To overcome the problem that soft sensor models cannot be updated with the process changes,a softsensor modeling algorithm based on hybrid fuzzy c-means(FCM)algorithm and incremental support vector ma-chines(ISVM)is proposed.This hybrid algorithm FCMISVM includes three parts:samples clustering based onFCM algorithm,learning algorithm based on ISVM,and heuristic sample displacement method.In the trainingprocess,the training samples are first clustered by the FCM algorithm,and then by training each clustering with theSVM algorithm,a sub-model is built to each clustering.In the predicting process,when an incremental sample thatrepresents new operation information is introduced in the model,the fuzzy membership function of the sample toeach clustering is first computed by the FCM algorithm.Then,a corresponding SVM sub-model of the clusteringwith the largest fuzzy membership function is used to predict and perform incremental learning so the model can beupdated on-line.An old sample chosen by heuristic sample displacement method is then discarded from thesub-model to control the size of the working set.The proposed method is applied to predict the p-xylene(PX)purityin the adsorption separation process.Simulation results indicate that the proposed method actually increases themodel’s adaptive abilities to various operation conditions and improves its generalization capability. To overcome the problem that soft sensor models can not be updated with the process changes, a soft sensor model based on hybrid fuzzy c-means (FCM) algorithm and incremental support vector ma-chines (ISVM) is proposed. This hybrid algorithm FCMISVM includes three parts: samples clustering based onFCM algorithm, learning algorithm based on ISVM, and heuristic sample displacement method.In the trainingprocess, the training samples are first clustered by the FCM algorithm, and then by training each clustering with theSVM 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 toeach clustering is first computed by the FCM algorithm. Chen, 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 beupdated 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) purityin the adsorption separation process. Simulation results indicate that the proposed method actually increases themodel’s adaptive abilities to various operation conditions and improves its generalization capability.