Method for calculating confidence on prediction in fault diagnosis systems
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06F-019/00
G06F-011/07
G06F-011/30
G01M-015/14
출원번호
US-0112021
(2008-04-30)
등록번호
US-8417432
(2013-04-09)
발명자
/ 주소
Butler, Steven Wayne
출원인 / 주소
United Technologies Corporation
대리인 / 주소
Carlson, Gaskey & Olds, PC
인용정보
피인용 횟수 :
2인용 특허 :
12
초록
A method and system is developed that provides a confidence measure of a prediction of a fault in a gas turbine engine. The confidence measure is developed based upon evaluating the results of a plurality of past predictions and comparing them to an actual fault.
대표청구항▼
1. A fault diagnosis system comprising: a fault detection system for taking in a plurality of sensor readings from a gas turbine engine;said plurality of sensors providing readings to a fault isolation system, said fault isolation system predicting a current fault based upon said readings, and to a
1. A fault diagnosis system comprising: a fault detection system for taking in a plurality of sensor readings from a gas turbine engine;said plurality of sensors providing readings to a fault isolation system, said fault isolation system predicting a current fault based upon said readings, and to a network communicating with a database of prior predictions, and the database associating the prior predictions with a confidence level for the current prediction; andsaid fault isolation system providing the predicted current fault to an output, and the confidence level in the current prediction also being provided to the output. 2. The system as set forth in claim 1, wherein the database is developed, at least in part, using a model-based fault isolation system. 3. The system as set forth in claim 2, wherein a regression network is trained based upon the model-based fault isolation system to provide the confidence level. 4. The system as set forth in claim 3, wherein said regression network is trained by calculating a linear distance between shift magnitudes received from a fault detection system and each of the data points received from the database, using the following equation: Dk=∑i=1m(Measurementi-StoredMeasurementi,k)2, where Measurementi is sensor i from the received shift magnitudes, StoredMeasurementi,k is sensor i of stored data point k from the database, Dk is the distance to measurement k, and m is the total number of sensors monitored, then a Gaussian kernel function is applied to these distances, with the Gaussian kernel function being wk=exp(-Dk22h2), where wk is the calculated weight for data point k and h is a tuning factor to adjust the standard deviation of the Gaussian kernel function, and each of these weights, wk, are multiplied by a respective accuracy votes stored in the database, then a final confidence is calculated as, Confidence=∑k(votekwk)(∑kwk)+BIAS, where votek is the accuracy vote associated with data point k, Confidence is the output confidence from the algorithm, and BIAS is a positive bias applied to the denominator to ensure a low confidence if the shift magnitudes received are not near any previously encountered point. 5. The system as set forth in claim 2, wherein the database is also developed based upon actual examples of correct and incorrect predictions. 6. The system as set forth in claim 1, wherein the database is developed based upon actual examples of correct and incorrect predictions. 7. The system as set forth in claim 1, wherein the provided confidence level is in the form of a percentage chance that the predicted fault is an accurate fault. 8. The system as set forth in claim 7, wherein a bias factor is utilized to reduce the confidence level percentage if there are few or no previously encountered data points which closely resemble the current data point. 9. The system as set forth in claim 1, wherein the database associates the prior predictions with said confidence level at least in part utilizing the accuracy of said prior predictions. 10. The system as set forth in claim 1, wherein said output is a computer. 11. A method of operating a fault prediction system including the steps of: (a) taking in a plurality of sensor readings from a gas turbine engine;(b) providing readings to a fault isolation system, and predicting a current fault based upon said readings to a network communicating with a database of prior predictions, the database associating the prior predictions with a confidence level in the current prediction; and(c) said fault isolation system providing the predicted current fault to an output, and the confidence level in the current prediction also being provided to the output. 12. The method as set forth in claim 11, wherein the database is developed, at least in part, using a model-based fault isolation system. 13. The method as set forth in claim 12, wherein a regression network is trained based upon the model-based fault isolation system to provide the confidence level. 14. The method as set forth in claim 13, wherein said regression network is trained by calculating a linear distance between shift magnitudes received from a fault detection system and each of the data points received from the database, using the following equation: Dk=∑i=1m(Measurementi-StoredMeasurementi,k)2, where Measurementi is sensor i from the received shift magnitudes, StoredMeasurementi,k is sensor i of stored data point k from the database, Dk is the distance to measurement k, and m is the total number of sensors monitored, then a Gaussian kernel function is applied to these distances, with the Gaussian kernel function being wk=exp(-Dk22h2), where wk is the calculated weight for data point k and h is a tuning factor to adjust the standard deviation of the Gaussian kernel function, and each of these weights, wk, are multiplied by a respective accuracy votes stored in the database, then a final confidence is calculated as, Confidence=∑k(votekwk)(∑kwk)+BIAS, where votek is the accuracy vote associated with data point k, Confidence is the output confidence from the algorithm, and BIAS is a positive bias applied to the denominator to ensure a low confidence if the shift magnitudes received are not near any previously encountered point. 15. The method as set forth in claim 12, wherein the database also is developed utilizing actual examples of correct and incorrect predictions. 16. The method as set forth in claim 11, wherein the database is developed utilizing actual examples of correct and incorrect predictions. 17. The method as set forth in claim 11, wherein the provided confidence level is in the form of a percentage chance that the predicted fault is an accurate fault. 18. The method as set forth in claim 17, wherein a bias factor is utilized to reduce the confidence level percentage if there are few or no previously encountered data points which closely resemble the current data point. 19. The method as set forth in claim 11, wherein the database associates the prior predictions with said confidence level at least in part utilizing the accuracy of said prior predictions. 20. The method as set forth in claim 11, wherein the output is a computer.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (12)
Kemper Christian T. (Winter Park FL) Bellows James C. (Seminole FL) Kleinosky Pamela J. (Philadelphia PA), Diagnostic apparatus.
Hogg George W. (Palm Beach Gardens FL) Carron Karen A. (Palm Beach Gardens FL) Wright Brian D. (West Palm Beach FL) Stambaugh ; Sr. Craig T. (Port St. Lucie FL), Engine fault diagnostic system.
Wang Hsu-Pin (Tallahassee FL) Huang Hsin-Hao (Kaohsiung TWX) Knapp Gerald M. (Baton Rouge LA) Lin Chang-Ching (Tallahassee FL) Lin Shui-Shun (Tallahassee FL) Spoerre Julie K. (Tallahassee FL), Machine fault diagnostics system and method.
Sheppard John W. (Glen Burnie MD) Simpson William R. (Edgewater MD) Graham Jerry L. (Baldwin MD), Method and apparatus for diagnostic testing including a neural network for determining testing sufficiency.
Zwicke Philip E. (South Glastonbury CT) Rosenbush David M. (Granby CT) Couch Robert P. (Palm Beach Gardens FL), System fault discriminating electrostatic engine diagnostics.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.