Sensor Data based Models for Workforce Management in Smart Manufacturing

Abstract

Manufacturers conduct frequent product innovations to maintain their competence in the market. Accordingly, their workers need to upgrade skills and regain work efficiency in ever-changing manufacturing systems. Training and assisting workers on their job serve this purpose. Yet, their effectiveness relies on an understanding of workers' needs, their operational behavior, performance, and sometimes the prediction of these. This paper aims to discover the unique capability of workforce management in smart manufacturing (SM) where advanced sensor technologies and machine learning techniques are commonly implemented. The paper summarizes technologies for sensing workers in their workplace. Then, it shows that the sensed temporal-spatial data of workforce, after being processed, can be used to infer and model substantial worker information such as location, configuration, motion, and action. Provided these models, SM is able to assist and train manufacturing workforce in a precise and proactive manner. The paper demonstrates the implementation of the proposed models with a practical manufacturing operation. It also summarizes management implications of the models.

Department(s)

Mechanical and Aerospace Engineering

Comments

National Science Foundation, Grant CMMI-1646162

Keywords and Phrases

Performance measurement; Smart manufacturing; Temporal-spatial data; Worker activities; Workforce management

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2024 Curran Associates Inc., All rights reserved.

Publication Date

01 Jan 2018

This document is currently not available here.

Share

 
COinS