Prognosis of remaining bearing life using neural networks

Shao, Yi; Nezu, Kikuo

doi:10.1243/0959651001540582

Cited by 113 publications

(69 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Under these assumptions, it is easy to show Figure 2(a) illustrates the type of degradation signal this model is intended to represent. For additional information on this and other models typically used to model degradation, see Nelson (1990) and Shao and Nezu (2000).…”

Section: The Degradation Signal Modelmentioning

confidence: 99%

See 1 more Smart Citation

Residual-life distributions from component degradation signals: A Bayesian approach

et al. 2005

View full text Add to dashboard Cite

Real-time condition monitoring is becoming an important tool in maintenance decision-making. Condition monitoring is the process of collecting real-time sensor information from a functioning device in order to reason about the health of the device. To make effective use of condition information, it is useful to characterize a device degradation signal, a quantity computed from condition information that captures the current state of the device and provides information on how that condition is likely to evolve in the future. If properly modeled, the degradation signal can be used to compute a residual-life distribution for the device being monitored, which can then be used in decision models. In this work, we develop Bayesian updating methods that use real-time condition monitoring information to update the stochastic parameters of exponential degradation models. We use these degradation models to develop a closed-form residual-life distribution for the monitored device. Finally, we apply these degradation and residual-life models to degradation signals obtained through the accelerated testing of bearings.

show abstract

Section: The Degradation Signal Modelmentioning

confidence: 99%

“…Note that the functional form resembles an exponential. Indeed, exponential degradation models have been used for bearing degradation (Shao and Nezu, 2000). In the work that follows, we only use degradation data associated with this second phase.…”

Section: The Degradation Signals Of the Bearingsmentioning

confidence: 99%

Residual-life distributions from component degradation signals: A Bayesian approach

et al. 2005

View full text Add to dashboard Cite

show abstract

“…If is the continuous degradation signal at time then the exponential degradation signal can be described as depicted below (Nelson, 1990) (Shao and Nezu, 2000) (Gebraeel et al, 2005).…”

Section: Appendix B Questionnaire Resultsmentioning

confidence: 99%

Condition-Based Maintenance

Wessels¹

2010

Practical Reliability Engineering and Analysis for System Design and Life-Cycle Sustainment

View full text Add to dashboard Cite

This master thesis describes a research project conducted within the department of service development at Vanderlande Industries in Veghel. The objective of the thesis is to gain insights into the process of using condition monitoring data to determine an appropriate maintenance policy. A framework is developed for implementation of a condition-based maintenance program. Within this framework, the criteria for a unit to monitor, relevant aspects on the condition parameter to monitor, the available prognostic models, and the determination of an appropriate maintenance policy is discussed. Finally, the implementation of a condition-based maintenance program on a unit of Vanderlande Industries is evaluated. First of all, I would like to thank my supervisors of Eindhoven University of Technology. First, Alaa Elwany for his feedback and tips during our meetings within the first months of the research project. Furthermore, I would like to thank Geert-Jan van Houtum for providing guidance and for helping me to keep a structured overview on the problem. Also, I iv II Preface & AcknowledgementsThisthank Tarkan Tan for his ideas and contribution to the project.I would like to thank Vanderlande Industries for providing me with an interesting research topic, and for the opportunity to graduate within the company. Especially, I thank Erlend Hessel for supervising my daily activities at Vanderlande Industries. I enjoyed our weekly meetings in which we shared insights on the research focus, and during which I gained insights into the organizational ways of the company.I enjoyed the working environment at the service development department. Therefore, I would like to thank all my colleagues for the pleasant atmosphere at the company and for providing me with valuable information for my research.Special thanks goes out to Herman Rooijakkers, for providing me with a lot of valuable information and for spending the little time he had available on our meetings. I end these acknowledgements by thanking my parents for giving me the opportunities to explore my talents, and my friends for the memories on the good times outside the academic life that will never fade. Henk StadhoudersVeghel, 2011 v III Executive SummaryVanderlande Industries (VI) is an internationally operating company specialized in the design and implementation of automated material handling systems. The four business units of VI provide solutions for Distribution, Express Parcel & Postal, Baggage Handling, and Services. Although this research is focusing on Distribution-and Baggage Handling Systems, the results can be generalized internally across all business units, as well as externally outside the company boundaries.In order to increase the reliability and performance of systems, companies strive towards a pro-active maintenance strategy instead of using conventional preventive maintenance tactics and reactive fire-fighting techniques as typically used within industries. This enables a more efficient use of resources, time and money and will most importantl...

show abstract

“…In these time domain signals many feature parameters can be extracted for fault detection and diagnosis. In this study, RMS and kurtosis are selected to be the two inputs for monitoring gear healthy condition due to their combined stability and sensitivity in tracking condition changes [9]. The RMS of a vibration signal s is calculated by Equation 1.…”

Section: Feature Extractionmentioning

confidence: 99%