基于改进差别矩阵属性约简的聚合釜粗糙集_神经网络故障诊断.pdfVIP

62 3 Vol62 No3 2011 3 CIESC Journal M arch 2011 - 1, 2 1 1 1 高淑芝 , 高宪文 , 王介生 , 费鹏程 1 2 ( , 110189; , 110142) : ; ; ; ; BP : P 183 : A : 0438- 1157 ( 2011) 03- 0759- 07 Rough set-neural network fault diagnosis of polymerization based on improved attribut e reduction algorithm of discernibility matrix 1 2 1 1 1 GAO Shuzhi GAO Xianwen WANG Jiesheng FEI Pengcheng 1 ( School of I nf ormation Science and E ngineering , N ortheastern Univ ersity , Sheny ang 110189, L iaoning , China; 2 College of I nf ormation Engineering , S heny ang University of Chemical T echnology , Sheny ang 110142, L iaoning , China) Abstract: Aiming at the rea-l time fault diagnosis and optimized monitoring requirements of the polymerizer of PVC production process, a real-time polymerizer fault diagnosis strategy was proposed based on rough set ( RS) theory with improved discernibility matrix and back propagation ( BP) neural network he improved discernibility matrix was adopted to reduce the attributes of rough set in order to reduce the input dimensionality of fault characteristics effectivelyFuzzy C-means clustering algorithm was used to discrete the continuous variables of the decision table hen Levenberg-Marquardt BP neural network was trained according to the reduced decision table in order to decide the configuration parameters of the proposed polymerizer fault diagnosis model hus the classific