TW202129792A - Substrate processing device, method for manufacturing semiconductor device, and sign detection program - Google Patents

Abstract

Provided is a configuration for creating a normal model by acquiring sensor data relating to a member to be subjected to anomaly sign detection, and then monitoring the state of a device on the basis of the normal model. According to the configuration, after maintenance of the member to be subjected to anomaly sign detection, sensor data is acquired, a normal model is re-created from the sensor data, the state of the device is monitored on the basis of the normal model, and a sign of anomaly is detected before the device makes an anomalous shutdown.

Description

Substrate processing device, semiconductor device manufacturing method, and sign detection program

The present invention relates to a substrate processing device, a method for manufacturing a semiconductor device, and an omen detection program.

Generally, a substrate processing apparatus that forms a thin film on a substrate such as a wafer to manufacture a semiconductor device uses a vacuum pump that evacuates the processing chamber, a flow controller that controls the flow of reactive gases, etc., an on-off valve, and a pressure gauge. , The heater of the heat treatment chamber, and the conveying mechanism for conveying the substrate are composed of various components.

Each of these various components gradually deteriorates as they are used, leading to failures, so it is necessary to exchange new components. As an exchange method, there is a situation in which the components are used until failure, or the periodic exchange cycle is determined for each component, and there is a margin of exchange before failure. Here, when the component is used until it fails, all the substrates processed by the substrate processing apparatus at the time of the failure become defective products, and there is a situation in which the substrate is lost and the production time at the time of the failure is lost. In addition, when the exchange is performed periodically before failure, it is necessary to exchange it every period that has not become a failure, that is, for a short period of time. Therefore, the frequency of exchange of components increases, which may increase the operating cost.

In addition, as in Patent Document 1 or Patent Document 2, various technologies related to the maintenance of these components are proposed, but there are still situations where it is impossible to detect the abnormality of the components in advance. [Prior Technical Literature] [Patent Literature]

[Patent Document 1] International Publication No. 2016-157402 [Patent Document 2] International Publication No. 2017-158682

[The problem to be solved by the invention]

The object of the present invention is to provide a structure that can detect the signs of abnormalities in components. [Means to solve the problem]

According to the same state of the present invention, sensor data related to the component of the abnormal sign detection object is provided to make a normal state model, and the structure of the monitoring device state is based on the aforementioned normal model, and the component of the abnormal sign detection object is After the exchange or maintenance, obtain the aforementioned sensor data, re-create the normal model based on the sensor data, and monitor the state of the aforementioned device according to the normal model, and detect abnormal signs before the aforementioned device stops abnormally structure. [Effects of the invention]

According to the present invention, a technology that can detect the signs of abnormalities in components is provided.

Hereinafter, a description will be given of a method for manufacturing a semiconductor device, an omen detection program, and a substrate processing apparatus related to an embodiment of the present invention. Furthermore, in FIG. 1, arrow F indicates the front direction of the substrate processing apparatus, arrow B indicates the rear 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.

＜The overall structure of the processing device＞ The structure of the substrate processing apparatus 10 will be described with reference to FIGS. 1 and 2. As shown in FIG. 1, the substrate processing apparatus 10 is equipped with the frame body 12 which consists of a pressure-resistant container. The front wall of the frame body 12 is provided with an opening provided for maintenance, and the opening is provided with a pair of front maintenance doors 14 as an entry mechanism for opening and closing the opening. In addition, in the substrate processing apparatus 10, a wafer cassette (substrate storage container) 18 that houses a substrate (wafer) 16 (see FIG. 2) such as silicon, which will be described later, is used as a substrate 16 to be transported to the inside and outside of the housing 12. Vehicle.

On the front wall of the frame 12, the cassette loading and unloading port is opened to communicate the inside and outside of the frame 12. A loading port 20 is provided at the loading and unloading exit of the wafer cassette. The wafer cassette 18 is placed on the loading port 20 and the wafer cassette 18 is aligned.

On the upper part of the substantially central part in the frame 12, a rotary cassette rack 22 is provided. It is configured to store a plurality of wafer cassettes 18 on the rotating cassette rack 22. The rotary wafer cassette rack 22 is provided with pillars that are vertically erected and rotated in a horizontal plane, and a plurality of rack plates supported radially in each position of the upper, middle, and lower stages.

A cassette transport device 24 is provided between the loading port 20 in the frame 12 and the rotary cassette rack 22. The cassette conveying device 24 has a cassette elevator 24A that can be raised and lowered while holding the cassette 18, and a cassette conveying mechanism 24B. With the continuous operation of the cassette elevator 24A and the cassette transport mechanism 24B, the cassette 18 is mutually transported between the loading port 20, the rotary cassette rack 22, and the cassette opener 26 described later. Mode composition.

A sub-frame 28 is provided in the lower part of the frame 12, covering from the substantially central part of the frame 12 to the rear end. On the front wall of the sub-frame 28, a pair of box openers 26 that transport the substrate 16 to the inside and outside of the sub-frame 28 are respectively provided.

Each box opener 26 is provided with a mounting table on which the wafer cassette 18 is placed, and a lid attaching and detaching mechanism 30 for attaching and detaching the lid of the wafer cassette 18. The box opening machine 26 is constructed in a manner that the cover of the wafer cassette 18 placed on the mounting table is mounted and unloaded by the cover mounting and dismounting mechanism 30 to open and close the substrate entrance and exit of the wafer cassette 18.

In the sub-frame 28, a transfer chamber 32 fluidly isolated from the space in which the cassette transport device 24, the rotary cassette rack 22, and the like are installed is formed. A substrate transfer mechanism 34 is provided in the front area of the transfer chamber 32. The substrate transfer mechanism 34 is composed of a substrate transfer device 34A capable of rotating or linearly moving the substrate 16 in a horizontal direction, and a substrate transfer device elevator 34B for raising and lowering the substrate transfer device 34A.

The substrate transfer device elevator 34B is installed between the right end of the front area of the transfer chamber 32 of the sub-frame 28 and the right end of the frame 12. In addition, the substrate transfer device 34A includes tweezers (not shown) as a holding portion of the substrate 16. The substrate 16 is configured to be capable of charging or discharging the substrate 16 to the wafer boat 36 as a substrate holder by the continuous operation of the substrate transfer device elevator 34B and the substrate transfer device 34A.

In the sub-frame 28 (transfer chamber 32), as shown in FIG. 2, a wafer boat elevator 38 for raising and lowering the wafer boat 36 is provided. The robot arm 40 is connected to the lifting platform of the wafer boat elevator 38, and a cover 42 is horizontally arranged on the robot arm 40. The cover 42 is configured to vertically support the wafer boat 36 and can seal the lower end of the processing furnace 44 described later.

Mainly, by the rotary wafer cassette rack 22 shown in FIG. 1, the wafer cassette transport device 24, the substrate transfer mechanism 34, the wafer boat 36, the wafer boat elevator 38 shown in FIG. 2, and the rotating mechanism 46 described later , Constitute a transport mechanism for transporting the substrate 16.

As shown in FIG. 1, the processing furnace 44 is installed above the standby part 50 which accommodates the wafer boat 36 and makes it stand by. In addition, a cleaning unit 52 is provided at the left end portion of the transfer chamber 32 on the opposite side from the substrate transfer device elevator 34B side. The cleaning unit 52 is configured to supply a clean atmosphere or inert gas, ie, clean air 52A.

Furthermore, on the outer peripheries of the frame body 12 and the sub-frame body 28, as an entry mechanism into the substrate processing apparatus 10, a plurality of device covers (not shown) are attached. A door switch 54 (only the door switch 54 of the housing 12 is shown) as an entry sensor is provided at the ends of the frame body 12 and the sub frame body 28 facing the device covers.

In addition, a substrate detection sensor 56 for detecting the placement of the wafer cassette 18 is provided on the loading 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 apparatus controller 58 (refer to FIG. 2 and FIG. 3) as the main control unit described later.

As shown in FIG. 2, the substrate processing apparatus 10 is located outside the housing 12 and includes a gas supply unit 60 and an exhaust unit 62. In the gas supply unit 60, a processing gas supply system and a cleaning gas supply system are housed. The processing gas supply system includes a processing gas supply source and an on-off valve (not shown), a flow controller (hereinafter abbreviated as MFC) 64A as a gas flow controller, and a processing gas supply pipe 66A. In addition, the cleaning gas supply system includes a cleaning gas supply source, an on-off valve, MFC 64B, and a cleaning gas supply pipe 66B (not shown).

In the exhaust unit 62, a gas exhaust composed of an exhaust pipe 68, a pressure sensor 70 as a pressure detection unit, and a pressure adjustment unit 72 formed by, for example, an APC (Auto Pressure Controller) valve is stored. mechanism. Although illustration is omitted, a vacuum pump 74 as an exhaust device is connected to the exhaust pipe 68 on the downstream side of the exhaust unit 62. Furthermore, the vacuum pump 74 may also be included in the gas exhaust mechanism.

As shown in FIG. 2, the substrate processing apparatus controller 58 as the main control unit is connected to the transport controller 48, the temperature controller 76, the pressure controller 78, and the gas supply controller 80, respectively. Moreover, as shown in FIG. 5, the controller 58 for substrate processing apparatuses is connected to the sign detection controller 82 which is a sign detection part mentioned later.

＜The structure of the treatment furnace＞ As shown in FIG. 2, the processing furnace 44 is provided with a reaction tube (process tube) 84. The reaction tube 84 is provided with an internal reaction tube (inner tube) 84A, and an external reaction tube (outer tube) 84B provided outside the internal reaction tube (inner tube) 84A. The inner reaction tube 84A is formed in a cylindrical shape with an open upper end and a lower end, and a processing chamber 86 for processing the substrate 16 is formed in the hollow part of the inner reaction tube 84A. The processing chamber 86 is constructed in such a way that the wafer boat 36 can be accommodated.

On the outside of the reaction tube 84, a cylindrical heater 88 is provided so as to surround the side wall surface of the reaction tube 84. The heater 88 is supported by the heater base 90 and installed vertically.

Below the outer reaction tube 84B, a cylindrical furnace mouth (manifold) 92 is arranged so as to be concentric with the outer reaction tube 84B. The furnace mouth 92 is provided so as to support the lower end of the inner reaction tube 84A and the lower end of the outer reaction tube 84B, and is respectively engaged with the lower end of the inner reaction tube 84A and the lower end of the outer reaction tube 84B.

In addition, 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 mouth 92 is supported by the heater base 90, the reaction tube 84 is in a vertically installed state. The reaction tube 84 and the furnace mouth 92 form a reaction vessel.

At the furnace mouth 92, the processing gas nozzle 96A and the cleaning gas nozzle 96B are connected to communicate with the processing chamber 86. A processing gas supply pipe 66A is connected to the processing gas nozzle 96A. On the upstream side of the processing gas supply pipe 66A, an MFC 64A is permeated, and a processing gas supply source (not shown) or the like is connected. In addition, a cleaning gas supply pipe 66B is connected to the cleaning gas nozzle 96B. On the upstream side of the cleaning gas supply pipe 66B, an MFC 64B is permeated, and a cleaning gas supply source (not shown) or the like is connected.

To the furnace mouth 92, an exhaust pipe 68 for exhausting the atmosphere of the processing chamber 86 is connected. The exhaust pipe 68 is disposed at the lower end of the cylindrical space 98 formed by the gap between the inner reaction tube 84A and the outer reaction tube 84B, and communicates with the cylindrical space 98. On the downstream side of the exhaust pipe 68, the pressure sensor 70, the pressure adjusting unit 72, and the vacuum pump 74 are connected in this order from the upstream side.

Below the furnace mouth portion 92, there is provided a disc-shaped lid body 42 that can air-tightly block the opening of the lower end of the furnace mouth portion 92. On the upper surface of the lid body 42, a contact with the lower end of the furnace mouth portion 92 is provided. O-ring 100 as a sealing member.

A rotation mechanism 46 for rotating the wafer boat 36 is provided near the center of the lid 42 on the side opposite to the processing chamber 86. The rotating shaft 102 of the rotating mechanism 46 penetrates the cover 42 and supports the wafer boat 36 from below. In addition, the rotating mechanism 46 has a built-in rotating motor 46A, and the rotating shaft 102 of the rotating mechanism 46 is rotated by the rotating motor 46A, and the wafer boat 36 is rotated to rotate the substrate 16.

The cover 42 is constructed in such a manner that it is raised and lowered in a vertical direction by a wafer boat elevator 38 provided outside the reaction tube 84. It is configured to be able to transport the wafer boat 36 to the processing chamber 86 by raising and lowering the cover 42. The rotating motor 46A of the rotating mechanism 46 and the wafer boat elevator 38 are electrically connected to the transport controller 48.

The wafer boat 36 is constructed by aligning a plurality of substrates 16 in a horizontal posture and aligned with each other in the center, and holding them in multiple stages. In addition, in the lower part of the wafer boat 36, a plurality of heat-insulating plates 104 in the shape of a circular plate as a heat-insulating member are arranged in multiple stages in a horizontal posture. The wafer boat 36 and the heat insulation board 104 are made of, for example, heat-resistant materials such as quartz or silicon carbide. The heat insulation board 104 is installed so that it is difficult for the heat from the heater 88 to be transmitted to the furnace mouth 92 side.

In addition, in the reaction tube 84, a temperature sensor 106 as a temperature detector is provided. The heater 88 and the temperature sensor 106 are electrically connected to the temperature controller 76.

<Operation of substrate processing equipment> Next, referring to FIGS. 1 and 2, a method of forming a thin film on the substrate 16 will be described as one of the processes of manufacturing a semiconductor device. In addition, the operation of each part constituting the substrate processing apparatus 10 is controlled by the controller 58 for the substrate processing apparatus.

As shown in FIG. 1, if the wafer cassette 18 is supplied to the load port 20 by an in-process transport device (not shown), the wafer cassette 18 is detected by the substrate detection sensor 56 and the wafer cassette is loaded in and transported. The exit is opened by the front gate (not shown). Then, the cassette 18 on the load port 20 is carried in from the cassette carrying-in/outlet into the housing 12 by the cassette transport device 24.

The cassette 18 carried into the housing 12 is automatically transported to the shelf of the rotary cassette rack 22 by the cassette transport device 24 and temporarily stored. After that, the wafer cassette 18 is transferred from the shelf to the mounting table of the box opener 26 on one side. Furthermore, the cassette 18 carried into the housing 12 may be directly transferred to the mounting table of the cassette opener 26 by the cassette transport device 24.

The lid of the wafer cassette 18 placed on the mounting table is removed by the lid attaching and detaching mechanism 30 to open the substrate entrance and exit. After that, the substrate 16 (refer to FIG. 2) is picked up from the wafer cassette 18 by the tweezers of the substrate transfer device 34A through the substrate entrance and exit, and the orientation is aligned by a notch alignment device not shown, and then transferred to the transfer. The waiting part 50 at the rear of the chamber 32 is loaded in the wafer boat 36. Then, the substrate transfer device 34A returns to the stage where the wafer cassette 18 is placed, and the next substrate 16 is taken out from the wafer cassette 18 and loaded on the wafer boat 36.

During the loading operation of the wafer boat 36 of the substrate 16 by the substrate transfer mechanism 34 of the box opener 26 of the one side (upper or lower), on the mounting table of the box opener 26 of the other side (lower or upper) The other wafer cassettes 18 are transported from the rotary cassette rack 22 by the cassette transport device 24. The other wafer cassette 18 is transferred to the mounting table, and the wafer cassette 18 is opened by the cassette opener 26 at the same time.

When a predetermined number of substrates 16 are loaded into the wafer boat 36, the lower end of the processing furnace 44 is opened by a furnace gate (not shown). Next, the wafer boat 36 system cover 42 holding the group of substrates 16 is carried (loaded) into the processing furnace 44 by the raising of the wafer boat elevator 38.

As described above, when the wafer boat 36 holding the plurality of substrates 16 is carried (loaded) into the processing chamber 86 of the processing furnace 44, as shown in FIG. The state of the lower end of 92.

After that, the processing chamber 86 is evacuated by the vacuum pump 74 so as to have a desired pressure (vacuum degree). At this time, based on the pressure value measured by the pressure sensor 70, the pressure adjustment unit 72 (the opening degree of the valve) is feedback-controlled. Moreover, the processing chamber 86 is heated by the heater 88 so that it may become a desired temperature. At this time, according to the temperature value detected by the temperature sensor 106, the energization amount of the heater 88 is feedback-controlled. Next, the rotation mechanism 46 rotates the wafer boat 36 and the substrate 16.

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

When the preset processing time has elapsed, the cleaning gas supplied from the cleaning gas supply source and controlled to achieve the desired flow rate by the MFC64B is supplied to the processing chamber 86, the processing chamber 86 is replaced with an inert gas, and the pressure of the processing chamber 86 The pressure returns to normal pressure.

After that, the lid 42 is lowered by the wafer boat elevator 38, the lower end of the furnace mouth 92 is opened, and the wafer boat 36 holding the processed substrate 16 is carried out (unloaded) from the lower end of the furnace mouth 92 to the reaction tube 84 external. After that, the processed substrate 16 is taken out (unloaded) from the wafer boat 36 and stored in the wafer cassette 18.

After the removal, in addition to the integration process of the scribe calibration device, the wafer cassette 18 storing the processed substrate 16 is carried out of the housing 12 in a procedure almost opposite to the above-mentioned procedure.

<The structure of the controller for substrate processing equipment> Next, referring to FIG. 3, the controller 58 for the substrate processing apparatus as the main control unit will be specifically described.

The substrate processing device controller 58 is mainly composed of a CPU (Central Processing Unit) and other arithmetic control unit 108, a memory unit 114 equipped with RAM110, ROM112, and HDD (not shown), an input unit 116 such as a mouse and a keyboard, and monitoring It is composed of a display unit 118 such as a monitor. Furthermore, it is structured such that various 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 hub of the substrate processing device controller 58, executes the control program stored in the ROM 112, and follows the instructions from the input unit 116 to execute the recipe stored in the storage unit 114 that also constitutes the prescription storage unit (for example, as a substrate Process prescriptions for processing prescriptions, etc.).

The ROM 112 is a recording medium composed of a flash memory, a hard disk, etc., and stores the operation program of the arithmetic control unit 108 that controls the operation of the various components of the substrate processing apparatus 10 (for example, the vacuum pump 74, etc.). In addition, the RAM 110 (memory) has a function as a work area (temporary memory) of the arithmetic control unit 108.

Here, the substrate processing recipe (process recipe) is a recipe defining processing conditions and processing procedures for processing the substrate 16. In addition, in the recipe file, the setting values and transmission timings sent to the transport controller 48, the temperature controller 76, the pressure controller 78, and the gas supply controller 80 are set corresponding to each step of the substrate processing recipe.

The arithmetic control unit 108 has a function of controlling the temperature and pressure in the processing furnace 44, the flow rate of processing gas introduced into the processing furnace 44, and the like to perform predetermined processing on the substrate 16 loaded in the processing furnace 44.

The transfer controller 48 controls the transfer operations of the rotary wafer cassette rack 22, the wafer boat elevator 38, the wafer cassette transfer device 24, the substrate transfer mechanism 34, the wafer boat 36, and the rotating mechanism 46 that constitute the transfer substrate 16, respectively. The way to constitute.

In addition, sensors are built in the rotary wafer cassette rack 22, the wafer boat elevator 38, the wafer cassette transport device 24, the substrate transfer mechanism 34, the wafer boat 36, and the rotation mechanism 46, respectively. When each of these sensors indicates a predetermined value or an abnormal value, etc., the controller 58 for the substrate processing apparatus is notified of the essence thereof. Furthermore, the detection system for the signs of abnormalities in the various components of the substrate processing apparatus 10 will be described in detail later.

The memory portion 114 is provided with a data storage area 120 for storing various data, etc., and a program storage area 122 for storing various programs including substrate processing recipes. The data storage area 120 stores various parameters associated with the prescription file. In addition, in the program storage area 122, various programs required for controlling the device including the above-mentioned substrate processing recipe are stored.

Moreover, the display part 118 of the controller 58 for substrate processing apparatuses is provided with the touch panel which is not shown in figure. The touch panel is configured to display an operation screen that accepts input of operation instructions to the above-mentioned substrate transport system and substrate processing system. In addition, the controller 58 for the substrate processing apparatus is like an operation terminal (terminal device) such as a computer and a mobile terminal, as long as it has a structure including at least the display unit 118 and the input unit 116.

The temperature controller 76 controls the temperature of the heater 88 of the processing furnace 44 to adjust the temperature in the processing furnace 44. In addition, when the temperature sensor 106 indicates a predetermined value, an abnormal value, or the like, the substrate processing apparatus controller 58 is notified of the essence thereof.

The pressure controller 78 controls the pressure adjusting unit 72 in such a way that the pressure of the processing chamber 86 becomes the desired pressure at a desired timing based on the pressure value detected by the pressure sensor 70. In addition, when the pressure sensor 70 indicates a predetermined value, an abnormal value, or the like, the substrate processing apparatus controller 58 is notified of the essence thereof.

The gas supply controller 80 is configured to control the MFCs 64A and 64B so that the flow rate of the gas supplied to the processing chamber 86 becomes a desired flow rate at a desired timing. Furthermore, when a sensor (not shown) included in the MFC 64A, 64B, etc. indicates a predetermined value or an abnormal value, the controller 58 for the substrate processing apparatus is notified of the essence thereof.

＜Substrate processing engineering＞ Next, the outline of a substrate processing process in which the substrate processing apparatus 10 of this embodiment is used as a semiconductor manufacturing apparatus to process a substrate will be described with reference to FIG. 4. This substrate processing process is, for example, a process of manufacturing methods of semiconductor devices (IC, LSI, etc.). In addition, in the following description, the operation and processing of each part constituting the substrate processing apparatus 10 are controlled by the substrate processing apparatus controller 58.

Here, an example of forming a film on the substrate 16 by alternately supplying a source gas (first processing gas) and a reaction gas (second processing gas) to the substrate 16 will be described. In addition, in the following, hexachlorosilane (Si ₂ Cl ₆ , abbreviated as HCDS hereinafter) gas is _{used as the raw material gas, and ammonia (NH 3} ) is used as the reaction gas, and silicon nitride is formed as a thin film on the substrate 16 An example of (SiN) film will be described. Furthermore, 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.

(Board Import Project S102) First, in the substrate carrying process S102, the substrate 16 is loaded on the wafer boat 36 and carried into the processing chamber 86.

(Film forming process S104) In the film forming process S104, the next four steps are sequentially performed to form a thin film on the surface of the substrate 16. Furthermore, during steps 1 to 4, the heater 88 is used to heat the substrate 16 to a predetermined temperature.

[step 1] In step 1, the on-off valve (not shown) provided in the processing gas supply pipe 66A and the pressure adjusting part 72 (APC valve) provided in the exhaust pipe 68 are opened, and the HCDS gas whose flow rate is adjusted by the MFC64A is passed through Process gas supply pipe 66A. Then, while supplying the HCDS gas to the processing chamber 86 from the processing gas nozzle 96A, the gas is exhausted from the exhaust pipe 68. At this time, the pressure of the processing chamber 86 is maintained at a predetermined pressure. Thereby, a silicon thin film (Si 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, and the supply of HCDS gas is stopped. The pressure adjusting part 72 (APC valve) of the exhaust pipe 68 is set in an open state, and the processing chamber 86 is exhausted by the vacuum pump 74 to remove residual gas from the processing chamber 86. In addition, the on-off valve provided in the cleaning gas supply pipe 66B is opened to _{supply an inert gas such as N 2} to the processing chamber 86 to clean the processing chamber 86, and the residual gas in the processing chamber 86 is discharged to the outside of the processing chamber 86.

[Step 3] In step 3, the on-off valve not shown in the purge gas supply pipe 66B is opened, and the pressure adjustment part 72 (APC valve) provided in the exhaust pipe 68 is used to adjust the flow rate of NH by MFC64B. _{The gas of 3} passes through the purge gas supply pipe 66B. _{Then, while supplying the NH 3} gas from the cleaning gas nozzle 96B to the processing chamber 86, the gas is exhausted from the exhaust pipe 68. At this time, the pressure of the processing chamber 86 is maintained at a predetermined pressure. Thereby, the Si film formed on the surface of the substrate 16 by the HCDS gas _{reacts with the NH 3} gas to form a SiN film on the substrate 16.

[Step 4] In step 4, the on-off valve of the purge gas supply pipe 66B is closed, and the supply of _{NH 3 gas is stopped.} The pressure adjusting part 72 (APC valve) of the exhaust pipe 68 is set in an open state, and the processing chamber 86 is exhausted by the vacuum pump 74 to remove residual gas from the processing chamber 86. In addition, _{an inert gas such as N 2 is} supplied to the processing chamber 86, and the processing chamber 86 is cleaned again.

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

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

<The control system of this embodiment> Next, the control system for detecting the signs of abnormality (the signs of failure) of each member of the substrate processing apparatus 10 will be described with reference to FIGS. 5 and 6. Furthermore, the following description uses an example of forming a thin film on the substrate 16 by the substrate processing apparatus 10.

As shown in FIG. 5, the control system includes a substrate processing device controller 58 as a main control unit, an omen detection controller 82 as an omen detection unit, various sensors 124, and a data collection unit (Data Collection Unit). , Hereinafter referred to as DCU) 126, and Edge Controller (hereinafter referred to as EC) 128, which are respectively connected by wire or wireless.

The controller 58 for the substrate processing apparatus is connected to a host computer (not shown) including a host computer of the customer, and an operating unit (not shown). The operation part has a structure in which various data (sensor data, etc.) obtained by the substrate processing apparatus controller 58 can be interchanged with the host computer.

The omen detection controller 82 obtains sensor data from sensors provided in various components of the substrate processing apparatus 10 to monitor the state of the substrate processing apparatus 10. Specifically, the omen detection controller 82 uses data from various sensors 124 to calculate a numerical index, compares it with a predetermined threshold, and detects abnormal omen. Furthermore, the omen detection controller 82 is a built-in omen detection program that detects abnormal omen based on the movement of the sensor data.

In addition, the omen detection controller 82 has two systems of a system directly connected to the substrate processing device controller 58 and a system connected to the substrate processing device controller 58 via the DCU 126. Therefore, when an abnormal sign is detected by the sign detection controller 82, it does not pass through the DCU126 to directly output a signal to the substrate processing device controller 58 to generate an alarm, and it can be installed on the component that is determined to have an abnormal sign. The information of the sensor data of the sensor is displayed on the screen of the display unit 118 (refer to FIG. 3).

Various sensors 124 are sensors (for example, pressure sensor 70 and temperature sensor 106, etc.) installed in various components of the substrate processing apparatus 10 to detect the flow rate, concentration, temperature, and humidity of each component (Dew point), pressure, current, voltage, voltage, torque, vibration, position, rotation speed, etc.

The DCU 126 collects and accumulates data of various sensors 124 during the execution of the process recipe. In addition, EC128 is based on the type of sensor, once the sensor data is captured, the original data is processed by Fast Fourier Transform (hereinafter referred to as FFT), and then sent to the omen detection controller. 82.

In addition, 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 0.1 second units. From the first sensor system 124A through the substrate processing device controller 58 and DCU126, the raw data is sent to the omen detection controller 82 in real time . The first sensor system 124A includes sensors such as a temperature sensor, a pressure sensor, and a gas flow sensor.

On the other hand, the second sensor system 124B is a system that applies processing such as FFT with EC128, extracts only the parts necessary for analysis, and sends the data in the form of processed files. From the second sensor system 124B through EC128, The processed data is sent to the omen detection controller 82. The second sensor system 124B includes sensors such as vibration sensors.

When the sensor is a vibration sensor, the vibration data is accumulated in milliseconds, so the amount of data becomes large. If the data is directly sent to the omen detection controller 82, the memory capacity of the omen detection controller 82 will increase. Consumption. The data of the vibration sensor is finally processed by FFT, etc. for analysis. Therefore, using EC128 to implement this processing in advance can reduce the amount of information and send it to the omen detection controller 82 as a form of easy-to-analyze data. .

(First Embodiment) Hereinafter, the first embodiment of the detection process of the signs of abnormality in each member of the substrate processing apparatus 10 using the above-mentioned control system will be specifically described.

[Calculation of abnormality] First, use the values detected by the sensors of a plurality of components directly set on the component of the abnormal sign detection object, and the values detected by the sensors of other components that directly or indirectly affect the state of the component to calculate " Abnormality". In the present embodiment, for example, if a member with an abnormal sign detection target approaches an abnormal state, the value of abnormality will probably increase. Furthermore, the abnormality is constituted in a way that the value of the component with the detection target of anomaly signs will decrease if it approaches the abnormal state.

[Original data constituting abnormality] The sequence of substrate processing is, for example, the loading of the substrate 16 into the processing chamber 86, the vacuum processing in the processing chamber 86, the temperature rise, the cleaning by inert gas, the temperature rise waiting, the processing of the substrate 16 (e.g., film formation), and the processing chamber. The gas replacement in 86, the return to atmospheric pressure, and the carrying out of the processed substrate 16 are composed of many events with various purposes. Furthermore, the aforementioned event is an example of a substrate processing sequence, and each event may be more finely divided.

In this embodiment, not all the sensor data in the sequence are used, but the value of one or more sensors in one or more specific events in these events is used as the calculation in the algorithm. Numerical indicators are the raw data of "abnormality". In addition, the abnormality value of each Run is monitored, and the signs of abnormality of each member of the substrate processing apparatus 10 are detected. In this way, the use of data that only uses specific events can save data accumulation.

For example, the detection of abnormal signs of the vacuum pump 74 becomes an easy-to-detect state when the vacuum pump 74 bears a large load. The step of reducing the pressure of the processing chamber 86 from atmospheric pressure to a predetermined pressure, that is, the pressure band close to the atmospheric pressure between the beginning of the vacuum processing and a few minutes after the beginning of the vacuum processing corresponds to the timing when the vacuum pump 74 bears a large load.

Specifically, one substrate processing apparatus 10 is responsible for multiple processes, and there are cases where different film formation conditions are different, and different processing recipes are mixed and started. During the film formation of the substrate 16, the raw material gas is circulated, so the raw material gas reacts or thermally decomposes to produce a solid state. In this state, there may also be a load on the vacuum pump 74, so the film formation event is monitored One thing is effective for the detection of anomaly signs.

On the other hand, the events of the vacuum processing before the substrate processing are common even if the subsequent substrate processing events are different. That is, even when multiple recipes with different film forming conditions are started with the same device, it is possible to obtain sensor data by monitoring the state at the start of the vacuum process common to each Run, regardless of the content of the substrate processing. Knowing the changes over time in the same state enables highly accurate predictions.

[Calculation example of abnormality] Here, the conditions of using the sensor data of the vibration sensor are respectively disclosed, that is, the use of sensors other than the vibration sensor (such as current sensor, temperature sensor, exhaust pressure sensor, torque value) Data, that is, current data, etc.) The calculation example of the abnormality of the condition of the sensor data.

First, use the sensor data (vibration data) of the vibration sensor to determine whether there is an abnormal condition for each frequency individually, as the procedure shown below.

(1) Obtain the vibration data (original data) detected by the vibration sensor among the sensor data of the designated steps in each step of the process recipe. (2) Convert the acquired vibration data into a vibration frequency spectrum by processing such as FFT, and extract the frequency of the converted vibration frequency spectrum (for example, 10Hz~5000Hz) at a predetermined frequency interval (for example, every 10Hz) (numerical system). The amplitude (envelope) of the vibration, the exemplified situation is 500 dimensions). (3) For each frequency extracted, use the data of the specified number of times of the process recipe (for example, 30 Run minutes) to calculate the average value μ and the standard deviation σ of the amplitude of the vibration spectrum. The amplitude under normal conditions is assumed to follow the normal distribution. N(μ, σ), set it as a normal model. (4) Set the value of (2) after the normal model is created as an abnormality vector, and compare the amplitude value of the normal model with a predetermined threshold for each frequency extracted, and the number is greater than the set number (for example, m(m When the amplitude value of the frequency of ≧1) or more) deviates from the threshold value, it is determined that an abnormal sign has occurred (there is an abnormal sign). Furthermore, the threshold value is calculated in the range (μ±3σ) in which the average value μ and the standard deviation σ obtained in (3) are added to or subtracted from the value of 3 times the standard deviation σ. calculate.

In addition, when the sensor data (vibration data) of the vibration sensor is used to make a judgment based on the sum of the amplitude of each frequency, the procedure is as shown below.

(1) Obtain the vibration data (original data) detected by the vibration sensor among the sensor data of the designated steps in each step of the process recipe. (2) Convert the acquired vibration data into a vibration frequency spectrum by processing such as FFT, and extract the frequency of the converted vibration frequency spectrum (for example, 10Hz~5000Hz) at a predetermined frequency interval (for example, every 10Hz) (numerical system). The amplitude (envelope) of the vibration, the exemplified situation is 500 dimensions). (3) Add the sum of the amplitudes of the extracted frequencies to each Run under normal conditions (one amplitude sum is obtained for every 1 Run, so 30 numbers can be obtained for 30 Runs). (4) Calculate the average μ and standard deviation σ based on the numerical group obtained by each Run, and assume that the sum obtained by each Run follows the normal distribution N (μ, σ), and set it as a normal model. (5) Set the value of (3) after the normal state model is created as abnormality, compare the amplitude value of the normal state model with the predetermined threshold value. When the amplitude value deviates from the threshold value, it is judged that there is an anomaly (a sign of an abnormality) . Furthermore, the threshold value is calculated in the range (μ±3σ) in which the average value μ and the standard deviation σ obtained in (3) are added to or subtracted from the value of 3 times the standard deviation σ. calculate.

Also, when using sensor data other than vibration data to make a judgment for each basic statistic, the procedure is as shown below.

(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 under normal conditions. (2) Calculate the average μ and standard deviation σ of the selected basic statistics of the normal time, assuming that the basic statistics follow a normal distribution. Set it as a normal model of the basic statistics of the sensor. (3) The value of (1) after the normal state model is created is set as abnormality, and for each basic statistic, when the value deviates from a predetermined threshold value, it is judged that there is an abnormal sign. Furthermore, the threshold value is calculated in the range (μ±3σ) in which the average value μ and the standard deviation σ obtained in (2) are added to or subtracted from the value of 3 times the standard deviation σ. calculate.

Also, as shown in FIG. 6, when using sensor data other than vibration data and using singular spectrum conversion to make a judgment, the procedure is as shown below. Furthermore, in the following procedure, using the partial time series of the peripheral window width n of Run p, two data rows X and Z are created in the past and present measurements. The following procedure is a general calculation method for singular spectrum conversion.

(1) As an M-dimensional row vector (column vector), prepare to connect n columns from the top S(p-n+1, 1) to the bottom S(p, M). Row vector of Mn dimension. Run p-n+1 target event time 1, 2, ････, M sensor data {S(p-n+1, 1), S(p-n+1, 2), ･ ･･･, S(p-n+1, M)} ･･･ Time 1, 2, ････, M’s sensor data {S(p-1, 1 ), S(p-1, 2), ････, S(p-1, M)} Time 1, 2, ････, M’s sensor data {S( p, 1), S(p, 2), ････, S(p, M)} (2) are respectively regarded as M-dimensional row vectors, and prepare to start from the top S(p-n+1 , 1) Up to the bottom S(p,M), connect n rows of Mn-dimensional row vectors (compared with (1), shift to an older Run group). Run pn target event time 1, 2,････, M sensor data {S(pn,1), S(pn,2),････, S(pn,M)} ･ ･･ Time 1, 2, ････, M sensor data {S(p-2, 1), S(p-2, 2), ････, S(p-2, M)} Time 1, 2, ････ of the target event of Run p-1, M’s sensor data {S(p-1, 1), S(p-1, 2 ), ････, S(p-1, M)} (3) Same as above (1), (2), prepare K row vectors constructed in sequence, and make it from old to new and left to The rows and columns of Mn×K dimensions X(p) formed by the row vectors are arranged side by side on the right. Use the above content to create a history line for implementing the singular spectrum conversion. (4) As an M-dimensional row vector, prepare to connect n vertically from the top S(p+L, 1) to the bottom S(p+L-n+1, M). Row vector of Mn dimension. Furthermore, set L to a positive integer. Run p+L target event time 1, 2,････, M sensor data {S(p+L, 1), S(p+L, 2), ････, S( p+L, M)} ･･･ Run p+L-n+2 at time 1, 2,････, M sensor data {S(p+L-n+2, 1 ), S(p+L-n+2, 2), ････, S(p+L-n+2, M)} Time 1, 2, of the target event of Run p+L-n+1 ････, M sensor data {S(p+L-n+1, 1), S(p+L-n+1, 2), ････, S(p+L-n +1, M)} (5) are respectively regarded as M-dimensional row vectors, and prepare to connect them in tandem from the top S(p+L-1, 1) to the bottom S(p+Ln, M) Row vectors of Mn dimension formed by n (compared with (4), shifted to an older Run group). Run p+L-1 target event time 1, 2, ････, M sensor data {S(p+L-1, 1), S(p+L-1, 2), ･ ･･･, S(p+L-1, M)} ･･･ Run p+L-n+1 at time 1, 2, ････, M’s sensor data {S(p +L-n+1, 1), S(p+L-n+1, 2), ････, S(p+L-n+1, M)} Run p+Ln target event time Sensor data of 1, 2, ････, M {S(p+Ln, 1), S(p+Ln, 2), ････, S(p+Ln, M)} (6 ) Similar to the above (4) and (5), prepare R row vectors constructed in sequence, and create a Mn×R dimension row and column Z(p ). Using the above content, make a rank of singular spectrum conversion test. (7) Perform singular value decomposition on the aforementioned rank X(p) and rank Z(p), and implement singular spectrum conversion. (8) Take the left singular vector obtained by singular value decomposition, select r from X(p), select m from Z(p), and form a rank with U(r) and Q(m) respectively, and find The maximum singular value of the product U(r) ^T Q(m) of the same. Let this be λ (0≦λ≦1), and let 1-λ be the degree of abnormality (degree of change). When the degree of abnormality deviates from a predetermined threshold value, it is judged that there is a sign of abnormality.

[Using abnormality to determine the signs of abnormality] In addition, as a method of judging whether the abnormality is a sign of abnormality, for example, the following methods can be considered. In addition, when it is determined that there is a sign of abnormality, the controller 58 for the substrate processing apparatus is notified.

(1) When the abnormality of at least one sensor data deviates from the threshold, it is determined that there is an abnormal sign. (2) When the abnormality of two or more sensor data deviates from the threshold, it is determined that there is an abnormal sign. (3) When the abnormality of one or more sensor data deviates from the threshold a predetermined number of times (for example, 3 times), it is determined that there is a warning of abnormality. (4) When the abnormality of the sensor data other than the vibration data deviates from the threshold continuously a predetermined number of times (for example, 3 times), it is determined that there is a warning of abnormality. (5) Even if the abnormality of sensor data other than the vibration data deviates from the threshold, and the abnormality of the vibration data does not deviate from the threshold, the method is not judged as a sign of abnormality. (6) When the abnormality of the vibration data and the abnormality of the sensor data other than the vibration data deviate from the threshold value, it is a method to determine that there is an abnormal sign.

For example, in the aforementioned methods (2), (5), and (6), multiple sensor data are used to determine abnormal signs, so that false detection of sensors can be reduced. In addition, the dynamics of abnormality are not necessarily monotonous, so in the methods (3) and (4) described above, it is possible to reduce erroneous judgments when the value of abnormality shifts before or after the threshold value. Furthermore, the calculation formula of abnormality is different for each component and each device of the threshold, and the formula is incorporated in the omen detection controller 82 in advance.

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

[Existence of EC] Here, the case of the second sensor system 124B shown in FIG. 5, that is, the case where there is an EC128 between the sensor and the omen detection controller 82, will be described.

[Time synchronization] The data of the vibration sensor is converted by EC128, so it is sent to the omen detection controller 82 in the form of a time with EC128. In order to use the data of the vibration sensor together with the data of the DCU 126 and other sensors having the time on the side of the controller 58 for the substrate processing apparatus for analysis, it is necessary to synchronize the time of the two for analysis. Therefore, the EC128, DCU126, and the omen detection controller 82 use the time of the substrate processing apparatus controller 58 as the reference time, and periodically capture the time to synchronize the time. In this way, the time of all components is synchronized, and correct analysis can be performed.

Here, taking the vacuum pump 74 (refer to FIG. 2) as an example, the method for detecting the signs of abnormality of the components of the substrate processing apparatus 10 will be specifically described.

In the processing chamber 86 of the substrate processing apparatus 10, reaction by-products of the processing gas are accumulated inside. When the amount and height of the reaction by-products reach a certain level, the rotation of the vacuum pump 74 will abruptly stop.

Here, the current data, temperature data, exhaust pressure data, and vibration data of the vacuum pump 74 are continuously monitored for at least one sensor data, and these sensors are analyzed by the foreboding detection program in the foreboding detection controller 82 Changes in the behavior of the data can detect signs of abnormality in the vacuum pump 74. When a sign of abnormality is detected, the information is sent to the controller 58 for the substrate processing apparatus, and the operator is notified by the exchange and maintenance of the vacuum pump 74.

(Second Embodiment) Next, the second embodiment of the process of detecting abnormal signs of each member of the substrate processing apparatus 10 using the above-mentioned control system will be specifically described. In addition, the structure of the omen detection controller 82 and the like and the abnormal omen judgment using abnormality are the same as those of the first embodiment.

[Calculation of abnormality] In this embodiment, the sensor values of a plurality of components set on the detection target of anomaly signs and the sensor values of other components that directly or indirectly affect the state of the component are used to learn the normal sensing Calculate the "abnormality" by using the data from the learning and the data in operation.

In the present embodiment, for example, if a member with an abnormal sign detection target approaches an abnormal state, the value of abnormality will probably increase. Furthermore, the abnormality is constituted in a way that the value of the component with the detection target of anomaly signs will decrease if it approaches the abnormal state.

Here, taking the vacuum pump 74 (refer to FIG. 2) as an example, the method for detecting the signs of abnormality of the components of the substrate processing apparatus 10 will be specifically described.

Generally, in a state where the processing chamber 86 is vacuum-processed by the vacuum pump 74, the inert gas and the film-forming gas are circulated through the vacuum pump 74 to be in a state where the load is high, and it becomes a state where it is easy to detect abnormal signs. On the other hand, in a state where the vacuum pump 74 is not vacuuming the processing chamber 86, the load of the vacuum pump 74 becomes a small state, and it becomes a state where it is difficult to detect an abnormality or an abnormality is difficult to occur. Therefore, previously, the vacuum pump 74 was monitored in a state where the processing chamber 86 was subjected to vacuum processing.

In contrast, in this embodiment, the vacuum pump 74 does not perform vacuum processing on the processing chamber 86, and in the event that the substrate 16 is not in the state of the processing chamber 86, a large amount of gas is intentionally circulated to the vacuum pump 74 , 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 this state, it becomes easy to detect abnormal signs.

In this way, by applying a load to the vacuum pump 74 in a state where the processing chamber 86 is not subjected to vacuum processing, even if the vacuum pump 74 is stopped when the load is applied, it is possible to prevent the substrate 16 from being lost. In addition, when the vacuum pump 74 is stopped simply by applying a load in a state where the processing chamber 86 is not vacuumed, it can be estimated that the vacuum pump 74 is about to fail. Therefore, as a result, it is possible to avoid a situation in which the vacuum pump 74 is stopped in a state where the processing chamber 86 is subjected to vacuum processing, that is, during substrate processing.

(Third Embodiment) Next, the third embodiment of the process of detecting the signs of abnormality in each member of the substrate processing apparatus 10 using the above-mentioned control system will be specifically described. In addition, the structure of the omen detection controller 82 and the like, and the abnormal omen judgment using the degree of abnormality are the same as those of the first and second embodiments.

In this embodiment, when exchanging or maintaining the components to be detected for abnormal signs, a normal model after the exchange or maintenance is created, and the substrate processing apparatus 10 is monitored based on the normal model, and abnormal signs are judged.

In this embodiment, the exchange or maintenance of the components for the detection target of abnormal signs is automatically or semi-automatically detected. For example, when the component to be detected by the abnormal sign has accumulated operating time information, the accumulated operating time information can be used to detect component exchange. The accumulated operation time of the component to be detected by the anomaly sign is usually held by the non-volatile memory medium. Therefore, the accumulated operation time is calculated until the component is exchanged, and the operation time is reset by the exchange. Therefore, the accumulated operation time of the component that monitors the detection target of abnormal signs can detect that the component has been exchanged when the accumulated operation time is reduced.

Specifically, the controller 58 for the substrate processing apparatus transmits the accumulated operation time of the component subject to the abnormal sign detection to the sign detection controller 82 at predetermined intervals, and the sign detection controller judges the newly transmitted operation total. Is the time shorter than the accumulated running time previously memorized? When the judgment is affirmative, it can be judged that the component has been exchanged.

In addition, instead of the accumulated operation time information, even if the component to be detected by the abnormal sign does not have the accumulated operation time, the operation of removing the signal connector at the time of component exchange can be used to detect component exchange. In the work of removing the signal connector when the component is exchanged, the signal line of the component will become an open circuit (disconnection), so when the signal line of the component becomes an open circuit (disconnection), the next signal line is energized At the time, the operator urges the operator to confirm whether there is an exchange or maintenance input. For example, if it is set on the operation screen without confirmation input, other operations cannot be started. With this, it can be semi-automatically determined that the component has been exchanged.

When it is judged that there is an exchange or maintenance of the component targeted for the detection of anomaly signs, the omen detection controller 82, as a part of the omen detection process, retrieves the sensor data of the component targeted for the anomaly detection, and updates Normal model. Then, according to the updated normality model, the abnormality is calculated. The calculation of abnormality and the detection of signs caused by monitoring abnormality values can be performed in the same manner as in the first and second embodiments.

Here, taking the exchange vacuum pump 74 (refer to FIG. 2) as an example, the method for detecting the signs of abnormality of the components of the substrate processing apparatus 10 will be specifically described.

The substrate processing apparatus controller 58 uses the sensor data of the vacuum pump 74 to obtain the operating time until the vacuum pump 74 is exchanged. If the operating time is acquired, the operating time of the vacuum pump 74 obtained is accumulated, and the operating time is reset by the exchange (operating integration Time). In addition, the substrate processing apparatus controller 58 is connected to the sign detection controller 82 as shown in FIG. 5, and sends the accumulated operation time to the sign detection controller 82 at predetermined intervals. Furthermore, the time for accumulating the operating time of the vacuum pump 74 (operating integrated time) can also be managed by the omen detection controller 82 by directly obtaining the operating time from the vacuum pump 74.

The omen detection controller 82 is a part of the omen detection process. As shown in FIG. 7, it obtains the integrated operation time sent from the substrate processing apparatus controller 58 (S10), and determines whether it is shorter than the previously memorized integrated operation time (S12) When the judgment is affirmative, it is judged that there is an exchange of the vacuum pump 74, and the sensor data required for the creation of the normal model after the exchange is obtained (S14). For example, the sensor data (for example, 30 Run points) of a predetermined number of minutes of the process recipe is obtained. Then, based on the acquired sensor data, a normal model is created (S15). For example, using the sensor data of a predetermined number of times in the process recipe to find the average μ and the standard deviation σ, the sensor data under normal conditions is assumed to follow the normal distribution N (μ, σ), and set it as Normal model. According to the normal state model obtained, the abnormality is calculated (S16), and the previously memorized abnormality data is rewritten into the calculated abnormality (S17). Then, the substrate processing apparatus 10 is monitored (S18), and an abnormal sign judgment is performed. The calculation of the abnormality degree and the monitoring of the abnormality degree value can be performed in the same manner as in the first and second embodiments.

According to this embodiment, after the replacement or maintenance of the components for the detection object of abnormal signs, a new normal model will be created, so appropriate abnormal signs detection (detection of abnormal signs occurring) can be performed. In addition, the exchange or maintenance of the components of the detection target for abnormal signs is automatically or semi-automatically detected. Therefore, the necessary abnormal values of the monitoring target can be changed appropriately.

(Fourth Embodiment) Next, the fourth embodiment of the process of detecting abnormal signs of the components of the substrate processing apparatus 10 using the above-mentioned control system will be specifically described. In addition, the structure of the omen detection controller 82 and the like and the abnormal omen judgment using abnormality are the same as those of the first to third embodiments.

In this embodiment, when exchanging or maintaining the components subject to the detection of anomaly signs, before creating a new normal model after the exchange or maintenance, it is necessary to create the normal model newly, or continue to use the normal model before the exchange or maintenance. Model judgment. Regarding the automatic or semi-automatic detection of the replacement or maintenance of components for the detection target of anomaly signs, it is performed in the same manner as in the third embodiment.

Specifically, when it is determined that there is an exchange or maintenance of the component for the detection target of anomaly signs, the omen detection controller 82 obtains sensor data with a smaller amount of data than the data required to create a normal state model. Then, based on the acquired sensor data, it is judged whether the normal model before exchange or maintenance can be used continuously.

When it is judged that the normal model before the exchange or maintenance can continue to be used, the sensor data required to make the normal model is not obtained, and the normal model before the exchange or maintenance is used. Therefore, there is no need to calculate the abnormality, monitor the same abnormality value as before the exchange or maintenance, and perform the omen detection.

When it is judged that the normal model before the exchange or maintenance cannot be used anymore, the sensor data is acquired to obtain the sensor data required to form the normal model, and the normal model is recreated. Then, according to the new normal state model, the abnormality is calculated, the new abnormality value is monitored, and the omen detection is performed.

Here, as a specific example, taking the exchange vacuum pump 74 (refer to FIG. 2) as an example, a method for detecting an abnormal sign of the substrate processing apparatus 10 will be specifically described.

[Specific example] The omen detection controller 82 is shown in FIG. 8 and obtains the accumulated operation time sent from the substrate processing apparatus controller 58 (S30), and judges whether it is shorter than the previously memorized accumulated operation time (S32), and the judgment is affirmed If it is, it is judged that there is an exchange of the vacuum pump 74, and sensor data (sensor data for judgment) required for judging whether the normal model before the exchange can be used is obtained (S33). The data volume of the sensor data for the judgment is less than the data volume of the sensor data (e.g. 30Run) required for the process recipe required to make the normal model. The sensor data (e.g. 10Run points). Then, it is statistically judged whether the distribution of the obtained judgment sensor data is equal to the data distribution of the normal model before the exchange, and it is judged whether the normal model before the exchange can be used (S34).

As an example, the statistical judgment system can be performed as described below. (1) For the data group before the exchange and the data group after the exchange, use the Shapiro-Wilk Test to determine the normality, (2) use the F test to determine the data group before the exchange Whether it is equal to the distribution of the exchanged data group, (3) According to the results of (1) and (2) above, use any of the Stuton t test, Welch t test, and Mann Whitney U test to calculate the average value ( Representative value).

When the distribution of the acquired sensor data is equal to the data distribution of the normal model before the exchange, it is judged that the normal model (Y) before the exchange can be used, and the sensor data required to create the normal model is not obtained. Monitor the abnormality value caused by the normal model before the exchange (S39), and perform omen detection.

When the distribution of the acquired sensor data is not equal to the data distribution of the normal model before the exchange, it is judged that the normal model before the exchange (N) is not available, and then the sensor data is obtained (S35) to obtain In order to create the sensor data required for the normal model, the normal model is recreated (S36). According to the normal state model obtained, the abnormality is calculated (S37), and the previously memorized abnormality data is rewritten into the calculated abnormality (S38). Then, the substrate processing apparatus 10 is monitored (S39), and an abnormal sign judgment is performed. The calculation of the abnormality degree and the monitoring of the abnormality degree value can be performed in the same manner as in the first and second embodiments.

According to this embodiment, by acquiring sensor data with a smaller amount of data than the sensor data required for the normal model of the component related to the detection target of anomaly omen, it is judged whether the exchange or maintenance of the component can be used. Model of normality. Therefore, it is possible to shorten the time during which the monitoring for the detection of abnormal signs is stopped due to the creation of the normal state model.

(Effect) According to the foregoing embodiment, the substrate processing apparatus 10 is equipped with a control system for detecting abnormal signs of a component, so the component can be exchanged or maintained at a time point when the abnormal sign of the component is detected by the control system. In particular, regarding the detection of the precursors of the failure of the vacuum pump 74, sensor data such as current data, temperature data, exhaust pressure data, and vibration data of the vacuum pump 74 can be continuously monitored to improve the accuracy of the abnormal warnings.

In this way, it is possible to deal with exchanges and the like before the component fails, and the use of the component before the failure can be used to reduce the frequency of exchange. In addition, by preventing failures in substrate processing, it is possible to improve the operation rate of the device, prevent a decrease in the yield of the product (substrate 16), and reduce useless maintenance time.

Furthermore, according to the foregoing embodiment, the omen detection controller 82 for detecting abnormal omen is connected to the controller 58 for the substrate processing apparatus. Therefore, it is limited to a specific substrate processing sequence that is easy to detect abnormal signs, and data can be obtained and analyzed.

In addition, even after the replacement or maintenance of the components of the detection object of anomaly signs, an appropriate normal model can be used to detect the signs of abnormality of the components of the detection object of anomaly signs.

(Other embodiments) The embodiments of the present invention have been described in detail above, but the present invention is not limited to the above-mentioned embodiments, and various modifications can be made without departing from the gist of the present invention.

For example, in the above-mentioned embodiment, an example in which a thin film is formed on the substrate 16 has been described. However, the present invention is not limited to this aspect. For example, the thin film formed on the substrate 16 may be suitably applied to a situation in which treatments such as oxidation treatment, diffusion treatment, annealing treatment, and etching treatment are performed.

In addition, in this embodiment, an example in which the substrate processing apparatus 10 having a hot-wall type processing furnace 44 is used to form a thin film has been described. However, the present invention is not limited to this, and a cold-wall type processing furnace is used. The substrate processing equipment used for film formation can also be ideally applied. Furthermore, in the above-mentioned embodiment, the example in which a thin film is formed by the batch-type substrate processing apparatus 10 which processes a plurality of substrates 16 at a time has been described, but the present invention is not limited to this.

In addition, the present invention is not limited to a semiconductor manufacturing device that processes semiconductor substrates like the substrate processing device 10 of the above-mentioned embodiment, and can also be applied to an LCD (Liquid Crystal Display) manufacturing device that processes glass substrates.

10: Substrate processing equipment 12: Frame 14: Front maintenance door 16: substrate 18: Wafer box 20: load port 22: Rotating wafer cassette holder 24: Wafer cassette transfer device 24A: Wafer cassette elevator 24B: Wafer cassette transport mechanism 26: box opener 28: Sub-frame 30: Lid loading and unloading mechanism 32: transfer room 34: substrate transfer mechanism 34A: substrate transfer device 34B: substrate transfer device elevator 36: Crystal Boat 38: Crystal Boat Lift 40: Robotic arm 42: Lid 44: Treatment furnace 46: Rotating mechanism 46A: Rotating motor 50: Standby 52: Cleaning unit 52A: Clean air 54: Door switch 56: substrate detection sensor 58: Controller for substrate processing equipment (an example of the main control unit) 60: Gas supply unit 62: Exhaust unit 64A: Flow Controller (MFC) 64B: Flow Controller (MFC) 66A: Process gas supply pipe 66B: Cleaning gas supply pipe 68: Exhaust pipe 70: Pressure sensor 72: Pressure Adjustment Department 74: Vacuum pump 76: temperature controller 78: Pressure Controller 80: Gas supply controller 82: Omen detection controller (an example of Omen detection part) 84: reaction tube 84A: Internal reaction tube 84B: External reaction tube 86: processing room 88: heater 90: heater base 92: Furnace Mouth 94: O ring 96A: Process gas nozzle 96B: Cleaning gas nozzle 98: cylindrical space 100: O ring 102: Rotation axis 104: Insulation board 106: temperature sensor 108: Operation Control Department 110: RAM 112: ROM 114: Memory Department 116: Input section 118: Display 120: Data storage area 122: program storage area 124: Sensors 124A: 1st sensor system 124B: 2nd sensor system 126: Data Collection Unit (DCU) 128: Edge Controller (EC) μ: average σ: standard deviation

[Fig. 1] A perspective view showing a schematic structure of a substrate processing apparatus according to an embodiment. [FIG. 2] A cross-sectional view showing the schematic structure of a processing furnace of a substrate processing apparatus according to an embodiment. [FIG. 3] A block diagram showing the schematic structure of a main control unit of a substrate processing apparatus according to an embodiment. [FIG. 4] A flowchart showing a substrate processing process when the substrate processing apparatus according to an embodiment is used as a semiconductor manufacturing apparatus. [FIG. 5] A block diagram of a control system of a substrate processing apparatus related to an embodiment is disclosed. [Fig. 6] An explanatory diagram showing the singular spectrum conversion of the control system of the substrate processing apparatus according to an embodiment. [Fig. 7] A flowchart showing a part of the process of the omen detection processing related to the specific example of the third embodiment. [Fig. 8] A flowchart showing a part of the process of the omen detection processing related to the specific example of the fourth embodiment.

Claims (13)

A substrate processing device, which is characterized by having: The main control unit is to execute a process recipe including a plurality of steps, and to control the substrate by applying a predetermined process; and The anomaly warning part is to obtain the sensor data related to the component of the anomaly detection object to make a normal state model, and monitor the state of the device according to the normal state model; The aforesaid omen detection unit is to obtain the aforementioned sensor data after the exchange or maintenance of the components of the aforementioned abnormal omen detection object, and from the sensor data, obtain the designated steps in each step constituting the aforementioned process recipe Among the aforementioned sensor data, the vibration data detected by the vibration sensor, Convert the obtained vibration data into vibration spectrum, At a predetermined frequency interval, extract the converted vibration spectrum. For each frequency extracted, use the data of the specified number of times of the aforementioned process recipe under normal conditions to calculate the average value and standard deviation of the amplitude of the aforementioned vibration spectrum, and use The obtained average value and standard deviation of the amplitude of the aforementioned vibration spectrum are again made into the aforementioned normal model, According to the normal state model, the state of the aforementioned device is monitored, and an abnormal sign is detected before the aforementioned device stops abnormally. The substrate processing apparatus described in claim 1, wherein: The aforementioned omen detection unit judges whether the aforementioned exchange or pre-maintenance model can be used as the aforementioned normal model after exchange or maintenance based on the aforementioned sensor data which is less than the amount of data required for the creation of the aforementioned normal model The aforementioned normal model. The substrate processing apparatus described in claim 2, wherein: The aforesaid omen detection unit determines that the normal model after the exchange or maintenance can be used as the normal model before the exchange or maintenance, and the normal model after the exchange or maintenance is used as the normal model after the exchange or maintenance. Of the aforementioned normal model, When it is determined that the normal model after the exchange or maintenance cannot be used as the normal model before the exchange or maintenance, the sensor data is obtained, and the normal model after the exchange or maintenance is created based on the sensor data. The substrate processing apparatus described in claim 1, wherein: The aforementioned designated step is a step of reducing the pressure of the processing chamber for processing the aforementioned substrate from atmospheric pressure to a predetermined pressure. The substrate processing apparatus described in claim 1, wherein: The aforementioned omen detection unit uses the average value and standard deviation of the amplitude of the aforementioned vibration spectrum to create the aforementioned normal model, and compares the amplitude value of the aforementioned normal model with a predetermined threshold value for the aforementioned extracted frequency points, and the number is more than a predetermined number When the aforementioned amplitude value of the frequency deviates from the aforementioned threshold value, it is judged that there is an abnormal sign. The substrate processing apparatus described in claim 5, wherein: The aforementioned predetermined threshold value is calculated using the aforementioned average value and the aforementioned standard deviation, in the range of addition or subtraction of the aforementioned average value by 3 times the aforementioned standard deviation. The substrate processing apparatus described in claim 5, wherein: The aforesaid omen detection unit, when judging that there is an abnormal omen, generates an alarm and displays the sensor data of the component identified as having an abnormal omen on the screen. The substrate processing apparatus described in claim 1, wherein: When the aforementioned abnormal sign detection target member is an exhaust device that exhausts the atmosphere of the processing chamber where the substrate is processed, The aforesaid omen detection unit is formed by obtaining vibration data detected by the vibration sensor, current data of the exhaust device, temperature data of the exhaust device, and exhaust pressure data of the exhaust device. At least one of the aforementioned sensor data of the group is constructed in the manner of the aforementioned normal model. A method of manufacturing a semiconductor device is a method of manufacturing a semiconductor device having a substrate processing process that executes a process recipe including a plurality of steps and applies a predetermined process to the substrate, and is characterized by: The aforementioned substrate processing project has: The process of obtaining sensor data related to the components of the detection objects of abnormal signs after the exchange or maintenance of the components of the detection objects of abnormal signs; From the collected sensor data, the process of obtaining the vibration data detected by the vibration sensor among the sensor data constituting the designated steps in each step of the manufacturing recipe; The project that converts the obtained vibration data into vibration frequency spectrum; At a predetermined frequency interval, extract the converted frequency of the predetermined range of the aforementioned vibration spectrum, and for each extracted frequency, use the data of the specified number of times of the aforementioned process recipe under normal conditions to calculate the average value of the amplitude of the aforementioned vibration spectrum and Standard deviation engineering; Use the average value and standard deviation of the amplitude of the aforementioned vibration spectrum to create a normal model project again; and According to this normal state model, the state of the device is monitored, and an abnormal sign is detected before the device stops abnormally. A sign detection program that obtains sensor data related to the component of an abnormal sign detection object to create a normal state model, and monitors the state of the device based on the aforementioned normal state model. The sign detection program is executed by a substrate processing device. In order to use the computer to make the aforementioned substrate processing device execute the following procedures: After the exchange or maintenance of the components of the detection object of the aforementioned abnormality, the aforementioned sensor data is obtained, and from the aforementioned sensor data obtained, the aforementioned sensor data constituting the designated step in each step of the aforementioned manufacturing recipe is obtained , The procedure of vibration data detected by the vibration sensor; A program to convert the obtained vibration data into a vibration frequency spectrum; At a predetermined frequency interval, extract the converted frequency of the predetermined range of the aforementioned vibration spectrum, and for each extracted frequency, use the data of the specified number of times of the aforementioned process recipe under normal conditions to calculate the average value of the amplitude of the aforementioned vibration spectrum and Standard deviation procedure; Using the average value and standard deviation of the amplitude of the aforementioned vibration spectrum, based on the obtained sensor data, the procedure of recreating the normal model; and A program that monitors the status of the aforementioned device based on the aforementioned normal state model and detects the signs of abnormality of the aforementioned device. A method for manufacturing a semiconductor device is a method for manufacturing a semiconductor device that executes a process recipe including a plurality of steps and applies a predetermined treatment to a substrate, which is characterized by having: The process of collecting sensor data of various sensors installed in at least any one of the device and accessory equipment while executing the aforementioned manufacturing process prescription; From the collected sensor data, the process of obtaining the vibration data detected by the vibration sensor among the sensor data constituting the designated steps in each step of the manufacturing recipe; The project that converts the obtained vibration data into vibration frequency spectrum; At a predetermined frequency interval, extract the converted frequency of the predetermined range of the aforementioned vibration spectrum, and for each extracted frequency, use the data of the specified number of times of the aforementioned process recipe under normal conditions to calculate the average value of the amplitude of the aforementioned vibration spectrum and Standard deviation engineering; Use the average value and standard deviation of the amplitude of the aforementioned vibration spectrum to create a normal model, and compare the amplitude value of the aforementioned normal model with a predetermined threshold for the extracted frequency points. The aforementioned amplitude value of the frequency above the predetermined number deviates from the aforementioned When the threshold is reached, it is judged to be a project with a sign of abnormality. An omen detection program includes a main control unit that executes a process recipe that includes a plurality of steps to apply a predetermined process to a substrate, and obtains sensing from various sensors installed in at least any one of the device and the attached equipment. Detector data, a sign detection program executed by the substrate processing device of the sign detection section that monitors the state of the aforementioned device, characterized in that the sign detection section executes the following procedures: The procedure of collecting sensor data while executing the aforementioned manufacturing process prescription; From the collected sensor data, a procedure for obtaining the vibration data detected by the vibration sensor among the sensor data constituting the designated steps in each step of the process recipe; A program to convert the obtained vibration data into a vibration frequency spectrum; At a predetermined frequency interval, extract the converted frequency of the predetermined range of the aforementioned vibration spectrum, and for each extracted frequency, use the data of the specified number of times of the aforementioned process recipe under normal conditions to calculate the average value of the amplitude of the aforementioned vibration spectrum and Standard deviation procedures; and Use the average value and standard deviation of the amplitude of the aforementioned vibration spectrum to create a normal model, and compare the amplitude value of the aforementioned normal model with a predetermined threshold for the extracted frequency points. The aforementioned amplitude value of the frequency above the predetermined number deviates from the aforementioned At the threshold value, it is judged as a program with an abnormal sign. A substrate processing apparatus includes a main control unit that controls the manner in which a predetermined process is applied to a substrate by executing a process recipe including a plurality of steps, and obtains sensing from various sensors installed in at least any one of the apparatus and auxiliary equipment The device data, the substrate processing device of the omen detecting section that monitors the status of the aforementioned device, is characterized by: The aforementioned omen detection unit obtains the vibration data detected by the vibration sensor among the aforementioned sensor data of the designated steps in each step of the aforementioned process recipe, Convert the obtained vibration data into vibration spectrum, At a predetermined frequency interval, extract the converted frequency of the predetermined range of the aforementioned vibration spectrum, and for each extracted frequency, use the data of the specified number of times of the aforementioned process recipe under normal conditions to calculate the average value of the amplitude of the aforementioned vibration spectrum and Standard deviation, Use the average value and standard deviation of the amplitude of the aforementioned vibration spectrum to create a normal model, For each frequency extracted above, compare the amplitude value of the normal model with a predetermined threshold value, When the amplitude value of the frequency above the predetermined number deviates from the threshold value, it is determined that there is an abnormal sign.

Images