Semantic Scholar Open Access 2019 438 sitasi

A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults

Te Han Chao Liu Wenguang Yang D. Jiang

Abstrak

Abstract In recent years, deep learning has become an emerging research orientation in the field of intelligent monitoring and fault diagnosis for industry equipment. Generally, the success of supervised deep models is largely attributed to a mass of typically labeled data, while it is often limited in real diagnosis tasks. In addition, the diagnostic model trained with data from limited conditions may generalize poorly for conditions not observed during training. To tackle these challenges, adversarial learning is introduced as a regularization into the convolutional neural network (CNN), and a novel deep adversarial convolutional neural network (DACNN) is accordingly proposed in this paper. By adding an additional discriminative classifier, an adversarial learning framework can be developed to train the convolutional blocks with the split data subsets, leading to a minimax two-player game. This process contributes to making the feature representation robust, boosting the generalization ability of the trained model as well as avoiding overfitting with a small size of labeled samples. The comparison studies with respect to conventional deep models on two fault datasets demonstrate the applicability and superiority of proposed method.

Topik & Kata Kunci

Penulis (4)

T

Te Han

C

Chao Liu

W

Wenguang Yang

D

D. Jiang

Format Sitasi

Han, T., Liu, C., Yang, W., Jiang, D. (2019). A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults. https://doi.org/10.1016/J.KNOSYS.2018.12.019

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber doi.org/10.1016/J.KNOSYS.2018.12.019
Informasi Jurnal
Tahun Terbit
2019
Bahasa
en
Total Sitasi
438×
Sumber Database
Semantic Scholar
DOI
10.1016/J.KNOSYS.2018.12.019
Akses
Open Access ✓