Patent US5528730A successfully refreshed from Google Patents.
US5528730A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method of control rule generation and method of fuzzy control using the same, and apparatus for automatic control rule generation and fuzzy control apparatus using the same
Assignee: Hitachi Ltd
•
Filing: 1990-10-02
•
Granted: 1996-06-18
•
Expires: 2010-10-02
Abstract
Abstract A method and apparatus for generating a control rule for controlling a control object which is controlled in accordance with operational information and a method and apparatus of fuzzy control which is based on the control rule generation method are designed to acquire measured information provided by measuring means equipped in the control object for measuring a state of the control object, acquire operational information of the operation which has been implemented for the control object at the time of acquisition of the measured information, and generate a control rule of operational information for measured information on the basis of the acquired measured information and operational information.
Inventors
- 👤 Hiroyuki Yagi
- 👤 Takahide Kawasaki
- 👤 Takao Watanabe
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 18:31
CPC Classifications
G; G06; G06N; G06N5/00; G06N5/04; G06N5/048; G05; G05B; G05B13/00; G05B13/02; G05B13/0265; G05B13/0275; G06N5/02; G06N5/022; Y; Y10; Y10S; Y10S706/00; Y10S706/90
Claims Analysis
Total Claims: 24
Claim 1
Independent Claim
160 words
A method of generating a control rule relating operational information for controlling a control object to at least one measured information, said method comprising the steps of: acquiring a plurality of measured information respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; acquiring operational information of a control operation performed on said control object at a time of acquisition of said plurality of measured information; calculating a degree of correlation between each of said plurality of measured information and said operational information; judging whether said degree of correlation between each of said plurality of measured information and said operational information is not less than a prescribed value; and generating a control rule for controlling said control object on the basis of said operational information and only those measured information for which said degree of correlation is judged to be not less than said prescribed value.
Claim 2
Independent Claim
160 words
A method of generating a control rule relating operational information for controlling a control object to at least one measured information, said method comprising the steps of: acquiring a plurality of measured information respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; acquiring operational information of a control operation performed on said control object at a time of acquisition of said plurality of measured information; calculating a degree of correlation between each of said plurality of measured information and said operational information; judging whether said degree of correlation between each of said plurality of measured information and said operational information is not less than a prescribed value; and generating a control rule for controlling said control object on the basis of said operational information and only those measured information for which said degree of correlation is judged to be not less than said prescribed value.
Claim 3
Independent Claim
180 words
A method of generating a control rule relating a control value for controlling a control object to at least one measured value, said method comprising the steps of: acquiring a plurality of sets of measured values respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; acquiring a set of control values of a control operation performed on said control object at a time of acquisition of said plurality of sets of measured values; calculating a degree of correlation between each of said plurality of sets of measured values and said set of control values; judging whether said degree of correlation between each of said plurality of sets of measured values and said set of control values is not less than a prescribed value; and generating a control rule for controlling said control object on the basis of said set of control values and only those sets of measured values for which said degree of correlation is judged to be not less than said prescribed value.
Claim 4
Independent Claim
180 words
A method of generating a control rule relating a control value for controlling a control object to at least one measured value, said method comprising the steps of: acquiring a plurality of sets of measured values respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; acquiring a set of control values of a control operation performed on said control object at a time of acquisition of said plurality of sets of measured values; calculating a degree of correlation between each of said plurality of sets of measured values and said set of control values; judging whether said degree of correlation between each of said plurality of sets of measured values and said set of control values is not less than a prescribed value; and generating a control rule for controlling said control object on the basis of said set of control values and only those sets of measured values for which said degree of correlation is judged to be not less than said prescribed value.
Claim 5
Dependent Claim
92 words
A method according to claim 2, wherein said step of generating a control rule includes the steps of: deriving a regression line or a regression curve for each set of measured values for which said degree of correlation is judged to be not less than said prescribed value representing a relation between said set of control values and said each set of measured values; and generating a control rule for said control object on the basis of said regression line or said regression curve derived for said each set of measured values.
Claim 6
Independent Claim
255 words
A method of generating a control rule relating a control value for controlling a control object to at least one measured value, said method comprising the steps of: acquiring a plurality of sets of measured values respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; acquiring a set of control values of a control operation performed on said control object at a time of acquisition of said plurality of sets of measured values; calculating respective deviations of said measured values in each of said plurality of sets of measured values from a respective normal measured value; calculating respective amounts of change of said control values in said set of control values relative to respective previous ones of said control values in said set of control values; calculating a correlation coefficient for each of said plurality of sets of measured values on the basis of said respective deviations of said measured values in each of said plurality of sets of measured values and said respective amounts of change of said control values in said set of control values; judging whether said correlation coefficient for each of said plurality of sets of measured values is not less than a prescribed value; and generating a control rule for controlling said control object on the basis of said set of control values and only those sets of measured values for which said correlation coefficient is judged to be not less than said prescribed value.
Claim 7
Independent Claim
255 words
A method of generating a control rule relating a control value for controlling a control object to at least one measured value, said method comprising the steps of: acquiring a plurality of sets of measured values respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; acquiring a set of control values of a control operation performed on said control object at a time of acquisition of said plurality of sets of measured values; calculating respective deviations of said measured values in each of said plurality of sets of measured values from a respective normal measured value; calculating respective amounts of change of said control values in said set of control values relative to respective previous ones of said control values in said set of control values; calculating a correlation coefficient for each of said plurality of sets of measured values on the basis of said respective deviations of said measured values in each of said plurality of sets of measured values and said respective amounts of change of said control values in said set of control values; judging whether said correlation coefficient for each of said plurality of sets of measured values is not less than a prescribed value; and generating a control rule for controlling said control object on the basis of said set of control values and only those sets of measured values for which said correlation coefficient is judged to be not less than said prescribed value.
Claim 8
Independent Claim
164 words
An apparatus for generating a control rule relating operational information for controlling a control object to measured information, said apparatus comprising: means for acquiring a plurality of measured information respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; means for acquiring operational information of a control operation performed on said control object at a time of acquisition of said plurality of measured information; means for calculating a degree of correlation between each of said plurality of measured information and said operational information; means for judging whether said degree of correlation between each of said plurality of measured information and said operational information is not less than a prescribed value; and means for generating a control rule for controlling said control object on the basis of said operational information and only those measured information for which said degree of correlation is judged to be not less than said prescribed value.
Claim 9
Independent Claim
164 words
An apparatus for generating a control rule relating operational information for controlling a control object to measured information, said apparatus comprising: means for acquiring a plurality of measured information respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; means for acquiring operational information of a control operation performed on said control object at a time of acquisition of said plurality of measured information; means for calculating a degree of correlation between each of said plurality of measured information and said operational information; means for judging whether said degree of correlation between each of said plurality of measured information and said operational information is not less than a prescribed value; and means for generating a control rule for controlling said control object on the basis of said operational information and only those measured information for which said degree of correlation is judged to be not less than said prescribed value.
Claim 10
Independent Claim
187 words
An apparatus for generating a control rule relating a control value for controlling a control object to at least one measured value, said apparatus comprising: means for acquiring a plurality of sets of measured values respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; means for acquiring a set of control values of a control operation performed on said control object at a time of acquisition of said plurality of sets of measured values; means for calculating a degree of correlation between each of said plurality of sets of measured values and said set of control values; means for judging whether said degree of correlation between each of said plurality of sets of measured values and said set of control values is not less than a prescribed value; and means for generating a control rule for controlling said control object on the basis of said set of control values and only those sets of measured values for which said degree of correlation is judged to be not less than said prescribed value.
Claim 11
Independent Claim
187 words
An apparatus for generating a control rule relating a control value for controlling a control object to at least one measured value, said apparatus comprising: means for acquiring a plurality of sets of measured values respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; means for acquiring a set of control values of a control operation performed on said control object at a time of acquisition of said plurality of sets of measured values; means for calculating a degree of correlation between each of said plurality of sets of measured values and said set of control values; means for judging whether said degree of correlation between each of said plurality of sets of measured values and said set of control values is not less than a prescribed value; and means for generating a control rule for controlling said control object on the basis of said set of control values and only those sets of measured values for which said degree of correlation is judged to be not less than said prescribed value.
Claim 12
Dependent Claim
101 words
An apparatus according to claim 6, wherein said means for generating a control rule includes: means for performing a statistical process on each set of measured values for which said degree of correlation is judged to be not less than said prescribed value and said set of control values to derive an equation for said each set of measured values representing a relation between said each set of measured values and said set of control values; and means for generating a control rule for said control object on the basis of said equation derived for said each set of measured values.
Claim 13
Dependent Claim
104 words
An apparatus according to claim 6, wherein said means for generating a control rule includes: means for performing a statistical process on each set of measured values for which said degree of correlation is judged to be not less than said prescribed value and said set of control values to derive a regression line or a regression curve representing a relation between said set of control values and said each set of measured values; and means for generating a control rule for said control object on the basis of said regression line or said regression curve derived for said each set of measured values.
Claim 14
Dependent Claim
184 words
An apparatus according to claim 6, wherein said means for calculating a degree of correlation includes: means for calculating respective deviations of said measured values in each of said plurality of sets of measured values from a respective normal measured value; means for calculating respective amounts of change of said control values in said set of control values relative to respective previous ones of said control values in said set of control values; and means for calculating a correlation coefficient for each of said plurality of sets of measured values on the basis of said respective deviations of said measured values in each of said plurality of sets of measured values and said respective amounts of change of said control values in said set of control values; wherein said means for judging judges whether said degree of correlation between each of said plurality of sets of measured values and said set of control values is not less than a prescribed value by judging whether said correlation coefficient for each of said plurality of sets of measured values is not less than a prescribed value.
Claim 15
Independent Claim
210 words
A method of generating a control rule relating a control value for controlling a control object to at least one measured value, said method comprising the steps of: acquiring a plurality of sets of measured values respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; acquiring a set of control values of a control operation performed on said control object at a time of acquisition of said plurality of measured values; calculating a degree of correlation between each of said plurality of sets of measured values and said set of control values; judging whether said degree of correlation between each of said plurality of sets of measured values and said set of control values is not less than a prescribed value; deriving a regression line or a regression curve for each set of measured values for which said degree of correlation is judged to be not less than said prescribed value representing a relation between said set of control values and said each set of measured values; and generating a control rule for said control object on the basis of said regression line or said regression curve derived for said each set of measured values.
Claim 16
Independent Claim
210 words
A method of generating a control rule relating a control value for controlling a control object to at least one measured value, said method comprising the steps of: acquiring a plurality of sets of measured values respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; acquiring a set of control values of a control operation performed on said control object at a time of acquisition of said plurality of measured values; calculating a degree of correlation between each of said plurality of sets of measured values and said set of control values; judging whether said degree of correlation between each of said plurality of sets of measured values and said set of control values is not less than a prescribed value; deriving a regression line or a regression curve for each set of measured values for which said degree of correlation is judged to be not less than said prescribed value representing a relation between said set of control values and said each set of measured values; and generating a control rule for said control object on the basis of said regression line or said regression curve derived for said each set of measured values.
Claim 17
Dependent Claim
377 words
A fuzzy control method for controlling a control object in accordance with a first control rule relating a first control value to a first measured value and a second control rule relating a second control value to a second measured value, the first control rule and the second control rule being generated by a method of generating a control rule relating a control value for controlling a control object to at least one measured value, said method of generating a control rule including the steps of acquiring a plurality of sets of measured values respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object, acquiring a set of control values of a control operation performed on said control object at a time of acquisition of said plurality of measured values, calculating a degree of correlation between each of said plurality of sets of measured values and said set of control values, judging whether said degree of correlation between each of said plurality of sets of measured values and said set of control values is not less than a prescribed value, deriving a regression line or a regression curve for each set of measured values for which said degree of correlation is judged to be not less than said prescribed value representing a relation between said set of control values; and said each set of measured values, and generating a control rule for said control object on the basis of said regression line or said regression curve derived for said each set of measured values, said fuzzy control method comprising the steps of: determining a first reliability of the first control value on the basis of the regression line or the regression curve on the basis of which the first control rule was generated; determining a second reliability of the second control value on the basis of the regression line or the regression curve on the basis of which the second control rule was generated; generating a third control value by averaging the first control value weighted by the first reliability and the second control value weighted by the second reliability; and operating said control object on the basis of the third control value.
Claim 18
Dependent Claim
377 words
A fuzzy control method for controlling a control object in accordance with a first control rule relating a first control value to a first measured value and a second control rule relating a second control value to a second measured value, the first control rule and the second control rule being generated by a method of generating a control rule relating a control value for controlling a control object to at least one measured value, said method of generating a control rule including the steps of acquiring a plurality of sets of measured values respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object, acquiring a set of control values of a control operation performed on said control object at a time of acquisition of said plurality of measured values, calculating a degree of correlation between each of said plurality of sets of measured values and said set of control values, judging whether said degree of correlation between each of said plurality of sets of measured values and said set of control values is not less than a prescribed value, deriving a regression line or a regression curve for each set of measured values for which said degree of correlation is judged to be not less than said prescribed value representing a relation between said set of control values; and said each set of measured values, and generating a control rule for said control object on the basis of said regression line or said regression curve derived for said each set of measured values, said fuzzy control method comprising the steps of: determining a first reliability of the first control value on the basis of the regression line or the regression curve on the basis of which the first control rule was generated; determining a second reliability of the second control value on the basis of the regression line or the regression curve on the basis of which the second control rule was generated; generating a third control value by averaging the first control value weighted by the first reliability and the second control value weighted by the second reliability; and operating said control object on the basis of the third control value.
Claim 19
Independent Claim
231 words
An apparatus for generating a control rule relating a control value for controlling a control object to at least one measured value, said apparatus comprising: means for acquiring a plurality of sets of measured values respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; means for acquiring a set of control values of a control operation performed on said control object at a time of acquisition of said plurality of sets of measured values; means for calculating a degree of correlation between each of said plurality of sets of measured values and said set of control values; means for judging whether said degree of correlation between each of said plurality of sets of measured values and said set of control values is not less than a prescribed value; means for performing a statistical process on each set of measured values for which said degree of correlation is judged to be not less than said prescribed value and said set of control values to derive a regression line or a regression curve representing a relation between said set of control values and said each set of measured values; and means for generating a control rule for said control object on the basis of said regression line or said regression derived for said each set of measured values.
Claim 20
Independent Claim
231 words
An apparatus for generating a control rule relating a control value for controlling a control object to at least one measured value, said apparatus comprising: means for acquiring a plurality of sets of measured values respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; means for acquiring a set of control values of a control operation performed on said control object at a time of acquisition of said plurality of sets of measured values; means for calculating a degree of correlation between each of said plurality of sets of measured values and said set of control values; means for judging whether said degree of correlation between each of said plurality of sets of measured values and said set of control values is not less than a prescribed value; means for performing a statistical process on each set of measured values for which said degree of correlation is judged to be not less than said prescribed value and said set of control values to derive a regression line or a regression curve representing a relation between said set of control values and said each set of measured values; and means for generating a control rule for said control object on the basis of said regression line or said regression derived for said each set of measured values.
Claim 21
Dependent Claim
402 words
A fuzzy control apparatus for controlling a control object in accordance with a first control rule relating a first control value to a first measured value and a second control rule relating a second control value to a second measured value, the first control rule and the second control rule being generated by an apparatus for generating a control rule relating a control value for controlling a control object to at least one measured value, said apparatus for generating a control rule including means for acquiring a plurality of sets of measured values respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object, means for acquiring a set of control values of a control operation performed on said control object at a time of acquisition of said plurality of sets of measured values, means for calculating a degree of correlation between each of said plurality of sets of measured values and said set of control values, means for judging whether said degree of correlation between each of said plurality of sets of measured values and said set of control values is not less than a prescribed value, means for performing a statistical process on each set of measured values for which said degree of correlation is judged to be not less than said prescribed value and said set of control values to derive a regression line or a regression curve representing a relation between said set of control values and said each set of measured values, and means for generating a control rule for said control object on the basis of said regression line or said regression derived for said each set of measured values, said fuzzy control apparatus comprising: means for determining a first reliability of the first control value on the basis of the regression line or the regression curve on the basis of which the first control rule was generated, and determining a second reliability of the second control value on the basis of the regression line or the regression curve on the basis of which the second control rule was generated; and means for generating a third control value by averaging the first control value weighted by the first reliability and the second control value weighted by the second reliability, and for operating said control object on the basis of the third control value.
Claim 22
Dependent Claim
402 words
A fuzzy control apparatus for controlling a control object in accordance with a first control rule relating a first control value to a first measured value and a second control rule relating a second control value to a second measured value, the first control rule and the second control rule being generated by an apparatus for generating a control rule relating a control value for controlling a control object to at least one measured value, said apparatus for generating a control rule including means for acquiring a plurality of sets of measured values respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object, means for acquiring a set of control values of a control operation performed on said control object at a time of acquisition of said plurality of sets of measured values, means for calculating a degree of correlation between each of said plurality of sets of measured values and said set of control values, means for judging whether said degree of correlation between each of said plurality of sets of measured values and said set of control values is not less than a prescribed value, means for performing a statistical process on each set of measured values for which said degree of correlation is judged to be not less than said prescribed value and said set of control values to derive a regression line or a regression curve representing a relation between said set of control values and said each set of measured values, and means for generating a control rule for said control object on the basis of said regression line or said regression derived for said each set of measured values, said fuzzy control apparatus comprising: means for determining a first reliability of the first control value on the basis of the regression line or the regression curve on the basis of which the first control rule was generated, and determining a second reliability of the second control value on the basis of the regression line or the regression curve on the basis of which the second control rule was generated; and means for generating a third control value by averaging the first control value weighted by the first reliability and the second control value weighted by the second reliability, and for operating said control object on the basis of the third control value.
Claim 23
Independent Claim
210 words
A method of fuzzy control for controlling a control object on the basis of a control rule relating operational information for controlling said control object to at least one measured information, said method comprising the steps of: acquiring a plurality of measured information respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; acquiring operational information of a control operation performed on said control object at a time of acquisition of said plurality of measured information; calculating a degree of correlation between each of said plurality of measured information and said operational information; judging whether said degree of correlation between each of said plurality of measured information and said operational information is not less than a prescribed value; generating a control rule for controlling said object on the basis of said operational information and only those measured information for which said degree of correlation is judged to be not less than said prescribed value; and. obtaining operational information for controlling said control object from measured information provided by any measuring means which provided said measured information for which said degree of correlation is not less than said prescribed value on the basis of said control rule.
Claim 24
Independent Claim
210 words
A method of fuzzy control for controlling a control object on the basis of a control rule relating operational information for controlling said control object to at least one measured information, said method comprising the steps of: acquiring a plurality of measured information respectively provided by a plurality of measuring means disposed in said control object for respectively measuring a plurality of states of said control object; acquiring operational information of a control operation performed on said control object at a time of acquisition of said plurality of measured information; calculating a degree of correlation between each of said plurality of measured information and said operational information; judging whether said degree of correlation between each of said plurality of measured information and said operational information is not less than a prescribed value; generating a control rule for controlling said object on the basis of said operational information and only those measured information for which said degree of correlation is judged to be not less than said prescribed value; and. obtaining operational information for controlling said control object from measured information provided by any measuring means which provided said measured information for which said degree of correlation is not less than said prescribed value on the basis of said control rule.
References Cited (Backward Citations)
US3846752A
Cited
JPS60237539A
Cited
US4816994A
Cited
US4777585A
Cited
US4803636A
Cited
JPS62271146A
Cited
JPS62288941A
Cited
US4760896A
Cited
JPS63271534A
Cited
US4931951A
Cited
US4930084A
Cited
US5014327A
Cited
JPS6444546A
Cited
US5375448A
Cited
US4984773A
Cited
US4984174A
Cited
US4958406A
Cited
US5084813A
Cited
US5179634A
Cited
EP0421793A2
Cited
US5065440A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1999-06-18 | 1999-12-18 | 2000-06-18 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2003-06-18 | 2003-12-18 | 2004-06-18 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2007-06-18 | 2007-12-18 | 2008-06-18 | $7700.00 | Window Closed / Lapsed |