JP6973544B2 - Status determination device, status determination method, and status determination program - Google Patents

Description

The present disclosure relates to a state determination device, a state determination method, and a state determination program.

Conventionally, a state determination device that provides an operator with useful information for identifying a faulty part in a work machine has been known (see, for example, Patent Document 1).

Japanese Unexamined Patent Publication No. 2013-199804

When the occurrence of a failure is predicted in the processing device, it is determined that the state of the processing device is abnormal. If it is determined that the condition of the processing equipment is abnormal, the processing equipment is stopped and inspected. If the judgment is incorrect, opportunity loss occurs due to unnecessary stoppage of the processing equipment. It is required to improve the accuracy of determining the state of the processing device so that the frequency of unnecessarily stopping the processing device can be reduced.

Therefore, an object of the present disclosure is to propose a state determination device, a state determination method, and a state determination program capable of improving the state determination accuracy of the processing apparatus.

An embodiment of the present disclosure that solves the above problems is as follows.
[1] A control unit for determining the state of the processing apparatus is provided.
The control unit
The feature amount of each of the plurality of data items representing the state of the processing apparatus is acquired, and the feature amount is acquired.
In a unit space representing the characteristics of a lot group normally processed by the processing apparatus, which is generated based on the cause data item that causes the processing apparatus to stop in a known failure mode among the plurality of data items. Calculate the Mahalanobis distance of the feature amount of the cause data item,
A state determination device that outputs a result of determining that the state of the processing device is an abnormal state based on a known mode when the Mahalanobis distance is equal to or greater than a threshold value set based on the unit space.
[2] The unit space includes at least a first unit space generated based on the first cause data item and a second unit space generated based on the second cause data item.
At least a part of the data items included in the first cause data item is not included in the second cause data item.
At least a part of the data items included in the second cause data item is not included in the first cause data item.
The control unit
When the Mahalanobis distance calculated in the first unit space becomes equal to or greater than the first threshold value, it is determined that the processing apparatus is in the first abnormal state.
The state determination device according to the above [1], wherein when the Mahalanobis distance calculated in the second unit space becomes equal to or larger than the second threshold value, it is determined that the processing device is in the second abnormal state.
[3] The control unit is
When it is not determined that the state of the processing apparatus is an abnormal state based on the known mode, the Mahalanobis distance of the feature amount of the plurality of data items is calculated in the unit space generated based on the plurality of data items. Calculate and
When the Mahalanobis distance is equal to or greater than the cause unknown threshold value, a data item having an MD contribution degree indicating the magnitude of the influence on the Mahalanobis distance is determined as a cause candidate item and the cause candidate item is selected. The state determination device according to the above [1] or [2], which outputs the data.
[4] The control unit is
The feature quantities of a plurality of data items obtained for each of the plurality of lots processed by the processing apparatus from the start of operation to the stop of the operation in the past predetermined period are acquired.
The plurality of lots are divided into lots within the unit space and lots outside the unit space.
The unit space is generated based on the feature amount of the lot in the unit space, and the unit space is generated.
The Mahalanobis distance of the feature amount of the lot outside the unit space is calculated in the unit space.
The state determination device according to any one of the above [1] to [3], wherein the threshold value is set to a value larger than the Mahalanobis distance of the feature amount of the lot outside the unit space.
[5] In the control unit, the difference between the Mahalanobis distance of the feature amount of the lot outside the unit space calculated in the unit space and the Mahalanobis distance of the feature amount of the lot inside the unit space calculated in the unit space is a predetermined value. The state determination device according to the above [4], which separates the lot in the unit space and the lot outside the unit space so as described above.
[6] A step in which the state determination device for determining the state of the processing device acquires a feature amount of each of a plurality of data items representing the state of the processing device.
Characteristics of a lot group normally processed by the processing device, which is generated based on the cause data item that causes the processing device to stop in a known failure mode among the plurality of data items. In the unit space representing the above, the step of calculating the Mahalanobis distance of the feature amount of the cause data item and
The state determination device includes a step of outputting a result of determining that the state of the processing device is an abnormal state based on a known mode when the Mahalanobis distance is equal to or more than a threshold value set based on the unit space. Status judgment method.
[7] To the processor of the state determination device that determines the state of the processing device,
A step of acquiring the feature amount of each of a plurality of data items representing the state of the processing apparatus, and
In a unit space representing the characteristics of a lot group normally processed by the processing apparatus, which is generated based on the cause data item that causes the processing apparatus to stop in a known failure mode among the plurality of data items. The step of calculating the Mahalanobis distance of the feature amount of the cause data item and
A state determination program for executing a step of outputting a result of determining that the state of the processing apparatus is an abnormal state based on a known mode when the Mahalanobis distance is equal to or greater than a threshold value set based on the unit space.

According to one embodiment of the present disclosure, the accuracy of determining the state of the processing apparatus can be improved.

It is a block diagram which shows the structural example of the state determination system which concerns on one Embodiment. It is a figure which shows the structural example of the wire saw apparatus as a processing apparatus. It is a table which shows an example of the data item obtained from a wire saw device. It is a graph which shows an example of MD of each lot calculated in the unit space based on the cause data item. It is a graph which shows an example of MD of each lot calculated in the unit space which concerns on a comparative example. It is a flowchart which shows the procedure example of the state determination method which concerns on one Embodiment. It is a flowchart which shows an example of the subroutine processing which generates a unit space.

(Outline of the state determination system 1 according to one embodiment)
The state determination system 1 (see FIG. 1) or the state determination device 50 (see FIG. 1) according to the embodiment of the present disclosure is a processing device 10 (see FIG. 1 or FIG. 2) installed in a factory or the like that manufactures a product. Judge the state of. The processing apparatus 10 processes the received member in at least a part of the process of manufacturing the product, and dispenses it as a processed product.

The processing apparatus 10 may break down and stop during processing. In this case, the processed product that was being processed becomes a defective product. The occurrence of defective products results in factory loss. Further, the man-hours required for the restoration work of the processing apparatus 10 are larger than the man-hours required for the maintenance work of the processing apparatus 10. Therefore, a failure during processing of the processing apparatus 10 increases the loss of the factory.

The state determination system 1 or the state determination device 50 according to the embodiment of the present disclosure determines the possibility of failure before the processing device 10 fails during processing, and prompts the stopping or maintenance work of the processing device 10. By doing so, the loss caused by the processing apparatus 10 can be reduced.

Hereinafter, a configuration example of the state determination system 1 and the state determination device 50 according to the embodiment will be described.

(System configuration example)
As shown in FIG. 1, the state determination system 1 according to the embodiment includes a state determination device 50 and a sensor 60. The sensor 60 measures and outputs various data regarding the state of the processing apparatus 10.

The state determination device 50 includes a control unit 51, an output unit 53, and an input unit 54. The control unit 51 provides control and processing capacity for executing various functions of the state determination device 50. As will be described later, the control unit 51 determines whether the state of the processing apparatus 10 is an abnormal state.

The control unit 51 may include at least one processor. The processor can execute a program that realizes various functions of the control unit 51. The processor may be realized as a single integrated circuit. The integrated circuit is also referred to as an IC (Integrated Circuit). The processor may be realized as a plurality of communicably connected integrated circuits and discrete circuits. The processor may be implemented on the basis of various other known techniques.

The control unit 51 may include a storage unit. The storage unit may include an electromagnetic storage medium such as a magnetic disk, or may include a memory such as a semiconductor memory or a magnetic memory. The storage unit may include a non-temporary computer-readable medium. The storage unit stores various information and programs executed by the control unit 51. The storage unit may function as a work memory of the control unit 51. At least a part of the storage unit may be configured as a separate body from the control unit 51.

The control unit 51 acquires measurement data from the sensor 60. The control unit 51 may acquire measurement data from the sensor 60 based on a standard such as RS485. The control unit 51 may be connected to the sensor 60 via a communication interface such as a LAN (Local Area Network). The control unit 51 is not limited to the above example, and may be connected to the sensor 60 by various methods.

The output unit 53 outputs the information acquired from the control unit 51. The output unit 53 may output so as to notify the operator of the processing apparatus 10 or the person in charge of maintenance of the information. The output unit 53 may include a display device. The display device may include, for example, a liquid crystal display, an organic EL (Electroluminescence) display, an inorganic EL display, and the like, but is not limited to these, and may include other devices. The output unit 53 may display the information acquired from the control unit 51 on the display device as characters, images, or the like, and notify the information to the surroundings.

The output unit 53 may include a light source such as an LED (Light Emission Diode) or a halogen lamp. The output unit 53 may notify the information to the operators or maintenance personnel in the vicinity by turning on or blinking the light source based on the information acquired from the control unit 51. The output unit 53 may include a buzzer such as a piezoelectric buzzer or an electromagnetic buzzer, or a speaker that emits a predetermined sound. The output unit 53 may notify the surrounding operator, maintenance person, or the like of the information by sounding a buzzer or generating a voice from a speaker based on the information acquired from the control unit 51.

The output unit 53 may output information to the processing apparatus 10. The output unit 53 may include a communication module so as to be communicably connected to the processing device 10.

The input unit 54 includes an input device for receiving an operation or input by an operator who manages the state determination device 50, a maintenance person, or the like. The input device may include, for example, a keyboard or physical keys, or may include a pointing device such as a touch panel or touch sensor or a mouse. When the input device is a touch panel or a touch sensor, it may be integrally configured with the display of the output unit 53. The input device may include, for example, a microphone or the like that accepts voice input. The input unit 54 is not limited to these examples as an input device, and may include various other devices.

(Specific example of processing device 10: wire saw device)
In this embodiment, it is assumed that the processing device 10 is a wire saw device. As shown in FIG. 2, the processing device 10 as a wire saw device includes a wire group 16 in which a wire 12 is stretched between a plurality of rollers 14 so as to be able to travel in parallel and reciprocate. The processing apparatus 10 includes a work holding mechanism 18 that holds the work W and moves the work W in a direction of pushing the work W with respect to the wire group 16. The processing apparatus 10 includes a pair of nozzles 20 for supplying the slurry to the region where the work W is pushed in the wire group 16. The processing apparatus 10 cuts the work W by the wire group 16. It is assumed that the work W is a block (single crystal ingot cut out in a block shape) such as silicon. The processing apparatus 10 dispenses a sliced wafer such as silicon obtained by cutting the work W as a processed product.

The wire 12 is wound around a set of wire reels 38A and 38B. The wire 12 is stretched from one wire reel 38A to the other wire reel 38B via a guide roller 32, a roller 14, and the like.

The wire reels 38A and 38B are each rotated by the drive motor 36. By driving the drive motor 36 to rotate the wire reels 38A and 38B, the wire 12 is unwound from one wire reel 38A and can travel to the other wire reel 38B via the guide roller 32, the roller 14, and the like. The wire 12 travels via a tension applying means including a dancer arm 33, a dancer roller 34, and the like. Tension is applied to the wire 12 by traveling through the tension applying means. The wire 12 travels via the touch roller 35. The touch roller 35 follows the position of the wire 12 that moves when it is unwound from the wire reels 38A and 38B or wound up by the wire reels 38A and 38B.

The wire 12 is spirally wound over a plurality of times across a plurality of rollers 14. The spirally wound wire 12 constitutes a wire group 16 arranged in parallel between the rollers 14 in a direction orthogonal to the roller axial direction X. It is assumed that the roller 14 has a structure in which a polyurethane resin is press-fitted around a steel cylinder and grooves are cut at a constant pitch on the surface thereof. By fitting the wire 12 into the groove cut in the surface of the roller 14, the wire group 16 can run stably.

The traveling direction of the wire 12 is controlled by the rotation direction of the drive motor 36. The wire 12 can be controlled to travel in one direction or to reciprocate as needed. The magnitude of the tension applied to the wire 12 may be appropriately set. The traveling speed of the wire 12 may be appropriately set.

The slurry supplied from the nozzle 20 to the wire group 16 is stored in the slurry tank 40, and is sent from the slurry tank 40 to the nozzle 20 via the slurry chiller 42 that regulates the temperature of the slurry.

The sliced wafer as a processed product discharged from the wire saw device is further processed in a process such as polishing and shipped as a final product wafer.

(Configuration example of state determination device 50)
Hereinafter, a configuration example for the state determination device 50 to determine whether the state of the processing device 10 is an abnormal state will be described. In the following description, it is assumed that the processing device 10 is a wire saw device.

<Abnormal state of wire saw device>
The abnormal state of the wire saw device corresponds to a state in which there is a high possibility that the wire saw device will stop during cutting of the block. In the wire saw device, the wire 12 may break and stop. In the wire saw device, the wire 12 may stop without breaking.

Various factors can be considered as the cause of the wire saw device stopping. For example, the following factors can be considered as known factors. For example, when an abnormality occurs in the supply of the slurry, the wire 12 may be easily broken. For example, when the slurry adheres to the sensor that detects the disconnection of the wire 12, the wire saw device may erroneously detect the disconnection of the wire 12 and stop. For example, the wire saw device may stop due to an abnormality in the amount or temperature of the slurry in the slurry tank 40. On the other hand, the wire saw device may stop due to an unknown factor that does not apply to the known factor.

The control unit 51 of the state determination device 50 acquires measured values of various data items obtained from the wire saw device. Data items obtained from the wire saw device include, for example, slurry flow rate, wire tension, cooling water flow rate, and the like. The data items obtained from the wire saw device are not limited to these examples and may include various other items.

The wire saw device performs a process of cutting one block into a sliced wafer as a process of one lot. The control unit 51 can acquire a plurality of measured values for each data item during the processing of one lot. The wire saw device cuts one block into a plurality of sliced wafers over a predetermined time. That is, it takes a predetermined time to process one lot. The control unit 51 may acquire the measured value of each data item, for example, every 15 seconds during the processing of one lot. Then, the control unit 51 can acquire a plurality of measured values for each data item during the processing of one lot. The control unit 51 calculates the average value and standard deviation of a plurality of measured values acquired during the processing of each lot. The mean and standard deviation of multiple measurements in each lot is also referred to as the lot feature. The lot feature amount calculated based on the measured value of each data item is also simply referred to as the lot feature amount of each data item.

The control unit 51 determines whether the wire saw device has a low probability of stopping or the wire saw device has a high possibility of stopping based on the lot feature amount of each data item of the wire saw device. do. A state in which the probability that the wire saw device will stop is low is also called a normal state. A condition in which the wire saw device is likely to stop is also referred to as an abnormal condition.

<About the MT method (Mahalanobis-Taguchi method)>
The state of the wire saw device may be determined each time the processing of one lot is executed. The state of the wire saw device may be determined by focusing on only one data item of the wire saw device. In this case, under the assumption that the distribution of the feature amount of the lot of one data item follows a normal distribution, it can be determined whether the feature amount of the lot obtained when the lot is processed by the wire saw device is an abnormal value. If it is determined that the feature amount of one lot is an abnormal value, it may be determined that the wire saw device is more likely to be stopped during the processing of the next lot. That is, the state of the wire saw device can be determined to be an abnormal state.

When the number of data items obtained from the wire saw device is large, the state of the wire saw device may be determined based on a plurality of data items. In this case, the distribution of features in lots of each of the plurality of data items may be considered to follow a multivariate normal distribution. The control unit 51 determines whether the lot feature amount of each data item is an abnormal value based on the MT method (Mahalanobis-Taguchi method), which is one of the multivariate analysis methods, and the lot feature amount is an abnormal value. If this is the case, it may be determined that the state of the wire saw device when the lot is processed is an abnormal state.

The control unit 51 generates a unit space based on the feature amount of each lot of the plurality of data items obtained when the state of the wire saw device is a normal state. The unit space is expressed as a mathematical formula that specifies the distribution of lot features of each data item. Specifically, the control unit 51 normalizes the lot feature quantity of each data item, generates a correlation coefficient matrix including the correlation coefficient between the data items as an element, and calculates the inverse matrix of the correlation coefficient matrix. By doing so, a mathematical formula representing the unit space can be generated. That is, the unit space is specified by the inverse matrix of the correlation coefficient matrix.

The unit space represents the characteristics of the distribution of the feature amount of the processed lot when the state of the wire saw device is normal. It can be said that the unit space represents the characteristics of the lot group normally cut by the wire saw device. It can be said that the unit space represents the characteristics of the lot group normally processed by the processing apparatus 10. The control unit 51 can calculate the Mahalanobis Distance (MD) of the data in which the feature amounts of the plurality of data items obtained from the wire saw device are set as one set, based on the mathematical formula representing the unit space. MD is a concept generally used in the field of quality engineering, and is described, for example, in the following documents.
References: Makoto Sakai, "Introduction to Mahalanobis Distance", Journal of the Society of Quality Engineering "Quality Engineering", Vol.9, No.1, p.13-19

In MD, how close is the feature amount of the lot processed when the state of the wire saw device is unknown to the distribution of the feature amount of the lot processed when the state of the wire saw device is normal? It is an index showing. It can be said that the smaller the MD calculated from the feature amount of the lot, the higher the possibility that the feature amount of the lot is the feature amount of the processed lot when the state of the wire saw device is normal. On the contrary, it can be said that the larger the MD calculated from the feature amount of the lot, the higher the possibility that the feature amount of the lot is the feature amount of the lot processed when the state of the wire saw device is in an abnormal state. ..

Therefore, the control unit 51 calculates the MD of the feature amount of the newly processed lot based on the unit space, and the state of the wire saw device when the feature amount of the lot is obtained is normal or abnormal. Can be determined. Hereinafter, the data of the wire saw device including the feature amount of the lot processed in the past predetermined period used for generating the unit space is also referred to as reference data. Further, the data obtained when the wire saw device newly processes a lot and used for determining the state of the wire saw device when the lot is being processed is also referred to as determination target data. Will be done. The control unit 51 calculates the MD of the determination target data in the unit space generated based on the reference data, and determines the state of the wire saw device. The control unit 51 may generate a unit space based on the reference data, or may acquire information about the unit space from an external device.

<Generation of unit space based on cause data items>
As described above, the wire saw device stops due to various factors. Factors leading to the stoppage of the wire saw device may include factors known to the user of the wire saw device and factors unknown to the user of the wire saw device. Known factors are classified as known failure modes. Known failure modes are also referred to as known modes.

When the probability that the wire saw device is stopped is high, the lot feature amount of the data item corresponding to the factor causing the stop may be an abnormal value. The control unit 51 can determine whether the wire saw device is likely to be stopped by determining whether the lot feature amount of the data item corresponding to the factor causing the wire saw device stop is an abnormal value. The factor that causes the wire saw device to stop is also called the stop factor. The data item corresponding to the outage factor is also referred to as the cause data item. There can be multiple factors that cause the wire saw device to stop. Therefore, there are cause data items corresponding to each of the plurality of stop factors.

The control unit 51 may generate a unit space based on the feature amount of the lot of the cause data item in order to determine whether the feature amount of the lot of the cause data item is an abnormal value. The unit space may be generated by an external device. Specifically, the control unit 51 acquires, as reference data, the measured values of each of a plurality of data items for each lot processed from the start to the stop of the operation of the wire saw device, and uses the measured values as the measured values. Based on this, the feature amount of the lot is calculated. The control unit 51 generates a unit space based on the feature amount of the lot processed when the state of the wire saw device is known to be normal among the acquired reference data.

In order to determine the state of the wire saw device, the control unit 51 acquires the measured values of each of a plurality of data items of the lot newly processed by the wire saw device as the determination target data, and based on the measured values. Calculate the feature amount of the lot. The control unit 51 calculates the MD of the feature amount of the lot of the cause data item among the data acquired as the determination target data in the unit space generated in advance based on the feature amount of the lot of the cause data item for each stop factor. .. The control unit 51 can determine whether the feature amount of the lot of the cause data item is an abnormal value based on the calculated MD. If the lot features of the cause data item are outliers, it can be determined that the wire saw device is more likely to stop during the processing of the next lot. That is, the state of the wire saw device when the lot of the target from which the determination target data is acquired is processed can be determined to be an abnormal state.

Here, it is assumed that the unit space is generated based on the lot features of the data items other than the cause data item and which do not correspond to the stop factor. Data items that do not correspond to the outage factor are also referred to as non-cause data items. If the unit space is generated based not only on the lot features of the causal data item but also on the lot features of the non-causal data item, the unit space also represents a tendency that is not related to the shutdown of the wire saw device. It will be. As described above, the unit space is generated based on the correlation of the lot features of each data item. Then, the unit space generated based on the feature quantity of the lot of the non-causal data item is redundant because the correlation is smaller than that of the unit space generated based only on the feature quantity of the lot of the cause data item. Is. The MD calculated in the redundant unit space becomes insensitive to changes in the feature amount of the lot of the cause data item due to the influence of the feature amount of the lot of the non-cause data item. Conversely, since the unit space is generated based only on the cause data item, the control unit 51 calculates the MD in the unit space, so that the change in the lot feature amount of the cause data item is highly sensitive. Can be detected with.

The control unit 51 acquires the measured value of each data item of the lot when the wire saw device processes one lot as the determination target data, and calculates the feature amount of the lot based on the measured value. The control unit 51 calculates the MD of the lot feature amount of the cause data item included in the determination target data in the generated unit space. When the calculated MD is less than the threshold value, the control unit 51 determines that the state when the wire saw device processes one lot is a normal state. When the calculated MD is equal to or greater than the threshold value, the control unit 51 determines that the state when the wire saw device processes one lot is an abnormal state.

<Generation of unit space corresponding to known mode>
The failure mode that causes the wire saw device to stop may include a known failure mode or an unknown failure mode. Hereinafter, it is assumed that the failure mode that causes the wire saw device to stop includes at least two known modes. The control unit 51 generates a unit space based on the cause data item corresponding to each known mode. The unit space may be generated for each known mode. If the unit space is generated for each known mode, it is associated with each known mode.

The control unit 51 is the feature amount of the lot of the cause data item corresponding to each known mode included in the determination target data obtained when the wire saw device processes one lot in the unit space corresponding to each known mode. Calculate MD. When the MD calculated for a certain known mode is equal to or higher than a predetermined threshold value, the control unit 51 determines that there is a high possibility that the wire saw device will stop in the known mode when processing the next lot. The predetermined threshold may be set to the same value or different values in each known mode.

It is assumed that at least two known modes that cause the wire saw device to stop include a first known mode and a second known mode. The known mode is not limited to only two, a first known mode and a second known mode, and may include, for example, a third known mode. Also, it should be noted that the identifiers such as "first" and "second" do not represent the superiority or inferiority of the known mode. The data item corresponding to the factor that causes the wire saw device to stop in the first known mode is also referred to as the first cause data item. The control unit 51 generates a unit space based on the lot feature amount of the first cause data item. The unit space generated based on the lot features of the first cause data item is also referred to as the first unit space. The data item corresponding to the factor that causes the wire saw device to stop in the second known mode is also referred to as a second cause data item. The control unit 51 generates a unit space based on the lot feature amount of the second cause data item. The unit space generated based on the lot features of the second cause data item is also referred to as the second unit space. The cause data item is not limited to only two, the first cause data item and the second cause data item, and may include, for example, a third cause data item corresponding to a factor that stops in the third known mode. The unit space is not limited to only two, the first unit space and the second unit space, and may include, for example, a third unit space generated based on the feature amount of the lot of the third cause data item. Further, the identifiers such as "first" and "second" do not represent the superiority or inferiority of the cause data item or the unit space.

The control unit 51 calculates the MD of the lot feature amount of the first cause data item included in the determination target data obtained when the wire saw device processes one lot in the first unit space. The control unit 51 calculates the MD of the lot feature amount of the second cause data item included in the determination target data in the second unit space. When the MD calculated in the first unit space is equal to or higher than a predetermined threshold value, the control unit 51 may determine that the wire saw device is more likely to stop in the first known mode. When the MD calculated in the second unit space is equal to or higher than a predetermined threshold value, the control unit 51 may determine that the wire saw device is more likely to stop in the second known mode. When the control unit 51 determines that there is a high possibility of stopping in one of the first known mode and the second known mode, it is not necessary to determine the other mode. Even if it is determined that the control unit 51 is likely to stop in at least one mode, the control unit 51 may determine whether the possibility of stopping in the other mode is high. If it is determined that there is a high possibility of stopping in a plurality of failure modes, the user can collectively perform maintenance work for the target failure modes.

The first cause data item and the second cause data item each include a plurality of data items. Both the first cause data item and the second cause data item include data items that are not included in the other cause data item. In other words, the first cause data item and the second cause data item do not have an inclusive relationship with each other. Further, the data item included in the first cause data item and the data item included in the second cause data item are not completely the same. If the first cause data item and the second cause data item are inclusive or completely the same, the first known mode and the second known mode are not independent failure modes but related to each other. It can be said that it is the same kind of failure mode. By including a data item in which both the first cause data item and the second cause data item are not included in the other cause data item, the control unit 51 can perform each of at least two known modes that occur independently of each other with high accuracy. Can be detected.

<Data used to generate unit space>
As described above, the control unit 51 generates a unit space based on the lot feature amount of the cause data item of the lot processed during the period when the state of the wire saw device is normal in the reference data. Hereinafter, an example of the data included in the reference data will be described.

The state of the wire saw device is the replaced parts or assembled parts in the processing of several lots to a dozen lots after the operation is started after the parts replacement work, disassembly and assembly work, cleaning work, etc. of the wire saw device are performed. Can be in an unstable state, which is not yet running smoothly. After that, the state of the wire saw device can be stable in the processing of tens to hundreds of lots, with the parts starting to operate smoothly. Further, the state of the wire saw device may become unstable in the processing of several lots to several tens of lots until the failure due to the increase in the failure probability due to the deterioration of the cleaning state due to the deterioration of parts or the accumulation of slurry.

The control unit 51 acquires the measured value of each data item in each lot processed from the start to the stop of the operation of the wire saw device, and calculates the feature amount of each lot as reference data based on the measured value. do. The feature amount of each lot is calculated based on the measured values of N data items from D1 to DN.

As illustrated in the table of FIG. 3, lot features calculated as reference data are associated with lots and data items. The columns of the table in FIG. 3 represent N data items from D1 to DN. The rows of the table in FIG. 3 represent lots. Lots are further divided into three periods, P1, P2 and P3, based on the time of processing. P1 corresponds to a lot of M1 processed after restarting the operation of the wire saw device. P3 corresponds to a lot of M3 processed immediately before the lot in which the wire saw device is stopped. P2 corresponds to M2 lots not included in P1 and P3. It can be said that P2 corresponds to the lot processed while the state of the wire saw device is in a stable state.

The control unit 51 calculates the feature amount of M1 lots from D1P1_1 to D1P1_M1 based on the measured value of the data item D1 of each M1 lot in the period P1. In the period P1, the control unit 51 calculates the feature amount of the M1 lot from DNP1_1 to DNP1_M1 based on the measured value of the data item DN of each M1 lot. The control unit 51 calculates the feature amount of the M2 lots from D1P2_1 to D1P2_M2 based on the measured value of the data item D1 of each of the M2 lots in the period P2. The control unit 51 calculates the feature amount of the M2 lots from DNP2_1 to DNP2_M2 based on the measured value of the data item DN of each of the M2 lots in the period P2. The control unit 51 calculates the feature amount of the M3 lots from D1P3_1 to D1P3_M3 based on the measured value of the data item D1 of each of the M3 lots in the period P3. The control unit 51 calculates the feature amount of the M3 lots from DNP3_1 to DNP3_M3 based on the measured value of the data item DN of each of the M3 lots in the period P3.

It is assumed that the wire saw device for which the reference data exemplified in the table of FIG. 3 is acquired is stopped in the known mode during the processing of the lot after the period P3. In other words, the lots of period P3 correspond to the last M3 lots processed by the wire saw device before the wire saw device was shut down in the known mode.

The control unit 51 generates a unit space based on the lot feature amount of the period P2 in which the state of the wire saw device is in a stable state among the lot feature amounts included in the acquired reference data. Here, it is assumed that the features of some lots are excluded from the features of each lot in the period P2 used to generate the unit space. The reason why the features of some lots are excluded will be described later. The generated unit space is associated with a known mode.

<Condition determination of wire saw device based on MD>
The control unit 51 acquires the feature amount of the lot of each data item at the time of lot processing of the wire saw device as the determination target data, and acquires it as the determination target data in the unit space generated in advance based on the reference data. The MD of the feature amount of the lot is calculated.

<< Verification of validity of unit space >>
Here, in the unit space, the state determination device 50 can determine whether the wire saw device is in a stable state or in a state in which the possibility of failure is high, based on the MD of the feature amount of the lot. Must be generated in. That is, the MD of the feature amount of the lot in the state where the wire saw device is highly likely to stop is equal to or higher than the predetermined threshold value, and the MD of the feature amount of the lot in the state where the wire saw device is stable is set. The unit space needs to be generated so that it is less than a predetermined threshold.

In order to confirm whether the generated unit space satisfies the above conditions, MD was calculated for the feature amount of each lot included in the reference data exemplified in FIG. FIG. 4 shows a bar graph in which the MD values calculated for the feature amounts of each lot included in the reference data are arranged in the order of processing by the wire saw device. The MD calculated for the feature amount of each lot is also referred to as the MD of each lot. The horizontal axis represents a lot. The vertical axis represents the MD value of each lot. Along the horizontal axis, the range of lots included in each of the periods P1, P2 and P3 divided based on the state of the wire saw device is displayed. The number of lots included in the period P1 (M1), the number of lots included in the period P2 (M2), and the number of lots included in the period P3 (M3) are 10 lots, 143 lots, and 40 lots, respectively. The ratio of the number of lots included in each of the periods P1, P2 and P3 is about 5%, about 75% and about 20% with respect to the total number of lots. The ratio of the number of lots included in each period is not limited to this example, and may be changed as appropriate.

The bar graph shown on the far right of FIG. 4 represents the MD of the stop lot 71 that was being processed when the wire saw device was stopped. In the graph of FIG. 4, the predetermined threshold value is represented by MD_T. When the vertical bar representing the value of MD in each lot extends above the dashed line representing the value of MD_T, MD is greater than a predetermined threshold. The control unit 51 sets the value of MD_T so that the MD of each lot included in the period P2 is less than MD_T and the MD of at least one lot included in the period P3 is MD_T or more. A lot in which MD becomes MD_T or more is represented as an abnormality detection lot 72. By setting MD_T in this way, the control unit 51 can determine that the state of the wire saw device is in an abnormal state before the wire saw device stops during lot processing and causes a loss.

The MD of the lot included in the period P2 tends to be smaller than the MD of the lot included in the periods P1 and P3. The reason for this is that the unit space is generated based on the features of the lot included in the period P2. The feature amount of each lot used to generate the unit space acts to expand the unit space according to the feature amount itself of each lot. Therefore, in a certain unit space, when the MD of the feature amount of the lot used to generate the unit space is calculated, the calculated MD naturally becomes a small value. On the contrary, when the MD of the feature amount of the lot not used to generate the unit space is calculated in a certain unit space, the calculated MD is likely to be a large value. In other words, the wider the distribution of the lot features used to generate the unit space, the smaller the MD calculated in the generated unit space.

As described above, the features of some lots are excluded from the features of the lots of period P2 used to generate the unit space. The lot from which the measured value used for calculating the feature amount used to generate the unit space is obtained is referred to as the lot 73 in the unit space. The lot from which the measured values used to calculate the features that were not used to generate the unit space was obtained is referred to as the out-of-unit space lot 74. In other words, the unit space is generated based on the feature amount of the lot of the lot 73 in the unit space and not based on the feature amount of the lot of the lot 74 outside the unit space. As mentioned above, the MD of the lot used to generate the unit space is naturally calculated with a small value. Therefore, the MD of the lot 74 outside the unit space tends to be larger than the MD of the lot 73 inside the unit space.

Here, the out-of-unit space lot 74 was processed during the period P2 in which the state of the wire saw device is normal, although the feature amount calculated based on the measured value is not used to generate the unit space. It is a lot. Therefore, a predetermined threshold value is set so that the MD of the lot 74 outside the unit space is less than the predetermined threshold value. If the MD of the lot 74 outside the unit space is set to be equal to or higher than a predetermined threshold value, even if the state of the wire saw device is in the normal state, it is likely to be erroneously determined as an abnormal state. Therefore, the control unit 51 sets a predetermined threshold value to a value larger than the MD of the lot 74 outside the unit space, so that the state of the wire saw device is normal in the state determination of the wire saw device described later. It becomes easier to avoid determining that it is abnormal. Further, when the threshold value is already set, it can be verified whether the unit space is appropriately set based on the MD value of the lot removed from the unit space (lot 74 outside the unit space). ..

As described above, the control unit 51 creates a unit space based on the feature amount of each lot processed from the start to the stop of the operation of the wire saw device in the past predetermined period. That is, the control unit 51 acquires the feature amount of the past processing lot for which the timing at which the wire saw device is stopped is known as reference data, and generates a unit space based on the reference data. In the unit space generated in this way, the control unit 51 acquires the feature amount of the lot newly processed by the wire saw device as the determination target data, calculates the MD of the lot, and determines the state of the wire saw device. It can be judged.

<< Comparison example of data item selection >>
The unit space for which the above-mentioned validation was performed was generated based on the lot features of the cause data item, which is known to have a large contribution to the known mode. Here, as a comparative example, among the data items of the lot processed before stopping in the known mode, the non-causal data items that are known to have little contribution or a small contribution to the known mode are generated. An example of MD values calculated in unit space will be described. FIG. 5 shows a bar graph in which the MD values of each lot are arranged in the order processed by the wire saw device in the unit space generated based on the non-cause data item. The meanings of the horizontal axis and the vertical axis, and the meanings of the periods P1, P2, and P3 are the same as those in FIG. 4 and are omitted.

Comparing the MD values of each lot exemplified in FIG. 5, the difference between the MD of the out-of-unit space lot 74 in the period P2 and the MD of each lot in the period P3 is small. When MD_T representing a predetermined threshold value is set low, there is an increased possibility that the wire saw device is erroneously determined to be in an abnormal state even though it is in a normal state. When MD_T is set higher, there is an increased possibility that the wire saw device will not be determined to be in an abnormal state even though it is in an abnormal state in which there is a high possibility that the wire saw device will stop. If the wire saw device is in an abnormal state but is not determined to be in an abnormal state, the wire saw device loses the opportunity to be stopped prophylactically and fails during lot processing and stops. The possibility increases. In the example of FIG. 5, no matter how the MD_T is set, the possibility of erroneously determining the state of the wire saw device increases.

In view of the examples of FIGS. 4 and 5, the state of the wire saw device is such that the value obtained by subtracting the MD of the lot 74 outside the unit space in the period P2 from the MD of at least a part of the lots in the period P3 becomes a predetermined value or more. Judgment accuracy can be improved. The predetermined value may be appropriately set. The control unit 51 can appropriately select a cause data item from a plurality of data items and generate a unit space based on the cause data item so that the MDs of the lots included in the periods P2 and P3 satisfy the above conditions. The control unit 51 sets a predetermined threshold value to a value smaller than the MD of at least a part of the lots in the period P3 and larger than the maximum value of the MDs of the lot 74 outside the unit space in the period P2. This makes it easier for the control unit 51 to avoid determining that the wire saw device is abnormal even though the state of the wire saw device is normal.

If the state determination device 50 generates a unit space based on all data items, the unit space is also generated based on a non-causal data item that hardly contributes or has a low contribution as a factor that causes the wire saw device to stop. Will be done. Then, the MD value of the lot calculated in the unit space generated based on all the data items is less likely to reflect the change in the state of the wire saw device. Therefore, when the state of the wire saw device is determined based on the MD value of the lot calculated in the unit space generated based on all the data items, the determination accuracy may be as low as in the example of FIG.

<< Judgment of the state of the wire saw device based on the generated unit space and threshold value >>
For the wire saw device whose stop timing is unknown, the control unit 51 acquires the feature amount calculated based on the measured value obtained when the device processes the lot as the determination target data, and is based on the determination target data. To determine if the wire saw device is more likely to stop.

Specifically, the control unit 51 calculates the MD of the newly processed lot in the unit space generated based on the feature amount of the past processed lot. Based on the calculated MD value, the control unit 51 determines whether there is a high possibility that the wire saw device will stop in the processing after the next lot of the lot.

When the MD is less than a predetermined threshold value, the control unit 51 determines that the wire saw device is unlikely to stop, that is, the state of the wire saw device at the time of processing the lot is a normal state. When the MD is equal to or higher than a predetermined threshold value, the control unit 51 determines that the wire saw device is likely to stop, that is, the state of the wire saw device at the time of processing the lot is an abnormal state.

The control unit 51 may notify the user that the state of the wire saw device is in an abnormal state by displaying it on the output unit 53 or outputting it by voice. The user may prevent the wire saw device from processing the next lot based on the notification, and may stop prophylactically to perform the maintenance work. The control unit 51 may output to the wire saw device that the state of the wire saw device is in an abnormal state and stop the wire saw device prophylactically.

<< Judgment of abnormal condition based on known mode >>
When it is known that the wire saw device has stopped in the known mode, the control unit 51 may acquire the feature amount of the lot processed from the start to the stop of the operation as reference data. The data including the feature amount of the lot processed before stopping in the known mode is also referred to as the known mode data. The control unit 51 may generate a unit space based on known mode data. A unit space based on known mode data is also referred to as a known mode unit space.

The control unit 51 calculates the MD of the lot processed by the wire saw device whose state is unknown in the known mode unit space. When the MD of the lot calculated in the known mode unit space is equal to or higher than a predetermined threshold value, the control unit 51 may determine that the wire saw device is in an abnormal state in which the possibility of stopping in the known mode is high. An abnormal condition in which the wire saw device is more likely to stop in a known mode is also referred to as an abnormal condition based on the known mode.

When the known mode includes a plurality of failure modes such as a first known mode or a second known mode, the control unit 51 performs each failure based on reference data including lot data processed before stopping in each failure mode. The unit space corresponding to the mode may be generated. For example, the control unit 51 may generate a first unit space corresponding to the first known mode or a second unit space corresponding to the second known mode. The control unit 51 may calculate the MD of the lot processed by the wire saw device in the unit space corresponding to each failure mode. When the MD of the lot calculated in the unit space corresponding to each failure mode is equal to or higher than a predetermined threshold value, the control unit 51 may stop the wire saw device in the failure mode in which the MD is equal to or higher than the predetermined threshold value. It may be determined that the condition is high and abnormal. The threshold values for determining the MD values of the first unit space and the second unit space are also referred to as the first threshold value and the second threshold value, respectively. The first threshold value and the second threshold value may be different values from each other, or may be the same value as each other. The states in which the wire saw device is likely to stop in the first known mode and the second known mode are also referred to as a first abnormal state and a second abnormal state, respectively. The threshold value is not limited to only two of the first threshold value and the second threshold value, and may include, for example, a third threshold value set for determining MD in the third unit space. The abnormal state is not limited to only two, the first abnormal state and the second abnormal state, and may include, for example, a third abnormal state corresponding to a state that is likely to stop in the third known mode. Also, it should be noted that the identifiers such as "first" and "second" do not represent the superiority or inferiority of the threshold value or the abnormal state.

The control unit 51 may determine whether the state of the wire saw device is an abnormal state based on a known mode, a first abnormal state, or a second abnormal state, and output the determined result to the output unit 53. The control unit 51 may notify the user such as the operator of the wire saw device or the person in charge of maintenance of the determination result. The user performs various operations such as inspection work, parts replacement work, and repair work of the wire saw device based on the notified determination result. This allows the user to properly maintain the wire saw device so that the wire saw device does not fail during lot processing.

<< Judgment of possible stoppage of unknown cause >>
When the wire saw device is stopped for unknown reasons, the control unit 51 may acquire the feature amount of the lot processed from the start to the stop of the operation as reference data. Data including feature quantities of lots processed before stopping due to unknown cause is also referred to as unknown cause data. The control unit 51 may generate a unit space based on unknown cause data. A unit space based on unknown cause data is also referred to as an unknown cause unit space. The control unit 51 may select all the data items obtained from the wire saw device to generate the unexplained unit space, or may select some data items to generate the unexplained unit space. ..

The control unit 51 calculates the MD of the lot processed by the wire saw device whose state is unknown in the unit space of unknown cause. When the MD of the lot calculated in the unit space of unknown cause is equal to or higher than a predetermined threshold value, the control unit 51 may determine that the wire saw device is in an abnormal state in which there is a high possibility that the wire saw device will stop due to unknown cause. .. The threshold value for determining the MD value of the lot calculated in the unknown cause unit space is also referred to as an unknown cause threshold value. The unknown cause threshold value is set to a predetermined threshold value used for determining the MD value of the lot calculated in the known mode unit space, or the same value as the first threshold value, the second threshold value, or the like, but is different. It may be set to a value.

When the control unit 51 determines that the wire saw device is likely to stop due to unknown cause, the control unit 51 may further execute an effectiveness analysis to narrow down the factors that cause the wire saw device to stop. The effectiveness analysis corresponds to analyzing which of the data items used to generate the causal unit space had a significant effect on the MD value. The control unit 51 can perform the effectiveness analysis by various methods. The control unit 51 can determine a data item for increasing the MD value of the lot calculated in the unexplained inferior unit space by the effectiveness analysis. A data item that increases the MD value of a lot calculated in an unknown cause unit space is also referred to as a cause candidate item. A specific example of a method for determining a cause candidate item by effectiveness analysis will be described later.

The control unit 51 may notify the user such as the operator of the wire saw device or the person in charge of maintenance of the cause candidate item by determining the cause candidate item and causing the output unit 53 to output the cause candidate item. The user executes various operations such as inspection work, parts replacement work, and repair work of the wire saw device based on the data items determined as the cause candidate items. This allows the wire saw device to be properly maintained before it fails during lot processing.

<Summary>
As described above, according to the state determination system 1 and the state determination device 50 according to the present embodiment, there is an increased possibility that the processing device 10 will fail before the processing device 10 such as the wire saw device fails. It can be determined whether it is in an abnormal state. By doing so, the processing apparatus 10 is less likely to break down during the processing. If the processing apparatus 10 fails during the processing process, a large loss occurs. The loss can be reduced by making the processing apparatus 10 less likely to break down during the processing.

(Example of procedure for determining the status)
The control unit 51 of the state determination device 50 may execute, for example, a state determination method including the procedure of the flowchart illustrated in FIGS. 6 and 7. The control unit 51 can determine whether the state of the wire saw device is an abnormal state by executing the illustrated state determination method. The state determination method may be realized as a state determination program to be executed by the control unit 51. The procedure shown in FIGS. 6 and 7 is an example and may be changed as appropriate.

The control unit 51 creates a unit space (step S1). The control unit 51 generates a unit space based on the reference data of the wire saw device. When the wire saw device is stopped in the known mode, the control unit 51 may generate a unit space corresponding to the known mode based on the reference data obtained as the data of the lot processed before the stop. When the wire saw device is stopped due to an unknown cause, the control unit 51 may generate a unit space corresponding to the case where the cause is unknown, based on the reference data obtained as the data of the lot processed until the stop. .. FIG. 7 shows an example of a procedure for generating a unit space as a subroutine.

The control unit 51 acquires reference data (step S11 in FIG. 7). The reference data includes features calculated based on the measured values of each lot processed when the wire saw device was operated until it stopped in the past. The control unit 51 may acquire the feature amount of the lot processed before the wire saw device is stopped in the known mode such as the first known mode or the second known mode as reference data. The control unit 51 may acquire the feature amount of the lot processed before the wire saw device is stopped due to an unknown cause as reference data.

The control unit 51 selects a cause data item from the reference data (step S12). The reference data includes a plurality of data items that can be obtained from the wire saw device. The control unit 51 may select a data item corresponding to a predetermined failure mode, which is the cause of the stop of the wire saw device, as the cause data item. The control unit 51 may select, for example, the data items corresponding to the first known mode and the second known mode as the first cause data item and the second cause data item, respectively. When the control unit 51 acquires the feature amount of the lot processed before the wire saw device stops due to an unknown cause as reference data, the control unit 51 may select all the cause data items.

The control unit 51 divides the reference data into the unit space data which is the data of the unit space lot 73 and the unit space data which is the data of the unit space outside lot 74 (step S13).

The control unit 51 generates a unit space based on the data in the unit space (step S14). The control unit 51 may generate a first unit space, a second unit space, a unit space of unknown cause, or the like as a unit space.

The control unit 51 determines whether the generated unit space is appropriate (step S15). Specifically, the control unit 51 calculates the MD of the lot 73 in the unit space and the MD of the lot 74 outside the unit space in the generated unit space. For example, when the difference between the MD of the lot 73 in the unit space and the MD of the lot 74 outside the unit space is not more than a predetermined value, the control unit 51 may determine that the generated unit space is appropriate. When the control unit 51 determines that the generated unit space is not valid (step S15: NO), the control unit 51 returns to the procedure of step S13. The control unit 51 may return to the procedure of step S12. When the control unit 51 determines that the generated unit space is appropriate (step S15: YES), the control unit 51 ends the subroutine processing exemplified in FIG. 7 and returns to the procedure of step S2 in FIG.

The control unit 51 may generate a unit space corresponding to a plurality of known modes in the subroutine processing of the unit space generation procedure exemplified in FIG. 7. The control unit 51 may generate an unexplained unit space corresponding to an unexplained stop.

Returning from the subroutine process of FIG. 7 executed as the procedure of step S1 of FIG. 6, the control unit 51 acquires the determination target data (step S2 of FIG. 6).

The control unit 51 calculates the MD of the lot included in the determination target data (step S3). The control unit 51 may calculate the MD of the lot included in the determination target data for each of the plurality of unit spaces generated in the procedure of step S1. The control unit 51 may calculate the MD of the lot included in the determination target data in the first unit space. The MD of the lot included in the determination target data calculated in the first unit space is also referred to as the MD of the first unit space. The control unit 51 may calculate the MD of the lot included in the determination target data in the second unit space. The MD of the lot included in the determination target data calculated in the second unit space is also referred to as the MD of the second unit space. The control unit 51 may calculate the MD of the lot included in the determination target data in the unit space of unknown cause. The MD of the lot included in the determination target data calculated in the unknown cause unit space is also referred to as the MD of the unknown cause unit space.

The control unit 51 determines whether the MD in the first unit space is equal to or higher than the first threshold value (step S4). The control unit 51 may set the first threshold value, for example, when the first unit space is generated in the procedure of step S1. The first threshold value detects that the state of the wire saw device is in an abnormal state based on the first known mode, and prevents the wire saw device from being erroneously detected as abnormal when the state of the wire saw device is normal. Can be set.

When the MD of the first unit space is equal to or greater than the first threshold value (step S4: YES), the control unit 51 proceeds to the procedure of step S8. When the MD of the first unit space is not equal to or more than the first threshold value (step S4: NO), that is, when the MD of the first unit space is less than the first threshold value, the control unit 51 has the MD of the second unit space second. It is determined whether or not it is equal to or higher than the threshold value (step S5). The control unit 51 may set a second threshold value, for example, when the second unit space is generated in the procedure of step S1. The second threshold value detects that the state of the wire saw device is in an abnormal state based on the second known mode, and prevents the wire saw device from being mistakenly detected as abnormal when the state of the wire saw device is normal. Can be set.

When the MD of the second unit space is equal to or greater than the second threshold value (step S5: YES), the control unit 51 proceeds to the procedure of step S8. When the MD of the second unit space is not equal to or higher than the second threshold value (step S5: NO), that is, when the MD of the second unit space is less than the second threshold value, the cause of the MD of the second unit space is unknown. It is determined whether or not it is equal to or higher than the threshold value (step S6). The control unit 51 may set an unknown cause threshold value when generating the unknown cause unit space in the procedure of step S1, for example. The unknown cause threshold is set so that when the state of the wire saw device is in the normal state, it is not erroneously detected as an abnormal state while detecting that the state of the wire saw device is in the abnormal state of unknown cause. Can be done.

When the MD of the unexplained unit space is not equal to or greater than the unexplained threshold value (step S6: NO), that is, when the MD of the unexplained unit space is less than the unexplained threshold value, the control unit 51 executes the procedure shown in the flowchart of FIG. finish.

When the MD of the unexplained unit space is equal to or greater than the unexplained threshold value (step S6: YES), the control unit 51 sets a cause candidate item which is a data item corresponding to a factor increasing the possibility that the wire saw device is stopped. Determine (step S7). The control unit 51 may determine a cause candidate item by effectiveness analysis. Specific examples of effectiveness analysis will be described later.

The control unit 51 proactively stops the wire saw device after the procedure of step S7 or when it is determined in the procedure of step S4 or S5 that the MD is equal to or higher than the threshold value (step S8). By doing so, the wire saw device as the processing device 10 can be maintained by inspection work, parts replacement work, repair work, or the like before it fails and stops.

According to the state determination method described above, it is possible to determine whether the state of the wire saw device is in an abnormal state before the wire saw device as the processing device 10 fails. By doing so, the wire saw device as the processing device 10 breaks down during the lot processing and it becomes difficult to stop. If the processing apparatus 10 fails during lot processing, a large loss such as disposal of the lot being processed occurs. The loss can be reduced by making it difficult for the processing apparatus 10 to fail and stop during lot processing.

(Other embodiments)
Hereinafter, as another embodiment, a modification of at least a part of the above-described embodiment, or a configuration example that can be added or deleted will be described.

<Selection of data items for generation of unit space>
As described above, when a unit space is generated based on the feature quantity of a lot of non-causing data items that contributes little or has a low contribution as a factor of the stop of the wire saw device, the lot calculated in the unit space. The correlation between the MD and the possibility of the wire saw device being stopped is low. That is, such a unit space is redundant as compared with the unit space generated based on the feature amount of the lot of the cause data item having a high contribution as a factor of stopping the wire saw device. The MD calculated in the redundant unit space becomes insensitive to changes in the lot features of the cause data item, which is closely related to the cause of the stoppage. Conversely, the control unit 51 of the state determination device 50 generates a unit space based on the feature amount of the lot of the cause data item closely related to each factor of the stop, and the lot is calculated in the unit space. Based on the MD, changes in the lot features of the cause data item can be detected with high sensitivity. The control unit 51 can determine the state of the wire saw device with high accuracy by detecting the change in the feature amount of the lot of the cause data item with high sensitivity.

The control unit 51 may select a cause data item having a high degree of contribution as a factor of stopping the wire saw device from a plurality of data items based on the content input by the user from the input unit 54.

The control unit 51 may select data items in various combinations from a plurality of data items of the reference data to generate a temporary unit space based on the feature amount of the lot of the selected data items. The control unit 51 calculates the MD of each lot of reference data in the temporary unit space. The control unit 51 determines whether or not the difference between the MD of the lot of the period P3 and the MD of the lot of the period P2 of the reference data is equal to or larger than a predetermined value. When the difference between the MD of the lot of the period P3 and the MD of the lot of the period P2 is equal to or more than a predetermined value, the control unit 51 adopts the temporary unit space as the unit space for determining the state of the wire saw device. It's okay. The control unit 51 calculates the difference between the MD of the lot of the period P3 and the MD of the lot of the period P2 with various combinations of data items, and sets the combination of the data items when the difference is maximum as the cause data item. The unit space may be generated based on the cause data item.

<Determining cause candidate items by effectiveness analysis>
The control unit 51 may determine the cause candidate item by, for example, executing the process described below.

The control unit 51 determines a data item to be evaluated from a plurality of data items. Data items to be evaluated are also referred to as evaluation target items. The control unit 51 generates a unit space based on the feature amount of the lot of the data item that does not include the evaluation target item. A unit space based on the feature quantity of a lot of data items that does not include the evaluation target item is also referred to as an evaluation target unit space. The control unit 51 calculates the MD of the lot in the evaluation target unit space. The control unit 51 calculates the difference between the MD of the lot calculated in the unit space of unknown cause and the MD of the lot calculated in the evaluation target unit space as the MD contribution degree of the evaluation target item. The MD contribution degree represents the magnitude of the influence of the evaluation target item on MD.

When the MD contribution of the evaluation target item is equal to or higher than a predetermined value, the control unit 51 may determine the evaluation target item as a cause candidate item. The control unit 51 calculates the MD contribution degree with each of the plurality of data items as the evaluation target item, and even if the data item that becomes higher when each data item is arranged in the order of the MD contribution degree is determined as the cause candidate item. good. The control unit 51 may determine a predetermined number of data items as cause candidate items, counting from the upper level. The predetermined number may be set to one or more various numerical values.

In the above example, the control unit 51 calculates the MD contribution of the evaluation target item as the difference between the MD of the lot calculated in the unit space of unknown cause and the MD of the lot calculated in the unit space of evaluation target. The control unit 51 may use the MD of the lot calculated in the unit space generated based on the feature amount of the lot of the data item including at least the evaluation target item, instead of the MD of the lot calculated in the unit space of unknown cause. ..

Specifically, the control unit 51 may generate a comparison target unit space based on the evaluation target item, at least one other data item, and the feature amount of each lot. The control unit 51 may calculate the difference between the MD of the lot calculated in the comparison target unit space and the MD of the lot calculated in the evaluation target unit space as the MD contribution of the evaluation target item. When the control unit 51 determines a plurality of data items as evaluation target items, the control unit 51 may generate a comparison target unit space based on the feature amount of the lot of only the evaluation target items.

Further, when the control unit 51 determines one data item as the evaluation target item, it may be assumed that the appearance probability of the feature amount of the lot of the evaluation target item follows a normal distribution. The control unit 51 sets the data items of the lot as evaluation target items one by one for the lot determined that the wire saw device is likely to stop due to unknown cause, and the appearance of the feature amount of the lot of each evaluation target item. The probabilities may be calculated based on the probabilities of the normal distribution. The control unit 51 may determine an evaluation target item whose calculated appearance probability is less than a predetermined value as a cause candidate item. The control unit 51 may determine the data item having the lowest calculated appearance probability as the cause candidate item. The control unit 51 may determine a predetermined number of data items as cause candidate items, counting from the one with the lowest calculated appearance probability. The predetermined number may be set to one or more various numerical values.

As described above, the state determination device 50 determines the cause, although the cause is unknown, by executing the effectiveness analysis when it is determined that the wire saw device is likely to stop due to unknown cause. It can be narrowed down. As a result, a user such as an operator of the wire saw device or a person in charge of maintenance can easily perform maintenance work on the wire saw device.

<Limitation on the number of data>
When the wire saw device is stopped for unknown reasons, the control unit 51 selects all the data items of the reference data and generates a unit space when the data of the lot processed before the stop is acquired as reference data. You can do it. The reason for selecting all the data items is that the cause data item cannot be identified because the cause of the stop of the wire saw device is unknown. When the cause data item cannot be specified, the control unit 51 needs to select all the data items and generate a unit space in order to widely monitor each data item.

The feature amount of each data item obtained from the wire saw device is not limited to one for each lot. By further classifying the wire saw device according to the distance at which the block is cut, the feature amount in each class can be obtained. For example, each data item may be acquired in the section from the start of the wire saw device cutting of the block to the center, and in the section beyond the center to the end of the cutting. In this case, the control unit 51 can acquire the feature amount of each data item by the number of divisions when the wire saw device processes one lot. Therefore, the total number of features used to generate the unit space is expressed as the product of the number of data items and the number of divisions based on the cutting distance of the block.

For example, assume that the number of data items of the wire saw device is 40. It is assumed that when the wire saw device cuts a block having a diameter of 300 mm, the feature amount of each data item is acquired in each of the five divisions in which the cutting distance is divided by 60 mm. In this case, the total number of features obtained by processing one lot is 200 (40 × 5). Further, it is assumed that when the wire saw device cuts a block having a diameter of 300 mm, the feature amount of each data item is acquired in each of the 30 divisions in which the cutting distance is divided by 10 mm. In this case, the total number of features obtained by processing one lot is 1200 (40 × 30).

Here, when the feature amount is calculated based on the measured values of the data items of each of the plurality of lots and the unit space is generated based on the calculated feature amount, the number is larger than the total number of feature amounts obtained by the processing of one lot. It is necessary to acquire the data of the lot of as reference data. The number of lots for which the measured value for calculating the feature amount as reference data is acquired is larger than the total number of feature amounts obtained in the processing of one lot, which is the correlation coefficient matrix included in the formula representing the unit space. This is because it is a condition for the existence of the inverse matrix. In other words, if the number of lots for which the measured value for calculating the feature amount as reference data is acquired is less than or equal to the total number of feature amounts obtained in the processing of one lot, the inverse matrix of the correlation coefficient matrix does not exist. Is. Regarding the existence condition of the inverse matrix of the correlation coefficient matrix, the description in Section 4.2.2 on page 19 of the above-mentioned document (“Introduction to Mahalanobis Distance”) can be referred to.

When the unexplained unit space is generated based on all the data items obtained from the wire saw device, the number of data divisions in one lot of each data item is determined by the existence condition of the inverse matrix of the correlation coefficient matrix. Based on this, it needs to be reduced according to the number of lots. It can be said that by reducing the number of data divisions during the processing of one lot, the monitoring resolution of the change in the feature amount calculated based on the measured value during the lot processing is lowered. On the other hand, by selecting all the data items, it can be said that the factors leading to the stoppage of the wire saw device can be widely monitored.

On the other hand, by selecting the cause data item, which is a part of the data item, in order to generate the known mode unit space, it is possible to increase the number of divisions of the data being processed in one lot. By increasing the number of data divisions during the processing of one lot, it can be said that the monitoring resolution of the change in the feature amount calculated based on the measured value during the lot processing is improved.

(Application to devices other than wire saw devices)
In the above-described embodiment, the configuration in which the state determination device 50 determines the state of the wire saw device as the processing device 10 has been described. The state determination device 50 is not limited to the wire saw device as the processing device 10, and may determine the state of other devices such as a polishing device.

Although the embodiments according to the present disclosure have been described based on the drawings and examples, it should be noted that those skilled in the art can easily make various modifications or modifications based on the present disclosure. It should be noted, therefore, that these modifications or modifications are within the scope of this disclosure. For example, the functions included in each component or each step can be rearranged so as not to be logically inconsistent, and a plurality of components or steps can be combined or divided into one. Is. Although the embodiment according to the present disclosure has been mainly described with respect to the apparatus, the embodiment according to the present disclosure can also be realized as a method including steps executed by each component of the apparatus. The embodiments according to the present disclosure can also be realized as a method, a program, or a storage medium on which a program is recorded, which is executed by a processor included in the apparatus. It should be understood that these are also included in the scope of this disclosure.

The graphs included in this disclosure are schematic. The scale etc. do not always match the real thing.

According to the embodiment according to the present disclosure, the accuracy of determining the state of the processing apparatus 10 can be improved.

1 Condition judgment system 10 Processing equipment (12: wire, 14: roller, 16: wire group, 18: work holding mechanism, 20: nozzle, 32: guide roller, 33: dancer arm, 34: dancer roller, 35: touch roller, 36 : Drive motor, 38A, 38B: Wire reel, 40: Slurry tank, 42: Slurry chiller, W: Work (block), X: Roller axial direction)
50 Status determination device (51: control unit, 53: output unit, 54: input unit)
60 Sensor 71 Stop lot 72 Abnormality detection lot 73 Unit space lot 74 Unit space outside lot

Claims (7)

Equipped with a control unit that determines the status of the processing equipment
The control unit
The feature amount of each of the plurality of data items representing the state of the processing apparatus is acquired, and the feature amount is acquired.
Represents the characteristics of a lot group successfully processed by the processing apparatus, which is selected from the plurality of data items and is generated based only on the cause data item that causes the processing apparatus to stop in a known failure mode. In the unit space, the Mahalanobis distance of the feature amount of the cause data item is calculated.
A state determination device that outputs a result of determining that the state of the processing apparatus is an abnormal state based on the known failure mode when the Mahalanobis distance is equal to or greater than a threshold value set based on the unit space. The unit space includes at least a first unit space generated based on the first cause data item and a second unit space generated based on the second cause data item.
At least a part of the data items included in the first cause data item is not included in the second cause data item.
At least a part of the data items included in the second cause data item is not included in the first cause data item.
The control unit
When the Mahalanobis distance calculated in the first unit space becomes equal to or greater than the first threshold value, it is determined that the processing apparatus is in the first abnormal state.
The state determination device according to claim 1, wherein when the Mahalanobis distance calculated in the second unit space becomes equal to or larger than the second threshold value, it is determined that the processing device is in the second abnormal state. The control unit
When it is not determined that the state of the processing apparatus is an abnormal state based on the known failure mode, Mahalanobis of the feature amount of the plurality of data items in the unit space generated based on the plurality of data items. Calculate the distance,
When the Mahalanobis distance is equal to or greater than the unknown cause threshold value, a data item having an MD contribution degree indicating the magnitude of the influence on the Mahalanobis distance is determined as a cause candidate item and the cause candidate item is selected. The state determination device according to claim 1 or 2, which outputs the data. The control unit
The feature quantities of a plurality of data items obtained for each of the plurality of lots processed by the processing apparatus from the start of operation to the stop of the operation in the past predetermined period are acquired.
The plurality of lots are divided into lots within the unit space and lots outside the unit space.
The unit space is generated based on the feature amount of the lot in the unit space, and the unit space is generated.
The Mahalanobis distance of the feature amount of the lot outside the unit space is calculated in the unit space.
The state determination device according to any one of claims 1 to 3, wherein the threshold value is set to a value larger than the Mahalanobis distance of the feature amount of the lot outside the unit space. In the control unit, the difference between the Mahalanobis distance of the feature amount of the lot outside the unit space calculated in the unit space and the Mahalanobis distance of the feature amount of the lot inside the unit space calculated in the unit space becomes a predetermined value or more. The state determination device according to claim 4, wherein the lot in the unit space and the lot outside the unit space are separated as described above. A step in which the state determination device for determining the state of the processing device acquires a feature amount of each of a plurality of data items representing the state of the processing device.
The state determination device was successfully processed by the processing device, which was generated based only on the cause data item selected from the plurality of data items and causing the processing device to stop in a known failure mode. In the unit space representing the characteristics of the lot group, the step of calculating the Mahalanobis distance of the characteristic amount of the cause data item and
The step of the state determining apparatus, and outputs the result of the Mahalanobis distance is determined and the state of the processing apparatus when it is above the threshold that is set based on the unit space is in an abnormal state based on the known failure mode A state determination method including and. To the processor of the state judgment device that judges the state of the processing device,
A step of acquiring the feature amount of each of a plurality of data items representing the state of the processing apparatus, and
Represents the characteristics of a lot group successfully processed by the processing apparatus, which is selected from the plurality of data items and is generated based only on the cause data item that causes the processing apparatus to stop in a known failure mode. In the unit space, the step of calculating the Mahalanobis distance of the feature amount of the cause data item and
State determination and a step of outputting the result of the Mahalanobis distance is determined and the state of the processing apparatus when it is above the threshold that is set based on the unit space is in an abnormal state based on the known failure mode program.

Images