| With the development of science, the control of modern industrial production process is becoming increasingly complex. The system contains more nonlinear and uncertain. The traditional control method of establishing accurate model has been difficult to achieve the desired effect. The synthetic ammonia decarbornization process system is a complex, nonlinear and non-Gaussian system. The system still exist randomness, lagging and fuzzy. A complex industrial process control is researched in this paper. An effective way is given to solve the complex modeling and optimization.Neural network technology as an intelligent algorithm is better in the modeling, and it is used in the industrial applications. Particle filter algorithm overcomes gaussian distribution limitation of random variables which appear in nonlinear filtering problems. It gives a better solution to the strongly nonlinear system.The principle and algorithm of particle filter are introduced in detail, and the advantages that nonlinear problem is solved by the particle filter algorithm is analyzed in the paper. The development and learning of neural networks and the influence factors of the united soda and carbonation process are also introduced in the paper. The RBF neural network control method based on nonlinear particle filter algorithm is given. The RBF neural network is used to model and control the synthetic ammonia decarbornization production process, and then the nonlinear particle filter algorithm is used to optimize the weights of the RBF neural network.The particle filter and the RBF neural network are combined in the paper. The advantages of the two technologies are used. Nonlinear particle filter algorithm could be used to solve the system problem of nonlinear and non-Gaussian. The advantage of RBF neural network is that it can approximate any continuous function. Modeling and optimization. is researched in the carbonation process of the synthetic ammonia decarbornization production process. So a control method is gotten to be applied the industrial complex process. |