A novel performance monitoring and online modeling method to deal with a non-Gaussian chemical process with multiple operating conditions is proposed. On the basis of the framework of the proposed method, a kernel extreme learning machine (ELM) technique is used to efficiently extract features from high dimensional process data. Additionally, the Fastfood kernel is introduced into kernel ELM to accelerate computation efficiency, which is relatively low at the prediction time. Then, a modified just-in-time learning (JITL) technique is applied for Online modeling. In JITL, a novel similarity index; called modified adjusted cosine similarity (MACS), is proposed so as to improve the prediction performance of online modeling. The proposed paradigm provides an efficient, accurate, and fast approach to. monitor and model the multimode chemical process. The validity and effectiveness are evaluated by applying the method to a synthetic non-Gaussian multimode model and the distillation system.