Abstract
This study develops a novel dual-stage diagnosis scheme for accelerating bearing failure diagnosis. The schema integrates the intelligent methods, i.e., genetic algorithm, k-nearest neighbors, and neural network, in the featuring and modeling stages to automatically select the significant features from various feature candidates for modeling bearing failure modes. After applying the scheme to classify two cases of bearing faults, the mean training time for model diagnosis is reduced to 8.1% that of using a neural network model. In this work, case 1 indicates that training and testing accuracies of seven failure modes are 98.8% and 94.5%, respectively; in addition, case 2 shows that the training and testing accuracies are 96.2% and 91.8% while using the top seven features.
| Original language | English |
|---|---|
| Title of host publication | SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts |
| Publisher | Society of Instrument and Control Engineers (SICE) |
| Pages | 235-239 |
| Number of pages | 5 |
| ISBN (Print) | 9784907764395 |
| Publication status | Published - 2011 Jan 1 |
| Event | 50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011 - Tokyo, Japan Duration: 2011 Sep 13 → 2011 Sep 18 |
Publication series
| Name | Proceedings of the SICE Annual Conference |
|---|
Other
| Other | 50th Annual Conference on Society of Instrument and Control Engineers, SICE 2011 |
|---|---|
| Country | Japan |
| City | Tokyo |
| Period | 11-09-13 → 11-09-18 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Computer Science Applications
- Electrical and Electronic Engineering
Cite this
}
Automatic feature selection and failure diagnosis for bearing faults. / Yang, Haw Ching; Tieng, Hao; Chen, Shih Fang.
SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts. Society of Instrument and Control Engineers (SICE), 2011. p. 235-239 6060609 (Proceedings of the SICE Annual Conference).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Automatic feature selection and failure diagnosis for bearing faults
AU - Yang, Haw Ching
AU - Tieng, Hao
AU - Chen, Shih Fang
PY - 2011/1/1
Y1 - 2011/1/1
N2 - This study develops a novel dual-stage diagnosis scheme for accelerating bearing failure diagnosis. The schema integrates the intelligent methods, i.e., genetic algorithm, k-nearest neighbors, and neural network, in the featuring and modeling stages to automatically select the significant features from various feature candidates for modeling bearing failure modes. After applying the scheme to classify two cases of bearing faults, the mean training time for model diagnosis is reduced to 8.1% that of using a neural network model. In this work, case 1 indicates that training and testing accuracies of seven failure modes are 98.8% and 94.5%, respectively; in addition, case 2 shows that the training and testing accuracies are 96.2% and 91.8% while using the top seven features.
AB - This study develops a novel dual-stage diagnosis scheme for accelerating bearing failure diagnosis. The schema integrates the intelligent methods, i.e., genetic algorithm, k-nearest neighbors, and neural network, in the featuring and modeling stages to automatically select the significant features from various feature candidates for modeling bearing failure modes. After applying the scheme to classify two cases of bearing faults, the mean training time for model diagnosis is reduced to 8.1% that of using a neural network model. In this work, case 1 indicates that training and testing accuracies of seven failure modes are 98.8% and 94.5%, respectively; in addition, case 2 shows that the training and testing accuracies are 96.2% and 91.8% while using the top seven features.
UR - http://www.scopus.com/inward/record.url?scp=81255178797&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=81255178797&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:81255178797
SN - 9784907764395
T3 - Proceedings of the SICE Annual Conference
SP - 235
EP - 239
BT - SICE 2011 - SICE Annual Conference 2011, Final Program and Abstracts
PB - Society of Instrument and Control Engineers (SICE)
ER -