The Fault Diagnosis Model Established Based on RVM
This paper introduces the application of Relevance Vector Machine (RVM) in fault diagnosis. First, the theoretical contents of RVM including the algorithm characteristics, the derivation of mathematical models, the characteristics of kernel functions and multimode classification are introduced. Then, the multi-classification fault diagnosis model of building electrical system is established by using RVM. Finally, the experimental results show that the RVM model has good classification effect on small sample data.
KeywordsFault diagnosis Relevance vector machine Small sample data
The project was partially supported by “The Fundamental Research Funds for Beijing University of Civil Engineering and Architecture”, Beijing, China with the grant No. X18191.
- 1.An, Y., Wang, Y.H., Zhang, F.C.: Research on gas pressure regulator fault diagnosis based on deep confidence network (DBN) theory. CAC (2017). https://doi.org/10.1109/cac.2017.824344
- 2.Shen, Y., Ding, S.X., et al.: A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process. J. Process Control 22(22), 1567–1581 (2012)Google Scholar
- 5.Ando, S., Kato, M.: Criticism of the Desmarais method for kernel function computation. Trans. Jpn. Soc. Aeronaut. Space Sci. 31(93), 161–170 (1988)Google Scholar
- 6.Li, C., Sanchez, R.V., Zurita, G., et al.: Multimodal deep support vector classification with homologous features and its application to gearbox fault diagnosis. Neurocomputing 168(C), 119–127 (2015)Google Scholar