| 1. |
- Barabadi, Abbas, et al.
(författare)
-
Maintainability analysis of equipment using point process models
- 2015
-
Ingår i: 2015 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM). - Piscataway, NJ : IEEE Communications Society. - 9781467380669 ; , s. 797-801
-
Konferensbidrag (refereegranskat)abstract
- The maintenance cost can be reduced significantly by applying the maintainability principle in the design and operation phase. An effective maintainability prediction can help the designer to improve performance and safety of equipment. The analysis of historical repair by an affective statistical approach provides essential information for decision-making regarding the planning of operation and maintenance activities of the plant. However, the literature on field repair data is quite scarce and they are not detailed. This paper will try to provide step by step guideline for field repair data using point process models by a case study.
|
|
| 2. |
- Block, J., et al.
(författare)
-
Optimal repair for repairable components during phaseout an aircraft fleet
- 2010
-
Ingår i: IEEE Aerospace Conference Proceedings. - Piscataway, NJ. - 9781424438877
-
Konferensbidrag (refereegranskat)abstract
- The successive removal of units from a group of systems during phasing out leads to a variable requirement for stock level of spare parts. Repairable units from phased out systems can be reused for the remaining functional systems in the group. Hence, the stock level of spare parts increases and the demand for spare parts decreases. This can lead to excessive stocking of spare parts and high maintenance costs for spare parts. This paper proposes a methodology to determine the optimum time to stop repair of repairable units to minimize the maintenance cost. It uses a Poisson Distribution based on NHPP (Non-Homogenous Poisson Process) to predict the available number of units, while fulfilling the demand for spare parts for the remaining systems. A concept, called Minimal Margin is introduced to formulate the problem and nonlinear programming is proposed to obtain the optimum solution. Finally, a numerical example is presented to demonstrate the approach
|
|
| 3. |
- Dandotiya, Rajiv, et al.
(författare)
-
Optimal maintenance decision for line reparable units (LRU’s) for an aircraft system — A conceptual approach
- 2008
-
Ingår i: Quarterly Journal of the Operational Research Society of India (OPSEARCH). - 0030-3887 .- 0975-0320. ; 45:3, s. 291-302
-
Tidskriftsartikel (refereegranskat)abstract
- Maintenance decisions concerning repair of the Line Replaceable Unit (LRU) of an aircraft fleet need to be considered carefully while deciding the phasing out of the fleet. This is important for achieving higher degree of cost effectiveness and fleet availability at desired level. Discard rate and phasing out period for an aircraft fleet are the critical parameters for determining optimum time to stop the maintenance of LRU. The economic value of remaining useful life of an aircraft fleet should be taken into consideration by salvaging the LRU at the end of the phasing out. The paper suggests a methodology to arrive the time that will minimize the total life cycle cost and provide us economic basis to withdraw the maintenance resources. A mathematical model has been developed for the discard rate of aircrafts based on failure rate, mission life and remaining useful life of the aircrafts in the fleet. This will assist in fulfilling the managing demand of LRU while phasing out of the aircraft fleet.
|
|
| 4. |
- Fuqing, Yuan, et al.
(författare)
-
A comparative study of artificial neural networks and support vector machine for fault diagnosis
- 2013
-
Ingår i: International Journal of Performability Engineering. - 0973-1318. ; 9:1, s. 49-60
-
Tidskriftsartikel (refereegranskat)abstract
- Fault detection is a crucial step in condition based maintenance requiring. The importance of fault diagnosis necessitates an efficient and effective failure pattern identification method. Artificial Neural Networks (ANN) and Support Vector Machines (SVM) emerging as prospective pattern recognition techniques in fault diagnosis have been showing its adaptability, flexibility and efficiency. Regardless of variants of the two techniques, this paper discusses the principle of the two techniques, and discusses their theoretical similarity and difference. Eventually using the commonest ANN, SVM, a case study is presented for fault diagnosis using a wide used bearing data. Their performances are compared in terms of accuracy, computational cost and stability
|
|
| 5. |
- Fuqing, Yuan, et al.
(författare)
-
A cost model for repairable system considering multi-failure type over finite time horizon
- 2011
-
Ingår i: International Journal of Performability Engineering. - 0973-1318. ; 7:2, s. 186-194
-
Tidskriftsartikel (refereegranskat)abstract
- In general, downtime of a system can be attributed due to multiple failure categories and repair costs for each failure categories can be different. Many of these failure types are repaired to a state which can be called as bad as old and such repair actions are termed as “minimal repair”. Many system or components are replaced after a certain number of such minimal repair actions. In this study, we intend to prove that if the system failure process can be described by NHPP (Non Homogenous Poisson Process), then each failure category can also be modelled by NHPP. Based on this, a cost model is developed by using the decomposition of the NHPP and renewal theory. Using the cost model, a model is developed to obtain the optimal number of minimum repair action every failure category. Since it is not possible to find any analytical solution, solution to the renewal function, an approximate approach is introduced to obtain numerical solution. Finally, a numerical example is presented to demonstrate the method.
|
|
| 6. |
- Fuqing, Yuan, et al.
(författare)
-
A general imperfect repair model considering time-dependent repair effectiveness
- 2012
-
Ingår i: IEEE Transactions on Reliability. - 0018-9529 .- 1558-1721. ; 61:1, s. 95-100
-
Tidskriftsartikel (refereegranskat)abstract
- Kijima I and Kijima II models are two important imperfect repair models in literature. These two models use one constant parameter to represent the degree of repair, which is called Repair Effectiveness (RE) in this paper. We developed a more general imperfect repair model by extending the constant RE to a time-dependent function based on the virtual age process, where the Kijima models are special cases of the new model. A simulation method is developed to estimate the cumulative number of failures for the new model, and a Bayesian inference method is proposed to select the best imperfect repair model. Finally, to demonstrate the new model, a numerical example is provided. From this example, the new model shows a more accurate mean and a narrower confidence interval than that of the Non-Homogeneous Poisson Processes, and Kijima I and Kijima II models.
|
|
| 7. |
- Fuqing, Yuan, et al.
(författare)
-
An adaptive multiple kernel method-based support vector machine used for classication
- 2013
-
Ingår i: International Journal of Condition Monitoring. - : British Institute of Non-Destructive Testing (BINDT). - 2047-6426. ; 3:1, s. 8-15
-
Tidskriftsartikel (refereegranskat)abstract
- Classification is an important technique used for condition monitoring. Extensive research has been carried out on classification and numerous techniques have been developed. The support vector machine (SVM) is one of these techniques; it has excellent classification capacity and is widely used. The effectiveness of the SVM depends on the selection of the kernel function, so to maximise performance this paper proposes using an adaptive multiple kernel SVM (AMK-SVM). Using AMK, many heterogeneous features, such as continuous, categorical, logical etc, can be merged. Instead of predefining the parameters of kernel functions as with other multiple kernel SVMs, this method can adapt its parameters to data automatically through kernel alignment. The paper offers two numerical examples: one with benchmarking data to test the feasibility and performance of the approach (for this case a two-layer neural network and two single kernel SVMs are applied to the same datasets to compare their performance with the AMK-SVM); the other example uses the AMK-SVM to discriminate a healthy bearing from a defective bearing
|
|
| 8. |
- Fuqing, Yuan, et al.
(författare)
-
Anomaly detection using support vector machines on overhead contact wire
- 2013
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- This paper describes an anomaly detection method on the Overhead Contact Wire (OCW) in electrified railway system. The fundamental basic of contact wire is described. Their mechanical property and thermal property are discussed. The principle of the current collection through the overhead wire is described in brief. Some classical mechanic dynamic models between the pantograph and overhead contact wire are presented. Concentrating on the anomaly detection using vertical acceleration signal, this paper proposes a support vector regression based method to detect the anomaly detection on the surface of the overhead contact wire. The Support Vector Regression (SVR) is used to model the dependency between vertical acceleration and the other factor such as uplift, train speed, height of the wire. Correlation is used to find the significant factors which influence the vertical acceleration. The SVR model is used to de-trend the vertical acceleration signal. The statistical model is proposed to find the anomaly points on the contact wire.
|
|
| 9. |
- Fuqing, Yuan, et al.
(författare)
-
Complex system reliability evaluation using support vector machine
- 2010
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Support Vector Machine (SVM) is a data mining technique that has been successfully used in classification problems, starting from a known training data set (TDS). In systems modeled as networks, SVM has been used to classify the state of a network as failed or operating and jointly combined in a Monte Carlo sampling approach to approximate the network reliability. The analytical expression of the binary function (failed/operating) produced by SVM is difficult to be understood, since it generally involves the evaluation of non-linear operators, which consider a subset of the TDS, called Support Vectors (SV) and sampled system states. In this paper a different approach is proposed to assess system reliability. Information about path and cut sets is obtained directly from SV, without considering the analytical expression of the binary function produced by SVM. From here the system reliability is approximated directly. Several examples illustrate the approach.
|
|
| 10. |
- Fuqing, Yuan, et al.
(författare)
-
Complex system reliability evaluation using support vector machine for incomplete data-set
- 2011
-
Ingår i: International Journal of Performability Engineering. - 0973-1318. ; 7:1, s. 32-42
-
Tidskriftsartikel (refereegranskat)abstract
- Support Vector Machine (SVM) is an artificial intelligence technique that has been successfully used in data classification problems, taking advantage of its learning capacity. In systems modelled as networks, SVM has been used to classify the state of a network as failed or operating to approximate the network reliability. Due to the lack of information, or high computational complexity, the complete analytical expression of system states may be impossible to obtain, that is to say, only incomplete data-set can be obtained. Using these incomplete data-sets, depending on amount of missed data-set, this paper proposes two different approaches named rough approximation method and simulation based method to evaluate system reliability. SVM is used to make the incomplete data-set complete. Simulation technique is also employed in the so called simulation based approximation method. Several examples are presented to illustrate the approaches.
|
|
