Researches On The High Temperature Seepage Heat Transfer Rule And The Temperature Prediction Model Of Cement Grate Cooler

Cement grate cooler is the key equipment when cooling the high temperature cement clinker and recycling heat in the cement production line.The heat transfer efficiency of grate cooler directly affects the clinker quality and the energy consumption of cement production.Thus,the researches on the gas-clinker heat transfer rule and the temperature prediction model of high temperature clinker layer have important theoretical significance and social value to grate cooler.For example,it can enhance the system stability,improve the efficiency of heat recovery,reduce the emissions,and lower energy consumption of clinker production.Aiming at the limited research on gas-clinker heat transfer at present,the paper build an unsteady high temperature seepage heat transfer model of grate cooler considering the thermal radiation effect between the high temperature clinker particles.Then the corresponding solving algorithm coupled turbulent flow is proposed to show the seepage heat transfer rule of high temperature cement clinker under non-uniform distribution of the clinker particle layer.On the basis of the mentioned above,a Double Parallel and Double Hidden Layers Fast Learning Machine is presented to build a hybrid temperature prediction model for grate cooler combined the high temperature seepage heat transfer mechanism with DDFLM.The specific researches work are as follows.Firstly,the seepage heat transfer mechanism of porous media is introduced into the heat transfer researches of cement clinker layer and the distribution of particle diameter and porosity inside of the clinker layer is given according to experiments.During the radiation heat transfer research of the clinker particle,the high temperature cement clinker particles can be regarded as the optically thick medium to deduce the heat transfer coefficients between the particles under the combination of heat conduction and thermal radiation.Based on nonlinear darcy's law and local thermal non-equilibrium theory,one-dimensional and two-dimensional unsteady high temperature seepage heat transfer model of grate cooler are built considering the effects of radiation heat transfer between the packing particles.Secondly,in allusion to the one-dimensional and two-dimensional model constructed,the finite difference method is used to discretize the solving region and the mathematical model respectively.Then the solving algorithm coupled turbulent flow in different dimensionalities are designed to accomplish the solving process of unsteady high temperature seepage heat transfer model of grate cooler.Meanwhile,the gas-clinker temperature distribution of the heterogeneous high temperature cement clinker is given and the correctness of the constructed model and the proposed algorithm is verified.Using numerical simulation,the effects of particle feature in clinker layer and operating parameter of grate cooler on the cooling process of heterogeneous high temperature cement clinker layer are studied to achieve the seepage heat transfer rule of heterogeneous high temperature cement clinker layer.Thirdly,in order to eliminate the error generated in the temperature prediction by unsteady high temperature seepage heat transfer model,the Double Parallel and Double Hidden Layers Fast Learning Machine is proposed based on the extreme learning machine.By the typical regression problems,the DDFLM neural network is tested to verify its effectiveness.Besides,the researches on the error identification of high temperature seepage heat transfer mechanism model are conducted according to DDFLM.Then it constructs a hybrid temperature prediction model for grate cooler combined the high temperature seepage heat transfer mechanism with DDFLM which takes DDFLM as the error estimator of high temperature seepage heat transfer mechanism model.Finally,using the actual production data of grate cooler and the cooling experiment platform of high temperature clinker accumulation body,the measuring points' temperature prediction experiment inside of grate cooler and the clinker's temperature prediction experiment under forced cooling air of high temperature clinker accumulation body are conducted respectively.The experiments verify that the direct prediction of measuring points' temperature inside of grate cooler and the clinker's temperature of clinker layer is feasible using the hybrid temperature prediction model combined the high temperature seepage heat transfer mechanism with DDFLM constructed above.