An independent component analysis (ICA) mixture model based local dissimilarity method is proposed in this article for performance monitoring of multimode dynamic processes with non-Gaussian features in each operating mode. The normal benchmark set is assumed to be from different operating modes, each of which can be characterized by a localized ICA model. Thus, an ICA mixture model is developed with a number of non-Gaussian components that correspond to various operating modes in the normal benchmark set. Further, the Bayesian inference rules are adopted to determine the local operating modes that the monitored set belongs to and the ICA mixture model based dissimilarity index is derived to evaluate the non-Gaussian patterns of process data by comparing the localized IC subspaces between the benchmark and the monitored sets. Moreover, the process dynamics are taken into account by implementing sliding window strategy on the monitored data set. The proposed ICA mixture model based dissimilarity method is applied to monitor the performance of the Tennessee Eastman Chemical process with multiple operating modes and the fault detection results demonstrate the superiority of the proposed method over the conventional eigenvalue decomposition based and geometric angle based principal component analysis (PCA) mixture dissimilarity methods.