Abstract—With the development of sensor network
technologies and the popularization of Industry 4.0, data-driven
machine health monitoring has become increasingly important,
not only to save maintenance costs of factory machinery, but also
to guarantee the safety of factories. However, traditional
data-driven algorithms are limited by two aspects. Firstly, the
information fusion of multiple sensors heavily relies on domain
knowledge. Secondly, imbalanced distribution of machinery
data brings a challenge for the machine learning algorithm
performance. In order to tackle these issues, we propose a
general methodology to organize collected sensor data into
image form and utilize visual element detectors learned by a
pre-trained convnet to explore meaningful information hidden
in data. We also design a Convolutional Neural Network (CNN)
model, named Senvis-Net. Applied to an imbalance learning task
of remaining useful life (RUL) prediction, our model
outperforms the state-of-the-art CNN that learns directly from
sensor data. Moreover, transferring visual element detectors can
bring another 20.1% ~ 97% performance benefits depending on
severity of imbalance.
Index Terms—Machine health monitoring, convolutional neural network, imbalanced data, transfer learning.
Qingwei Guo, Huazhong Yang, Yongpan Liu are with Tsinghua University, China (e-mail: firstname.lastname@example.org, email@example.com, firstname.lastname@example.org).
Yoshinori Miyamae, Zhongjun Wang, Koji Taniuchi are with ROHM Semiconductor, Japan (e-mail: Yoshinori.Miyamae@dsn.rohm.co.jp, email@example.com, firstname.lastname@example.org).
Cite: Qingwei Guo, Yoshinori Miyamae, Zhongjun Wang, Koji Taniuchi, Huazhong Yang, and Yongpan Liu, "Senvis-Net: Learning from Imbalanced Machinery Data by Transferring Visual Element Detectors," International Journal of Machine Learning and Computing vol. 8, no. 5, pp. 416-422, 2018.