ABSTRACT
This paper uses fault injection to simulate the degradation state of each module of P2020. Based on the time-domain data of the sensitivity parameters of each module under normal and fault injection conditions, a health and effectiveness evaluation method for general aviation processing system based on parameter feature analysis isproposed. Firstly, feature extraction, feature selection and principal component analysis are used to form a sample set of health assessment parameters for each module of P2020 system. Then, mahalanobis distance is used to evaluate the health status of each key module and calculate the health degree. Finally, the system effectiveness of P2020 is obtained by AHP (The analytic hierarchy process) and ADC model. The analysis of test data shows that this method has high accuracy and accuracy for health and effectiveness evaluation of general aviation processing system.
- Tsui K L, Chen N, Zhou Q, et al. Prognostics and Health Management: A Review onData Driven Approaches{J}. Mathematical Problems in Engineering, 2015,(2015-5-19), 2015, 2015(6):1--17.Google Scholar
- Vichare N M, Pecht M G. Prognostics and health management of electronics{J}. IEEE Transactions on Components & Packaging Technologies, 2006, 29(1):222--229.Google ScholarCross Ref
- Lee J, Wu F, Zhao W, et al. Prognostics and health management design for rotary machinery systems-Reviews, methodology and applications{J}. Mechanical Systems & Signal Processing, 2014, 42(1--2):314--334.Google ScholarCross Ref
- Xiang S, Nie F, Zhang C. Learning a Mahalanobis distance metric for data clustering and classification{J}. Pattern Recognition, 2008, 41(12):3600--3612. Google ScholarDigital Library
- Srinivasaraghavan J, Allada V. Application of mahalanobis distance as a lean assessment metric{J}. International Journal of Advanced Manufacturing Technology, 2006, 29(11--12):1159--1168.Google ScholarCross Ref
- Kumar S, Chow T W S, Pecht M. Approach to Fault Identification for Electronic Products Using MahalanobisDistance{J}. IEEE Transactions on Instrumentation & Measurement, 2010, 59(8):2055--2064.Google ScholarCross Ref
- Li Tongyan, Wang Peiguo, Zhang Ting. Effectiveness evaluation method based on ADC model in communicationnetworks{J}.Application of Electronic Technique, 2015, 41(9):18--20, 28.Google Scholar
Index Terms
- Health and Effectiveness Assessment of Aeronautical General Processing System Based on Feature Analysis of State Parameters
Recommendations
cFEM: a cluster based feature extraction method for network intrusion detection
AbstractThe recent trend in network intrusion detection leverages key features of machine learning (ML) algorithms to detect network traffic anomalies. Network traffic flows contain high dimensional features which significantly affect data-driven ...
Transforming supervised classifiers for feature extraction
ICTAI '00: Proceedings of the 12th IEEE International Conference on Tools with Artificial IntelligenceAbstract: Supervised feature extraction is used in data classification and (unlike unsupervised feature extraction) it uses class labels to evaluate the quality of the extracted features. It can be computationally inefficient to perform exhaustive ...
Nonnegative Matrix Factorization (NMF) Based Supervised Feature Selection and Adaptation
IDEAL '08: Proceedings of the 9th International Conference on Intelligent Data Engineering and Automated LearningWe proposed a novel algorithm of supervised feature selection and adaptation for enhancing the classification accuracy of unsupervised Nonnegative Matrix Factorization (NMF) feature extraction algorithm. At first the algorithm extracts feature vectors ...
Comments