JPWO2020188747A1 - Semiconductor device manufacturing method, sign detection program, and substrate processing device - Google Patents

Abstract

A technique for executing a process recipe including a plurality of steps to perform a predetermined process on the substrate, and among the sensor data in the designated step of each step constituting the process recipe, the vibration data detected by the vibration sensor. Is acquired, the acquired vibration data is converted into a vibration frequency spectrum, frequencies in a predetermined range of the converted vibration frequency spectrum are extracted at predetermined frequency intervals, and for each extracted frequency, a predetermined number of normal process recipes are performed. Calculate the average value and standard deviation of the amplitude of the vibration frequency spectrum using the minute data, create a normal model using the average value and standard deviation of the amplitude of the vibration frequency spectrum, and create a normal model using the extracted frequency minutes and the amplitude of the normal model. Provided is a technique for comparing a value with a predetermined threshold value and determining that there is an abnormality sign when the amplitude value of a predetermined number or more of frequencies deviates from the threshold value.

Description

The present disclosure relates to a method for manufacturing a semiconductor device, a sign detection program, and a substrate processing device.

There are known substrate processing devices and semiconductor device manufacturing methods for manufacturing semiconductor devices by forming a thin film on a substrate such as a silicon wafer. For example, in Japanese Patent Application Laid-Open No. 2014-127702, a raw material gas and a reaction gas that reacts with a raw material gas are sequentially supplied to a processing chamber containing a substrate to form a thin film on the substrate housed in the processing chamber. A method for manufacturing a semiconductor device is disclosed.

Generally, such a substrate processing apparatus includes a vacuum pump that evacuates the processing chamber, a mass flow controller that controls the flow rate of reactive gas, an on-off valve, a pressure gauge, a heater that heats the processing chamber, and a substrate. It is composed of various members such as a transport mechanism for transport.

Since each of these various members gradually deteriorates and fails as they are used, it is necessary to replace them with new members. As a method of replacement, either the member is used until it breaks down, or a regular replacement cycle is determined for each member and the member is replaced with a margin before the failure. ..

Here, when the member is used until it fails, all the substrates processed by the substrate processing device at the time of failure may become defective, and the substrate and the production time at the time of failure may be lost. In particular, when the vacuum pump breaks down, the backflow when the vacuum pump is stopped contaminates the processing chamber, which may result in loss of replacement time, cleaning time, cost, and manpower. In addition, when replacing the parts regularly before they break down, it is necessary to replace them every short period with sufficient margin, that is, a period that does not lead to a failure, so the frequency of parts replacement increases and the operating cost increases. May be connected.

An object of the present disclosure is to provide a technique capable of detecting an abnormality sign of a member.

According to one aspect of the present disclosure, it is a technique of executing a process recipe including a plurality of steps to perform a predetermined process on the substrate, and among the sensor data in the designated step of each step constituting the process recipe. , Acquires the vibration data detected by the vibration sensor, converts the acquired vibration data into a vibration frequency spectrum, extracts frequencies in a predetermined range of the converted vibration frequency spectrum at predetermined frequency intervals, and extracts each frequency. , Calculate the average value and standard deviation of the amplitude of the vibration frequency spectrum using the data for a predetermined number of times in the normal process recipe, and create a normal model using the average value and standard deviation of the amplitude of the vibration frequency spectrum. Provided is a technique for comparing the amplitude value of a normal model with a predetermined threshold value for the extracted frequency, and determining that there is an abnormality sign when the amplitude value of a predetermined number or more of frequencies deviates from the threshold value.

According to the present disclosure, a technique capable of detecting an abnormality sign of a member is provided.

It is a perspective view which shows the schematic structure of the substrate processing apparatus which concerns on one Embodiment. It is a vertical cross-sectional view which shows the schematic structure of the processing furnace of the substrate processing apparatus which concerns on one Embodiment. It is a block diagram which shows the schematic structure of the main control part of the substrate processing apparatus which concerns on one Embodiment. It is a flow chart which shows the substrate processing process when the substrate processing apparatus which concerns on one Embodiment is used as a semiconductor manufacturing apparatus. It is a block diagram which shows the control system of the substrate processing apparatus which concerns on one Embodiment. It is explanatory drawing of the singular spectrum conversion in the control system of the substrate processing apparatus which concerns on one Embodiment.

Hereinafter, a method for manufacturing a semiconductor device, a sign detection program, and a substrate processing device according to an embodiment of the present disclosure will be described. In FIG. 1, arrow F indicates the front direction of the substrate processing apparatus, arrow B indicates the rear surface direction, arrow R indicates the right direction, arrow L indicates the left direction, arrow U indicates the upward direction, and arrow D indicates the downward direction.

<Overall configuration of processing equipment>
The configuration of the substrate processing apparatus 10 will be described with reference to FIGS. 1 and 2. As shown in FIG. 1, the substrate processing device 10 includes a housing 12 made of a pressure-resistant container. An opening provided for maintenance is provided on the front wall of the housing 12, and a pair of front maintenance doors 14 are provided in the opening as an entry mechanism for opening and closing the opening. In the substrate processing apparatus 10, a pod (board container) 18 containing a substrate (wafer) 16 (see FIG. 2) such as silicon, which will be described later, is used as a carrier for transporting the substrate 16 into and out of the housing 12. NS. The substrate 16 is used, for example, in a semiconductor device.

On the front wall of the housing 12, a pod loading / unloading outlet is provided so as to communicate the inside and outside of the housing 12. A load port 20 is installed at the pod loading / unloading outlet. The pod 18 is placed on the load port 20, and the pod 18 is configured to be aligned.

A rotary pod shelf 22 is installed at an upper portion in a substantially central portion of the housing 12. A plurality of pods 18 are stored on the rotary pod shelf 22. The rotary pod shelf 22 includes a support column that is vertically erected and rotated in a horizontal plane, and a plurality of shelf boards that are radially supported on the support column at each position of the upper, middle, and lower stages.

A pod transfer device 24 is installed between the load port 20 and the rotary pod shelf 22 in the housing 12. The pod transfer device 24 has a pod elevator 24A and a pod transfer mechanism 24B that can move up and down while holding the pod 18. By continuous operation of the pod elevator 24A and the pod transfer mechanism 24B, the pod 18 is configured to transfer the pod 18 to each other between the load port 20, the rotary pod shelf 22, and the pod opener 26 described later.

A sub-housing 28 is provided in the lower part of the housing 12 from a substantially central portion in the housing 12 to a rear end. A pair of pod openers 26 for transporting the substrate 16 inside and outside the sub-housing 28 are installed on the front wall of the sub-housing 28, respectively.

Each pod opener 26 includes a mounting table on which the pod 18 is placed, and a cap attachment / detachment mechanism 30 for attaching / detaching the cap of the pod 18. The pod opener 26 is configured to open and close the substrate loading / unloading port of the pod 18 by attaching / detaching the lid of the pod 18 placed on the mounting table by the cap attachment / detachment mechanism 30.

Inside the sub-housing 28, a transfer chamber 32 fluidly isolated from the space in which the pod transfer device 24, the rotary pod shelf 22, and the like are installed is configured. A substrate transfer mechanism 34 is installed in the front region of the transfer chamber 32. The board transfer mechanism 34 includes a board transfer device 34A capable of rotating or linearly moving the board 16 in the horizontal direction, and a board transfer device elevator 34B for raising and lowering the board transfer device 34A.

The board transfer device elevator 34B is installed between the right end of the front region of the transfer chamber 32 of the sub-housing 28 and the right end of the housing 12. Further, the substrate transfer device 34A includes a tweezers (not shown) as a holding portion of the substrate 16. By the continuous operation of the board transfer device elevator 34B and the board transfer device 34A, the board 16 can be loaded (charged) and removed (discharged) from the boat 36 as a board holder. ing.

As shown in FIG. 2, a boat elevator 38 for raising and lowering the boat 36 is installed in the sub-housing 28 (transfer chamber 32). An arm 40 is connected to the lift of the boat elevator 38, and a lid (seal cap) 42 is horizontally installed on the arm 40. The lid 42 vertically supports the boat 36 and is configured to be able to close the lower end of the processing furnace 44, which will be described later.

Mainly, a transport mechanism that transports the substrate 16 by the rotary pod shelf 22 shown in FIG. 1, the pod transfer device 24, the substrate transfer mechanism 34, the boat 36, the boat elevator 38 shown in FIG. 2, and the rotary mechanism 46 described later. Is configured. The rotary pod shelf 22, the boat elevator 38, the pod transfer device 24, the substrate transfer mechanism 34, the boat 36, and the rotary mechanism 46 are electrically connected to a transfer controller 48, which will be described later.

As shown in FIG. 1, a processing furnace 44 is provided above the standby unit 50 that accommodates and waits for the boat 36. A clean unit 52 is installed at the left end of the transfer chamber 32, which is opposite to the board transfer device elevator 34B side. The clean unit 52 is configured to supply a clean atmosphere or clean air 52A, which is an inert gas.

The clean air 52A blown out from the clean unit 52 circulates around the board transfer device 34A and the boat 36 in the standby unit 50. After that, the clean air 52A is sucked by a duct (not shown) and exhausted to the outside of the housing 12, or is circulated to the primary side (supply side) which is the suction side of the clean unit 52 and transferred by the clean unit 52. It is blown out again into the loading room 32.

A plurality of device covers (not shown) are attached to the outer periphery of the housing 12 and the sub-housing 28 as an entry mechanism into the substrate processing device 10. By removing these device covers during maintenance work, maintenance personnel can enter the board processing device 10. A door switch 54 as an entry sensor (only the door switch 54 of the housing 12 is shown) is provided at the ends of the housing 12 and the sub-housing 28 facing the device cover.

Further, a board detection sensor 56 for detecting the placement of the pod 18 is provided on the load port 20. The switches and sensors such as the door switch 54 and the substrate detection sensor 56 are electrically connected to the substrate processing device controller 58 (see FIGS. 2 and 3) as the main control unit described later.

As shown in FIG. 2, the substrate processing device 10 includes a gas supply unit 60 and an exhaust unit 62 in addition to the housing 12. A processing gas supply system and a purge gas supply system are housed in the gas supply unit 60. The processing gas supply system includes a processing gas supply source and an on-off valve (not shown), a mass flow controller (hereinafter abbreviated as MFC) 64A as a gas flow rate controller, and a processing gas supply pipe 66A. Further, the purge gas supply system includes a purge gas supply source and an on-off valve (not shown), an MFC 64B, and a purge gas supply pipe 66B.

In the exhaust unit 62, a gas exhaust mechanism including an exhaust pipe 68, a pressure sensor 70 as a pressure detection unit, and a pressure adjusting unit 72 including, for example, an APC (Auto Pressure Controller) valve is housed. .. Although not shown, a vacuum pump 74 as an exhaust device is connected to the exhaust pipe 68 on the downstream side of the exhaust unit 62. The vacuum pump 74 may also be included in the gas exhaust mechanism. Further, the exhaust unit 62 and the vacuum pump 74 may be installed close to each other, such as on the same floor, or the exhaust unit 62 and the vacuum pump 74 may be installed separately from each other, such as on different floors.

As shown in FIG. 2, the substrate processing device controller 58 as the main control unit is connected to the transfer controller 48, the temperature controller 76, the pressure controller 78, and the gas supply controller 80, respectively. Further, as shown in FIG. 5, the controller 58 for the substrate processing device is connected to the sign detection controller 82 as a sign detection unit, which will be described later.

<Composition of processing furnace>
As shown in FIG. 2, the processing furnace 44 includes a reaction tube (process tube) 84. The reaction tube 84 includes an internal reaction tube (inner tube) 84A and an external reaction tube (outer tube) 84B provided on the outside thereof. The internal reaction tube 84A is formed in a cylindrical shape with the upper end and the lower end open, and a processing chamber 86 for processing the substrate 16 is formed in the hollow portion of the cylinder in the internal reaction tube 84A. The processing chamber 86 is configured to accommodate the boat 36.

A cylindrical heater 88 is provided on the outside of the reaction tube 84 so as to surround the side wall surface of the reaction tube 84. The heater 88 is vertically installed by being supported by the heater base 90.

Below the external reaction tube 84B, a cylindrical furnace mouth portion (manifold) 92 is arranged so as to be concentric with the external reaction tube 84B. The furnace port portion 92 is provided so as to support the lower end portion of the internal reaction tube 84A and the lower end portion of the external reaction tube 84B, and engages with the lower end portion of the internal reaction tube 84A and the lower end portion of the external reaction tube 84B, respectively. doing.

An O-ring 94 as a sealing member is provided between the furnace mouth portion 92 and the external reaction tube 84B. Since the furnace port portion 92 is supported by the heater base 90, the reaction tube 84 is in a vertically installed state. A reaction vessel is formed by the reaction tube 84 and the furnace port portion 92.

The processing gas nozzle 96A and the purge gas nozzle 96B are connected to the furnace port portion 92 so as to communicate with each other in the processing chamber 86. A processing gas supply pipe 66A is connected to the processing gas nozzle 96A. A processing gas supply source (not shown) or the like is connected to the upstream side of the processing gas supply pipe 66A via the MFC64A. Further, a purge gas supply pipe 66B is connected to the purge gas nozzle 96B. A purge gas supply source (not shown) or the like is connected to the upstream side of the purge gas supply pipe 66B via the MFC64B.

An exhaust pipe 68 for exhausting the atmosphere of the processing chamber 86 is connected to the furnace port portion 92. The exhaust pipe 68 is arranged at the lower end of the cylindrical space 98 formed by the gap between the internal reaction pipe 84A and the external reaction pipe 84B, and communicates with the tubular space 98. A pressure sensor 70, a pressure adjusting unit 72, and a vacuum pump 74 are connected to the downstream side of the exhaust pipe 68 in this order from the upstream side.

A disk-shaped lid 42 capable of airtightly closing the lower end opening of the furnace opening 92 is provided below the furnace opening 92, and the upper surface of the lid 42 is in contact with the lower end of the furnace opening 92. An O-ring 100 is provided as a contacting seal member.

A rotation mechanism 46 for rotating the boat 36 is installed on the side opposite to the processing chamber 86 near the center of the lid 42. The rotation shaft 102 of the rotation mechanism 46 penetrates the lid 42 and supports the boat 36 from below. Further, the rotation mechanism 46 has a built-in rotation motor 46A, and the rotation motor 46A is configured to rotate the rotation shaft 102 of the rotation mechanism 46 and rotate the boat 36 to rotate the substrate 16. ing.

The lid 42 is configured to be raised and lowered in the vertical direction by a boat elevator 38 provided outside the reaction tube 84. By raising and lowering the lid body 42, the boat 36 can be transported to the inside and outside of the processing chamber 86. A transfer controller 48 is electrically connected to the rotary motor 46A and the boat elevator 38 of the rotary mechanism 46.

The boat 36 is configured to align a plurality of substrates 16 in a horizontal posture and in a state of being centered on each other and hold them in multiple stages. Further, in the lower part of the boat 36, a plurality of disk-shaped heat insulating plates 104 as heat insulating members are arranged in a horizontal posture in multiple stages. The boat 36 and the heat insulating plate 104 are made of a heat-resistant material such as quartz or silicon carbide. The heat insulating plate 104 is provided to make it difficult to transfer the heat from the heater 88 to the furnace port portion 92 side.

Further, a temperature sensor 106 as a temperature detector is installed in the reaction tube 84. A temperature controller 76 is electrically connected to the heater 88 and the temperature sensor 106.

<Operation of board processing device>
Subsequently, a method of forming a thin film on the substrate 16 will be described as one step of the semiconductor device manufacturing process with reference to FIGS. 1 and 2. The operation of each part constituting the substrate processing apparatus 10 is controlled by the substrate processing apparatus controller 58.

As shown in FIG. 1, when the pod 18 is supplied to the load port 20 by an in-process transfer device (not shown), the pod 18 is detected by the board detection sensor 56, and the pod carry-in / carry-out outlet is a front shutter (not shown). Is released by. Then, the pod 18 on the load port 20 is carried into the housing 12 from the pod carry-in / carry-out outlet by the pod transport device 24.

The pod 18 carried into the housing 12 is automatically transported onto the shelf board of the rotary pod shelf 22 by the pod transfer device 24 and temporarily stored. After that, the pod 18 is transferred from the shelf board onto the mounting table of one of the pod openers 26. The pod 18 carried into the housing 12 may be directly transferred onto the mounting table of the pod opener 26 by the pod transport device 24.

The lid of the pod 18 mounted on the mounting table is removed by the cap attachment / detachment mechanism 30, and the substrate insertion / removal port is opened. After that, the substrate 16 (see FIG. 2) is picked up from the inside of the pod 18 through the substrate loading / unloading port by the tweezers of the substrate transfer device 34A, and after the orientations are aligned by a notch alignment device (not shown), the rear of the transfer chamber 32. It is carried into the standby unit 50 in the above, and loaded (charged) into the boat 36. The board transfer device 34A in which the board 16 is loaded on the boat 36 returns to the mounting table on which the pod 18 is mounted, takes out the next board 16 from the pod 18, and loads the next board 16 into the boat 36.

During the loading work of the substrate 16 into the boat 36 by the substrate transfer mechanism 34 in the one (upper or lower) pod opener 26, another pod is placed on the mounting table of the other (lower or upper) pod opener 26. 18 is transported from the rotary pod shelf 22 by the pod transfer device 24. By transferring this other pod 18 to the mounting table, the opening work of the pod 18 by the pod opener 26 is simultaneously carried out.

When a predetermined number of substrates 16 are loaded into the boat 36, the lower end of the processing furnace 44 is opened by a furnace opening shutter (not shown). Subsequently, the boat 36 holding the substrate 16 group is carried (loaded) into the processing furnace 44 by raising the lid 42 by the boat elevator 38.

As described above, when the boat 36 holding the plurality of substrates 16 is carried (loaded) into the processing chamber 86 of the processing furnace 44, the lid 42 is passed through the O-ring 100 as shown in FIG. The lower end of the furnace mouth portion 92 is sealed.

After that, the inside of the processing chamber 86 is evacuated by the vacuum pump 74 so as to have a desired pressure (vacuum degree). At this time, the pressure adjusting unit 72 (opening degree of the valve) is feedback-controlled based on the pressure value measured by the pressure sensor 70. Further, the processing chamber 86 is heated by the heater 88 so as to have a desired temperature. At this time, the amount of electricity supplied to the heater 88 is feedback-controlled based on the temperature value detected by the temperature sensor 106. Subsequently, the rotation mechanism 46 rotates the boat 36 and the substrate 16.

Next, the processing gas supplied from the processing gas supply source and controlled by the MFC 64A so as to have a desired flow rate flows through the processing gas supply pipe 66A and is introduced into the processing chamber 86 from the processing gas nozzle 96A. The introduced processing gas rises in the processing chamber 86, flows out from the upper end opening of the internal reaction pipe 84A into the cylindrical space 98, and is exhausted from the exhaust pipe 68. The processing gas comes into contact with the surface of the substrate 16 as it passes through the processing chamber 86, and at this time, a thin film is deposited on the surface of the substrate 16 by a thermal reaction.

When the preset processing time elapses, the purge gas supplied from the purge gas supply source and controlled by the MFC64B to have a desired flow rate is supplied to the processing chamber 86, and the inside of the processing chamber 86 is replaced with the inert gas. At the same time, the pressure in the processing chamber 86 is restored to the normal pressure.

After that, the lid 42 is lowered by the boat elevator 38 to open the lower end of the furnace opening 92, and the boat 36 holding the processed substrate 16 moves from the lower end of the furnace opening 92 to the outside of the reaction tube 84. It is carried out (unloading). After that, the processed substrate 16 is taken out from the boat 36 and stored (discharged) in the pod 18.

After the discharge, the pod 18 containing the processed substrate 16 is carried out of the housing 12 in a procedure substantially opposite to the above procedure except for the matching step in the notch matching device.

<Controller configuration for board processing equipment>
Next, with reference to FIG. 3, the controller 58 for the substrate processing apparatus as the main control unit will be specifically described.

The controller 58 for a board processing device mainly includes an arithmetic control unit 108 such as a CPU (Central Processing Unit), a storage unit 114 including a RAM 110, a ROM 112, and an HDD (not shown), an input unit 116 such as a mouse and a keyboard, and a monitor. Etc. is composed of a display unit 118 and the like. Each data can be set by the arithmetic control unit 108, the storage unit 114, the input unit 116, and the display unit 118.

The arithmetic control unit 108 constitutes the center of the substrate processing device controller 58, executes the control program stored in the ROM 112, and is stored in the storage unit 114 which also constitutes the recipe storage unit according to the instruction from the input unit 116. Execute a recipe (for example, a process recipe as a substrate processing recipe).

The ROM 112 is a recording medium composed of a flash memory, a hard disk, and the like, and stores an operation program and the like of an arithmetic control unit 108 that controls the operation of each member (for example, a vacuum pump 74 and the like) of the substrate processing apparatus 10. Further, the RAM 110 (memory) functions as a work area (temporary storage unit) of the arithmetic control unit 108.

Here, the substrate processing recipe (process recipe) is a recipe in which processing conditions, processing procedures, and the like for processing the substrate 16 are defined. Further, in the recipe file, set values (control values) and transmission timings to be transmitted to the transfer controller 48, the temperature controller 76, the pressure controller 78, the gas supply controller 80, etc. are set for each step of the substrate processing. ..

The arithmetic control unit 108 determines the temperature and pressure in the processing furnace 44, the flow rate of the processing gas introduced into the processing furnace 44, and the like so that the substrate 16 loaded in the processing furnace 44 is subjected to a predetermined treatment. Has a function to control.

The transport controller 48 controls the transport operations of the rotary pod shelf 22, the boat elevator 38, the pod transport device 24, the board transfer mechanism 34, the boat 36, and the rotary mechanism 46, which form a transport mechanism for transporting the substrate 16, respectively. It is configured as follows.

Further, sensors are built in each of the rotary pod shelf 22, the boat elevator 38, the pod transfer device 24, the substrate transfer mechanism 34, the boat 36, and the rotary mechanism 46. When each of these sensors shows a predetermined value, an abnormal value, or the like, the controller 58 for the substrate processing apparatus is notified to that effect. The abnormality sign detection system for each member of the substrate processing apparatus 10 will be described in detail later.

The storage unit 114 is provided with a data storage area 120 for storing various data and the like, and a program storage area 122 for storing various programs including a substrate processing recipe (process recipe). The data storage area 120 stores various parameters related to the recipe file. Further, in the program storage area 122, various programs necessary for controlling the apparatus including the above-mentioned substrate processing recipe (process recipe) are stored.

Further, the display unit 118 of the controller 58 for the substrate processing device is provided with a touch panel (not shown). The touch panel is configured to display an operation screen that accepts input of operation commands to the above-mentioned board transfer system and board processing system. The controller 58 for the board processing device may have a configuration including at least a display unit 118 and an input unit 116, like an operation terminal (terminal device) of a personal computer, a mobile device, or the like.

The temperature controller 76 adjusts the temperature inside the processing furnace 44 by controlling the temperature of the heater 88 of the processing furnace 44. When the temperature sensor 106 shows a predetermined value, an abnormal value, or the like, the controller 58 for the substrate processing device is notified to that effect.

The pressure controller 78 controls the pressure adjusting unit 72 so that the pressure in the processing chamber 86 becomes a desired pressure at a desired timing based on the pressure value detected by the pressure sensor 70. When the pressure sensor 70 shows a predetermined value, an abnormal value, or the like, the controller 58 for the substrate processing device is notified to that effect.

The gas supply controller 80 is configured to control the MFC 64A and 64B so that the flow rate of the gas supplied into the processing chamber 86 becomes a desired flow rate at a desired timing. When the sensors (not shown) included in the MFC64A, 64B, etc. show a predetermined value, an abnormal value, or the like, the controller 58 for the substrate processing device is notified to that effect.

<Substrate processing process>
Next, the outline of the substrate processing process for processing the substrate by using the substrate processing apparatus 10 of the present embodiment as the semiconductor manufacturing apparatus will be described with reference to FIG. This substrate processing step is, for example, one step of a method for manufacturing a semiconductor device (IC, LSI, etc.). In the following description, the operation and processing of each part constituting the substrate processing apparatus 10 is controlled by the substrate processing apparatus controller 58.

Here, an example in which a film is formed on the substrate 16 by alternately supplying the raw material gas (first processing gas) and the reaction gas (second processing gas) to the substrate 16 will be described. Further, hereinafter, hexachlorodisilane (Si ₂ Cl ₆ , hereinafter abbreviated as HCDS) gas is used _{as a raw material gas, and ammonia (NH 3} ) is used as a reaction gas to form a silicon nitriding (SiN) film as a thin film on the substrate 16. An example will be described. For example, a predetermined film may be formed in advance on the substrate 16, and a predetermined pattern may be formed in advance on the substrate 16 or the predetermined film.

(Substrate carry-in process S102)
First, in the substrate loading step S102, the substrate 16 is loaded into the boat 36 and carried into the processing chamber 86.

(Film formation step S104)
In the film forming step S104, the following four steps are sequentially executed to form a thin film on the surface of the substrate 16. During steps 1 to 4, the substrate 16 is heated to a predetermined temperature by the heater 88.

[Step 1]
In step 1, both the on-off valve (not shown) provided on the processing gas supply pipe 66A and the pressure adjusting unit 72 (APC valve) provided on the exhaust pipe 68 are opened, and the HCDS gas whose flow rate is adjusted by the MFC 64A is supplied to the processing gas supply pipe. Pass through 66A. Then, the HCDS gas is supplied from the processing gas nozzle 96A into the processing chamber 86 and exhausted from the exhaust pipe 68. At this time, the pressure in the processing chamber 86 is kept at a predetermined pressure. As a result, a silicon thin film is formed on the surface of the substrate 16.

[Step 2]
In step 2, the on-off valve of the processing gas supply pipe 66A is closed to stop the supply of HCDS gas. The pressure adjusting unit 72 (APC valve) of the exhaust pipe 68 is left open, and the inside of the processing chamber 86 is exhausted by the vacuum pump 74 to remove the residual gas from the inside of the processing chamber 86. Further, the on-off valve provided in the purge gas supply pipe 66B is opened _{to supply an inert gas such as N 2} into the processing chamber 86 to purge the inside of the processing chamber 86 and treat the residual gas in the processing chamber 86. Discharge to the outside of the room 86.

[Step 3]
In step 3, both the on-off valve (not shown) provided on the purge gas supply pipe 66B and the pressure adjusting unit 72 (APC valve) provided on the exhaust pipe 68 are opened, and the NH ₃ gas whose flow rate is adjusted by the MFC 64B is supplied to the purge gas supply pipe. Pass through 66B. Then, _{while supplying NH 3} gas from the purge gas nozzle 96B into the processing chamber 86, the gas is exhausted from the exhaust pipe 68. At this time, the pressure in the processing chamber 86 is kept at a predetermined pressure. Thus, the silicon thin film and the NH ₃ gas formed on the surface of the substrate 16 by the HCDS gas is surface reaction, SiN film is formed on the substrate 16.

[Step 4]
In step 4, by closing the opening and closing valve of the purge gas supply pipe 66B, stops the supply of the NH ₃ gas. The pressure adjusting unit 72 (APC valve) of the exhaust pipe 68 is left open, and the inside of the processing chamber 86 is exhausted by the vacuum pump 74 to remove the residual gas from the inside of the processing chamber 86. Further, _{an inert gas such as N 2} is supplied into the treatment chamber 86, and the inside of the treatment chamber 86 is purged again.

Steps 1 to 4 above are set as one cycle, and by repeating this cycle a plurality of times, a SiN film having a predetermined film thickness is formed on the substrate 16.

(Substrate unloading step S106)
In the substrate unloading step S106, the boat 36 on which the substrate 16 on which the SiN film is formed is placed is unloaded from the processing chamber 86.

<Control system in this embodiment>
Next, a control system for detecting an abnormality sign (failure sign) of each member of the substrate processing device 10 will be described with reference to FIGS. 5 and 6. Hereinafter, an example of forming a thin film on the substrate 16 by the substrate processing apparatus 10 will be described.

As shown in FIG. 5, the control system includes a controller 58 for a board processing device as a main control unit, a sign detection controller 82 as a sign detection unit, various sensors 124, and a data collection unit (Data Collection Unit, hereinafter. It includes 126 (abbreviated as DCU) and 128 edge controller (hereinafter abbreviated as EC) 128. It should be noted that these constituting the control system are connected by wire or wirelessly, respectively.

The controller 58 for the board processing device is connected to a host computer (not shown) including a customer host computer and an operation unit (not shown). The operation unit has a configuration in which various data (sensor data, etc.) acquired by the controller 58 for the board processing device can be exchanged with a host computer.

The sign detection controller 82 acquires sensor data from sensors of various members provided in the board processing device 10 and its ancillary equipment, and monitors the state of the board processing device 10. Specifically, the sign detection controller 82 calculates a numerical index using data from various sensors 124, and detects an abnormality sign (that is, a failure sign) by comparing with a predetermined threshold value. The sign detection controller 82 has a built-in sign detection program that detects the occurrence of an abnormal sign based on the movement of the sensor data.

Further, the sign detection controller 82 has two systems, a system directly connected to the controller 58 for the board processing device and a system connected to the controller 58 for the board processing device via the DCU 126. Therefore, when an abnormality sign is detected by the sign detection controller 82, a signal is directly output to the substrate processing device controller 58 without going through the DCU 126 to generate an alarm, and the member provided with the abnormality sign is provided. It is possible to display the sensor data information of the sensor on the screen of the display unit 118 (see FIG. 3).

The various sensors 124 are sensors (for example, a pressure sensor 70, a temperature sensor 106, etc.) provided on various members provided in the substrate processing device 10 and its ancillary equipment, and the flow rate, concentration, temperature, and humidity of each member. (Dew point), pressure, current, voltage, voltage, torque, vibration, position, rotation speed, etc. are detected.

The DCU126 collects and accumulates data from various sensors 124 during the execution of the process recipe. Further, the EC128 temporarily captures sensor data as needed depending on the type of sensor, applies a process such as a fast Fourier transform (hereinafter abbreviated as FFT) to the raw data, and then transmits the raw data to the sign detection controller 82. ..

Further, the various sensors 124 are divided into a first sensor system 124A and a second sensor system 124B having different transmission paths. The first sensor system 124A is a system that captures raw data in real time in units of 0.1 seconds, and the raw data is transmitted from the first sensor system 124A to the sign detection controller 82 in real time via the controller 58 for the substrate processing device and the DCU 126. Will be sent. The first sensor system 124A includes, for example, a temperature sensor, a pressure sensor, a gas flow rate sensor, and other sensors.

On the other hand, the second sensor system 124B is a system in which only the part necessary for analysis is taken out by processing such as FFT with EC128 and data is transmitted in a processed file format, and the data is transmitted from the second sensor system 124B via EC128. The processed data is transmitted to the sign detection controller 82. The second sensor system 124B includes a sensor such as a vibration sensor.

When the sensor is a vibration sensor, vibration data is accumulated in milliseconds, so that the amount of data becomes enormous, and if the data is transmitted to the sign detection controller 82 as it is, it leads to a large consumption of the storage capacity of the sign detection controller 82. Since the data of this vibration sensor is finally processed by FFT or the like and used for analysis, the amount of information can be reduced by performing the processing in advance with EC128, and predictive detection is performed as a data format that is easy to analyze. It can be transmitted to the controller 82.

(First Embodiment)
Hereinafter, the first embodiment of the step of detecting an abnormality sign of each member of the substrate processing apparatus 10 using the above-mentioned control system will be specifically described.

[Calculation of abnormalities]
First, by using a plurality of values detected by a sensor directly installed on a member whose abnormality sign is to be detected and a value detected by a sensor of another member whose state directly or indirectly affects the state of the member, " Calculate "abnormality". In the present embodiment, for example, when the member to be detected as an abnormality sign approaches an abnormal state, the value of the abnormal degree is substantially increased. The degree of abnormality may be configured to have a property that the value decreases when the member to be detected as an abnormality sign approaches an abnormal state.

[Original data that constitutes abnormalities]
The substrate processing sequence includes, for example, carrying the substrate 16 into the processing chamber 86, evacuating the processing chamber 86, raising the temperature, purging with an inert gas, waiting for the temperature rise, and processing the substrate 16 (for example, film formation). It is composed of many events having their respective purposes, such as gas replacement in the processing chamber 86, returning to atmospheric pressure, and carrying out the substrate 16 after processing. The above event is an example of a substrate processing sequence, and each event may be further subdivided.

In the present embodiment, the value of one or more sensors in one or more specific events in these events is used as a numerical index in the algorithm, "abnormal", without using all the sensor data in the sequence. It is used as the original data to calculate the degree. In addition, the abnormal degree value for each Run is monitored to detect an abnormality sign of each member of the substrate processing apparatus 10. In this way, it is possible to save the amount of data accumulated by using only the data of a specific event.

For example, the abnormality sign detection of the vacuum pump 74 becomes easy to detect at the timing when a large load is applied to the vacuum pump 74. The step of reducing the pressure in the processing chamber 86 from atmospheric pressure to a predetermined pressure, that is, the pressure zone close to atmospheric pressure at the start of evacuation or several minutes after the start of evacuation corresponds to the timing when a large load is applied to the vacuum pump 74. ..

Specifically, one substrate processing apparatus 10 is in charge of a plurality of processes, and different processing recipes such as those having different film forming conditions may be mixed and started. Since the raw material gas flows during the film formation of the substrate 16, the raw material gas may react or thermally decompose to form a solid substance, which may put a load on the vacuum pump 74, so that the film formation event is monitored. This is also effective for detecting abnormal signs.

However, if Runs with different film formation events are mixed, the conditions are different between different film formation events, making direct comparison difficult, and only those with the same film formation event will be monitored over time. There is a risk that the monitoring targets will be dispersed and the tendency will be difficult to understand.

On the other hand, the evacuation event before substrate processing is often common even if the subsequent substrate processing event is different. In other words, even when multiple recipes with different film formation conditions are started with the same device, it depends on the substrate processing content by monitoring the state at the start of evacuation common to each Run and acquiring sensor data. Instead, it is possible to know the change over time in the same state, and it is possible to make highly accurate predictions.

[Example of calculation of abnormality]
Here, when the sensor data of the vibration sensor is used, and when the sensor data of a sensor other than the vibration sensor (for example, a current sensor, a temperature sensor, an exhaust pressure sensor, a torque value data, a current data, etc.) is used, the degree of abnormality is Calculation examples are shown respectively.

First, when determining the presence or absence of an abnormality for each individual frequency using the sensor data (vibration data) of the vibration sensor, the procedure is as follows.

(1) Of the sensor data in the designated step of each step constituting the process recipe, the vibration data (raw data) detected by the vibration sensor is acquired.
(2) The acquired vibration data is converted into a vibration frequency spectrum by processing such as FFT, and frequencies in a predetermined range (for example, 10 Hz to 5000 Hz) of the converted vibration frequency spectrum are extracted at predetermined frequency intervals (for example, every 10 Hz). (The numerical value is the amplitude (environmental line) of vibration, which is 500 dimensions in the example).
(3) For each extracted frequency, the average value μ and standard deviation σ of the amplitude of the vibration frequency spectrum are calculated using the data for a predetermined number of times of the normal process recipe (for example, 30 Run), and the normal amplitude is calculated. It is assumed that the normal distribution N (μ, σ) is followed, and this is used as a normal model.
(4) Using the numerical value of (2) after creating the normal model as an abnormal degree vector, the amplitude value of the normal model is compared with a predetermined threshold value for each extracted frequency, and the number is equal to or more than a predetermined number (for example, m (m ≧ 1)). If the amplitude value of the frequency of () or more) deviates from the threshold value, it is judged that there is a sign of abnormality. The threshold value is calculated in the range (μ ± 3σ) obtained by adding or subtracting the value obtained by multiplying the standard deviation σ by 3 to the average value μ using, for example, the average value μ and the standard deviation σ obtained in (3).

Further, when judging by the sum of the amplitudes of each frequency using the sensor data (vibration data) of the vibration sensor, the procedure is as follows.

(1) Of the sensor data in the designated step of each step constituting the process recipe, the vibration data (raw data) detected by the vibration sensor is acquired.
(2) The acquired vibration data is converted into a vibration frequency spectrum by processing such as FFT, and frequencies in a predetermined range (for example, 10 Hz to 5000 Hz) of the converted vibration frequency spectrum are extracted at predetermined frequency intervals (for example, every 10 Hz). (The numerical value is the amplitude (environmental line) of vibration, which is 500 dimensions in the example).
(3) Add all the sums of the extracted amplitudes for each frequency for each Run in the normal state (since one sum of amplitudes is obtained for each Run, 30 numbers can be obtained for 30 Runs).
(4) Calculate the average value μ and standard deviation σ from the numerical group obtained for each Run, and assume that the sum obtained for each Run follows the normal distribution N (μ, σ), and use this as a normal model. ..
(5) The value of (3) after creating the normal model is set as the abnormal degree, and the amplitude value of the normal model is compared with a predetermined threshold value. If the amplitude value deviates from the threshold value, it is determined that there is an abnormality sign. The threshold value is calculated in the range (μ ± 3σ) obtained by adding or subtracting the value obtained by multiplying the standard deviation σ by 3 to the average value μ using, for example, the average value μ and the standard deviation σ obtained in (3).

In addition, when making a judgment for each basic statistic using sensor data other than vibration data, the procedure is as follows.

(1) Select one or more data from the basic statistics of the average value, standard deviation, N quantile, maximum value, and minimum value of the sensor data of the target event in the normal state.
(2) Obtain the average value μ and standard deviation σ for each of the selected normal basic statistics, and assume that each basic statistics follows a normal distribution. Let this be a normal model for each basic statistic of the sensor.
(3) After the normal model is created, if the value of (1) is regarded as an abnormal degree and the value deviates from a predetermined threshold value determined in advance for each basic statistic, it is judged that there is an abnormality sign. The threshold value is calculated in the range (μ ± 3σ) obtained by adding or subtracting the value obtained by multiplying the standard deviation σ by 3 to the average value μ using, for example, the average value μ and the standard deviation σ obtained in (2).

Further, as shown in FIG. 6, when the judgment is made by using the singular spectrum conversion using the sensor data other than the vibration data, the procedure is as follows. In the following procedure, two data matrices X and Z are created on the past and present sides using a partial time series of the window width n around Run p. The following procedure is a general method of singular spectrum transformation.

(1) Prepare Mn-dimensional vertical vectors that can be regarded as M-dimensional vertical vectors and connected vertically from the top S (pn + 1, 1) to the bottom S (p, M). ..
Sensor data at time 1, 2, ..., M of the target event of Run pn + 1, {S (pn + 1, 1), S (pn + 1, 2), ..., S (p- n + 1, M)}
・ ・ ・
Sensor data at time 1, 2, ..., M of the target event of Run p-1 {S (p-1, 1), S (p-1, 2), ..., S (p- 1, M)}
Sensor data at time 1, 2, ..., M of the target event of Run p {S (p, 1), S (p, 2), ..., S (p, M)}
(2) Each is regarded as an M-dimensional vertical vector, and an Mn-dimensional vertical vector ((1)) formed by connecting n vertically from the top S (pn + 1, 1) to the bottom S (p, M). ) Is shifted to the one older Run group).
Sensor data at time 1, 2, ..., M of the target event of Run pn {S (pn, 1), S (pn, 2), ..., S (p- n, M)}
・ ・ ・
Sensor data at time 1, 2, ..., M of the target event of Run p-2 {S (p-2, 1), S (p-2, 2), ..., S (p- 2, M)}
Sensor data at time 1, 2, ..., M of the target event of Run p-1 {S (p-1, 1), S (p-1, 2), ..., S (p- 1, M)}
(3) Similar to the above (1) and (2), K vertical vectors composed in order are prepared, and the vertical vectors can be arranged from left to right from the oldest to the newest in Mn × K dimension. Create a matrix X (p). With the above, the history matrix for performing the singular spectrum transformation is created.
(4) Assuming each as an M-dimensional vertical vector, prepare an Mn-dimensional vertical vector formed by connecting n vertically from the top S (p + L, 1) to the bottom S (p + L-n + 1, M). .. Let L be a positive integer.
Sensor data at time 1, 2, ..., M of the target event of Run p + L {S (p + L, 1), S (p + L, 2), ..., S (p + L, M)}
・ ・ ・
Sensor data at time 1, 2, ..., M of the target event of Run p + L-n + 2, {S (p + L-n + 2, 1), S (p + L-n + 2, 2), ..., S (p + L-) n + 2, M)}
Sensor data at time 1, 2, ..., M of the target event of Run p + L-n + 1, {S (p + L-n + 1, 1), S (p + L-n + 1, 2), ..., S (p + L-) n + 1, M)}
(5) Each is regarded as an M-dimensional vertical vector, and an Mn-dimensional vertical vector (Mn-dimensional vertical vector) formed by connecting n vertically from the top S (p + L-1, 1) to the bottom S (p + Ln, M). Prepare a run group that is one older than (4)).
Sensor data at time 1, 2, ..., M of the target event of Run p + L-1 {S (p + L-1, 1), S (p + L-1, 2), ..., S (p + L-) 1, M)}
・ ・ ・
Sensor data at time 1, 2, ..., M of the target event of Run p + L-n + 1, {S (p + L-n + 1, 1), S (p + L-n + 1, 2), ..., S (p + L-) n + 1, M)}
Sensor data at time 1, 2, ..., M of the target event of Run p + Ln {S (p + Ln, 1), S (p + Ln, 2), ..., S (p + L-) n, M)}
(6) Similar to the above (4) and (5), R vertical vectors composed in order are prepared, and the vertical vectors can be arranged from left to right from the oldest to the newest in the Mn × R dimension. Create a matrix Z (p). With the above, the test matrix for singular spectrum transformation is created.
(7) Singular value decomposition is performed on the above-mentioned matrix X (p) and matrix Z (p), and singular spectrum conversion is performed.
(8) Select r left singular vectors obtained by singular value decomposition in X (p) and m in Z (p), and form a matrix with U (r) and Q (m), respectively, to form a matrix of them. The maximum singular value of the product U (r) ^T Q (m) is obtained. Let it be λ (0 ≦ λ ≦ 1), and let 1-λ be the degree of abnormalities (degree of change). When this abnormality deviates from a predetermined threshold value determined in advance, it is determined that there is a sign of abnormality.

[Judgment of abnormal signs using abnormalities]
Further, as a method of determining the presence or absence of an abnormality sign using the degree of abnormality, for example, the following method can be considered. If it is determined that there is a sign of abnormality, the controller 58 for the board processing device is notified.

(1) A method of determining that there is a sign of abnormality when the degree of abnormalities of at least one sensor data deviates from the threshold value.
(2) A method of determining that there is a sign of abnormality when the abnormalities of two or more sensor data deviate from the threshold value.
(3) A method of determining that there is a sign of abnormality when the degree of abnormalities of one or more sensor data deviates from the threshold value a predetermined number of times (for example, three times).
(4) A method of determining that there is an abnormality sign when the abnormality of sensor data other than vibration data deviates from the threshold value a predetermined number of times (for example, three times) in succession.
(5) A method in which even if the abnormalities of sensor data other than the vibration data deviate from the threshold value, if the abnormalities of the vibration data do not deviate from the threshold value, it is not determined that there is an abnormality sign.
(6) A method of determining that there is an abnormality sign when both the abnormality of vibration data and the abnormality of sensor data other than vibration data deviate from the threshold value.

For example, in the above methods (2), (5), and (6), since the abnormality sign is determined using a plurality of sensor data, false detection of the sensor can be reduced. Further, since the movement of the abnormal degree is not always monotonous, the methods (3) and (4) above can reduce erroneous judgment when the value of the abnormal degree fluctuates around the threshold value. The calculation formula, the threshold value, and the program of the abnormal degree are different for each member and each device, and are incorporated in the sign detection controller 82 in advance.

[Display of analysis screen for abnormality sign detection]
The analysis screen for detecting an abnormality sign can be displayed on the display unit 118 (see FIG. 3) of the controller 58 for the substrate processing device. Therefore, the transition of the abnormal degree, the threshold value, the number of times the threshold value is exceeded, and the like can be visually observed, and the state of the member can be confirmed by the abnormal degree.

[Case with EC]
Here, the case of the second sensor system 124B shown in FIG. 5, that is, the case where the EC128 is interposed between the sensor and the sign detection controller 82 will be described.

[Time synchronization]
Since the vibration sensor data is converted by EC128, it is transmitted to the sign detection controller 82 in a form having the time of EC128. In order to use the data of this vibration sensor and the data of other sensors having the time on the DCU126 and the controller 58 side of the substrate processing device for the analysis at the same time, it is necessary to synchronize the time of both. Therefore, the EC128, the DCU126, and the sign detection controller 82 periodically capture the time and synchronize the time with the time of the controller 58 for the substrate processing device as the reference time. As a result, the times of all the members are synchronized, and accurate analysis becomes possible.

Here, the vacuum pump 74 (see FIG. 2) is taken as an example of the first embodiment, and the rotary motor 46A (see FIG. 2) is taken as an example of the second embodiment. To explain.

[Specific example 1]
In the processing chamber 86 of the substrate processing apparatus 10, the reaction by-products of the processing gas are deposited inside, and when the amount and height of the reaction by-products reach a certain level, the rotation of the vacuum pump 74 suddenly stops. ..

Here, at least one sensor data of the current data, the temperature data, the exhaust pressure data, and the vibration data of the vacuum pump 74 is continuously monitored, and the change in the behavior of the sensor data is detected by the sign detection program in the sign detection controller 82. By analyzing, it is possible to detect an abnormality sign of the vacuum pump 74. When a sign of abnormality is detected, the information is transmitted to the controller 58 for the substrate processing device, and the operator is notified to replace or maintain the vacuum pump 74.

[Specific example 2]
In the batch type substrate processing apparatus 10, in order to improve the in-plane film thickness uniformity of the substrate 16, the rotation mechanism 46 rotates the boat 36 during film formation so that the processing gas and the reaction gas evenly hit the outer periphery of the substrate 16. Is rotating by. The rotary motor 46A constituting the rotary mechanism 46 may become difficult to rotate due to deterioration due to long-term use or a slight amount of film formation by-products being gradually mixed in, resulting in failure.

Here, at least one sensor data of the torque value data, the current data, and the vibration data of the rotary motor 46A is continuously monitored, and the change in the behavior of the sensor data is analyzed by the sign detection program in the sign detection controller 82. Therefore, it is possible to detect an abnormality sign of the rotary motor 46A. When a sign of abnormality is detected, the information is transmitted to the controller 58 for the substrate processing device, and the operator is notified to replace or maintain the rotary motor 46A.

(Second Embodiment)
Next, a second embodiment of the step of detecting an abnormality sign of each member of the substrate processing apparatus 10 using the above-mentioned control system will be specifically described. The configuration of the sign detection controller 82 and the like and the abnormality sign determination using the abnormal degree are the same as those in the first embodiment.

[Calculation of abnormalities]
In the present embodiment, a plurality of values of a sensor directly installed on a member to be detected for an abnormality sign and a value of a sensor of another member whose state directly or indirectly affects the state of the member are used in a normal state. The sensor data of is learned, and the "abnormality" is calculated using the learned data and the operating data.

In the present embodiment, for example, when the member to be detected as an abnormality sign approaches an abnormal state, the value of the abnormal degree is substantially increased. The degree of abnormality may be configured to have a property that the value decreases when the member to be detected as an abnormality sign approaches an abnormal state.

Here, a method for detecting an abnormality sign of a member of the substrate processing apparatus 10 will be specifically described by taking a vacuum pump 74 (see FIG. 2) as a specific example 1.

[Specific example 1]
Generally, in a state where the inside of the processing chamber 86 is evacuated by the vacuum pump 74, an inert gas or a film-forming gas flows through the vacuum pump 74, resulting in a high load, which makes it easy to detect an abnormality sign. .. On the other hand, when the vacuum pump 74 does not evacuate the processing chamber 86, the load of the vacuum pump 74 becomes small, and it becomes difficult to detect an abnormality sign or an abnormality is unlikely to occur. Therefore, conventionally, the vacuum pump 74 has been monitored while the inside of the processing chamber 86 is evacuated.

On the other hand, in the present embodiment, a large amount of gas is intentionally vacuum pumped in an event in which the inside of the processing chamber 86 is not evacuated by the vacuum pump 74 and the substrate 16 is not inside the processing chamber 86. It flows through 74 to increase the load on the vacuum pump 74. Then, by monitoring the current data, vibration data, temperature data, back pressure data, etc. of the vacuum pump 74 in that state, it becomes easy to detect an abnormality sign.

By applying a load to the vacuum pump 74 in the state where the inside of the processing chamber 86 is not evacuated in this way, even if the vacuum pump 74 stops when the load is applied, it is possible to prevent a loss from occurring in the substrate 16. be able to. Further, when the vacuum pump 74 is stopped while the inside of the processing chamber 86 is not evacuated and a load is applied, it is considered that the vacuum pump 74 is in the state immediately before the failure. Therefore, as a result, it is possible to avoid a state in which the inside of the processing chamber 86 is evacuated, that is, a situation in which the vacuum pump 74 is stopped during substrate processing.

(Action, effect)
According to the above embodiment, since the substrate processing device 10 includes a control system for detecting an abnormality sign of a member, the member can be replaced or maintained when the control system detects an abnormality sign of the member. can.

As a result, it is possible to take measures such as replacement before the member breaks down, and it is possible to reduce the replacement frequency by using the member until just before the failure. Further, by preventing a failure during substrate processing, it is possible to improve the operating rate of the apparatus, prevent a decrease in the yield of the product (board 16), and reduce unnecessary maintenance time.

Further, according to the above embodiment, the sign detection controller 82 for detecting the abnormality sign is connected to the controller 58 for the board processing device. Therefore, it is possible to acquire and analyze data only in a specific substrate processing sequence in which an abnormality sign is easily detected.

Regarding the detection of a failure sign of the vacuum pump 74, in addition to continuously monitoring the current data, temperature data, exhaust pressure data, and vibration data of the vacuum pump 74, the processing chamber 86 is not evacuated. By intentionally creating a state in which the vacuum pump 74 is in a high load state and prone to an abnormality in the vacuum pump 74 and monitoring each of the above sensor data, it is possible to increase the accuracy of the abnormality sign.

(Other embodiments)
Although the embodiments of the present disclosure have been specifically described above, the present disclosure is not limited to the above-described embodiments, and various changes can be made without departing from the gist thereof.

For example, in the above-described embodiment, an example of forming a thin film on the substrate 16 has been described. However, the present disclosure is not limited to such an embodiment, and is also suitable when, for example, a thin film or the like formed on the substrate 16 is subjected to a treatment such as an oxidation treatment, a diffusion treatment, an annealing treatment, and an etching treatment. Applicable to.

Further, in the above-described embodiment, an example of forming a thin film by using a substrate processing apparatus 10 having a hot wall type processing furnace 44 has been described, but the present disclosure is not limited to this, and a cold wall type processing furnace is used. It can also be suitably applied to the case of forming a thin film using a substrate processing apparatus having the same. Further, in the above-described embodiment, an example of forming a thin film by using a batch type substrate processing apparatus 10 that processes a plurality of substrates 16 at a time has been described, but the present disclosure is not limited to this.

Further, the present disclosure is not limited to a semiconductor manufacturing apparatus for processing a semiconductor substrate such as the substrate processing apparatus 10 according to the above-described embodiment, and is also applicable to an LCD (Liquid Crystal Display) manufacturing apparatus for processing a glass substrate. Can be done.

10 Board processing device 16 Board 58 Controller for board processing device (example of main control unit)
74 Vacuum pump 82 Prediction detection controller (example of symptom detection unit)
86 Processing chamber μ Average value σ Standard deviation

Claims (16)

A method for manufacturing a semiconductor device in which a process recipe including a plurality of steps is executed to perform a predetermined process on a substrate.
A process of collecting sensor data of various sensors provided in at least one of the apparatus and ancillary equipment while executing the process recipe.
From the collected sensor data, a step of acquiring vibration data detected by the vibration sensor among the sensor data in the designated step of each step constituting the process recipe, and
The process of converting the acquired vibration data into a vibration frequency spectrum, and
Frequency in a predetermined range of the converted vibration frequency spectrum is extracted at a predetermined frequency interval, and for each extracted frequency, the average of the amplitudes of the vibration frequency spectrum is averaged using the data for a predetermined number of times of the process recipe in the normal state. The process of calculating values and standard deviations,
A normal model is created using the average value and standard deviation of the amplitude of the vibration frequency spectrum, and the amplitude value of the normal model is compared with a predetermined threshold value for the extracted frequencies, and the frequencies of a predetermined number or more are used. When the amplitude value deviates from the threshold value, the step of determining that there is an abnormality sign and
A method for manufacturing a semiconductor device having. The method for manufacturing a semiconductor device according to claim 1, wherein the threshold value is calculated in a range in which a value obtained by multiplying the standard deviation by 3 is added to or subtracted from the average value by using the average value and the standard deviation. The method for manufacturing a semiconductor device according to claim 1, wherein the average value and the standard deviation of the amplitude of the vibration frequency spectrum are assumed to follow a normal distribution. The method for manufacturing a semiconductor device according to claim 1, wherein the designated step is a step of reducing the pressure in the processing chamber for processing the substrate from atmospheric pressure to a predetermined pressure. Sensor data related to a vacuum pump that exhausts the atmosphere of a processing chamber for processing the substrate, and at least one of the sensor data selected from the group consisting of current data, temperature data, and exhaust pressure data of the vacuum pump. The method for manufacturing a semiconductor device according to claim 1, wherein the device is further acquired to monitor the state of the device. When the statistic of at least one sensor data selected from the group consisting of the current data, the temperature data, and the exhaust pressure data of the vacuum pump deviates from a preset threshold value for a predetermined number of times in a row, an abnormality occurs. The method for manufacturing a semiconductor device according to claim 5, which is determined to have a sign. Sensor data related to a vacuum pump that exhausts the atmosphere of a processing chamber for processing the substrate, and at least one said sensor data selected from the group consisting of current data, temperature data, and exhaust pressure data of the vacuum pump. Even if the statistic of is out of the threshold value, if the index indicating the abnormality sign calculated from the vibration data detected by the vibration sensor of the vacuum pump does not deviate from the threshold value, it is not determined that there is an abnormality sign. Item 2. The method for manufacturing a semiconductor device according to Item 1. Both the index indicating the abnormality sign calculated from the vibration data and the statistic of at least one sensor data selected from the group consisting of the current data, the temperature data, and the exhaust pressure data of the vacuum pump. The method for manufacturing a semiconductor device according to claim 7, wherein if the value deviates from the threshold value, it is determined that there is a sign of abnormality. Sensor data related to a rotary motor that rotates the substrate, which is arranged in a processing chamber for processing the substrate, and is at least one sensor data selected from a group consisting of torque value data and current data of the rotary motor. The method for manufacturing a semiconductor device according to claim 1, wherein the device is further acquired to monitor the state of the device. The method for manufacturing a semiconductor device according to claim 9, wherein if the respective statistics of the torque value data and the current data deviate from the threshold value continuously for a predetermined number of times, it is determined that there is an abnormality sign. Sensor data related to a rotary motor that rotates the substrate arranged in a processing chamber for processing the substrate, and at least one said sensor data selected from a group consisting of torque value data and current data of the rotary motor. Even if the statistic of is out of the threshold value, if the index indicating the abnormality sign calculated from the vibration data detected by the vibration sensor of the rotary motor does not deviate from the threshold value, it is not determined that there is an abnormality sign. Item 2. The method for manufacturing a semiconductor device according to item 1. When both the index indicating the abnormality sign calculated from the vibration data and the statistic of at least one of the sensor data selected from the group consisting of the torque value data and the current data deviate from the threshold value, there is an abnormality sign. The method for manufacturing a semiconductor device according to claim 11. The method for manufacturing a semiconductor device according to claim 1, wherein an index indicating a sign of abnormality is calculated from the sensor data using singular spectrum transformation, and if the index deviates from a preset threshold value, it is determined that there is a sign of abnormality. In claim 1, when it is determined that there is a sign of abnormality, an alarm is generated and the sensor data information of the sensor provided in at least one of the device and the ancillary equipment in which the sign of abnormality is recognized is displayed on the screen. The method for manufacturing a semiconductor device according to the description. Sensor data is acquired from a main control unit that controls a board to perform a predetermined process by executing a process recipe including a plurality of steps, and various sensors provided in at least one of the device and ancillary equipment. A sign detection program executed by a board processing device including a sign detection unit that monitors the state of the device.
The procedure for collecting sensor data while executing the process recipe,
From the collected sensor data, a procedure for acquiring vibration data detected by the vibration sensor among the sensor data in the designated step of each step constituting the process recipe, and
The procedure for converting the acquired vibration data into a vibration frequency spectrum and
Frequency in a predetermined range of the converted vibration frequency spectrum is extracted at a predetermined frequency interval, and for each extracted frequency, the average of the amplitudes of the vibration frequency spectrum is averaged using the data for a predetermined number of times of the process recipe in the normal state. Procedures for calculating values and standard deviations,
A normal model is created using the average value and standard deviation of the amplitude of the vibration frequency spectrum, and the amplitude value of the normal model is compared with a predetermined threshold value for the extracted frequency, and the frequencies of a predetermined number or more are said to be. If the amplitude value deviates from the threshold value, the procedure for determining that there is a sign of abnormality and
A sign detection program that causes the sign detection unit to execute. Sensor data is acquired from a main control unit that controls a board to perform a predetermined process by executing a process recipe including a plurality of steps, and various sensors provided in at least one of the device and ancillary equipment. A substrate processing device including a sign detection unit that monitors the state of the device.
The sign detection unit
Of the sensor data in the designated step of each step constituting the process recipe, the vibration data detected by the vibration sensor is acquired.
The acquired vibration data is converted into a vibration frequency spectrum, and the vibration data is converted into a vibration frequency spectrum.
Frequency in a predetermined range of the converted vibration frequency spectrum is extracted at a predetermined frequency interval, and for each extracted frequency, the average of the amplitudes of the vibration frequency spectrum is averaged using the data for a predetermined number of times of the process recipe in the normal state. Calculate the value and standard deviation,
A normal model is created using the average value and standard deviation of the amplitude of the vibration frequency spectrum.
For each extracted frequency, the amplitude value of the normal model is compared with a predetermined threshold value.
When the amplitude value of a predetermined number or more of frequencies deviates from the threshold value, it is determined that there is an abnormality sign.
Is configured to
Board processing equipment.

Images