TWI721314B - Abnormality detection device and abnormality detection method - Google Patents

Abstract

An abnormality detection device (102) detects an abnormality of a substrate processing apparatus (101). The substrate processing apparatus (101) performs specific processing on a substrate (W). The abnormality detection device (102) includes storage (123) and a controller (124). The storage stores therein a statistical reference range of variations obtained from a plurality of observation targets. The controller (124) obtains current variations from the observation targets and calculates a statistical abnormality degree of the obtained variations based on the reference range. The controller (124) determines whether or not to perform the specific processing by referencing the abnormality degree.

Description

Anomaly detection device and anomaly detection method

The present invention relates to an abnormality detection device and an abnormality detection method.

When some trouble (error) occurs in the substrate processing apparatus, the substrate processing apparatus generates an alarm (for example, refer to Patent Document 1). By generating an alarm, the user is notified that the use of the substrate processing apparatus (chamber) is prohibited. Typically, when any of the parameters of the substrate processing device exceeds a preset threshold, an alarm will be generated.

Generally speaking, the threshold value of each parameter is set so that the substrate processing apparatus can reliably apply a predetermined processing program to the substrate. In other words, the threshold is set so that Type II Error does not occur. That is, it is set so as not to miss the occurrence of errors. The parameters of the substrate processing device include, for example, the exhaust pressure of the chamber, the pressure in the chamber, the temperature in the chamber, the opening of the needle valve, the flow rate of the processing liquid, and the liquid temperature of the processing liquid. Furthermore, Type I Error is the error caused by the misdetection error.

[Prior Technical Literature] [Patent Literature]

[Patent Document 1] Japanese Patent Laid-Open No. 2008-004112

However, in the case where the threshold value is set so that the type 2 error does not occur, the type 1 error may be increased. Specifically, although it is actually in the state of an executable processing program, it is possible that a certain parameter value exceeds the threshold value and an alarm is generated. In other words, it is possible to detect an abnormality by mistake.

The present invention was made in view of the above-mentioned problems, and its object is to provide an abnormality detection device and an abnormality detection method that can reduce the possibility of erroneous detection of abnormalities.

The abnormality detection device of the present invention detects abnormality of the substrate processing device. The above-mentioned substrate processing apparatus executes a predetermined processing program for the substrate. The abnormality detection device described above includes a memory unit and a control unit. The storage unit stores the statistical reference range of fluctuation values obtained from a plurality of monitoring objects. The control unit obtains the variation value from the plurality of monitoring objects, and calculates the degree of statistical abnormality of the obtained variation value based on the reference range. The control unit refers to the degree of abnormality to determine whether the predetermined processing program can be executed.

In an embodiment, the storage unit stores the threshold value for the abnormality degree.

In an embodiment, the control unit determines whether the predetermined processing program can be executed based on whether the abnormality degree exceeds the threshold value.

In a certain embodiment, the said abnormality detection apparatus is equipped with the input part which an operator can operate. The input unit accepts an instruction to select one of a plurality of threshold values. The memory unit memorizes the selected threshold value.

In an embodiment, the above-mentioned substrate processing apparatus can execute a plurality of processing programs. The storage unit stores the reference range for each processing program. The control unit calculates the abnormality degree of each of the plurality of processing programs, and determines whether each of the plurality of processing programs can be executed.

In an embodiment, the monitoring target is different for each processing program.

In one embodiment, for each of the above-mentioned processing programs, the above-mentioned storage unit stores the threshold value for the above-mentioned abnormality degree.

In an embodiment, the control unit determines whether each of the plurality of processing procedures can be executed based on whether the degree of abnormality of each of the plurality of processing procedures exceeds the corresponding threshold value.

In a certain embodiment, the said abnormality detection apparatus is equipped with the input part which an operator can operate. The input unit accepts an instruction to select one of a plurality of threshold values for each of the processing procedures. The memory unit memorizes the selected threshold value.

In an embodiment, the control unit calculates the degree of abnormality based on an abnormality detection method or an outlier detection method.

In an embodiment, the storage unit stores a unit space as the reference range. The control unit calculates Mahalanobis distance as the degree of abnormality.

The abnormality detection method of the present invention is a method for detecting abnormality of a substrate processing device. The above-mentioned substrate processing apparatus executes a predetermined processing program on the substrate. The above-mentioned abnormality detection method includes a reference range acquisition step, an abnormality degree calculation step, and an abnormality determination step. In the above-mentioned reference range obtaining step, a statistical reference range of variation values obtained from a plurality of monitoring objects is obtained. In the abnormality degree calculation step, the variation value is obtained from the plurality of monitoring objects, and the statistical abnormality degree of the obtained variation value is calculated based on the reference range. In the above abnormality determination step, it is determined whether the above-mentioned predetermined processing program can be executed with reference to the above-mentioned abnormality degree.

In an embodiment, the above-mentioned abnormality detection method further includes a threshold value setting step of setting a threshold value for the above-mentioned abnormality degree.

In an embodiment, in the abnormality determination step, it is determined whether the predetermined processing program can be executed based on whether the abnormality degree exceeds the threshold value.

In an embodiment, in the above-mentioned threshold value setting step, a threshold value selected from a plurality of threshold values is set.

In an embodiment, the substrate processing apparatus can execute a plurality of processing programs. In the above-mentioned reference range obtaining step, the above-mentioned reference range is obtained for each of the above-mentioned processing procedures. In the abnormality degree calculation step, the abnormality degree of the processing program being executed by the substrate processing apparatus among the plurality of processing programs is calculated. In the abnormality determination step, it is determined whether or not the above-mentioned processing program which is executed by the above-mentioned substrate processing apparatus among the above-mentioned plural processing programs can be executed.

In an embodiment, the monitoring target is different for each processing program.

In an embodiment, the abnormality detection method further includes a threshold value setting step that sets the threshold value of the abnormality degree for each of the processing programs.

In an embodiment, in the abnormality determination step, whether the abnormality degree of the processing program being executed by the substrate processing apparatus exceeds the corresponding threshold value is used to determine whether the processing performed by the substrate processing apparatus can be executed. The above processing procedure.

In an embodiment, in the above threshold value setting step, for each of the above processing procedures, a threshold value selected from a plurality of threshold values is set.

In an embodiment, in the abnormality degree calculation step, the abnormality degree is calculated according to an abnormality detection method or an outlier detection method.

In an embodiment, in the reference range acquisition step, a unit space is acquired as the reference range. In the aforementioned abnormality degree calculation step, the Mahalanobis distance is calculated as the aforementioned abnormality degree.

According to the present invention, the possibility of false detection of abnormalities can be reduced.

1‧‧‧Rotating Chuck

2‧‧‧SC1 Supply Organization

3‧‧‧SC2 Supply Organization

4‧‧‧HF supply mechanism

5‧‧‧SPM Supply Organization

6‧‧‧Eluent supply mechanism

7‧‧‧ Chamber

7a‧‧‧The first chamber

7b‧‧‧The second chamber

7c‧‧‧Chamber 3

7d‧‧‧Chamber 4

7e‧‧‧The 5th chamber

11‧‧‧Rotation axis

12‧‧‧Rotating base

13‧‧‧Clamping member

14‧‧‧Drive device

15‧‧‧Rotation number detection sensor

21‧‧‧Nozzle 1

22‧‧‧The first supply pipe

23‧‧‧The first valve

24‧‧‧The first flow sensor

25‧‧‧The first liquid temperature sensor

31‧‧‧Nozzle 2

32‧‧‧Second supply pipe

33‧‧‧Second valve

34‧‧‧Second flow sensor

35‧‧‧The second liquid temperature sensor

41‧‧‧Nozzle 3

42‧‧‧3rd supply pipe

43‧‧‧3rd valve

44‧‧‧The third flow sensor

45‧‧‧The third liquid temperature sensor

51‧‧‧Nozzle 4

52‧‧‧4th supply pipe

53‧‧‧4th valve

54‧‧‧Fourth flow sensor

55‧‧‧4th liquid temperature sensor

61‧‧‧Nozzle 5

62‧‧‧Fifth supply pipe

63‧‧‧Fifth valve

64‧‧‧Fifth Flow Sensor

65‧‧‧The fifth liquid temperature sensor

71‧‧‧Temperature sensor in the chamber

72‧‧‧ Chamber pressure sensor

100‧‧‧Anomaly Detection System

101‧‧‧Substrate processing equipment

102‧‧‧Operating device (abnormal detection device)

111‧‧‧The first washing process

112‧‧‧Second washing process

113‧‧‧The third cleaning process

114‧‧‧Fourth Washing Process

115‧‧‧Fifth Washing Process

121‧‧‧Display

122‧‧‧Input part

123‧‧‧Memory Department

124‧‧‧Control Department

151‧‧‧The first processing program

152‧‧‧Second processing program

153‧‧‧The third processing program

154‧‧‧The fourth processing program

155‧‧‧Fifth processing program

601‧‧‧Threshold value setting screen

610‧‧‧Option button

611‧‧‧Project 1

612‧‧‧Project 2

613‧‧‧Project 3

614‧‧‧Project 4

615‧‧‧The first value setting column

616‧‧‧The second value setting column

620‧‧‧「OK」button

AX‧‧‧Rotation axis

W‧‧‧Substrate

Fig. 1 is a diagram showing an abnormality detection system according to Embodiment 1 of the present invention.

Fig. 2 is a diagram showing the structure of a substrate processing apparatus according to the first embodiment of the present invention.

Figures 3(a) to (e) are diagrams showing five washing processes in the first embodiment of the present invention.

Fig. 4 is a diagram showing the structure of the operating device of the first embodiment of the present invention.

Fig. 5 is a diagram showing the flow of previous processing executed by the operating device of the first embodiment of the present invention.

Fig. 6 is a diagram showing the threshold value setting screen in the first embodiment of the present invention.

Fig. 7 is a diagram showing an abnormality detection processing flow executed by the operating device of the first embodiment of the present invention.

8(a) to (e) are diagrams showing another example of the object for calculating the abnormality degree in the first embodiment of the present invention.

Fig. 9 is a diagram showing an abnormality detection system according to Embodiment 2 of the present invention.

Fig. 10 is a diagram showing the structure of a substrate processing apparatus according to Embodiment 2 of the present invention.

Hereinafter, embodiments of the abnormality detection device and abnormality detection method of the present invention will be described with reference to the drawings. However, the present invention is not limited to the following embodiments. In the figure, the same reference signs are attached to the same or equivalent parts without repetitive description.

[Embodiment 1]

Fig. 1 is a diagram showing an abnormality detection system 100 of this embodiment. As shown in FIG. 1, the abnormality detection system 100 includes a substrate processing device 101 and an operating device 102.

The substrate processing apparatus 101 executes a predetermined processing program for the substrate W. The operating device 102 operates the substrate processing device 101 according to instructions from the operator. The operating device 102 corresponds to the abnormality detection device of the present invention. In this embodiment, the operating device 102 detects an abnormality of the substrate processing device 101.

Next, referring to FIG. 2, the structure of the substrate processing apparatus 101 will be described. FIG. 2 is a diagram showing the structure of the substrate processing apparatus 101 of this embodiment. In this embodiment, the substrate processing apparatus 101 is a single-chip cleaning apparatus that cleans the substrates W one by one. In addition, in this embodiment, the substrate W is a semiconductor wafer.

As shown in FIG. 2, the substrate processing apparatus 101 includes: a spin chuck 1, an SC1 supply mechanism 2, an SC2 supply mechanism 3, an HF supply mechanism 4, an SPM supply mechanism 5, and a Rinse liquid supply mechanism 6. , The chamber 7, the chamber temperature sensor 71, and the chamber pressure sensor 72. The substrate processing apparatus 101 of this embodiment can supply five types of chemical solutions (SC1, SC2, HF, SPM, and rinsing solution) to the substrate W.

The rotating chuck 1 rotates the substrate W with the rotation axis AX of the rotating shaft 11 as the center. Specifically, the rotating chuck 1 includes a rotating shaft 11, a rotating base 12, a plurality of clamping members 13, a driving device 14, and a rotation number detection sensor 15.

The rotating shaft 11 supports the rotating base 12. The rotating base 12 is typically a disc-shaped flat plate. The plurality of clamping members 13 are arranged at intervals on the peripheral edge of the rotating base 12. The plurality of clamping members 13 cooperate with each other to clamp one substrate W. Specifically, the plurality of clamping members 13 clamp the substrate W in such a manner that the rotation axis AX of the rotation shaft 11 passes through the center of the substrate W.

The driving device 14 rotates the rotating shaft 11 about the rotation axis AX. As a result, the substrate W rotates around the rotation axis AX. The driving device 14 is typically a motor that can control the number of rotations.

The rotation number detection sensor 15 detects the rotation number of the rotating shaft 11. In other words, the rotation number detection sensor 15 detects the rotation number of the substrate W. The rotation number detection sensor 15 outputs a signal showing the detected rotation number. Specifically, the output of the rotation number detection sensor 15 displays the rotation number of the substrate W in a time series. In other words, the output of the rotation number detection sensor 15 displays the variation value of the rotation number of the substrate W. The rotation number detecting sensor 15 may be, for example, an optical rotary encoder.

Next, the SC1 supply mechanism 2, the SC2 supply mechanism 3, the HF supply mechanism 4, the SPM supply mechanism 5, and the eluent supply mechanism 6 will be described. However, the SC1 supply mechanism 2, the SC2 supply mechanism 3, the HF supply mechanism 4, the SPM supply mechanism 5, and the eluent supply mechanism 6 are almost the same in structure. Therefore, only the structure of the SC1 supply mechanism 2 will be described in detail. The structure of the liquid supply mechanism (the SC2 supply mechanism 3, the HF supply mechanism 4, the SPM supply mechanism 5, and the eluent supply mechanism 6) will only be described as different from the SC1 supply mechanism 2.

The SC1 supply mechanism 2 supplies the chemical solution SC1 to the rotating substrate W. The chemical liquid SC1 is a _{mixed liquid containing "NH 4} OH", "H ₂ O ₂ "and "H ₂ O". When the chemical solution SC1 is supplied to the substrate W, the particles adhering to the surface of the substrate W are removed. The SC1 supply mechanism 2 includes a first nozzle 21, a first supply pipe 22, a first valve 23, a first flow sensor 24, and a first liquid temperature sensor 25.

The first nozzle 21 discharges the medical solution SC1. Typically, the first nozzle 21 is a direct current nozzle that discharges the liquid medicine SC1 in a continuous flow state. The first nozzle 21 is arranged above the spin chuck 1 with its discharge port facing downward. The first nozzle 21 may be a fixed nozzle or a scanning nozzle. Specifically, the first nozzle 21 may be fixed at a predetermined position in the chamber 7, or the injection position of the liquid chemical SC1 may be moved between the center portion of the surface of the substrate W and the peripheral portion of the surface of the substrate W. Move within 7.

The first supply pipe 22 is connected to the first nozzle 21. The first supply pipe 22 supplies the chemical liquid SC1 to the first nozzle 21. The first valve 23 is interposed in the first supply pipe 22 and switches the supply of the chemical liquid SC1 to the first nozzle 21 and the stop of the supply of the chemical liquid SC1.

The first flow rate sensor 24 detects the flow rate of the medical solution SC1 flowing through the first supply pipe 22. The first flow sensor 24 outputs a signal indicating the detected flow. Specifically, the output of the first flow sensor 24 displays the flow rate of the liquid medicine SC1 in a time series. In other words, the output of the first flow sensor 24 shows the fluctuation value of the flow rate of the liquid medicine SC1.

The first liquid temperature sensor 25 detects the temperature (liquid temperature) of the chemical liquid SC1 flowing through the first supply pipe 22. The first liquid temperature sensor 25 outputs a signal indicating the detected liquid temperature. Specifically, the output of the first liquid temperature sensor 25 displays the liquid temperature of the chemical liquid SC1 in a time series. In other words, the output of the first liquid temperature sensor 25 shows the fluctuation value of the liquid temperature of the liquid medicine SC1.

The SC2 supply mechanism 3 supplies the chemical liquid SC2 to the rotating substrate W. The chemical liquid SC2 is a mixed liquid containing "HCl", "H ₂ O ₂ "and "H ₂ O". When the chemical solution SC2 is supplied to the substrate W, heavy metals (for example, Fe, Ni, Cr, Cu) adhering to the surface of the substrate W are removed. The SC2 supply mechanism 3 includes a second nozzle 31, a second supply pipe 32, a second valve 33, a second flow sensor 34, and a second liquid temperature sensor 35.

The second flow rate sensor 34 detects the flow rate of the liquid medicine SC2 flowing through the second supply pipe 32. The second flow sensor 34 outputs a signal indicating the detected flow. Specifically, the output of the second flow rate sensor 34 displays the flow rate of the liquid medicine SC2 in a time series. In other words, the output of the second flow sensor 34 shows the fluctuation value of the flow of the liquid medicine SC2.

The second liquid temperature sensor 35 detects the temperature (liquid temperature) of the chemical liquid SC2 flowing through the second supply pipe 32. The second liquid temperature sensor 35 outputs a signal indicating the detected liquid temperature. Specifically, the output of the second liquid temperature sensor 35 displays the liquid temperature of the liquid medicine SC2 in a time series. In other words, the output of the second liquid temperature sensor 35 shows the fluctuation value of the liquid temperature of the liquid medicine SC2.

The HF supply mechanism 4 supplies the chemical liquid HF (hydrofluoric acid) to the rotating substrate W. When the chemical liquid HF is supplied to the substrate W, the natural oxide film formed on the surface of the substrate W is removed. The HF supply mechanism 4 includes a third nozzle 41, a third supply pipe 42, a third valve 43, a third flow sensor 44, and a third liquid temperature sensor 45.

The third flow sensor 44 detects the flow rate of the chemical liquid HF flowing through the third supply pipe 42. The third flow sensor 44 outputs a signal showing the detected flow. Specifically, the output of the third flow sensor 44 displays the flow of the chemical liquid HF in a time series. In other words, the output of the third flow sensor 44 shows the fluctuation value of the flow rate of the chemical liquid HF.

The third liquid temperature sensor 45 detects the temperature (liquid temperature) of the chemical liquid HF flowing through the third supply pipe 42. The third liquid temperature sensor 45 outputs a signal indicating the detected liquid temperature. Specifically, the output of the third liquid temperature sensor 45 displays the liquid temperature of the chemical liquid HF in a time series. In other words, the output of the third liquid temperature sensor 45 shows the fluctuation value of the liquid temperature of the chemical liquid HF.

The SPM supply mechanism 5 supplies the chemical liquid SPM to the rotating substrate W. The chemical liquid SPM is a mixed liquid _{containing "H 2} SO ₄ "and "H ₂ O _{2 ".} When the chemical solution SPM is supplied to the substrate W, the organic matter adhering to the surface of the substrate W is removed. Specifically, the chemical solution SPM is used to peel off the resist film. The SPM supply mechanism 5 includes a fourth nozzle 51, a fourth supply pipe 52, a fourth valve 53, a fourth flow sensor 54, and a fourth liquid temperature sensor 55.

The fourth flow rate sensor 54 detects the flow rate of the chemical solution SPM flowing through the fourth supply pipe 52. The fourth flow sensor 54 outputs a signal showing the detected flow. Specifically, the output of the fourth flow sensor 54 displays the flow rate of the liquid medicine SPM in a time series. In other words, the output of the fourth flow sensor 54 shows the fluctuation value of the flow rate of the liquid medicine SPM.

The fourth liquid temperature sensor 55 detects the temperature (liquid temperature) of the chemical liquid SPM flowing through the fourth supply pipe 52. The fourth liquid temperature sensor 55 outputs a signal indicating the detected liquid temperature. Specifically, the output of the fourth liquid temperature sensor 55 displays the liquid temperature of the chemical liquid SPM in a time series. In other words, the output of the fourth liquid temperature sensor 55 shows the fluctuation value of the liquid temperature of the chemical liquid SPM.

The rinsing liquid supply mechanism 6 supplies the rinsing liquid to the rotating substrate W. Specifically, the rinsing liquid supply mechanism 6 supplies the rinsing liquid to the substrate W after other chemical liquids (SC1, SC2, HF, or SPM) are supplied to the substrate W. By supplying the rinse liquid to the substrate W, other chemical liquids are rinsed from the surface of the substrate W. The eluent is, for example, ultrapure water (deionized water), carbonated water, electrolyzed ionized water, hydrogen water, ozone water, ammonia water, or diluted hydrochloric acid water (for example, hydrochloric acid water with a concentration of about 10 ppm to 100 ppm). The eluent supply mechanism 6 includes a fifth nozzle 61, a fifth supply pipe 62, a fifth valve 63, a fifth flow sensor 64, and a fifth liquid temperature sensor 65.

The fifth flow sensor 64 detects the flow of the eluent flowing through the fifth supply pipe 62. The fifth flow sensor 64 outputs a signal showing the detected flow. Specifically, the output of the fifth flow sensor 64 displays the flow of the eluent in time series. In other words, the output of the fifth flow sensor 64 shows the fluctuation value of the flow rate of the eluent.

The fifth liquid temperature sensor 65 detects the temperature (liquid temperature) of the eluent flowing through the fifth supply pipe 62. The fifth liquid temperature sensor 65 outputs a signal indicating the detected liquid temperature. Specifically, the output of the fifth liquid temperature sensor 65 displays the liquid temperature of the eluent in time series. In other words, the output of the fifth liquid temperature sensor 65 shows the fluctuation value of the liquid temperature of the eluent.

Next, the chamber 7, the chamber temperature sensor 71, and the chamber pressure sensor 72 will be described. The chamber 7 accommodates the rotating chuck 1 and the first nozzle 21 to the fifth nozzle 61. The chamber 7 is a processing chamber partitioned by a partition wall, and the substrate processing apparatus 101 executes a cleaning process of the substrate W in the chamber 7.

The chamber temperature sensor 71 detects the temperature of the internal space of the chamber 7 and outputs a signal indicating the detected temperature. Specifically, the output of the temperature sensor 71 in the chamber displays the temperature of the inner space of the chamber 7 in a time series. In other words, the output of the temperature sensor 71 in the chamber shows the variation value of the temperature of the inner space of the chamber 7. Furthermore, in the following description, the temperature of the internal space of the chamber 7 may be described as the "chamber temperature".

The chamber pressure sensor 72 detects the pressure of the internal space of the chamber 7, and outputs a signal indicating the detected pressure. Specifically, the output of the pressure sensor 72 in the chamber displays the pressure of the inner space of the chamber 7 in a time series. In other words, the output of the pressure sensor 72 in the chamber shows the fluctuation value of the pressure in the internal space of the chamber 7. In addition, in the following description, the pressure of the internal space of the chamber 7 may be described as "pressure in the chamber".

In this embodiment, the operating device 102 described with reference to FIG. 1 monitors the "number of rotations of the substrate W", "the flow rate of SC1", "the liquid temperature of SC1", "the flow rate of SC2", and the descriptions described with reference to FIG. 2 SC2 liquid temperature", "HF flow rate", "HF liquid temperature", "SPM flow rate", "SPM liquid temperature", "eluent flow rate", "eluent liquid temperature", " "Temperature in the chamber" and "Pressure in the chamber". The operating device 102 detects the abnormality of the substrate processing device 101 based on the variation values obtained from the monitoring objects. Specifically, according to the number of rotation detection sensor 15, the first flow sensor 24, the first liquid temperature sensor 25, the second flow sensor 34, and the second liquid temperature sensor shown in FIG. 35. The third flow sensor 44, the third liquid temperature sensor 45, the fourth flow sensor 54, the fourth liquid temperature sensor 55, the fifth flow sensor 64, the fifth liquid temperature sensor The output (variation value) of the sensor 65, the temperature sensor 71 in the chamber, and the pressure sensor 72 in the chamber (hereinafter referred to as “sensors”) are used to detect the abnormality of the substrate processing apparatus 101.

Next, referring to FIGS. 3(a) to 3(e), the cleaning processing program executable by the substrate processing apparatus 101 will be described. The substrate processing apparatus 101 of this embodiment can execute five types of cleaning processing programs.

Fig. 3(a) to Fig. 3(e) are diagrams showing five washing treatment procedures of this embodiment. In detail, FIG. 3(a) shows the steps of the first washing processing program 111, FIG. 3(b) shows the steps of the second washing processing program 112, and FIG. 3(c) shows the steps of the third washing processing program 113 Steps, FIG. 3(d) shows the steps of the fourth washing processing program 114, and FIG. 3(e) shows the steps of the fifth washing processing program 115.

Specifically, FIGS. 3(a) to 3(e) show the sequence of supplying a plurality of chemical liquids to the substrate W in a time series. For example, as shown in FIG. 3(a), the substrate processing apparatus 101 that executes the first cleaning processing program 111 is in the order of "SC1", "eluent", "SC2", and "eluent". The liquid is supplied to the substrate W. Similarly, the substrate processing apparatus 101 that executes the second cleaning processing program 112 supplies each chemical solution to the substrate W in the order shown in FIG. 3(b). The substrate processing apparatus 101 that executes the third cleaning processing program 113 supplies each chemical solution to the substrate W in the order shown in FIG. 3(c). The substrate processing apparatus 101 that executes the fourth cleaning processing program 114 supplies each chemical solution to the substrate W in the order shown in FIG. 3(d). The substrate processing apparatus 101 that executes the fifth cleaning processing program 115 supplies each chemical solution to the substrate W in the order shown in FIG. 3(e).

In addition, as shown in FIGS. 3(a) to 3(e), the last steps of the first washing treatment program 111 to the fifth washing treatment program 115 are all drying steps. The drying step is a step of drying the substrate W. Typically, in the drying step, the substrate processing apparatus 101 performs spin drying processing. Specifically, the substrate processing apparatus 101 increases the rotation speed of the substrate W more than when the chemical solution is supplied. As a result, a large centrifugal force acts on the rinsing liquid attached to the substrate W, and the rinsing liquid is thrown away to the periphery of the substrate W. Thus, by performing the spin drying process, the rinse liquid is removed from the substrate W and the substrate W is dried.

In this embodiment, the operating device 102 described with reference to FIG. 1 detects an abnormality in each of the first washing processing program 111 to the fifth washing processing program 115. In other words, the target of the abnormality detected by the operating device 102 is each processing program of the first washing processing program 111 to the fifth washing processing program 115.

Next, the configuration of the operating device 102 will be described with reference to Figs. 1 to 4. FIG. 4 is a diagram showing the structure of the operating device 102. As shown in FIG. As shown in FIG. 4, the operating device 102 includes a display unit 121, an input unit 122, a storage unit 123, and a control unit 124.

The display unit 121 displays various screens. The display portion 121 is typically a display device such as a liquid crystal display device or an organic EL (electroluminescence) display device. In the present embodiment, when an abnormality is detected in the execution of any one of the first washing processing program 111 to the fifth washing processing program 115, the display unit 121 displays an alarm screen. The alarm screen contains a message to notify the operator of abnormal situations.

The input unit 122 is a user interface device for operators to operate. The input unit 122 inputs an instruction (control signal) corresponding to the operator's operation to the control unit 124. In addition, the input unit 122 inputs data corresponding to the operator's operation to the control unit 124. Typically, the input unit 122 has a keyboard and a mouse. Furthermore, the input unit 122 may also have a touch sensor. The touch sensor is superimposed on the display surface of the display part 121 to generate a signal showing the operator's touch operation on the display surface. The operator can input various instructions to the operating device 102 through touch operation.

In this embodiment, the operator can operate the input unit 122 to input (register or set) various information into the input field of the screen displayed on the display unit 121. In addition, the operator can operate the input unit 122 to cause the substrate processing apparatus 101 to execute one of the first cleaning processing program 111 to the fifth cleaning processing program 115.

The storage unit 123 is composed of, for example, HDD (Hard Disk Drive), RAM (Random Access Memory), and ROM (Read Only Memory). The storage unit 123 stores a recipe corresponding to each of the first washing processing program 111 to the fifth washing processing program 115. Each recipe represents necessary information for operating the substrate processing apparatus 101. Specifically, the recipe of the first washing processing program 111 shows the steps described with reference to Fig. 3(a). Similarly, the recipes of the second washing treatment program 112 to the fifth washing treatment program 115 show the steps described with reference to FIGS. 3(b) to 3(e).

Furthermore, the storage unit 123 stores the statistical reference range of the variation value obtained from the plurality of monitoring objects described with reference to FIGS. 1 and 2. Specifically, the storage unit 123 stores the reference range of each of the first washing processing program 111 to the fifth washing processing program 115. In addition, the storage unit 123 stores control programs and configuration information of various screens.

The control unit 124 is constituted by an arithmetic circuit such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). The control unit 124 controls the actions of each part of the operating device 102 according to the control program (computer program) stored in the memory unit 123. Furthermore, the control unit 124 controls the substrate processing apparatus 101. Specifically, the control unit 124 causes the substrate processing apparatus 101 to execute any one of the first cleaning processing program 111 to the fifth cleaning processing program 115 in accordance with an instruction from the operator. When causing the substrate processing apparatus 101 to execute the cleaning processing program, the control unit 124 refers to the recipe corresponding to the executed cleaning processing program.

In this embodiment, the control unit 124 determines whether each of the first washing processing program 111 to the fifth washing processing program 115 can be executed. Specifically, when an abnormality is detected during the execution of the washing processing program, the control unit 124 suspends (stops) the washing processing program. Furthermore, the control unit 124 decides not to permit execution of the suspended washing processing program, and causes the display unit 121 to display an alarm screen. The alarm screen contains a message to inform the operator that the execution of the suspended cleaning process is prohibited.

In detail, the control unit 124 obtains variation values from the plurality of monitoring objects described with reference to FIG. 2. Specifically, a signal indicating the variation value of each monitoring object is input to the control unit 124 from each sensor described with reference to FIG. 2. In this embodiment, the control unit 124 generates the time series data of the variation values described with reference to FIG. 2 based on the output of each sensor described with reference to FIG. 2. In other words, the control unit 124 generates a multivariate data group. For example, the control unit 124 captures the variation value from the output of each sensor at a predetermined time interval, thereby generating time series data. Or, the control unit 124 calculates the average value, differential value, or integral value of the output (variation value) of each sensor at predetermined time intervals, thereby generating time series data.

Furthermore, the control part 124 calculates the statistical abnormality degree of the fluctuation value (multivariate data group) acquired from the output of each sensor shown in FIG. 2 based on the reference range memorized by the memory part 123. Specifically, the control unit 124 calculates the degree of abnormality by a statistical method. The degree of abnormality indicates whether the statistics of the multivariate data group deviate from the reference range. The control unit 124 refers to the calculated abnormality degree to detect whether an abnormality has occurred. Typically, the degree of anomaly represents the distance from the origin of the multivariate data group.

In more detail, the control unit 124 calculates an abnormality degree for each of the first washing processing program 111 to the fifth washing processing program 115, and determines whether the calculated abnormality degree exceeds a preset threshold value. Whether each of the first washing processing program 111 to the fifth washing processing program 115 can be executed. In the following, the threshold for abnormality may be described as the "first threshold". The first threshold value is stored in the memory unit 123.

In this embodiment, the control unit 124 monitors different monitoring objects in each of the first washing treatment program 111 to the fifth washing treatment program 115 according to the difference of the chemical liquid used.

Next, referring to FIGS. 1 to 4, the monitoring targets of the first washing processing program 111 to the fifth washing processing program 115 will be specifically described.

When executing the first washing processing program 111 shown in FIG. 3(a), the control unit 124 selects the number of rotation detection sensor 15, the first flow sensor 24, and the first liquid temperature sensor shown in FIG. Device 25, second flow sensor 34, second liquid temperature sensor 35, fifth flow sensor 64, fifth liquid temperature sensor 65, chamber temperature sensor 71, and chamber pressure sensor The output of the device 72 obtains a variable value. That is, when the first cleaning processing program 111 is executed, according to the steps shown in FIG. 3(a), the number of rotations of the substrate W, the flow rate of SC1, the liquid temperature of SC1, the flow rate of SC2, the liquid temperature of SC2, The signal of the fluctuation value of each of the flow rate of the eluent, the temperature of the eluent, the temperature in the chamber, and the pressure in the chamber is input to the control unit 124. Furthermore, the control unit 124 generates a multivariate data group based on each variation value, and calculates the statistics of the multivariate data group (hereinafter referred to as "the first multivariate data group") based on the reference range of the first cleaning processing program 111 Sexual abnormality.

Similarly, when the second washing process program 112 shown in FIG. 3(b) is executed, the control unit 124 selects the number of rotation detection sensor 15, the first flow sensor 24, and the first liquid shown in FIG. Temperature sensor 25, second flow sensor 34, second liquid temperature sensor 35, third flow sensor 44, third liquid temperature sensor 45, fifth flow sensor 64, fifth The output of the liquid temperature sensor 65, the chamber temperature sensor 71, and the chamber pressure sensor 72 obtain variable values. That is, when the second cleaning process 112 is executed, the number of rotations of the substrate W, the flow rate of SC1, the liquid temperature of SC1, the flow rate of SC2, and the liquid temperature of SC2 will be displayed according to the steps shown in FIG. 3(b). The signal of the fluctuation value of each of the flow rate of HF, the liquid temperature of HF, the flow rate of the eluent, the temperature of the eluent, the temperature in the chamber and the pressure in the chamber is input to the control unit 124. Furthermore, the control unit 124 generates a multivariate data group based on each variation value, and calculates the statistics of the multivariate data group (hereinafter referred to as "the second multivariate data group") based on the reference range of the second cleaning processing program 112 Sexual abnormality.

In addition, when the third cleaning processing program 113 shown in FIG. 3(c) is executed, the control unit 124 detects the sensor 15, the first flow rate sensor 24, and the first liquid temperature from the rotation number detection sensor 15 shown in FIG. Sensor 25, second flow sensor 34, second liquid temperature sensor 35, third flow sensor 44, third liquid temperature sensor 45, fourth flow sensor 54, fourth liquid The outputs of the temperature sensor 55, the fifth flow sensor 64, the fifth liquid temperature sensor 65, the chamber temperature sensor 71, and the chamber pressure sensor 72 obtain variable values. That is, when the third cleaning processing program 113 is executed, the number of rotations of the substrate W, the flow rate of SC1, the liquid temperature of SC1, the flow rate of SC2, and the liquid temperature of SC2 will be displayed according to the steps shown in FIG. 3(c). The signals of the flow rate of HF, the liquid temperature of HF, the flow rate of SPM, the liquid temperature of SPM, the flow rate of eluent, the liquid temperature of eluent, the temperature of the chamber and the pressure of the chamber are input to the control unit. 124. Furthermore, the control unit 124 generates a multivariate data group based on each variation value, and calculates the statistics of the multivariate data group (hereinafter referred to as "the third multivariate data group") based on the reference range of the third cleaning processing program 113 Sexual abnormality.

In addition, when the fourth washing processing program 114 shown in FIG. 3(d) is executed, the control unit 124 detects the sensor 15, the first flow rate sensor 24, and the first liquid temperature from the rotation number detection sensor 15 shown in FIG. Sensor 25, second flow sensor 34, second liquid temperature sensor 35, third flow sensor 44, third liquid temperature sensor 45, fourth flow sensor 54, fourth liquid The outputs of the temperature sensor 55, the fifth flow sensor 64, the fifth liquid temperature sensor 65, the chamber temperature sensor 71, and the chamber pressure sensor 72 obtain variable values. That is, when the fourth cleaning processing program 114 is executed, the number of rotations of the substrate W, the flow rate of SC1, the liquid temperature of SC1, the flow rate of SC2, and the liquid temperature of SC2 will be displayed according to the steps shown in FIG. 3(d). The signals of the flow rate of HF, the liquid temperature of HF, the flow rate of SPM, the liquid temperature of SPM, the flow rate of the eluent, the temperature of the eluent, the temperature in the chamber, and the variation of the pressure in the chamber are input to the control unit 124. Furthermore, the control unit 124 generates a multivariate data group based on each variation value, and calculates the statistics of the multivariate data group (hereinafter referred to as "fourth multivariate data group") based on the reference range of the fourth cleaning processing program 114 Sexual abnormality.

In addition, when the fifth washing processing program 115 shown in FIG. 3(e) is executed, the control unit 124 detects the sensor 15, the first flow rate sensor 24, and the first liquid temperature from the rotation number detection sensor 15 shown in FIG. Sensor 25, fourth flow sensor 54, fourth liquid temperature sensor 55, fifth flow sensor 64, fifth liquid temperature sensor 65, chamber temperature sensor 71, and chamber pressure The output of the sensor 72 obtains a variable value. That is, when the fifth cleaning process 115 is executed, according to the steps shown in FIG. 3(e), the number of rotations of the substrate W, the flow rate of SC1, the liquid temperature of SC1, the flow rate of SPM, the liquid temperature of SPM, The signal of the fluctuation value of each of the flow rate of the eluent, the temperature of the eluent, the temperature in the chamber, and the pressure in the chamber is input to the control unit 124. Furthermore, the control unit 124 generates a multivariate data group based on each variation value, and calculates the statistics of the multivariate data group (hereinafter referred to as "the fifth multivariate data group") based on the reference range of the fifth cleaning processing program 115 Sexual abnormality.

Next, referring to FIGS. 1 to 4, the reference range of the first washing processing program 111 to the fifth washing processing program 115 will be specifically described. The control unit 124 obtains (calculates) the first cleaning treatment program 111 to the fifth cleaning treatment program by causing the normally operating substrate processing apparatus 101 to execute the first cleaning treatment program 111 to the fifth cleaning treatment program 115 Baseline range of 115.

In detail, the control unit 124 generates the first multivariable data group as a reference by causing the substrate processing apparatus 101 in normal operation to execute the first cleaning processing program 111. Furthermore, the control unit 124 calculates the range of the first multivariate data group distribution as a reference by a statistical method, and uses it as the reference range of the first cleaning processing program 111.

Similarly, the control unit 124 executes the second cleaning process 112 to the fifth cleaning process 115 by the normally operating substrate processing apparatus 101 to generate the second multivariate data group to the fifth multivariate data as a reference group. Furthermore, the control unit 124 calculates the distribution range of each of the second multivariate data group to the fifth multivariate data group as a reference by a statistical method, as the second cleaning processing program 112 to the fifth cleaning. The reference range of each of the net processing procedures 115.

Next, referring to FIG. 1 to FIG. 4, the operation device 102 will be further described. The control unit 124 specifies a monitoring target whose abnormality degree is increased based on the multivariate data group acquired during the execution of the cleaning processing program. Specifically, the control unit 124 calculates the SN ratio of the time-series data obtained from the fluctuation value of each monitoring object. When an abnormality is detected because the degree of abnormality exceeds the first threshold value, the control unit 124 refers to the data group of the SN ratio when the abnormality is detected, and determines from the SN ratio of each monitored object that the SN ratio exceeds the preset threshold value. Below, the threshold value for the SN ratio may be described as the "second threshold value". The second threshold value is stored in the memory unit 123. Since a monitoring target whose SN ratio exceeds the second threshold value may increase the degree of abnormality, the control unit 124 identifies a monitoring target whose SN ratio exceeds the second threshold value as a monitoring target that increases the abnormality degree.

Next, referring to FIGS. 1 to 7, the substrate processing apparatus 101 and the operating apparatus 102 will be further described. FIG. 5 is a diagram showing the flow of the previous processing executed by the operating device 102. FIG. 6 is a diagram showing the threshold value setting screen 601 of this embodiment.

The operator selects the execution of the pre-processing by operating the input unit 122 to start the pre-processing shown in FIG. 5. The operator operates the input unit 122 after the execution of the pre-processing is selected, and selects the cleaning processing program to be executed by the substrate processing apparatus 101 from the first cleaning processing program 111 to the fifth cleaning processing program 115 (step S501). In addition, after the operator selects the cleaning process program to be executed by the substrate processing apparatus 101, the operator operates the input unit 122 to instruct to execute the selected cleaning process program. At this time, the operator designates the number of substrates W (for example, 100) to be processed.

When the operator instructs the execution of the cleaning processing program, the control unit 124 obtains the reference range of the cleaning processing program selected by the operator (step S502). Specifically, the control unit 124 causes the substrate processing apparatus 101 to execute the cleaning processing program selected by the operator. Furthermore, the control unit 124 generates a multivariate data group as a reference based on the output of each sensor corresponding to the washing processing program (the washing processing program selected by the operator) being executed. As a result, the multivariable data group of the number of pieces of the specified substrate W is stored in the memory portion 123. When the cleaning process for the designated number of substrates W ends, the control unit 124 calculates the reference range of the cleaning process selected by the operator based on the multivariate data group stored in the memory 123.

In more detail, in this embodiment, the control unit 124 obtains the reference range based on a multidimensional statistical method, that is, an abnormality detection method or an outlier detection method. Specifically, the control unit 124 uses the Mahalanobis-Taguchi method (Mahalanobis-Taguchi method, Mahalanobis-Taguchi method) as an example of an abnormality detection method or an outlier detection method. The Bis-Taguchi method) or the MTA method (Mahalanobis-Taguchi Adjoint method) calculates the unit space (Mahalanobis-Taguchi Adjoint method) as the reference range. Specifically, data showing the inverse matrix of the correlation coefficient matrix or the cofactor matrix of the variance-covariance matrix is generated and used as the unit space. When the unit space is acquired, the control unit 124 causes the display unit 121 to display the threshold value setting screen 601 shown in FIG. 6 (step S503).

As shown in FIG. 6, the threshold value setting screen 601 displays an option button (Radio Button) 610, a first numerical value setting field 615, a second numerical value setting field 616, and an "OK" button 620. The threshold value setting screen 601 is used to set the first threshold value for the cleaning process program selected by the operator in step S501 shown in FIG. 5 (hereinafter, it is described as "selected cleaning process") The picture. Specifically, the threshold value setting screen 601 of this embodiment is a screen for setting the threshold value of the Mahalanobis distance. The "OK" button 620 is a button for confirming the information registered in the threshold setting screen 601. When the operator operates the input unit 122 and inputs an instruction to press the "OK" button 620, confirm registration in the threshold setting screen The information of 601 ends the processing shown in FIG. 5.

The option button 610 includes the first item 611 to the fourth item 614. The operator can operate the input unit 122 to select one of the first item 611 to the fourth item 614.

When the operator selects the third item 613 or the fourth item 614, the input of a value in the first numerical value setting field 615 or the second numerical value setting field 616 is permitted. The first numerical setting column 615 is a setting column for setting the significance level of the ^{x 2 value to an arbitrary value.} The second numerical value setting column 616 is a setting column for setting the threshold value (the first threshold value) of the abnormality degree (Mahalanobis distance) of the selected washing process to an arbitrary value. When the third item 613 or the fourth item 614 is selected, the operator operates the input unit 122 to input an arbitrary value into the first numerical value setting field 615 or the second numerical value setting field 616.

In the state where the first item 611 is selected, when the operator inputs an instruction to press the "OK" button 620, the control unit 124 generates and displays the multivariate data group used when obtaining the unit space of the selected cleaning process The x ² distribution data. The control unit 124 sets ^{the significance level of the x 2} value to a value of 5% as the threshold value (first threshold value) for the abnormality of the selected washing process.

In the state where the second item 612 is selected, when the operator inputs an instruction to press the "OK" button 620, the control unit 124 generates and displays the multivariate data group used when obtaining the unit space of the selected cleaning process The x ² distribution data. The control unit 124 sets ^{the significance level of the x 2} value to a value of 1% as the threshold value (first threshold value) of the abnormality for the selected washing process.

In the state where the third item 613 is selected, when the operator inputs an instruction to press the "OK" button 620, the control unit 124 generates and displays the multivariate data group used when obtaining the unit space of the selected cleaning process The x ² distribution data. The control unit 124 sets ^{the significance level of the x 2} value as the value of the input value of the first numerical setting column 615 as the threshold value (first threshold value) of the abnormality for the selected washing process.

In the state where the fourth item 614 is selected, when the operator inputs an instruction to press the "OK" button 620, the control unit 124 sets the input value of the second numerical setting field 616 as the abnormality degree for the selected washing process The threshold (the first threshold).

Above, with reference to FIGS. 5 and 6, the previous processing performed by the control unit 124 will be described. The operator causes the operating device 102 to execute the previous processing shown in FIG. 5 until the unit space (reference range) and the first threshold value of each of the first washing processing program 111 to the fifth washing processing program 115 are stored in the memory unit 123 until.

Next, referring to FIGS. 1 to 7, the abnormality detection processing executed by the operating device 102 will be described. FIG. 7 is a diagram showing the flow of an abnormality detection process executed by the operating device 102.

The abnormality detection processing shown in FIG. 7 is started by the operator operating the input unit 122 and selecting execution of the abnormality detection processing. After selecting the execution of the abnormality detection process, the operator operates the input unit 122 to select the cleaning process program to be executed by the substrate processing apparatus 101 from the first cleaning process program 111 to the fifth cleaning process program 115 (step S511). In addition, after selecting the cleaning processing program to be executed by the substrate processing apparatus 101, the operator operates the input unit 122 to instruct the execution of the selected cleaning processing program. At this time, the operator designates the number of substrates W to be processed.

When the operator instructs to execute the cleaning processing program, the control unit 124 repeats the processing from step S512 to step S514 until the cleaning processing program for the number of substrates W designated by the operator ends.

Specifically, the control unit 124 causes the substrate processing apparatus 101 to execute the cleaning processing program selected by the operator. Furthermore, the control unit 124 generates a multivariate data group based on the output of each sensor corresponding to the washing processing program (the washing processing program selected by the operator) being executed. Furthermore, the control unit 124 calculates the Mahalanobis distance MD based on the unit space of the washing processing program in execution as the abnormality degree of the washing processing program in execution (step S512).

When the Mahalanobis distance MD is calculated, the control unit 124 determines whether the Mahalanobis distance MD exceeds the first threshold value set in the threshold value setting screen 601 shown in FIG. 6 (step S513).

When it is determined that the Mahalanobis distance MD does not exceed the first threshold value (No in step S513), the control unit 124 determines whether the cleaning processing program for the number of substrates W designated by the operator has ended ( Step S514).

When it is determined that the cleaning processing program for the number of substrates W designated by the operator has not ended (No in step S514), the control unit 124 returns to step S512 and repeats the processing from step S512 to step S514.

When it is determined that the cleaning processing program for the number of substrates W designated by the operator has ended (Yes in step S514), the control unit 124 ends the abnormality detection processing.

In addition, when it is determined that the Mahalanobis distance MD exceeds the first threshold value (Yes in step S513), the control unit 124 suspends (stops) the washing processing program. Furthermore, the control unit 124 decides not to permit execution of the suspended washing processing program, and causes the display unit 121 to display an alarm screen (step S515). The alarm screen contains a message to inform the operator that the execution of the suspended cleaning process is prohibited.

Furthermore, after the washing process program is terminated, the control unit 124 specifies the monitoring target that increases the Mahalanobis distance MD (step S516). Specifically, the control unit 124 refers to the data group of the SN ratio when the Mahalanobis distance MD exceeds the first threshold value (when an abnormality is detected) to specify the monitoring target whose SN ratio exceeds the second threshold value, and As a surveillance target to increase the MD distance of Mahalanobis. Furthermore, the control unit 124 displays a screen for notifying the operator of the specific monitoring target on the display unit 121, and ends the abnormality detection process.

Furthermore, it is preferable that when the Mahalanobis distance MD (abnormality) is calculated, the resolution of the time series data obtained from the output of the sensor is increased according to the increase of the members constituting the multivariate data group. By improving the resolution, anomalies can be detected more accurately. It can also be that, for example, in the case where the change value is captured from the output of the sensor at a predetermined time interval, a period with a small number of members makes the time (time point) for capturing the change value wider. According to the increase in the number of members, the interval of the time (time point) for capturing the change value is gradually narrowed. Also, in the case where the average, differential, or integral value of the output (variation value) of each sensor is calculated every predetermined time interval, the same applies to the period when the number of members is small. The interval of time (time points) for taking the average value, differential value, or integral value is wide, and according to the increase in the number of members, the interval of time (time point) for obtaining the average value, differential value, or integral value gradually changes narrow.

Above, the first embodiment has been described. According to this embodiment, since it is not necessary to set the threshold value (first threshold value) for detecting abnormality of the processing program for each monitored object (parameter), the first type error can be reduced. In addition, the abnormality of the processing program is detected based on the statistical abnormality of the variation values (parameter values) obtained from a plurality of monitoring objects, thereby reducing the type 2 error. Therefore, the possibility of false detection of abnormalities can be reduced.

Furthermore, according to this embodiment, it is determined whether each of a plurality of washing processing programs (the first washing processing program 111 to the fifth washing processing program 115 shown in FIGS. 3(a) to 3(e)) can be executed Therefore, even if it is decided not to permit the execution of a certain cleaning process, other cleaning processes can still be executed. Therefore, the operation rate of the substrate processing apparatus 101 can be improved.

Furthermore, in the case of deciding not to permit the execution of a certain cleaning processing program, when the operator selects the cleaning processing program (step S511 in FIG. 7), the control unit 124 will notify the operator that the execution is not permitted The screen of the cleaning process is displayed on the display part 121.

In addition, in this embodiment, the substrate processing apparatus 101 has been executed for the five types of cleaning processing programs shown in FIGS. 3(a) to 3(e) (the first cleaning processing program 111 to the fifth cleaning processing program). The structure of 115) will be described, but it is sufficient as long as the types of the cleaning processing program executed by the substrate processing apparatus 101 are two or more types.

In addition, in the present embodiment, the abnormality detection process shown in FIG. 7 is executed after the step of displaying the alarm screen on the display unit 121 (step S515) to specify the monitoring target that increases the Mahalanobis distance MD (Step S516), but the order of Step S515 and Step S516 can be exchanged.

In addition, in the present embodiment, it is determined whether each of the first washing processing program 111 to the fifth washing processing program 115 can be executed, but the object (processing program) for determining whether the execution can be performed can be arbitrarily set. In other words, the object (processing program) for which the degree of abnormality is calculated can be arbitrarily set. Specifically, it is possible to arbitrarily set the multivariate data group generated in order to calculate the degree of abnormality.

For example, when detecting an abnormality in the third cleaning processing program 113 shown in FIG. 3(c), multivariate data corresponding to the second cleaning processing program 112 shown in FIG. 3(b) is generated Group (the second multivariate data group). Since the steps of the third cleaning processing program 113 shown in FIG. 3(c) include the steps of the second cleaning processing program 112 shown in FIG. 3(b), the abnormality degree is calculated based on the second multivariate data group Thus, the abnormality of the third cleaning processing program 113 can be detected.

In addition, for example, each of the first washing processing program 111 to the fifth washing processing program 115 except for the drying step (the last step) may be used as a target for calculating the degree of abnormality.

In addition, for example, the first processing program 151 to the fifth processing program 155 shown in FIG. 8(a) to FIG. 8(e) may be the target for calculating the abnormality degree. Figures 8(a) to 8(e) are diagrams showing other examples of objects for which the degree of abnormality is calculated. In detail, as shown in FIG. 8(a), the first processing program 151 is a processing program in which each chemical solution is supplied to the substrate W in the order of "SC1" and "eluent". Similarly, the second processing program 152 to the fourth processing program 154 are processing programs for supplying each chemical solution to the substrate W in the order shown in FIGS. 8(b) to 8(d). The fifth processing program 155 is a processing program for drying the substrate W after supplying the "rinsing liquid" to the substrate W.

For example, when an abnormality is detected when the first processing program 151 is executed, the control unit 124 decides not to permit execution of the washing processing program including the first processing program 151 (execution is prohibited). Specifically, since the first washing processing program 111 to the fifth washing processing program 115 shown in FIGS. 3(a) to 3(e) all include the first processing program 151 shown in FIG. 8(a), Therefore, when an abnormality is detected when the first processing program 151 is executed, execution of all the first washing processing program 111 to the fifth washing processing program 115 is prohibited.

[Embodiment 2]

Next, the second embodiment of the present invention will be described with reference to FIGS. 3 to 10. However, only the matters different from the first embodiment will be described, and the description of the same matters as the first embodiment will be omitted. The second embodiment is different from the first embodiment in that the substrate processing apparatus 101 includes a plurality of chambers. The substrate processing apparatus 101 of the second embodiment executes different cleaning processing procedures in each chamber.

FIG. 9 is a diagram showing the abnormality detection system 100 of this embodiment. As shown in Fig. 9, the substrate processing apparatus 101 of the present embodiment includes a first chamber 7a to a fifth chamber 7e. In addition, the substrate processing apparatus 101 of this embodiment is provided with a chamber temperature sensor 71 and a chamber pressure sensor 72 in each of the first chamber 7a to the fifth chamber 7e.

The substrate processing apparatus 101 executes the first cleaning processing program 111 in the first chamber 7a. Similarly, the substrate processing apparatus 101 executes the second cleaning processing program 112 to the fifth cleaning processing program 115 in the second chamber 7b to the fifth chamber 7e.

The substrate processing apparatus 101 transports the substrate W into one of the first chamber 7a to the fifth chamber 7e. The chamber to which the substrate W is transported corresponds to the cleaning process program selected from the first cleaning process program 111 to the fifth cleaning process program 115 by operating the input unit 122 of the operating device 102 (refer to FIG. 4) .

FIG. 10 is a diagram showing the structure of the substrate processing apparatus 101 of this embodiment. As shown in FIG. 10, the 1st chamber 7a accommodates the 1st nozzle 21, the 2nd nozzle 31, and the 5th nozzle 61. As shown in FIG. The second chamber 7b accommodates the first nozzle 21, the second nozzle 31, the third nozzle 41, and the fifth nozzle 61. The third chamber 7c accommodates the first nozzle 21, the second nozzle 31, the third nozzle 41, the fourth nozzle 51, and the fifth nozzle 61. The fourth chamber 7d accommodates the first nozzle 21, the second nozzle 31, the third nozzle 41, the fourth nozzle 51, and the fifth nozzle 61. The fifth chamber 7e houses the first nozzle 21, the third nozzle 41, and the fifth nozzle 61. In addition, although not shown in the figure, the first chamber 7a to the fifth chamber 7e respectively contain the rotating chuck 1 described with reference to FIG. 2.

The operating device 102 (control unit 124) of the second embodiment is the same as the operating device 102 of the first embodiment, which calculates a plurality of preset processing programs (for example, the first washing processing program 111 to the fifth washing processing program 115). ) And determine whether each of the preset multiple processing procedures can be executed. For example, in the case where the objects to be judged whether they can be executed are the first washing processing program 111 to the fifth washing processing program 115, and the abnormality of the first washing processing program 111 exceeds the corresponding first threshold value, the operating device 102 decides not to permit execution of the first washing processing program 111. Specifically, the operating device 102 decides not to permit the transfer of the substrate W to the first chamber 7a.

The second embodiment has been described above. According to the second embodiment, as in the first embodiment, since there is no need to set the threshold value (the first threshold value) for detecting abnormality of the processing program for each monitored object (parameter), the first type error can be made cut back. In addition, the abnormality of the processing program is detected based on the statistical abnormality of the variation values (parameter values) obtained from a plurality of monitoring objects, thereby reducing the type 2 error. Therefore, the possibility of false detection of abnormalities can be reduced.

Furthermore, according to the second embodiment, it is determined whether each of a plurality of washing processing programs can be executed. Therefore, even if it is determined not to permit execution of a certain washing processing program, other washing processing programs can still be executed. Specifically, even if it is determined that the execution of the first washing processing program 111 is not permitted, the second washing processing program 112 to the fifth washing processing program 115 can be executed. In other words, even if the loading of the substrate W into the first chamber 7a is prohibited, the substrate W can be loaded into the second chamber 7b to the fifth chamber 7e. Therefore, the operation rate of the substrate processing apparatus 101 can be improved.

Furthermore, in the present embodiment, the substrate processing apparatus 101 that executes the first cleaning processing program 111 to the fifth cleaning processing program 115 in the first chamber 7a to the fifth chamber 7e has been described, and is referred to as the plural An example of the substrate processing apparatus 101 that executes different processes in two chambers, but the plurality of processing programs executed by the substrate processing apparatus 101 is not particularly limited. For example, the substrate processing apparatus 101 may include a chamber for performing an etching process for a semiconductor wafer, a chamber for performing a peeling process for peeling a resist film from a semiconductor wafer, and a cleaning process for cleaning the semiconductor wafer. The chamber.

Above, the embodiments of the present invention have been described with reference to the drawings. However, the present invention is not limited to the above-mentioned embodiment, and the present invention can be implemented in various aspects without departing from the scope thereof.

For example, in the embodiment of the present invention, the abnormality is detected based on whether the abnormality degree exceeds the first threshold value, but the abnormality may be detected based on whether the abnormality degree exceeds the reference range. For example, when the Mahalanobis distance is calculated as the anomaly degree, it can also be based on whether the value of the Mahalanobis distance exceeds "1", in other words, whether the Mahalanobis distance exceeds Unit space, while detecting anomalies. Specifically, it may be that when the value of the Mahalanobis distance exceeds "1", an abnormality is detected.

In addition, in the embodiment of the present invention, the clamp-type chuck that clamps the substrate W has been described as the structure for holding the substrate W, but a vacuum-type chuck may also be used as the structure for holding the substrate W. .

In addition, in the embodiment of the present invention, the operator is notified of the alarm by displaying the alarm screen on the display unit 121, but the alarm may also be notified to the operator by sound. In this case, the operating device 102 includes a speaker.

In addition, in the embodiment of the present invention, the form in which the substrate W is a semiconductor wafer has been described, but the substrate W is not limited to a semiconductor wafer. The substrate W can be a glass substrate for a photomask, a glass substrate for a liquid crystal display device, a substrate for a flat panel display such as an organic EL display, a substrate for an optical disk, a substrate for a magnetic disk, or a substrate for a magneto-optical disk.

In addition, in the embodiment of the present invention, the structure in which the substrate processing apparatus 101 executes the first cleaning processing program 111 to the fifth cleaning processing program 115 shown in FIGS. 3(a) to 3(e) has been described. However, the substrate processing apparatus 101 may also perform other cleaning processing procedures.

In addition, in the embodiment of the present invention, the structure of calculating the abnormality degree (Mahalanobis distance) by the MT method or the MTA method has been described, but the method for calculating the abnormality degree is only available by The method of detecting abnormalities (outliers) by multivariate analysis (abnormal detection method or outlier detection method) is not particularly limited. For example, a distance-based method, or One Class Support Vector Machine (One Class Support Vector Machine) can be used as a method for calculating the abnormality degree.

In addition, in the embodiment of the present invention, the substrate processing apparatus 101 executes a plurality of processing procedures, but the present invention can also be applied to the substrate processing apparatus 101 that executes one processing procedure.

(Industrial availability)

The present invention is useful for abnormal detection of substrate processing equipment.

100‧‧‧Anomaly Detection System

101‧‧‧Substrate processing equipment

102‧‧‧Operating device (abnormal detection device)

121‧‧‧Display

122‧‧‧Input part

123‧‧‧Memory Department

124‧‧‧Control Department

Claims (24)

An abnormality detection device that detects abnormalities in a substrate processing device that executes a predetermined processing program for a substrate; it is provided with: a memory unit that stores the variation values obtained from each of a plurality of monitoring objects in the predetermined processing program A statistical reference range; and a control unit that obtains the above-mentioned variation value from each of the plurality of monitoring objects in the above-mentioned predetermined processing program, and calculates the statistical abnormality of the obtained variation value according to the above-mentioned reference range; The predetermined processing program includes a first processing step and a second processing step that is different from the first processing step. The plurality of monitoring objects includes the first monitoring object that is monitored during the execution of the first processing step, and the For the second monitoring object to be monitored in the second processing step, the second monitoring object is different from the first monitoring object, and the control unit refers to the abnormality degree to determine whether the predetermined processing program can be executed. The abnormality detection device of claim 1, wherein the liquid medicine supplied in the first processing step is different from the liquid medicine supplied in the second processing step. The abnormality detection device of claim 1 or 2, wherein the storage unit stores the threshold value for the abnormality degree. For example, the abnormality detection device of claim 3, wherein the control unit determines whether the predetermined processing procedure can be executed based on whether the abnormality degree exceeds the threshold value. For example, the abnormality detection device of claim 3, which has an input unit for the operator to operate, and the input unit accepts an instruction to select one of a plurality of threshold values, The memory unit memorizes the selected threshold value. The abnormality detection device of claim 1 or 2, wherein the substrate processing device can execute a plurality of processing programs, the storage unit stores the reference range for each processing program, and the control unit calculates each of the plurality of processing programs According to the above-mentioned abnormality degree, it is judged whether each of the above-mentioned plural processing procedures can be executed. Such as the abnormality detection device of claim 6, wherein the above-mentioned monitoring object is different in each of the above-mentioned processing procedures. Such as the abnormality detection device of claim 6, wherein, for each of the processing procedures, the storage unit stores the threshold value for the abnormality degree. For example, the abnormality detection device of claim 8, wherein the control unit determines whether each of the plurality of processing procedures can be executed by whether the degree of abnormality of each of the plurality of processing procedures exceeds the corresponding threshold value. For example, the anomaly detection device of claim 8, which is provided with an input unit for an operator to operate, the input unit accepts an instruction to select one of a plurality of threshold values for each of the processing procedures, and the memory unit stores Select the above threshold. The abnormality detection device of claim 1 or 2, wherein the control unit calculates the abnormality degree based on an abnormality detection method or an outlier detection method. An abnormality detection device according to claim 1 or 2, wherein the storage unit stores the unit space as the reference range, and the control unit calculates the Mahalanobis distance as the abnormality degree. An anomaly detection method, which detects the execution of a predetermined processing program for the substrate The abnormality of the substrate processing apparatus; including: a reference range obtaining step, which obtains the statistical reference range of the variation value obtained from each of the plurality of monitoring objects in the above-mentioned predetermined processing program; the abnormal degree calculation step, which is Each of the plurality of monitoring objects in the predetermined processing program obtains the above-mentioned variation value, and calculates the statistical abnormality degree of the obtained variation value based on the above-mentioned reference range; and an abnormality determination step, which determines with reference to the above-mentioned abnormality degree Can the above-mentioned predetermined processing procedure be executed; the above-mentioned predetermined processing procedure includes a first processing step and a second processing step that is different from the above-mentioned first processing step, and the plurality of monitoring objects include those monitored during the execution of the above-mentioned first processing step The first monitoring target and the second monitoring target that is monitored when the second processing step is executed, the second monitoring target is different from the first monitoring target. The abnormality detection method of claim 13, wherein the liquid medicine supplied in the first processing step is different from the liquid medicine supplied in the second processing step. For example, the abnormality detection method of claim 13 or 14, which further includes a threshold setting step of setting the threshold for the above-mentioned abnormality. For example, the abnormality detection method of claim 15, wherein, in the abnormality determination step, it is determined whether the above-mentioned predetermined processing procedure can be executed according to whether the abnormality degree exceeds the above-mentioned threshold value. Such as the abnormality detection method of claim 15, wherein in the above threshold setting step, a threshold value selected from a plurality of threshold values is set. Such as the abnormality detection method of claim 13 or 14, wherein the above-mentioned substrate processing apparatus can execute a plurality of processing programs, In the above-mentioned reference range obtaining step, the above-mentioned reference range is obtained for each of the above-mentioned processing programs, and in the above-mentioned abnormality degree calculating step, the above-mentioned abnormality of the above-mentioned processing program being executed by the above-mentioned substrate processing apparatus is calculated in the above-mentioned abnormality degree calculation step In the above abnormality determination step, it is determined whether the above-mentioned processing program in execution by the above-mentioned substrate processing apparatus among the above-mentioned plural processing programs can be executed. For example, the abnormality detection method of claim 18, wherein the monitoring object is different in each of the processing procedures. For example, the abnormality detection method of claim 18, which further includes a threshold setting step, and the threshold setting step sets a threshold for the abnormality degree for each of the above-mentioned processing procedures. For example, the abnormality detection method of claim 20, wherein, in the abnormality determination step, whether the abnormality degree of the processing program being executed by the substrate processing apparatus exceeds the corresponding threshold value is used to determine whether the execution can be performed by the above-mentioned threshold value. The above-mentioned processing program in the execution of the substrate processing apparatus. Such as the abnormality detection method of claim 20, wherein, in the above threshold setting step, for each of the above processing procedures, a threshold value selected from a plurality of threshold values is set. The abnormality detection method of claim 13 or 14, wherein, in the abnormality degree calculation step, the abnormality degree is calculated according to an abnormality detection method or an outlier detection method. The abnormality detection method of claim 13 or 14, wherein in the reference range obtaining step, the unit space is obtained as the reference range, and in the abnormality degree calculation step, the Mahalanobis distance is calculated as the abnormality degree.

Images