Just-in-time Kernel Classifier for Online Process Diagnosis
A novel just-in-time kernel modeling method is proposed to online fault detection and diagnosis for chemical processes.The model parameters can be suitably selected using a fast cross-validation strategy.For a query sample,an online kernel classifier is constructed adaptively in a just-in-time manner for mode identification,i.e.,fault detection and diagnosis,using the most relevant samples around it.The superiority of the proposed kernel classifier is demonstrated through a simulated chemical example,compared with the related method with fixed parameters.
fault detection and diagnosis mode identification kernel classifier just-in-time learning
Yi Liu Wenlu Chen
Institute of Process Equipment and Control Engineering,Zhejiang University of Technology Hangzhou,31 Jiangnan Institute of Computing Technology Wuxi,214083,China
国际会议
杭州
英文
1338-1341
2013-03-22（万方平台首次上网日期，不代表论文的发表时间）