Fault Log Recovery Using an Incomplete-data-trained FDA Classifier for Failure Diagnosis of Engineered Systems
In the 2015 PHM Data Challenge Competition, the goal of the competition problem was to diagnose failure of industrial plant systems using incomplete data. The available data consisted of sensor measurements, control reference signals, and fault logs. A detailed description of the plant system of int...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Prognostics and Health Management Society
2016-01-01
|
| Series: | International Journal of Prognostics and Health Management |
| Subjects: | |
| Online Access: | https://papers.phmsociety.org/index.php/ijphm/article/view/2330 |
| id |
doaj-2bd3ea667c944046b3ff9642ee828efb |
|---|---|
| record_format |
Article |
| spelling |
doaj-2bd3ea667c944046b3ff9642ee828efb2021-07-02T18:48:09ZengThe Prognostics and Health Management SocietyInternational Journal of Prognostics and Health Management2153-26482153-26482016-01-0171doi:10.36001/ijphm.2016.v7i1.2330Fault Log Recovery Using an Incomplete-data-trained FDA Classifier for Failure Diagnosis of Engineered SystemsHyunjae Kim0Jong Moon Ha1Jungho Park2Sunuwe Kim3Keunsu Kim4Beom Chan Jang5Hyunseok Oh6Byeng D. Youn7Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul 151-742, Republic of KoreaDepartment of Mechanical and Aerospace Engineering, Seoul National University, Seoul 151-742, Republic of KoreaDepartment of Mechanical and Aerospace Engineering, Seoul National University, Seoul 151-742, Republic of KoreaDepartment of Mechanical and Aerospace Engineering, Seoul National University, Seoul 151-742, Republic of KoreaDepartment of Mechanical and Aerospace Engineering, Seoul National University, Seoul 151-742, Republic of KoreaDepartment of Mechanical and Aerospace Engineering, Seoul National University, Seoul 151-742, Republic of KoreaDepartment of Mechanical and Aerospace Engineering, Seoul National University, Seoul 151-742, Republic of KoreaDepartment of Mechanical and Aerospace Engineering, Seoul National University, Seoul 151-742, Republic of KoreaIn the 2015 PHM Data Challenge Competition, the goal of the competition problem was to diagnose failure of industrial plant systems using incomplete data. The available data consisted of sensor measurements, control reference signals, and fault logs. A detailed description of the plant system of interest was not revealed, and partial fault logs were eliminated from the dataset. This paper presents a fault log recovery method using a machine-learning-based fault classification approach for failure diagnosis. For optimal performance, it was critical to be able to utilize a set of incomplete data and to select relevant features. First, physical interpretation of the given data was performed to select proper features for a fault classifier. Second, Fisher discriminant analysis (FDA) was employed to minimize the effect of outliers in the incomplete data sets. Finally, the type of the missing fault logs and the duration of the corresponding faults were recovered. The proposed approach, based on the use of an incomplete-data-trained FDA classifier, led to the second-highest score in the 2015 PHM Data Challenge Competition.https://papers.phmsociety.org/index.php/ijphm/article/view/2330data-drivendiagnostics & prognostics methodsincomplete datafault classification |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Hyunjae Kim Jong Moon Ha Jungho Park Sunuwe Kim Keunsu Kim Beom Chan Jang Hyunseok Oh Byeng D. Youn |
| spellingShingle |
Hyunjae Kim Jong Moon Ha Jungho Park Sunuwe Kim Keunsu Kim Beom Chan Jang Hyunseok Oh Byeng D. Youn Fault Log Recovery Using an Incomplete-data-trained FDA Classifier for Failure Diagnosis of Engineered Systems International Journal of Prognostics and Health Management data-driven diagnostics & prognostics methods incomplete data fault classification |
| author_facet |
Hyunjae Kim Jong Moon Ha Jungho Park Sunuwe Kim Keunsu Kim Beom Chan Jang Hyunseok Oh Byeng D. Youn |
| author_sort |
Hyunjae Kim |
| title |
Fault Log Recovery Using an Incomplete-data-trained FDA Classifier for Failure Diagnosis of Engineered Systems |
| title_short |
Fault Log Recovery Using an Incomplete-data-trained FDA Classifier for Failure Diagnosis of Engineered Systems |
| title_full |
Fault Log Recovery Using an Incomplete-data-trained FDA Classifier for Failure Diagnosis of Engineered Systems |
| title_fullStr |
Fault Log Recovery Using an Incomplete-data-trained FDA Classifier for Failure Diagnosis of Engineered Systems |
| title_full_unstemmed |
Fault Log Recovery Using an Incomplete-data-trained FDA Classifier for Failure Diagnosis of Engineered Systems |
| title_sort |
fault log recovery using an incomplete-data-trained fda classifier for failure diagnosis of engineered systems |
| publisher |
The Prognostics and Health Management Society |
| series |
International Journal of Prognostics and Health Management |
| issn |
2153-2648 2153-2648 |
| publishDate |
2016-01-01 |
| description |
In the 2015 PHM Data Challenge Competition, the goal of the competition problem was to diagnose failure of industrial plant systems using incomplete data. The available data consisted of sensor measurements, control reference signals, and fault logs. A detailed description of the plant system of interest was not revealed, and partial fault logs were eliminated from the dataset. This paper presents a fault log recovery method using a machine-learning-based fault classification approach for failure diagnosis. For optimal performance, it was critical to be able to utilize a set of incomplete data and to select relevant features. First, physical interpretation of the given data was performed to select proper features for a fault classifier. Second, Fisher discriminant analysis (FDA) was employed to minimize the effect of outliers in the incomplete data sets. Finally, the type of the missing fault logs and the duration of the corresponding faults were recovered. The proposed approach, based on the use of an incomplete-data-trained FDA classifier, led to the second-highest score in the 2015 PHM Data Challenge Competition. |
| topic |
data-driven diagnostics & prognostics methods incomplete data fault classification |
| url |
https://papers.phmsociety.org/index.php/ijphm/article/view/2330 |
| work_keys_str_mv |
AT hyunjaekim faultlogrecoveryusinganincompletedatatrainedfdaclassifierforfailurediagnosisofengineeredsystems AT jongmoonha faultlogrecoveryusinganincompletedatatrainedfdaclassifierforfailurediagnosisofengineeredsystems AT junghopark faultlogrecoveryusinganincompletedatatrainedfdaclassifierforfailurediagnosisofengineeredsystems AT sunuwekim faultlogrecoveryusinganincompletedatatrainedfdaclassifierforfailurediagnosisofengineeredsystems AT keunsukim faultlogrecoveryusinganincompletedatatrainedfdaclassifierforfailurediagnosisofengineeredsystems AT beomchanjang faultlogrecoveryusinganincompletedatatrainedfdaclassifierforfailurediagnosisofengineeredsystems AT hyunseokoh faultlogrecoveryusinganincompletedatatrainedfdaclassifierforfailurediagnosisofengineeredsystems AT byengdyoun faultlogrecoveryusinganincompletedatatrainedfdaclassifierforfailurediagnosisofengineeredsystems |
| _version_ |
1721324406712565760 |