Batch chemical industries have been attracting for safety engineers since they pose a number problem in behavior and operations. the reliability of a chemical reactor installed in a plant depends on the capability of the control/ supervision system to estimate its state and to identify, in time its operational malfunctions or failure modes. in this paper, fault daignosis in batch chemical process control system using intellient system is proposed. the artificial intellgence technologies that are associated with knowledge-based approaches and adopted for monitoring, control, and diagnosis in the process industries include expert systems, fuzzy logic, neural network, and support vector machine. as has been mentioned, a correct choice of reactor operating conditions does not totally protect the plant against a thermal runaway. so, apart from the off-line activities, which help to define safe operating conditions, also on-line prevention measures are necessary to detect any unexpected situation leading to runaway scenario. among others under the on-line safety measures, an early warning detection system is indispensable to detect and evalute unexpected dangerous situations, which may occur in batch reactors e.g., due to a failure of the cooling or strirring systems or to a human mistake. nowadays, the batch industries are seeking for the more real time, accurate, efficient and low-cost mrthod and application for supporting safety in their industries. the use of intelligent system mrthod (comparing between neural network and support vector machine) for fault diagnosis in chemical batch plant can be the best choice for the solutions. the solutions, which are recommended by the use of intelligent system, will support the operator in their activities to control, prevent, and mitigate the hazards.