The coagulation process is one of the most important stages m water treatment plant, which involves many comlex physical and chemical phenomena. Moreover, coagulant dosing rate is non-linearly correlated to raw water characteristics such as turbidity, conductivity, PH, temperature, etc. As such, coagulation reaction is hard or even impossible to control satisfactorily by conventional methods. Based on neural network and rule models, an expert system for determining the optimum chemical dosage rate is developed and used m a water treatment work, and the results of actual runs show that in the condition of satisfying the demand of drinking water quality, the usage of coagulant is lowered.