Sintering Mixing System Grain Of Process Water Intelligent Control Strategy And Industrial Application

Sintering process is an important procedure of iron ore pretreatment in the iron and steel smelting process, and sinter, the production of sintering, which has a direct impact on the output and quality of steel, is a vital raw material for blast furnace. Mixing granulation is a very important sub process of sintering to improve the permeability of sinter bed and the stability for the sintering process. Due to the above situation, researching on the mixing granulation process control is an urgent matter for the steel manufacture process.The mixing granulation process is a very complex industrial process with the features of non-linear, some difficulty detected parameters, numerous interference factors. Based on the intensive analysis of the technological mechanism and control difficulties in the mixing granulation process, as well as the profound researching on the influencing factors, the moisture intelligent optimal control strategy for the mixing granulation process is proposed by using the fuzzy comprehensive evaluation and intelligent optimal control theory.At first, to deal with the problem that mixture size distribution is difficult to detected, the fuzzy comprehensive evaluation model is established based on the thought of analytic hierarchy process and fuzzy logic. Then, according to value of mixture size distribution and its fuzzy evaluation, the size distribution relation model is built by applying the neural network method. In order to obtain the best mixture size distribution, the particle swarm optimization algorithm is used to optimize the relation model. For the purpose of receiving reasonable and effective moisture set value, another neural network relation model which related to the mixture size distribution, moisture and weight is set up, and according to the best mixture size distribution and the current weight, the optimal set value of moisture is got. After that, with considering various factors, such as the raw material weight, the rate of flow, and the original moisture content of each brand of iron ore, the raw material conditions-adaptive based feedforward calculation model for watering is established by using the expert rules and material balance principle. Based on this model, the moisture cascade control system with adaptive Fuzzy-PID algorithm is developed, in order to stabilize the moisture content of mixture.Simulations validate the effectiveness of the modeling strategy proposed in this paper. Meanwhile, in order to verify its value of practical application, moisture feedforward-casecade intelligent control system is developed in a domestic iron and steel enterprise. The operational effect shows that the system not only sufficiently suppresses the fluctuation brought by raw material flow, but also improves the control accuracy, at the same time, reduces the labor intensity, and benefits the stable for the sintering process.