Control method, control apparatus, mechanical equipment, and recording medium

{
  "publication_number": "US11740592B2",
  "country": "US",
  "kind": "B2",
  "title": "Control method, control apparatus, mechanical equipment, and recording medium",
  "abstract": "A control apparatus includes a controller. The controller is configured to obtain a measurement value of a state of mechanical equipment corresponding to a period in which the mechanical equipment reaches a second state from a first state, extract at least one predetermined feature value by using the measurement value, and extract data for machine learning from data of the at least one predetermined feature value on a basis of a separation degree for distinguishing the first state and the second state from each other.",
  "claims": [
    "1. A control method comprising: obtaining a measurement value of a state of mechanical equipment corresponding to a period in which the mechanical equipment reaches a second state from a first state; obtaining at least one predetermined feature value by using the measurement value; selecting learning data for machine learning from data of the at least one predetermined feature value on a basis of a separation degree for distinguishing the first state and the second state from each other, the selecting including setting a period on a basis of the separation degree, with the period being a period in which the mechanical equipment is in the first state, and with the at least one predetermined feature value corresponding to the period as the learning data for machine learning; and generating a post-learning model by machine learning using the learning data for machine learning.",
    "2. The control method according to claim 1, wherein the obtaining the at least one predetermined feature value comprises: obtaining a plurality of feature values by using the measurement value; and selecting the at least one predetermined feature value from the plurality of feature values on the basis of the separation degree.",
    "3. The control method according to claim 2, further comprising obtaining a maximum value of the separation degree and a timing at which the separation degree reaches the maximum value for each of the plurality of feature values, wherein the at least one predetermined feature value is selected on a basis of the maximum value of the separation degree of each of the plurality of feature values, and wherein the data of the at least one predetermined feature value corresponding to the period is extracted as the learning data for machine learning, the period being set on a basis of the timing for the at least one predetermined feature value that has been selected.",
    "4. The control method according to claim 3, wherein the selecting the at least one predetermined feature value comprises comparing each of the maximum value of the separation degree with a predetermined threshold value to select the at least one predetermined feature value.",
    "5. The control method according to claim 3, wherein the selecting the at least one predetermined feature value comprises selecting a predetermined number of feature values having largest maximum values of the separation degree as the at least one predetermined feature value.",
    "6. The control method according to claim 3, wherein the period is set as a period earlier than an earliest timing among the timings of the predetermined feature values.",
    "7. The control method according to claim 3, further comprising displaying, on a display portion, information related to selection of the at least one predetermined feature value and/or information related to extraction of data corresponding to the period in which the mechanical equipment is in the first state.",
    "8. The control method according to claim 3, further comprising displaying, on a display portion, information related to the maximum value of the separation degree, information related to the timing at which the separation degree has reached the maximum value, and/or information related to designation of the period in which the mechanical equipment is in the first state.",
    "9. The control method according to claim 1, further comprising determining a state of the mechanical equipment by using the post-learning model.",
    "10. The control method according to claim 9, wherein the determining of the state of the mechanical equipment comprises: inputting, to the post-learning model, data of a feature value of the same kind as the at least one predetermined feature value that corresponds to the period in which the mechanical equipment reaches the second state from the first state; obtaining a deviation degree between input data input to the post-learning model and output data output from the post-learning model; setting a determination threshold value on a basis of temporal change of the deviation degree in a period in which the mechanical equipment reaches the second state from the first state; obtaining a feature value of the same kind as the at least one predetermined feature value as an evaluation feature value by using a measurement value related to the state of the mechanical equipment corresponding to a time of evaluation; and obtaining an indicator value indicating a degree of deviation of the mechanical equipment from the first state by using the evaluation feature value and the post-learning model, and determining the state of the mechanical equipment corresponding to the time of evaluation by using the indicator value and the determination threshold value.",
    "11. The control method according to claim 9, wherein the generating the post-learning model comprises generating the post-learning model by machine learning using an auto encoder.",
    "12. The control method according to claim 9, further comprising notifying a result of determination of the state of the mechanical equipment by a controller.",
    "13. A non-transitory computer-readable recording medium storing a control program that causes a computer to perform the control method according to claim 1.",
    "14. The control method according to claim 1, wherein the separation degree is obtained on a basis of a first average of a first data set, a first variance of the first data set, a second average of a second data set, and a second variance of the second data set, and wherein the first data set is the data, of a part before a predetermined timing in time-series, of the at least one predetermined feature value, and the second data set is the data, of a part after the predetermined timing in time-series, of the at least one predetermined feature value.",
    "15. The control method according to claim 1, further comprising displaying on a display portion a screen for a user to set the separation degree.",
    "16. The control method according to claim 1, further comprising displaying on a display portion predetermined feature values in descending order of the separation degree.",
    "17. The control method according to claim 1, wherein the selecting includes displaying on a display portion a screen for a user to set whether the data of the at least one predetermined feature value is to be selected for learning data for machine learning.",
    "18. The control method according to claim 1, wherein the first state corresponds to a normal state of the mechanical equipment, and the second state corresponds to a malfunction state of the mechanical equipment.",
    "19. A control apparatus comprising a controller, the controller comprising: at least one processor and at least one memory, the at least one processor being configured to read and execute at least one program stored in the at least one memory that causes the control apparatus to: obtain a measurement value of a state of mechanical equipment corresponding to a period in which the mechanical equipment reaches a second state from a first state, obtain at least one predetermined feature value by using the measurement value, and select learning data for machine learning from data of the at least one predetermined feature value on a basis of a separation degree for distinguishing the first state and the second state from each other, with the selecting including setting a period on a basis of the separation degree, with the period being a period in which the mechanical equipment is in the first state, and with the at least one predetermined feature value corresponding to the period as the data for machine learning; and generate a post-learning model by machine learning using the learning data for machine learning.",
    "20. Mechanical equipment comprising the control apparatus according to claim 19.",
    "21. A method for manufacturing a product by using the mechanical equipment according to claim 20."
  ],
  "description_excerpt": "The present invention relates to a control method, a control apparatus, mechanical equipment including the control apparatus, a control program, and a computer-readable recording medium.\n\nAn operation status of mechanical equipment can change every moment depending on status change of a constituent part or the like. If an operation status within an allowable range based on the use purpose of the mechanical equipment is referred to as a normal state and an operation status out of the allowable range is referred to as a malfunction state, for example, in the case where a manufacturing machine is in the malfunction state, a malfunction such as manufacture of a defected product or stoppage of a manufacturing line occurs.\n\nIn the case of a manufacturing machine or the like, generally a maintenance operation is performed regularly or irregularly even if the same operation is repeatedly and continuously performed to suppress the occurrence of the malfunction state as much as possible. Although it is effective to shorten an execution interval between maintenance operations for increasing the preventive safety, since the manufacturing machine or the like is stopped during the maintenance operation, the operation rate of the manufacturing machine or the like is decreased if the frequency of the maintenance operation is excessively increased. Therefore, when occurrence of the malfunction state is near while the machine or the like is still in the normal state, it is desirable that this state can be detected.",
  "cpc": [
    "G05B 13/0265",
    "B25J 9/1674",
    "G05B 19/406",
    "G05B 2219/24065",
    "G05B 2219/34477",
    "G05B 23/0243",
    "G05B 23/0283",
    "G06N 20/00",
    "G06N 20/10",
    "G06N 3/045",
    "G06N 3/0455",
    "G06N 3/08",
    "G06N 3/09",
    "G06N 5/04"
  ],
  "ipc": [
    "G05B 13/02",
    "G06N 20/00",
    "G06N 5/04"
  ],
  "assignees": [
    "Canon Inc"
  ],
  "inventors": [
    "Makoto Hirano"
  ],
  "filing_date": "2020-12-01",
  "publication_date": "2023-08-29",
  "grant_date": "2023-08-29",
  "priority_date": "2019-12-10",
  "application_number": "US-202017108055-A",
  "family_id": "76209215",
  "cited_by_count": 0,
  "citations": [
    "US9113582B2",
    "JP2011070635A",
    "US20120290879A1",
    "US8682824B2",
    "JP2011059790A",
    "US20120166142A1",
    "US9483049B2",
    "US20160054360A1",
    "JP2015184823A",
    "US20150269120A1",
    "JP2018081523A",
    "US20180164756A1",
    "US20180275631A1",
    "JP2018159981A",
    "US10503146B2",
    "US20190018392A1",
    "US20210097417A1"
  ]
}