The Gas Predicting And Optimal Scheduling Modeling For Steel Enterprise

In2012, the energy consumption of China’s iron and steel industry accounts forabout16%of the country’s total energy consumption. In the large steel companies,energy costs about30%of its total production cost, while the by-product gases canprovide the production of1/3of the energy consumption. In the process of steel making,it gives off a large amount of by-product gases (blast furnace gas, coke gas and convertergas). These gases are not only an important secondary energy, but also a mainatmospheric pollution sources. If they are not effectively collected and used, it will leadto the waste of energy, the pollution of atmosphere.The forecast of energy resources is the basis of energy optimization scheduling. Theconsumption of energy prediction based on the production plan can grasp the dynamicneeds of the various energy sources opportunely. The production forecast based onenergy consumption, can determine whether there are mistakes in the production andoperation process, then we can detect and maintain the equipment, or correct theoperation timely. The article uses BP neural network based on historical data to forecastthe energy in production and consumption process. The forecast results will providedecision support to optimize the scheduling.In the article the gas system is divided into two categories abstractly: gas pipelinenetwork and production unit. The network structure of the gas pipeline network isexpressed in matrix form; establish an optimization model based scheduling unitclassification. According to the specific characteristics of scheduling unit, the productionunits are divided into four categories. The gas flow prediction model was establishedfinally. Comparing the difference between the predicted results and the actual gasmeasuring data, Using least squares regression and partial least squares regression theoryto establish the gas optimization scheduling model.