Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Using Text Analytics Solutions with Small to Medium Sized Manufacturers: Lessons Learned

Published

Author(s)

Michael P. Brundage, Radu Pavel

Abstract

As Smart Manufacturing becomes more prevalent throughout industry, manufacturers are continuing to look for ways to more efficiently apply advanced data analysis methods to improve their decision processes. One promising area for improving decision making is through the use of natural language processing (NLP) methods on text-based data in maintenance. Maintenance personnel often capture important information on the problems and repairs throughout the manufacturing facility in informal text. This information is key to improving maintenance decisions, such as scheduling, dispatching, diagnosis, and inventory management, but is difficult to access due to the informal and domain specific nature of the text. Methods are available to aid manufacturers with parsing through this information, however small-to-medium sized manufacturers (SMMs) still have issues in implementing NLP solutions in practice. To this end, this paper discusses lessons learned in applying a NIST developed methodology to SMMs maintenance data.
Proceedings Title
Proceedings of the 11th Model-Based Enterprise Summit
Conference Dates
March 30-April 3, 2020
Conference Location
Gaithersburg, MD
Conference Title
Model-Based Enterprise Summit

Keywords

maintenance, smart manufacturing, natural language processing

Citation

Brundage, M. and Pavel, R. (2020), Using Text Analytics Solutions with Small to Medium Sized Manufacturers: Lessons Learned, Proceedings of the 11th Model-Based Enterprise Summit, Gaithersburg, MD, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=930321 (Accessed April 17, 2024)
Created April 30, 2020, Updated May 15, 2020