[특허]Monitoring system using kernel regression modeling with pattern sequences

Smartsignal Corporation

검색어에 아래의 연산자를 사용하시면 더 정확한 검색결과를 얻을 수 있습니다.
검색연산자

검색도움말
검색연산자	기능	검색시 예
()	우선순위가 가장 높은 연산자	예1) (나노 (기계 \| machine))
공백	두 개의 검색어(식)을 모두 포함하고 있는 문서 검색	예1) (나노 기계) 예2) 나노 장영실
\|	두 개의 검색어(식) 중 하나 이상 포함하고 있는 문서 검색	예1) (줄기세포 \| 면역) 예2) 줄기세포 \| 장영실
!	NOT 이후에 있는 검색어가 포함된 문서는 제외	예1) (황금 !백금) 예2) !image
*	검색어의 *란에 0개 이상의 임의의 문자가 포함된 문서 검색	예) semi*
""	따옴표 내의 구문과 완전히 일치하는 문서만 검색	예) "Transform and Quantization"

과학기술 지식인프라 ScienceON

연합인증

연합인증 가입 기관의 연구자들은 소속기관의 인증정보(ID와 암호)를 이용해 다른 대학, 연구기관, 서비스 공급자의 다양한 온라인 자원과 연구 데이터를 이용할 수 있습니다.

이는 여행자가 자국에서 발행 받은 여권으로 세계 각국을 자유롭게 여행할 수 있는 것과 같습니다.

연합인증으로 이용이 가능한 서비스는 NTIS, DataON, Edison, Kafe, Webinar 등이 있습니다.

한번의 인증절차만으로 연합인증 가입 서비스에 추가 로그인 없이 이용이 가능합니다.

다만, 연합인증을 위해서는 최초 1회만 인증 절차가 필요합니다. (회원이 아닐 경우 회원 가입이 필요합니다.)

연합인증 절차는 다음과 같습니다.

최초이용시에는
ScienceON에 로그인 → 연합인증 서비스 접속 → 로그인 (본인 확인 또는 회원가입) → 서비스 이용

그 이후에는
ScienceON 로그인 → 연합인증 서비스 접속 → 서비스 이용

연합인증을 활용하시면 KISTI가 제공하는 다양한 서비스를 편리하게 이용하실 수 있습니다.

특허 상세정보

MyON담기

내보내기 페이스북 공유 트위터 공유 카카오톡 공유

Monitoring system using kernel regression modeling with pattern sequences

특허상세정보
국가/구분	United States(US) Patent 등록
국제특허분류(IPC7판)	G06F-017/00
미국특허분류(USC)	706/052;
출원번호	US-0186128 (2011-07-19)
등록번호	US-8660980 (2014-02-25)
발명자 / 주소	Herzog, James P.
출원인 / 주소	Smartsignal Corporation
대리인 / 주소	Global Patent Operation
인용정보	피인용 횟수 : 16 인용 특허 : 181

초록
▼

A monitoring system for determining the condition of an object includes an empirical model with reference data that indicates the normal operational state of the object, and input pattern arrays. Each input pattern array has a plurality of time-ordered input vectors, while each input vector has input values representing a plurality of parameters indicating the current condition of the object. The empirical model generates estimate values based on a calculation that uses an input pattern array and the reference data to determine a similarity measure betwe...

대표
청구항
▼

1. A monitoring system for determining the condition of an object, comprising: an empirical model operated by at least one processor and having reference data that indicates the normal operational state of the object, and input pattern arrays, each input pattern array having a plurality of time-ordered input vectors, each input vector having input values representing a plurality of parameters indicating the current condition of the object, the reference data being grouped in equal-sized and multi-dimensional training arrays, each of the training arrays being equal in size to a corresponding input multi-dimensional pattern array and each training array including a plurality of time-ordered reference vectors sequenced in time,the empirical model being configured to generate estimate values based on a calculation that uses an input pattern array and the reference data to determine a similarity measure between the input values and the reference data; anda differencing module comparing the estimate values to the corresponding input values so that resulting values from the comparison can be used to determine the condition of the object. 2. The system of claim 1, wherein at least one of the input vectors is in multiple input pattern arrays. 3. The system of claim 1, wherein each input pattern array represents a time period including a plurality of time points along a sequence of the input vectors representing the operational state of the object. 4. The system of claim 3, wherein each input pattern array represents a time period that is different than, but overlaps, the time period of at least one of the other input pattern arrays. 5. The system of claim 3, wherein each input pattern array has a current primary vector from the sequence of input vectors and representing the most recent time point within the input pattern array. 6. The system of claim 5 wherein the input vectors are selected for each input pattern array by moving a look-back window along the sequence, selecting the current primary vector, and selecting one or more older vectors that follow the primary vector along the sequence and fit within the window. 7. The system according to claim 6 wherein the older vectors are consecutive along the sequence. 8. The system according to claim 6 wherein the older vectors are not consecutive along the sequence. 9. The system according to claim 1 wherein time intervals between the time points represented by the input vectors within an input pattern array are uniform. 10. The system according to claim 1 wherein time intervals between the time points represent by the input vectors within an input pattern array are unequal. 11. The system according to claim 1 wherein time intervals between time points represented by the input vectors within an input pattern array are shorter between input vectors that are more recent than the time intervals between later input vectors within the same input pattern array. 12. The system according to claim 1 wherein the total duration represented by the input pattern arrays varies. 13. The system according to claim 1 wherein the calculation is based on an equation that comprises: S⁡(X↔new,X↔i)=11+1ρ[1nsens⁢∑j=1nsens⁢(∑k=1nlb⁢(Wk⁢X↔new;j,k-X↔i;j,krangej)∑k=1nlb⁢Wk)]λ. 14. The system according to claim 1 wherein the calculation is based on an equation that comprises: S⁡(X↔new,X↔i)=1nsens⁢∑j=1nsens⁢[11+1ρ⁢(∑k=1nlb⁢(Wk⁢X↔new;j,k-X↔i;j,krangej)∑k=1nlb⁢Wk)λ]. 15. The system of claim 1 wherein the similarity measure is a value on a bounded range that indicates an input value and reference value are identical at one end of the range and have no similarity at another end of the range. 16. The system of claim 1, wherein the reference data comprises at least one learned sequential pattern matrix, each learned sequential pattern matrix having a plurality of reference vectors, each reference vector having reference values representing a plurality of parameters. 17. The system of claim 16 wherein the reference data forms a three-dimensional collection of the learned sequential pattern matrices. 18. The system of claim 17 wherein the three-dimensional collection is defined by three dimensions representing the parameters along a first dimension, the learned sequential pattern matrices along a second dimension, and time represented by the reference vectors in a third dimension. 19. The system of claim 17 wherein each input pattern array is compared to each learned sequential pattern matrix in the three-dimensional collection to determine a similarity measure for each learned sequential pattern matrix. 20. The system of claim 17 herein each learned sequential pattern matrix represents a time period including time points represented by the reference vectors, wherein the time period is different than, but overlaps, the time period of at least some of the other learned sequential pattern matrices in the three-dimensional collection. 21. The system of claim 17 wherein the learned sequential pattern matrices have the same number of vectors as the input pattern arrays. 22. The system of claim 17 wherein the learned sequential pattern matrices represent the same time points as the input pattern arrays. 23. The system of claim 17 wherein the similarity between one of the learned sequential pattern matrices and one of the input pattern arrays is based on the similarity between corresponding reference and input values that represent the same vector position relative to the position of the other vectors represented within their respective array. 24. The system of claim 17 wherein the similarity between one of the learned sequential pattern matrices and one of the input pattern arrays comprises calculating an average scalar similarity value for each parameter represented by the arrays. 25. The system of claim 17 wherein at least some of the input pattern arrays represent a time period that is different than the time period represented by at least one of the learned sequential pattern matrices. 26. The system according to claim 17 wherein the time period represented by the learned sequential pattern matrices varies. 27. The system according to claim 1 wherein the empirical model is configured to generate the estimate values in the form of an estimate matrix having a plurality of estimate vectors. 28. The system of claim 27 wherein the estimate vectors in each estimate matrix corresponds to the time points represented by the input vectors in the input pattern arrays. 29. The system of claim 27 wherein less than all of the estimate values within the estimate matrix are used to determine the condition of the object. 30. The system of claim 27 wherein the differencing module only uses the estimate values that represent the most recent time point within each estimate matrix to determine the condition of the object. 31. The system of claim 27 comprising providing a single estimate vector for each time point represented across multiple estimate matrices to determine the condition of the object. 32. The system of claim 31 wherein the single estimate vector is provided by using at least one of: selecting the estimate vector with one or more estimate values that has a maximum, minimum, or median value relative to other estimate vectors at the time point across multiple estimate matrices,calculating an average, a weighted average, or weighted norm of the estimate values at the time point across multiple estimate matrices, andselecting an estimate vector with the greatest similarity to a corresponding input vector relative to other estimate vectors at the time point across multiple estimate matrices. 33. The system of claim 27 wherein the empirical model provides an estimate vector to determine the condition of the object by using at least one of: an estimate vector within each estimate matrix that has a maximum, minimum, or median estimate value,a weighted average or weighted norm of the estimate values in the estimate matrix to form a single estimate for each matrix, andthe estimate vector within the estimate matrix with the greatest similarity to a respective corresponding input vector. 34. The system of claim 1 wherein the empirical model is configured to use the similarity measures as weights in a calculation with a three-dimensional collection of learned sequential pattern matrices that represents parameters that are not represented in the input pattern arrays. 35. The system of claim 34 wherein the reference data used to generate the similarity measures do not represent all of the parameters represented by the three-dimensional collection. 36. The system of claim 34 wherein the three-dimensional collection represents only parameters that are not represented by the input pattern arrays. 37. The system of claim 35 wherein the three-dimensional collection represents both parameters that are not represented by the input pattern arrays and parameters that are represented by the input pattern arrays. 38. The system of claim 1 comprising a localization module to predetermine which reference data is to be used to generate the estimate values for each input pattern array. 39. The system of claim 1 comprising an adaption module configured to add the input pattern arrays to the reference data when the estimate values indicate the corresponding input pattern array represents normal operation. 40. A monitoring system for determining the condition of an object, comprising: an empirical model operated by at least one processor and comprising reference data that indicates the normal operational state of the object and in the form of a plurality of learned, equal-size, time sequential and multi-dimensional pattern matrices, each learned, equal-size, time sequential and multi-dimensional pattern matrix having a plurality of reference vectors, each reference vector having reference values representing a plurality of parameters, each of the plurality of learned, equal-size, time sequential and multi-dimensional pattern matrices being equal in size to a corresponding input multi-dimensional pattern array, andinput data representing a plurality of parameters indicating the current condition of the object, the input data being a plurality of input multi-dimensional pattern arrays,wherein the empirical model is configured to generate estimate values based on a calculation that uses the input data and the learned, equal-size, time sequential and multi-dimensional pattern matrices to determine a similarity measure between the input data and reference values in the plurality of learned, equal-size, time sequential, and multi-dimensional pattern matrices; anda differencing module comparing the estimate values to corresponding input values so that resulting values from the comparison can be used to determine the condition of the object. 41. A monitoring system for determining the condition of an object, comprising: an empirical model operated by at least one processor and comprising reference data that indicates the normal operational state of the object, the reference data being grouped in equal-sized and multi-dimensional training arrays, each of the training arrays being equal in size to a corresponding input multi-dimensional pattern array and each training array including a plurality of time-ordered reference vectors sequenced in time, andinput data representing a plurality of parameters indicating the current condition of the object, the input data being a plurality of input multi-dimensional pattern arrays,wherein the empirical model is configured to generate estimate values based on a calculation that uses both the input data and the reference data to determine similarity measures between the input data and the reference data, wherein the estimate values are generated in the form of an estimate matrix having a plurality of time-ordered estimate vectors, each estimate vector having estimate values representing multiple parameters; anda differencing module comparing at least one estimate vector for each time period represented by the estimate matrix to the input data so that the resulting values from the comparison can be used to determine the condition of the object.

이 특허에 인용된 특허 (181)

이 특허를 인용한 특허 피인용횟수: 16

IPC 상위 출원인

내보내기

상세정보
내보내기 구분	파일저장 인쇄 메일전송
구성항목	관리번호, 국가코드, 자료구분, 상태, 출원번호, 출원일자, 공개번호, 공개일자, 등록번호, 등록일자, 발명명칭(한글), 발명명칭(영문), 출원인(한글), 출원인(영문), 출원인코드, 대표IPC 관리번호, 국가코드, 자료구분, 상태, 출원번호, 출원일자, 공개번호, 공개일자, 공고번호, 공고일자, 등록번호, 등록일자, 발명명칭(한글), 발명명칭(영문), 출원인(한글), 출원인(영문), 출원인코드, 대표출원인, 출원인국적, 출원인주소, 발명자, 발명자E, 발명자코드, 발명자주소, 발명자 우편번호, 발명자국적, 대표IPC, IPC코드, 요약, 미국특허분류, 대리인주소, 대리인코드, 대리인(한글), 대리인(영문), 국제공개일자, 국제공개번호, 국제출원일자, 국제출원번호, 우선권, 우선권주장일, 우선권국가, 우선권출원번호, 원출원일자, 원출원번호, 지정국, Citing Patents, Cited Patents
저장형식	Text(ASCII format) Excel format PIAS분석(.xls)
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	> 총 건의 자료가 검색되었습니다. > 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) > 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. > 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) > 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오 > ~ > Text(ASCII format) Excel format

과학기술 지식인프라 ScienceON

ScienceON Chatbot

연합인증

특허 상세정보

Monitoring system using kernel regression modeling with pattern sequences

초록
▼

대표
청구항
▼

이 특허에 인용된 특허 (181)

이 특허를 인용한 특허 피인용횟수: 16

IPC 상위 출원인

과제정보

상세정보조회

원문조회

IPC 상세정보(version : 201201)

연구과제 성과물(0)

참여연구원의 다른 문헌(0)

처리중입니다.

잠시만 기다려주세요.

ScienceON Chatbot

연합인증

특허 상세정보

Monitoring system using kernel regression modeling with pattern sequences

초록 ▼

대표청구항 ▼

이 특허에 인용된 특허 (181)

이 특허를 인용한 특허 피인용횟수: 16

IPC 상위 출원인

과제정보

상세정보조회

원문조회

IPC 상세정보(version : 201201)

연구과제 성과물(0)

참여연구원의 다른 문헌(0)

처리중입니다.

잠시만 기다려주세요.

초록
▼

대표
청구항
▼