Abstract-Fault detection and fault diagnosis have become increasingly important for improvement of the reliability, safety and efficiency of many technical processes. In this research, a new robust fault detection and isolation (FDI) scheme is developed for open-loop Chylla-Haase polymerization reactor. This reactor has been widely used as an industrial Benchmark. The independent Radial Basis Function (RBF) Neural Network (RBFNN) is employed here for on-line diagnosis of faults on the actuator, sensors, and reactor components when the system is subjected to system uncertainties and disturbances. Two different techniques to employ RBF neural networks are investigated. Firstly, an independent neural network is used to model the reactor dynamics and generate residuals. Secondly, an additional RBF neural network is developed as a classifier to isolate faults from the generated residuals. Three sensor faults and one actuator fault are simulated on the Chylla-Haase reactor. Moreover, many practical disturbances and system uncertainties, such as monomer feed rate, fouling factor, impurity factor, ambient temperature and measurement noise are modelled. The simulation results are presented to illustrate the effectiveness and robustness of the proposed method.