Abstract: A control strategy based on real-coding adaptive genetic algorithm(AGA) was developed and applied to the optimal control of cobalt oxalate synthesis. Based on the least squares support vector machine with the dynamic mechanism model of the synthesis process, a hybrid modeling method of the distribution was used to predict the particle size distribution(PSD). On this basis, the objective function and constraints of the PSD optimization model were established. The real-coding AGA was developed to solve the optimization problem. Simulation results showed that the method proposed can achieve a higher yield. Therefore, the optimization of cobalt oxalate PSD is of great importance to the industrial production of cobalt oxalate and to promote the development of cemented carbide industry.