Next Article in Journal
A Theoretical Conversation about Responses to Information Overload
Next Article in Special Issue
Editorial for the Special Issue on “CDEC: Cross-Disciplinary Data Exchange and Collaboration”
Previous Article in Journal
Model for Collaboration among Carriers to Reduce Empty Container Truck Trips
Previous Article in Special Issue
Topic Jerk Detector: Detection of Tweet Bursts Related to the Fukushima Daiichi Nuclear Disaster
 
 
Article

Feature Extraction of Laser Machining Data by Using Deep Multi-Task Learning

Department of Systems Innovation, School of Engineering, The University of Tokyo, Hongo 7-3-1, Bunkyo-ku, Tokyo 113-8656, Japan
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Information 2020, 11(8), 378; https://doi.org/10.3390/info11080378
Received: 30 June 2020 / Revised: 18 July 2020 / Accepted: 23 July 2020 / Published: 27 July 2020
(This article belongs to the Special Issue CDEC: Cross-disciplinary Data Exchange and Collaboration)
Laser machining has been widely used for materials processing, while the inherent complex physical process is rather difficult to be modeled and computed with analytical formulations. Through attending a workshop on discovering the value of laser machining data, we are profoundly motivated by the recent work by Tani et al., who proposed in situ monitoring of laser processing assisted by neural networks. In this paper, we propose an application of deep learning in extracting representative features from laser processing images with a multi-task loss that consists of cross-entropy loss and logarithmic smooth L1 loss. In the experiment, AlexNet with multi-task learning proves to be better than deeper models. This framework of deep feature extraction also has tremendous potential to solve more laser machining problems in the future. View Full-Text
Keywords: deep learning; feature extraction; multi-task learning; laser processing deep learning; feature extraction; multi-task learning; laser processing
Show Figures

Figure 1

MDPI and ACS Style

Zhang, Q.; Wang, Z.; Wang, B.; Ohsawa, Y.; Hayashi, T. Feature Extraction of Laser Machining Data by Using Deep Multi-Task Learning. Information 2020, 11, 378. https://doi.org/10.3390/info11080378

AMA Style

Zhang Q, Wang Z, Wang B, Ohsawa Y, Hayashi T. Feature Extraction of Laser Machining Data by Using Deep Multi-Task Learning. Information. 2020; 11(8):378. https://doi.org/10.3390/info11080378

Chicago/Turabian Style

Zhang, Quexuan, Zexuan Wang, Bin Wang, Yukio Ohsawa, and Teruaki Hayashi. 2020. "Feature Extraction of Laser Machining Data by Using Deep Multi-Task Learning" Information 11, no. 8: 378. https://doi.org/10.3390/info11080378

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop