Judging the Normativity of PAF Based on TFN and NAN

作     者：李志强 鲍劲松 刘天元 王佳诚 LI Zhiqiang;BAO Jinsong;LIU Tianyuan;WANG Jiacheng

作者机构：College of Mechanical EngineeringDonglma UniversityShanghai 201600China 

出 版 物：《Journal of Shanghai Jiaotong university(Science)》 (上海交通大学学报（英文版）)

年 卷 期：2020年第25卷第5期

页      面：569-577页

核心收录：

学科分类：081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the National Natural Science Foundation of China(No.51475301) 

主　　题：producing action normativity sequential model attention mechanism deep learning 

摘      要：The normativity of workers actions during producing has a great impact on the quality of the products and the safety of the operation *** studies mainly focused on the normativity of each single producing action instead of considering the normativity of continuous producing actions,which is defined as producing action flow(PAF)in this paper,during operation *** this issue,a normativity judging method based on two-LSTM fusion network(TFN)and normativity-aware attention network(NAN)is ***,TFN is designed to detect and recognize the producing actions based on skeleton sequences of a worker during complete operation process,and PAF data in sequential form are *** is built to allocate difTerent levels of attention to each producing action within the sequence of *** by this means,an efficient normativity judging is *** combustor surface cleaning(CSC)process of rocket engine is taken as the experimental case,and the CSC-Action2D dataset is established for *** results show the high performance of TFN and *** the effectiveness of the proposed method for PAF normativity judging.