This paper presents a new condition monitoring method based on a latent process model. The method consists of three steps. First, a sensor signal is modeled by a latent process model that is a combination of a time-varying auto-regression model and a dynamic linear model, which decomposes the signal into several components, and each component represents a different part of the monitored system with different time-frequency behavior. Based on the latent process model, important features are extracted. Finally, using the generative topographic mapping, the selected features are mapped to a lower (two)-dimension space for classification. The proposed method is tested in condition monitoring of sheet metal stamping processes. A large number of experiments were conducted. In particular, two cases are presented in detail. From the testing results, it is found that the proposed method is able to detect various defects with a success rate around 98%. This result is significantly better than the conventional artificial neural network method. In addition, the new method is a self-organizing method and hence, little training is necessary. These advantages make the method very attractive for practical applications.
Skip Nav Destination
Article navigation
Technical Papers
Condition Monitoring Using a Latent Process Model with an Application to Sheet Metal Stamping Processes
Xiaoli Li, Professor,
Xiaoli Li, Professor
Institute of Electrical Engineering, Yanshan University, Qinhuangdao, China, D66004
Search for other works by this author on:
R. Du, Professor
R. Du, Professor
Department of Automation & Computer Aided Engineering, The Chinese University of Hong Kong, Hong Kong, China
Search for other works by this author on:
Xiaoli Li, Professor
Institute of Electrical Engineering, Yanshan University, Qinhuangdao, China, D66004
R. Du, Professor
Department of Automation & Computer Aided Engineering, The Chinese University of Hong Kong, Hong Kong, China
Contributed by the Manufacturing Engineering Division for publication in the JOURNAL OF MANUFACTURING SCIENCE AND ENGINEERING. Manuscript received May 7, 2003; revised June 14, 2004. Associate Editor: C. J. Li.
J. Manuf. Sci. Eng. May 2005, 127(2): 376-385 (10 pages)
Published Online: April 25, 2005
Article history
Received:
May 7, 2003
Revised:
June 14, 2004
Online:
April 25, 2005
Citation
Li, X., and Du, R. (April 25, 2005). "Condition Monitoring Using a Latent Process Model with an Application to Sheet Metal Stamping Processes ." ASME. J. Manuf. Sci. Eng. May 2005; 127(2): 376–385. https://doi.org/10.1115/1.1870015
Download citation file:
Get Email Alerts
Related Articles
Design and Testing of a Thin-Flexure Bistable Mechanism Suitable for Stamping From Metal Sheets
J. Mech. Des (July,2010)
Degradation Assessment and Fault Modes Classification Using Logistic Regression
J. Manuf. Sci. Eng (November,2005)
Empirical Model Decomposition Based Time-Frequency Analysis for the Effective Detection of Tool Breakage
J. Manuf. Sci. Eng (February,2006)
Quality and Inspection of Machining Operations: Tool Condition Monitoring
J. Manuf. Sci. Eng (August,2010)
Related Proceedings Papers
Related Chapters
Certification by Data Reports and Stamping
Power Boilers: A Guide to the Section I of the ASME Boiler and Pressure Vessel Code, Second Edition
Section VIII: Division 2—Alternative Rules
Companion Guide to the ASME Boiler & Pressure Vessel Code, Volume 2, Second Edition: Criteria and Commentary on Select Aspects of the Boiler & Pressure Vessel and Piping Codes
On-Line Cutting Tool Condition Monitoring in Turning Processes Using Artificial Intelligence and Vibration Signals
International Conference on Advanced Computer Theory and Engineering, 4th (ICACTE 2011)