0
research-article

Cloud-Based Parallel Machine Learning for Prognostics and Health Management: A Tool Wear Prediction Case Study

[+] Author and Article Information
Dazhong Wu

Department of Mechanical and Aerospace Engineering, University of Central Florida, Orlando, FL 32816, USA
dazhong.wu@ucf.edu

Connor Jennings

Department of Industrial and Manufacturing Engineering, Pennsylvania State University, University Park, PA 16802, USA
connor@psu.edu

Janis Terpenny

Department of Industrial and Manufacturing Engineering, Pennsylvania State University, University Park, PA 16802, USA
jpt5311@psu.edu

Soundar Kumara

Department of Industrial and Manufacturing Engineering, Pennsylvania State University, University Park, PA 16802, USA
skumara@psu.edu

Robert Gao

Department of Mechanical and Aerospace Engineering, Case Western Reserve University, Cleveland, OH 44106, USA
robert.gao@case.edu

1Corresponding author.

ASME doi:10.1115/1.4038002 History: Received May 30, 2017; Revised September 17, 2017

Abstract

The emergence of cloud computing, Industrial Internet of Things (IIoT), and new machine learning techniques over the past few years have shown the potential to advance manufacturing towards a higher degree of digitization, remote accessibility, and intelligence. While model-based prognostics and health management (PHM) techniques provide insight into the progression of faults in mechanical components, certain assumptions on the underlying physical mechanisms for fault development are required to develop the models. In situations where there is a lack of adequate prior knowledge of the underlying physics, data-driven methods have been increasingly investigated as a complementary approach to machinery prognostics and intelligent maintenance scheduling. However, data-driven methods typically require large volumes of training data to generate accurate predictive analytics. Consequently, computational efficiency remains a challenge, especially when large volumes of sensor-generated data need to be processed for real-time applications. This research investigates a random forest (RFs)-based algorithm for fault propagation prediction in manufacturing machines based on cloud computing and machine learning. Because the regression trees in RFs are de-correlated, the RF algorithm is parallelized using the MapReduce data processing scheme and implemented on a scalable cloud computing system with varying combinations of processors and memories. By parallelizing RFs with MapReduce on the cloud, a significant increase in the processing speed (14.7 times in terms of increase in training time) has been achieved, with a high prediction accuracy of tool wear (8 times in terms of reduction in mean squared error).

Copyright (c) 2017 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In