WO2023189107A1 - Dispositif d'estimation et procédé d'estimation - Google Patents

Dispositif d'estimation et procédé d'estimation Download PDF

Info

Publication number
WO2023189107A1
WO2023189107A1 PCT/JP2023/007264 JP2023007264W WO2023189107A1 WO 2023189107 A1 WO2023189107 A1 WO 2023189107A1 JP 2023007264 W JP2023007264 W JP 2023007264W WO 2023189107 A1 WO2023189107 A1 WO 2023189107A1
Authority
WO
WIPO (PCT)
Prior art keywords
state
feature amount
degree
contribution
target
Prior art date
Application number
PCT/JP2023/007264
Other languages
English (en)
Japanese (ja)
Inventor
光樹 佃
Original Assignee
オムロン株式会社
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 オムロン株式会社 filed Critical オムロン株式会社
Publication of WO2023189107A1 publication Critical patent/WO2023189107A1/fr

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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M13/00—Testing of machine parts
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M99/00—Subject matter not provided for in other groups of this subclass

Definitions

  • the present disclosure relates to an estimation device and an estimation method that are capable of estimating factors of a change in the state of a target.
  • Patent Document 1 discloses a cultivation device that estimates the amount of water contained in plants with high accuracy.
  • a method for capturing changes in the state of an object there is a method of setting a threshold value for the feature amount obtained from the object. With such a method, it is only possible to know whether the feature value exceeds a threshold value, and it may be difficult to estimate the cause of a change in the state of the object.
  • An object of the present disclosure is to provide an estimation device and an estimation method capable of estimating factors of a change in the state of a target.
  • An estimation device includes: an acquisition unit that acquires the feature amount obtained from the object in a first state of the object and the feature amount in a second state of the object different from the first state; a testing unit that tests a significant difference between the acquired feature amount in the first state and the acquired feature amount in the second state; a generation unit that generates a degree of contribution of the feature amount to a state change between the first state and the second state of the object from the tested significant difference; and an estimation unit that quantitatively estimates a factor of a state change between the first state and the second state of the target based on the generated contribution degree.
  • An estimation method includes: obtaining the feature amount obtained from the object in a first state of the object and the feature amount in a second state of the object different from the first state; testing a significant difference between the acquired feature amount in the first state and the acquired feature amount in the second state; Generating a degree of contribution of the feature amount to a change of the object from the first state to the second state from the tested significant difference; Based on the generated contribution degree, a factor of a state change between the first state and the second state of the target is quantitatively estimated.
  • estimation device and estimation method of the above aspect it is possible to quantitatively estimate the cause of a change in the state of the object.
  • FIG. 1 is a block diagram showing an estimation device according to an embodiment of the present disclosure.
  • FIG. 2 is a diagram showing an example of a feature amount acquired by an acquisition unit of the estimation device of FIG. 1 and an example of a test value indicating a significant difference tested by a test unit.
  • 2 is a diagram showing an example of a contribution degree generated by a generation unit of the estimation device of FIG. 1 and an example of a standard contribution degree acquired by an acquisition unit.
  • FIG. 2 is a flowchart for explaining an estimation method using the estimation device of FIG. 1.
  • an estimation device 1 includes an acquisition unit 10, a verification unit 20, a generation unit 30, and an estimation unit 40, and quantitatively evaluates the factors of a state change of a target. is configured to estimate.
  • Targets include machine tools that create workpieces into desired shapes, and equipment such as processing machines that use machine tools to process materials into desired shapes.
  • the target states include a normal state in which the device operates normally, and an abnormal state in which the device does not operate normally. For example, if the equipment is a machine tool that performs end mill processing, abnormal conditions include a state in which the end mill is worn and the machine tool cannot perform normal processing, or a state in which the machine tool is unable to perform processing normally due to lack of lubrication due to lack of cutting oil. Including the state where there is no.
  • the estimation device 1 includes, for example, a processor 2, a storage device 3, and a communication device 4.
  • Each of the acquisition unit 10, the verification unit 20, the generation unit 30, and the estimation unit 40 is realized, for example, by the processor 2 executing a predetermined program.
  • the processor 2 includes a CPU, MPU, GPU, DSP, FPGA, ASIC, etc.
  • the storage device 3 is composed of, for example, an internal recording medium or an external recording medium.
  • the internal recording medium includes nonvolatile memory and the like. External recording media include hard disks (HDD), solid state drives (SSD), optical disk devices, and the like.
  • the communication device 4 includes, for example, a communication circuit or a communication module for transmitting and receiving data to and from an external device such as a server.
  • the acquisition unit 10 is configured to acquire, for example via the communication device 4, a feature amount of the target in a first state and a feature amount of the target in a second state different from the first state.
  • the feature amount is a numerical value that quantitatively indicates the feature of the object.
  • the feature amount includes an effective value, an average value, a peak value, a harmonic content rate, etc. calculated from analog values of voltage and current of the target.
  • the feature amount may be calculated by an external device such as a server, or may be calculated by the estimation device 1.
  • the acquisition unit 10 is configured to acquire the standard contribution degree.
  • the standard contribution includes a contribution corresponding to each factor of a plurality of state changes that may occur in the target.
  • the reference degree of contribution includes a degree of contribution corresponding to a factor of a state change of the object from state X1 to state Y2, and a degree of contribution corresponding to a factor of a state change of object from state X1 to state Z2.
  • the standard contribution degree may be acquired from an external device such as a server, or may be acquired from the storage device 3 of the estimation device 1 in which the standard contribution degree is stored in advance.
  • the test unit 20 is configured to statistically test the significant difference between the acquired feature amount in the first state and the acquired feature amount in the second state.
  • the type of test is determined by the characteristics of the subject. For example, when the target is a device such as a processing machine, "Welch's t-test" is used for the following reasons. - Since the state of the device changes depending on the state change factor, it is not possible to obtain features from objects in the same state. - Feature amounts obtained from objects in two different states (for example, a normal state and an abnormal state) do not correspond to each other. ⁇ Features obtained from objects in two different states have different populations, and it cannot be assumed that the population variances are equal.
  • State X1 is an example of a first state
  • state X2 is an example of a second state.
  • the testing unit 20 tests the significant difference between the feature amount A in the obtained state X1 and the feature amount A in the obtained state A significant difference between the feature amount B and the feature amount C is tested, and a significant difference between the feature amount C in the acquired state X1 and the feature amount C in the acquired state X2 is tested.
  • the result of testing the significance of each feature amount is calculated as a test value.
  • the feature amount A is determined to be the feature amount that most easily detects the state change between the target states X1 and X2.
  • the generation unit 30 is configured to generate the degree of contribution of the feature amount to the state change between the first state and the second state of the object (hereinafter referred to as contribution degree) from the tested significant difference.
  • the degree of contribution is the degree to which the feature amount contributes to the discrimination between one state of the target and another state.
  • the generation unit 30 generates a degree of contribution from the test result of the test unit 20 using a plurality of feature quantities in the same order as the acquired standard contribution degree.
  • the generation section 30 generates the degree of contribution from the test values of the feature amounts A, B, and C.
  • the generated degree of contribution is represented, for example, by a straight line L1 (indicated by a broken line) connecting the test values of the feature amounts A, B, and C, as shown in FIG.
  • the estimation unit 40 is configured to quantitatively estimate the cause of the state change between the first state and the second state of the target based on the generated degree of contribution.
  • the estimation unit 40 is configured to quantitatively estimate the cause of the state change between the first state and the second state of the target from the generated contribution degree and the acquired reference contribution degree. has been done.
  • the standard contribution is the contribution corresponding to the cause of the state change from the target state X1 to the state Y2 (hereinafter referred to as standard contribution 1), and the contribution corresponding to the cause of the state change from the target state X1 to the state Z2. (hereinafter referred to as standard contribution 2).
  • the standard contribution degree 1 is represented by a straight line L2 (indicated by a dotted line) connecting the test values of the feature quantities A, B, and C
  • the standard contribution degree 2 is Suppose that it is represented by a straight line L3 (indicated by a solid line) connecting the test values of .
  • the estimating unit 40 compares the straight line L1 with the straight lines L2 and L3, and determines whether the factor corresponding to the standard contribution degree 2 represented by the straight line L3 having substantially the same slope as the straight line L1 is in the target state. It is estimated that this is the cause of the state change between X1 and X2.
  • the estimation unit 40 is configured to estimate the degree of transition for the entire state change from the ratio of the generated contribution degree to the acquired standard contribution degree. For example, if the generated contribution test values are (t A , t B , t C ), and the obtained standard contribution degree 2 test values are ( TA , T B , T C ), The transition degree for the entire state change is given by (t A +t B +t C )/(T A +T B +T C ).
  • t A and T A are test values obtained by testing the feature amount A
  • t B and T B are test values obtained by testing the feature amount B
  • t C and T C are the test values obtained by testing the feature amount B. This is the test value obtained by testing C.
  • the estimation method is implemented, for example, by the processor 2 executing a predetermined program.
  • the acquisition unit 10 acquires the feature amount of the first state of the target and the feature amount of the second state of the target from the target (step S1).
  • the testing unit 20 determines the significant difference between the acquired feature amount of the first state and the feature amount of the second state. Verify (step S2).
  • the generation unit 30 calculates the difference between the first state and the second state of the object based on the tested significant difference.
  • the degree of contribution of the feature amount to the state change is generated (step S3).
  • the estimation unit 40 compares the generated degree of contribution and the standard contribution and determines the first state and the second state of the target.
  • the factor of the state change between the second states is quantitatively estimated (step S4), and the estimation method ends.
  • the estimation device 1 can exhibit the following effects.
  • the estimation device 1 includes an acquisition section 10, a verification section 20, a generation section 30, and an estimation section 40.
  • the acquisition unit 10 acquires the feature amount obtained from the object in the first state of the object and the feature amount in the second state of the object different from the first state.
  • the testing unit 20 tests the significant difference between the acquired feature amount in the first state and the acquired feature amount in the second state.
  • the generation unit 30 generates the degree of contribution of the feature amount to the state change between the first state and the second state of the object from the tested significant difference.
  • the estimating unit 40 quantitatively estimates the cause of the state change between the first state and the second state of the target based on the generated degree of contribution. With such a configuration, it is possible to quantitatively estimate the cause of a change in the state of the object.
  • the target is a machine tool that performs end mill processing
  • the machine tool changes from a normal state to an abnormal state
  • whether the cause of this state change is wear of the end mill or lack of lubrication due to lack of cutting oil. It is possible to estimate whether
  • the acquisition unit 10 acquires a standard contribution degree that includes a contribution degree corresponding to each factor of a plurality of state changes that may occur in the target.
  • the estimation unit 40 compares the generated degree of contribution with the acquired reference degree of contribution, and quantitatively estimates the cause of the state change between the first state and the second state of the object. With such a configuration, it is possible to quantitatively estimate the cause of a change in the state of the object.
  • the estimation unit 40 estimates the degree of transition for the entire state change from the ratio of the generated contribution degree to the acquired standard contribution degree. With such a configuration, the degree of transition of the state change of the object can be quantified.
  • the estimation method of the present disclosure can exhibit the following effects.
  • the estimation method includes the following steps. With such a configuration, it is possible to quantitatively estimate the cause of a change in the state of the object. - Obtain the feature amount obtained from the object in the first state of the object and the feature amount in the second state different from the first state of the object. - Testing the significant difference between the acquired feature amount in the first state and the acquired feature amount in the second state. - Generate the degree of contribution of the feature amount to the change from the first state to the second state of the object from the tested significant difference. - Quantitatively estimate the cause of the state change between the first state and the second state of the target based on the generated contribution degree.
  • the estimation device 1 can also be configured as follows.
  • the type of feature amount to be acquired may or may not be set in advance. If the types of feature amounts to be acquired are not set in advance, for example, the acquisition unit 10 acquires all types of feature amounts that can be acquired, and based on the test results of the test unit 20, selects the features to be used for generating the degree of contribution. The type of amount may also be determined.
  • the estimation unit 40 quantitatively estimates the cause of the state change between the first state and the second state of the target based on the generated contribution, not only when using the standard contribution but also using other methods. It can be configured as possible.
  • the estimation device 1 includes: an acquisition unit 10 configured to acquire the feature amount obtained from the object in a first state of the object and the feature amount in a second state of the object different from the first state; a testing unit 20 configured to test a significant difference between the acquired feature amount in the first state and the acquired feature amount in the second state; a generation unit 30 configured to generate a degree of contribution of the feature amount to a state change between the first state and the second state of the object from the tested significant difference; The estimation unit 40 is configured to quantitatively estimate a factor of a state change between the first state and the second state of the target based on the generated contribution degree.
  • the estimation device 1 includes: The acquisition unit 10 is configured to acquire a standard contribution degree including the contribution degree corresponding to each factor of a plurality of state changes that may occur in the object, The estimation unit 40 compares the generated degree of contribution with the acquired standard contribution to quantitatively estimate the cause of the state change between the first state and the second state of the target. It is configured as follows.
  • the estimation device 1 includes: The estimation unit 40 is configured to estimate the degree of transition for the entire state change from the ratio of the generated contribution degree to the acquired reference contribution degree.
  • the estimation method includes: obtaining the feature amount obtained from the object in a first state of the object and the feature amount in a second state of the object different from the first state; testing a significant difference between the acquired feature amount in the first state and the acquired feature amount in the second state; Generating a degree of contribution of the feature amount to a change of the object from the first state to the second state from the tested significant difference; Based on the generated contribution degree, a factor of a state change between the first state and the second state of the target is quantitatively estimated.
  • the estimation device and estimation method of the present disclosure can be applied, for example, when the state of a device such as a machine tool changes from a normal state to an abnormal state, to estimate the factors that caused the state change.
  • Estimation device 1 Estimation device 2 Processor 3 Storage device 4 Communication device 10 Acquisition unit 20 Verification unit 30 Generation unit 40 Estimation unit

Abstract

L'invention concerne un dispositif d'estimation comprenant une unité d'acquisition, une unité de test, une unité de génération et une unité d'estimation. L'unité d'acquisition acquiert une quantité caractéristique obtenue à partir d'une cible dans un premier état de la cible et une quantité caractéristique dans un second état de la cible différent du premier état. L'unité de test teste une différence significative entre la quantité caractéristique acquise dans le premier état et la quantité caractéristique acquise dans le second état. L'unité de génération génère un degré de contribution de la quantité caractéristique au changement d'état entre le premier état et le second état de la cible, à partir de la différence significative testée. L'unité d'estimation estime quantitativement un facteur de changement d'état entre le premier état et le second état de la cible sur la base du degré de contribution généré.
PCT/JP2023/007264 2022-04-01 2023-02-28 Dispositif d'estimation et procédé d'estimation WO2023189107A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2022061860A JP2023151970A (ja) 2022-04-01 2022-04-01 推定装置および推定方法
JP2022-061860 2022-04-01

Publications (1)

Publication Number Publication Date
WO2023189107A1 true WO2023189107A1 (fr) 2023-10-05

Family

ID=88200533

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2023/007264 WO2023189107A1 (fr) 2022-04-01 2023-02-28 Dispositif d'estimation et procédé d'estimation

Country Status (3)

Country Link
JP (1) JP2023151970A (fr)
TW (1) TW202403275A (fr)
WO (1) WO2023189107A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012189319A (ja) * 2011-02-21 2012-10-04 Sumitomo Heavy Ind Ltd 変速機の評価方法及び評価装置
JP2015172945A (ja) * 2009-08-28 2015-10-01 株式会社日立製作所 設備状態監視方法およびその装置
JP2019128704A (ja) * 2018-01-23 2019-08-01 三菱重工業株式会社 設備状態監視装置および設備状態監視方法
JP6851558B1 (ja) * 2020-04-27 2021-03-31 三菱電機株式会社 異常診断方法、異常診断装置および異常診断プログラム

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015172945A (ja) * 2009-08-28 2015-10-01 株式会社日立製作所 設備状態監視方法およびその装置
JP2012189319A (ja) * 2011-02-21 2012-10-04 Sumitomo Heavy Ind Ltd 変速機の評価方法及び評価装置
JP2019128704A (ja) * 2018-01-23 2019-08-01 三菱重工業株式会社 設備状態監視装置および設備状態監視方法
JP6851558B1 (ja) * 2020-04-27 2021-03-31 三菱電機株式会社 異常診断方法、異常診断装置および異常診断プログラム

Also Published As

Publication number Publication date
JP2023151970A (ja) 2023-10-16
TW202403275A (zh) 2024-01-16

Similar Documents

Publication Publication Date Title
JP5153865B2 (ja) ディジタル・システムの信頼性を監視するシステム、およびその監視する方法
CN111199018B (zh) 异常数据检测方法、装置、存储介质及电子设备
JP2010524101A (ja) デジタル・システムの信頼性を監視する方法、及びそのシステム
US10866939B2 (en) Alignment and deduplication of time-series datasets
CN108022046A (zh) 一种电力系统数据质量评估方法、存储介质及设备
US20130006569A1 (en) Control policy adjusting apparatus, method of adjusting control policy, and program
US20080255773A1 (en) Machine condition monitoring using pattern rules
WO2023189107A1 (fr) Dispositif d'estimation et procédé d'estimation
US20150286548A1 (en) Information processing device and method
US20150220648A1 (en) Systems and Methods for Performing Machine-Implemented Tasks
JP2011252761A5 (fr)
US20080120064A1 (en) Detecting a failure condition in a system using three-dimensional telemetric impulsional response surfaces
US10157116B2 (en) Window deviation analyzer
JP6365146B2 (ja) 時系列データの解析方法及び時系列データの異常監視装置
CN112965885B (zh) 访存带宽的检测方法、装置、计算机设备及可读存储介质
US20200409817A1 (en) Method and apparatus for evaluating and selecting signal comparison metrics
CN106979794B (zh) 传感器测试方法及装置
JP6365145B2 (ja) 時系列データの解析方法及び時系列データの異常監視装置
CN110888811A (zh) 代码覆盖率信息处理方法、装置、电子设备及介质
EP3457609A1 (fr) Système et procédé de calcul d'anomalies sur la base d'une transformation entraînée par la fréquence et calcul de nouvelles caractéristiques sur la base de la densité d'anomalie de point
KR100403844B1 (ko) 메모리 대규모 집적 회로 불량 분석 장치 및 그 분석 방법과 이에 사용되는 컴퓨터 프로그램을 기록한 기록 매체
JP2020173547A (ja) 画像検査システム、画像検査装置及び画像検査プログラム
CN110633579A (zh) 投标文件在线解密结果预测方法、系统、设备及存储介质
CN114738294B (zh) 水泵缺水检测方法、装置、计算机设备及介质
KR102155007B1 (ko) 독립성 측정을 이용한 엔트로피 관리 장치 및 방법, 이를 이용한 난수 생성 장치

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: 23779137

Country of ref document: EP

Kind code of ref document: A1