Seungjae Won
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Seungjae Won has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Joel Jang
Department of Computer Science and Engineering Korea University 02841 Seoul Republic of Korea
1 shared publication - Mayank Shekhar Jha
Université de Lorraine, CNRS, CRAN, Nancy, France
1 shared publication - Sungho Suh
Korea University, Seoul, Republic of Korea
1 shared publication - Yong Oh Lee
Department of Industrial and Data Engineering, Hongik University, Seoul 04066, Republic of Korea
1 shared publication
Latest Publications
- Open Access
Supervised Health Stage Prediction Using Convolutional Neural Networks for Bearing Wear
Early detection of faults in rotating machinery systems is crucial in preventing system failure, increasing safety, and reducing maintenance costs. Current methods of fault detection suffer from the lack of efficient feature extraction method, the need for designating a threshold producing minimal false alarm rates, and the need for expert domain knowledge, which is costly. In this paper, we propose a novel data-driven health division method based on convolutional neural networks using a graphical representation of time series data, called a nested scatter plot. The proposed method trains the model with a small amount of labeled data and does not require a threshold value to predict the health state of rotary machines. Notwithstanding the lack of datasets that show the ground truth of health stages, our experiments with two open datasets of run-to-failure bearing demonstrated that our method is able to detect the early symptoms of bearing wear earlier and more efficiently than other threshold-based health indicator methods.
Open AccessSupervised Health Stage Prediction Using Convolutional Neural Networks for Bearing Wear
Early detection of faults in rotating machinery systems is crucial in preventing system failure, increasing safety, and reducing maintenance costs. Current methods of fault detection suffer from the lack of efficient feature extraction method, the need for designating a threshold producing minimal false alarm rates, and the need for expert domain knowledge, which is costly. In this paper, we propose a novel data-driven health division method based on convolutional neural networks using a graphical representation of time series data, called a nested scatter plot. The proposed method trains the model with a small amount of labeled data and does not require a threshold value to predict the health state of rotary machines. Notwithstanding the lack of datasets that show the ground truth of health stages, our experiments with two open datasets of run-to-failure bearing demonstrated that our method is able to detect the early symptoms of bearing wear earlier and more efficiently than other threshold-based health indicator methods.