Abnormality detection method of gas curtain system, program stored in recording medium, and substrate processing apparatus

Abstract

The present invention provides a method for detecting whether a gas curtain system forming a gas curtain that encompasses the surface of a substrate is abnormal. The method may comprise: a data collection step of normally operating the gas curtain system so as to acquire a plurality of pieces of normal sample data, and abnormally operating the gas curtain system so as to acquire a plurality of pieces of defective sample data; and a reference time point specifying step of matching data selected from the plurality of pieces of normal sample data and the plurality of pieces of defective sample data collected in the data collection step to each other so as to derive a reference time point at which the difference in data distribution is greater than or equal to the set value.

Description

Method for detecting abnormalities in a gas curtain system, program stored in a recording medium, and substrate processing device

[0001] The present invention relates to a method for detecting an abnormality in a gas curtain, a program stored in a recording medium, and a substrate processing device.

[0002] Typically, manufacturing semiconductor devices requires repeated processes such as photolithography, etching, exposure, ashing, and ion implantation on substrates such as wafers. After etching or ashing processes, which remove film-like structures from the substrate, the substrate surface can become extremely sensitive.

[0003] After a process such as an etching process or an ashing process to remove a film on a substrate is performed, if impurities such as particles adhere to the surface of the substrate, which is in a very sensitive state, this can cause defects in the semiconductor devices being manufactured. To prevent this problem, after the etching process or ashing process is performed, the surface of the substrate is covered with nitrogen gas to prevent the attachment of impurities to the surface of the substrate. The nitrogen gas can be supplied in the form of a downflow to the space where the substrate is provided. The nitrogen gas supplied in the downflow function as a nitrogen curtain by surrounding the surface of the substrate.

[0004] Meanwhile, monitoring is required to ensure that the nitrogen curtain is formed normally. Failure to detect abnormal nitrogen curtain formation can negatively impact the quality of the semiconductor devices being manufactured. Furthermore, it can compromise the efficiency and stability of the semiconductor device manufacturing process.

[0005] However, the nitrogen curtain covering the substrate is affected by several external variables. For example, it is affected by the temperature and pressure of the space where the nitrogen gas is supplied, and the operating conditions of other equipment (e.g., the transport operation of the substrate transport robot). Therefore, it is very complex to determine in real time whether the nitrogen curtain is properly covering the substrate.

[0006] The present invention aims to provide a method for detecting abnormal operation of a gas curtain system for preventing impurities from attaching to a substrate after a process is performed on the substrate, a program stored in a recording medium, and a substrate processing device.

[0007] The problems to be solved by the present invention are not limited to the problems described above, and problems not mentioned can be clearly understood by a person having ordinary skill in the technical field to which the present invention pertains from this specification and the attached drawings.

[0008] The present invention provides a method for detecting an abnormality in a gas curtain system forming a gas curtain that surrounds the surface of a substrate. The method may include a data collection step of acquiring a plurality of normal sample data by operating the gas curtain system normally and acquiring a plurality of defective sample data by operating the gas curtain system abnormally; and a reference point specifying step of matching selected data from among the plurality of normal sample data and the plurality of defective sample data collected in the data collection step to derive a reference point at which a difference in data distribution exceeds a set value.

[0009] According to one embodiment, preprocessing can be performed on the plurality of normal sample data and the plurality of defective sample data based on the reference point in time.

[0010] In one embodiment, the preprocessing may be a process of setting a pre / post set period as a range of interest based on the reference point.

[0011] According to one embodiment, the method may further include a reference data selection step of selecting reference data using a DBA (DTW Barycenter Averaging) algorithm for the plurality of normal sample data.

[0012] According to one embodiment, the method may further include a step of selecting an abnormality determination criterion for calculating warping distances by comparing the reference data and the plurality of defective sample data using a DTW (Dynamic Time Warping) algorithm, calculating warping distances by comparing the reference data and the plurality of normal sample data using the DTW algorithm, and setting a warping distance threshold value for determining an abnormality in the gas curtain system based thereon.

[0013] In one embodiment, the normal sample data and the defective sample data may be the supply flow rate of the inert gas forming the gas curtain or the pressure of the exhaust line exhausting the inert gas.

[0014] In one embodiment, the normal sample data and the defective sample data may be the pressure of an exhaust line that exhausts the inert gas.

[0015] In one embodiment, monitoring data is collected to determine whether the gas curtain system is abnormal, wherein the monitoring data may be the supply flow rate of the inert gas or the pressure of the exhaust line that exhausts the inert gas.

[0016] According to one embodiment, the method may further include a monitoring step of comparing the monitoring data and the reference data with each other through the DTW algorithm to calculate a warping distance and determining whether the calculated warping distance exceeds the warping distance threshold value.

[0017] In one embodiment, an alarm may be generated when the calculated warping distance exceeds the warping distance threshold value.

[0018] In addition, the present invention provides a program stored in a recording medium that performs the above-described abnormality detection method.

[0019] In addition, the present invention provides a device for processing a substrate. The device includes a chamber providing a space in which a substrate is positioned; a supply line for supplying an inert gas to the space; an exhaust line for exhausting the inert gas from the space; a flow sensor installed in the supply line and measuring a supply flow rate of the inert gas; a pressure sensor installed in the exhaust line and measuring a pressure of the exhaust line; at least one component performing an operation for affecting a flow of the inert gas from the space; and a controller, wherein the controller generates a plurality of normal sample data by collecting the supply flow rate or the pressure by normally operating the supply line, the exhaust line, and the components, generates a plurality of defective sample data by collecting the supply flow rate or the pressure by normally operating the supply line, the exhaust line, and the components, and matches selected data from among the plurality of normal sample data and the plurality of defective sample data to derive a reference point in time at which a difference in a data distribution exceeds a set value.

[0020] According to one embodiment, the controller can derive a reference point in time at which a difference in data distribution exceeds a set value by matching data selected from among the collected plurality of normal sample data and the plurality of defective sample data.

[0021] In one embodiment, the controller may perform preprocessing on the plurality of normal sample data and the plurality of defective sample data based on the reference point in time.

[0022] In one embodiment, the preprocessing may be a process of setting a pre / post set period as a range of interest based on the reference point.

[0023] According to one embodiment, the controller may select reference data using a DBA (DTW Barycenter Averaging) algorithm for the plurality of normal sample data.

[0024] According to one embodiment, the controller may calculate warping distances by comparing the reference data and the plurality of defective sample data using a DTW (Dynamic Time Warping) algorithm, calculate warping distances by comparing the reference data and the plurality of normal sample data using the DTW algorithm, and set a warping distance threshold value for determining an abnormality in the gas curtain system based on the warping distances.

[0025] In one embodiment, the controller can compare the monitoring data and the reference data with each other through the DTW algorithm to calculate a warping distance, and determine whether the calculated warping distance exceeds the warping distance threshold value.

[0026] In one embodiment, the controller may generate an alarm when the calculated warping distance exceeds the warping distance threshold value.

[0027] In one embodiment, the normal sample data and the defective sample data may be the pressure measured at set time intervals.

[0028] According to one embodiment of the present invention, after a process is performed on a substrate, abnormal operation of a gas curtain system for preventing impurities from attaching to the substrate can be effectively detected.

[0029] The effects of the present invention are not limited to the effects described above, and effects not mentioned can be clearly understood by a person having ordinary skill in the art to which the present invention pertains from this specification and the attached drawings.

[0030] FIG. 1 is a drawing showing a substrate processing device according to one embodiment of the present invention.

[0031] Figure 2 is a flow chart showing an anomaly detection method according to one embodiment of the present invention.

[0032] Figure 3 is an explanatory diagram for explaining sample data collected through the data collection step of Figure 2.

[0033] Figure 4 is a graph comparing normal sample data and abnormal sample data to explain a specific step at the reference point of Figure 2.

[0034] Figure 5 is a drawing for explaining the reference data derived through the reference data selection step of Figure 2.

[0035] Figures 6 to 9 are drawings for explaining the DTW algorithm applied when performing the abnormality determination criterion setting step and the monitoring step of Figure 2.

[0036] The various features and advantages of the non-limiting embodiments of this disclosure will become more apparent upon review of the detailed description in conjunction with the accompanying drawings. The accompanying drawings are provided for illustrative purposes only and should not be construed as limiting the scope of the claims. The accompanying drawings are not to scale unless explicitly stated otherwise. Various dimensions in the drawings may be exaggerated for clarity.

[0037] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. These exemplary embodiments are provided so that this disclosure will be thorough and will fully convey the scope of the present disclosure to those skilled in the art. To provide a thorough understanding of the embodiments of the present disclosure, numerous specific details, such as examples of specific components, devices, and methods, are set forth. It will be apparent to those skilled in the art that specific details are not necessarily required, and that the exemplary embodiments can be implemented in many different forms, and neither should be construed as limiting the scope of the present disclosure. In some exemplary embodiments, well-known processes, well-known device structures, and well-known techniques are not described in detail.

[0038] The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting of the example embodiments. As used herein, the singular or non-plural forms are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises," "comprising," "including," and "having" are open-ended and thus specify the presence of stated features, elements, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, elements, steps, operations, elements, components, and / or groups thereof. The method steps, processes, and operations herein are not necessarily to be construed as necessarily being performed in the particular order discussed or described, unless such order is explicitly stated. Additionally, additional or alternative steps may be selected.

[0039] When an element or layer is referred to as being "on," "connected," "joined," "attached," "adjacent," or "covering" another element or layer, it is intended that it is directly on, connected, joined, attached, adjacent, or covering said other element or layer, or that intermediate elements or layers may be present. Conversely, when an element is referred to as being "directly on," "directly connected to," or "directly coupled to" another element or layer, it should be understood that no intermediate elements or layers are present. Like reference numerals refer to like elements throughout the specification. The term "and / or" as used herein includes all combinations and subcombinations of one or more of the listed items.

[0040] Although terms such as first, second, third, etc. may be used herein to describe various elements, regions, layers, and / or sections, it should be understood that these elements, regions, layers, and / or sections are not limited by these terms. These terms are used merely to distinguish one element, region, layer, or section from another element, region, layer, or section. Thus, a first element, a first region, a first layer, or a first section discussed below could also be referred to as a second element, a second region, a second layer, or a second section without departing from the teachings of the exemplary embodiments.

[0041] Spatially relative terms (e.g., "beneath," "beneath," "lower," "above," "top," etc.) may be used for convenience of description to describe the relationship of one element or feature to other element(s) or features as depicted in the drawings. It should be understood that spatially relative terms are intended to encompass not only the orientation depicted in the drawings, but also other orientations of the device in use or operation. For example, if the device in the drawings were turned over, elements described as "beneath" or "below" other elements or features would then be oriented "above" the other elements or features. Thus, the term "beneath" can encompass both above and below orientations. The device can be oriented differently (rotated 90 degrees, or at other orientations), and the spatially relative descriptive phrases used herein can be interpreted accordingly.

[0042] When using the terms "same" or "same" in the description of embodiments, it should be understood that there may be some inaccuracy. Therefore, when one element or value is referred to as being the same as another element or value, it should be understood that the element or value is the same as the other element or value within a manufacturing or operating tolerance (e.g., ±10%).

[0043] When the terms "approximately" or "substantially" are used herein in connection with a numerical value, it should be understood that the numerical value includes manufacturing or operating tolerances (e.g., ±10%) of the stated value. Furthermore, when the terms "typically" and "substantially" are used in connection with geometrical shapes, it should be understood that geometrical accuracy is not required, but that latitude in the shape is within the disclosed scope.

[0044] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the exemplary embodiments pertain. Furthermore, terms, including terms defined in commonly used dictionaries, should be interpreted to have a meaning consistent with their meaning within the context of the relevant art, and will not be interpreted in an idealized or overly formal sense unless explicitly defined herein.

[0045] FIG. 1 is a drawing showing a substrate processing device according to one embodiment of the present invention.

[0046] Referring to FIG. 1, a substrate processing device (1) has an equipment front end module (EFEM) (20), a processing module (30), and a controller (70). The equipment front end module (20) and the processing module (30) can be arranged along a first direction (X).

[0047] The equipment front end module (20) has a load port (10) and a transfer frame (21). The load port (10) is arranged in front of the equipment front end module (20) in the first direction (11). The load port (10) has a plurality of support members (6). Each support member (6) is arranged in a row in the second direction (Y), and a carrier (4) (e.g., a cassette, FOUP, etc.) storing a substrate (W) to be provided to a process and a substrate (W) that has completed a process is mounted on the carrier. The substrate (W) to be provided to a process and the substrate (W) that has completed a process are stored in the carrier (4). The transfer frame (21) is arranged between the load port (10) and the processing module (30). The transfer frame (21) includes a first transfer robot (25) that is arranged inside the transfer frame and transfers the substrate (W) between the load port (10) and the processing module (30). The first transport robot (25) moves along a transport rail (27) provided in the second direction (Y) to transport the substrate (W) between the carrier (4) and the processing module (30).

[0048] The processing module (30) includes a load lock chamber (40), a transfer chamber (50), and a process chamber (60). The processing module (30) can receive a substrate (W) from the equipment front end module (20) and process the substrate (W).

[0049] The load lock chamber (40) is arranged adjacent to the transfer frame (21). For example, the load lock chamber (40) may be arranged between the transfer chamber (50) and the equipment front end module (20). The load lock chamber (40) provides a waiting space for a substrate (W) to be provided for a process before being transferred to the process chamber (60), or for a substrate (W) that has completed a process before being transferred to the equipment front end module (20).

[0050] Additionally, the load lock chamber (40) may include a first load lock chamber (41) and a second load lock chamber (42). The first load lock chamber (41) may provide a space in which an unprocessed substrate (W) waits before being returned to the process chamber (60). The second load lock chamber (42) may provide a space in which a substrate (W) processed in the process chamber (60) waits before being returned to the transfer frame (21).

[0051] The transfer chamber (50) can transport the substrate (W). The transfer chamber (50) is arranged adjacent to the load lock chamber (40). The transfer chamber (50) has a polygonal body when viewed from above. Referring to FIG. 1, the transfer chamber (50) has a pentagonal body when viewed from above. On the outside of the body, a load lock chamber (40) and a plurality of process chambers (60) are arranged along the periphery of the body. A passage (not shown) through which the substrate (W) enters and exits is formed on each side wall of the body, and the passage connects the transfer chamber (50) and the load lock chamber (40) or the process chambers (60). A door (not shown) that opens and closes the passage to seal the interior is provided in each passage. A second transfer robot (53) is arranged in the interior space of the transfer chamber (50) to transfer the substrate (W) between the load lock chamber (40) and the process chambers (60). The second transfer robot (53) transfers an unprocessed substrate (W) waiting in the load lock chamber (40) to the process chamber (60), or transfers a substrate (W) on which a process has been completed to the load lock chamber (40). In addition, the substrate (W) is transferred between process chambers (60) in order to sequentially provide the substrate (W) to a plurality of process chambers (60). As shown in Fig. 1, when the transfer chamber (50) has a pentagonal body, load lock chambers (40) are respectively arranged on the side walls adjacent to the equipment front end module (20), and process chambers (60) are arranged in series on the remaining side walls. The transfer chamber (50) may be provided in various forms depending on the required process module, in addition to the above shape.

[0052] The process chamber (60) may be arranged adjacent to the transfer chamber (50). The process chamber (60) is arranged along the periphery of the transfer chamber (50). A plurality of process chambers (60) may be provided. Process processing for a substrate (W) may be performed in each process chamber (60). The process chamber (60) receives the substrate (W) from the second transfer robot (53), performs the process processing, and provides the substrate (W) on which the process processing has been completed to the second transfer robot (53). The process processing performed in each process chamber (60) may be different from each other.

[0053] The process chamber (60) can process a substrate (W) using plasma. The process chamber (60) may include a configuration including an electrostatic chuck that supports the substrate (W), a plasma source that generates plasma that is transferred to the substrate (W) supported by the electrostatic chuck, a gas supply that supplies a process gas excited by the plasma, a heater for controlling the temperature of the substrate (W), and the like. The process chamber (60) can perform a process of removing a film formed on a substrate (W), such as a wafer, using plasma. For example, the process chamber (60) can perform an etching or ashing process that removes a film on the substrate (W).

[0054] The controller (70) may include a memory, a processor, a display, an interface unit, and a bus.

[0055] Various components such as memory, processor, display, and interface unit can be connected and communicated with each other (i.e., control message transmission and data transmission) by the bus.

[0056] The memory may include volatile memory (e.g., DRAM, SRAM, or SDRAM) and / or nonvolatile memory (e.g., one time programmable ROM (OTPROM), PROM, EPROM, EEPROM, mask ROM, flash ROM, flash memory, PRAM, RRAM, MRAM, a hard drive, or a solid state drive (SSD)). The memory may include internal memory and / or external memory. The memory may store, for example, instructions or data related to at least one other component of the electronic device. Additionally, the memory may store software and / or programs. The programs may include, for example, a kernel, middleware, an application programming interface (API), and / or an application program (or "application"). At least a portion of the kernel, middleware, or API may be referred to as an operating system.

[0057] In addition, the controller (70) may be provided with a non-transitory computer-readable medium. A non-transitory computer-readable medium refers to a medium that stores data semi-permanently and can be read by a computer, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, the various applications or programs described above may be stored and provided in a non-transitory computer-readable medium, such as a CD, DVD, hard disk, Blu-ray disk, USB, memory card, or ROM. Examples of program instructions include not only machine language codes created by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. The above-described hardware device may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

[0058] The processor may include one or more of a central processing unit, an application processor, or a communication processor (CP). The processor (20) may, for example, perform calculations or data processing related to control and / or communication of at least one other component of a computing device or a non-transitory computer-readable medium.

[0059] The display may include, for example, a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a micro electro mechanical systems (MEMS) display, or an electronic paper display. The display may, for example, display various content (e.g., text, images, videos, icons, and / or symbols) to a user. The display may include a touch screen and may receive touch, gesture, proximity, or hovering inputs, for example, using an electronic pen or a part of the user's body.

[0060] The interface unit enables the computing device to communicate with the outside world via a network. Here, the network includes both wired and wireless methods. In particular, the wireless communication may include cellular communication using at least one of LTE, LTE-A (LTE Advance), CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), or GSM (Global System for Mobile Communications). Alternatively, the wireless communication may include at least one of WiFi (wireless fidelity), LiFi (light fidelity), Bluetooth, Bluetooth low energy (BLE), Zigbee, near field communication (NFC), Magnetic Secure Transmission, Radio Frequency (RF), or Body Area Network (BAN). Alternatively, the wireless communication may include GNSS. GNSS may be, for example, GPS (Global Positioning System), Glonass (Global Navigation Satellite System), Beidou Navigation Satellite System (hereinafter "Beidou"), or Galileo, the European global satellite-based navigation system.Wired communication may include at least one of, for example, USB (universal serial bus), HDMI (high definition multimedia interface), RS-232 (recommended standard232), power line communication, or POTS (plain old telephone service), a computer network (e.g., LAN or WAN), etc.

[0061] In addition, the present invention may include a gas curtain unit (GU). The gas curtain unit (GU) may be composed of a supply line (S), an exhaust line (E), a flow sensor (F), and a pressure sensor (P). The supply line (S) may supply an inert gas to a space where a substrate (W) is provided, and the exhaust line (E) may exhaust the inert gas from the space where the substrate (W) is provided. The flow sensor (F) may be installed in the supply line (S) to measure the supply flow rate of the inert gas per unit time. The pressure sensor (P) may be installed in the exhaust line (E) to measure the pressure of the exhaust line (E).

[0062] A gas curtain unit (GU) can supply an inert gas to a space where a substrate (W) is provided. For example, the gas curtain unit (GU) can supply an inert gas downflow to a space where a substrate (W) is provided. The inert gas supplied downflow can surround the surface of the substrate (W). The inert gas can be nitrogen gas.

[0063] A plurality of gas curtain units (GU) may be provided. A gas curtain unit (GU) may be applied to each of the first load lock chamber (41), the second load lock chamber (42), the transfer chamber (50), and the process chamber (60) that provide a space in which a substrate (W) is provided.

[0064] For example, a gas curtain unit (GU) applied to a first load lock chamber (41) may include a first load lock chamber supply line (41S), a first load lock chamber exhaust line (41E), a first load lock chamber flow sensor (41F), and a first load lock chamber pressure sensor (41P). A gas curtain unit (GU) applied to a second load lock chamber (42) may include a second load lock chamber supply line (42S), a second load lock chamber exhaust line (42E), a second load lock chamber flow sensor (42F), and a second load lock chamber pressure sensor (42P). A gas curtain unit (GU) applied to a transfer chamber (50) may include a transfer chamber supply line (50S), a transfer chamber exhaust line (50E), a transfer chamber flow sensor (50F), and a transfer chamber pressure sensor (50P). A gas curtain unit (GU) applied to a process chamber (60) may include a process chamber supply line (60S), a process chamber exhaust line (60E), a process chamber flow sensor (60F), and a process chamber pressure sensor (60P).

[0065] The abnormality detection method described below can be implemented by a program recorded in a memory provided to the controller (70) or a non-transitory computer-readable medium.

[0066] Figure 2 is a flow chart showing an anomaly detection method according to one embodiment of the present invention.

[0067] Referring to FIG. 2, an abnormality detection method according to an embodiment of the present invention may include a data collection step (S10), a reference point specification step (S20), a reference data selection step (S30), an abnormality determination criterion setting step (S40), and a monitoring step (S50).

[0068] The data collection step (S10) may be a step for collecting data in advance in order to perform the reference point specific step (S20), reference data selection step (S30), and abnormality determination criterion setting step (S40) described below.

[0069] Figure 3 is an explanatory diagram for explaining sample data collected through the data collection step of Figure 2.

[0070] Referring to FIGS. 2 and 3, in the data collection step (S10), normal sample data (ND) and defective sample data (FD) can be collected. A plurality of normal sample data (ND) can be collected. For example, the normal sample data (ND) can be collected as the first normal sample data (ND1), the second normal sample data (ND2), the third normal sample data (ND3), …, and the Nth normal sample data (NDN). The defective sample data (FD) can be collected as the first defective sample data (FD1), the second defective sample data (FD2), the third defective sample data (FD3), …, and the Nth defective sample data (FDN).

[0071] The inert gas supplied by the gas curtain unit (GU) can surround the substrate (W). The gas curtain unit (GU) can form a gas curtain that surrounds the substrate (W). Normal formation of the gas curtain may mean that the inert gas supplied by the gas curtain unit (GU) normally surrounds the substrate (W). Conversely, abnormal formation of the gas curtain may mean that the inert gas supplied by the gas curtain unit (GU) abnormally surrounds the substrate (W) or fails to properly surround the substrate (W).

[0072] For the gas curtain to be formed normally, the inert gas supply from the supply line (S) and the inert gas exhaust from the exhaust line (E) must be performed normally. In addition, the operation of various components other than the gas curtain unit (GU) regarding the process for the substrate (W) must also be performed normally. For example, the flow of the inert gas is affected by the temperature of the substrate (W) and the space in which the substrate (W) is provided, the position at which the electrostatic chuck chucks the substrate (W), and the return operation of the first transfer robot (25) and the second transfer robot (53).

[0073] That is, in order for the gas curtain to be formed normally, not only the gas curtain unit (GU) must operate normally, but also the operations of all components of the substrate processing device (1) that affect the gas curtain, including the gas curtain unit (GU), must be considered. Hereinafter, the components of the substrate processing device (1) that affect the formation of the gas curtain, including the gas curtain unit (GU), are defined as a gas curtain system. Normal operation of the gas curtain system means that the gas curtain is formed normally and wraps the substrate (W) normally. Here, wrapping may mean that the entire surface of the substrate (W) is wrapped with an inert gas, or alternatively, it may mean that at least one of the upper surface, lower surface, and side surfaces of the substrate (W) is covered with the inert gas. In addition, abnormal operation of the gas curtain system means that the gas curtain is formed abnormally and wraps the substrate (W) abnormally.

[0074] Normal sample data (ND) may be data obtained by the normal operation of the gas curtain system. For example, it may be data obtained by normally controlling the inert gas supply flow rate in the supply line (S) and the inert gas exhaust pressure in the exhaust line (E). In addition, it may be data obtained by normally controlling the operation of various components affecting the gas curtain, such as a plasma source, a heater for controlling the temperature of the substrate (W), and the first transfer robot (25) and the second transfer robot (53).

[0075] Conversely, defective sample data (FD) may be data obtained by intentionally operating the gas curtain system abnormally. For example, this may be data obtained by abnormally controlling the inert gas supply flow rate in the supply line (S) or the inert gas exhaust pressure in the exhaust line (E). Furthermore, this may be data obtained by abnormally controlling various components affecting the gas curtain, such as the plasma source, the heater controlling the temperature of the substrate (W), the first transfer robot (25), and the second transfer robot (53).

[0076] The normal sample data (ND) and the defective sample data (FD) may be time-series data obtained by measuring the supply flow rate of the inert gas per unit time measured by the above-described flow sensor (F), or the pressure of the exhaust line (E) measured by the above-described pressure sensor (P) at set time intervals. Among them, data suitable for use as the sample data (ND, FD) may be the pressure of the exhaust line (E) measured by the pressure sensor (P). Since the pressure of the exhaust line (E) is affected not only by the supply flow rate of the inert gas in the supply line (S), but also by the temperature of the substrate (W), the atmosphere of the space in which the substrate (W) is provided, the operation of the plasma source, and the operations of the first transfer robot (25) and the second transfer robot (53), it may be suitable for detecting abnormal operation of the gas curtain system.

[0077] Fig. 4 is a graph comparing normal sample data and abnormal sample data to explain a specific step at a reference point in Fig. 2. Fig. 4 shows changes in the measured pressure value of the pressure sensor (P) over time.

[0078] Referring to FIGS. 2 and 4, in a reference time point specific step (S20), data selected from among normal sample data (ND) and data selected from among defective sample data (FD) can be matched with each other. Specifically, the data acquisition times of the normal sample data (ND) and the defective sample data (FD) can be matched with each other and compared with each other. As illustrated in FIG. 4, by matching the data acquisition times of the normal sample data (ND, Normal) and the defective sample data (FD, Faulty) with each other and comparing them with each other, it is possible to identify the time point at which the difference between the data distribution of the normal sample data (ND) and the data distribution of the defective sample data (FD) exceeds a set value. The corresponding time point can be specified as a reference time point (Key Time Point in FIG. 4).

[0079] Once the reference point is specified, preprocessing can be performed on normal sample data (ND) and defective sample data (FD) based on the reference point. For the preprocessed data, a set period before and after the reference point can be set as the range of interest. The reference data selection step (S30), the abnormality determination criterion setting step (S40), and the monitoring step (S50) described below can be performed only on the data distribution within the period designated as the range of interest.

[0080] Figure 5 is a drawing for explaining the reference data derived through the reference data selection step of Figure 2.

[0081] Referring to FIGS. 2 and 5, the reference data selection step (S30) may be a step for selecting reference data representing normal sample data (ND) collected in the data collection step (S10) and preprocessed through the reference time point specific step (S20). The reference data may be data representing normal sample data (ND), and may be data to be used as a standard for normal data in the abnormality determination criterion setting step (S40) and monitoring step (S50) described below.

[0082] Normal sample data (ND) may be temporally shifted left or right relative to a reference point. To align the temporal shifts of the normal sample data (ND) and select a single reference data representing the normal sample data (ND), the present invention uses the DTW Barycenter Averaging (DBA) algorithm. The DBA algorithm is performed in the following order.

[0083] 1. Selecting an initial reference time series: Typically, one time series is randomly selected from the data set, or the average of the entire data is used.

[0084] 2. DTW alignment between all time series and the initial reference time series: Align each time series to the initial reference time series. At this time, a set of values ​​for each time point is obtained using the DTW path.

[0085] 3. Compute a new reference time series: At each time point, calculate the average of the values ​​obtained through DTW sorting to obtain a new reference time series.

[0086] 4. Check convergence conditions and repeat: If the new reference time series is not significantly different from the previous reference time series, terminate the algorithm. Otherwise, repeat from step 2 using the new reference time series.

[0087] Through the DBA algorithm above, reference data, which is representative data of normal sample data (ND), can be selected.

[0088] Below, the abnormality determination criterion setting step (S40) and the monitoring step (S50) are described.

[0089] In the abnormality determination criterion setting step (S40), a threshold value can be set to determine abnormal operation of the gas curtain system by comparing the reference data and defective sample data (FD).

[0090] In the abnormality determination criteria setting step (S40), the Dynamic Time Warping (DTW) algorithm can be used to compare the reference data with multiple defective sample data (FD) to calculate the warping distance. Furthermore, the Dynamic Time Warping (DTW) algorithm can be used to compare the reference data with multiple normal sample data (ND) to calculate the warping distance. Based on this, a warping distance threshold value can be set to determine abnormal operation of the gas curtain system.

[0091] In the monitoring step (S50), abnormal operation of the gas curtain system can be determined in real time by comparing the reference data with the monitoring data collected in real time. The monitoring data may be time-series data collected by the flow sensor (F) or pressure sensor (P) of the substrate processing device (1) described above.

[0092] In the monitoring step (S50), a DTW (Dynamic Time Warping) algorithm can be used to compare reference data with monitoring data to calculate a warping distance. If the calculated warping distance exceeds the above-described warping distance threshold, it can be determined that an abnormality has occurred (i.e., abnormal operation) in the gas curtain system. This allows for real-time determination of abnormal operation of the gas curtain system. If abnormal operation of the gas curtain system is detected, the controller (70) can generate an audible or visual alarm through a display to notify the operator of the abnormal operation of the gas curtain system.

[0093] Below, the DTW algorithm applied to the abnormality determination criterion setting step (S40) and the monitoring step (S50) is described.

[0094] In Dynamic Time Warping, the dictionary definition of warping is to twist or bend, and Dynamic Time Warping, as its name suggests, is an algorithm that 'measures the similarity (distance) between two time series with different movements depending on speed or length', and matches them in the direction where the distance is minimized to find the warping path that minimizes the accumulated distance.

[0095] The working principle of the DTW algorithm is as follows.

[0096] Assume that there are two time series Q=(q1, q2, …, qn) and C=(c1,C2, …, Cn) of length m and n, respectively. First, list the two time series to create an mxn matrix. The (i, j)-th element of this matrix represents the Euclidean distance d(qi, cj) = (qi-cj)^2 between two points qi and cj, which is used to search for the optimal warping path. The warping path W is a set of warping distances that represent a mapping between Q and C, and must be continuous.

[0097] W = w1, w2, … wk, max(m,n) ≤ K < m+n-1

[0098] The kth element in W is defined as wk=(i,j)k, which is called the warping distance. At this time, W satisfies the following three conditions.

[0099] 1. Boundary conditions: w1=(1,1) and wk(m,n) must be connected. That is, the start and end points must be w1(1, 1) and wk(m,n).

[0100] 2. Continuity: In wk(a, b) and wk(a', b'), aa' ≤1, bb' ≤1 must be satisfied. That is, the warping path is restricted to adjacent cells containing diagonal elements.

[0101] 3. Monotonicity: aa' in wk(a,b) and wk-1=(a', b') 0, bb' It should be 0, i.e. the warping path does not move in the negative direction.

[0102] The goal is to find a path that satisfies the three conditions above and minimizes the sum of the warping distances wk. This is called the warping path cost.

[0103]

[0104] Here, K is used to compensate for warping paths with different lengths. Starting from i=j=0, the cumulative warping distance D(i,j) of the k-th warping distance wk can be defined by the equation below. The meaning of the equation is [the distance between the i-th element and the j-th element] + [the minimum of the cumulative distances to the adjacent cell of the (i,j)-th element], which ultimately means proceeding in the shortest distance direction.

[0105] The cumulative warping distance D(i,j) starts from i=j=0, and the value representing the final similarity is the same as the value of DTW(Q, C) above.

[0106]

[0107] Below, specific examples are described with reference to FIGS. 6 and 7.

[0108] 1. Assume there are two time series data, Data 1 and Data 2, as shown in [Table 1] below.

[0109] Time 12345678910 Data 114510932684 Data 217341105474

[0110] 2. List the two time series to create a 10 x 10 matrix as shown in Figure 7. This can be called a Cost Matrix.

[0111] 3. The cumulative warping distance of the Cost Matrix is ​​calculated using the following formula.

[0112]

[0113] Let's look at a concrete example:

[0114] The (4, 4)th element is 11 = |10 - 4| + min(5, 12, 5) = 6 + 5

[0115] The (2, 1)th element is 3 = |4 - 1| + min(0) = 3

[0116] The (1, 3)th element is 8 = |1 - 3| + min(6) = 8

[0117] 4. Figure 7 shows the calculated Cost Matrix.

[0118] 5. The optimal warping path is the one with the minimum cumulative warping distance. The search begins from the upper rightmost point to the lower leftmost point. The search target is the neighborhood of the starting point, which is the neighborhood of 15, (15, 18, 18).

[0119] 6. Select the minimum value, 15, and explore the area around the selected 15.

[0120] 7. The area around 15 is (15, 19, 14), and the minimum value, 14, is selected. This process continues until the bottom left.

[0121] 8. The final path is the shaded path in Figure 7.

[0122] 9. The final selected warping path cost (= total warping distance) is as follows.

[0123] DTW(Q, C) = [15 + 15 + 14 + 13 + 11 + 9 + 8 + 8 + 4 + 4 + 3 + 0] / 12

[0124] Figures 8 and 9 illustrate examples of only the time difference between two time series data with the same pattern as described in [Table 2] below.

[0125] Time 12345678910 Data A 11410932684 Data B 14109326844

[0126] DTW(P, Q) = [0 + 0 + 0 + 0 + 0 + 0 + 0 + 0 + 0 + 0 + 0] / 11 = 0, which means that the two time series have the same pattern.

[0127] It should be understood that exemplary embodiments have been disclosed herein, and that other variations are possible. Individual elements or features of a particular embodiment are generally not limited to that particular embodiment, but, where applicable, may be interchangeable and used in a selected embodiment, even if not specifically illustrated or described. Such variations should not be considered a departure from the spirit and scope of the present disclosure, and all such modifications apparent to those skilled in the art are intended to be included within the scope of the following claims.

[0128]

[0129]

[0130] [Explanation of symbols]

[0131] Data collection phase: S10

[0132] Specific stage at baseline: S20

[0133] Baseline data selection step: S30

[0134] Step 4: Setting the criteria for abnormality determination: S40

[0135] Monitoring phase: S50

Claims

1. A method for detecting an abnormality in a gas curtain system forming a gas curtain covering the surface of a substrate, A data collection step of acquiring a plurality of normal sample data by operating the gas curtain system normally and acquiring a plurality of defective sample data by operating the gas curtain system abnormally; and Including a reference point specific step of matching selected data from among the plurality of normal sample data and the plurality of defective sample data collected in the data collection step to derive a reference point at which a difference in data distribution occurs greater than a set value. method.

2. In paragraph 1, Preprocessing is performed on the plurality of normal sample data and the plurality of defective sample data based on the above reference point in time. method.

3. In paragraph 2, The above preprocessing is a process that sets the pre / post setting period as the range of interest based on the above reference point. method.

4. In paragraph 2, Further comprising a reference data selection step of selecting reference data using the DBA (DTW Barycenter Averaging) algorithm for the above plurality of normal sample data. method.

5. In paragraph 4, A step of selecting an abnormality determination criterion for calculating warping distances by comparing the reference data and the plurality of defective sample data with a DTW (Dynamic Time Warping) algorithm, calculating warping distances by comparing the reference data and the plurality of normal sample data with the DTW algorithm, and setting a warping distance threshold value for determining an abnormality in the gas curtain system based thereon, further comprising: method.

6. In paragraph 5, The above normal sample data and the above defective sample data are the supply flow rate of the inert gas forming the gas curtain or the pressure of the exhaust line exhausting the inert gas. method.

7. In paragraph 6, The above normal sample data and the above defective sample data are the pressure of the exhaust line that exhausts the inert gas. method.

8. In paragraph 6, Collect monitoring data to determine whether the gas curtain system is abnormal, wherein the monitoring data is the supply flow rate of the inert gas or the pressure of the exhaust line that exhausts the inert gas. method.

9. In paragraph 8, Further comprising a monitoring step of comparing the monitoring data and the reference data with each other through the DTW algorithm to calculate a warping distance and determining whether the calculated warping distance exceeds the warping distance threshold value. method.

10. In paragraph 9, If the calculated warping distance exceeds the warping distance threshold, an alarm is generated. method.

11. A program stored in a recording medium that performs the abnormality detection method of any one of clauses 1 to 10.

12. In a device for processing a substrate, A chamber that provides a space in which the substrate is located; A supply line for supplying inert gas to the above space; An exhaust line for exhausting the inert gas from the space; A flow sensor installed in the above supply line and measuring the supply flow rate of the inert gas; A pressure sensor installed in the exhaust line and measuring the pressure of the exhaust line; At least one component that performs an action affecting the flow of the inert gas in the space; and including a controller, The above controller, The above supply line, the above exhaust line and the above components are operated normally to collect the supply flow rate or the above pressure and generate a plurality of normal sample data, The supply line, the exhaust line and the components are operated normally to collect the supply flow rate or the pressure and generate a plurality of defective sample data, Matching selected data from among the plurality of normal sample data and the plurality of defective sample data with each other to derive a reference point at which the difference in data distribution exceeds a set value. Substrate processing device.

13. In paragraph 12, The above controller, Matching the collected plurality of normal sample data and the selected plurality of defective sample data with each other to derive a reference point at which the difference in data distribution exceeds a set value. Substrate processing device.

14. In paragraph 13, The above controller, Preprocessing is performed on the plurality of normal sample data and the plurality of defective sample data based on the above reference point in time. Substrate processing device.

15. In paragraph 14, The above preprocessing is a process that sets the pre / post setting period as the range of interest based on the above reference point. Substrate processing device.

16. In paragraph 13, The above controller, Selecting reference data using the DBA (DTW Barycenter Averaging) algorithm for the above multiple normal sample data, Substrate processing device.

17. In paragraph 16, The above controller, Comparing the above reference data and the plurality of defective sample data with the DTW (Dynamic Time Warping) algorithm to calculate warping distances, comparing the above reference data and the plurality of normal sample data with the DTW algorithm to calculate warping distances, and setting a warping distance threshold value for determining an abnormality in the gas curtain system based on the warping distances. Substrate processing device.

18. In paragraph 17, The above controller, Comparing the above monitoring data and the above reference data with each other through the DTW algorithm to calculate the warping distance, and determining whether the calculated warping distance exceeds the warping distance threshold value. Substrate processing device.

19. In paragraph 18, The above controller, If the calculated warping distance exceeds the warping distance threshold, an alarm is generated. Substrate processing device.

20. In any one of paragraphs 12 to 19, The above normal sample data and the above defective sample data are the pressures measured at set time intervals, Substrate processing device.

Images