To overcome the problem that soft sensor models cannot be updated with the process changes, a soft sensor modeling algorithm based on hybrid fuzzy c-means （FCM） algorithm and incremental support vector machines （I...To overcome the problem that soft sensor models cannot be updated with the process changes, a soft sensor modeling algorithm based on hybrid fuzzy c-means （FCM） algorithm and incremental support vector machines （ISVM） is proposed. This hybrid algorithm FCMISVM includes three parts： samples clustering based on FCM algorithm, learning algorithm based on ISVM, and heuristic sample displacement method. In the training process, the training samples are first clustered by the FCM algorithm, and then by training each clustering with the SVM algorithm, a sub-model is built to each clustering. In the predicting process, when an incremental sample that represents new operation information is introduced in the model, the fuzzy membership function of the sample to each clustering is first computed by the FCM algorithm. Then, a corresponding SVM sub-model of the clustering with the largest fuzzy membership function is used to predict and perform incremental learning so the model can be updated on-line. An old sample chosen by heuristic sample displacement method is then discarded from the sub-model to control the size of the working set. The proposed method is applied to predict the p-xylene （PX） purity in the adsorption separation process. Simulation results indicate that the proposed method actually increases the model＇s adaptive abilities to various operation conditions and improves its generalization capability.展开更多
A force-based quadrilateral plate element( 4NQP13) for the analysis of the plate bending problems using large increment method( LIM) was proposed. The LIM, a force-based finite element method( FEM),has been successful...A force-based quadrilateral plate element( 4NQP13) for the analysis of the plate bending problems using large increment method( LIM) was proposed. The LIM, a force-based finite element method( FEM),has been successfully developed for the analysis of truss,beam,frame,and 2D continua problems. In these analyses,LIMcan provide more precise stress results and less computational time consumption compared with displacement-based FEM. The plate element was based on the Mindlin-Reissner plate theory which took into account the transverse shear effects.Numerical examples were presented to study its performance including accuracy and convergence behavior,and the results were compared with the results have been obtained from the displacementbased quadrilateral plate elements and the analytical solutions. The4NQP13 element can analyze the moderately thick plates and the thin plates using LIMand is free from spurious zero energy modes and free from shear locking for thin plate analysis.展开更多
Many displacement-based quadrilateral plate elements based on Mindlin-Reissner plate theory have been proposed to analyze the thin and moderately thick plate problems. However, numerical inaccuracies of some elements ...Many displacement-based quadrilateral plate elements based on Mindlin-Reissner plate theory have been proposed to analyze the thin and moderately thick plate problems. However, numerical inaccuracies of some elements appear since the presence of shear locking and spurious zero energy modes for thin plate problems. To overcome these shortcomings, we employ the large increment method(LIM) for the analyses of the plate bending problems, and propose a force-based 8-node quadrilateral plate(8NQP) element which is based on MindlinReissner plate theory and has no extra spurious zero energy mode. Several benchmark plate bending problems are presented to illustrate the accuracy and convergence of the plate element by comparing with the analytical solutions and displacement-based plate elements. The results show that the 8-node plate element produces fast convergence and accurate stress distributions in both the moderately thick and thin plate bending problems. The plate element is insensitive to mesh distortion and it can avoid the shear locking for thin plate analysis.展开更多
基金Supported by the National Natural Science Foundation of China （60421002） and priority supported financially by ＂the New Century 151 Talent Project＂ of Zhejiang Province.
文摘To overcome the problem that soft sensor models cannot be updated with the process changes, a soft sensor modeling algorithm based on hybrid fuzzy c-means （FCM） algorithm and incremental support vector machines （ISVM） is proposed. This hybrid algorithm FCMISVM includes three parts： samples clustering based on FCM algorithm, learning algorithm based on ISVM, and heuristic sample displacement method. In the training process, the training samples are first clustered by the FCM algorithm, and then by training each clustering with the SVM algorithm, a sub-model is built to each clustering. In the predicting process, when an incremental sample that represents new operation information is introduced in the model, the fuzzy membership function of the sample to each clustering is first computed by the FCM algorithm. Then, a corresponding SVM sub-model of the clustering with the largest fuzzy membership function is used to predict and perform incremental learning so the model can be updated on-line. An old sample chosen by heuristic sample displacement method is then discarded from the sub-model to control the size of the working set. The proposed method is applied to predict the p-xylene （PX） purity in the adsorption separation process. Simulation results indicate that the proposed method actually increases the model＇s adaptive abilities to various operation conditions and improves its generalization capability.
基金National Natural Science Foundation of China(No.10872128)
文摘A force-based quadrilateral plate element( 4NQP13) for the analysis of the plate bending problems using large increment method( LIM) was proposed. The LIM, a force-based finite element method( FEM),has been successfully developed for the analysis of truss,beam,frame,and 2D continua problems. In these analyses,LIMcan provide more precise stress results and less computational time consumption compared with displacement-based FEM. The plate element was based on the Mindlin-Reissner plate theory which took into account the transverse shear effects.Numerical examples were presented to study its performance including accuracy and convergence behavior,and the results were compared with the results have been obtained from the displacementbased quadrilateral plate elements and the analytical solutions. The4NQP13 element can analyze the moderately thick plates and the thin plates using LIMand is free from spurious zero energy modes and free from shear locking for thin plate analysis.
基金the National Natural Science Foundation of China(No.10872128)
文摘Many displacement-based quadrilateral plate elements based on Mindlin-Reissner plate theory have been proposed to analyze the thin and moderately thick plate problems. However, numerical inaccuracies of some elements appear since the presence of shear locking and spurious zero energy modes for thin plate problems. To overcome these shortcomings, we employ the large increment method(LIM) for the analyses of the plate bending problems, and propose a force-based 8-node quadrilateral plate(8NQP) element which is based on MindlinReissner plate theory and has no extra spurious zero energy mode. Several benchmark plate bending problems are presented to illustrate the accuracy and convergence of the plate element by comparing with the analytical solutions and displacement-based plate elements. The results show that the 8-node plate element produces fast convergence and accurate stress distributions in both the moderately thick and thin plate bending problems. The plate element is insensitive to mesh distortion and it can avoid the shear locking for thin plate analysis.
