptual diagram of the training data 61. The difference from the training data of Embodiment 1 is that the information on the maintenance performed on the input value is included, and further, in addition to the recipe history, the history information includes the maintenance history.

[0076] For example, assume there are three types of maintenance with different contents and effects (Maintenance 1, Maintenance 2, Maintenance 3). The input value of the training data 61 includes the information on the maintenance performed before the process. When no maintenance is performed, the value indicating maintenance is 0. When maintenance is performed, a numerical value corresponding to the type of maintenance is included in the input value. The value indicating maintenance is, for example, 1 for Maintenance 1, 2 for Maintenance 2, and 3 for Maintenance 3. Note that the identifier for maintenance is arbitrary. By adding the details of the maintenance performed to the input and history, the semiconductor manufacturing management system 100 can autonomously determine the necessary maintenance.

[0077] Hereinafter, a specific example of this embodiment for determining the necessity for maintenance will be described. Mainly, the differences from Embodiment 1 will be described. FIG. 20 shows a more specific example of the training data 61. In addition to the training data 31 in Embodiment 1, the input data 611 has a pre-film deposition maintenance column. The pre-film deposition maintenance column indicates the identifier of the maintenance performed before the film deposition process, and "0" indicates that no maintenance was performed.

[0078] FIG. 21 shows an example of the target value 65 for the next film formation process. FIG. 22 shows an example of the optimal input value (recipe) 66 determined by the recipe search unit 24. The optimal input value (recipe) 66 has a cell for pre-film formation maintenance corresponding to the input data 611. The example of FIG. 22 indicates that maintenance 2 should be executed before performing the film formation process indicated by the optimal input value (recipe) 66.

[0079] With reference to FIGS. 23 and 24, the processing of the semiconductor manufacturing management system 100 will be described. FIG. 23 is a logical configuration diagram for explaining the processing of the semiconductor manufacturing management system 100 of the present embodiment. The recipe search unit 24 includes a maintenance effect evaluation unit 245 in addition to the components of Embodiment 1.

[0080] The user includes, in the input data 51 from the input device 151, in addition to the information of Embodiment 1, the identifier of the actually performed maintenance. The maintenance identifier is stored in the training data database 131. The semiconductor manufacturing management system 100 outputs, as the output data 52 from the output device 152, in addition to the information of Embodiment 1, the necessary maintenance notification and the maintenance evaluation result.

[0081] FIG. 24 shows a flowchart of the processing executed by the semiconductor manufacturing management system 100 of the present embodiment. Steps S121 to S128 correspond to steps S101 to 108 in the flowchart of FIG. 15 of Embodiment 1. The flowchart of FIG. 24 has different steps when the determination result in step S123 is NO from that of Embodiment 1.

[0082] In step S123, if the estimated processing result is not within the error tolerance range from the target value (S123: NO), the recipe estimation unit 242 uses the estimation model 23 to derive a maintenance and recipe that achieve a value close to the target value, and estimates the processing result (S129). For example, the recipe estimation unit 242 determines the input value closest to the target value using a random search method or an annealing method. The input value indicates any maintenance to be executed, and the values of the elements corresponding to the maintenance are non-zero values. The output value of the estimation model 23 for the input value is the estimated processing result.

[0083] The recipe estimation unit 242 notifies the user of the necessary maintenance in the output device 152 via the integrated management unit 21. For example, the recipe estimation unit 242 holds a message list associated with maintenance identifiers, and presents the message corresponding to the determined maintenance identifier in the output device 152. The user executes the maintenance of the semiconductor manufacturing apparatus according to the maintenance notification, and inputs the information of the executed maintenance from the input device 151. Note that the semiconductor manufacturing management system 100 may execute the maintenance automatically.

[0084] When the maintenance effect evaluation unit 245 receives the maintenance information via the integrated management unit 21, it evaluates the effect of the maintenance in the semiconductor manufacturing apparatus. For example, the maintenance effect evaluation unit 245 uses a sensor mounted in the chamber to evaluate the thickness or the reduction amount of the deposits on the sidewall. The maintenance effect evaluation unit 245 presents the evaluation result in the output device 152 via the integrated management unit 21. The user can check whether appropriate maintenance has been performed by referring to the evaluation result. Note that the user may execute the maintenance evaluation and omit the maintenance effect evaluation unit 245.

[0085] The device control unit 22 acquires the optimal recipe after maintenance, which is determined by the recipe estimation unit 242, via the integrated management unit 21. The device control unit 22 designates the optimal recipe, instructs the process execution unit 27 to execute the process, and adds the information on maintenance and the optimal recipe to the input data 611 of the training data 61 via the integrated management unit 21. The process execution unit 27 executes the process according to the designated optimal recipe (S130).

[0086] The analysis and evaluation unit 25 analyzes and evaluates the processing result by the process execution unit 27 (S131). The analysis and evaluation unit 25 stores the analysis and evaluation result in the training data database 131 in association with the corresponding optimal recipe via the integrated management unit 21 (S132). The analysis and evaluation result may be input by the user. The analysis and evaluation unit 25 further presents the analysis and evaluation to the user on the output device 152 via the integrated management unit 21. The model configuration unit 241 updates the estimation model 23 using the updated training data database 131 (S133). Then, the flow proceeds to step S128.

[0087] As described above, in the present embodiment, the historical information of the past processes of the semiconductor manufacturing apparatus includes information on the maintenance of the semiconductor manufacturing apparatus. Also, the input to the estimation model 23 includes the maintenance to be performed before the next process. By adding the maintenance implementation details to the process history information, it is possible to autonomously estimate the change over time of the semiconductor manufacturing apparatus from the process history information and determine the necessity of maintenance.

[0088] Specifically, in the present embodiment, an optimal recipe adapted to the device situation can be derived in a state where maintenance is unnecessary, and a maintenance method can be presented when maintenance is necessary. By presenting the necessary maintenance, the user can perform appropriate maintenance in a timely manner. According to the present embodiment, film formation for checking the change over time of the semiconductor manufacturing apparatus becomes unnecessary, and man-hours can be reduced.

[0089] <Embodiment 3> Embodiment 3 determines whether it is necessary to change the substrate to be processed. Thereby, a substrate that does not satisfy the required characteristics can be appropriately changed to a new substrate, and the number of unnecessary processes can be reduced. For example, when the estimation result by the optimal recipe found by search is not within the allowable range from the target value, the semiconductor manufacturing management system 100 determines that it is necessary to change the substrate.

[0090] For example, a SiC substrate has more defects such as dislocations than a Si substrate, and its dislocation density affects the defect density after epitaxy. Therefore, when the output of the estimation model 23 includes the defect density, it is necessary to consider the defect information of the substrate. Also, the warpage of the substrate affects the epitaxial result. Therefore, by taking into account the substrate information, the optimal recipe can be derived accurately.

[0091] The input of the estimation model 23 of this embodiment includes substrate information in addition to the input of Embodiment 2. Therefore, the input data of the training data includes substrate information. When deriving the optimal recipe (the input value that gives an output value within the error tolerance range from the target value), the input substrate information needs to satisfy the specified substrate specifications. If the substrate has many defects, the optimal recipe may not fall within the specified value (a predetermined value).

[0092] Therefore, this embodiment calculates, using the estimation model 23, how much defect can derive the optimal recipe. For example, the number of substrate defects in the substrate information input to the estimation model 23 is gradually reduced, and it is calculated whether the optimal recipe can be derived (falls within the allowable range) under the condition of each number of defects, and a method such as notifying the defect density at which the optimal recipe can be derived is used. After that, the user is asked to determine whether to change the substrate, and if the substrate is not changed, it is determined whether maintenance is required.

[0093] Referring to FIG. 25, the processing of the semiconductor manufacturing management system 100 will be described. In the following, the differences from Embodiment 2 will mainly be described. The logical configuration diagram for explaining the processing of the semiconductor manufacturing management system 100 of this embodiment is substantially the same as FIG. 23 in Embodiment 2. One difference from Embodiment 2 is that the input data 51 includes information on the substrate to be processed. As described above, the input data of the estimation model 23 and the training data includes substrate information indicating the substrate specifications.

[0094] In the flowchart of FIG. 25, steps S141, S143 to S149 correspond to steps S121 to S128 in the flowchart of FIG. 24. In step S142, the integrated management unit 21 acquires the substrate information input by the user from the input device 151 and passes it to the recipe search unit 24.

[0095] In step S144, if the estimation result by the estimation model 23 is outside the error tolerance range from the target value (S144: NO), the recipe estimation unit 242 uses the estimation model 23 to derive the substrate specifications necessary for deriving a recipe that realizes a value close to the target value (S150). Specifically, the recipe estimation unit 242 maintains the recipe and maintenance information in the input values to the estimation model 23 and only changes the substrate information. As described in Embodiment 1, the recipe estimation unit 242 searches for substrate information for which the error between the output value of the estimation model 23 and the target value is within the error tolerance range. The substrate specifications to be searched are selected from a predetermined range.

[0096] If substrate information that can obtain an output value within the tolerance range is found, the recipe estimation unit 242 determines that the substrate is to be changed (S151: YES). The recipe estimation unit 242 presents, via the integrated management unit 21, at the output device 152, a notification of the substrate change and the specifications required for the new substrate to the user. The flow returns to step S142.

[0097] If substrate information that can obtain an output value within the allowable range cannot be found, the recipe estimation unit 242 determines not to change the substrate (S151: NO). Thereafter, the recipe estimation unit 242 determines whether maintenance is required. Steps S152 to S156 correspond to steps S129 to S133 in the flowchart of FIG. 24.

[0098] In the above example, substrate information is obtained from the user via the input device 151. In other examples, the semiconductor manufacturing management system 100 may use a substrate evaluation apparatus to obtain substrate information. The semiconductor manufacturing management system 100 executes an evaluation of the substrate installed in the chamber before performing the processing of the flowchart of FIG. 25. The maintenance processing of the present embodiment may be omitted.

[0099] Hereinafter, examples of GUI images displayed on the output device 152 that can be used in some embodiments will be described. The images described below are merely examples, and any GUI image may be used as long as necessary information can be input and output. First, an example of a GUI image for the user to input data will be described. Information input in the input window is stored in the memory 120 or the auxiliary storage device 130 by the integrated management unit 21.

[0100] FIG. 26 shows an example of a recipe search function setting window 531. The user can enable or disable the recipe search function in the recipe search function setting window 531. When the recipe search function is set to be enabled, each of the processes of the plurality of embodiments in this specification is executed.

[0101] FIG. 27 shows an example of a target value setting input window 532. The target value setting input window 532 receives input of the target value and the allowable range of the estimation model 23 from the user. In the example of FIG. 27, the target value and the allowable range are set for each parameter (element of the output value). Further, the upper and lower limits of the allowable range are set individually.

[0102] FIG. 28 shows an example of the substrate information input window 533. The substrate information input window 533 receives input of information about the substrate from the user. In the example of FIG. 28, the substrate information input window 533 can input information of a plurality of substrates, and the number of the slot into which the substrate is inserted, the substrate ID, and values of a plurality of attributes of the substrate are input. The input values to the estimation model 23 include the attribute values of the substrate information.

[0103] FIG. 29 shows an example of the evaluation result input window 534. The evaluation result input window 534 is a window for the user to input the evaluation result of the object processed by the semiconductor manufacturing apparatus. The evaluation result input window 534 has cells for inputting a process number for identifying the process and an evaluation value of the process result. In the example of the above film formation, at least values of film thickness, impurity concentration, and crystal defect density are input. When the semiconductor manufacturing management system 100 automatically evaluates the object to be processed, this window is not used.

[0104] Next, an example of the GUI image for presenting information to the user will be described. FIG. 30 shows an example of the optimal recipe output window 535. The optimal recipe output window 535 is displayed on the output device 152 via the integrated management unit 21. It includes the recipe content and the estimation result obtained by the recipe. For example, the recipe estimation unit 242 presents to the user, via the optimal recipe output window 535, the recipe estimated to obtain an estimation result within the allowable range specified by the user and the estimation result.

[0105] FIG. 31 shows an example of the maintenance notification message box 536. The maintenance notification message box 536 presents information on the maintenance required for the user to obtain a desired processing result. As described above, information indicating the relationship between the maintenance and the message is preset, and the recipe estimation unit 242 refers to the information, acquires the message corresponding to the maintenance determined using the estimation model 23, and displays it via the maintenance notification message box 536.

[0106] FIG. 32 shows an example of a maintenance evaluation result output window 537. The maintenance evaluation result output window 537 shows the maintenance content (identifier) and the evaluation result of the maintenance. When the maintenance effect evaluation unit 245 evaluates the maintenance result, this window 537 is used. When the user evaluates the maintenance, this window 537 is not used.

[0107] FIG. 33 shows an example of a history information output window 538. The history information output window 538 shows the basic information of the process, the process recipe, and the evaluation result of the object to be processed. The basic information of the process includes, for example, the processing date and time and the identifier of the substrate to be processed. For example, the integrated management unit 21 displays the history information output window 538 in response to a request from the user. The basic information of the process is stored, for example, in the memory 120 or the auxiliary storage device 130 and updated by the integrated management unit 21. The process recipe and the evaluation result of the object to be processed correspond to the input data and output data of the training data database 131.

[0108] <Embodiment 4> Since the methods of Embodiments 1, 2, and 3 use recipe history information, they require a huge amount of computation, which may cause the calculation time to increase and the processing power of the computer to be insufficient. As a countermeasure, a method of reducing the number of variables (elements of the recipe) can be considered, but this may narrow the search range and affect the derivation of the optimal solution. Therefore, Embodiments 4, 5, and 6 will explain a technique for reducing the amount of computation.

[0109] In order to obtain the optimal recipe (recipe within the allowable range) by calculation, as described in Embodiments 1, 2, and 3, it is preferable to autonomously acquire the feature amount of the change over time from the history information. However, as described above, the huge increase in the amount of computation becomes a problem. Therefore, in this embodiment, in order to reduce the amount of computation, factors considered to affect the change over time are added to the input values of the estimation model.

[0110] FIG. 34 shows an example of the input data 711 of the training data including factors considered to affect changes over time. The input data 711 has columns for the integrated processing time, integrated film thickness, and integrated flow rate (SiH 4 ) in addition to the input data 311 of the training data 31 of Embodiment 1. These represent the integrated values (cumulative values) from the last maintenance to the immediately preceding process. The integrated values are examples of historical information of past processes, similar to the recipe history. The output data of the training data in this embodiment is the same as the output data 312 of Embodiment 1. Note that the target value of the recipe and the process may be added to the integrated values input to the estimation model 23 simultaneously with the recipe.

[0111] FIG. 34 shows an example of a film formation process by epitaxial growth of SiC, and the integrated processing time, integrated film thickness, and integrated flow rate (SiH 4 ) represent the integrated time of the epitaxial growth time, the integrated value of the epitaxial growth film thickness, and the integrated value of the flow rate of the gas (SiH 4 ), respectively, from the last maintenance. The integrated processing time and integrated flow rate are the integrated values (cumulative values) of the recipe elements of past processes by the semiconductor manufacturing apparatus, and the integrated value of the growth film thickness is the integrated value (cumulative value) of the processing product. The processing product is the product aimed at by the film formation process and does not include by-products. In this embodiment, the input values of the estimation model 23 include the above integrated values as historical information instead of the recipe history described in Embodiments 1, 2, and 3. Thereby, the variables of the input values can be significantly reduced compared to the input values including the recipe history.

[0112] The recipe estimation unit 242 uses the estimation model 23 to search for a recipe (optimal recipe) that gives an output value within the allowable range from the target value, as described in the other embodiments. There are constraints on the semiconductor manufacturing apparatus for each of the integrated values. For example, when the film thickness target value is 10 μm, the integrated film thickness becomes the current value + 10 μm. The integrated processing time becomes the current value + the processing time. Note that there are upper limit values determined by the apparatus structure for other processing temperatures and processing pressures as well. The optimal recipe is searched within the range of these constraints.

[0113] <Embodiment 5> In Embodiment 5, in order to reduce the amount of calculation, factors considered to affect changes over time are added to the input values of the estimation model. FIG. 35 shows an example of the input data 811 of the training data including factors considered to affect changes over time. The input data 811 has a column for the by-product film thickness in addition to the input data 311 of the training data 31 in Embodiment 1.

[0114] In the input data 811, the by-product film thickness column indicates the by-product film thickness value before performing the process according to the recipe of the same record. The by-product film thickness indicates the film thickness of the by-products deposited in the processing chamber, for example, the film thickness of the by-products deposited on the inner wall of the chamber or the film thickness of the by-products on the wafer susceptor. The by-product film is a film of any substance that is not originally intended to be generated by the process. The by-product film thickness can be measured by the user or by a sensor in the chamber.

[0115] In the present embodiment, the input values of the estimation model 23 include the by-product film thickness value before processing, as historical information, instead of the recipe history described in Embodiments 1, 2, and 3. Since the by-product film thickness changes due to past processes, it indicates the history of the processes. By using the by-product film thickness as historical information, the variables of the input values can be significantly reduced as compared with the input values including the recipe history. In addition, since the by-product film thickness more directly indicates the changes over time of the semiconductor manufacturing apparatus (chamber), the optimal recipe can be estimated more appropriately.

[0116] <Embodiment 6> In Embodiment 6, the recipe for the next process of the semiconductor manufacturing apparatus is determined using an estimation model (function) and a change-over-time function. In this embodiment, the actual processing result (output of the training data) is corrected by the change-over-time function. The correction by the change-over-time function removes the components caused by the change-over-time of the semiconductor manufacturing apparatus. That is, the corrected processing result is the processing result assuming that there is no change-over-time of the semiconductor manufacturing apparatus.

[0117] The input values to the estimation model 23 in this embodiment include the recipe candidates for the following processes and do not include historical information as in the other embodiments described above. The output data of the training data is the processing result assuming no change over time in the semiconductor manufacturing apparatus, and is a value obtained by correcting the actual processing result with a function of change over time. In the comparison between the output value (estimated value) of the estimation model 23 and the target value, the estimated value and / or the target value are compared after being corrected by the function of change over time. In this way, the estimation model 23 outputs an estimated value of the processing result for the recipe of the semiconductor manufacturing apparatus assumed to have no change over time.

[0118] As described above, since the estimation model 23 does not include historical information in the input values, the processing load for searching for the optimal recipe using the estimation model 23 can be reduced. The historical information of the semiconductor manufacturing apparatus is used to create the function of change over time. Hereinafter, a method for deriving the function of change over time will be described using an example. The function of change over time is derived by regression analysis using historical information.

[0119] As an example, the defect density D, which is one of the film formation results in a certain chamber state, is described by the following function g. The variable t of the function g represents the thickness of the by-product film in the chamber. D = g(t)

[0120] When the recipe a is implemented when the thickness of the by-product film in the chamber is t1 or t2, the defect densities D_t1 and D_t2 are represented as follows, respectively. D_t1 = g_a(t1) D_t2 = g_a(t2)

[0121] Here, since the function g_a(t) is unknown, regression analysis is performed to derive the function g_a(t). FIG. 36 shows an example of the graph of the function g_a(t). The black dots in the graph are the measured values, and the actual curve is the curve fitted to the measured values and corresponds to the function g_a(t).

[0122] Next, consider the function \(g_a(t)\). The function \(g_a(t)\) is considered to be the sum of a factor resulting only from recipe \(a\) and a factor resulting from changes over time. Therefore, the function \(g_a(t)\) can be rewritten as follows. \(g_a(t)=D_a + f_a(t)\) The function \(D_a\) is a constant representing the defect density caused by recipe \(a\) regardless of changes over time. The function \(f_a(t)\) represents the defect density caused by changes over time in the process of recipe \(a\). The function \(f_a(t)\) is a function of change over time.

[0123] Next, consider the relationship of \(f(t)\) when recipe \(a\) and recipe \(b\) are implemented. When the recipe is changed, an increase or decrease in the influence of changes over time can be considered. However, since the physical mechanism causing changes over time does not change, the following relationship holds. \(f_b(t)=cf_a(t)\) That is, \(g_b(t)\) is \(g_b(t)=D_b + f_b(t)=D_b + cf_a(t)\) Note that \(D_b\) is a constant representing the defect density caused by recipe \(b\).

[0124] Since there are two unknowns, \(D_b\) and \(c\), if there are two processing results for recipe \(b\), the function of change over time in recipe \(b\) can be derived. As described above, the model configuration unit 241 derives the function of change over time for each recipe and further constructs the estimation model 23 that is not affected by changes over time. The input of the estimation model 23 does not include the processing history information.

[0125] As described above, it becomes possible to remove the influence caused by changes over time from the output data of the training data using the function of change over time, and it becomes easy to construct the estimation model 23 that is not affected by changes over time. In the above description, the defect density is given as an example of the output value. However, the output value may be, for example, the concentration or average concentration or in-plane concentration variation of impurities at a certain coordinate within the wafer, the film thickness or average film thickness or in-plane film thickness variation at a certain coordinate within the wafer, downfall defects, stacking defects, basal plane dislocations, etc.

[0126] In addition, although the by-product thickness of the chamber wall has been given as an example of the input value, the input value may be, for example, the by-product thickness of the susceptor or the variation in the inner diameter caused by the clogging of the injector. Although it is necessary to monitor the by-product thickness and the inner diameter, for the sake of simplicity, instead of these, the input value may be, for example, the integrated film thickness, the integrated flow rate of the material gas, the integrated amount of heat applied to the chamber, etc.

[0127] The function of change over time can be used for determining whether maintenance is required. The recipe estimation unit 242 may determine whether maintenance is required based on the comparison result between the output of the function of change over time and the threshold value. FIG. 37 shows an example of a graph of the function of change over time of recipe a. For example, when the value of the function of change over time according to the recipe determined as the optimal recipe exceeds a specified value (a value determined in advance), the recipe estimation unit 242 may determine that maintenance is necessary.

[0128] Note that the present invention is not limited to the above-described embodiments and includes various modifications. For example, the above-described embodiments have been described in detail for the purpose of easily explaining the present invention, and are not necessarily limited to those having all the configurations described. Also, a part of the configuration of one embodiment can be replaced with the configuration of another embodiment, and the configuration of another embodiment can be added to the configuration of one embodiment. Also, for a part of the configuration of each embodiment, it is possible to add, delete, or replace with other configurations.

[0129] In addition, each of the above-described configurations, functions, processing units, etc. may be realized in hardware by designing a part or all of them, for example, by using an integrated circuit. Also, each of the above-described configurations, functions, etc. may be realized in software by a processor interpreting and executing a program for realizing each function. Information such as a program, a table, and a file for realizing each function can be stored in a memory, a recording device such as a hard disk or an SSD (Solid State Drive), or a recording medium such as an IC card or an SD card.

[0130] In addition, the control lines and information lines show those considered necessary for explanation purposes, and not all control lines and information lines are necessarily shown on the product. In reality, it may be considered that almost all components are interconnected.

Explanation of Signs

[0131] 21 Integrated Management Department, 22 Device Control Department, 23 Estimation Model, 24 Recipe Search Department, 25 Analysis and Evaluation Department, 27 Process Execution Department, 31 Training Data, 35 Target Value, 41 Input Value, 42 Output Value, 51 Input Data at Input Device, 52 Output Data at Output Device, 61 Training Data, 65 Target Value, 66 Optimal Input Value, 100 Semiconductor Manufacturing Management System, 110 Processor, 120 Memory, 121 Integrated Management Program, 122 Device Control Program, 123 Estimation Model Program, 124 Recipe Search Program, 125 Analysis and Evaluation Program, 130 Auxiliary Storage Device, 131 Training Data Database, 140 Network Interface, 145 I / O Interface, 151 Input Device, 152 Output Device, 241 Model Configuration Section, 242 Recipe Estimation Section, 243 Convergence Judgment Section, 245 Maintenance Effect Evaluation Section, 311, 611, 711, 811 Input Data of Training Data, 312, 612 Output Data of Training Data, 400 Cluster Device, 401 Substrate Analysis Chamber, 402 Cleaning Chamber, 403 Analysis and Evaluation Chamber, 404 Processing Chamber, 405 Recycling Chamber, 406 Load Lock Chamber and Transfer Chamber, 450 SiC Epitaxial Cluster Device, 451 Substrate Analysis Chamber, 452 Epitaxial Analysis Chamber, 453 Defect Analysis Chamber, 454 Epitaxial Growth Chamber, 455 CMP Chamber, 456 Load Lock Chamber and Transfer Chamber, 501 Function Curve, 502 Dashed Rectangle, 531 Recipe Search Function Setting Window, 532 Target Value Setting Input Window, 533 Substrate Information Input Window, 534 Evaluation Result Input Window, 535 Optimal Recipe Output Window, 536 Maintenance Notification Message Box, 537 Maintenance Evaluation Result Output Window, 538 History Information Output Window

Claims

1. A management system that determines a recipe for a film formation process in a semiconductor manufacturing apparatus that forms a SiC film on a SiC substrate by epitaxial growth, comprising: one or more storage devices; one or more processors; The semiconductor manufacturing equipment includes a means for monitoring a thickness of by-products on a chamber wall or a susceptor, the one or more storage devices store history information of past film formation processes of the semiconductor manufacturing equipment; The one or more processors acquire target values ​​of characteristics of a film to be formed in a next film formation process by the semiconductor manufacturing equipment; determining a recipe for the next film formation process of the semiconductor manufacturing equipment using one or more functions including an estimation model based on the history information and the target value; an input of the estimation model includes a recipe candidate for the next film formation process of the semiconductor manufacturing equipment; an output of the estimation model includes an estimate of a property of the resulting film; the one or more functions include a time-varying function indicating a time-varying change of the semiconductor manufacturing equipment, the thickness of the by-product is utilized to derive the aging function; the time-varying function is constructed based on the historical information including a thickness of the by-product; The one or more processors determine whether or not maintenance of the semiconductor manufacturing equipment is required based on a comparison result between the value of the time-varying function and a specified value.

2. The management system according to claim 1, A management system in which the one or more processors compare the target value and the estimated value after correcting the target value and / or the estimated value using the time-varying function, and determine the recipe based on the result of the comparison.

3. A method for determining a recipe for a film formation process in a semiconductor manufacturing apparatus for forming a SiC film on a SiC substrate by epitaxial growth, comprising: Monitoring the thickness of the by-products on the chamber walls or the susceptor; The management system stores history information of past film formation processes of the semiconductor manufacturing equipment, The method comprises: The management system acquires target values ​​of characteristics of a film to be formed in a next film formation process by the semiconductor manufacturing equipment, the management system determines a recipe for the next film formation process of the semiconductor manufacturing equipment using one or more functions including an estimation model based on the history information and the target value; an input of the estimation model includes a recipe candidate for the next film formation process of the semiconductor manufacturing equipment; an output of the estimation model includes an estimate of a property of the resulting film; the one or more functions include a time-varying function indicating a time-varying change of the semiconductor manufacturing equipment, the thickness of the by-product is utilized to derive the aging function; the time-varying function is constructed based on the historical information including a thickness of the by-product; The method further comprises the step of: determining whether or not maintenance of the semiconductor manufacturing equipment is required based on a result of comparing the value of the time-varying function with a specified value.

Images