Condition monitoring of a complex hydraulic system using multivariate statistics. Helwig, N., Pignanelli, E., & Schütze, A. In 2015 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings, pages 210–215, May, 2015. ISSN: 1091-5281doi abstract bibtex In this paper, a systematic approach for the automated training of condition monitoring systems for complex hydraulic systems is developed and evaluated. We analyzed different fault scenarios using a test rig that allows simulating a reversible degradation of component's conditions. By analyzing the correlation of features extracted from raw sensor data and the known fault characteristics of experimental obtained data, the most significant features specific to a fault case can be identified. These feature values are transferred to a lower-dimensional discriminant space using linear discriminant analysis (LDA) which allows the classification of fault condition and grade of severity. We successfully implemented and tested the system for a fixed working cycle of the hydraulic system. Furthermore, the classification rate for random load cycles was enhanced by a distribution analysis of feature trends.
@inproceedings{helwig_condition_2015,
title = {Condition monitoring of a complex hydraulic system using multivariate statistics},
doi = {10.1109/I2MTC.2015.7151267},
abstract = {In this paper, a systematic approach for the automated training of condition monitoring systems for complex hydraulic systems is developed and evaluated. We analyzed different fault scenarios using a test rig that allows simulating a reversible degradation of component's conditions. By analyzing the correlation of features extracted from raw sensor data and the known fault characteristics of experimental obtained data, the most significant features specific to a fault case can be identified. These feature values are transferred to a lower-dimensional discriminant space using linear discriminant analysis (LDA) which allows the classification of fault condition and grade of severity. We successfully implemented and tested the system for a fixed working cycle of the hydraulic system. Furthermore, the classification rate for random load cycles was enhanced by a distribution analysis of feature trends.},
booktitle = {2015 {IEEE} {International} {Instrumentation} and {Measurement} {Technology} {Conference} ({I2MTC}) {Proceedings}},
author = {Helwig, Nikolai and Pignanelli, Eliseo and Schütze, Andreas},
month = may,
year = {2015},
note = {ISSN: 1091-5281},
keywords = {Condition monitoring, Cooling, Correlation, Correlation coefficient, Feature extraction, Valves, condition monitoring, hydraulic system, linear discriminant analysis, multivariate statistics},
pages = {210--215},
}
Downloads: 0
{"_id":"oLctH294h7jbDX4Jd","bibbaseid":"helwig-pignanelli-schtze-conditionmonitoringofacomplexhydraulicsystemusingmultivariatestatistics-2015","author_short":["Helwig, N.","Pignanelli, E.","Schütze, A."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Condition monitoring of a complex hydraulic system using multivariate statistics","doi":"10.1109/I2MTC.2015.7151267","abstract":"In this paper, a systematic approach for the automated training of condition monitoring systems for complex hydraulic systems is developed and evaluated. We analyzed different fault scenarios using a test rig that allows simulating a reversible degradation of component's conditions. By analyzing the correlation of features extracted from raw sensor data and the known fault characteristics of experimental obtained data, the most significant features specific to a fault case can be identified. These feature values are transferred to a lower-dimensional discriminant space using linear discriminant analysis (LDA) which allows the classification of fault condition and grade of severity. We successfully implemented and tested the system for a fixed working cycle of the hydraulic system. Furthermore, the classification rate for random load cycles was enhanced by a distribution analysis of feature trends.","booktitle":"2015 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings","author":[{"propositions":[],"lastnames":["Helwig"],"firstnames":["Nikolai"],"suffixes":[]},{"propositions":[],"lastnames":["Pignanelli"],"firstnames":["Eliseo"],"suffixes":[]},{"propositions":[],"lastnames":["Schütze"],"firstnames":["Andreas"],"suffixes":[]}],"month":"May","year":"2015","note":"ISSN: 1091-5281","keywords":"Condition monitoring, Cooling, Correlation, Correlation coefficient, Feature extraction, Valves, condition monitoring, hydraulic system, linear discriminant analysis, multivariate statistics","pages":"210–215","bibtex":"@inproceedings{helwig_condition_2015,\n\ttitle = {Condition monitoring of a complex hydraulic system using multivariate statistics},\n\tdoi = {10.1109/I2MTC.2015.7151267},\n\tabstract = {In this paper, a systematic approach for the automated training of condition monitoring systems for complex hydraulic systems is developed and evaluated. We analyzed different fault scenarios using a test rig that allows simulating a reversible degradation of component's conditions. By analyzing the correlation of features extracted from raw sensor data and the known fault characteristics of experimental obtained data, the most significant features specific to a fault case can be identified. These feature values are transferred to a lower-dimensional discriminant space using linear discriminant analysis (LDA) which allows the classification of fault condition and grade of severity. We successfully implemented and tested the system for a fixed working cycle of the hydraulic system. Furthermore, the classification rate for random load cycles was enhanced by a distribution analysis of feature trends.},\n\tbooktitle = {2015 {IEEE} {International} {Instrumentation} and {Measurement} {Technology} {Conference} ({I2MTC}) {Proceedings}},\n\tauthor = {Helwig, Nikolai and Pignanelli, Eliseo and Schütze, Andreas},\n\tmonth = may,\n\tyear = {2015},\n\tnote = {ISSN: 1091-5281},\n\tkeywords = {Condition monitoring, Cooling, Correlation, Correlation coefficient, Feature extraction, Valves, condition monitoring, hydraulic system, linear discriminant analysis, multivariate statistics},\n\tpages = {210--215},\n}\n\n","author_short":["Helwig, N.","Pignanelli, E.","Schütze, A."],"key":"helwig_condition_2015","id":"helwig_condition_2015","bibbaseid":"helwig-pignanelli-schtze-conditionmonitoringofacomplexhydraulicsystemusingmultivariatestatistics-2015","role":"author","urls":{},"keyword":["Condition monitoring","Cooling","Correlation","Correlation coefficient","Feature extraction","Valves","condition monitoring","hydraulic system","linear discriminant analysis","multivariate statistics"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["condition monitoring","cooling","correlation","correlation coefficient","feature extraction","valves","condition monitoring","hydraulic system","linear discriminant analysis","multivariate statistics"],"search_terms":["condition","monitoring","complex","hydraulic","system","using","multivariate","statistics","helwig","pignanelli","schütze"],"title":"Condition monitoring of a complex hydraulic system using multivariate statistics","year":2015}