Journal of Prognostics and Health Management

Journal Information
Published by: Carleton University, MacOdrum Library (10.22215)
Total articles ≅ 5
Filter:

Articles in this journal

Xin Wen, Guoliang Lu, Shaohua Yang, Jinyin Li, Peng Yan
Journal of Prognostics and Health Management, Volume 1, pp 9-26; https://doi.org/10.22215/jphm.v1i1.1330

Abstract:
The ability to achieve accurate and reliable lifetime prognostics is critical to predictive maintenance of nano/micro motion systems. However, techniques to accomplish this task have not been well studied. This paper presents a stiffness-based degradation model for lifetime monitoring of a considered nanopositioning stage. Based on the dynamic model of the stage, an analysis of the relationship between system stiffness, running time and failure lifetime is investigated. A failure lifetime prognostic model for the stage is formulated by means of a dynamic stiffness analysis. This methodology is evaluated with numerical simulation and verified based on our experimental setup. The results reveal that this model can be used to effectively predict the failure lifetime and the remaining life of the investigated stage, which suggests its promising potentials in real applications.
Linghui Meng, Michael Pecht, Jie Liu, Yuanhang Wang, Keqiang Cheng
Journal of Prognostics and Health Management, Volume 1, pp 64-85; https://doi.org/10.22215/jphm.v1i1.1349

Abstract:
IGBTs are used everywhere ranging from aerospace, to transportation systems to the grid but it’s the most fragile device in power electronics. So it’s very critical to evaluate the health state and take advanced and active maintenance measures to avoid the accidents. This paper develops a rule-based sub-safety recognition model using neural networks to evaluate the degradation degree of the IGBTs and determine the health state. The model was validated with two groups of experimental data.
Haoren Wang, Yixiang Huang, Liang Gong, Pengfei Ye, Chengliang Liu, Zhiyu Tao
Journal of Prognostics and Health Management, Volume 1, pp 86-107; https://doi.org/10.22215/jphm.v1i1.1660

Abstract:
A piston pump is one of the key components in a hydraulic system. Therefore, a failure may severely hurt the reliability of the hydraulic system and cause great loss. Currently, how to effectively evaluate the health condition of the piston pump remains an open problem. In this paper, a novel health assessment method based on an integration of Laplacian eigenmaps and random forests is proposed, which takes full advantage of both the fusion ability of correlated features enabled by the Laplacian eigenmaps and the optimized feature-selection ability provided by the random forest. The proposed method (LE-RF) is applied to piston pumps for validation. The results indicate that the Laplacian eigenmaps-random forest (LE-RF) technique can provide an effective tool for piston pump health condition assessment. Compare with other manifold methods, e.g., LLE and ISOMAP and classification method of KNN, the LE-RF method can achieve better and more accurate assessment results.
Xuyun Fu, Xingjie Zhou, Shisheng Zhong
Journal of Prognostics and Health Management, Volume 1, pp 27-41; https://doi.org/10.22215/jphm.v1i1.1336

Abstract:
Through consideration of problems that the influence of the aero-engine state before shop visit and the adopted maintenance work scope on its performance after shop visit is complex and the sample size is small, we propose a lazy support vector machine regression (LSVMR) model for aero-engine performance prediction after shop visit based on the ε-support vector machine regression (ε-SVMR) model. Unlike the ε-SVMR, the insensitive loss function in LSVMR depends on the distance between the training sample and the predicted sample. The proposed model not only makes full use of the information of the predicted sample, but also seeks the best tradeoff between the model complexity and the learning ability. In this article, we give the solving process of LSVMR and collect the actual aero-engine maintenance samples from an airline to validate it. By comparing the prediction accuracy among LSVMR, ε-SVMR and k-nearest neighbor algorithm (k-NN), we find that LSVMR has the best prediction accuracy and can be seen as an effective method for the aero-engine performance prediction after shop visit.
Lixiang Duan, Dejun Zhang, Zhuang Yuan
Journal of Prognostics and Health Management, Volume 1, pp 42-63; https://doi.org/10.22215/jphm.v1i1.1345

Abstract:
Centrifugal pump is an important kind of water injection equipment used to maintain reservoir pressure in oilfield development. The health condition evaluation of centrifugal pumps is helpful to improve the operation and maintenance level. Although Analytic Hierarchy Process (AHP) and fuzzy evaluation method are widely applied in health condition assessment, there are still some problems, such as the determination of weight is greatly influenced by subjective factors and the calculation is complicated. To solve the above problems, this paper puts forward a catastrophe theory evaluation model combining fuzzy mathematics for the evaluation of centrifugal pump. Firstly, the structure, common faults model and operation mechanism of centrifugal pump units were considered, a multi-level security evaluation index system was established; combined with fuzzy mathematics, the bottom indexes used to evaluate centrifugal pump unit was calculated by dimensionless method; and various indicators of the impact of centrifugal pump operation have been processed with standardization and normalization. Secondly, the total security membership value layer by layer was obtained by using the security membership value of the underlying index layer, recursive quantization. Finally, the health level of the centrifugal pump unit was obtained according to the scores obtained by the catastrophe progression. The method takes the advantage of avoiding the quantification of assessing indexes and the choice of parameter values. Thus, the results of this evaluation model are reliable, and the evaluation method is objective, accurate and has a high value in engineering.
Back to Top Top