non-gaussianprocesses monitoring has recently caught much attentions in this area, with several methods successfully developed, such as non-parameter estimation,independent component analysis(ICA), support vector dat...
详细信息
non-gaussianprocesses monitoring has recently caught much attentions in this area, with several methods successfully developed, such as non-parameter estimation,independent component analysis(ICA), support vector data description(SVDD), and etc. However, most of current research works are under the assumption that the process is operated in a single mode. This paper proposed a novel method for monitoringmultimodenon-gaussianprocesses, which is based on bayesian inference. To improve the comprehension of the process for the operation engineer, a corresponding mode localization approach is also given. A case study on the Tennessee Eastman(TE) benchmark process shows the feasibility and efficiency of the proposed method.
暂无评论