Abnormality diagnosing device and method for wire saw

Abstract

The abnormality diagnosis device for the wire saw (1) includes a diagnosis mode execution unit (51), a data set acquisition unit (52), a deviation information calculation unit (54), and a determination unit (55). The diagnosis mode execution unit (51) executes the following diagnosis modes before cutting with the wire saw (1): a first diagnosis mode where the processing roller rotates at a constant speed, a second diagnosis mode where the winding spool rotates at a constant speed, and a third diagnosis mode where the winding spool rotates at a constant speed. The data set acquisition unit (52) acquires first to third data sets for multiple data items using the first to third diagnosis modes. The deviation information calculation unit (54) calculates deviation information related to the deviation obtained by comparing the first to third data sets with the first to third reference data sets under normal conditions. The determination unit (55) determines whether the wire saw (1) has any abnormalities based on the deviation information. Thus, the operating status of the wire saw before cutting is fully monitored, and abnormality diagnosis is accurately performed.

Description

Technical Field

[0001] This invention relates to a device and method for diagnosing abnormalities in wire saws. Background Technology

[0002] There are wire saws that use saw wire to cut workpieces such as semiconductor materials and magnetic materials (for example, see Patent Document 1). This wire saw performs cutting by moving saw wires wound at predetermined intervals around multiple processing rollers at high speed and pushing the workpiece against the saw wires. Generally, a wire saw includes: multiple processing rollers on which the saw wire is wound; a feed spool for feeding the saw wire to the processing rollers; and a winding spool for winding the saw wire fed from the processing rollers.

[0003] The device described in Patent Document 1 measures the tension of the saw wire and the vibration of a vibration sensor installed in the workpiece holding part before cutting the workpiece, and uses the measured values ​​to determine whether the wire saw is normal or abnormal. Moreover, if the wire saw is determined to be normal, the workpiece is cut, thereby preventing the quality deterioration of products such as wafers cut from the workpiece (see paragraphs

[0009] and

[0010] of Patent Document 1).

[0004] [Existing Technical Documents]

[0005] [Patent Literature]

[0006] Patent Document 1: Japanese Patent Application Publication No. 6729697. Summary of the Invention

[0007] [The technical problem the invention aims to solve]

[0008] It can be assumed that in the device of Patent Document 1, the wire saw operates under the same conditions as during subsequent cutting operations, such as a constant wire speed (linear speed), and the measurement is performed before the workpiece is cut.

[0009] However, wire saws are complex structures requiring multi-axis synchronous control of the processing rollers, feed spools, and winding spools. When operating at a constant linear speed, the amount of wire stored and the effective diameter of the feed spool and winding spool vary each time. Furthermore, sometimes during maintenance, repairs to the grooves on the outer circumference of the planing rollers reduce the effective diameter, causing further variations. Therefore, the monitoring of the operating status of the device in Patent Document 1 before cutting is not sufficient, making accurate anomaly diagnosis difficult.

[0010] The objective of this invention is to accurately diagnose abnormalities by fully monitoring the operating status of a wire saw before cutting.

[0011] [Technical solutions used to solve technical problems]

[0012] To address the aforementioned issues, the present invention provides an anomaly diagnosis device for a wire saw that uses a saw wire for cutting workpieces. The wire saw comprises: a plurality of processing rollers; a saw wire wound around the plurality of processing rollers; a feed spool for feeding the saw wire to the processing rollers; and a winding spool for winding the saw wire fed from the processing rollers. The abnormality diagnosis device includes: a diagnosis mode execution unit that executes the following diagnosis modes before the cutting process: a first diagnosis mode that operates the wire saw by making the processing roller rotate at a constant first rotation speed; a second diagnosis mode that operates the wire saw by making the delivery spool rotate at a constant second rotation speed; and a third diagnosis mode that operates the wire saw by making the winding spool rotate at a constant third rotation speed; a data set acquisition unit that acquires, respectively, a first data set obtained through the first diagnosis mode, a second data set obtained through the second diagnosis mode, and a third data set obtained through the third diagnosis mode for multiple data items representing the operating state of the wire saw; a deviation information calculation unit that calculates deviation information for the multiple data items, the deviation information being related to the following deviation: a deviation obtained by comparing the first reference data set obtained through the first diagnosis mode when the wire saw is operating normally, the second reference data set obtained through the second diagnosis mode when the wire saw is operating normally, and the third reference data set obtained through the third diagnosis mode when the wire saw is operating normally with the first data set, the second data set, and the third data set, respectively; and a determination unit that determines whether the wire saw has an abnormality based on the calculated deviation information.

[0013] In addition, the present invention is an abnormality diagnosis method for a wire saw that uses saw wire to cut workpieces. The abnormality diagnosis method includes the following steps: before the cutting process, performing the following diagnostic modes respectively: a first diagnostic mode that operates the wire saw by making the processing roller a constant first rotational speed, a second diagnostic mode that operates the wire saw by making the delivery spool a constant second rotational speed, and a third diagnostic mode that operates the wire saw by making the winding spool a constant third rotational speed; obtaining the following data sets for multiple data items representing the operating state of the wire saw respectively: a first data set obtained through the first diagnostic mode, a second data set obtained through the second diagnostic mode, and a third data set obtained through the third diagnostic mode; calculating deviation information for the multiple data items, the deviation information relating to the following deviations: a deviation obtained by comparing a first reference data set obtained through the first diagnostic mode when the wire saw is normal, a second reference data set obtained through the second diagnostic mode when the wire saw is normal, and a third reference data set obtained through the third diagnostic mode when the wire saw is normal with the first data set, the second data set, and the third data set respectively; and determining whether the wire saw has any abnormalities based on the calculated deviation information.

[0014] [Invention Effects]

[0015] According to the present invention, the operating status of the wire saw before cutting can be fully monitored and anomalies can be accurately diagnosed. Attached Figure Description

[0016] Figure 1 This is a diagram showing the schematic structure of a wire saw using an abnormality diagnosis device according to an embodiment of the present invention.

[0017] Figure 2 This is a schematic block diagram representing the control structure of a wire saw.

[0018] Figure 3 This is a functional block diagram representing the internal structure related to anomaly diagnosis in the control device of a wire saw.

[0019] Figure 4 This is a flowchart illustrating the content of the anomaly diagnosis method involved in this embodiment. Detailed Implementation

[0020] Embodiments of the present invention will be described in detail with appropriate reference to the accompanying drawings.

[0021] Furthermore, in each drawing, common components and components of the same type are given the same reference numerals, and repeated descriptions are omitted where appropriate. In addition, for ease of explanation, the dimensions and shapes of components are sometimes distorted or exaggerated to represent them schematically.

[0022] Figure 1 This is a diagram showing the schematic structure of the wire saw 1 of the abnormality diagnosis device according to an embodiment of the present invention.

[0023] like Figure 1 As shown, the wire saw 1 uses a saw wire 2 to cut the workpiece 15. The wire saw 1 includes: a plurality of processing rollers 6; a feed spool 3 that feeds the saw wire 2 to the processing rollers 6; and a winding spool 9 that winds the saw wire 2 fed from the processing rollers 6. For example, the saw wire 2 of the abrasive type is wound around the plurality of processing rollers 6 that extend in parallel at predetermined intervals.

[0024] Multiple annular grooves (not shown) are formed on the outer circumferential surface of the processing roller 6 at a predetermined pitch. A saw wire 2, made of a single wire, continuously wraps around each groove of the multiple processing rollers 6. In this embodiment, two processing rollers 6 are arranged.

[0025] The saw wire 2 is fed from the feed reel 3, and is wound multiple times on two processing rollers 6 via the traverse device 4 and tension adjustment roller device 5 on the feed side, and then wound onto the winding reel 9 via the tension adjustment roller device 7 and traverse device 8 on the winding side.

[0026] The saw wire 2 reciprocates between two processing rollers 6. In this case, the saw wire 2 is driven in a step-like manner, alternating between a certain amount of forward movement and a certain amount of backward movement less than that amount of forward movement. Alternatively, the saw wire 2 can also be driven to move continuously in one direction.

[0027] The traversing devices 4 and 8 are provided to ensure that the saw wire 2 is always orthogonal to the axis of the feed spool 3 or the winding spool 9, respectively. In addition, the tension adjusting roller devices 5 and 7 are provided to allow the reciprocating movement of the saw wire 2 while applying a certain tension to the saw wire 2 through the reciprocating motion of the tension adjusting rollers (not shown).

[0028] The saw wires 2 form a cutting zone between the two processing rollers 6 and the workpiece 15 being processed. The spacing of the saw wires 2 in the cutting zone is limited by the pitch of the grooves formed on the outer peripheral surface of the processing rollers 6. The pitch of the grooves determines the thickness of the plate-like body, i.e., the wafer, after the workpiece 15 has been cut.

[0029] The spool 3, processing roller 6, and winding spool 9 are respectively driven by a spool drive motor 11, a processing roller drive motor 12, and a winding spool drive motor 13. These motors 11, 12, and 13 are all controlled by a control device 50 (see reference). Figure 2 )control.

[0030] The workpiece 15 is fixed at a position corresponding to the cutting area of ​​the saw wire 2 between the two processing rollers 6 by the feed device 16 for processing, and is pushed into the cutting area of ​​the saw wire 2 at a predetermined feed speed. The workpiece feed motor 14 of the feed device 16 has, for example, a built-in rotary-linear motion conversion mechanism such as a feed screw unit (not shown). Under the control of the control device 50, the workpiece feed motor 14 moves the workpiece 15 in the processing feed direction at a predetermined feed speed in accordance with the feed movement amount of the workpiece 15 for cutting processing. The feed movement amount corresponds to the feed position and even the cutting depth of the workpiece 15, and is detected by a signal from the encoder 20 connected to the workpiece feed motor 14.

[0031] Encoders 17, 18, and 19 are connected to motor 11 for driving the feed reel, motor 12 for driving the processing roller, and motor 13 for driving the winding reel, respectively. Therefore, the rotational speeds of the feed reel 3, the processing roller 6, and the winding reel 9 are detected using signals from encoders 17, 18, and 19, respectively.

[0032] Figure 2 This is a schematic block diagram representing the control structure of the wire saw 1.

[0033] like Figure 2 As shown, the wire saw 1 includes a control device 50 that provides overall control over all parts of the wire saw 1. The control device 50 includes a CPU (Central Processing Unit) (not shown), and storage units such as RAM, ROM, and hard disk. The storage units store programs for executing the anomaly diagnosis method according to this embodiment.

[0034] Signals from encoders 17-20 are input to control device 50. Control device 50 controls the driving of motors 11-14 via drivers 21-24. Input device 25 and display device 26 are connected to control device 50. Input device 25 receives and processes user operations and other information. Display device 26 displays operation screens, display screens, alarm messages, and other information. Signals from vibration detection units 31-33 and temperature detection units 34-36 are also input to control device 50.

[0035] Vibration detection unit 31 detects the vibration characteristics of the feed roll 3 or its support member (not shown). Vibration detection unit 32 detects the vibration characteristics of the processing roller 6 or its support member (not shown). Vibration detection unit 33 detects the vibration characteristics of the winding roll 9 or its support member (not shown). The support members for the processing roller 6, the feed roll 3, and the winding roll 9 are, for example, bearings or housings for the bearings. Temperature detection unit 34 detects the temperature of the feed roll 3 or its support member. Temperature detection unit 35 detects the temperature of the processing roller 6 or its support member. Temperature detection unit 36 ​​detects the temperature of the winding roll 9 or its support member. Vibration detection unit 32 and temperature detection unit 35 are provided corresponding to one or both of the two processing rollers 6.

[0036] In wire saw 1, for example, the bearings of the processing roller 6 typically have a short lifespan due to high load and high speed rotation. Furthermore, the motor load on the motor driving the processing roller 6 can sometimes become excessively high. Additionally, thermal displacement caused by temperature rise around the processing area of ​​the workpiece 15 can sometimes lead to warping of the wafer obtained from cutting the workpiece 15, thus reducing the processing quality of the workpiece 15. Therefore, various abnormalities can occur in wire saw 1. Even if an abnormality is detected during cutting using wire saw 1, it is sometimes difficult to repair immediately, and in such cases, a decrease in yield cannot be avoided. In contrast, this embodiment performs abnormality diagnosis of wire saw 1 before cutting.

[0037] Figure 3 This is a functional block diagram representing the internal structure related to anomaly diagnosis in the control device 50 of the wire saw 1.

[0038] like Figure 3 As shown, the control device 50 of the wire saw 1 includes: a diagnostic mode execution unit 51, a data acquisition unit 52, a reference data set setting unit 53, a deviation information calculation unit 54, a judgment unit 55, and a main cause inference unit 56. Figure 3 The components shown constitute the fault diagnosis device for the wire saw 1. The functions of these components are implemented in the control device 50 by executing a specified program stored in the memory unit on the RAM. Furthermore, Figure 3 The components shown can also be control circuits made of hardware.

[0039] The diagnostic mode execution unit 51 executes three diagnostic modes: a first diagnostic mode, a second diagnostic mode, and a third diagnostic mode. The first diagnostic mode operates the wire saw 1 at a constant first rotational speed for the processing roller 6 before cutting. The second diagnostic mode operates the wire saw 1 at a constant second rotational speed for the delivery spool 3 before cutting. The third diagnostic mode operates the wire saw 1 at a constant third rotational speed for the winding spool 9. In these first, second, and third diagnostic modes, the saw wire 2 operates without contacting the workpiece 15 (hereinafter also referred to as "idle operation").

[0040] The data acquisition unit 52 acquires: a first data group obtained through a first diagnostic mode, a second data group obtained through a second diagnostic mode, and a third data group obtained through a third diagnostic mode.

[0041] The first to third data groups are obtained from multiple data items representing the operating status of the wire saw 1.

[0042] In this embodiment, the data items obtained in the first data set are: the torque load of the motor 12 that drives the rotation of the processing roller 6, the temperature of the processing roller 6 or its support member (not shown), and the vibration characteristics of the processing roller 6 or its support member. However, other data items may also be included. The data items obtained in the second data set are: the torque load of the motor 11 that drives the rotation of the given spool 3, the temperature of the given spool 3 or its support member (not shown), and the vibration characteristics of the given spool 3 or its support member. However, other data items may also be included. The data items obtained in the third data set are: the torque load of the motor 13 that drives the rotation of the winding spool 9, the temperature of the winding spool 9 or its support member (not shown), and the vibration characteristics of the given spool 3 or its support member. However, other data items may also be included.

[0043] The vibration characteristics can be represented by amplitude, frequency, or characteristic quantities referred to as changes or existence. The torque load of motors 11 to 13 is determined by the torque command values ​​output from control device 50 to drivers 21 to 23, or the drive current values ​​output from drivers 21 to 23 to motors 11 to 13.

[0044] The reference data set setting unit 53 sets a first reference data set, a second reference data set, and a third reference data set as data sets constituting a unit space. The first reference data set contains multiple data items identical to those obtained when the first data set was acquired, obtained through a first diagnostic mode when the wire saw 1 is functioning normally. The second reference data set contains multiple data items identical to those obtained when the second data set was acquired, obtained through a second diagnostic mode when the wire saw 1 is functioning normally. The third reference data set contains multiple data items identical to those obtained when the third data set was acquired, obtained through a third diagnostic mode when the wire saw 1 is functioning normally. The first, second, and third reference data sets are set in advance before acquiring them.

[0045] The deviation information calculation unit 54 calculates deviation information related to the following deviations: deviations obtained by comparing the first reference data set, the second reference data set, and the third reference data set with the first data set, the second data set, and the third data set, respectively. That is, the deviation information includes: first deviation information regarding the deviation between the first reference data set and the first data set; second deviation information regarding the deviation between the second reference data set and the second data set; and third deviation information regarding the deviation between the third reference data set and the third data set. In other words, the deviation information includes: first deviation information obtained through the first diagnostic mode; second deviation information obtained through the second diagnostic mode; and third deviation information obtained through the third diagnostic mode.

[0046] In this embodiment, the first deviation information is the Mahalanobis distance between a first unit space composed of a first reference data set and a first signal space composed of the first data set. The second deviation information is the Mahalanobis distance between a second unit space composed of a second reference data set and a second signal space composed of the second data set. The third deviation information is the Mahalanobis distance between a third unit space composed of a third reference data set and a third signal space composed of the third data set. Alternatively, the deviation information can be calculated using a deviation information calculation model learned through machine learning.

[0047] The determination unit 55 determines whether the wire saw 1 has any abnormalities based on the deviation information calculated by the deviation information calculation unit 54. In this embodiment, this determination is performed by comparing the Mahalanobis distance, which is the deviation information, with a preset threshold. That is, the determination unit 55 monitors the situation where the Mahalanobis distance calculated by the deviation information calculation unit 54 does not exceed the predetermined threshold.

[0048] Under normal operating conditions, the Mahalanobis distance of the wire saw 1 converges within a specific range. However, when the operating condition exhibits abnormal signs, the correlations between multiple data items deviate from the unit space. Therefore, by calculating the Mahalanobis distance used in the MT method and the standardized error compression method, abnormalities in the operating condition of the wire saw 1 can be diagnosed.

[0049] When the main cause inference unit 56 determines that there is an anomaly in the wire saw 1, it infers the main cause of the anomaly based on the contribution of each of the multiple data items to the Mahalanobis distance, which is the information of deviation.

[0050] Next, refer to Figure 4 The abnormality diagnosis method involved in this embodiment will be described.

[0051] Figure 4 This is a flowchart illustrating the content of the anomaly diagnosis method involved in this embodiment.

[0052] like Figure 4 As shown, the diagnostic mode execution unit 51 executes one of a plurality of diagnostic modes (step S1). Specifically, firstly, before the cutting process, a first diagnostic mode is executed to make the wire saw idling so that the processing roller 6 is at a constant first rotational speed.

[0053] Next, the data acquisition unit 52 acquires the first data set obtained through the first diagnostic mode for multiple data items representing the operating status of the wire saw 1 (step S2).

[0054] In step S3, it is determined whether all of the multiple diagnostic modes, namely the first diagnostic mode, the second diagnostic mode, and the third diagnostic mode, have been executed. If all of the multiple diagnostic modes have been executed ("Yes" in step S3), proceed to step S4. If there are any diagnostic modes that have not been executed ("No" in step S3), return to step S1.

[0055] Therefore, steps S1 and S2 are repeated to obtain a second data set obtained by idling the wire saw 1 using a second diagnostic mode that keeps the given reel 3 at a constant second rotational speed. Additionally, a third data set is obtained by idling the wire saw 1 using a third diagnostic mode that keeps the winding reel 9 at a constant third rotational speed.

[0056] Next, the deviation information calculation unit 54 calculates the deviation information (step S4). The deviation information is information about the deviation obtained by comparing the first reference data set, the second reference data set, and the third reference data set with the first data set, the second data set, and the third data set, respectively. Here, the first to third reference data sets are obtained in advance by using the first to third diagnostic modes when the above-mentioned multiple data items are normal on the online saw 1.

[0057] In step S5, the determination unit 55 determines whether the wire saw 1 is abnormal based on the deviation information calculated by the deviation information calculation unit 54. In this embodiment, if the Mahalanobis distance, which is the deviation information, does not exceed a preset threshold, it is determined that the wire saw 1 is not abnormal. Furthermore, this determination is performed separately for each of the first deviation information, the second deviation information, and the third deviation information constituting the deviation information.

[0058] If it is determined that the wire saw 1 is normal (No in step S5), proceed to step S7. If it is determined that the wire saw 1 is abnormal (Yes in step S5), proceed to step S6.

[0059] In step S6, the principal cause inference unit 56 infers the main cause of the anomaly based on the contribution of each of the multiple data items to the Mahalanobis distance, which serves as deviation information. For example, the principal cause inference unit 56 infers the data items that contribute highly to the increase in the Mahalanobis distance as the main cause that should be investigated. Alternatively, more specific main causes can be inferred, for example, empirically or experimentally, based on the distribution of the contributions of the multiple data items.

[0060] In step S7, the determination result of the determination unit 55, i.e., whether the wire saw 1 is abnormal, is displayed on the display device 26. Furthermore, if it is determined that the wire saw 1 is abnormal, the main cause of the abnormality inferred by the main cause inference unit 56 is displayed on the display device 26. At this time, various information may also be displayed on the display device 26, such as alarm messages urging the wire saw 1 to stop operating, empirically or experimentally derived handling methods, etc.

[0061] As described above, the fault diagnosis device for the wire saw 1 according to this embodiment includes: a diagnosis mode execution unit 51, which executes the following diagnosis modes before cutting: a first diagnosis mode that operates the wire saw 1 by making the processing roller 6 rotate at a constant first speed; a second diagnosis mode that operates the wire saw 1 by making the delivery spool 3 rotate at a constant second speed; and a third diagnosis mode that operates the wire saw 1 by making the winding spool 9 rotate at a constant third speed; and a data acquisition unit 52, which acquires, respectively, a first data set obtained through the first diagnosis mode, and a third data set obtained through the third diagnosis mode for multiple data items representing the operating state of the wire saw 1. The second data set obtained through the second diagnostic mode and the third data set obtained through the third diagnostic mode; the deviation information calculation unit 54 calculates deviation information for multiple data items, the deviation information being related to the following deviations: the deviation obtained by comparing the first reference data set obtained through the first diagnostic mode when the wire saw 1 is normal, the second reference data set obtained through the second diagnostic mode when the wire saw 1 is normal, and the third reference data set obtained through the third diagnostic mode when the wire saw 1 is normal with the first data set, the second data set, and the third data set respectively; and the determination unit 55 determines whether the wire saw 1 has any abnormalities based on the calculated deviation information.

[0062] In this embodiment, before cutting using the wire saw 1, a first diagnostic mode is executed, in which the processing roller 6 rotates at a constant speed; a second diagnostic mode is executed, in which the reel 3 rotates at a constant speed; and a third diagnostic mode is executed, in which the winding reel 9 rotates at a constant speed. Furthermore, in the first to third diagnostic modes, first to third sets of data are acquired for multiple data items, and based on the deviation information calculated by comparing these data with the first to third reference data sets under normal conditions, it is determined whether the wire saw 1 has any abnormalities.

[0063] The wire saw 1 typically operates at a constant linear speed. During this operation, the amount of wire stored in the feed spool 3 and the winding spool 9, as well as their effective diameter, vary each time. Furthermore, maintenance may sometimes cause a decrease in the effective diameter of the processing roller 6. Thus, the operating state before the cutting process is usually inconsistent, making it difficult to adequately monitor the operating state in the prior art. In contrast, this embodiment is configured to sequentially execute a first to a third diagnostic mode, where the rotational speeds of the processing roller 6, the feed spool 3, and the winding spool 9 are each individually set to a constant speed, to acquire data sets before the cutting process.

[0064] Therefore, according to this embodiment, the operating status of the wire saw 1 before cutting can be fully monitored and abnormalities can be accurately diagnosed. This allows for the prevention of abnormalities in the wire saw 1 during cutting, thus preventing the wire saw 1 from stopping or requiring repair during cutting and improving the yield rate.

[0065] Furthermore, in this embodiment, the multiple data items obtained when the first data set and the first reference data set are obtained include: the torque load of the motor 12 that drives the rotation of the processing roller 6, the temperature of the processing roller 6 or its support member, and the vibration characteristics of the processing roller 6 or its support member. In this structure, a data set of data items related to the processing roller 6, which is particularly relevant to the diagnosis of anomalies in the wire saw 1, is obtained. Therefore, efficient and effective anomaly diagnosis can be performed.

[0066] Furthermore, in this embodiment, the multiple data items obtained when acquiring the second data set and the second reference data set include: the torque load of the motor 11 that drives the rotation of the given reel 3, the temperature of the given reel 3 or its support member, and the vibration characteristics of the given reel 3 or its support member. In this structure, a data set of data items highly correlated with the given reel 3 for anomaly diagnosis of the wire saw 1 is obtained. Therefore, efficient and effective anomaly diagnosis can be performed.

[0067] Furthermore, in this embodiment, the multiple data items obtained when obtaining the third data set and the third reference data set include: the torque load of the motor 13 that drives the rotation of the winding spool 9, the temperature of the winding spool 9 or its support member, and the vibration characteristics of the winding spool 9 or its support member. In this structure, a data set of data items related to the winding spool 9, which are highly correlated with the anomaly diagnosis of the wire saw 1, is obtained. Therefore, efficient and effective anomaly diagnosis can be performed.

[0068] Furthermore, in this embodiment, the deviation information calculation unit 54 calculates the Mahalanobis distance between the unit space composed of a pre-set reference data set and the signal space composed of the acquired data set as deviation information. In this structure, it is possible to determine whether the wire saw 1 has any abnormalities based on whether the Mahalanobis distance exceeds a predetermined threshold.

[0069] Furthermore, this embodiment includes a primary cause inference unit 56, which infers the primary cause of the anomaly based on the contribution of each of the multiple data items to the deviation information. In this structure, appropriate actions such as replacement, repair, and adjustment of parts of the wire saw 1 related to the inferred primary cause of the anomaly can be performed on it.

[0070] The present invention has been described above based on embodiments; however, the present invention is not limited to the structures described in the above embodiments. The present invention includes appropriate combinations and even selections of the structures described in the above embodiments, and its structure can be appropriately modified without departing from its spirit. Furthermore, it is possible to add, delete, or replace parts of the structures described in the above embodiments.

[0071] For example, in the above embodiment, two processing rollers 6 are configured, but this is not the only option. For example, three rollers may be configured at the vertices of the inverted triangle, or four rollers may be configured at the vertices of the quadrilateral.

[0072] [Explanation of reference numerals in the attached figures]

[0073] 1-wire saw

[0074] 2. Saw wire

[0075] 3. Give the scroll

[0076] 6 Processing Rollers

[0077] 9 rolls of reel

[0078] 11-13 motors

[0079] 15 workpieces

[0080] 31-33 Vibration detection unit; 34-36 Temperature detection unit; 51 Diagnostic mode execution unit.

[0081] 52 Data Acquisition Department

[0082] 54 Deviation Information Calculation Department

[0083] 55 Judgment Department

[0084] 56. Main Causes Inference Section

Claims

1. A fault diagnosis device for a wire saw, the wire saw comprising: a plurality of processing rollers; a saw wire wound on the plurality of processing rollers; a feed spool for feeding the saw wire to the processing rollers; and a winding spool for winding the saw wire fed from the processing rollers, the wire saw using the saw wire to cut workpieces, the fault diagnosis device for the wire saw characterized in that it includes: The diagnostic mode execution unit executes the following diagnostic modes before the cutting process: a first diagnostic mode that operates the wire saw by making the processing roller a constant first rotational speed, a second diagnostic mode that operates the wire saw by making the delivery spool a constant second rotational speed, and a third diagnostic mode that operates the wire saw by making the winding spool a constant third rotational speed. The data acquisition unit acquires, respectively, a first data group obtained through the first diagnostic mode, a second data group obtained through the second diagnostic mode, and a third data group obtained through the third diagnostic mode for multiple data items representing the operating status of the wire saw. The deviation information calculation unit calculates deviation information for multiple data items. The deviation information is related to the following deviations: the deviation obtained by comparing the first reference data set obtained through the first diagnostic mode when the wire saw is normal with the first data set, the second reference data set obtained through the second diagnostic mode when the wire saw is normal with the second data set, and the third reference data set obtained through the third diagnostic mode when the wire saw is normal with the third data set. as well as The determination unit determines whether the wire saw has any abnormalities based on the calculated deviation information.

2. The abnormality diagnosis device for a wire saw according to claim 1, characterized in that, The data items obtained when the first data set and the first reference data set are: the torque load of the motor that drives the rotation of the processing roller, the temperature of the processing roller or the support member of the processing roller, and the vibration characteristics of the processing roller or the support member of the processing roller.

3. The abnormality diagnosis device for a wire saw according to claim 1, characterized in that, The data items obtained when the second data set and the second reference data set are: the torque load of the motor that drives the rotation of the given reel, the temperature of the given reel or its support member, and the vibration characteristics of the given reel or its support member.

4. The abnormality diagnosis apparatus of the wire saw according to claim 1, characterized by The data items obtained when the third data set and the third reference data set are obtained include: the torque load of the motor that drives the rotation of the winding spool, the temperature of the winding spool or the support member of the winding spool, and the vibration characteristics of the winding spool or the support member of the winding spool.

5. The abnormality diagnosis device for a wire saw according to claim 1, characterized in that, The deviation information calculation unit calculates the Mahalanobis distance as the deviation information. The Mahalanobis distance is obtained by comparing the first unit space composed of the first reference data group with the first signal space composed of the first data group, the second unit space composed of the second reference data group with the second signal space composed of the second data group, and the third unit space composed of the third reference data group with the third signal space composed of the third data group.

6. The abnormality diagnosis device for a wire saw according to claim 1, characterized in that, The abnormality diagnosis device for the wire saw includes a main cause inference unit. When the wire saw is determined to be abnormal, the main cause inference unit infers the main cause of the abnormality based on the contribution of each of the multiple data items to the deviation information.

7. A method for diagnosing anomalies in a wire saw, the wire saw comprising: a plurality of processing rollers; saw wire wound around the plurality of processing rollers; a feed spool for feeding the saw wire to the processing rollers; and a winding spool for winding the saw wire fed from the processing rollers, the wire saw using the saw wire to cut workpieces, the method for diagnosing anomalies in the wire saw characterized by comprising the following steps: Before the cutting process, the following diagnostic modes are performed respectively: a first diagnostic mode that operates the wire saw in a way that makes the processing roller a constant first rotational speed, a second diagnostic mode that operates the wire saw in a way that makes the delivery spool a constant second rotational speed, and a third diagnostic mode that operates the wire saw in a way that makes the winding spool a constant third rotational speed. The steps for obtaining the following data sets for each of the multiple data items representing the operating status of the wire saw are: a first data set obtained through the first diagnostic mode; a second data set obtained through the second diagnostic mode; and a third data set obtained through the third diagnostic mode. The step of calculating deviation information for multiple data items, wherein the deviation information relates to the following deviations: deviations obtained by comparing a first reference data set obtained through the first diagnostic mode when the wire saw is normal with the first data set, a second reference data set obtained through the second diagnostic mode when the wire saw is normal with the second data set, and a third reference data set obtained through the third diagnostic mode when the wire saw is normal with the third data set; and deviations obtained by comparing the first reference data set obtained through the first diagnostic mode when the wire saw is normal with the third data set; and The step of determining whether the wire saw has any abnormalities based on the calculated deviation information.

Images