ABSTRACT Today's competition in industry depends not just on lean manufacturing, but also on the ability to provide customers with accountable life-cycle support for sustainable value. To improve customer service responsiveness and aftermarket business efficiency, new service business model for enable products and systems to achieve near-zero unscheduled downtime has been adopted by many companies. This transformation necessitates the depolyment of smart prognsotics tools to predict and prevent possible failures before they occur. This paper introduces an innovative approach in using Watchdog AgentTM for machine degradation and failure prognostics. The methods of Watchdog AgentTM are developed to use multi-sensor information from product for performance degradation assessment and life prediction. Specially, the logistic regression (LR) method is introduced and applied to an elevator hoistway performance aseessment. The logistic regression model is designed for repeatable tracking of motor speed profile of elevator hoistway movement for on-line monitoring and prognostic purposes. Features such as acceleration time (interval from triggering elevator to reaching maximum speed), deceleration time (from maximum speed to elevator stop), as well as average maximum speed were used as inputs to Logistic Regression tool for performance assessment. The real application results show that the LR is a very promising methodology for machine degradation assessment.
[1]
Jun Ni,et al.
Time-Frequency Based Sensor Fusion in the Assessment and Monitoring of Machine Performance Degradation
,
2002
.
[2]
Jay Lee.
Measurement of machine performance degradation using a neural network model
,
1996
.
[3]
S. Czepiel,et al.
Maximum Likelihood Estimation of Logistic Regression Models : Theory and Implementation
,
2022
.
[4]
Jay Lee,et al.
Multisensor Process Performance Assessment Through Use of Autoregressive Modeling and Feature Maps
,
2003
.
[5]
K. E. Spezzaferro.
Applying logistic regression to maintenance data to establish inspection intervals
,
1996,
Proceedings of 1996 Annual Reliability and Maintainability Symposium.
[6]
Jay Lee,et al.
Machine performance monitoring and proactive maintenance in computer-integrated manufacturing: review and perspective
,
1995
.
[7]
Stephen J. Engel,et al.
Prognostics, the real issues involved with predicting life remaining
,
2000,
2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484).
[8]
Frank L. Greitzer,et al.
Development of a Framework for Predicting Life of Mechanical Systems: Life Extension Analysis and Prognostics (LEAP)
,
1999
.