Aiming at the problems of poor flow stability among the current rice whitening unit, low single machine efficiency, unbalanced whitening or excessive broken rice caused by overmilling, a rice whitening unit control system based on particle swarm optimization (PSO) optimized BP-PID control was proposed. Using the multi-machine collaborative optimization technology, the flow balance control by adjusting the ratio of the rice bran-removing powder and the matching operating parameters of the online rice whitening machine. The parameters of the PID controller was trained through the BP neural network, a mathematical model for the regulation of the rice whitening unit was established, and then PSO was introduced to optimize the performance of the BP neural network. The simulation test showed that the control system optimized by PSO had faster response speed, improved steady-state accuracy and good control effect.