WO2019186620A1 - Abnormality sign detection device and machine tool - Google Patents

Abnormality sign detection device and machine tool Download PDF

Info

Publication number
WO2019186620A1
WO2019186620A1 PCT/JP2018/012013 JP2018012013W WO2019186620A1 WO 2019186620 A1 WO2019186620 A1 WO 2019186620A1 JP 2018012013 W JP2018012013 W JP 2018012013W WO 2019186620 A1 WO2019186620 A1 WO 2019186620A1
Authority
WO
WIPO (PCT)
Prior art keywords
abnormality
sign
tool
unit
sign detection
Prior art date
Application number
PCT/JP2018/012013
Other languages
French (fr)
Japanese (ja)
Inventor
アヌスヤ ナラサンビ
弘健 江嵜
内田　剛
博史 大池
Original Assignee
株式会社Ｆｕｊｉ
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社Ｆｕｊｉ filed Critical 株式会社Ｆｕｊｉ
Priority to PCT/JP2018/012013 priority Critical patent/WO2019186620A1/en
Priority to JP2020510174A priority patent/JP7000560B2/en
Publication of WO2019186620A1 publication Critical patent/WO2019186620A1/en

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
    • B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
    • B23Q17/09—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool

Definitions

  • This specification discloses an abnormality sign detection device and a machine tool.
  • the main purpose of the present disclosure is to enable appropriate use of a tool by enabling detection of a sign of tool abnormality at an early stage.
  • An abnormality sign detection device of the present disclosure is an abnormality sign detection device that detects a sign of abnormality of a tool used for machining, a data collection unit that collects vibration data of the tool during machining, and the machine A model construction unit that constructs a determination model in a one-class support vector machine using the vibration data collected by the data collection unit in a predetermined period at the beginning of processing as normal region data, and the model construction unit constructed by the model construction unit A gist is provided with a sign detection unit that detects whether or not the tool has an abnormality by determining whether or not the vibration data is included in the normal region using a determination model.
  • the abnormality sign detection device of the present disclosure constructs a determination model in a one-class support vector machine using vibration data collected in a predetermined period at the beginning of machining as normal region data, and the vibration data is in the normal region of the determination model. By determining whether or not it is included, the presence or absence of a sign of abnormality of the tool is detected. Thereby, the determination model can be constructed in a predetermined period at the beginning of machining, and detection of a sign of abnormality can be started promptly. In addition, for the same type of tool that performs machining with the same content, it is also possible to detect a sign of abnormality from the beginning of machining using the already established determination model. Therefore, it is possible to detect a sign of abnormality of the tool at an early stage, and to appropriately use the tool.
  • FIG. 1 is a configuration diagram illustrating an example of a schematic configuration of a machine tool 10.
  • Explanatory drawing which shows an example of the time transition of vibration data.
  • the flowchart which shows an example of an abnormality sign detection process.
  • Explanatory drawing which shows an example of threshold value Th and similarity Ds.
  • Explanatory drawing which shows an example of the time transition of vibration data and similarity Ds.
  • FIG. 1 is a configuration diagram illustrating an example of a schematic configuration of the machine tool 10
  • FIG. 2 is an explanatory diagram illustrating an electrical connection relationship of the machine tool 10. 1 is defined as the Y-axis direction, the vertical direction as the Z-axis direction, and the direction perpendicular to the paper surface of FIG. 1 as the X-axis direction.
  • the machine tool 10 is configured as a processing apparatus such as a machining center that performs a processing operation on the workpiece W using a tool T such as a tip or a drill.
  • the machine tool 10 includes a base 12 as a gantry, a table 14 and a column 16 provided on the base 12, a work chuck device 20, a spindle device 30, and a spindle moving mechanism. 40 and a control device 50.
  • the machine tool 10 includes an operation panel 18 and a notification device 19.
  • the operation panel 18 is configured as a touch panel type liquid crystal screen, and displays various instruction screens such as processing menus, various setting change screens, status screens indicating work conditions, etc., and selection and setting operations by the operator. Or accept.
  • the operation panel 18 includes a power button for turning on / off the power of the machine tool 10, a start button for starting the operation of the machine tool 10, a stop button for stopping the operation, and the like.
  • the alarm 19 includes a speaker that outputs a warning sound or a sound indicating an abnormality, a rotating lamp that is lit in an abnormality notification mode, and the like.
  • the machine tool 10 includes an automatic tool changer (not shown), and can automatically change the tool T mounted on the spindle device 30 according to the content of machining.
  • the work chuck device 20 is configured by a mounting table 22 on the table 14 on which the workpiece W is mounted, a servo motor and a ball screw mechanism (not shown), and the like.
  • a Y-axis moving mechanism that moves the mounting table 22 in the Y-axis direction. 24, a plurality of pairs of chuck claws 26 for chucking the workpiece W placed on the placing table 22, and an opening / closing device (not shown) for opening and closing the chuck claws 26.
  • the spindle device 30 includes a spindle 32 on which a tool T is replaceably mounted at the tip, a spindle motor 34 that rotationally drives the spindle 32, and a vibration sensor 36 that detects vibration of the spindle 32.
  • the main shaft moving mechanism 40 includes a servo motor and a ball screw mechanism (not shown).
  • the main shaft moving mechanism 40 moves the main shaft device 30 in the Z-axis direction, and the main shaft device 30 provided on the column 16 is moved to the Z-axis moving mechanism.
  • an X-axis moving mechanism 44 that moves the entire 42 in the X-axis direction.
  • the control device 50 includes a CPU, ROM, RAM, various interfaces, etc., not shown.
  • a detection value of the vibration sensor 36 of the spindle device 30, a position signal from each servo motor, an operation signal received by the operation panel 18, and the like are input to the control device 50.
  • the control device 50 includes a servo motor and a switching device for the Y-axis moving mechanism 24 of the work chuck device 20, a spindle motor 34 for the spindle device 30, a Z-axis moving mechanism 42 for the spindle moving mechanism 40, and an X-axis moving mechanism 44.
  • a drive signal is output to the servo motor, a display signal is output to the operation panel 18, and an abnormal sign alarm notification command indicating an abnormal sign is output to the alarm device 19.
  • control device 50 has a function of detecting a sign of abnormality of the tool T by using a well-known 1 class support vector machine (hereinafter, 1 class SVM) using the vibration data from the vibration sensor 36.
  • FIG. 3 is a functional block diagram of the control device 50 relating to the detection of a sign of abnormality. As illustrated, the control device 50 includes a data collection unit 51, a feature amount extraction unit 53, a model construction unit 54, a similarity calculation unit 56, a threshold change unit 57, and an abnormality sign notification unit 58. .
  • the data collection unit 51 collects the detection voltage (V) of the vibration sensor 36 of the spindle device 30 as vibration data and stores it in a vibration data area 52 such as a RAM.
  • FIG. 4 is an explanatory diagram showing an example of time transition of vibration data, where the horizontal axis represents time (seconds) and the vertical axis represents the detection voltage (V) of the vibration sensor 36.
  • FIG. 4 shows an example of vibration data when the machine tool 10 performs a plurality of machining operations, for example, a plurality of drilling operations on one or a plurality of workpieces W.
  • the tool T such as a drill for drilling is continuously used
  • the tool T is worn out or fatigue is accumulated in the tool T.
  • the tool T may break depending on the degree of accumulation of fatigue.
  • the vibration data at the right end is remarkably large, and the tool T is broken.
  • it is desirable for the operator to replace the tool T at an appropriate timing before such breakage of the tool T occurs it is difficult for the operator to determine an appropriate replacement time for the tool T. For this reason, although the operator can still use it sufficiently, the operator may change the tool T early, or the operator's replacement of the tool T may be delayed and breakage may occur.
  • the accumulated degree of fatigue of the tool T is unknown or individual differences are large for each tool T, making it more difficult for the operator to determine the replacement time. Become.
  • the feature amount extraction unit 53 performs, for example, a fast Fourier transform (FFT) on the vibration data collected by the data collection unit 51, and extracts frequency feature amounts.
  • the model construction unit 54 treats the frequency feature quantity extracted by the feature quantity extraction unit 53 during a predetermined learning period as normal region data, and constructs a determination model 55 used for abnormality determination by the one-class SVM.
  • the similarity calculation unit 56 uses a threshold value Th as a criterion for classifying normal region data and other data in the one-class SVM determination model 55, and a frequency feature amount extracted by the feature amount extraction unit 53. And a similarity Ds indicating a distance from the threshold Th is calculated.
  • the abnormality determination in the one-class SVM it is determined as normal when the similarity Ds calculated by the similarity calculation unit 56 is 0 or more, and is determined as abnormal when the similarity Ds is less than 0.
  • the threshold changing unit 57 changes the setting of the threshold Th based on the setting changing operation of the threshold Th received via the operation panel 18.
  • the abnormality sign notification unit 58 outputs a notification command to the notification device 19 so as to notify that there is a sign of abnormality.
  • FIG. 5 is a flowchart showing an example of the abnormality sign detection process. This process is executed by each function relating to the above-described abnormality sign detection of the control device 50 in a state where the machine tool 10 is ready for machining.
  • the control device 50 first waits for the machining using the tool T to start (S100), and when the machining is started, based on the vibration data collected from the vibration sensor 36.
  • 1 class SVM determination model 55 is constructed (S110).
  • the determination model 55 is constructed until the predetermined learning period ends (S120).
  • the predetermined learning period may be, for example, a period from when the machine tool 10 starts drilling to when several drilling processes are completed.
  • the control device 50 constructs the determination model 55 based on the initial vibration data when machining is started. This is because the tool T is less likely to break during the initial period when machining is started, and vibration data obtained during that period can be handled as data in a normal state.
  • the control device 50 determines whether or not a threshold Th setting change operation has been accepted via the operation panel 18 (S130) and whether or not machining is in progress (S150). To do.
  • the control device 50 changes the setting of the threshold Th based on the setting change operation (S140).
  • S140 setting change operation
  • control device 50 determines that machining is being performed in S150, whether or not the vibration data collected from the vibration sensor 36 is included in the normal region of the determination model 55 using the determination model 55 constructed in S110. Based on the above, a sign of abnormality is detected (S160). Further, the control device 50 determines whether or not there is a sign of abnormality in the processing of S160 (S170) and whether or not the machining (once processing) being executed is completed (S180), The process of S160 is continued. In S160, as described above, the control device 50 compares the feature quantity of the frequency extracted from the vibration data with the threshold value Th, calculates the similarity Ds indicating the distance between the feature quantity and the threshold Th, and calculates the similarity degree. If Ds is less than 0, it is determined in S170 that there is a sign of abnormality. Note that if the degree of similarity Ds is 0 or more, the control device 50 determines that there is no sign of abnormality in S170.
  • FIG. 6 is an explanatory diagram showing an example of the threshold Th and the similarity Ds.
  • ⁇ indicates data of the determination model 55 collected during the learning period
  • ⁇ and ⁇ indicate data after model construction.
  • the dotted line indicates the threshold Th of the normal region
  • the control device 50 determines that there is no sign of abnormality if the similarity Ds is positive and the ⁇ is negative in the similarity Ds. If there is, it is determined that there is a sign of abnormality.
  • the threshold Th is changed to the negative side by the threshold changing unit 57 before the change, the similarity Ds calculated by the similarity calculating unit 56 is likely to be greater than or equal to the value 0.
  • the similarity Ds calculated by the similarity calculating unit 56 tends to be less than 0, so that it is easily determined as abnormal. Become.
  • the control device 50 determines whether or not there is a next machining (S190). If it is determined that there is no processing, the abnormality sign detection process is terminated. On the other hand, when determining that there is the next machining in S190, the control device 50 determines whether the machining content (machining condition) in the next machining is the same (S200). In S200, the control device 50 is based on whether the material, shape, size, machining position, machining cost, type of tool T used in machining, and the like of the workpiece W to be machined are the same. Then, it is determined whether or not the processing contents are the same. When determining that the processing contents are the same, the control device 50 returns to S150 and repeats the processing.
  • the control device 50 when the next machining is started, the control device 50 will detect a sign of abnormality using the already established determination model 55. That is, once the determination model 55 is constructed, the control device 50 continues to use the same determination model 55 without constructing a new determination model 55 for machining with the same machining content. Therefore, for example, when a used tool T is used, if a judgment model 55 of the same type of tool T has already been constructed, a sign of abnormality can be detected from the beginning of machining using the used tool T. It becomes possible. As described above, since it is difficult for the used tool T to determine the replacement time by the operator, it is possible to prevent the breakage of the used tool T by enabling the detection of an abnormality sign from the beginning of machining. And can be used appropriately. If the control device 50 determines that the machining content of the next machining is not the same in S200, the control device 50 returns to S100 and performs the process. That is, when the processing content is switched, the control device 50 newly constructs the determination model 55.
  • the control device 50 determines that there is a sign of abnormality in S170, and outputs an abnormality sign warning indicating the sign of abnormality from the notification device 19 (S210).
  • the control device 50 may display a warning message indicating a sign of abnormality on the operation panel 18.
  • FIG. 7 is an explanatory diagram showing an example of time transition of the vibration data and the similarity Ds.
  • the determination model 55 is constructed in a predetermined learning period after the start of machining. Further, the similarity Ds gradually approaches the value 0 due to changes in vibration data accompanying changes in the state such as wear of the tool T and accumulation of fatigue. Then, the control device 50 determines that there is a sign of abnormality at time T1 when the similarity Ds falls below the value 0, and outputs an abnormality sign warning.
  • the control device 50 When the control device 50 outputs an abnormality sign warning, it waits for an instruction to reconstruct the determination model 55 (instruction to continue using the tool T) to be replaced by the operator (S220) ( S230).
  • the worker who has noticed the abnormal sign warning confirms the state of the tool T and, if necessary, replaces the tool T, and inputs that the replacement of the tool T is completed via the operation panel 18.
  • the operator uses the instruction screen of the operation panel 18 to instruct reconfiguration of the determination model 55 and to continue using the current tool T. Enter the instructions. If the control device 50 determines that the tool T has been replaced in S220, the control device 50 has been replaced with the same type of tool T, and there is no need to construct a new determination model 55, so the process returns to S130.
  • FIG. 8 is an explanatory diagram showing a change in the similarity Ds accompanying model reconstruction.
  • FIG. 8A shows a case where the similarity Ds accidentally falls below the value 0 at time T2, and the tool T is in a state where it can be used continuously. In this case, when the operator instructs the reconstruction of the determination model 55, the control device 50 reconstructs the determination model 55 including the vibration data at time T2.
  • the control apparatus 50 detects the precursor of abnormality using the reconstructed determination model 55, as shown in FIG.8 (b), it can make it difficult for the similarity Ds to fall below the value 0.
  • FIG. 8 (b) As described above, by reconstructing the determination model 55 using the vibration data when the abnormality sign is detected as normal data, the accidental drop in the similarity Ds is suppressed and the abnormality sign detection accuracy is improved. Can do. Further, even if a warning sign of abnormality is notified, the operator T determines the continued use of the tool T after confirming it, so that the replacement timing of the tool T can be made appropriate.
  • the control device 50 of the machine tool 10 according to the present embodiment corresponds to an abnormality sign detection device
  • the data collection unit 51 that collects vibration data from the vibration sensor 36 in S110 of the abnormality sign detection processing corresponds to a data collection unit, and an abnormality is detected.
  • the model construction unit 54 that constructs the determination model 55 in the sign detection process S110 corresponds to the model construction unit
  • the similarity calculation unit 56 that performs sign detection in the abnormality sign detection processes S160 and S170 corresponds to the sign detection unit.
  • the abnormality sign notification unit 58 that outputs an abnormality sign warning using the notification device 19 in S210 of the abnormality sign detection process corresponds to the sign notification unit.
  • the threshold value changing unit 57 that receives a setting change of the threshold value Th via the operation panel 18 in the abnormality sign detection processing S130 and S140 and changes the threshold value Th corresponds to the threshold value changing unit.
  • the control device 50 that receives a restructuring instruction via the operation panel 18 in S230 of the abnormality sign detection process corresponds to a receiving unit.
  • the machine tool 10 corresponds to a machine tool.
  • the determination model 55 in the 1-class SVM is constructed in the learning period (predetermined period) at the beginning of machining, so that detection of a sign of abnormality of the tool T is started promptly. can do.
  • the learning period predetermined period
  • the machine tool 10 can output an abnormal warning warning of the tool T to prompt the worker to take an appropriate response. Further, since the machine tool 10 can change the threshold value Th of the determination model 55, it can adjust the detection sensitivity of an abnormality sign. Further, since the machine tool 10 reconstructs the determination model 55 by including vibration data when a sign of abnormality of the tool T is detected in the normal region based on the restructuring instruction, the vibration data is accidental. Therefore, it is possible to improve the detection accuracy of the sign by suppressing the detection of the sign of abnormality when it is out of the normal region.
  • the vibration data obtained when the abnormality sign is detected is included in the data in the normal region, and the determination model 55 is restored.
  • the tool T may be continuously used and the determination model 55 may not be reconstructed.
  • the determination model 55 may be reconstructed.
  • the setting change of the threshold value Th can be received from the worker.
  • the present invention is not limited to this, and the threshold value Th may not be changed.
  • the control device 50 of the machine tool 10 detects an abnormality sign.
  • the present invention is not limited to this, and an apparatus other than the control device 50 of the machine tool 10 detects an abnormality sign.
  • a management device that manages and manages a plurality of machine tools 10 may collect vibration data from each machine tool 10 and detect signs of abnormality.
  • the alarm device 19 provided in the machine tool 10 is not limited to outputting an abnormality sign warning, and the display screen provided in the management device may indicate an abnormality sign. A warning message indicating this may be displayed, or information indicating that a sign of abnormality has been detected may be transmitted from the management device to the portable terminal of the worker.
  • the abnormality sign detection device may include a sign notification unit that notifies a sign of abnormality (abnormal sign warning) when the sign detection unit detects a sign of abnormality in the tool. By so doing, it is possible to promptly notify the operator of the sign of the abnormality of the tool, and to promote appropriate measures such as tool replacement.
  • a sign notification unit that notifies a sign of abnormality (abnormal sign warning) when the sign detection unit detects a sign of abnormality in the tool.
  • a threshold value changing unit that can change the threshold value of the normal area for determining whether or not the vibration data is included in the normal area based on an instruction from an operator.
  • the sign detection unit may determine whether the vibration data is included in the normal region based on the changed threshold value changed by the threshold value changing unit. In this way, the detection sensitivity of the abnormality sign can be adjusted by changing the threshold value, so that it is possible to detect the sign further early or suppress the detection of the frequent sign.
  • the abnormality detection apparatus when the sign detection unit detects an abnormality sign of the tool, the abnormality detection apparatus includes a reception unit that receives an instruction to reconstruct the determination model from an operator.
  • the determination model When the restructuring instruction is accepted by the accepting unit, the determination model may be reconstructed by including the vibration data when the sign of abnormality of the tool is detected in the data of the normal region.
  • the gist of the machine tool of the present disclosure is a machine tool that performs machining using a replaceable tool, and includes any one of the abnormality sign detection devices described above.
  • the machine tool of the present disclosure includes any one of the above-described abnormality sign detection devices, the same effect as the above-described abnormality sign detection device, for example, a tool abnormality can be detected early and an appropriate use of the tool can be detected. The effect that can be obtained is obtained.
  • the present disclosure can be used for monitoring abnormality of a tool used in a machine tool.

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Numerical Control (AREA)
  • Machine Tool Sensing Apparatuses (AREA)

Abstract

This abnormality sign detection device, for detecting signs of abnormality in a tool used in machining is provided with: a data collection unit which collects vibration data about a tool during machining; a model construction unit which sets the vibration data collected by the data collection unit during a prescribed period at the beginning of machining as data in a normal region, and constructs a determination model in a one-class support vector machine; and a sign detection unit which detects whether or not there are signs of an abnormality in the tool by using the determination model constructed by the model construction unit to determine whether or not the vibration data is contained in the normal region.

Description

異常予兆検出装置および工作機械Abnormal sign detection device and machine tool
　本明細書は、異常予兆検出装置および工作機械を開示する。 This specification discloses an abnormality sign detection device and a machine tool.
　従来より、バイト等の工具（切削体）を用いた機械加工中に工具の状態に関するデータを取得し、そのデータに基づいて工具の異常を検出するものが知られている。例えば、特許文献１には、工具の振動を一定周期でサンプリングし、現在のサンプリング値と過去の複数回のサンプリング値とによってモデルのパラメータを演算する。そして、パラメータの基準値と、演算した現在のパラメータとの乖離度を求め、求めた乖離度が所定の管理基準に達した場合に工具の異常を検出するものとしている。 2. Description of the Related Art Conventionally, it is known that data relating to the state of a tool is acquired during machining using a tool (cutting body) such as a bite and a tool abnormality is detected based on the data. For example, in Patent Document 1, tool vibration is sampled at a constant period, and a model parameter is calculated based on the current sampling value and a plurality of past sampling values. Then, the degree of divergence between the parameter reference value and the calculated current parameter is obtained, and the tool abnormality is detected when the obtained degree of divergence reaches a predetermined management standard.
特開昭５７－５４０５３号公報JP-A-57-54053
　このような工具の異常を検出することは、工具を用いた機械加工を行う工作機械において重要な課題といえる。しかしながら、上述した手法では、複数回のサンプリングが必要となることから、工具の異常の予兆を速やかに検出するために、なお改善の余地がある。 Detecting such tool abnormalities can be said to be an important issue in machine tools that perform machining using tools. However, since the method described above requires a plurality of samplings, there is still room for improvement in order to quickly detect a sign of tool abnormality.
　本開示は、工具の異常の予兆を早期に検出可能として工具の適切な使用を可能とすることを主目的とする。 The main purpose of the present disclosure is to enable appropriate use of a tool by enabling detection of a sign of tool abnormality at an early stage.
　本開示は、上述の主目的を達成するために以下の手段を採った。 This disclosure has taken the following measures to achieve the main purpose described above.
　本開示の異常予兆検出装置は、機械加工に用いられる工具の異常の予兆を検出する異常予兆検出装置であって、前記機械加工中の前記工具の振動データを収集するデータ収集部と、前記機械加工の開始当初の所定期間において前記データ収集部により収集された前記振動データを正常領域のデータとして１クラスサポートベクターマシンにおける判定モデルを構築するモデル構築部と、前記モデル構築部により構築された前記判定モデルを用いて、前記振動データが前記正常領域に含まれるか否かを判定することにより、前記工具の異常の予兆の有無を検出する予兆検出部と、を備えることを要旨とする。 An abnormality sign detection device of the present disclosure is an abnormality sign detection device that detects a sign of abnormality of a tool used for machining, a data collection unit that collects vibration data of the tool during machining, and the machine A model construction unit that constructs a determination model in a one-class support vector machine using the vibration data collected by the data collection unit in a predetermined period at the beginning of processing as normal region data, and the model construction unit constructed by the model construction unit A gist is provided with a sign detection unit that detects whether or not the tool has an abnormality by determining whether or not the vibration data is included in the normal region using a determination model.
　本開示の異常予兆検出装置は、機械加工の開始当初の所定期間において収集された振動データを正常領域のデータとして１クラスサポートベクターマシンにおける判定モデルを構築し、振動データが判定モデルの正常領域に含まれるか否かを判定することにより、工具の異常の予兆の有無を検出する。これにより、判定モデルを機械加工の開始当初の所定期間で構築して、異常の予兆の検出を速やかに開始することができる。また、同じ内容の機械加工を行う同じ種類の工具については、既に構築した判定モデルを用いて、機械加工の開始当初から異常の予兆を検出することも可能となる。したがって、工具の異常の予兆を早期に検出可能として工具の適切な使用を可能とすることができる。 The abnormality sign detection device of the present disclosure constructs a determination model in a one-class support vector machine using vibration data collected in a predetermined period at the beginning of machining as normal region data, and the vibration data is in the normal region of the determination model. By determining whether or not it is included, the presence or absence of a sign of abnormality of the tool is detected. Thereby, the determination model can be constructed in a predetermined period at the beginning of machining, and detection of a sign of abnormality can be started promptly. In addition, for the same type of tool that performs machining with the same content, it is also possible to detect a sign of abnormality from the beginning of machining using the already established determination model. Therefore, it is possible to detect a sign of abnormality of the tool at an early stage, and to appropriately use the tool.
工作機械１０の構成の概略の一例を示す構成図。1 is a configuration diagram illustrating an example of a schematic configuration of a machine tool 10. FIG. 工作機械１０の電気的な接続関係を示す説明図。An explanatory view showing an electrical connection relation of machine tool 10. FIG. 異常の予兆検出に関する制御装置５０の機能ブロック図。The functional block diagram of the control apparatus 50 regarding the abnormality sign detection. 振動データの時間推移の一例を示す説明図。Explanatory drawing which shows an example of the time transition of vibration data. 異常予兆検出処理の一例を示すフローチャート。The flowchart which shows an example of an abnormality sign detection process. 閾値Ｔｈと類似度Ｄｓの一例を示す説明図。Explanatory drawing which shows an example of threshold value Th and similarity Ds. 振動データと類似度Ｄｓの時間推移の一例を示す説明図。Explanatory drawing which shows an example of the time transition of vibration data and similarity Ds. モデル再構築に伴う類似度Ｄｓの変化を示す説明図。Explanatory drawing which shows the change of the similarity Ds accompanying model reconstruction.
　次に、本開示の実施の形態を図面を用いて説明する。図１は工作機械１０の構成の概略の一例を示す構成図であり、図２は工作機械１０の電気的な接続関係を示す説明図である。なお、図１中の左右方向をＹ軸方向、上下方向をＺ軸方向とし、図１の紙面と垂直な方向をＸ軸方向とする。 Next, an embodiment of the present disclosure will be described with reference to the drawings. FIG. 1 is a configuration diagram illustrating an example of a schematic configuration of the machine tool 10, and FIG. 2 is an explanatory diagram illustrating an electrical connection relationship of the machine tool 10. 1 is defined as the Y-axis direction, the vertical direction as the Z-axis direction, and the direction perpendicular to the paper surface of FIG. 1 as the X-axis direction.
　工作機械１０は、チップやドリルなどの工具Ｔを用いてワークＷに加工作業を行うマシニングセンタなどの加工装置として構成されている。工作機械１０は、図１，図２に示すように、架台としてのベース１２と、ベース１２上に設けられたテーブル１４およびコラム１６と、ワークチャック装置２０と、主軸装置３０と、主軸移動機構４０と、制御装置５０とを備える。また、工作機械１０は、操作パネル１８と、報知器１９とを備える。操作パネル１８は、タッチパネル式の液晶画面として構成されており、加工メニュー等の各種指示画面や各種設定の変更画面、作業状況を示す状況画面などを表示したり、操作者による選択操作や設定操作を受け付けたりする。また、操作パネル１８は、その他に、工作機械１０の電源をオンオフする電源ボタンや工作機械１０の作動を開始する開始ボタン、作動を停止させる停止ボタンなどを備える。報知器１９は、警告音や異常の旨の音声などを出力するスピーカや異常報知用の態様で点灯する回転灯などで構成されている。なお、工作機械１０は、図示しない自動工具交換装置を備えており、機械加工の内容に応じて主軸装置３０に装着する工具Ｔを自動で交換可能となっている。 The machine tool 10 is configured as a processing apparatus such as a machining center that performs a processing operation on the workpiece W using a tool T such as a tip or a drill. As shown in FIGS. 1 and 2, the machine tool 10 includes a base 12 as a gantry, a table 14 and a column 16 provided on the base 12, a work chuck device 20, a spindle device 30, and a spindle moving mechanism. 40 and a control device 50. Further, the machine tool 10 includes an operation panel 18 and a notification device 19. The operation panel 18 is configured as a touch panel type liquid crystal screen, and displays various instruction screens such as processing menus, various setting change screens, status screens indicating work conditions, etc., and selection and setting operations by the operator. Or accept. In addition, the operation panel 18 includes a power button for turning on / off the power of the machine tool 10, a start button for starting the operation of the machine tool 10, a stop button for stopping the operation, and the like. The alarm 19 includes a speaker that outputs a warning sound or a sound indicating an abnormality, a rotating lamp that is lit in an abnormality notification mode, and the like. The machine tool 10 includes an automatic tool changer (not shown), and can automatically change the tool T mounted on the spindle device 30 according to the content of machining.
　ワークチャック装置２０は、テーブル１４上に配置されワークＷが載置される載置台２２と、図示しないサーボモータとボールねじ機構などにより構成され載置台２２をＹ軸方向に移動させるＹ軸移動機構２４と、載置台２２に載置されたワークＷをチャックする複数対のチャック爪２６と、チャック爪２６を開閉する図示しない開閉装置とを備える。主軸装置３０は、先端に工具Ｔが交換可能に装着される主軸３２と、主軸３２を回転駆動させる主軸モータ３４と、主軸３２の振動を検出する振動センサ３６と、を備える。主軸移動機構４０は、それぞれ図示しないサーボモータとボールねじ機構などにより構成され、主軸装置３０をＺ軸方向に移動させるＺ軸移動機構４２と、コラム１６に設けられ主軸装置３０をＺ軸移動機構４２ごとＸ軸方向に移動させるＸ軸移動機構４４と、を備える。 The work chuck device 20 is configured by a mounting table 22 on the table 14 on which the workpiece W is mounted, a servo motor and a ball screw mechanism (not shown), and the like. A Y-axis moving mechanism that moves the mounting table 22 in the Y-axis direction. 24, a plurality of pairs of chuck claws 26 for chucking the workpiece W placed on the placing table 22, and an opening / closing device (not shown) for opening and closing the chuck claws 26. The spindle device 30 includes a spindle 32 on which a tool T is replaceably mounted at the tip, a spindle motor 34 that rotationally drives the spindle 32, and a vibration sensor 36 that detects vibration of the spindle 32. The main shaft moving mechanism 40 includes a servo motor and a ball screw mechanism (not shown). The main shaft moving mechanism 40 moves the main shaft device 30 in the Z-axis direction, and the main shaft device 30 provided on the column 16 is moved to the Z-axis moving mechanism. And an X-axis moving mechanism 44 that moves the entire 42 in the X-axis direction.
　制御装置５０は、図示しないＣＰＵやＲＯＭ、ＲＡＭ、各種インターフェースなどを備える。制御装置５０には、主軸装置３０の振動センサ３６の検出値や各サーボモータからの位置信号、操作パネル１８で受け付けられた操作信号などが入力される。また、制御装置５０は、ワークチャック装置２０のＹ軸移動機構２４のサーボモータや開閉装置、主軸装置３０の主軸モータ３４、主軸移動機構４０のＺ軸移動機構４２やＸ軸移動機構４４の各サーボモータに駆動信号を出力したり、操作パネル１８に表示信号を出力したり、異常の予兆の旨を示す異常予兆警報の報知指令を報知器１９に出力したりする。 The control device 50 includes a CPU, ROM, RAM, various interfaces, etc., not shown. A detection value of the vibration sensor 36 of the spindle device 30, a position signal from each servo motor, an operation signal received by the operation panel 18, and the like are input to the control device 50. The control device 50 includes a servo motor and a switching device for the Y-axis moving mechanism 24 of the work chuck device 20, a spindle motor 34 for the spindle device 30, a Z-axis moving mechanism 42 for the spindle moving mechanism 40, and an X-axis moving mechanism 44. A drive signal is output to the servo motor, a display signal is output to the operation panel 18, and an abnormal sign alarm notification command indicating an abnormal sign is output to the alarm device 19.
　また、制御装置５０は、振動センサ３６からの振動データを用いて、周知の１クラスサポートベクターマシン（以下、１クラスＳＶＭ）により、工具Ｔの異常の予兆を検出する機能を有する。図３は異常の予兆検出に関する制御装置５０の機能ブロック図である。図示するように、制御装置５０は、データ収集部５１と、特徴量抽出部５３と、モデル構築部５４と、類似度演算部５６と、閾値変更部５７と、異常予兆報知部５８とを備える。 Further, the control device 50 has a function of detecting a sign of abnormality of the tool T by using a well-known 1 class support vector machine (hereinafter, 1 class SVM) using the vibration data from the vibration sensor 36. FIG. 3 is a functional block diagram of the control device 50 relating to the detection of a sign of abnormality. As illustrated, the control device 50 includes a data collection unit 51, a feature amount extraction unit 53, a model construction unit 54, a similarity calculation unit 56, a threshold change unit 57, and an abnormality sign notification unit 58. .
　データ収集部５１は、主軸装置３０の振動センサ３６の検出電圧（Ｖ）を振動データとして収集しＲＡＭなどの振動データ領域５２に格納する。図４は振動データの時間推移の一例を示す説明図であり、横軸が時間（秒）、縦軸が振動センサ３６の検出電圧（Ｖ）を示す。この図４では、工作機械１０の複数回の加工作業、例えば１または複数のワークＷに対する複数回の穴開け加工時における振動データの一例を示す。工作機械１０において、穴開け用のドリルなどの工具Ｔの使用が継続されるうちに、その工具Ｔが摩耗したり工具Ｔに疲労が蓄積されたりするため、加工開始当初の正常状態における振動との差が大きくなり、疲労の蓄積度合いによっては工具Ｔが折損する場合がある。図４の例では、右端の振動データが著しく大きくなっており、工具Ｔが折損した場合を示している。このような工具Ｔの折損が生じる前の適切なタイミングで作業者が工具Ｔを交換することが望ましいが、作業者が工具Ｔの適切な交換時期を見極めるのは困難である。このため、まだ十分に使用できるにも拘わらず作業者が早めに工具Ｔを交換したり、作業者の工具Ｔの交換が遅れて折損が生じたりする場合がある。特に、工作機械１０において中古の工具Ｔが用いられる場合、工具Ｔの疲労の蓄積度合いが不明であったり工具Ｔ毎に個体差が大きかったりするため、作業者による交換時期の見極めが一層困難となる。 The data collection unit 51 collects the detection voltage (V) of the vibration sensor 36 of the spindle device 30 as vibration data and stores it in a vibration data area 52 such as a RAM. FIG. 4 is an explanatory diagram showing an example of time transition of vibration data, where the horizontal axis represents time (seconds) and the vertical axis represents the detection voltage (V) of the vibration sensor 36. FIG. 4 shows an example of vibration data when the machine tool 10 performs a plurality of machining operations, for example, a plurality of drilling operations on one or a plurality of workpieces W. In the machine tool 10, while the tool T such as a drill for drilling is continuously used, the tool T is worn out or fatigue is accumulated in the tool T. The tool T may break depending on the degree of accumulation of fatigue. In the example of FIG. 4, the vibration data at the right end is remarkably large, and the tool T is broken. Although it is desirable for the operator to replace the tool T at an appropriate timing before such breakage of the tool T occurs, it is difficult for the operator to determine an appropriate replacement time for the tool T. For this reason, although the operator can still use it sufficiently, the operator may change the tool T early, or the operator's replacement of the tool T may be delayed and breakage may occur. In particular, when a used tool T is used in the machine tool 10, the accumulated degree of fatigue of the tool T is unknown or individual differences are large for each tool T, making it more difficult for the operator to determine the replacement time. Become.
　特徴量抽出部５３は、データ収集部５１により収集された振動データに対し、例えば高速フーリエ変換（ＦＦＴ）を施して周波数の特徴量を抽出する。モデル構築部５４は、所定の学習期間において特徴量抽出部５３により抽出された周波数の特徴量を正常領域のデータとして取り扱い、１クラスＳＶＭによる異常判定に用いる判定モデル５５を構築する。類似度演算部５６は、１クラスＳＶＭの判定モデル５５における正常領域のデータとそれ以外のデータとを分類する判定基準としての閾値Ｔｈと、特徴量抽出部５３により抽出された周波数の特徴量とを比較し、閾値Ｔｈとの距離を示す類似度Ｄｓを演算する。１クラスＳＶＭでの異常判定では、類似度演算部５６により演算された類似度Ｄｓが値０以上である場合に正常と判定し、類似度Ｄｓが値０未満である場合に異常と判定する。閾値変更部５７は、操作パネル１８を介して受け付けられた閾値Ｔｈの設定変更操作に基づいて、閾値Ｔｈの設定を変更する。異常予兆報知部５８は、類似度演算部５６により演算された類似度Ｄｓが値０未満である場合に、異常の予兆の旨を報知するように報知器１９に報知指令を出力する。 The feature amount extraction unit 53 performs, for example, a fast Fourier transform (FFT) on the vibration data collected by the data collection unit 51, and extracts frequency feature amounts. The model construction unit 54 treats the frequency feature quantity extracted by the feature quantity extraction unit 53 during a predetermined learning period as normal region data, and constructs a determination model 55 used for abnormality determination by the one-class SVM. The similarity calculation unit 56 uses a threshold value Th as a criterion for classifying normal region data and other data in the one-class SVM determination model 55, and a frequency feature amount extracted by the feature amount extraction unit 53. And a similarity Ds indicating a distance from the threshold Th is calculated. In the abnormality determination in the one-class SVM, it is determined as normal when the similarity Ds calculated by the similarity calculation unit 56 is 0 or more, and is determined as abnormal when the similarity Ds is less than 0. The threshold changing unit 57 changes the setting of the threshold Th based on the setting changing operation of the threshold Th received via the operation panel 18. When the similarity Ds calculated by the similarity calculation unit 56 is less than 0, the abnormality sign notification unit 58 outputs a notification command to the notification device 19 so as to notify that there is a sign of abnormality.
　次に、こうして構成された本実施形態の工作機械１０の動作について説明する。ここでは、異常の予兆を検出する動作を説明する。図５は異常予兆検出処理の一例を示すフローチャートである。この処理は、工作機械１０の機械加工の準備が整った状態で、制御装置５０の上述した異常の予兆検出に関する各機能により実行される。この処理が開始されると、制御装置５０は、まず、工具Ｔを用いた機械加工が開始されるのを待ち（Ｓ１００）、機械加工が開始されると振動センサ３６から収集した振動データに基づいて１クラスＳＶＭの判定モデル５５を構築する（Ｓ１１０）。この判定モデル５５の構築は、所定の学習期間が終了するまで（Ｓ１２０）、行われる。なお、所定の学習期間は、例えば工作機械１０が穴開け加工を開始してから数回の穴開け加工が終了するまでの期間などとすることができる。このように、制御装置５０は、機械加工が開始された当初の振動データに基づいて判定モデル５５を構築するのである。これは、機械加工が開始された当初の期間であれば工具Ｔが折損する可能性が低く、その期間に得られる振動データは正常状態のデータとして取り扱うことができるためである。 Next, the operation of the machine tool 10 of the present embodiment configured as described above will be described. Here, an operation for detecting a sign of abnormality will be described. FIG. 5 is a flowchart showing an example of the abnormality sign detection process. This process is executed by each function relating to the above-described abnormality sign detection of the control device 50 in a state where the machine tool 10 is ready for machining. When this process is started, the control device 50 first waits for the machining using the tool T to start (S100), and when the machining is started, based on the vibration data collected from the vibration sensor 36. 1 class SVM determination model 55 is constructed (S110). The determination model 55 is constructed until the predetermined learning period ends (S120). Note that the predetermined learning period may be, for example, a period from when the machine tool 10 starts drilling to when several drilling processes are completed. In this way, the control device 50 constructs the determination model 55 based on the initial vibration data when machining is started. This is because the tool T is less likely to break during the initial period when machining is started, and vibration data obtained during that period can be handled as data in a normal state.
　制御装置５０は、所定の学習期間が終了すると、操作パネル１８を介して閾値Ｔｈの設定変更操作が受け付けられたか否か（Ｓ１３０）、機械加工中であるか否か（Ｓ１５０）、をそれぞれ判定する。制御装置５０は、Ｓ１３０で設定変更操作が受け付けられたと判定すると、その設定変更操作に基づいて閾値Ｔｈの設定を変更する（Ｓ１４０）。ここで、図示は省略するが、作業者は、操作パネル１８の設定画面を介して、閾値Ｔｈを正側または負側に調整可能となっている。 When the predetermined learning period ends, the control device 50 determines whether or not a threshold Th setting change operation has been accepted via the operation panel 18 (S130) and whether or not machining is in progress (S150). To do. When determining that the setting change operation has been accepted in S130, the control device 50 changes the setting of the threshold Th based on the setting change operation (S140). Here, although illustration is omitted, the operator can adjust the threshold Th to the positive side or the negative side via the setting screen of the operation panel 18.
　また、制御装置５０は、Ｓ１５０で機械加工中であると判定すると、Ｓ１１０で構築した判定モデル５５を用いて、振動センサ３６から収集した振動データが判定モデル５５の正常領域に含まれるか否かに基づいて異常の予兆を検出する（Ｓ１６０）。また、制御装置５０は、Ｓ１６０の処理で異常の予兆があるか否か（Ｓ１７０）、実行中の機械加工（１回の加工）が終了したか否か（Ｓ１８０）、をそれぞれ判定しながら、Ｓ１６０の処理を継続する。Ｓ１６０では、制御装置５０は、上述したように、振動データから抽出した周波数の特徴量と閾値Ｔｈとを比較して、特徴量と閾値Ｔｈとの距離を示す類似度Ｄｓを演算し、類似度Ｄｓが値０未満である場合に、Ｓ１７０で異常の予兆があると判定する。なお、制御装置５０は、類似度Ｄｓが値０以上である場合には、Ｓ１７０で異常の予兆はないと判定する。 If the control device 50 determines that machining is being performed in S150, whether or not the vibration data collected from the vibration sensor 36 is included in the normal region of the determination model 55 using the determination model 55 constructed in S110. Based on the above, a sign of abnormality is detected (S160). Further, the control device 50 determines whether or not there is a sign of abnormality in the processing of S160 (S170) and whether or not the machining (once processing) being executed is completed (S180), The process of S160 is continued. In S160, as described above, the control device 50 compares the feature quantity of the frequency extracted from the vibration data with the threshold value Th, calculates the similarity Ds indicating the distance between the feature quantity and the threshold Th, and calculates the similarity degree. If Ds is less than 0, it is determined in S170 that there is a sign of abnormality. Note that if the degree of similarity Ds is 0 or more, the control device 50 determines that there is no sign of abnormality in S170.
　ここで、図６は、閾値Ｔｈと類似度Ｄｓの一例を示す説明図である。図６では、○印が学習期間中に収集した判定モデル５５のデータを示し、□印と△印とがモデル構築後のデータを示す。また、点線が正常領域の閾値Ｔｈを示しており、制御装置５０は、類似度Ｄｓが正となる□印であれば異常の予兆がないと判定し、類似度Ｄｓが負となる△印であれば異常の予兆があると判定する。なお、閾値変更部５７により変更前よりも負側に閾値Ｔｈが変更されると、類似度演算部５６で演算される類似度Ｄｓが値０以上となり易くなるため、正常と判定され易いものとなる。一方、閾値変更部５７により変更前よりも正側に閾値Ｔｈが変更されると、類似度演算部５６で演算される類似度Ｄｓが値０未満となり易くなるため、異常と判定され易いものとなる。 Here, FIG. 6 is an explanatory diagram showing an example of the threshold Th and the similarity Ds. In FIG. 6, ◯ indicates data of the determination model 55 collected during the learning period, and □ and Δ indicate data after model construction. In addition, the dotted line indicates the threshold Th of the normal region, and the control device 50 determines that there is no sign of abnormality if the similarity Ds is positive and the Δ is negative in the similarity Ds. If there is, it is determined that there is a sign of abnormality. If the threshold Th is changed to the negative side by the threshold changing unit 57 before the change, the similarity Ds calculated by the similarity calculating unit 56 is likely to be greater than or equal to the value 0. Become. On the other hand, when the threshold Th is changed to the positive side by the threshold changing unit 57 before the change, the similarity Ds calculated by the similarity calculating unit 56 tends to be less than 0, so that it is easily determined as abnormal. Become.
　制御装置５０は、Ｓ１７０で異常の予兆がないと判定したまま、今回の機械加工が終了したと判定すると（Ｓ１８０）、次の機械加工があるか否かを判定し（Ｓ１９０）、次の機械加工がないと判定すると、異常予兆検出処理を終了する。一方、制御装置５０は、Ｓ１９０で次の機械加工があると判定すると、次の機械加工における加工内容（加工条件）が同一であるか否かを判定する（Ｓ２００）。Ｓ２００では、制御装置５０は、機械加工の対象となるワークＷの材質や形状、サイズ、加工位置、加工代や機械加工で使用される工具Ｔの種類などが同一であるか否かに基づいて、加工内容が同一であるか否かを判定する。制御装置５０は、加工内容が同一であると判定すると、Ｓ１５０に戻り処理を繰り返す。 If it is determined that there is no sign of abnormality in S170 and the current machining has been completed (S180), the control device 50 determines whether or not there is a next machining (S190). If it is determined that there is no processing, the abnormality sign detection process is terminated. On the other hand, when determining that there is the next machining in S190, the control device 50 determines whether the machining content (machining condition) in the next machining is the same (S200). In S200, the control device 50 is based on whether the material, shape, size, machining position, machining cost, type of tool T used in machining, and the like of the workpiece W to be machined are the same. Then, it is determined whether or not the processing contents are the same. When determining that the processing contents are the same, the control device 50 returns to S150 and repeats the processing.
　この場合、次の機械加工が開始されると、制御装置５０は、既に構築した判定モデル５５を用いて異常の予兆検出を行うことになる。即ち、制御装置５０は、一旦判定モデル５５を構築すると、以降は同じ加工内容の機械加工に対して、新たに判定モデル５５を構築することなく、同じ判定モデル５５を継続して用いるのである。したがって、例えば中古の工具Ｔを用いる場合において、同じ種類の工具Ｔの判定モデル５５が既に構築されていれば、中古の工具Ｔを用いた機械加工の開始当初から異常の予兆を検出することが可能となる。上述したように、中古の工具Ｔは、作業者による交換時期の見極めが困難であるから、機械加工の開始当初から異常の予兆検出を可能とすることで中古の工具Ｔの折損を未然に防止して適切に使用することが可能となる。また、制御装置５０は、Ｓ２００で次の機械加工の加工内容が同一ではないと判定すると、Ｓ１００に戻り処理を行う。即ち、加工内容が切り替わる場合には、制御装置５０は、新たに判定モデル５５を構築するのである。 In this case, when the next machining is started, the control device 50 will detect a sign of abnormality using the already established determination model 55. That is, once the determination model 55 is constructed, the control device 50 continues to use the same determination model 55 without constructing a new determination model 55 for machining with the same machining content. Therefore, for example, when a used tool T is used, if a judgment model 55 of the same type of tool T has already been constructed, a sign of abnormality can be detected from the beginning of machining using the used tool T. It becomes possible. As described above, since it is difficult for the used tool T to determine the replacement time by the operator, it is possible to prevent the breakage of the used tool T by enabling the detection of an abnormality sign from the beginning of machining. And can be used appropriately. If the control device 50 determines that the machining content of the next machining is not the same in S200, the control device 50 returns to S100 and performs the process. That is, when the processing content is switched, the control device 50 newly constructs the determination model 55.
　また、制御装置５０は、類似度Ｄｓが値０未満になると、Ｓ１７０で異常の予兆があると判定して、異常の予兆の旨を示す異常予兆警報を報知器１９から出力する（Ｓ２１０）。なお、制御装置５０は、異常の予兆の旨を示す警告メッセージを操作パネル１８に表示させるものとしてもよい。 Further, when the degree of similarity Ds becomes less than 0, the control device 50 determines that there is a sign of abnormality in S170, and outputs an abnormality sign warning indicating the sign of abnormality from the notification device 19 (S210). The control device 50 may display a warning message indicating a sign of abnormality on the operation panel 18.
　図７は、振動データと類似度Ｄｓの時間推移の一例を示す説明図である。上述したように、機械加工を開始してからの所定の学習期間において判定モデル５５を構築する。また、工具Ｔの摩耗や疲労の蓄積などの状態の変化に伴う振動データの変化により、類似度Ｄｓが値０に徐々に近付いていく。そして、制御装置５０は、類似度Ｄｓが値０を下回った時刻Ｔ１で異常の予兆があると判定し、異常予兆警報を出力する。 FIG. 7 is an explanatory diagram showing an example of time transition of the vibration data and the similarity Ds. As described above, the determination model 55 is constructed in a predetermined learning period after the start of machining. Further, the similarity Ds gradually approaches the value 0 due to changes in vibration data accompanying changes in the state such as wear of the tool T and accumulation of fatigue. Then, the control device 50 determines that there is a sign of abnormality at time T1 when the similarity Ds falls below the value 0, and outputs an abnormality sign warning.
　制御装置５０は、異常予兆警報を出力すると、作業者により工具Ｔが交換されるか（Ｓ２２０）、判定モデル５５の再構築の指示（工具Ｔの継続使用の指示）がなされるのを待つ（Ｓ２３０）。異常予兆警報に気付いた作業者は、工具Ｔの状態を確認し、必要があれば工具Ｔを交換してから、操作パネル１８を介して工具Ｔの交換が完了した旨を入力する。あるいは、作業者は、工具Ｔの状態を確認して、まだ交換の必要がないと判断すると、操作パネル１８の指示画面を介して判定モデル５５の再構築の指示と現在の工具Ｔの継続使用の指示とを入力する。そして、制御装置５０は、Ｓ２２０で工具Ｔが交換されたと判定すると、同じ種類の工具Ｔに交換されており判定モデル５５を新たに構築する必要はないから、Ｓ１３０に戻り処理を行う。 When the control device 50 outputs an abnormality sign warning, it waits for an instruction to reconstruct the determination model 55 (instruction to continue using the tool T) to be replaced by the operator (S220) ( S230). The worker who has noticed the abnormal sign warning confirms the state of the tool T and, if necessary, replaces the tool T, and inputs that the replacement of the tool T is completed via the operation panel 18. Alternatively, when the operator confirms the state of the tool T and determines that it is not yet necessary to be replaced, the operator uses the instruction screen of the operation panel 18 to instruct reconfiguration of the determination model 55 and to continue using the current tool T. Enter the instructions. If the control device 50 determines that the tool T has been replaced in S220, the control device 50 has been replaced with the same type of tool T, and there is no need to construct a new determination model 55, so the process returns to S130.
　また、制御装置５０は、Ｓ２３０で判定モデル５５の再構築が指示されたと判定すると、Ｓ１６０，Ｓ１７０で異常の予兆ありと判定した際の振動データを含めて判定モデル５５を再構築する処理を行ってから（Ｓ２４０）、Ｓ１３０に戻る。ここで、図８はモデル再構築に伴う類似度Ｄｓの変化を示す説明図である。図８（ａ）は、時刻Ｔ２で類似度Ｄｓが偶発的に値０を下回った場合を示しており、工具Ｔは継続使用が可能な状態とする。この場合、作業者が判定モデル５５の再構築を指示すると、制御装置５０は、時刻Ｔ２の振動データを含めて判定モデル５５を再構築する。そして、制御装置５０は、再構築した判定モデル５５を用いて異常の予兆検出を行うから、図８（ｂ）に示すように、類似度Ｄｓが値０を下回り難くすることができる。このように、異常の予兆を検出した際の振動データを正常なデータとして判定モデル５５を再構築することで、偶発的な類似度Ｄｓの落ち込みを抑えて、異常の予兆の検出精度を上げることができる。また、異常の予兆が報知されても、作業者が確認した上で工具Ｔの継続使用を判断するから、工具Ｔの交換タイミングを適切なものとすることができる。 Further, when the control device 50 determines that the reconstruction of the determination model 55 is instructed in S230, the control device 50 performs a process of reconstructing the determination model 55 including vibration data when it is determined that there is a sign of abnormality in S160 and S170. (S240), the process returns to S130. Here, FIG. 8 is an explanatory diagram showing a change in the similarity Ds accompanying model reconstruction. FIG. 8A shows a case where the similarity Ds accidentally falls below the value 0 at time T2, and the tool T is in a state where it can be used continuously. In this case, when the operator instructs the reconstruction of the determination model 55, the control device 50 reconstructs the determination model 55 including the vibration data at time T2. And since the control apparatus 50 detects the precursor of abnormality using the reconstructed determination model 55, as shown in FIG.8 (b), it can make it difficult for the similarity Ds to fall below the value 0. FIG. As described above, by reconstructing the determination model 55 using the vibration data when the abnormality sign is detected as normal data, the accidental drop in the similarity Ds is suppressed and the abnormality sign detection accuracy is improved. Can do. Further, even if a warning sign of abnormality is notified, the operator T determines the continued use of the tool T after confirming it, so that the replacement timing of the tool T can be made appropriate.
　ここで、本実施形態の構成要素と本開示の構成要素との対応関係を明らかにする。本実施形態の工作機械１０の制御装置５０が異常予兆検出装置に相当し、異常予兆検出処理のＳ１１０で振動センサ３６からの振動データを収集するデータ収集部５１がデータ収集部に相当し、異常予兆検出処理のＳ１１０で判定モデル５５を構築するモデル構築部５４がモデル構築部に相当し、異常予兆検出処理のＳ１６０，Ｓ１７０で予兆検出を行う類似度演算部５６が予兆検出部に相当する。また、異常予兆検出処理のＳ２１０で報知器１９を用いて異常予兆警報を出力する異常予兆報知部５８が予兆報知部に相当する。異常予兆検出処理のＳ１３０，Ｓ１４０で操作パネル１８を介して閾値Ｔｈの設定変更を受け付けて閾値Ｔｈを変更する閾値変更部５７が閾値変更部に相当する。異常予兆検出処理のＳ２３０で操作パネル１８を介して再構築の指示を受け付ける制御装置５０が受付部に相当する。また、工作機械１０が工作機械に相当する。 Here, the correspondence between the constituent elements of the present embodiment and the constituent elements of the present disclosure will be clarified. The control device 50 of the machine tool 10 according to the present embodiment corresponds to an abnormality sign detection device, and the data collection unit 51 that collects vibration data from the vibration sensor 36 in S110 of the abnormality sign detection processing corresponds to a data collection unit, and an abnormality is detected. The model construction unit 54 that constructs the determination model 55 in the sign detection process S110 corresponds to the model construction unit, and the similarity calculation unit 56 that performs sign detection in the abnormality sign detection processes S160 and S170 corresponds to the sign detection unit. In addition, the abnormality sign notification unit 58 that outputs an abnormality sign warning using the notification device 19 in S210 of the abnormality sign detection process corresponds to the sign notification unit. The threshold value changing unit 57 that receives a setting change of the threshold value Th via the operation panel 18 in the abnormality sign detection processing S130 and S140 and changes the threshold value Th corresponds to the threshold value changing unit. The control device 50 that receives a restructuring instruction via the operation panel 18 in S230 of the abnormality sign detection process corresponds to a receiving unit. Further, the machine tool 10 corresponds to a machine tool.
　以上説明した本実施形態の工作機械１０では、１クラスＳＶＭにおける判定モデル５５を機械加工の開始当初の学習期間（所定期間）で構築することで、工具Ｔの異常の予兆の検出を速やかに開始することができる。また、同じ機械加工に用いられる別の工具Ｔについては、既に構築した判定モデル５５を用いて、機械加工の開始当初から異常の予兆を検出することも可能である。したがって、工具Ｔの異常の予兆を早期に検出可能として工具Ｔの適切な使用を可能とすることができる。 In the machine tool 10 of the present embodiment described above, the determination model 55 in the 1-class SVM is constructed in the learning period (predetermined period) at the beginning of machining, so that detection of a sign of abnormality of the tool T is started promptly. can do. For another tool T used for the same machining, it is also possible to detect a sign of abnormality from the beginning of machining using the already established determination model 55. Therefore, it is possible to detect the sign of abnormality of the tool T at an early stage, and to appropriately use the tool T.
　また、工作機械１０は、工具Ｔの異常予兆警報を出力して作業者に適切な対応を促すことができる。また、工作機械１０は、判定モデル５５の閾値Ｔｈを変更可能であるから、異常の予兆の検出感度を調整することができる。また、工作機械１０は、再構築の指示に基づいて、工具Ｔの異常の予兆が検出された際の振動データを正常領域のデータに含めて判定モデル５５を再構築するから、振動データが偶発的に正常領域から外れた場合などに異常の予兆を検出するのを抑えて、予兆の検出精度を向上させることができる。 Further, the machine tool 10 can output an abnormal warning warning of the tool T to prompt the worker to take an appropriate response. Further, since the machine tool 10 can change the threshold value Th of the determination model 55, it can adjust the detection sensitivity of an abnormality sign. Further, since the machine tool 10 reconstructs the determination model 55 by including vibration data when a sign of abnormality of the tool T is detected in the normal region based on the restructuring instruction, the vibration data is accidental. Therefore, it is possible to improve the detection accuracy of the sign by suppressing the detection of the sign of abnormality when it is out of the normal region.
　なお、本開示は上述した実施形態に何ら限定されることはなく、本開示の技術的範囲に属する限り種々の態様で実施し得ることはいうまでもない。 It should be noted that the present disclosure is not limited to the above-described embodiment, and it goes without saying that the present disclosure can be implemented in various modes as long as it belongs to the technical scope of the present disclosure.
　例えば、上述した実施形態では、異常の予兆を出力した場合に工具Ｔの継続使用が指示されると、異常の予兆を検出した際の振動データを正常領域のデータに含めて判定モデル５５を再構築するものとしたが、これに限られるものではない。即ち、単に工具Ｔの継続使用を行い、判定モデル５５の再構築を行わないものとしてもよい。あるいは、工具Ｔは交換するものの、判定モデル５５の再構築を行うものとしてもよい。 For example, in the above-described embodiment, if the tool T is instructed to be used continuously when an abnormality sign is output, the vibration data obtained when the abnormality sign is detected is included in the data in the normal region, and the determination model 55 is restored. Although it was supposed to be built, it is not limited to this. In other words, the tool T may be continuously used and the determination model 55 may not be reconstructed. Alternatively, although the tool T is replaced, the determination model 55 may be reconstructed.
　上述した実施形態では、閾値Ｔｈの設定変更を作業者から受け付け可能なものとしたが、これに限られず、閾値Ｔｈの設定変更を受け付けないものなどとしてもよい。 In the above-described embodiment, the setting change of the threshold value Th can be received from the worker. However, the present invention is not limited to this, and the threshold value Th may not be changed.
　上述した実施形態では、工作機械１０の制御装置５０が異常の予兆を検出するものとしたが、これに限られず、工作機械１０の制御装置５０とは別の装置が異常の予兆を検出するものなどとしてもよい。例えば、複数の工作機械１０を統括して管理する管理装置が、各工作機械１０から振動データを収集してそれぞれの異常の予兆を検出するものなどとしてもよい。また、そのようにする場合、異常の予兆を検出した場合に、工作機械１０が備える報知器１９を用いて異常予兆警報を出力するものに限られず、管理装置が備える表示画面に異常の予兆の旨を示す警告メッセージを表示したり、管理装置から作業者の携帯端末に異常の予兆を検出した旨の情報を送信するものなどとしてもよい。 In the above-described embodiment, the control device 50 of the machine tool 10 detects an abnormality sign. However, the present invention is not limited to this, and an apparatus other than the control device 50 of the machine tool 10 detects an abnormality sign. And so on. For example, a management device that manages and manages a plurality of machine tools 10 may collect vibration data from each machine tool 10 and detect signs of abnormality. In addition, in such a case, when an abnormality sign is detected, the alarm device 19 provided in the machine tool 10 is not limited to outputting an abnormality sign warning, and the display screen provided in the management device may indicate an abnormality sign. A warning message indicating this may be displayed, or information indicating that a sign of abnormality has been detected may be transmitted from the management device to the portable terminal of the worker.
　本開示の異常予兆検出装置において、前記予兆検出部により前記工具の異常の予兆が検出された場合に、異常の予兆の旨（異常予兆警報）を報知する予兆報知部を備えるものとしてもよい。こうすれば、工具の異常の予兆の旨を速やかに作業者に報知して、工具の交換などの適切な対応を促すことができる。 The abnormality sign detection device according to the present disclosure may include a sign notification unit that notifies a sign of abnormality (abnormal sign warning) when the sign detection unit detects a sign of abnormality in the tool. By so doing, it is possible to promptly notify the operator of the sign of the abnormality of the tool, and to promote appropriate measures such as tool replacement.
　本開示の異常予兆検出装置において、前記振動データが前記正常領域に含まれるか否かを判定するための前記正常領域の閾値を、作業者からの指示に基づいて変更可能な閾値変更部を備え、前記予兆検出部は、前記閾値変更部により変更された変更後の前記閾値に基づいて前記振動データが前記正常領域に含まれるか否かを判定するものとしてもよい。こうすれば、閾値を変更することにより異常の予兆の検出感度を調整することができるから、予兆のさらなる早期検出を図ったり頻繁な予兆の検出を抑えたりすることができる。 In the abnormality sign detection device of the present disclosure, a threshold value changing unit that can change the threshold value of the normal area for determining whether or not the vibration data is included in the normal area based on an instruction from an operator. The sign detection unit may determine whether the vibration data is included in the normal region based on the changed threshold value changed by the threshold value changing unit. In this way, the detection sensitivity of the abnormality sign can be adjusted by changing the threshold value, so that it is possible to detect the sign further early or suppress the detection of the frequent sign.
　本開示の異常予兆検出装置において、前記予兆検出部により前記工具の異常の予兆が検出された場合に、作業者から前記判定モデルの再構築の指示を受け付ける受付部を備え、前記モデル構築部は、前記受付部により再構築の指示が受け付けられると、前記工具の異常の予兆が検出された際の前記振動データを前記正常領域のデータに含めて前記判定モデルを再構築するものとしてもよい。こうすれば、振動データが偶発的に正常領域から外れた場合などに異常の予兆を検出するのを抑えることができるから、予兆の検出精度を向上させることができる。 In the abnormality sign detection device of the present disclosure, when the sign detection unit detects an abnormality sign of the tool, the abnormality detection apparatus includes a reception unit that receives an instruction to reconstruct the determination model from an operator. When the restructuring instruction is accepted by the accepting unit, the determination model may be reconstructed by including the vibration data when the sign of abnormality of the tool is detected in the data of the normal region. By so doing, it is possible to suppress the detection of a sign of abnormality when the vibration data accidentally deviates from the normal region, and thus the sign detection accuracy can be improved.
　本開示の工作機械は、交換可能な工具を用いて機械加工を行う工作機械であって、上述したいずれかの異常予兆検出装置を備えることを要旨とする。 The gist of the machine tool of the present disclosure is a machine tool that performs machining using a replaceable tool, and includes any one of the abnormality sign detection devices described above.
　本開示の工作機械は、上述したいずれかの異常予兆検出装置を備えるため、上述した異常予兆検出装置と同様の効果、例えば、工具の異常の予兆を早期に検出可能として工具の適切な使用を可能とする効果が得られるものとなる。 Since the machine tool of the present disclosure includes any one of the above-described abnormality sign detection devices, the same effect as the above-described abnormality sign detection device, for example, a tool abnormality can be detected early and an appropriate use of the tool can be detected. The effect that can be obtained is obtained.
　本開示は、工作機械で用いられる工具の異常の監視などに利用可能である。 The present disclosure can be used for monitoring abnormality of a tool used in a machine tool.
　１０　工作機械、１２　ベース、１４　テーブル、１６　コラム、１８　操作パネル、１９　報知器、２０　ワークチャック装置、２２　載置台、２４　Ｙ軸移動機構、２６　チャック爪、３０　主軸装置、３２　主軸、３４　主軸モータ、３６　振動センサ、４０　主軸移動機構、４２　Ｚ軸移動機構、４４　Ｘ軸移動機構、５０　制御装置、５１　データ収集部、５２　振動データ領域、５３　特徴量抽出部、５４　モデル構築部、５５　判定モデル、５６　類似度演算部、５７　閾値変更部、５８　異常予兆報知部、Ｄｓ　類似度、Ｔ　工具、Ｔｈ　閾値、Ｗ　ワーク。 10 machine tools, 12 bases, 14 tables, 16 columns, 18 operation panels, 19 alarms, 20 work chuck devices, 22 mounting tables, 24 Y-axis moving mechanisms, 26 chuck claws, 30 spindle devices, 32 spindles, 34 spindle motors , 36 vibration sensor, 40 spindle movement mechanism, 42 Z-axis movement mechanism, 44 X-axis movement mechanism, 50 control device, 51 data collection unit, 52 vibration data area, 53 feature quantity extraction unit, 54 model construction unit, 55 judgment model , 56 similarity calculation unit, 57 threshold change unit, 58 abnormality predictor notification unit, Ds similarity, T tool, Th threshold, W work.

Claims (5)

  1. 　機械加工に用いられる工具の異常の予兆を検出する異常予兆検出装置であって、
    　前記機械加工中の前記工具の振動データを収集するデータ収集部と、
    　前記機械加工の開始当初の所定期間において前記データ収集部により収集された前記振動データを正常領域のデータとして１クラスサポートベクターマシンにおける判定モデルを構築するモデル構築部と、
    　前記モデル構築部により構築された前記判定モデルを用いて、前記振動データが前記正常領域に含まれるか否かを判定することにより、前記工具の異常の予兆の有無を検出する予兆検出部と、
    　を備える異常予兆検出装置。     An abnormal sign detection device for detecting an abnormal sign of a tool used for machining,
    A data collection unit for collecting vibration data of the tool during the machining;
    A model construction unit for constructing a determination model in a one-class support vector machine using the vibration data collected by the data collection unit in a predetermined period at the beginning of the machining as normal region data;
    By using the determination model constructed by the model construction unit, by determining whether or not the vibration data is included in the normal region, a sign detection unit that detects the presence or absence of a sign of abnormality of the tool;
    An anomaly sign detection device comprising:
  2. 　請求項１に記載の異常予兆検出装置であって、
    　前記予兆検出部により前記工具の異常の予兆が検出された場合に、異常の予兆の旨を報知する予兆報知部を備える
    　異常予兆検出装置。     The abnormality sign detection device according to claim 1,
    An abnormality sign detection apparatus comprising: a sign notifying unit for notifying that a sign of abnormality is detected when the sign detection unit detects a sign of abnormality of the tool.
  3. 　請求項１または２に記載の異常予兆検出装置であって、
    　前記振動データが前記正常領域に含まれるか否かを判定するための前記正常領域の閾値を、作業者からの指示に基づいて変更可能な閾値変更部を備え、
    　前記予兆検出部は、前記閾値変更部により変更された変更後の前記閾値に基づいて前記振動データが前記正常領域に含まれるか否かを判定する
    　異常予兆検出装置。     The abnormality sign detection device according to claim 1 or 2,
    A threshold value changing unit capable of changing the threshold value of the normal region for determining whether or not the vibration data is included in the normal region based on an instruction from an operator;
    The said sign detection part determines whether the said vibration data are contained in the said normal area | region based on the said threshold value after the change changed by the said threshold value change part.
  4. 　請求項１ないし３のいずれか１項に記載の異常予兆検出装置であって、
    　前記予兆検出部により前記工具の異常の予兆が検出された場合に、作業者から前記判定モデルの再構築の指示を受け付ける受付部を備え、
    　前記モデル構築部は、前記受付部により再構築の指示が受け付けられると、前記工具の異常の予兆が検出された際の前記振動データを前記正常領域のデータに含めて前記判定モデルを再構築する
    　異常予兆検出装置。     The abnormality sign detection device according to any one of claims 1 to 3,
    When a sign of abnormality of the tool is detected by the sign detection unit, a reception unit that receives an instruction to reconstruct the determination model from an operator,
    When the restructuring instruction is accepted by the accepting unit, the model constructing unit reconstructs the determination model by including the vibration data when the sign of abnormality of the tool is detected in the normal region data Abnormal sign detection device.
  5. 　交換可能な工具を用いて機械加工を行う工作機械であって、
    　請求項１ないし４のいずれか１項に記載の異常予兆検出装置を備える
    　工作機械。     A machine tool that performs machining using a replaceable tool,
    A machine tool comprising the abnormality sign detection device according to any one of claims 1 to 4.
PCT/JP2018/012013 2018-03-26 2018-03-26 Abnormality sign detection device and machine tool WO2019186620A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2018/012013 WO2019186620A1 (en) 2018-03-26 2018-03-26 Abnormality sign detection device and machine tool
JP2020510174A JP7000560B2 (en) 2018-03-26 2018-03-26 Abnormality sign detection device and machine tool

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2018/012013 WO2019186620A1 (en) 2018-03-26 2018-03-26 Abnormality sign detection device and machine tool

Publications (1)

Publication Number Publication Date
WO2019186620A1 true WO2019186620A1 (en) 2019-10-03

Family

ID=68062345

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/012013 WO2019186620A1 (en) 2018-03-26 2018-03-26 Abnormality sign detection device and machine tool

Country Status (2)

Country Link
JP (1) JP7000560B2 (en)
WO (1) WO2019186620A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2021074821A (en) * 2019-11-08 2021-05-20 Dmg森精機株式会社 Machine tool and display device
US20210279573A1 (en) * 2020-03-04 2021-09-09 Robert Bosch Gmbh Detecting when a piece of material is caught between a chuck and a tool

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08328651A (en) * 1995-06-06 1996-12-13 Hitachi Ltd Method and device for collecting data
JPH10146740A (en) * 1996-11-14 1998-06-02 Brother Ind Ltd Tool abnormality detection device
JPH11267949A (en) * 1998-03-20 1999-10-05 Kawasaki Heavy Ind Ltd Device and method for detecting wear of tool
JP2001205545A (en) * 2000-01-31 2001-07-31 Toshiba Mach Co Ltd Tool replacement timing judging system
JP2015203646A (en) * 2014-04-15 2015-11-16 三菱重工業株式会社 Diagnosis method of machine tool and system thereof
JP2017205821A (en) * 2016-05-17 2017-11-24 株式会社リコー Information processor, information processing method, information processing program, and information processing system
WO2018030033A1 (en) * 2016-08-10 2018-02-15 三菱重工工作機械株式会社 Abnormality-detecting device and method for tool of machine tool

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08328651A (en) * 1995-06-06 1996-12-13 Hitachi Ltd Method and device for collecting data
JPH10146740A (en) * 1996-11-14 1998-06-02 Brother Ind Ltd Tool abnormality detection device
JPH11267949A (en) * 1998-03-20 1999-10-05 Kawasaki Heavy Ind Ltd Device and method for detecting wear of tool
JP2001205545A (en) * 2000-01-31 2001-07-31 Toshiba Mach Co Ltd Tool replacement timing judging system
JP2015203646A (en) * 2014-04-15 2015-11-16 三菱重工業株式会社 Diagnosis method of machine tool and system thereof
JP2017205821A (en) * 2016-05-17 2017-11-24 株式会社リコー Information processor, information processing method, information processing program, and information processing system
WO2018030033A1 (en) * 2016-08-10 2018-02-15 三菱重工工作機械株式会社 Abnormality-detecting device and method for tool of machine tool

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
MORI, KAZUO: "Development of a drilling inprocess diagnostic system.1.Prediction of the breadage by neural network", PROCEEDINGS OF JSPE SEMESTRIAL MEETING 1959-2002, 25 May 2009 (2009-05-25), pages 1071 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2021074821A (en) * 2019-11-08 2021-05-20 Dmg森精機株式会社 Machine tool and display device
US20210279573A1 (en) * 2020-03-04 2021-09-09 Robert Bosch Gmbh Detecting when a piece of material is caught between a chuck and a tool

Also Published As

Publication number Publication date
JPWO2019186620A1 (en) 2021-02-18
JP7000560B2 (en) 2022-01-19

Similar Documents

Publication Publication Date Title
JP4569494B2 (en) Tool abnormality detection device and tool abnormality detection system
WO2019186620A1 (en) Abnormality sign detection device and machine tool
KR20140010317A (en) Tool monitoring system of machine tools and method thereof
US20230008247A1 (en) Diagnostic system, diagnostic method, and recording medium
JP6637689B2 (en) Machine tool tool state determination device
JP5223283B2 (en) Chip dress state monitoring method, monitoring device, and spot welding system
JP2019030954A (en) Machine tool and method for calculating degree of abrasion of tool
JP3291677B2 (en) Method and apparatus for monitoring condition of machining blade for machine tool
JP6924529B1 (en) Machine tool current measurement system and its method
JP2016124054A (en) Machining chip recovery method and machining chip recovery system
JPH10286743A (en) Tool abnormality detection device for machine tool, and recording medium in which tool abnormality detecting program for machine tool is recorded
US6234869B1 (en) Machine control gage system
JP6387653B2 (en) Numerical controller
JP6690896B2 (en) Cutting device and cutting method
JP2014091187A (en) Tool abnormality detection device, and tool abnormality detection method
JP6431008B2 (en) Electric discharge machine and failure determination method
JP2017140675A (en) Cutting tool monitoring device
JP6967321B1 (en) Machine tool current measurement system and its method
JP2011121139A (en) Device and method for detecting tool failure
EP3287224A2 (en) Electrical discharge machine
JP2001087863A (en) Plate working method and device
JPH10146740A (en) Tool abnormality detection device
JP6413504B2 (en) Tool management apparatus and tool management method
TWM550193U (en) Smart sensing tool structure
TWM549671U (en) Tool inspection device

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18912808

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020510174

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18912808

Country of ref document: EP

Kind code of ref document: A1