Coke Oven Flue Temperature Soft Measurement Model And Its Application Research

As one of the critical technical parameters in the course of the coke oven heating combustion, the coke oven flow temperature is tightly connected with the output and quality of the product, as well as the life-span of the oven. The high temperature makes it most cost and consuming for the thermocouple to detect the oven flow. And that has been a difficult problem standing in the way of many coke engineers.In the view of technical mechanism, this paper analyzed several factors associated with coke oven flow temperature including the temperature in the regenerator, the reverse operation of the coal gas, the operation of coke pushing, the percentage of water in the coal, the coal gas type and heat quality, the gas flowing flux and the weather, etc. Following a kind of soft sensor model was put forward, which can be divided into two sorts sub-model, linear regress model and neural network model. The temperature at the top of the regenerator and the water percentage in coal were selected as the second variables, and the flow temperature of double sides of the oven were predicted by the sub-models. In order to improve the precision of the model, the paper constructs the rules library based on the experts' experiences. And the sub-models are integrated with the fuzzy combination and artificial intelligence technology. The simulation results shows that the method is valid and feasible.The industrial application of the soft sensor model was also discussed in this paper. The model was implemented with the C++ language and the block programming. The application software communicated with the configure software with help of the OPC technology. The model worked efficiently in the plant and benefited great to the heating combustion system.