Multivariate Statistical Kernel PCA for Nonlinear Process Fault Diagnosis in Military Barracks

Luo, Kaiwen; Li, Shenglin; Deng, Ren; Zhong, Wei; Cai, Hui

doi:10.14257/ijhit.2016.9.1.17

Cited by 5 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fault diagnosis plays an important role in safe and stable operation of the machines, which was developed from the fault diagnosis of machine equipment by the aerospace industry during the industrial revolution. Fault diagnosis technique applies various theories, such as, reliability theory, information theory, systematology, and has been widely applied to multiple fields, for instance, military [1], [2], economics [3], [4], and medicine [5]- [8]. One of the problems that must be solved when fault diagnosis technology is applied to engineering practice is the robustness of fault diagnosis algorithm.…”

Section: Introductionmentioning

confidence: 99%

A New Fault Diagnosis Method Based on Attributes Weighted Neutrosophic Set

Gou

Zhong

2019

IEEE Access

View full text Add to dashboard Cite

Fault diagnosis is an extensively applied issue to monitor condition and diagnose fault for safe and stable operation of the machine, which started to develop during the industrial revolution and contains various theories and technologies. Due to the growing complexity of contributing factors of a fault and the correlation of fault attributes which are often interrelated, traditional fault diagnosis methods fail to handle with this complex condition. To solve this problem, a new fault diagnosis method based on attributes weighted neutrosophic set is proposed in this paper. In the proposed approach, a attributes weighted model is developed to obtain the weights of attributes by the fault information. For a sample whose fault type is unknown, the neutrosophic set generated from the fault sample data are aggregated via the single valued neutrosophic power weighted averaging (SVNPWA) operator with the obtained attributes weights, then, the fault diagnosis results could be determined by the defuzzification method of fused neutrosophic set. This proposed method have capacity to differentiate the individual impact of attributes and handle the uncertain problems in the process of fault diagnosis. Finally, an illustrative example was provided to demonstrate the reasonableness and effectiveness of the proposed method.

show abstract