Abstract
Recently, sensor fusion is received much attention in various fields. In sensor fusion, sensor values are integrated and fused for inferring states which conventional sensors cannot measure easily. This paper describes a novel sensor fusion method by a link selective neural network based on sensor selection. In this method, sensors are selected by offline sensor selection according to process condition and online sensor selection according to the reliability of each sensor value. The link selective neural network consists on two neural networks, a fusion neural network and a gating neural network. The gating neural network determines the structure of the fusion neural network according to sensor selection and process conditions. For showing the effectiveness, we apply the proposed method to inference of the surface roughness in the grinding process.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series C
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
