Visually enhanced situation awareness for complex manufacturing facility monitoring in smart factories

With the widespread application of networked information-based technologies throughout industry manufacturing, modern manufacturing facilities give rise to unprecedented levels of process data generation. Data-rich manufacturing environments provide a broad stage on which advanced data analytics pla...

Full description

Saved in:
Bibliographic Details
Published inJournal of visual languages and computing Vol. 44; pp. 58 - 69
Main Authors Zhou, Fangfang, Lin, Xiaoru, Luo, Xiaobo, Zhao, Ying, Chen, Yi, Chen, Ning, Gui, Weihua
Format Journal Article
LanguageEnglish
Published Elsevier Ltd 01.02.2018
Subjects
Manufacturing industry
Roller Hearth Kiln
Situation awareness
Smart factory
Visual analytics
Situation awareness
Roller Hearth Kiln
Visual analytics
Smart factory
Manufacturing industry
Online AccessGet full text
ISSN1045-926X
1095-8533
DOI10.1016/j.jvlc.2017.11.004

Cover

More Information
Summary:With the widespread application of networked information-based technologies throughout industry manufacturing, modern manufacturing facilities give rise to unprecedented levels of process data generation. Data-rich manufacturing environments provide a broad stage on which advanced data analytics play leading roles in creating manufacturing intelligence to support operational efficiency and process innovation. In this paper, we introduce a process data analysis solution that integrates the technologies of situation awareness and visual analytics for the routine monitoring and troubleshooting of roller hearth kiln (RHK), a complex key manufacturing facility for lithium battery cathode materials. Guided by a set of detailed scenarios and requirement analyses, we first propose a qualitative and quantitative situation assessment model to generate the comprehensive description of RHK's operating situation. An informative visual analysis system then is designed and implemented to enhance the users’ abilities of situation perception and understanding for insightful anomaly root cause reasoning and efficient decision making. We conduct case studies and a user interview together with the managers and operators from manufacturing sites as system evaluation. The result demonstrates its effectiveness and prospects its possible inspiration for other similar scenarios about complex manufacturing facility monitoring in smart factories.
ISSN:1045-926X
1095-8533
DOI:10.1016/j.jvlc.2017.11.004