Genetically programmed-based artificial features extraction applied to fault detection

@article{Firpi2008, abstract = {This paper presents a novel application of genetically programmed artificial features, which are computer crafted, data driven, and possibly without physical interpretation, to the problem of fault detection. Artificial features are extracted from vibration data of an accelerometer sensor to monitor and detect a crack fault or incipient failure seeded in an intermediate gearbox of a helicopter's main transmission. Classification accuracies for the artificial feature constructed from raw data exceeded 99\% over training and independent validation sets. As a benchmark, GP-based artificial features constructed from conventional ones underperformed those derived from raw data by over 2\% over the training and over 11\% over the testing data.}, author = {Firpi, Hiram and Vachtsevanos, George }, citeulike-article-id = {2843988}, doi = {http://dx.doi.org/10.1016/j.engappai.2007.06.004}, journal = {Engineering Applications of Artificial Intelligence}, month = {June}, number = {4}, pages = {558--568}, posted-at = {2008-05-29 11:01:02}, priority = {2}, title = {Genetically programmed-based artificial features extraction applied to fault detection}, url = {http://dx.doi.org/10.1016/j.engappai.2007.06.004}, volume = {21}, year = {2008} }

TY - JOUR ID - Firpi2008 L3 - citeulike-article-id:2843988 N2 - This paper presents a novel application of genetically programmed artificial features, which are computer crafted, data driven, and possibly without physical interpretation, to the problem of fault detection. Artificial features are extracted from vibration data of an accelerometer sensor to monitor and detect a crack fault or incipient failure seeded in an intermediate gearbox of a helicopter's main transmission. Classification accuracies for the artificial feature constructed from raw data exceeded 99% over training and independent validation sets. As a benchmark, GP-based artificial features constructed from conventional ones underperformed those derived from raw data by over 2% over the training and over 11% over the testing data. IS - 4 JF - Engineering Applications of Artificial Intelligence EP - 568 TI - Genetically programmed-based artificial features extraction applied to fault detection VL - 21 SP - 558 AU - Firpi, Hiram AU - Vachtsevanos, George PY - 2008/06// UR - http://dx.doi.org/10.1016/j.engappai.2007.06.004 ER -