Unsupervised condition change detection in large diesel engines

被引：19

作者：

Pontoppidan, NH ^{[1
]}

Larsen, J ^{[1
]}

机构：

[1] Tech Univ Denmark, DK-2800 Lyngby, Denmark

来源：

2003 IEEE XIII WORKSHOP ON NEURAL NETWORKS FOR SIGNAL PROCESSING - NNSP'03 | 2003年

关键词：

D O I：

10.1109/NNSP.2003.1318056

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a new method for unsupervised change detection which combines independent component modeling and probabilistic outlier detection. The method further provides a compact data representation, which is amenable to interpretation, i.e., the detected condition changes can be investigated further. The method is successfully applied to unsupervised condition change detection in large diesel engines from acoustical emission sensor signal and compared to more classical techniques based on principal component analysis and Gaussian mixture models.

引用

页码：565 / 574

页数：10

共 22 条

[1]

Basseville M., 1993, DETECTION ABRUPT CHA

[2] AN INFORMATION MAXIMIZATION APPROACH TO BLIND SEPARATION AND BLIND DECONVOLUTION [J].

BELL, AJ ;

SEJNOWSKI, TJ .

NEURAL COMPUTATION, 1995, 7 (06) :1129-1159

[3] NOVELTY DETECTION AND NEURAL-NETWORK VALIDATION [J].

BISHOP, CM .

IEE PROCEEDINGS-VISION IMAGE AND SIGNAL PROCESSING, 1994, 141 (04) :217-222

[4]

CHANDROTH G, 1999, COMADEM 99

[5]

CHANDROTH G, 1999, MARINE TECHNOLOGY OD

[6]

FOG T, 1998, IMMPHD199852

[7]

FOG TL, 1999, P IEEE WORKSH NEUR N, V9, P225

[8]

Gustafsson F, 2000, ADAPTIVE FILTERING C

[9]

Hansen LK, 2001, INT CONF ACOUST SPEE, P3197, DOI 10.1109/ICASSP.2001.940338

[10]

Hansen LK, 2000, INT CONF ACOUST SPEE, P3494, DOI 10.1109/ICASSP.2000.860154

← 1 2 3 →