| The steel tapping operation with high temperature is often performed by many domestic steel plants in order to keep the continuous casting operation in order. This kind of operation not only easily results in the accident of leaking steel, but also would increase the hot burthen of the furnace and the production cost, lower the life of the furnace lining. It becomes a very urgent problem to establish a reasonable temperature system and accurately control molten steel temperature. It is an important premise to predict accurately the end temperature of molten steel in LF for organizing production, improving steel quality, cutting down cost and controlling the steel water temperature.The model of pridicting molten steel terminal temperature in LF was established by using the artificial intelligence technique aimed at the production technique of 300t LF in the first steel mill of Shanghai Baoshan Iron & Steel Corporation. A hybrid algorithm was included which uses genetic algorithm to accelerate the BP neural network. GA-BP hybrid network was built up by using global optimizing abilities of genetic algorithm and local searching abilities of BP neural network. The problem of local minimum was avoided and the convergence speed was quickened by the algorithm which combined Genetic Algorithms with improved BP network. The factors of influencing molten steel temperature of LF were deeply investigated during building up the model of GA-BP network. See the whole steel the system as a system considering of the energy balance. Therefore, the factors used in model were confirmed as follows: the supplying power to heat molten steel, initial temperature, ladle states, absorbing and emanating heat of metal alloy and slag, argon blowing quantity and soaks time.The model was simulated and the network parameter was optimized by using the MATLAB toolbox. The GA-BP network was compared with standard BP network and improved BP network. The GA-BP program was developed by C++. The system...
|
PDF Full Text Request