Topic：ACMAE 2019 conference presentation

Time：Thursday 16:00pm, January 2, 2020

Location：Room 2149, Building 2, iHarbour campus

Presenter：Yuanhong CHANG(常元洪)

Conference Name：2019 The 10th Asia Conference on Mechanical and Aerospace Engineer, ACMAE 2019

Conference Time：26-28 December, 2019

Conference Location：Bangkok, Thailand

Conference introduction：The major goal and feature of ACMAE 2019 is to bring academic scientists, engineers, industry researchers together to exchange and share their experiences and researchresults, and discuss the practical challenges encountered and the solutions adopted.Prestigious experts and professors have been invited to deliver the latest information intheir respective expertise areas. The conference has 2 Keynote Speakers, 1 PlenarySpeaker and 3 Technical Sessions. It will be a golden opportunity for the students,researchers and engineers to interact with the experts and specialists to get their advice orconsultation on technical matters, sales and marketing strategies.

Information of conference paper

Title:Intelligent Fault Diagnosis ofSatellite CommunicationAntenna via a Novel Meta-learning Network Combining with Attention Mechanism

Author:Yuanhong Chang, Jinglong Chen, Shuilong He

Abstract:Shipborne satellite communication antenna which is used for remote control plays an irreplaceable role in ships, it is necessary to monitor its operation state. However, obtaining sufficient fault information in mass monitoring data is particularly difficult, which greatly degrades performance of existing intelligent algorithms. In this paper, a novel meta-learning network is proposed to realize state recognition of shipborne antenna under small samples prerequisite. The network is constructed to improve generalization even though inputs collected under different operating conditions. Meta-learning network consists of sampler, feature extractor, auxiliary classifier and discriminator. It trains an adaptive pseudo-distance to evaluate the degree of correlation between different data, then realize classification task. Feasibility and effectiveness of the network are verified by three bearing datasets. Results show that the proposed method uses few samples to successfully classify mechanical data of shipborne antenna even with different rotating speed and random noise.