Substrate processing device, abnormality detection method, and abnormality detection program

Abstract

To provide a substrate processing device, an abnormality detection method, and an abnormality detection program capable of detecting an abnormality at an early stage.SOLUTION: In a substrate processing device, a substrate is processed using a processing liquid. A first operating component and a second operating component are used to process the substrate. A first operating value of the first operating component and a second operating value of the second operating component are acquired by an operating value acquiring unit. An abnormality determination unit 230 determines whether an abnormality has occurred on the basis of the correlation between the first operating value and the second operating value acquired by the operating value acquisition unit 210.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a substrate processing apparatus for processing a substrate, an abnormality detection method, and an abnormality detection program. [Background technology]

[0002] Substrate processing apparatuses are used to perform various processes such as film formation, development, and cleaning on substrates such as semiconductor substrates, glass substrates for liquid crystal displays, glass substrates for photomasks, and glass substrates for optical disks. When substrate processing apparatuses are operated for a long period of time, abnormalities such as damage or deterioration of operating parts of the substrate processing apparatus may occur.

[0003] Patent Document 1 describes an anomaly detection device that can predict anomalies in semiconductor manufacturing equipment. In this anomaly detection device, status information indicating the status of each part of the semiconductor manufacturing equipment is collected at a predetermined cycle. The status information includes, for example, the temperature, pressure, gas flow rate, or power of each part of the semiconductor manufacturing equipment. The collected status information is stored as a log in predetermined units.

[0004] Based on the stored logs, a monitoring band is generated to monitor the status of each part of the semiconductor manufacturing equipment. The monitoring band is a waveform used to determine whether the collected status information is normal, and is generated, for example, by interpolating based on upper and lower limit values ​​set at predetermined intervals. Based on the status information and the monitoring band, it is determined whether the status of each part of the semiconductor manufacturing equipment is abnormal. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2018-77764 Summary of the Invention [Problem to be solved by the invention]

[0006] It is desirable to detect an abnormality in a substrate processing apparatus before it breaks down, as in the abnormality detection device described in Patent Document 1.

[0007] An object of the present invention is to provide a substrate processing apparatus, an abnormality detection method, and an abnormality detection program that are capable of detecting an abnormality at an early stage. [Means for solving the problem]

[0008] (1) A substrate processing apparatus according to a first aspect of the present invention is a substrate processing apparatus including a first operating component and a second operating component used in processing a substrate using a processing liquid, and is equipped with an operating value acquisition unit that acquires a first operating value of the first operating component and a second operating value of the second operating component, and an abnormality determination unit that determines whether an abnormality has occurred based on the correlation between the first operating value and the second operating value acquired by the operating value acquisition unit.

[0009] In this substrate processing apparatus, substrates are processed using a processing liquid. Furthermore, whether or not an abnormality has occurred is determined based on a correlation between a first operational value of a first operational component and a second operational value of a second operational component. Therefore, an abnormality in the substrate processing apparatus can be detected early before a breakdown occurs in the substrate processing apparatus.

[0010] (2) The abnormality determination unit may determine whether an abnormality has occurred based on the proportion of data points determined by a pair of the first operating value and the second operating value acquired by the operating value acquisition unit that exceed an allowable range determined based on the correlation between the first operating value and the second operating value. In this case, an abnormality in the substrate processing apparatus can be detected by a simple process.

[0011] (3) The allowable range may be determined so as to include a predetermined percentage of data points among data points determined by a pair of the first operating value and the second operating value acquired in advance by the operating value acquisition unit before processing the substrate. In this case, the allowable range used for determining an abnormality can be easily determined.

[0012] (4) The abnormality determination unit may determine whether an abnormality has occurred when a predetermined number of substrates have been processed or when a predetermined time has elapsed. This configuration makes it easier to detect abnormalities in the substrate processing apparatus at an early stage.

[0013] (5) The first operating component may include a first adjusting valve that adjusts the flow rate of the processing liquid supplied to the substrate based on a first pulse value, and the second operating component may include a second adjusting valve that adjusts the flow rate of the processing liquid supplied to the substrate based on a second pulse value, wherein the first operating value is the first pulse value applied to the first adjusting valve, and the second operating value is the second pulse value applied to the second adjusting valve.

[0014] In this case, an abnormality in the substrate processing apparatus can be detected early based on the correlation between the first pulse value applied to the first adjusting valve and the second pulse value applied to the second adjusting valve.

[0015] (6) The first operating component may include an adjusting valve that adjusts the flow rate of the processing liquid supplied to the substrate based on a pulse value, and the second operating component may include a pressure gauge that detects the pressure of the processing liquid guided to the adjusting valve, wherein the first operating value is the pulse value applied to the adjusting valve, and the second operating value may be the pressure detected by the pressure gauge.

[0016] In this case, an abnormality in the substrate processing apparatus can be detected early based on the correlation between the pulse value given to the adjusting valve and the pressure detected by the pressure gauge.

[0017] (7) The first operating component includes a first flow meter and a second flow meter that detect the flow rates of the first treatment liquid and the second treatment liquid, respectively; the second operating component includes a concentration meter that detects the concentration of a mixed treatment liquid produced by mixing the first treatment liquid and the second treatment liquid; the first operating value is a theoretical value of the concentration of the mixed treatment liquid calculated by the ratio of the flow rates of the first treatment liquid and the second treatment liquid detected by the first flow meter and the second flow meter, respectively; and the second operating value may be an actual measured value of the concentration of the mixed treatment liquid detected by the concentration meter.

[0018] In this case, an abnormality in the substrate processing apparatus can be detected early based on the correlation between the theoretical value of the concentration of the mixed processing liquid calculated from the ratio between the flow rate of the first processing liquid and the flow rate of the second processing liquid and the actual measured value of the concentration of the mixed processing liquid detected by the concentration meter.

[0019] (8) The substrate processing apparatus further includes a storage section into which a mixed processing liquid, which is a mixture of a first processing liquid and a second processing liquid, flows, the first operating component includes a first flow meter and a second flow meter that detect the flow rates of the first processing liquid and the second processing liquid, respectively, the second operating component includes a concentration meter that detects the concentration of the mixed processing liquid flowing out of the storage section, the mixed processing liquid flowing into the storage section reaches the concentration meter at a first time, the first operating value is a theoretical value of the concentration of the mixed processing liquid calculated by an integrated value of the flow rate of the first processing liquid and an integrated value of the flow rate of the second processing liquid detected by the first flow meter and the second flow meter, respectively, between a first time point and a second time point that is a second time point after the first time point, and the second operating value may be a statistical value of the concentration of the mixed processing liquid detected by the concentration meter between a third time point that is a first time point after the first time point and a fourth time point that is a first time point after the second time point.

[0020] In this case, whether or not an abnormality has occurred in the substrate processing apparatus is determined based on the correlation between the theoretical concentration value of the mixed processing liquid calculated from the integrated value of the flow rates of the first processing liquid and the second processing liquid and the statistical value of the concentration of the mixed processing liquid. Here, since there is a strong correlation between the theoretical concentration value of the mixed processing liquid and the statistical value of the concentration of the mixed processing liquid, it is possible to more reliably detect the abnormality in the substrate processing apparatus.

[0021] (9) The first operating component includes a first flow meter and a second flow meter that detect the flow rates of the first processing liquid and the second processing liquid, respectively. The second operating component includes a concentration meter that detects the concentration of a mixed processing liquid generated by mixing the first processing liquid and the second processing liquid. A concentration prediction is performed by machine learning on a relationship between the flow rate of the first processing liquid, the flow rate of the second processing liquid, and the concentration of the mixed processing liquid between a first time point and a second time point that is a first time elapsed from the first time point, and the concentration of the mixed processing liquid at a third time point that is a second time elapsed from the second time point. A measurement model is prepared, and the first operating value is a predicted value of the concentration of the mixed treatment liquid at a sixth time point, a second time point after the fifth time point, obtained by applying to the concentration prediction model the flow rate of the first treatment liquid detected by the first flow meter, the flow rate of the second treatment liquid detected by the second flow meter, and the concentration of the mixed treatment liquid detected by the concentration meter between the fourth time point and a fifth time point, a first time point after the fourth time point, and the second operating value may be an actual measured value of the concentration of the mixed treatment liquid detected by the concentration meter at the sixth time point.

[0022] In this case, based on the correlation between the predicted value of the concentration of the mixed processing liquid obtained based on the concentration prediction model and the actual measured value of the concentration of the mixed processing liquid detected by the concentration meter, it is possible to detect a single abnormality that occurs in the substrate processing apparatus over a relatively short period of time.

[0023] (10) A substrate processing apparatus further includes a storage unit that stores a mixed processing liquid obtained by mixing a first processing liquid and a second processing liquid, a substrate processing unit that processes a substrate using a mixing process, a first flow path unit that mixes the first processing liquid and the second processing liquid to generate a mixed processing liquid and guides the mixed processing liquid to the storage unit, a second flow path unit that guides the mixed processing liquid stored in the storage unit to the substrate processing unit, and a third flow path unit that guides unused mixed processing liquid in the substrate processing unit to the storage unit, wherein the first operating part includes a first flow meter and a second flow meter that detect the flow rates of the first processing liquid and the second processing liquid, respectively, and the second operating part includes a concentration meter that detects the concentration of the mixed processing liquid flowing out of the storage unit, and guides the unused mixed processing liquid to the storage unit through the first flow path unit. The mixed treatment liquid that flows in reaches the concentration meter in a first time, and the first operating value is a theoretical value of the concentration of the mixed treatment liquid stored in the storage unit at each time point, calculated from the volume of the mixed treatment liquid flowing into the storage unit through the first flow path unit, the volume of the mixed treatment liquid flowing from the storage unit through the second flow path unit, and the volume of the mixed treatment liquid flowing into the storage unit through the third flow path unit per unit time, and the flow rates of the first treatment liquid and the second treatment liquid detected by the first flow meter and the second flow meter, respectively, and the second operating value may be an actual measured value of the concentration of the mixed treatment liquid detected by the concentration meter at a time point a first time has elapsed since the mixed treatment liquid flowed into the storage unit through the first flow path unit.

[0024] When the concentration of the mixed processing liquid supplied to the substrate processing unit fluctuates, the concentration of the mixed processing liquid stored in the storage unit fluctuates due to the unused mixed processing liquid in the substrate processing unit being returned to the storage unit. Even in this case, with the above configuration, whether or not an abnormality has occurred in the substrate processing unit is determined based on the correlation between the theoretical value of the concentration of the mixed processing liquid stored in the storage unit, calculated from the volume of the mixed processing liquid flowing into or out of the storage unit, the flow rates of the first processing liquid and the second processing liquid, and the actual measured value of the concentration of the mixed processing liquid detected by the concentration meter. In this case, the correlation between the theoretical value of the concentration of the mixed processing liquid and the statistical value of the concentration of the mixed processing liquid can be strengthened. This makes it possible to more reliably detect abnormalities in the substrate processing unit.

[0025] (11) The first operating component may include a first chuck pin that transitions between a first closed state in which the substrate is held and a first open state in which the substrate is not held, the second operating component may include a second chuck pin that transitions between a second closed state in which the substrate is held and a second open state in which the substrate is not held, the first operating value may be a transition time of the first chuck pin between the first closed state and the first open state, and the second operating value may be a transition time of the second chuck pin between the second closed state and the second open state.

[0026] In this case, an abnormality in the substrate processing apparatus can be detected early based on the correlation between the transition time of the first chuck pin and the transition time of the second chuck pin.

[0027] (12) The first operating component includes a chuck pin that transitions between a first closed state in which the substrate is held and a first open state in which the substrate is not held, and the second operating component includes a chuck driver that transitions between a second closed state in which the chuck pin transitions to the first closed state and a second open state in which the chuck pin transitions to the first open state, and the first operating value may be a transition time of the chuck pin between the first closed state and the first open state, and the second operating value may be a transition time of the chuck driver between the second closed state and the second open state.

[0028] In this case, an abnormality in the substrate processing apparatus can be detected early based on the correlation between the transition time of the chuck pin and the transition time of the chuck driving unit.

[0029] (13) The first operating component may include a first processing tool that transitions between a first waiting position where the substrate is not processed and a first processing position where the substrate is processed, and the second operating component may include a second processing tool that transitions between a second waiting position where the substrate is not processed and a second processing position where the substrate is processed, and the first operating value may be a transition time for the first processing tool between the first waiting position and the first processing position, and the second operating value may be a transition time for the second processing tool between the second waiting position and the second processing position.

[0030] In this case, an abnormality in the substrate processing apparatus can be detected early based on the correlation between the transition time of the first processing tool and the transition time of the second processing tool.

[0031] (14) The substrate processing apparatus may further include an operating value selection unit that selects a second operating value that satisfies a predetermined criterion from among the second operating values ​​acquired by the operating value acquisition unit, and selects a first operating value that corresponds to the selected second operating value from among the first operating values ​​acquired by the operating value acquisition unit, and the abnormality determination unit may determine whether an abnormality has occurred based on a time-series change in the first operating value selected by the operating value selection unit.

[0032] In this case, whether or not an abnormality has occurred is determined based on a time series change in the acquired first operational values ​​that satisfy a predetermined criterion, thereby enabling accurate detection of an abnormality in the substrate processing apparatus.

[0033] (15) The first operating component may include a torque sensor that detects the torque of the spin drive unit, and the second operating component may include a temperature sensor that detects the temperature of the spin drive unit, and the first operating value may be the torque of the spin drive unit detected by the torque sensor, and the second operating value may be the temperature of the spin drive unit detected by the temperature sensor.

[0034] In this case, based on the temperature of the spin drive unit detected by the temperature sensor, it is possible to easily select a torque of the spin drive unit detected by the torque sensor that satisfies a predetermined standard, thereby making it possible to easily detect an abnormality in the substrate processing apparatus.

[0035] (16) The first operating value may be the torque of the spin drive unit detected by a torque sensor when the spin drive unit is rotating at a predetermined constant rotation speed, and the second operating value may be the temperature of the spin drive unit detected by a temperature sensor when the spin drive unit is rotating at a constant rotation speed. In this case, an abnormality in the substrate processing apparatus can be detected more accurately.

[0036] (17) An abnormality detection method according to a second aspect of the present invention is an abnormality detection method for detecting an abnormality in a substrate processing apparatus including a first operating component and a second operating component used in processing a substrate using a processing liquid, and includes acquiring a first operating value of the first operating component and a second operating value of the second operating component that are correlated with each other, and determining whether an abnormality has occurred based on the acquired first operating value and second operating value.

[0037] According to this anomaly detection method, whether or not an anomaly has occurred during substrate processing using a processing liquid is determined based on the correlation between the first operational value of the first operational component and the second operational value of the second operational component, thereby enabling early detection of an anomaly in the substrate processing apparatus before a breakdown occurs in the substrate processing apparatus.

[0038] (18) The third invention provides an abnormality detection program that is executed by a processing device to detect an abnormality in a substrate processing device that includes a first operating component and a second operating component used in processing a substrate using a processing liquid, and that causes the processing device to execute a process of acquiring a first operating value of the first operating component and a second operating value of the second operating component that are correlated with each other, and a process of determining whether an abnormality has occurred based on the acquired first operating value and second operating value.

[0039] According to this abnormality detection program, whether or not an abnormality has occurred during substrate processing using a processing liquid is determined based on the correlation between the first operational value of the first operational component and the second operational value of the second operational component, thereby enabling early detection of an abnormality in the substrate processing apparatus before a breakdown occurs in the substrate processing apparatus. [Effects of the Invention]

[0040] According to the present invention, an abnormality in a substrate processing apparatus can be detected at an early stage. [Brief explanation of the drawings]

[0041] [Figure 1] 1 is a block diagram showing a schematic configuration of a substrate processing apparatus according to an embodiment of the present invention; [Figure 2] FIG. 2 is a diagram illustrating a configuration of a processing liquid supply unit according to the first embodiment. [Figure 3] FIG. 2 is a functional block diagram showing the configuration of a control unit. [Figure 4] FIG. 10 is a diagram showing a correlation graph. [Figure 5] 4 is a flowchart showing an abnormality detection process performed by the control unit of FIG. 3. [Figure 6] FIG. 10 is a diagram showing a correlation graph. [Figure 7] FIG. 10 is a diagram showing the configuration of a chemical liquid generating unit in a second embodiment. [Figure 8] FIG. 10 is a diagram showing a correlation graph. [Figure 9] FIG. 11 is a diagram for explaining operating values ​​in the third embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of a procedure for constructing a concentration prediction model. [Figure 11] FIG. 8 is a partial enlarged view of the chemical solution generating unit in FIG. 7. [Figure 12] FIG. 13 is a side view showing the configuration of a rotation holder in the sixth embodiment. [Figure 13] FIG. 2 is a functional block diagram showing the configuration of a rotation holding unit. [Figure 14] 10A and 10B are diagrams for explaining transition times of the chuck pins when a closing command is issued. [Figure 15] 10A and 10B are diagrams for explaining transition times of the chuck pins when an open command is issued. [Figure 16] FIG. 10 is a diagram for explaining transition times of a chuck pin and a chuck driving unit. [Figure 17] FIG. 2 is a diagram showing a configuration of a processing liquid supply unit. [Figure 18] FIG. 10 is a diagram for explaining transition times of the cleaning tool. [Figure 19] FIG. 13 is a side view showing the configuration of a rotation holder in the eighth embodiment. [Figure 20] FIG. 2 is a functional block diagram showing the configuration of a control unit. [Figure 21] 10A and 10B are diagrams showing changes in rotation speed and torque of a spin drive unit during substrate processing. [Figure 22] FIG. 10 shows the torque and temperature obtained. [Figure 23] FIG. 10 is a diagram for explaining an example of a method for determining an abnormality. [Figure 24] 21 is a flowchart showing an abnormality detection process performed by the control unit in FIG. 20. DETAILED DESCRIPTION OF THE INVENTION

[0042] <1> Configuration of substrate processing equipment A substrate processing apparatus, an abnormality detection method, and an abnormality detection program according to embodiments of the present invention will be described below with reference to the drawings. In the following description, the term "substrate" refers to a semiconductor substrate, a substrate for an FPD (Flat Panel Display) such as a liquid crystal display device or an organic EL (Electro Luminescence) display device, a substrate for an optical disk, a substrate for a magnetic disk, a substrate for a magneto-optical disk, a substrate for a photomask, a ceramic substrate, a substrate for a solar cell, or the like.

[0043] Fig. 1 is a block diagram showing a schematic configuration of a substrate processing apparatus according to one embodiment of the present invention. As shown in Fig. 1, the substrate processing apparatus 1 includes a substrate processing section 100 and a control section 200. The substrate processing section 100 includes one or more processing units 110 that perform various processes on substrates using processing liquids.

[0044] Specifically, each processing unit 110 may be a cleaning unit that supplies a cleaning liquid to the substrate, a coating unit that supplies a coating liquid to the substrate, or a developing unit that supplies a developing liquid to the substrate. Each processing unit 110 is provided with a rotary holder that holds and rotates the substrate, a processing liquid supply unit that supplies a processing liquid to the substrate, etc.

[0045] Furthermore, when the processing unit 110 is an etching unit that supplies an etching liquid to the substrate, a chemical liquid generator 300 may be provided in the substrate processing unit 100. The chemical liquid generator 300 generates a diluted chemical liquid obtained by diluting an undiluted chemical liquid as an etching liquid and supplies the diluted chemical liquid to each substrate processing unit 100.

[0046] The control unit 200 is composed of a CPU (Central Processing Unit) and a memory, or a microcomputer, etc. The CPU of the control unit 200 controls the operations of various operating parts in the substrate processing unit 100 or the chemical solution producing unit 300. The memory of the control unit 200 stores an abnormality detection program for detecting abnormalities in the operating parts of the substrate processing unit 100.

[0047] Furthermore, the CPU of the control unit 200 collects predetermined information from various operating parts in the substrate processing unit 100 or the chemical liquid production unit 300 during substrate processing, and detects an abnormality in the substrate processing apparatus 1 based on the processing results of the collected information. An example of detecting an abnormality in the substrate processing apparatus 1 related to various operating parts in the substrate processing unit 100 or the chemical liquid production unit 300 will be described below.

[0048] <2> First embodiment (1) Processing liquid supply unit In the first embodiment, an abnormality is detected in a processing liquid supply unit included in each processing unit 110 as an operating part of the substrate processing unit 100. Fig. 2 is a diagram showing the configuration of the processing liquid supply unit in the first embodiment. As shown in Fig. 2, a plurality of processing liquid supply units 400 are connected to a circulation pipe 401 through which the processing liquid circulates. In addition, a pressure gauge 402 for detecting the pressure of the processing liquid is inserted in the circulation pipe 401.

[0049] The processing liquid supply unit 400 includes an upper surface supply unit 410 and a lower surface supply unit 420. The upper surface supply unit 410 includes a pipe 411, a flow meter 412, an on-off valve 413, an adjustment valve 414, and a nozzle 415. The pipe 411 is connected to the circulation pipe 401. As a result, the processing liquid from the circulation pipe 401 flows through the pipe 411. The flow meter 412, the on-off valve 413, the adjustment valve 414, and the nozzle 415 are inserted in this order from upstream to downstream in the pipe 411.

[0050] The flow meter 412 detects the flow rate of the processing liquid flowing through the pipe 411 and provides the detection result to the control unit 200. The on-off valve 413 opens and closes the flow path of the pipe 411. The adjustment valve 414 includes, for example, a motor needle valve, and adjusts the flow rate of the processing liquid flowing through the pipe 411 based on pulse control by the control unit 200. The nozzle 415 is disposed above the substrate W and supplies the processing liquid to the upper surface of the substrate W.

[0051] The lower surface supply unit 420 includes a pipe 421, a flow meter 422, an on-off valve 423, an adjustment valve 424, and a nozzle 425. The upstream end of the pipe 421 is connected to the pipe 411 upstream of the flow meter 412. This allows the processing liquid from the circulation pipe 401 to flow through the pipe 421. The flow meter 422, the on-off valve 423, the adjustment valve 424, and the nozzle 425 are inserted in this order from upstream to downstream in the pipe 421.

[0052] The flow meter 422 detects the flow rate of the processing liquid flowing through the pipe 421 and provides the detection result to the control unit 200. The on-off valve 423 opens and closes the flow path of the pipe 421. The adjustment valve 424 includes, for example, a motor needle valve, and adjusts the flow rate of the processing liquid flowing through the pipe 421 based on pulse control by the control unit 200. The nozzle 425 is disposed below the substrate W and supplies the processing liquid to the underside of the substrate W.

[0053] In this example, the nozzles 415, 425 supply the processing liquid at approximately the same flow rate and at approximately the same frequency to the upper and lower surfaces of the substrate W to be processed, thereby processing the upper and lower surfaces of the substrate W. The substrate W to be processed may be processed while being held and rotated by, for example, a spin holder 700 shown in FIG. 19 , which will be described later.

[0054] (2) Control Unit Fig. 3 is a functional block diagram showing the configuration of control unit 200. As shown in Fig. 3, control unit 200 includes, as functional units, an operating value acquisition unit 210, an abnormality determination unit 220, and a notification unit 230. The functional units of control unit 200 are realized by the CPU of control unit 200 executing an abnormality detection program stored in memory. Some or all of the functional units of control unit 200 may be realized by hardware such as electronic circuits.

[0055] The operating value acquisition unit 210 performs pulse control of the regulating valve 414 by providing a predetermined number of pulses to the regulating valve 414 so that the flow rate of the processing liquid flowing through the flow path of the upper surface supply unit 410 is adjusted to a predetermined value based on the detection result provided by the flow meter 412. In this way, the operating value acquisition unit 210 acquires the pulse value provided to the regulating valve 414 as a first operating value.

[0056] Similarly, the operating value acquisition unit 210 performs pulse control of the regulating valve 424 by providing a predetermined number of pulses to the regulating valve 424 so that the flow rate of the processing liquid flowing through the flow path of the lower surface supply unit 420 is adjusted to a predetermined value based on the detection result provided by the flow meter 422. In this way, the operating value acquisition unit 210 acquires the pulse value provided to the regulating valve 424 as the second operating value.

[0057] Note that the flow rate of the treatment liquid may not be stable immediately after the start and end of supply of the treatment liquid. Therefore, pulse values ​​do not need to be acquired immediately after the start and end of supply of the treatment liquid. In this case, pulse values ​​are acquired as the first and second operating values ​​during a period from a predetermined time point after the start of supply, when the flow rate of the treatment liquid is stable, to a predetermined time point before the end of supply.

[0058] Each time pulse control of regulating valves 414, 424 is performed, abnormality determination unit 220 plots data points determined by pairs of pulse values ​​to regulating valve 414 and regulating valve 424 on a correlation graph. FIG. 4 is a diagram showing the correlation graph. As shown in FIG. 4, the correlation graph is a two-dimensional graph with the first and second operating values ​​as axes. Specifically, the horizontal axis of the correlation graph in FIG. 4 indicates the pulse value to regulating valve 414, and the vertical axis indicates the pulse value to regulating valve 424.

[0059] In the correlation graph, an acceptable range R is predetermined based on the correlation between the pulse value to the adjusting valve 414 and the pulse value to the adjusting valve 424. In this example, the acceptable range R has an elliptical shape and is determined so as to include a predetermined percentage (e.g., 95%) of data points determined by pairs of pulse values ​​to the adjusting valve 414 and the adjusting valve 424 that are acquired in advance before substrate processing. The acceptable range R may be determined based on a regression curve obtained from the distribution of data points. It is preferable that the acceptable range R be determined based on data points acquired before the processing liquid supply unit 400 deteriorates over time, such as when the processing liquid supply unit 400 is installed.

[0060] The abnormality determination unit 220 determines, at a predetermined timing, whether an abnormality has occurred based on the proportion of plotted data points that fall outside the allowable range R. The abnormality determination may be performed every time a predetermined number of substrates W are processed, or every time a predetermined time period elapses. In this case, it becomes easier to detect an abnormality in the substrate processing apparatus early.

[0061] In this example, if the ratio of plotted data points that fall outside the tolerance range R exceeds a predetermined threshold, it is determined that an abnormality has occurred. In this case, it is presumed that an abnormality has occurred in an operating part associated with the regulating valve 414 or the regulating valve 424. The operating part associated with the regulating valve 414 or the regulating valve 424 includes a needle, a diaphragm, a bearing, a motor coil, or the like.

[0062] As another example of determining an abnormality, the tolerance range may be updated to include a predetermined proportion of the plotted data points at the timing of determining an abnormality, and it may be determined that an abnormality has occurred based on the rate of change of the updated tolerance range relative to a predetermined tolerance range R. The rate of change of the tolerance range includes the rate of change of the major axis of the tolerance range, the rate of change of the minor axis of the tolerance range, or the rate of change of the area of ​​the tolerance range.

[0063] When the abnormality determination unit 220 determines that an abnormality has occurred, the notification unit 230 notifies the user of this. As an example of notification by the notification unit 230, if the substrate processing apparatus 1 includes a display device, a character string indicating that an abnormality has occurred may be displayed. If the substrate processing apparatus 1 includes an audio output device, a sound indicating the same content may be output, or an alarm sound such as a buzzer may be output. If the substrate processing apparatus 1 includes an indicator light such as a lamp, the indicator light may be turned on, off, or flashing in a manner corresponding to the content of the alarm.

[0064] (3) Abnormality detection processing Fig. 5 is a flowchart showing the abnormality detection process by the control unit 200 of Fig. 3. The abnormality detection process of Fig. 5 is performed by the CPU of the control unit 200 executing an abnormality detection program stored in memory. The abnormality detection process is performed in parallel with substrate processing. The abnormality detection process will be described below using the flowchart of Fig. 5 together with the control unit 200 of Fig. 3.

[0065] First, the operating value acquisition unit 210 acquires a pulse value to the regulating valve 414 (step S1). The operating value acquisition unit 210 also acquires a pulse value to the regulating valve 424 (step S2). Step S1 is performed when the upper surface of the substrate W is processed, and step S2 is performed when the lower surface of the substrate W is processed. The order in which steps S1 and S2 are performed is determined by the substrate processing recipe. Therefore, steps S1 and S2 may be performed first, or may be performed simultaneously.

[0066] Next, the abnormality determination unit 220 plots data points determined by the pair of pulse values ​​acquired in steps S1 and S2 on a correlation graph (step S3). Subsequently, the abnormality determination unit 220 determines whether the current time is the timing to determine an abnormality (step S4). The current time may be determined to be the timing to determine an abnormality every time a predetermined number of substrates W are processed. Alternatively, the current time may be determined to be the timing to determine an abnormality every time a predetermined time elapses. If the current time is not the timing to determine an abnormality, the abnormality determination unit 220 returns to step S1. Steps S1 to S4 are repeated until the current time is the timing to determine an abnormality.

[0067] If the current time is the timing for determining an abnormality, the abnormality determination unit 220 evaluates the proportion of data points that exceed the allowable range R among the data points plotted on the correlation graph (step S5). Thereafter, the abnormality determination unit 220 determines whether the proportion evaluated in step S5 exceeds a predetermined threshold value (step S6). If the proportion is less than the threshold value, the abnormality determination unit 220 does not determine that an abnormality has occurred, and the process returns to step S1. If the proportion exceeds the threshold value, the abnormality determination unit 220 determines that an abnormality has occurred. In this case, the notification unit 230 notifies this fact (step S7), and the process returns to step S1.

[0068] In step S4, it may be determined that the current timing is the timing to determine whether or not an abnormality has occurred when the substrate processing apparatus 1 has completed processing all of the substrates W to be processed. In this configuration, the abnormality detection process ends when the ratio is less than the threshold value in step S6. Alternatively, the abnormality detection process ends after a notification is issued in step S7.

[0069] (4) Effects In the substrate processing apparatus 1 according to this embodiment, the pulse values ​​to the regulating valves 414 and 424 are acquired as first and second operating values ​​by the operating value acquisition unit 210. Whether or not an abnormality has occurred is determined by the abnormality determination unit 220 based on the correlation between the pulse value to the regulating valve 414 acquired by the operating value acquisition unit 210 and the pulse value to the regulating valve 424. In this case, an abnormality in the substrate processing apparatus 1 can be detected early based on the correlation between the pulse value to the regulating valve 414 and the pulse value to the regulating valve 424.

[0070] Whether or not an abnormality has occurred is determined based on the proportion of data points that exceed the allowable range R among data points determined by a pair of the pulse value to the regulating valve 414 and the pulse value to the regulating valve 424 acquired by the operating value acquisition unit 210. In this case, an abnormality in the substrate processing apparatus 1 can be detected by simple processing.

[0071] Furthermore, the allowable range R is determined so as to include a predetermined proportion of data points among data points determined by a pair of pulse values ​​to the regulating valve 414 and the regulating valve 424, which are acquired in advance by the operating value acquisition unit 210 before the substrate is processed. Therefore, the allowable range R used for determining an abnormality can be easily determined.

[0072] (5) Variations In the present embodiment, the pulse value to the regulating valve 414 is acquired as the first operating value, and the pulse value to the regulating valve 424 is acquired as the second operating value, but the embodiment is not limited to this. The operating value acquisition unit 210 is provided with the pressure of the processing liquid flowing through the circulation pipe 401, which is detected by the pressure gauge 402. Therefore, the pulse value to the regulating valve 414 may be acquired as the first operating value, and the pressure of the processing liquid flowing through the circulation pipe 401 may be acquired as the second operating value.

[0073] Fig. 6 is a diagram showing a correlation graph. The horizontal axis of the correlation graph in Fig. 6 represents the pulse value to the adjustment valve 414, and the vertical axis represents the pressure of the processing liquid. As shown in Fig. 6, each time pulse control of the adjustment valve 414 is performed, a data point determined by a pair of the pulse value to the adjustment valve 414 and the pressure of the processing liquid is plotted on the correlation graph. Whether or not an abnormality has occurred is determined based on the proportion of data points that fall outside the allowable range R among the plotted data points.

[0074] In this configuration, when it is determined that an abnormality has occurred, it is presumed that an abnormality has occurred in an operating part related to the regulating valve 414 or the circulation pipe 401. In a modified example, the pulse value to the regulating valve 424 may be acquired as the first operating value. In this configuration, when it is determined that an abnormality has occurred, it is presumed that an abnormality has occurred in an operating part related to the regulating valve 424 and the circulation pipe 401.

[0075] <3> Second embodiment (1) Chemical solution generation section In the second embodiment, an abnormality is detected in the chemical liquid generator 300. Fig. 7 is a diagram showing the configuration of the chemical liquid generator 300 in the second embodiment. As shown in Fig. 7, the chemical liquid generator 300 includes a concentrate supply unit 310, a diluent supply unit 320, a mixing pipe 330, a gas supply unit 340, a mixing tank 350, and a supply pipe 360.

[0076] The raw solution supply unit 310 includes a pipe 311, an on-off valve 312, a flow meter 313, and an adjustment valve 314. The upstream end of the pipe 311 is connected to a raw solution supply source 301 that supplies the raw solution of the chemical. As a result, the raw solution from the raw solution supply source 301 flows through the pipe 311. In this example, the raw solution is hydrofluoric acid.

[0077] An on-off valve 312, a flow meter 313, and an adjustment valve 314 are inserted in this order from upstream to downstream in the piping 311. The on-off valve 312 opens and closes the flow path of the piping 311. The flow meter 313 detects the flow rate of the concentrate flowing through the piping 311 and provides the detection result to the control unit 200. The adjustment valve 314 includes, for example, a motor needle valve, and adjusts the flow rate of the concentrate flowing through the piping 311 based on pulse control by the control unit 200.

[0078] The diluent supply unit 320 includes a pipe 321, an on-off valve 322, a flow meter 323, and an adjustment valve 324. The upstream end of the pipe 321 is connected to a diluent supply source 302 that supplies the diluent. As a result, the concentrate from the concentrate supply source 301 flows through the pipe 321. In this example, the diluent is DIW (deionized water).

[0079] An on-off valve 322, a flow meter 323, and an adjustment valve 324 are inserted in this order from upstream to downstream in the piping 321. The on-off valve 322 opens and closes the flow path of the piping 321. The flow meter 323 detects the flow rate of the diluent flowing through the piping 321 and provides the detection result to the control unit 200. The adjustment valve 324 includes, for example, an electric pressure regulator, and adjusts the flow rate of the diluent flowing through the piping 321 based on pulse control by the control unit 200.

[0080] The mixing pipe 330 has one main pipe 331 and two branch pipes 332, 333. The upstream end of the main pipe 331 is connected to the downstream end of the pipe 311 of the concentrate supply unit 310 and the downstream end of the pipe 321 of the diluent supply unit 320. The branch pipe 332 is connected between the downstream end of the main pipe 331 and the mixing tank 350. The branch pipe 333 is connected between the downstream end of the main pipe 331 and the waste liquid tank 303. Opening and closing valves 334, 335 are inserted in the branch pipes 332, 333, respectively.

[0081] In the main pipe 331, the stock solution supplied from the stock solution supply unit 310 and the diluent supplied from the diluent solution supply source 302 are mixed to generate a diluted chemical solution. In this example, the diluted chemical solution is dilute hydrofluoric acid. The diluted chemical solution generated in the main pipe 331 is supplied to the mixing tank 350 through the branch pipe 332.

[0082] Gas supply unit 340 includes pipe 341 and on-off valve 342. An upstream end of pipe 341 is connected to gas supply source 304 that supplies gas. As a result, gas from gas supply source 304 flows through pipe 341. In this example, the gas is an inert gas such as nitrogen. A downstream end of pipe 341 is connected to mixing tank 350. On-off valve 342 is inserted in pipe 341 and opens and closes the flow path of pipe 341.

[0083] The mixing tank 350 stores a mixture of the stock solution and the diluent liquid as a diluted chemical solution. Four liquid level sensors 351, 352, 353, and 354 are provided in the mixing tank 350. The liquid level sensors 351 to 354 detect the first to fourth liquid levels of the diluted chemical solution stored in the mixing tank 350, respectively, and provide the detection results to the control unit 200.

[0084] The first, second, third, and fourth liquid levels are surfaces located in this order from bottom to top. Specifically, the first liquid level is a surface slightly above the bottom surface of the mixing tank 350. The second liquid level is a surface that is a predetermined height above the first liquid level. The third liquid level is a surface that is a predetermined height below the fourth liquid level. The fourth liquid level is a surface that is slightly below the top surface of the mixing tank 350.

[0085] The supply pipe 360 ​​has one main pipe 361 and two branch pipes 362, 363. The upstream end of the main pipe 361 is connected to the mixing tank 350. The branch pipe 362 is a circulation pipe used to circulate the diluted chemical solution, and is connected between the downstream end of the main pipe 361 and the mixing tank 350. The branch pipe 363 is a processing pipe used to process the substrate W, and is connected between the downstream end of the main pipe 361 and the substrate processing unit 100.

[0086] A concentration meter 364 and a heater 365 are inserted in the main pipe 361. A pump 366, a filter 367, and an on-off valve 368 are inserted in the branch pipe 362. An on-off valve 369 is inserted in the branch pipe 363. The concentration meter 364 measures the concentration of the diluted chemical solution flowing through the main pipe 361, and provides the measurement result to the control unit 200.

[0087] As the pump 366 is driven and the on-off valve 368 is opened, the diluted chemical solution from the mixing tank 350 is heated by the heater 365 and then circulated to the mixing tank 350 through the filter 367. In this example, the diluted chemical solution stored in the mixing tank 350 is constantly circulated through the branch pipe 362.

[0088] Furthermore, by opening the on-off valve 342 and the on-off valve 369, the diluted chemical stored in the mixing tank 350 is pressurized by gas. As a result, the diluted chemical stored in the mixing tank 350 is guided downstream through the main pipe 361, heated by the heater 365, and then supplied to the substrate processing unit 100 through the branch pipe 363.

[0089] As indicated by the dashed dotted line in Figure 7, the chemical solution generator 300 may further include a circulation pipe 370 similar to the circulation pipe 401 in Figure 2. In this case, the substrate processing unit 100 and the mixing tank 350 are connected by the circulation pipe 370. In the substrate processing unit 100, a portion of the diluted chemical solution supplied from the mixing tank 350 is used for substrate processing such as cleaning. The volume of the diluted chemical solution used is determined by the substrate processing recipe. The other portion of the diluted chemical solution supplied to the substrate processing unit 100 is returned to the mixing tank 350 through the circulation pipe 370 without being used for substrate processing.

[0090] (2) Control Unit The configuration of the control unit 200 in this embodiment is basically the same as the configuration of the control unit 200 in the first embodiment shown in Fig. 3, so the operation of the control unit 200 will be simply explained using Fig. 3. The same applies to the control units 200 in the third to seventh embodiments described later.

[0091] In the substrate processing unit 100, the diluted chemical liquid supplied from the chemical liquid generator 300 is used, causing the liquid level of the diluted chemical liquid stored in the mixing tank 350 to drop. Therefore, when the liquid level sensor 352 detects the second liquid level, replenishment of the diluted chemical liquid is started.

[0092] 3 opens on-off valves 312 and 322. Furthermore, the operating value acquisition unit 210 performs pulse control of the adjustment valve 314 so that a constant flow rate of concentrate is supplied from the concentrate supply unit 310. Similarly, the operating value acquisition unit 210 performs pulse control of the adjustment valve 324 so that a constant flow rate of diluent is supplied from the diluent supply unit 320. As a result, the concentrate supply unit 310 and the diluent supply unit 320 supply the concentrate and diluent at constant flow rates, respectively.

[0093] The supplied stock solution and diluent solution are mixed in the main pipe 331 of the mixing pipe 330 to generate a diluted chemical solution. The operating value acquisition unit 210 calculates a theoretical value of the concentration of the diluted chemical solution to be generated based on the ratio between the flow rate of the stock solution and the flow rate of the diluent solution detected by the flow meters 313 and 323, respectively, and acquires the calculated theoretical value of the concentration as a first operating value.

[0094] The produced diluted chemical solution is stored in the mixing tank 350 through the branch pipe 332, causing the liquid level of the diluted chemical solution stored in the mixing tank 350 to rise. When the liquid level sensor 352 detects a third liquid level, the operating value acquisition unit 210 closes the on-off valves 312 and 322. This stops the replenishment of the diluted chemical solution. The operating value acquisition unit 210 acquires the actual concentration value of the diluted chemical solution after replenishment, detected by the concentration meter 364, as the second operating value.

[0095] Note that immediately after the start and end of diluted chemical production, the flow rate of the diluent or stock solution is unstable, which can cause the concentration of the diluted chemical to be unstable. Therefore, immediately after the start of diluted chemical production, on-off valve 335 is opened for a predetermined time and on-off valve 334 is closed, so that the diluted chemical with an unstable concentration is discarded into waste tank 303. Also, immediately after the end of diluted chemical production, on-off valve 335 is opened for a predetermined time and on-off valve 334 is closed, so that the diluted chemical with an unstable concentration is discarded into waste tank 303. As a result, diluted chemical with a stable concentration is stored in mixing tank 350.

[0096] FIG. 8 is a diagram showing a correlation graph. The horizontal axis of the correlation graph in FIG. 8 indicates the theoretical concentration value, and the vertical axis indicates the actual measured concentration value. As shown in FIG. 8, each time diluted chemical solution is replenished, abnormality determination unit 220 plots data points determined by pairs of the theoretical and actual measured concentrations of the replenished diluted chemical solution on the correlation graph. Furthermore, abnormality determination unit 220 determines whether an abnormality has occurred based on the proportion of plotted data points that fall outside tolerance range R. If an abnormality is determined to have occurred, it is inferred that an abnormality has occurred in an operating part related to adjustment valves 314, 324 or concentration meter 364.

[0097] When the abnormality determination unit 220 determines that an abnormality has occurred, the notification unit 230 notifies the user of this. In this embodiment, when the liquid level sensor 351 detects the first liquid level or the liquid level sensor 354 detects the fourth liquid level, the control of the chemical liquid generator 300 is stopped. In this case as well, the notification unit 230 may notify the user that the control of the chemical liquid generator 300 has been stopped.

[0098] The abnormality detection process in this example is similar to that in Fig. 5, except that the theoretical and actual values ​​of the concentration of the diluted chemical are obtained in steps S1 and S2, respectively. Step S1 is performed, for example, while the diluted chemical is being replenished. Step S2 is performed, for example, after the replenishment of the diluted chemical is stopped.

[0099] (3) Effects In the substrate processing apparatus 1 according to this embodiment, the theoretical value of the concentration of the diluted chemical calculated from the ratio between the flow rate of the undiluted solution and the flow rate of the diluent solution detected by the flow meters 313 and 323 is acquired as a first operating value by the operating value acquisition unit 210. Also, the actual measured value of the concentration of the diluted chemical detected by the concentration meter 364 is acquired as a second operating value by the operating value acquisition unit 210.

[0100] The abnormality determination unit 220 determines whether an abnormality has occurred based on the correlation between the theoretical value of the concentration of the diluted chemical liquid acquired by the operating value acquisition unit 210 and the actual measurement value of the concentration of the diluted chemical liquid. In this case, an abnormality in the substrate processing apparatus 1 can be detected early based on the correlation between the theoretical value of the concentration of the diluted chemical liquid and the actual measurement value of the concentration of the diluted chemical liquid.

[0101] In this embodiment, the abnormality determination unit 220 may determine whether or not an abnormality has occurred based on the difference between the first operating value and the second operating value using the Hotelling method, cumulative sum, etc. The same applies to the following third to fifth embodiments.

[0102] <4> Third embodiment (1) Operating value In the second embodiment, a theoretical value of the concentration of the diluted chemical is calculated as a first operating value based on the ratio between the instantaneous value of the flow rate of the stock solution detected by flow meter 313 and the instantaneous value of the flow rate of the diluent solution detected by flow meter 323. In addition, the instantaneous value of the concentration of the diluted chemical is detected by concentration meter 364 as a second operating value. However, the embodiment is not limited to this. Below, differences between the operating values ​​in the third embodiment and the operating values ​​in the second embodiment will be described, with appropriate reference to the chemical generation unit 300 in FIG. 7.

[0103] Fig. 9 is a diagram for explaining operating values ​​in the third embodiment. Fig. 9 shows time series of the flow rate of the stock solution, the flow rate of the diluent, and the concentration of the diluted chemical solution, respectively, detected by flow meter 313, flow meter 323, and concentration meter 364. As shown in Fig. 9, at time T1, a predetermined time after on-off valves 312 and 322 are opened, the stock solution and the diluent are mixed in mixing pipe 330, thereby starting the production of diluted chemical solution.

[0104] As described above, the flow rates of the stock solution and diluent solution are not stable immediately after the start of production of the diluted chemical solution. Therefore, during the period from time T1 to time T2, a predetermined time later, on-off valve 335 is opened and on-off valve 334 is closed. Therefore, the produced diluted chemical solution is discarded in waste tank 303. At time T2, on-off valve 335 is closed and on-off valve 334 is opened, thereby starting the supply of diluted chemical solution to mixing tank 350.

[0105] At time T4, when a predetermined time ΔT1 has elapsed since time T2, on-off valve 335 is opened and on-off valve 334 is closed. This terminates the supply of diluted chemical to mixing tank 350. The operating value acquisition unit 210 of control unit 200 in FIG. 3 calculates a theoretical value of the concentration of the diluted chemical to be produced based on the integrated value of the flow rate of the undiluted solution detected by flow meter 313 and the integrated value of the flow rate of the diluent solution detected by flow meter 323 during the period from time T2 to time T4. The operating value acquisition unit 210 also acquires the calculated theoretical value of the concentration of the diluted chemical as a first operating value.

[0106] At time T3, when a time ΔT2 smaller than the time ΔT1 has elapsed since time T2, the diluted chemical solution that started to be supplied to the mixing tank 350 at time T2 reaches the concentration meter 364. At time T5, when a time ΔT1 has elapsed since time T3, that is, when a time ΔT2 has elapsed since time T4, the diluted chemical solution that stopped being supplied to the mixing tank 350 at time T4 reaches the concentration meter 364. The operating value acquisition unit 210 calculates statistical values ​​of the concentration of the diluted chemical solution detected by the concentration meter 364 during the period from time T3 to time T5. The operating value acquisition unit 210 also acquires the calculated statistical values ​​of the concentration of the diluted chemical solution as a second operating value.

[0107] In this embodiment, the statistical value is an average value, specifically, the sum of the concentrations detected at each time point from time T3 to time T5 divided by the number of detections. The statistical value may be a weighted average value or other calculated value. Furthermore, the time ΔT2 may be determined by measurement or by calculation based on the length of the flow path, the cross-sectional area of ​​the flow path, and the flow rate of the diluted chemical solution.

[0108] The abnormality detection process in this embodiment is similar to the abnormality detection process in Fig. 5, except that the theoretical value and statistical value of the concentration of the diluted chemical solution are obtained in steps S1 and S2, respectively. Steps S1 and S2 are performed, for example, during a period when the diluted chemical solution is being replenished. Step S1 can be performed a time ΔT2 earlier than step S2, but step S2 may also be started before step S1 is completed.

[0109] (2) Effects In the present embodiment, the abnormality determination unit 220 of the control unit 200 determines whether an abnormality has occurred based on the correlation between the theoretical value of the diluted chemical concentration and the statistical value of the diluted chemical concentration. Here, the correlation between the theoretical value of the diluted chemical concentration and the statistical value of the diluted chemical concentration obtained in the present embodiment is stronger than the correlation between the theoretical value of the diluted chemical concentration and the actual measured value of the diluted chemical concentration obtained in the second embodiment. Therefore, an abnormality in the substrate processing apparatus 1 can be detected more reliably.

[0110] <5> Fourth embodiment (1) Operating value The differences between the operating values ​​in the fourth embodiment and those in the second embodiment will be described below with reference to the chemical solution generator 300 in Fig. 7. In this embodiment, a concentration prediction model for predicting the concentration of a diluted chemical solution is constructed in advance. The constructed concentration prediction model is stored in the memory of the control unit 200 in Fig. 1.

[0111] When constructing the concentration prediction model, the same control as during substrate processing is performed on each component of the chemical liquid generation unit 300. The concentration prediction model is preferably constructed before the chemical liquid generation unit 300 deteriorates over time, such as when the chemical liquid generation unit 300 is installed. Fig. 10 is a diagram for explaining an example of the procedure for constructing the concentration prediction model. Fig. 10 shows a time series of the flow rate of the undiluted liquid, the flow rate of the diluent liquid, the amount of diluted chemical liquid discharged onto the substrate W in the substrate processing unit 100, and the concentration of the diluted chemical liquid.

[0112] 10, when constructing a concentration prediction model, the flow rate of the stock solution, the flow rate of the diluent solution, the discharge rate of the diluted chemical solution, and the concentration of the diluted chemical solution are detected sequentially at multiple points in time. The flow rate of the stock solution, the flow rate of the diluent solution, and the concentration of the diluted chemical solution are detected by flow meter 313, flow meter 323, and concentration meter 364, respectively. The discharge rate of the diluted chemical solution may be detected by a flow meter (not shown), or may be detected by calculation based on the capacity of the flow path, the discharge time, etc.

[0113] A data set consisting of the flow rate of the stock solution, the flow rate of the diluent solution, the discharge rate of the diluted chemical, and the concentration of the diluted chemical detected between each time point and a time point a predetermined time ΔT11 before that time point is acquired as explanatory variables corresponding to each time point. In addition, the concentration of the diluted chemical a predetermined time ΔT12 after each time point is acquired as a response variable corresponding to each time point. Based on the explanatory variables and response variables corresponding to each acquired time point, training data indicating the relationship between the explanatory variables and response variables corresponding to that time point is generated.

[0114] 10, the data set detected between time T11 and time T12, which is time ΔT11 after time T11, becomes the explanatory variable corresponding to time T12. Also, the concentration of the diluted chemical solution detected at time T13, which is time ΔT12 after time T12, becomes the objective variable corresponding to time T12. For time points after time T12, explanatory variables and objective variables are sequentially acquired to generate multiple sets of training data.

[0115] A LightGBM (Gradient Boosting Machine) is prepared in advance as a machine learning model. A concentration prediction model is constructed by learning a plurality of training data generated by the LightGBM. In this embodiment, the machine learning model is LightGBM, but the embodiment is not limited to this. The machine learning model may be linear regression, Lasso regression, LSTM (Long Short Term Memory), or the like.

[0116] During substrate processing, the flow rate of the stock solution, the flow rate of the diluent solution, the discharge rate of the diluted chemical solution, and the concentration of the diluted chemical solution at multiple points in time are detected by flow meters 313, 323, concentration meter 364, etc. The operating value acquisition unit 210 of the control unit 200 in Fig. 3 acquires the flow rate of the stock solution, the flow rate of the diluent solution, the discharge rate of the diluted chemical solution, and the concentration of the diluted chemical solution detected between each point in time and a point in time ΔT11 before that point in time as a data set corresponding to each point in time.

[0117] Here, the operating value acquisition unit 210 predicts the concentration of the diluted chemical solution after a time ΔT12 from each time point based on the acquired data set corresponding to each time point and a concentration prediction model constructed in advance. The operating value acquisition unit 210 acquires the predicted value of the concentration of the diluted chemical solution as a first operating value. The operating value acquisition unit 210 also acquires the actual measured value of the concentration of the diluted chemical solution detected after a time ΔT12 from each time point as a second operating value. In this case, a correlation graph is created in which the horizontal axis indicates the predicted value of the concentration and the vertical axis indicates the actual measured value of the concentration.

[0118] The abnormality detection process in this example is similar to the abnormality detection process in Fig. 5, except that predicted and measured values ​​of the concentration of the diluted chemical are obtained in steps S1 and S2, respectively. Steps S1 and S2 are performed, for example, during a period when the diluted chemical is being replenished.

[0119] (2) Effects In the present embodiment, the abnormality determination unit 220 determines whether an abnormality has occurred based on the correlation between the predicted value of the concentration of the diluted chemical and the actual measured value of the concentration of the diluted chemical. Here, the correlation between the predicted value of the concentration of the diluted chemical and the actual measured value of the concentration of the diluted chemical obtained in the present embodiment is stronger than the correlation between the theoretical value of the concentration of the diluted chemical and the actual measured value of the concentration of the diluted chemical obtained in the second embodiment. Therefore, it is possible to more reliably detect a single abnormality that occurs in the substrate processing apparatus 1 over a relatively short period of time.

[0120] In this embodiment, the explanatory variables of the training data include the flow rate of the stock solution, the flow rate of the diluent solution, the discharge rate of the diluted chemical solution, and the concentration of the diluted chemical solution, but the embodiment is not limited to this. If the contribution of the discharge rate of the diluted chemical solution to the objective variable is relatively small, the explanatory variables of the training data do not need to include the discharge rate of the diluted chemical solution. On the other hand, the explanatory variables of the training data may include feature quantities other than the flow rate of the stock solution, the flow rate of the diluent solution, the discharge rate of the diluted chemical solution, and the concentration of the diluted chemical solution. In this case, it is possible to more accurately predict the concentration of the diluted chemical solution.

[0121] (3) Reference example In this embodiment, the flow rates of the concentrate and diluent are controlled to constant values ​​by adjusting valves 314 and 324, respectively. Furthermore, during periods when the flow rates are unstable, the diluent and concentrate are not supplied to mixing tank 350 but are instead disposed of in waste tank 303. In this configuration, the contribution of the flow rates of the concentrate and diluent to the objective variable is relatively small, so the explanatory variables of the training data do not need to include the flow rates of the concentrate or diluent. Even in this case, a predicted value of the diluted chemical concentration that has a strong correlation with the actual measured value of the diluted chemical concentration can be obtained.

[0122] <6> Fifth embodiment (1) Operating value The differences between the operating values ​​in the fifth embodiment and those in the third embodiment will be described with reference to FIG. 7 and the chemical liquid producing section 300 in FIG. 11, which will be described later.

[0123] 11 is a partially enlarged view of the chemical liquid generating unit 300 of FIG. 7. As shown in FIG. 11, at time t when the diluted chemical liquid is replenished, the volume W1 (t) The diluted chemical flows into the mixing tank 350 through the mixing pipe 330 per unit time. In this example, the unit time is the period τ1 of flow rate detection by the flow meters 313 and 323. Therefore, the capacity W1 (t) is the volume of diluted chemical solution flowing into the mixing tank 350 between time t and the time before the cycle τ1, and is calculated based on the flow rates of the original solution and diluent detected by the flow meters 313 and 323, respectively. (t) is calculated based on the flow rates of the concentrate and diluent and the specific gravity of the concentrate.

[0124] Furthermore, a volume W2 of diluted chemical solution flows out of the mixing tank 350 per unit time through the supply pipe 360. The volume W2 is a known constant value that does not depend on time, and is determined by the operating parameters of the pump 366.

[0125] Furthermore, at time t, capacity W3 (t) The diluted chemical solution flows into the mixing tank 350 through the circulation pipe 370 per unit time. Here, the diluted chemical solution that has passed through the substrate processing unit 100 reaches the mixing tank 350 after a predetermined time τ0 has elapsed. Therefore, the volume W3 (t) is calculated by subtracting the volume of the diluted chemical used in the substrate processing unit 100 at a time (t-τ0) before time t by a time τ0 from the volume W2. The time τ0 may be determined by measurement or by calculation based on the length of the flow path, the cross-sectional area of ​​the flow path, and the flow rate of the diluted chemical.

[0126] Due to the inflow and outflow of these diluted chemicals, the mixing tank 350 has a volume W (t) The volume W at time t is (t) The renewal formula and the concentration C of the diluted chemical solution stored in the mixing tank 350 (t) The update formula is calculated using the following formulas (1) and (2).

[0127]

number

[0128]

number

[0129] The operating value acquisition unit 210 of the control unit 200 in FIG. 3 calculates the concentration C of the diluted chemical solution stored in the mixing tank 350 at each time point t based on the formula (2). (t) The operating value acquisition unit 210 calculates the concentration C of the diluted chemical solution. (t) The operating value acquisition unit 210 acquires the theoretical value of the concentration detected by the concentration meter 364 at the time when the time ΔT2 in FIG. 9 has elapsed from each time point t (i.e., the concentration C (t+ΔT2) ) is acquired as the second operating value. Time ΔT2 is the time it takes for the diluted chemical solution flowing out of the mixing tank 350 to reach the concentration meter 364. In this case, a correlation graph is created in which the horizontal axis indicates the theoretical concentration value and the vertical axis indicates the actual concentration value.

[0130] The abnormality detection process in this example is similar to the abnormality detection process in FIG. 5, except that predicted and measured values ​​of the concentration of the diluted chemical are obtained in steps S1 and S2, respectively. Steps S1 and S2 may be performed during a period when the diluted chemical is being replenished. On the other hand, steps S1 and S2 may also be performed during a period when the diluted chemical is not being replenished. In this case, at times other than when the diluted chemical is being replenished, W1 (t) and concentration C0 (t) can be set to 0.

[0131] (2) Effects In this embodiment, the abnormality determination unit 220 of the control unit 200 determines whether an abnormality has occurred based on the correlation between the theoretical value of the concentration of the diluted chemical stored in the mixing tank 350 and the actual measured value of the concentration of the diluted chemical. Here, when the concentration of the diluted chemical supplied to the substrate processing unit 100 fluctuates, the unused diluted chemical in the substrate processing unit 100 is returned to the mixing tank 350, causing the concentration of the diluted chemical stored in the mixing tank 350 to fluctuate.

[0132] Even in this case, according to the present embodiment, the theoretical value of the concentration of the diluted chemical stored in the mixing tank 350 is calculated based on the volume of the diluted chemical flowing into or out of the mixing tank 350, the flow rate of the undiluted solution, and the flow rate of the diluent solution, so that the correlation between the theoretical value of the concentration of the diluted chemical and the statistical value of the concentration of the diluted chemical can be strengthened. This makes it possible to more reliably detect an abnormality in the substrate processing apparatus 1.

[0133] There may be a certain amount of deviation between the theoretical value of the concentration of the diluted chemical calculated based on formula (2) and the actual measured value of the concentration of the diluted chemical detected by the concentration meter 364. Therefore, in order to cancel out the deviation, an appropriately determined offset value is set to the concentration C0 of the diluent flowing into the mixing tank 350. (t) In this case, the correlation between the theoretical value of the concentration of the diluted chemical solution and the actually measured value of the concentration of the diluted chemical solution can be strengthened even in the period immediately after the calculation of the concentration of the diluted chemical solution starts.

[0134] <7> Sixth embodiment (1) Rotational support part In the sixth embodiment, an abnormality is detected in a spin holder included in each processing unit 110 as an operating part of the substrate processing unit 100. Fig. 12 is a side view showing the configuration of the spin holder in the sixth embodiment. As shown in Fig. 12, the spin holder 500 includes a spin chuck 510, a plurality of chuck pins 520, and a chuck driver 530. The spin chuck 510 is configured to horizontally hold and rotate the substrate W, and includes a spin driver 511, a rotation shaft 512, a plate support member 513, and a spin plate 514.

[0135] The spin drive unit 511 is provided in the upper part of the processing unit 110 in FIG. 1 and is supported by a support member (not shown). The rotation shaft 512 is provided to extend downward from the spin drive unit 511. The plate support member 513 is attached to the lower end of the rotation shaft 512. The spin plate 514 has a disk shape and is supported horizontally by the plate support member 513. When the rotation shaft 512 is rotated by the spin drive unit 511, the spin plate 514 rotates around a vertical axis.

[0136] A plurality of chuck pins 520 are provided on the periphery of the spin plate 514 at equal angular intervals with respect to the rotation axis 512. In this example, eight chuck pins 520 are provided on the periphery of the spin plate 514 at 45-degree intervals with respect to the rotation axis 512. Each chuck pin 520 includes a shaft portion 521, a pin support portion 522, and a holder portion 523. The shaft portion 521 is provided to penetrate the spin plate 514 vertically. The pin support portion 522 is provided to extend horizontally from the lower end of the shaft portion 521. The holder portion 523 is provided to protrude downward from the tip of the pin support portion 522.

[0137] Each chuck pin 520 switches between a closed state and an open state by rotating around a vertical axis centered on a shaft portion 521. In the closed state, each holding portion 523 abuts against the outer peripheral edge (bevel portion) of the substrate W. In the open state, each holding portion 523 is separated from the outer peripheral edge of the substrate W.

[0138] The chuck driver 530 includes, for example, a rotary actuator, a magnet, a linear slide, and a cam, and switches between a closed state and an open state. Fig. 13 is a functional block diagram showing the configuration of the rotary holder 500. As shown in Fig. 13, the control unit 200 issues an instruction to the chuck driver 530 to close the chuck driver 530 (hereinafter referred to as a close instruction). The control unit 200 also issues an instruction to the chuck driver 530 to open the chuck driver 530 (hereinafter referred to as an open instruction).

[0139] When a close command is given to the chuck driver 530, air is supplied to the rotary actuator, causing the chuck driver 530 to close. In this case, the magnet rotates, causing the linear slide to move linearly. The linear movement of the linear slide is converted by the cam into rotational movement that rotates each chuck pin 520. As a result, each chuck pin 520 is closed. On the other hand, when an open command is given to the chuck driver 530, the supply of air to the rotary actuator is stopped, causing the chuck driver 530 to open. In this case, each chuck pin 520 is open.

[0140] The rotary holder 500 also includes a plurality of Hall sensors 524 and a Hall sensor 531. The plurality of Hall sensors 524 correspond to the plurality of chuck pins 520, respectively. Each Hall sensor 524 detects the state of the corresponding chuck pin 520 based on a magnet (not shown) provided on the corresponding chuck pin 520, and provides the detection result to the control unit 200. The Hall sensor 531 detects the state of the chuck driver 530 based on the magnet of the chuck driver 530, and provides the detection result to the control unit 200.

[0141] (2) Control Unit In the following description, the eight chuck pins 520 will be referred to as the first to eighth chuck pins 520, respectively. The first and second chuck pins 520 form a pair, and the third and fourth chuck pins 520 form another pair. The fifth and sixth chuck pins 520 form a pair, and the seventh and eighth chuck pins 520 form another pair. Below, the operation of the control unit 200 for the first and second chuck pins 520 will be described, but the operation of the control unit 200 for the third to eighth chuck pins 520 is similar.

[0142] 3 issues a close command or an open command to the chuck driver 530. The operation value acquirer 210 also acquires the transition time of the first chuck pin 520 as a first operation value based on the detection result provided by the Hall sensor 524 corresponding to the first chuck pin 520. Similarly, the operation value acquirer 210 acquires the transition time of the second chuck pin 520 as a second operation value based on the detection result provided by the Hall sensor 524 corresponding to the second chuck pin 520.

[0143] The transition time of the chuck pin 520 is the time from when a close command is given to the chuck driver 530 until the chuck pin 520 is in the closed state, or the time from when an open command is given to the chuck driver 530 until the chuck pin 520 is in the open state.

[0144] 14 is a diagram illustrating the transition time of the chuck pins 520 when a close command is issued. As shown in FIG. 14, a close command is issued to the chuck driver 530 at time t1. In this case, the chuck driver 530 switches from the open state to the closed state. As a result, each chuck pin 520 switches from the open state to the closed state, and at time t2, the Hall sensor 524 detects that each chuck pin 520 is in the closed state. The operating value acquisition unit 210 acquires, for each chuck pin 520, the transition time Δt1 from time t1 when the close command is issued to time t2 when the chuck pin 520 is detected to be in the closed state.

[0145] 15 is a diagram illustrating the transition time of the chuck pins 520 when an open command is issued. As shown in FIG. 15, an open command is issued to the chuck driver 530 at time t11. In this case, the chuck driver 530 switches from the closed state to the open state. As a result, each chuck pin 520 switches from the closed state to the open state, and at time t12, the Hall sensor 524 detects that each chuck pin 520 is in the open state. The operating value acquisition unit 210 acquires, for each chuck pin 520, the transition time Δt11 from time t11 when the open command is issued to time t12 when the chuck pin 520 is detected to be in the open state.

[0146] 3 plots data points determined by a pair of the transition time of the first chuck pin 520 and the transition time of the second chuck pin 520 on a correlation graph every time a close command or an open command is given to the chuck driver 530. Data points may be plotted separately for the close command and the open command. In this case, the allowable range R is determined separately for the close command and the open command.

[0147] The abnormality determination unit 220 determines whether an abnormality has occurred based on the proportion of data points that exceed the tolerance range R among the plotted data points. If it is determined that an abnormality has occurred, it is presumed that an abnormality has occurred in a moving part associated with the first or second chuck pin 520. The moving part associated with the first or second chuck pin 520 includes a rotary actuator, a magnet, a linear slide, or a cam of the chuck drive unit 530. If the abnormality determination unit 220 determines that an abnormality has occurred, the notification unit 230 notifies the user of this fact.

[0148] 5 except that the transition times of the first and second chuck pins 520 are acquired in steps S1 and S2, respectively. Steps S1 and S2 are executed substantially simultaneously in response to a close command or an open command to the chuck driver 430. Steps S1 and S2 may be executed in response to only one of a close command or an open command.

[0149] (3) Effects In the substrate processing apparatus 1 according to this embodiment, the transition times of the first and second chuck pins 520 are acquired as first and second operating values ​​by the operating value acquisition unit 210. Whether or not an abnormality has occurred is determined by the abnormality determination unit 220 based on the correlation between the transition times of the first chuck pin 520 and the second chuck pin 520 acquired by the operating value acquisition unit 210. In this case, an abnormality in the substrate processing apparatus 1 can be detected early based on the correlation between the transition times of the first chuck pin 520 and the second chuck pin 520.

[0150] (4) Variations In this embodiment, the transition time of the first chuck pin 520 is acquired as the first operating value, and the transition time of the second chuck pin 520 is acquired as the second operating value, but the embodiment is not limited to this. There may be a time difference between the transition time of each chuck pin 520 and the transition time of the chuck driver 530.

[0151] 16 is a diagram illustrating the transition time of the chuck pins 520 and the chuck driver 530. As shown in FIG. 16, a close command is given to the chuck driver 530 at time t1. In this case, as in FIG. 14, the Hall sensors 524 detect that the chuck pins 520 are in the closed state at time t2. On the other hand, the Hall sensors 531 detect that the chuck driver 530 is in the closed state at time t3, which is later than time t2. A similar time difference may occur in an open command as well.

[0152] Therefore, the transition time Δt1 of any one of the chuck pins 520 may be acquired as a first operating value, and the transition time Δt2 of the chuck driver 530 may be acquired as a second operating value. Alternatively, instead of the transition time Δt2, the time from time t2 to time t3 may be acquired as the second operating value. In this configuration, when it is determined that an abnormality has occurred, it is inferred that an abnormality has occurred in an operating part related to any one of the chuck pins 520 or the chuck driver 530.

[0153] (5) Reference example In the reference example, the abnormality detection process may monitor the change over time of the transition time of each chuck pin 520 or the chuck driver 530, and determine that an abnormality has occurred if the transition time exceeds a predetermined allowable range. However, in the reference example, even if no abnormality has actually occurred, it may be determined that an abnormality has occurred because the transition time exceeds the predetermined allowable range. Therefore, in the reference example, it is difficult to accurately detect an abnormality.

[0154] <8> Seventh embodiment (1) Processing liquid supply unit In the seventh embodiment, an abnormality is detected in the processing liquid supply section included in each processing unit 110 as an operating part of the substrate processing section 100. Fig. 17 is a diagram showing the configuration of the processing liquid supply section. As shown in Fig. 17, the processing liquid supply section 600 includes scan drivers 610 and 620 and cleaners 630 and 640.

[0155] Each of the scan drivers 610 and 620 includes, for example, a stepping motor and an encoder. The scan driver 610 moves the cleaning tool 630 between a standby position outside the substrate W and a processing position below the center of the substrate W, based on pulse control by the controller 200. The scan driver 610 also detects, using the encoder, that the cleaning tool 630 has reached the processing position, and sends a positioning completion signal to the controller 200 indicating that positioning has been completed.

[0156] Based on pulse control by the control unit 200, the scan driver 620 moves the cleaning tool 640 between a standby position outside the substrate W and a processing position below the center of the substrate W. The scan driver 620 also detects, by an encoder, that the cleaning tool 640 has reached the processing position, and sends a positioning completion signal to the control unit 200 indicating that positioning has been completed.

[0157] Each of the cleaning tools 630, 640 is, for example, a nozzle, and supplies a processing liquid to the vicinity of the center of the lower surface of the substrate W at the processing position. This processes the substrate W. The substrate W may be processed while being held by, for example, the rotating holder 500 of FIG. 12. Note that the cleaning tool 630 may be a brush (including an abrasive brush) for cleaning the substrate W, rather than a nozzle. Similarly, the cleaning tool 640 may be a brush (including an abrasive brush) for cleaning the substrate W, rather than a nozzle.

[0158] In this example, the scan drivers 610 and 620 and the cleaners 630 and 640 are provided in the same processing unit 110, but the embodiment is not limited to this. As long as substrate processing using the cleaner 630 and substrate processing using the cleaner 640 are performed at approximately the same frequency, the scan drivers 610 and the cleaner 630 and the scan drivers 620 and the cleaner 640 may be provided in different processing units 110.

[0159] (2) Control Unit 3 pulse-controls the scan driver 610 to move the cleaning tool 630 from the standby position toward the processing position during substrate processing. The operating value acquisition unit 210 also acquires the transition time of the cleaning tool 630 as a first operating value based on a positioning completion signal provided by the scan driver 610. The transition time of the cleaning tool 630 is the time from when the pulse control of the scan driver 610 starts to when the positioning completion signal is provided.

[0160] FIG. 18 is a diagram illustrating the transition time of the cleaning tool 630. The horizontal axis of FIG. 18 represents time, and the vertical axis represents the pulse value to the scan driver 610. As shown in FIG. 18, pulse control of the scan driver 610 is started at time t21. In this case, the cleaning tool 630 moves from the standby position toward the processing position. At time t22, a positioning completion signal is given. This causes the operating value acquisition unit 210 to end the pulse control. The operating value acquisition unit 210 also acquires the transition time Δt21 from time t21 when the pulse control is started to time t22 when the positioning completion signal is given.

[0161] Similarly, during substrate processing, the operating value acquisition unit 210 pulse-controls the scan driver 620 to move the cleaning tool 640 from the standby position toward the processing position. Furthermore, the operating value acquisition unit 210 acquires the transition time of the cleaning tool 640 as a second operating value based on a positioning completion signal provided by the scan driver 620. The transition time of the cleaning tool 640 is the time from when the pulse control of the scan driver 620 starts to when the positioning completion signal is provided.

[0162] After substrate processing is completed, each of the cleaning tools 630 and 640 is returned from the processing position to the standby position. In the above example, the transition times of the cleaning tools 630 and 640 from the standby position to the processing position are the first and second operating values, respectively. However, the present invention is not limited to this. The transition times of the cleaning tools 630 and 640 from the processing position to the standby position may also be the first and second operating values, respectively.

[0163] 3 plots data points determined by pairs of transition times of the cleaning tool 630 and the cleaning tool 640 on a correlation graph each time the scan driving units 610 and 620 are pulse-controlled. The abnormality determination unit 220 also determines whether an abnormality has occurred based on the proportion of plotted data points that fall outside the allowable range R. If it is determined that an abnormality has occurred, it is assumed that an abnormality has occurred in an operating part related to the scan driving units 610 and 620. If the abnormality determination unit 220 determines that an abnormality has occurred, the notification unit 230 notifies the user of this.

[0164] 5 except that the transition times of the cleaners 630 and 640 are acquired in steps S1 and S2, respectively. Either step S1 or S2 may be executed first. When the scan driver 610 and the cleaner 630 and the scan driver 620 and the cleaner 640 are provided in separate processing units 110, steps S1 and S2 may be executed substantially simultaneously.

[0165] (3) Effects In the substrate processing apparatus 1 according to this embodiment, the transition times of the cleaning tools 630 and 640 are acquired as first and second operating values ​​by the operating value acquiring unit 210. The abnormality determining unit 220 determines whether an abnormality has occurred based on the correlation between the transition times of the cleaning tool 630 and the cleaning tool 640 acquired by the operating value acquiring unit 210. In this case, an abnormality in the substrate processing apparatus 1 can be detected early based on the correlation between the transition times of the cleaning tool 630 and the cleaning tool 640.

[0166] (4) Reference example In the reference example, the abnormality detection process may monitor the change over time of the transition time of the cleaner 630 or the cleaner 640, and determine that an abnormality has occurred if the transition time exceeds a predetermined allowable range. However, in the reference example, even if no abnormality has actually occurred, it may be determined that an abnormality has occurred because the transition time exceeds the predetermined allowable range. Therefore, in the reference example, it is difficult to accurately detect an abnormality.

[0167] <9> Eighth embodiment (1) Rotational support part In the eighth embodiment, an abnormality is detected in the spin holder included in each processing unit 110 as an operating part of the substrate processing section 100. Fig. 19 is a side view showing the configuration of the spin holder in the eighth embodiment. As shown in Fig. 19, the spin holder 700 includes a spin driver 710, a rotation shaft 720, and an adsorption section 730.

[0168] The spin drive unit 710 is provided at the bottom of the processing unit 110 in Figure 1. The rotation shaft 720 is provided to extend upward from the spin drive unit 710. The suction unit 730 is attached to the upper end of the rotation shaft 720 and holds the substrate W horizontally by suction. When the rotation shaft 720 is rotated by the spin drive unit 710, the suction unit 730 rotates around a vertical axis.

[0169] The spin driver 710 is provided with a torque sensor 711 and a temperature sensor 712. The torque sensor 711 detects the torque of the spin driver 710 and provides the detection result to the control unit 200. The temperature sensor 712 detects the temperature of the spin driver 710 and provides the detection result to the control unit 200. The torque detected in this example is expressed as a percentage [%] of the rated torque.

[0170] (2) Control Unit Fig. 20 is a functional block diagram showing the configuration of control unit 200. As shown in Fig. 20, control unit 200 in this embodiment further includes an operating value selection unit 240. The following describes the operation of control unit 200 in this embodiment, focusing on differences from control unit 200 in Fig. 3.

[0171] Figure 21 is a diagram showing changes in the rotation speed and torque of the spin driver 710 during substrate processing. The upper part of Figure 21 shows the change over time in the rotation speed of the spin driver 710 when one substrate W is processed. The change over time in the rotation speed of the spin driver 710 is determined by the substrate processing recipe. The lower part of Figure 21 shows the change over time in the torque of the spin driver 710 when one substrate W is processed, corresponding to the rotation speed of the spin driver 710.

[0172] 21, when the rotation speed of the spin driver 710 changes suddenly, the torque of the spin driver 710 becomes extremely large. Therefore, the operating value acquisition unit 210 acquires, based on the substrate processing recipe, the torque when the spin driver 710 is rotating at a predetermined constant rotation speed in part B of FIG. 21 from the torque sensor 711 as a first operating value. In addition, the operating value acquisition unit 210 acquires, from the temperature sensor 712, the temperature when the spin driver 710 is rotating at the above-mentioned constant rotation speed as a second operating value.

[0173] When the rotation speed of the spin driver 710 is substantially constant during substrate processing, all of the torque detected by the torque sensor 711 may be acquired as the first operating value. Similarly, when the rotation speed of the spin driver 710 is substantially constant during substrate processing, all of the temperatures detected by the temperature sensor 712 may be acquired as the second operating value.

[0174] FIG. 22 is a diagram showing the acquired torque and temperature. The upper part of FIG. 22 shows the time variation of the acquired torque. The lower part of FIG. 22 shows the time variation of the acquired temperature corresponding to the torque. FIG. 22 also shows whether the acquired temperature is equal to or higher than a predetermined reference temperature. If the temperature is equal to or higher than the reference temperature, it is displayed as "high," and if the temperature is lower than the reference temperature, it is displayed as "low."

[0175] 22, the torque is acquired when the spin drive unit 710 is rotating at a constant rotational speed, and therefore does not fluctuate extremely greatly, but rather fluctuates within a relatively limited range. However, the present inventors have conducted various experiments and conducted various studies, and have come to the following conclusions regarding the torque and temperature of the spin drive unit 710.

[0176] As shown in part C of FIG. K, the torque is relatively large immediately after the start of substrate processing. Similarly, as shown in part D of FIG. K, the torque is also relatively large when a relatively long time has passed since the previous torque was acquired. Furthermore, the temperature of the spin driver 710 is relatively low immediately after the start of substrate processing or when a relatively long time has passed since the previous torque was acquired. In other words, there is a correlation between torque and temperature, and even if the rotation speed of the spin driver 710 is constant, the torque is relatively large when the temperature of the spin driver 710 is relatively low.

[0177] Therefore, the operating value selection unit 240 selects a temperature equal to or higher than the reference temperature from among the temperatures acquired by the operating value acquisition unit 210. The operating value selection unit 240 also selects a torque corresponding to the selected temperature from among the torques acquired by the operating value acquisition unit 210. The abnormality determination unit 220 determines whether an abnormality has occurred based on a change in the torque selected by the operating value selection unit 240.

[0178] FIG. 23 is a diagram illustrating an example of a method for determining an abnormality. The horizontal axis of FIG. 23 indicates the day on which the torque was acquired, and the vertical axis indicates the acquired torque. As shown in FIG. 23, in this example, a box plot is created based on the torque acquired for each day, and the created box plots are arranged in chronological order. In addition, it is determined whether or not a line indicating a predetermined torque reference value (3% in the example of FIG. 23) passes through a box in the box plot. If the line indicating the torque reference value does not pass through the box in the box plot a predetermined number of times (a predetermined number of days in this example), it is determined that an abnormality has occurred.

[0179] The method of determining an abnormality is not limited to the above example. It is also possible to monitor the change over time of the torque selected by the operating value selection unit 240, and determine that an abnormality has occurred when the torque exceeds a predetermined allowable range a predetermined number of times or more. When the abnormality determination unit 220 determines that an abnormality has occurred, the notification unit 230 notifies the user of this.

[0180] (3) Abnormality detection processing Fig. 24 is a flowchart showing the abnormality detection process by the control unit 200 of Fig. 20. The abnormality detection process of Fig. 24 is performed by the CPU of the control unit 200 executing an abnormality detection program stored in memory. The abnormality detection process is performed daily in parallel with substrate processing. The abnormality detection process will be described below using the flowchart of Fig. 24 together with the control unit 200 of Fig. 20.

[0181] First, the operating value acquisition unit 210 acquires from the torque sensor 711 the torque of the spin driver 710 when the spin driver 710 is rotating at a predetermined constant rotation speed (step S11). The operating value acquisition unit 210 also acquires from the temperature sensor 712 the temperature corresponding to the torque acquired in step S1 (step S12). Steps S11 and S12 are performed substantially simultaneously during processing of the rotating substrate W based on the substrate processing recipe.

[0182] Next, the operating value selection unit 240 selects a temperature equal to or higher than the reference temperature from the temperatures acquired in step S12 (step S13). Subsequently, the operating value selection unit 240 selects a torque corresponding to the temperature selected in step S13 from the torques acquired in step S11 (step S14).

[0183] Thereafter, the abnormality determination unit 220 determines whether or not the processing of all the substrates to be processed has been completed (step S15). If the processing of all the substrates to be processed has not been completed, the abnormality determination unit 220 returns to step S11. Steps S11 to S15 are repeated until the processing of all the substrates to be processed has been completed.

[0184] When processing of all the substrates to be processed has been completed, the abnormality determination unit 220 creates a box-and-whisker plot using the torque selected in step S14 (step S16). Next, the abnormality determination unit 220 arranges the box-and-whisker plot created in step S16 in chronological order together with box-and-whisker plots created up to the previous day (step S17).

[0185] Next, the abnormality determination unit 220 determines whether the line indicating the torque reference value passes through the box portion of the box-and-whisker plot arranged in step S17 for a predetermined number of days or more (step S18). If the line passes through the box portion of the box-and-whisker plot for a predetermined number of days or more, the abnormality determination unit 220 does not determine that an abnormality has occurred and terminates the abnormality detection process. If the line does not pass through the box portion of the box-and-whisker plot for a predetermined number of days or more, the abnormality determination unit 220 determines that an abnormality has occurred. In this case, the notification unit 230 notifies this fact (step S19) and terminates the abnormality detection process.

[0186] (4) Effects In the substrate processing apparatus 1 according to this embodiment, the torque of the spin driver 710 is acquired as a first operating value by the operating value acquisition unit 210. The temperature of the spin driver 710 is acquired as a second operating value by the operating value acquisition unit 210. Of the temperatures acquired by the operating value acquisition unit 210, temperatures equal to or higher than a reference temperature are selected by the operating value selection unit 240. Of the torques acquired by the operating value acquisition unit 210, the torque corresponding to the selected temperature is selected by the operating value selection unit 240.

[0187] The abnormality determination unit 220 determines whether an abnormality has occurred based on the time-series change in the torque selected by the operating value selection unit 240. In this case, whether an abnormality has occurred is determined based on the time-series change in the torque that satisfies a predetermined standard among the acquired torques, so that an abnormality in the substrate processing apparatus 1 can be detected easily and accurately.

[0188] Furthermore, the torque acquired as the first operating value is the torque when the spin driver 710 rotates at a constant rotation speed. Similarly, the temperature acquired as the second operating value is the temperature when the spin driver 710 rotates at a constant rotation speed. Therefore, an abnormality in the substrate processing apparatus 1 can be detected more accurately.

[0189] (5) Reference example As an anomaly detection process in the reference example, it is also possible to create the box-and-whisker diagram using the torques of all spin drive units 710 acquired by the operating value acquisition unit 210, regardless of the temperature of the spin drive units 710. In this configuration, if the line indicating the torque reference value does not pass through the box portion of the box-and-whisker diagram for a predetermined number of days or more, it is determined that an anomaly has occurred.

[0190] However, in the reference example, the temperature of the spin drive unit 710 is low, so the straight line indicating the torque reference value may not pass through the box in the box-and-whisker plot. That is, even if no abnormality actually occurs, it may be determined that an abnormality has occurred because the straight line indicating the torque reference value does not pass through the box in the box-and-whisker plot for a predetermined number of days or more. Therefore, in the reference example, it is difficult to accurately detect an abnormality.

[0191] <7> Correspondence between each component of the claims and each part of the embodiment Below, examples of correspondence between each component of the claims and each part of the embodiments will be described, but the present invention is not limited to the following examples. Various other elements having the configuration or function described in the claims can also be used as each component of the claims.

[0192] In the above embodiment, the substrate W is an example of a substrate, the substrate processing apparatus 1 is an example of a substrate processing apparatus, the operating value acquisition unit 210 is an example of an operating value acquisition unit, and the abnormality determination unit 220 is an example of an abnormality determination unit. The allowable range R is an example of an allowable range, the operating value selection unit 240 is an example of an operating value selection unit, and the control unit 200 is an example of a processing apparatus.

[0193] In the first embodiment, regulating valve 414 is an example of a first operating component or a first regulating valve, and regulating valve 424 is an example of a second operating component or a second regulating valve. Alternatively, in the first embodiment, regulating valve 414 or regulating valve 424 is an example of a first operating component or a regulating valve, and pressure gauge 402 is an example of a second operating component or a pressure gauge.

[0194] In the second to fifth embodiments, flow meter 313 is an example of a first operating component or a first flow meter, flow meter 323 is an example of a first operating component or a second flow meter, and concentration meter 364 is an example of a second operating component or a concentration meter. Mixing tank 350 is an example of a storage section, substrate processing section 100 is an example of a substrate processing section, mixing piping 330 is an example of a first flow path section, supply piping 360 is an example of a second flow path section, and circulation piping 370 is an example of a third flow path section.

[0195] In the sixth embodiment, the first chuck pin 520 is an example of a first operating part or a first chuck pin, and the second chuck pin 520 is an example of a second operating part or a second chuck pin. Alternatively, in the sixth embodiment, either chuck pin 520 is an example of a first operating part or a chuck pin, and the chuck driver 530 is an example of a second operating part or a chuck driver.

[0196] In the seventh embodiment, cleaning tool 630 is an example of a first operating part or a first processing tool, and cleaning tool 640 is an example of a second operating part or a second processing tool. In the eighth embodiment, spin drive 710 is an example of a spin drive, torque sensor 711 is an example of a first operating part or a torque sensor, and temperature sensor 712 is an example of a second operating part or a temperature sensor. [Explanation of symbols]

[0197] 1... substrate processing apparatus, 100... substrate processing section, 200... control section, 210... operating value acquisition section, 220... abnormality detection section, 230... notification section, 240... operating value selection section, 300... chemical liquid generation section, 301... undiluted liquid supply source, 302... dilution liquid supply source, 303... waste liquid tank, 304... gas supply source, 310... undiluted liquid supply section, 311, 321, 341, 411, 421... piping, 312 ,322,334,335,342,368,369,413,423...Shut-off valve,313,323,412,422...Flow meter,314,324,414,424...Adjusting valve,320...Dilution liquid supply section,330...Mixing piping,331,361...Main pipe,332,333,362,363...Branch pipe,340...Gas supply section,350...Mixing tank,360...Supply piping , 364... concentration meter, 365... heater, 366... ​​pump, 367... filter, 370, 401... circulation piping, 400, 600... processing liquid supply unit, 402... pressure gauge, 410... upper surface supply unit, 415, 425... nozzle, 420... lower surface supply unit, 500, 700... rotation holding unit, 510... spin chuck, 511, 720... spin drive unit, 512, 730... rotation axis, 513...Plate support member, 514...Spin plate, 520...Chuck pin, 521...Shaft portion, 522...Pin support portion, 523...Holding portion, 524, 531...Hall sensor, 530...Chuck driving portion, 610, 620...Scan driving portion, 630, 640...Cleaning tool, 710...Suction portion, 711...Torque sensor, 712...Temperature sensor, R...Tolerance range, W...Substrate

Claims

1. 1. A substrate processing apparatus including a first operative component and a second operative component for use in processing a substrate with a processing liquid, an operation value acquisition unit that acquires a first operation value of the first operating part and a second operation value of the second operating part; an abnormality determination unit that determines whether an abnormality has occurred based on a correlation between the first operating value and the second operating value acquired by the operating value acquisition unit.

2. 2. The substrate processing apparatus of claim 1, wherein the abnormality determination unit determines whether or not an abnormality has occurred based on a proportion of data points that exceed an acceptable range determined based on a correlation between the first operating value and the second operating value, among data points determined by a pair of the first operating value and the second operating value acquired by the operating value acquisition unit.

3. The substrate processing apparatus of claim 2 , wherein the tolerance range is defined so as to include a predetermined percentage of data points among data points determined by a pair of the first operating value and the second operating value previously acquired by the operating value acquisition unit before the substrate is processed.

4. 4. The substrate processing apparatus according to claim 1, wherein the abnormality determination unit determines whether or not an abnormality has occurred each time a predetermined number of substrates are processed or a predetermined time has elapsed.

5. the first operating component includes a first adjusting valve that adjusts a flow rate of a processing liquid supplied to the substrate based on a first pulse value; the second operating component includes a second adjusting valve that adjusts a flow rate of the processing liquid supplied to the substrate based on a second pulse value; the first operating value being the first pulse value applied to the first regulator valve; 5. The substrate processing apparatus according to claim 1, wherein the second operating value is the second pulse value applied to the second regulating valve.

6. the first operating component includes an adjusting valve that adjusts a flow rate of a processing liquid supplied to the substrate based on a pulse value; the second operating component includes a pressure gauge that detects a pressure of the processing liquid guided to the regulating valve; the first operating value being the pulse value applied to the regulator valve; 5. The substrate processing apparatus according to claim 1, wherein the second operating value is a pressure detected by the pressure gauge.

7. the first operating component includes a first flow meter and a second flow meter for detecting flow rates of the first processing liquid and the second processing liquid, respectively; the second operating component includes a concentration meter that detects a concentration of a mixed processing liquid generated by mixing the first processing liquid and the second processing liquid; the first operating value is a theoretical value of a concentration of the mixed treatment liquid calculated from a ratio of a flow rate of the first treatment liquid to a flow rate of the second treatment liquid detected by the first flow meter and the second flow meter, respectively; 5. The substrate processing apparatus according to claim 1, wherein the second operating value is an actual measurement value of the concentration of the mixed processing liquid detected by the concentration meter.

8. the substrate processing apparatus further includes a reservoir into which a mixed processing liquid obtained by mixing the first processing liquid and the second processing liquid flows; the first operating component includes a first flow meter and a second flow meter detecting flow rates of the first processing liquid and the second processing liquid, respectively; the second operating component includes a concentration meter that detects a concentration of the mixed treatment liquid flowing out of the storage portion; The mixed treatment liquid that has flowed into the storage section reaches the concentration meter within a first time period, the first operating value is a theoretical value of a concentration of the mixed processing liquid calculated from an integrated value of a flow rate of the first processing liquid and an integrated value of a flow rate of the second processing liquid detected by the first flow meter and the second flow meter, respectively, between a first time point and a second time point that is a second time after the first time point; The substrate processing apparatus of any one of claims 1 to 4, wherein the second operating value is a statistical value of the concentration of the mixed processing liquid detected by the concentration meter between a third point in time at which the first time has elapsed since the first point in time and a fourth point in time at which the first time has elapsed since the second point in time.

9. the first operating component includes a first flow meter and a second flow meter for detecting flow rates of the first processing liquid and the second processing liquid, respectively; the second operating component includes a concentration meter that detects a concentration of a mixed processing liquid generated by mixing the first processing liquid and the second processing liquid; a concentration prediction model is prepared by machine learning a relationship between a flow rate of the first treatment liquid, a flow rate of the second treatment liquid, and a concentration of the mixed treatment liquid between a first time point and a second time point that is a first time elapsed from the first time point, and a concentration of the mixed treatment liquid at a third time point that is a second time elapsed from the second time point; the first operating value is a predicted value of a concentration of the mixed processing liquid at a sixth time point that is a second time elapsed from the fifth time point, the predicted value being obtained by applying to the concentration prediction model a flow rate of the first processing liquid detected by the first flow meter, a flow rate of the second processing liquid detected by the second flow meter, and a concentration of the mixed processing liquid detected by the concentration meter, between a fourth time point and a fifth time point that is a first time elapsed from the fourth time point; 5. The substrate processing apparatus according to claim 1, wherein the second operating value is an actual measurement value of the concentration of the mixed processing liquid detected by the concentration meter at the sixth time point.

10. The substrate processing apparatus includes: a storage section for storing a mixed processing liquid obtained by mixing the first processing liquid and the second processing liquid; a substrate processing section for performing a process on a substrate using the mixed process; a first flow path portion that mixes the first processing liquid and the second processing liquid to generate the mixed processing liquid and guides the mixed processing liquid to the storage portion; a second flow path portion that guides the mixed processing liquid stored in the storage portion to the substrate processing portion; a third flow path portion that guides the unused mixed processing solution in the substrate processing unit to the storage portion, the first operating component includes a first flow meter and a second flow meter detecting flow rates of the first processing liquid and the second processing liquid, respectively; the second operating component includes a concentration meter that detects a concentration of the mixed treatment liquid flowing out of the storage portion; the mixed treatment liquid that has flowed into the storage section through the first flow path section reaches the concentration meter within a first time; the first operating value is a theoretical value of a concentration of the mixed treatment liquid stored in the storage portion at each time point, calculated from a volume of the mixed treatment liquid flowing into the storage portion through the first flow path portion, a volume of the mixed treatment liquid flowing out of the storage portion through the second flow path portion, and a volume of the mixed treatment liquid flowing into the storage portion through the third flow path portion, and a flow rate of the first treatment liquid and a flow rate of the second treatment liquid detected by the first flow meter and the second flow meter, respectively; The substrate processing apparatus of any one of claims 1 to 4, wherein the second operating value is an actual measurement value of a concentration of the mixed processing liquid detected by the concentration meter at a point when the first time has elapsed from a point when the mixed processing liquid flows into the storage section through the first flow path section.

11. the first operational component includes a first chuck pin that transitions between a first closed state in which the substrate is held and a first open state in which the substrate is not held; the second operating component includes a second chuck pin that transitions between a second closed state in which the substrate is held and a second open state in which the substrate is not held; the first operating value is a transition time of the first chuck pin between the first closed state and the first open state; 5. The substrate processing apparatus according to claim 1, wherein the second operating value is a transition time of the second chuck pin between the second closed state and the second open state.

12. the first operational component includes a chuck pin that transitions between a first closed state in which the substrate is held and a first open state in which the substrate is not held; the second operating component includes a chuck driver that transitions between a second closed state that transitions the chuck pin to the first closed state and a second open state that transitions the chuck pin to the first open state; the first operating value is a transition time of the chuck pin between the first closed state and the first open state; 5. The substrate processing apparatus according to claim 1, wherein the second operating value is a transition time of the chuck driver between the second closed state and the second open state.

13. the first operating component includes a first processing tool that transitions between a first standby position at which the substrate is not processed and a first processing position at which the substrate is processed; the second operating component includes a second processing tool that transitions between a second standby position in which the substrate is not processed and a second processing position in which the substrate is processed; the first operating value is a transition time of the first processing tool between the first standby position and the first processing position, 5. The substrate processing apparatus according to claim 1, wherein the second operating value is a transition time of the second processing tool between the second standby position and the second processing position.

14. an operation value selection unit that selects a second operation value that satisfies a predetermined criterion from among the second operation values ​​acquired by the operation value acquisition unit, and selects a first operation value that corresponds to the selected second operation value from among the first operation values ​​acquired by the operation value acquisition unit, The substrate processing apparatus according to claim 1 , wherein the abnormality determination section determines whether or not an abnormality has occurred based on a time-series change in the first operating value selected by the operating value selection section.

15. the first operating part includes a torque sensor that detects a torque of a spin drive unit; the second operating component includes a temperature sensor that detects a temperature of the spin drive unit; the first operating value is a torque of the spin drive unit detected by the torque sensor, The substrate processing apparatus of claim 14 , wherein the second operating value is a temperature of the spin drive detected by the temperature sensor.

16. the first operating value is a torque of the spin drive unit detected by the torque sensor when the spin drive unit rotates at a predetermined constant rotation speed, 16 . The substrate processing apparatus according to claim 15 , wherein the second operating value is a temperature of the spin driver detected by the temperature sensor when the spin driver rotates at the constant rotation speed.

17. 1. A method for detecting an abnormality in a substrate processing apparatus including a first operating component and a second operating component used in processing a substrate using a processing liquid, comprising: obtaining a first operational value of the first operational component and a second operational value of the second operational component that are correlated to each other; determining whether or not an abnormality has occurred based on the acquired first and second operation values.

18. An abnormality detection program executed by a processing device, the abnormality detection program detecting an abnormality in a substrate processing device including a first operating component and a second operating component used in processing a substrate using a processing liquid, obtaining a first operational value of the first operational component and a second operational value of the second operational component that are correlated with each other; A process of determining whether or not an abnormality has occurred based on the acquired first operation value and the acquired second operation value. An abnormality detection program to be executed by the processing device.

Images