JP2016181622A - Processing system, processing method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a highly-accurate and user-friendly processing system, a processing method, and a program.SOLUTION: A control unit 50 of a heat treatment device, comprises: a recipe storage unit 52 which stores processing conditions; a learning history file storage unit 53 which stores learning history files; a model storage unit 51 which stores processing change models; a processing information receiving unit which receives information related to processing results; processing condition identifying means for identifying the processing conditions; processing result determining means for determining whether the processing results are in an allowable range; use determining means for determining whether to use the learning history file storing the same processing conditions according to whether device conditions changed after the learning history file has been created; learning history file determining means for determining the identified learning history file from the stored learning history files; processing condition calculating means for calculating processing conditions close to target processing results on the basis of the identified processing conditions, the determined learning history file, and the processing change models; and processing condition update means for updating the calculated processing conditions to the identified processing conditions.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a processing system, a processing method, and a program for processing an object to be processed such as a semiconductor wafer.

  In a manufacturing process of a semiconductor device, a batch type processing system is used that collectively performs film formation processing, oxidation processing, diffusion processing, or the like on a large number of objects to be processed, for example, semiconductor wafers. A batch type processing system can efficiently process semiconductor wafers, but it is difficult to ensure the uniformity of processing of a large number of semiconductor wafers.

  In order to solve such a problem, for example, Patent Document 1 proposes a heat treatment apparatus that automatically adjusts the temperature of the outside air so that the temperature of the outside air taken into the heater chamber becomes constant.

JP 2005-183596 A

  By the way, some of such processing systems are equipped with a learning function to improve accuracy. However, when using a processing system equipped with a learning function, the user selects to use the learning function, and further selects a learning history file in which information on past processing conditions and processing results is accumulated. There is a problem that work is necessary and it is difficult to use (it takes time). Further, if the user selects the learning history file incorrectly, there is a problem that the calculation result is incorrect and the accuracy of the processing result is lowered.

  The present invention has been made in view of the above circumstances, and an object thereof is to provide a processing system, a processing method, and a program that are accurate and easy to use.

In order to achieve the above object, a processing system according to a first aspect of the present invention includes:
A processing condition storage means for storing processing conditions corresponding to the processing content of the object to be processed contained in the processing chamber;
Learning history file storage means for storing a learning history file related to the processing conditions stored by the processing condition storage means;
A process change model storage unit that stores a process change model indicating a relationship between a change in the process condition and a change in the process result;
Processing information receiving means for receiving information on a processing result targeted by the object;
A processing condition specifying means for specifying a required processing condition based on information on a target processing result received by the processing information receiving means and a processing condition stored by the processing condition storage means;
A processing result determining means for determining whether or not a processing result processed under the processing condition specified by the processing condition specifying means is within an allowable range of information related to a target processing result received by the processing information receiving means;
When it is determined by the processing result determination means that it is not within the allowable range, a learning history file in which at least a part of the same processing condition is stored is specified from the learning history file stored by the learning history file storage means, Use discriminating means for discriminating whether or not to use the learning history file depending on whether or not at least a part of the device condition has changed since the specified learning history file was created;
A learning history file determining means for determining a learning history file identified from the learning history file stored by the learning history file storage means when the use determining means determines that the learning history file is used;
Based on the processing condition specified by the processing condition specifying means, the learning history file determined by the learning history file determining means, and the process change model stored in the process change model storage means, the target is set. Processing condition calculation means for calculating a processing condition close to the processing result;
Processing condition update means for updating the processing condition calculated by the processing condition calculation means to the processing condition specified by the processing condition specifying means;
A processing system comprising:

  The use determining unit determines whether or not the device condition is changed based on, for example, the device operation log and the process log.

For example, the processing content is a film forming process,
The processing result is the thickness of the thin film formed on the object to be processed or the impurity concentration in the film.

The processing method according to the second aspect of the present invention is:
A processing condition storage step for storing processing conditions according to the processing content of the object to be processed contained in the processing chamber;
A learning history file storage step for storing a learning history file related to the processing conditions stored in the processing condition storage step;
A process change model storage step for storing a process change model indicating a relationship between a change in the process condition and a change in the process result;
A process information receiving step for receiving information on a target processing result of the object to be processed;
A processing condition specifying step for specifying a required processing condition based on information on a target processing result received in the processing information receiving step and a processing condition stored in the processing condition storage step;
A processing result determining step for determining whether or not the processing result processed under the processing condition specified in the processing condition specifying step is within an allowable range of information related to the target processing result received in the processing information receiving step;
When it is determined in the processing result determination step that it is not within the allowable range, the learning history file stored in the learning history file storage step identifies a learning history file in which at least a part of the same processing condition is stored, A use determination step of determining whether to use the learning history file, based on whether or not at least a part of the device condition has changed since the specified learning history file was created;
When it is determined that the learning history file is used in the use determination step, a learning history file determination step for determining a learning history file specified from the learning history file stored in the learning history file storage step;
Based on the processing condition specified in the processing condition specifying step, the learning history file determined in the learning history file determination step, and the processing change model stored in the processing change model storage step, the target is set. A processing condition calculation step for calculating a processing condition close to the processing result;
A processing condition update step for updating the processing condition calculated in the processing condition calculation step to the processing condition specified in the processing condition specifying step;
It is characterized by comprising.

The program according to the third aspect of the present invention is:
Computer
Processing condition storage means for storing processing conditions according to the processing content of the object to be processed housed in the processing chamber;
Learning history file storage means for storing a learning history file related to the processing conditions stored by the processing condition storage means;
A process change model storage means for storing a process change model indicating a relationship between a change in the process condition and a change in the process result;
Processing information receiving means for receiving information on a processing result targeted by the object to be processed;
A processing condition specifying means for specifying a required processing condition based on information on a target processing result received by the processing information receiving means and a processing condition stored by the processing condition storage means;
A processing result determining means for determining whether or not the processing result processed under the processing condition specified by the processing condition specifying means is within an allowable range of information regarding the target processing result received by the processing information receiving means;
When it is determined by the processing result determination means that it is not within the allowable range, a learning history file in which at least a part of the same processing condition is stored is specified from the learning history file stored by the learning history file storage means, Use discriminating means for discriminating whether or not to use the learning history file depending on whether or not at least a part of the device condition has changed since the identified learning history file was created;
A learning history file determining means for determining a learning history file specified from the learning history file stored by the learning history file storage means when the use determining means determines that the learning history file is used;
Based on the processing condition specified by the processing condition specifying means, the learning history file determined by the learning history file determining means, and the process change model stored in the process change model storage means, the target is set. Processing condition calculation means for calculating processing conditions close to the processing result;
Processing condition update means for updating the processing condition calculated by the processing condition calculation means to the processing condition specified by the processing condition specifying means;
It is made to function as.

  According to the present invention, it is possible to provide a processing system, a processing method, and a program that are accurate and easy to use.

It is a figure which shows the structure of the heat processing apparatus which concerns on embodiment of this invention. It is a figure which shows the zone in a reaction tube. It is a figure which shows the structural example of the control part of FIG. It is an example of a thickness change model showing a relationship between the thickness variation of the SiO ₂ film formed with a change in temperature of the heater. It is a flowchart for demonstrating heat processing. It is a flowchart for demonstrating a learning history file specific process.

Hereinafter, the present embodiment will be described taking as an example the case where the processing system, the processing method, and the program of the present invention are applied to the batch type vertical heat treatment apparatus shown in FIG. In this embodiment mode, an example of forming a SiO ₂ film on a semiconductor wafer by using dichlorosilane (SiH ₂ Cl ₂ ) and dinitrogen monoxide (N ₂ O) as a film forming gas is taken as an example. The present invention will be described.

  As shown in FIG. 1, the heat treatment apparatus 1 of the present embodiment includes a reaction tube 2 having a substantially cylindrical shape and a ceiling. The reaction tube 2 is arranged so that its longitudinal direction is in the vertical direction. The reaction tube 2 is made of a material excellent in heat resistance and corrosion resistance, for example, quartz.

  A substantially cylindrical manifold 3 is provided below the reaction tube 2. The upper end of the manifold 3 is airtightly joined to the lower end of the reaction tube 2. An exhaust pipe 4 for exhausting the gas in the reaction tube 2 is airtightly connected to the manifold 3. The exhaust pipe 4 is provided with a pressure adjusting unit 5 including a valve, a vacuum pump, and the like, and the inside of the reaction pipe 2 is adjusted to a desired pressure (degree of vacuum).

  A lid 6 is disposed below the manifold 3 (reaction tube 2). The lid body 6 is configured to be movable up and down by the boat elevator 7. When the lid body 6 is raised by the boat elevator 7, the lower side (furnace port portion) of the manifold 3 (reaction tube 2) is closed. It arrange | positions so that the lower side (furnace port part) of the reaction tube 2 may be opened when the body 6 descends.

  A wafer boat 9 is provided above the lid 6 via a heat insulating cylinder (heat insulator) 8. The wafer boat 9 is a wafer holder that accommodates (holds) an object to be processed, for example, a semiconductor wafer W. In the present embodiment, a plurality of semiconductor wafers W, for example, at a predetermined interval in the vertical direction, for example, It is configured to accommodate 150 sheets. Then, the semiconductor wafer W is accommodated in the wafer boat 9 and the lid 6 is raised by the boat elevator 7, whereby the semiconductor wafer W is loaded into the reaction tube 2.

  Around the reaction tube 2, for example, a heater unit 10 made of a resistance heating element is provided so as to surround the reaction tube 2. The heater 10 heats the inside of the reaction tube 2 to a predetermined temperature, and as a result, the semiconductor wafer W is heated to a predetermined temperature. The heater unit 10 includes, for example, heaters 11 to 15 arranged in five stages, and power controllers 16 to 20 are connected to the heaters 11 to 15, respectively. For this reason, the heaters 11 to 15 can be independently heated to desired temperatures by supplying power to the power controllers 16 to 20 independently. Thus, the reaction tube 2 is divided into five zones as shown in FIG. 2 by the heaters 11 to 15. For example, when TOP (ZONE 1) in the reaction tube 2 is heated, the power controller 16 is controlled to heat the heater 11 to a desired temperature. When heating CENTER (CTR (ZONE 3)) in the reaction tube 2, the power controller 18 is controlled to heat the heater 13 to a desired temperature. When heating BOTTOM (BTM (ZONE5)) in the reaction tube 2, the power controller 20 is controlled to heat the heater 15 to a desired temperature.

  The manifold 3 is provided with a plurality of processing gas supply pipes for supplying a processing gas into the reaction tube 2. In FIG. 1, three process gas supply pipes 21 to 23 that supply process gas to the manifold 3 are illustrated. The processing gas supply pipe 21 is formed so as to extend from the side of the manifold 3 to the vicinity of the upper portion of the wafer boat 9 (ZONE 1). The processing gas supply pipe 22 is formed so as to extend from the side of the manifold 3 to the vicinity of the center of the wafer boat 9 (ZONE 3). The processing gas supply pipe 23 is formed so as to extend from the side of the manifold 3 to the vicinity of the lower portion of the wafer boat 9 (ZONE 5).

  The process gas supply pipes 21 to 23 are provided with flow rate adjusting units 24 to 26, respectively. The flow rate adjusting units 24 to 26 are configured by a mass flow controller (MFC) or the like for adjusting the flow rate of the processing gas flowing in the processing gas supply pipes 21 to 23. For this reason, the processing gas supplied from the processing gas supply pipes 21 to 23 is adjusted to a desired flow rate by the flow rate adjusting units 24 to 26 and supplied to the reaction pipe 2 respectively.

  Further, the heat treatment apparatus 1 includes a control unit (controller) 50 for controlling processing parameters such as a gas flow rate in the reaction tube 2, a pressure, and a processing atmosphere temperature. The control unit 50 outputs control signals to the flow rate adjustment units 24 to 26, the pressure adjustment unit 5, the power controllers 16 to 20 of the heaters 11 to 15, and the like. FIG. 3 shows the configuration of the control unit 50.

  As shown in FIG. 3, the control unit 50 includes a model storage unit 51, a recipe storage unit 52, a learning history file storage unit 53, a ROM (Read Only Memory) 54, a RAM (Random Access Memory) 55, It comprises an I / O (Input / Output Port) port 56, a CPU (Central Processing Unit) 57, a bus 58 for interconnecting them, and a log storage unit 60.

The model storage unit 51 stores a film thickness change model indicating a relationship between a change in the heater temperature and a change in the film thickness of the formed SiO ₂ film. FIG. 4 shows an example of the film thickness change model. As shown in FIG. 4, the film thickness change model indicates how much the film thickness of the SiO ₂ film formed on each ZONE changes when the temperature of the predetermined ZONE is raised by 1 ° C. For example, as shown in FIG. 4, when the temperature setting value of ZONE1 is raised by 1 ° C. by controlling the power controller 16 to heat the heater 11, the thickness of the SiO ₂ film formed on the ZONE1 increases by 2 nm. the film thickness of the SiO ₂ film formed ZONE2 decreases 0.7 nm, the film thickness of the SiO ₂ film formed ZONE3 increases 0.8 nm, the film thickness of the SiO ₂ film formed on Zone 4 0. Decrease by 05 nm.

  The recipe storage unit 52 stores a process recipe for determining a control procedure in accordance with the type of film forming process executed by the heat treatment apparatus 1. The process recipe is a recipe prepared for each process (process) actually performed by the user. The temperature and time from the loading of the semiconductor wafer W to the reaction tube 2 until the unloaded semiconductor wafer W is unloaded. Stipulate the gas flow rate, etc. Specifically, the temperature change of each part, the pressure change in the reaction tube 2, the start and stop timings of gas supply, the supply amount, etc. are defined.

  The learning history file storage unit 53 stores the created learning history file. In the learning history file, for example, the date and time created and registered by the adjustment process, process conditions (temperature, time, gas flow rate, etc.), necessary process log information, and the like are stored. The necessary process log information includes, for example, a total transfer number on the wafer boat 9, a product transfer layout indicating the number and position of products, a dummy wafer layout indicating the number and position of dummy wafers, and the number and position of monitor wafers. A monitor wafer layout indicating the accumulated film thickness, a cumulative film thickness of the reaction tube 2 (process tube), and the like are stored. By using the learning history file in the process described later, the accuracy of the process is improved.

The ROM 54 is a recording medium that includes an EEPROM (Electrically Erasable Programmable Read-Only Memory), a flash memory, a hard disk, and the like, and stores an operation program of the CPU 57 and the like.
The RAM 55 functions as a work area for the CPU 57.

  The I / O port 56 supplies measurement signals related to temperature, pressure, and gas flow rate to the CPU 57, and outputs control signals output from the CPU 57 to the respective units (the pressure adjustment unit 5, the power controllers 16 to 20 of the heaters 11 to 15, the flow rate). Output to the adjusting units 24-26 and the like). The I / O port 56 is connected to an operation panel 59 for an operator to operate the heat treatment apparatus 1.

  The CPU 57 constitutes the center of the control unit 50, executes an operation program stored in the ROM 54, and follows the process recipe stored in the recipe storage unit 52 in accordance with an instruction from the operation panel 59, and the heat treatment apparatus 1. To control the operation.

Based on the film thickness change model stored in the model storage unit 51 and the film thickness of the formed SiO ₂ film, the CPU 57 sets each ZONE (ZONE 1 to 5) in the reaction tube 2 in which the target film thickness is formed. ) To calculate the set temperature of the heaters 11 to 15.

  In addition, the CPU 57 specifies a learning history file to be used for processing from the learning history files stored in the learning history file storage unit 53. In this example, when the process conditions that match the process logs that store the process conditions (temperature, time, gas flow rate, etc.) are stored, large-scale maintenance is not performed, and the required process logs match, the learning history Identify the file.

  The learning history file to be used for processing is identified by, for example, the CPU 57 specifying the process recipe from the process recipe stored in the recipe storage unit 52 by the operator. A learning history file that stores process conditions that match the process conditions may be specified from the learning history file storage unit 53.

  The bus 58 transmits information between the units.

  The log storage unit 60 stores various logs related to the executed processing, for example, a process log and an alarm log. For example, when a large-scale maintenance is performed and the T / C is removed, a T / C disconnection alarm is generated, and an alarm log indicating the content and date is stored in the log storage unit 60. Further, when the temperature in the furnace is lowered to room temperature, a T / C short alarm is generated and an alarm log indicating the content and date is stored in the log storage unit 60. Further, when the cleaning recipe is executed, a process log indicating the content and date / time is stored in the log storage unit 60. In this way, it is possible to determine whether or not the condition of the apparatus has changed based on the presence or absence of the process log and the alarm log. As will be described later, the CPU 57 uses these logs stored in the log storage unit 60 to determine whether large-scale maintenance has been performed on the heat treatment apparatus 1.

  Next, a heat treatment method (heat treatment) including an adjustment method for adjusting the process conditions in the reaction tube 2 (ZONE 1 to 5) using the heat treatment apparatus 1 configured as described above will be described. The adjustment process is to calculate a process condition (temperature in this example) where the film thickness is closest to the target film thickness. FIG. 5 is a flowchart for explaining the heat treatment of this example.

First, the operator operates the operation panel 59 and inputs necessary information such as a process type to be executed in the adjustment process. Specifically, the operator performs a processing apparatus to be performed in the adjustment process, a process type, in this example, formation of a SiO ₂ film of dichlorosilane and dinitrogen monoxide (N ₂ O) (DCS-HTO). And the film thickness (target film thickness) of the target SiO ₂ film is input for each zone, for example.

  The control unit 50 (CPU 57) determines whether necessary information such as a process type has been input (step S1). When the CPU 57 determines that necessary information has been input (step S1; Yes), the CPU 57 reads out a process recipe corresponding to the input process type from the recipe storage unit 52 (step S2). Process conditions such as pressure and temperature in the reaction tube 2 are stored in the process recipe. For example, the temperature of ZONE 1 to 5 in the reaction tube 2 is stored in the process recipe.

Next, the CPU 57 executes a film forming process under the process conditions of the read process recipe (step S3). Specifically, the CPU 57 lowers the boat elevator 7 (the lid body 6) and arranges the wafer boat 9 on which the semiconductor wafer W (monitor wafer) is mounted on at least each ZONE on the lid body 6. Next, the CPU 57 raises the boat elevator 7 (lid body 6) and loads the wafer boat 9 (semiconductor wafer W) into the reaction tube 2. Then, the CPU 57 controls the pressure adjusting unit 5, the power controllers 16 to 20 of the heaters 11 to 15, the flow rate adjusting units 24 to 26, and the like according to the recipe in which the updated process conditions are described, so that the SiO ₂ is deposited on the semiconductor wafer W. A film is formed.

When the film forming process is completed, the CPU 57 measures the film thickness of the formed SiO ₂ film (step S4). For example, the CPU 57 lowers the boat elevator 7 (the lid body 6), unloads the semiconductor wafer W on which the SiO ₂ film is formed, transports the semiconductor wafer W to, for example, a measuring device (not shown), and the semiconductor wafer The thickness of the SiO ₂ film formed on W is measured. When the measurement apparatus measures the film thickness of the SiO ₂ film formed on the semiconductor wafer W, for example, the measured film thickness data of the SiO ₂ film is transmitted to the heat treatment apparatus 1 (CPU 57). CPU57 by receiving the film thickness data of the measured SiO ₂ film, to identify the thickness of the formed SiO ₂ film. Note that the operator may operate the operation panel 59 to input the measurement result.

When the film thickness of the formed SiO ₂ film is measured, the CPU 57 determines whether or not the measured film thickness is within an allowable range (step S5). The term “within the allowable range” means that it is included within a predetermined range allowable from the input target film thickness. For example, it is within ± 1% from the input target film thickness.

  When determining that the measured film thickness is not within the allowable range (step S5; No), the CPU 57 executes a learning history file specifying process (step S6). FIG. 6 is a flowchart for explaining the learning history file specifying process. In this example, as will be described later, the learning history file is specified when the process conditions match and the apparatus condition does not change. Regarding the change in the device condition, it was determined that the device condition was not changed when the large-scale maintenance was not performed and the necessary process logs coincided.

  First, the CPU 57 reads a process log corresponding to the film thickness measurement result (step S21). Next, the CPU 57 determines whether or not a learning history file storing a process condition that matches the process condition stored in the read process log is stored in the learning history file storage unit 53 (step S22). When the CPU 57 determines that the learning history file storing the matching process conditions is not stored in the learning history file storage unit 53 (step S22; No), the CPU 57 ends this process without specifying the learning history file. .

  When the CPU 57 determines that the learning history file storing the matching process conditions is stored in the learning history file storage unit 53 (step S22; Yes), the date and time when the determined learning history file is created and registered is specified. (Step S23). Next, the CPU 57 determines whether or not there is a log indicating that a large-scale maintenance has been performed after the specified date and time among the logs stored in the log storage unit 60 (step S24). For example, the CPU 57 stores an alarm log indicating that the T / C has been removed and the T / C disconnection alarm has occurred in the log storage unit 60 after the specified date and time, and the temperature in the furnace has decreased to room temperature. It is determined whether there is an alarm log indicating that a C short alarm has occurred or a process log indicating that a cleaning recipe has been executed. If the CPU 57 determines that such process log and alarm log exist (step S24; Yes), the CPU 57 ends this process without specifying the learning history file.

  If the CPU 57 determines that such process log and alarm log do not exist (step S24; No), the process log information stored in the learning history file determined in step S22 (the process log selected during the previous calculation) Information) and the current process log information (process log information selected during the current calculation) are compared (step S25). And CPU57 discriminate | determines whether there exists a difference in the part which should not have a difference in the information of both process logs (step S26). For example, the CPU 57 performs a total transfer number on the wafer boat 9, a product transfer layout indicating the number and position of products, a dummy wafer layout indicating the number and position of dummy wafers, a monitor wafer layout indicating the number and position of monitor wafers, When the accumulated film thickness of the reaction tube 2 (process tube) is larger than the previous time, it is determined that there is no difference in a portion where there should be no difference. If the CPU 57 determines that there is a difference in a portion that should not be different (step S26; Yes), the CPU 57 ends this process without specifying a learning history file.

  If the CPU 57 determines that there is no difference in the portion where there should not be a difference (step S26; No), this learning history file is identified as the device condition has not changed (step S27), and this process is terminated. To do. As described above, the learning history file is specified when the process conditions match and the apparatus condition does not change (the large-scale maintenance is not performed and the necessary process logs match).

  Here, there is no need for the operator to specify in consideration of whether or not to use the learning history file, which eliminates the problem of time and effort. Further, it is possible to eliminate the human error that the operator makes a mistake in selecting the learning history file, and the problem that the accuracy of the processing result is reduced is eliminated. For this reason, it is possible to perform processing that is accurate and easy to use.

  Subsequently, based on the read process recipe, the specified learning history file, and the film thickness change model stored in the model storage unit 51, the CPU 57 sets process conditions such as the temperature closest to the input target film thickness. Is calculated (step S7). If the learning history file is not specified in step S6, the CPU 57 inputs the target film thickness based on the read process recipe and the film thickness change model stored in the model storage unit 51. Process conditions such as the temperature closest to

  As the process condition calculation method, various methods can be used. For example, a method using a learning function using a Kalman filter disclosed in US Pat. No. 5,991,525 can be used.

  Next, the CPU 57 creates a new learning history file for storing the calculated new process condition and registers it in the learning history file storage unit 53 (step S8). Further, the CPU 57 updates the process recipe with the calculated process condition (temperature) (step S9). Then, the CPU 57 executes a film forming process under the registered process conditions (temperature) (step S3).

  When determining that the measured film thickness is within the allowable range (step S5; Yes), the CPU 57 determines whether or not the process recipe is completed (step S10). If the CPU 57 determines that the process recipe has not ended (step S10; No), the CPU 57 continues to perform the film forming process (step S3). When the CPU 57 determines that the process recipe has ended (step S10; Yes), the CPU 57 ends this process.

  As described above, according to the present embodiment, the process condition is matched, large-scale maintenance is not performed, and the necessary process logs are matched to identify the learning history file. This eliminates the need for the work of specifying whether or not to use the learning history file, thus eliminating the problem of time and effort. Furthermore, it is possible to eliminate the human error that the operator makes a mistake in selecting the learning history file, and the problem that the accuracy of the processing result is reduced is eliminated. For this reason, it is possible to perform processing that is accurate and easy to use.

  In addition, this invention is not restricted to said embodiment, A various deformation | transformation and application are possible. Hereinafter, other embodiments applicable to the present invention will be described.

  In the above embodiment, the present invention has been described by taking the case where the learning history file is specified when the process conditions match and the device condition does not change. For example, the process conditions match and the device condition The learning history file may also be specified when a part of the process condition does not change or when a part of the process condition matches and the apparatus condition does not change. Also in these cases, there is no problem that it takes time to specify the learning history file of the operator. For example, among the process conditions, learning history files having the same temperature and the like may be listed, and the operator may select from the listed learning history files. In addition, learning history files that match some of the necessary process logs may be listed, and the operator may select from the listed learning history files. Furthermore, a priority order may be set for process conditions and the like, and a learning history file that matches a condition with a high priority order may be specified. Further, the learning history file may be specified even if large-scale maintenance is performed.

  In the above-described embodiment, the present invention has been described by taking the case where the learning history file is stored in the learning history file storage unit 53 as an example. However, for example, another server or computer connected via a network may be used. The learning history file may be specified from the inside.

In the above embodiment, the present invention has been described by taking as an example the case where a SiO ₂ film is formed using dichlorosilane and dinitrogen monoxide. For example, a SiN film using dichlorosilane and ammonia (NH ₃ ). The present invention can also be applied to the film formation.

In the above-described embodiment, the present invention has been described by taking the case of forming a SiO ₂ film as an example. It can be applied to various heat treatment apparatuses.

In the above embodiment, the present invention has been described with respect to the target processing result by taking the thickness of the SiO ₂ film as an example. However, for example, the impurity concentration (impurity concentration in the film) contained in the Si film may be used. . In this case, the model storage unit 51 stores a change model indicating the relationship between the change in the temperature of the heaters 11 to 15 and the change in the impurity concentration in the formed Si film.

  In the above embodiment, the present invention has been described by taking the case where the number of heater stages (the number of zones) is five as an example, but it may be four stages or less, or may be six stages or more. Also. The number of semiconductor wafers W extracted from each zone can be arbitrarily set.

  In the above embodiment, the present invention has been described by taking the case of a batch type heat treatment apparatus having a single pipe structure as an example. For example, a batch type vertical type having a double pipe structure in which the reaction tube 2 is composed of an inner pipe and an outer pipe. It is also possible to apply the present invention to a mold heat treatment apparatus. Further, the present invention can be applied to a single wafer processing apparatus. The present invention is not limited to the processing of semiconductor wafers, and can be applied to processing of FPD (Flat Panel Display) substrates, glass substrates, PDP (Plasma Display Panel) substrates, and the like.

  The control unit 50 according to the embodiment of the present invention can be realized using a normal computer system, not a dedicated system. For example, the above-described processing is executed by installing the program from a recording medium (such as a flexible disk or a CD-ROM (Compact Disc Read Only Memory)) storing the program for executing the above-described processing in a general-purpose computer. The control unit 50 can be configured.

  The means for supplying these programs is arbitrary. In addition to being able to be supplied via a predetermined recording medium as described above, for example, it may be supplied via a communication line, a communication network, a communication system, or the like. In this case, for example, the program may be posted on a bulletin board (BBS: Bulletin Board System) of a communication network and provided by superimposing it on a carrier wave via the network. Then, the above-described processing can be executed by starting the program thus provided and executing it in the same manner as other application programs under the control of an OS (Operating System).

  The present invention is useful for a processing system for processing an object to be processed such as a semiconductor wafer.

DESCRIPTION OF SYMBOLS 1 Heat processing apparatus 2 Reaction tube 3 Manifold 6 Cover body 9 Wafer boat 10 Heater part 11-15 Heater 16-20 Power controller 21-23 Process gas supply pipe 24-26 Flow volume adjustment part 50 Control part 51 Model memory | storage part 52 Recipe memory | storage part 53 Learning history file storage 54 ROM
55 RAM
57 CPU
60 Log storage unit W Semiconductor wafer

Claims (5)

A processing condition storage means for storing processing conditions corresponding to the processing content of the object to be processed contained in the processing chamber;
Learning history file storage means for storing a learning history file related to the processing conditions stored by the processing condition storage means;
A process change model storage unit that stores a process change model indicating a relationship between a change in the process condition and a change in the process result;
Processing information receiving means for receiving information on a processing result targeted by the object;
A processing condition specifying means for specifying a required processing condition based on information on a target processing result received by the processing information receiving means and a processing condition stored by the processing condition storage means;
A processing result determining means for determining whether or not a processing result processed under the processing condition specified by the processing condition specifying means is within an allowable range of information related to a target processing result received by the processing information receiving means;
When it is determined by the processing result determination means that it is not within the allowable range, a learning history file in which at least a part of the same processing condition is stored is specified from the learning history file stored by the learning history file storage means, Use discriminating means for discriminating whether or not to use the learning history file depending on whether or not at least a part of the device condition has changed since the specified learning history file was created;
A learning history file determining means for determining a learning history file identified from the learning history file stored by the learning history file storage means when the use determining means determines that the learning history file is used;
Based on the processing condition specified by the processing condition specifying means, the learning history file determined by the learning history file determining means, and the process change model stored in the process change model storage means, the target is set. Processing condition calculation means for calculating a processing condition close to the processing result;
Processing condition update means for updating the processing condition calculated by the processing condition calculation means to the processing condition specified by the processing condition specifying means;
A processing system comprising:   The processing system according to claim 1, wherein the use determination unit determines whether or not the apparatus condition is changed based on the apparatus operation log and the process log. The content of the process is a film forming process,
The processing system according to claim 1, wherein the processing result is a film thickness or an impurity concentration in a thin film formed on the object to be processed. A processing condition storage step for storing processing conditions according to the processing content of the object to be processed contained in the processing chamber;
A learning history file storage step for storing a learning history file related to the processing conditions stored in the processing condition storage step;
A process change model storage step for storing a process change model indicating a relationship between a change in the process condition and a change in the process result;
A process information receiving step for receiving information on a target processing result of the object to be processed;
A processing condition specifying step for specifying a required processing condition based on information on a target processing result received in the processing information receiving step and a processing condition stored in the processing condition storage step;
A processing result determining step for determining whether or not the processing result processed under the processing condition specified in the processing condition specifying step is within an allowable range of information related to the target processing result received in the processing information receiving step;
When it is determined in the processing result determination step that it is not within the allowable range, the learning history file stored in the learning history file storage step identifies a learning history file in which at least a part of the same processing condition is stored, A use determination step of determining whether to use the learning history file, based on whether or not at least a part of the device condition has changed since the specified learning history file was created;
When it is determined that the learning history file is used in the use determination step, a learning history file determination step for determining a learning history file specified from the learning history file stored in the learning history file storage step;
Based on the processing condition specified in the processing condition specifying step, the learning history file determined in the learning history file determination step, and the processing change model stored in the processing change model storage step, the target is set. A processing condition calculation step for calculating a processing condition close to the processing result;
A processing condition update step for updating the processing condition calculated in the processing condition calculation step to the processing condition specified in the processing condition specifying step;
A processing method characterized by comprising: Computer
Processing condition storage means for storing processing conditions according to the processing content of the object to be processed housed in the processing chamber;
Learning history file storage means for storing a learning history file related to the processing conditions stored by the processing condition storage means;
A process change model storage means for storing a process change model indicating a relationship between a change in the process condition and a change in the process result;
Processing information receiving means for receiving information on a processing result targeted by the object to be processed;
A processing condition specifying means for specifying a required processing condition based on information on a target processing result received by the processing information receiving means and a processing condition stored by the processing condition storage means;
A processing result determining means for determining whether or not the processing result processed under the processing condition specified by the processing condition specifying means is within an allowable range of information regarding the target processing result received by the processing information receiving means;
When it is determined by the processing result determination means that it is not within the allowable range, a learning history file in which at least a part of the same processing condition is stored is specified from the learning history file stored by the learning history file storage means, Use discriminating means for discriminating whether or not to use the learning history file depending on whether or not at least a part of the device condition has changed since the identified learning history file was created;
A learning history file determining means for determining a learning history file specified from the learning history file stored by the learning history file storage means when the use determining means determines that the learning history file is used;
Based on the processing condition specified by the processing condition specifying means, the learning history file determined by the learning history file determining means, and the process change model stored in the process change model storage means, the target is set. Processing condition calculation means for calculating processing conditions close to the processing result;
Processing condition update means for updating the processing condition calculated by the processing condition calculation means to the processing condition specified by the processing condition specifying means;
A program characterized by functioning as

Images