Prognostic Enhancements to Diagnostic Systems for Improved Condition-Based Maintenance

Byington, Carl S.; Roemer, Michael; Kacprzynski, Gregory J.; Galie, Thomas R.

doi:10.21236/ada408880

Cited by 102 publications

(77 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…One of the widely-used probability distributions in reliability to model fatigue and wear-out phenomena is the normal distribution, as illustrated by the works of Tuomas et al (2001), Byington et al (2002), Batchoun et al (2003), Deshpande et al (2006), Muchiri andSmit (2011), andKiyak (2012). If we assume that f(x) is normally distributed, with a mean m x and standard deviation s x , the formula for the PDF is.…”

Section: Numerical and Iteration Methodsmentioning

confidence: 99%

Efficient aircraft spare parts inventory management under demand uncertainty

Zhang

2015

Journal of Air Transport Management

View full text Add to dashboard Cite

a b s t r a c tIn airline industries, the aircraft maintenance cost takes up about 13% of the total operating cost. It can be reduced by a good planning. Spare parts inventories exist to serve the maintenance planning. Compared with commonly used reorder point system (ROP) and forecasting methods which only consider historical data, this paper presents two non-linear programming models which predict impending demands based on installed parts failure distribution. The optimal order time and order quantity can be found by minimizing total cost. The first basic mathematical model assumes shortage period starts from mean time to failure (MTTF). An iteration method and GAMS are used to solve this model. The second improved mathematical model takes into account accurate shortage time. Due to its complexity, only GAMS is applied in solution methodology. Both models can be proved effective in cost reduction through revised numerical examples and their results. Comparisons of the two models are also discussed.

show abstract

Section: Numerical and Iteration Methodsmentioning

confidence: 99%

Efficient aircraft spare parts inventory management under demand uncertainty

Zhang

2015

Journal of Air Transport Management

View full text Add to dashboard Cite

show abstract

“…Various prognostic approaches have been developed ranging in fidelity from simple historical failure rate models to high-fidelity physics-based models [10]. These methods can be associated with one of the following two approaches, namely model based (or Physics-based) and data driven [23].…”

Section: Prediction/forecasting Approaches Overviewmentioning

confidence: 99%

“…A central problem can be pointed out as follows: the accuracy of a prognostic system is related to its ability to approximate and predict the degradation of the equipment: starting from a ''current situation,'' a prognostic tool must be able to forecast the ''future possible situations.'' From the research point of view, many developments exist to support these prognostic or forecasting activities [10,16,25,50]. However, choosing an efficient technique depends on classical constraints that limit the applicability of the tools: available data-knowledge-experiences, dynamic and complexity of the system, implementation requirements (precision, computation time, etc.…”

Section: Introductionmentioning

confidence: 99%

Autonomous and adaptive procedure for cumulative failure prediction

Zemouri

Zerhouni²

2011

Neural Comput & Applic

View full text Add to dashboard Cite

An autonomous adaptive reliability prediction model using evolutionary connectionist approach based on Recurrent Radial Basis Function architecture is proposed. Based on the currently available failure time data, Fuzzy Min-Max algorithm is used to globally optimize the number of the k Gaussian nodes. This technique allows determining and initializing the k-centers of the neural network architecture in an iterative way. The user does not have to define arbitrary some parameters. The optimized neural network architecture is then iteratively and dynamically reconfigured as new failure occurs. The performance of the proposed approach has been tested using sixteen real-time software failure data.

show abstract

“…Thus, two problems are solved, namely filtering of false alarms, and reduction in size of fault isolation ambiguity related to the occurrence of a failure. In [2], authors propose an effective way for diagnosing discreteevent systems using a timed-automaton with application to the aeronautic field. A dynamic model with temporal transitions is proposed to model the system.…”

Section: Introductionmentioning

confidence: 99%