The copper flash smelting process neural network model(CFSPNNM)was developed,its input layer includes eight nodes:oxygen grade(OG),oxygen volume per ton of concentrate(OVPTC),flux rate(FR)and quantifies of Cu,S,Fe,SiO...The copper flash smelting process neural network model(CFSPNNM)was developed,its input layer includes eight nodes:oxygen grade(OG),oxygen volume per ton of concentrate(OVPTC),flux rate(FR)and quantifies of Cu,S,Fe,SiO_2 and MgO in copper concentrate;output layer includes three nodes:matte grade,matte temperature and Fe/SiO_2 in slag,and net structure was 8-13-10-3.Then,the internal relationship between the technological parameters and the objective parameters was built after the CFSPNNM was trained by us...展开更多
A mathematical model of multistage and multiphase reactions in flash smelting furnace, which based on the description of chemical reactions and reaction rate, is presented. In this model, main components of copper con...A mathematical model of multistage and multiphase reactions in flash smelting furnace, which based on the description of chemical reactions and reaction rate, is presented. In this model, main components of copper concentrate are represented as FeS 2 and CuFeS based on experiment, intermediate products are assumed to be S 2 and FeS, and the final products are assumed as FeS, FeO, SO 2, Cu 2S, FeO and FeO(SiO 2) 2. The model incorporates the transport of momentum, heat and mass, reaction kinetics between gas and particles, and reactions between gas and gas. The k-ε model is used to describe gas phase turbulence. The model uses the Eulerian approach for the gas flow equations and the Lagrangian approach for the particles. The coupling of gas and particle equations is performed through the particle source in cell(PSIC) method. Comparison between the model predictions and the plant measurements shows that the model has high reliability and accuracy.展开更多
Fluid flow, heat transfer and combustion in Jinlong CJD concentrate burnerflash smelting furnace have been investigated by numerical modeling and flow visualization. Themodeling is based on the Eulerian approach for t...Fluid flow, heat transfer and combustion in Jinlong CJD concentrate burnerflash smelting furnace have been investigated by numerical modeling and flow visualization. Themodeling is based on the Eulerian approach for the gas flow equations and the Lagrangian approachfor the particles. Interaction between the gas phase and particle phase, such as frictional forces,heat and mass transfer, are included by the addition of sources and sinks. The modeling resultsincluding the fluid flow field, temperature field, concentration field of gas phase and thetrajectories of particles have been obtained. The predicted results are in good agreement with thedata obtained from a series of experiments and tests in the Jinlong Copper Smelter and thetemperature error is less than 20 K.展开更多
A kind of 3D color graphics display system for the STL model is developed by calling the functions from Open GL graphic library through VC++6.0 under the Windows environment in this paper. The STL model is a high qual...A kind of 3D color graphics display system for the STL model is developed by calling the functions from Open GL graphic library through VC++6.0 under the Windows environment in this paper. The STL model is a high quality one that can be quiescent or animated. This system is conducive to find out the disfigurement of the STL model in a rapid prototyping process and to repair it. Therefore, the component quality can be enhanced.展开更多
Due to the importance of detecting the matte grade in the copper flash smelting process, the mechanism model was established according to the multi-phase and multi-component mathematic model. Meanwhile this procedure ...Due to the importance of detecting the matte grade in the copper flash smelting process, the mechanism model was established according to the multi-phase and multi-component mathematic model. Meanwhile this procedure was a complicated production process with characteristics of large time delay, nonlinearity and so on. A fuzzy neural network model was set up through a great deal of production data. Besides a novel constrained gradient descent algorithm used to update the parameters was put forward to improve the parameters learning efficiency. Ultimately the self-adaptive combination technology was adopted to paralleled integrate two models in order to obtain the prediction model of the matte grade. Industrial data validation shows that the intelligently integrated model is more precise than a single model. It can not only predict the matte grade exactly but also provide optimal control of the copper flash smelting process with potent guidance.展开更多
山洪是全球范围内最危险的自然灾害之一,具有突发性强、成灾快和破坏力大并且难以短时临近预测的特点。传统山洪预报预警方法主要依赖于基于物理机制的水文-水动力山洪过程模拟,然而这种方法计算复杂耗时较长,难以满足山洪的短时临近预...山洪是全球范围内最危险的自然灾害之一,具有突发性强、成灾快和破坏力大并且难以短时临近预测的特点。传统山洪预报预警方法主要依赖于基于物理机制的水文-水动力山洪过程模拟,然而这种方法计算复杂耗时较长,难以满足山洪的短时临近预测需求。以浙江临安仁里村为例,在水文-水动力物理模拟所产生的8378条降雨时序和对应山洪淹没时空序列数据集的基础上,以基于卷积门控循环单元(convolutional gated recurrent unit convGRU)的深度神经网络作为核心,构建山洪时空序列预测代理模型。该模型通过输入过去24小时降雨观测时序和未来6小时的降雨预报时序,可实现未来6小时山洪淹没时空演变过程的快速预测。代理模型在测试集中能可靠地预测未来逐小时的山洪淹没范围、最大淹没深度以及淹没位置,未来6小时预测的可决系数均值为0.96,且预测速度平均比物理模拟快15625倍。这表明该代理模型能够捕捉物理模拟中降雨到山洪的复杂映射关系,实现目标区域山洪的快速预测,为山洪预警及应急响应决策制定提供有力的模型基础。展开更多
基金Key Industrial Technology Development Project of China (No.20051255)National Natural Science Foundation of China (No.50364004)+1 种基金Scientific and Technological Project of Jiangxi Province (No.20061B0101100)Natural Science Foundation of Jiangxi Province (No.2007GZC0713)
文摘The copper flash smelting process neural network model(CFSPNNM)was developed,its input layer includes eight nodes:oxygen grade(OG),oxygen volume per ton of concentrate(OVPTC),flux rate(FR)and quantifies of Cu,S,Fe,SiO_2 and MgO in copper concentrate;output layer includes three nodes:matte grade,matte temperature and Fe/SiO_2 in slag,and net structure was 8-13-10-3.Then,the internal relationship between the technological parameters and the objective parameters was built after the CFSPNNM was trained by us...
文摘A mathematical model of multistage and multiphase reactions in flash smelting furnace, which based on the description of chemical reactions and reaction rate, is presented. In this model, main components of copper concentrate are represented as FeS 2 and CuFeS based on experiment, intermediate products are assumed to be S 2 and FeS, and the final products are assumed as FeS, FeO, SO 2, Cu 2S, FeO and FeO(SiO 2) 2. The model incorporates the transport of momentum, heat and mass, reaction kinetics between gas and particles, and reactions between gas and gas. The k-ε model is used to describe gas phase turbulence. The model uses the Eulerian approach for the gas flow equations and the Lagrangian approach for the particles. The coupling of gas and particle equations is performed through the particle source in cell(PSIC) method. Comparison between the model predictions and the plant measurements shows that the model has high reliability and accuracy.
文摘Fluid flow, heat transfer and combustion in Jinlong CJD concentrate burnerflash smelting furnace have been investigated by numerical modeling and flow visualization. Themodeling is based on the Eulerian approach for the gas flow equations and the Lagrangian approachfor the particles. Interaction between the gas phase and particle phase, such as frictional forces,heat and mass transfer, are included by the addition of sources and sinks. The modeling resultsincluding the fluid flow field, temperature field, concentration field of gas phase and thetrajectories of particles have been obtained. The predicted results are in good agreement with thedata obtained from a series of experiments and tests in the Jinlong Copper Smelter and thetemperature error is less than 20 K.
文摘A kind of 3D color graphics display system for the STL model is developed by calling the functions from Open GL graphic library through VC++6.0 under the Windows environment in this paper. The STL model is a high quality one that can be quiescent or animated. This system is conducive to find out the disfigurement of the STL model in a rapid prototyping process and to repair it. Therefore, the component quality can be enhanced.
基金Project(60634020) supported by the National Natural Science Foundation of ChinaProject(2002CB312200) supported by the National Basic Research and Development Program of China
文摘Due to the importance of detecting the matte grade in the copper flash smelting process, the mechanism model was established according to the multi-phase and multi-component mathematic model. Meanwhile this procedure was a complicated production process with characteristics of large time delay, nonlinearity and so on. A fuzzy neural network model was set up through a great deal of production data. Besides a novel constrained gradient descent algorithm used to update the parameters was put forward to improve the parameters learning efficiency. Ultimately the self-adaptive combination technology was adopted to paralleled integrate two models in order to obtain the prediction model of the matte grade. Industrial data validation shows that the intelligently integrated model is more precise than a single model. It can not only predict the matte grade exactly but also provide optimal control of the copper flash smelting process with potent guidance.
文摘山洪是全球范围内最危险的自然灾害之一,具有突发性强、成灾快和破坏力大并且难以短时临近预测的特点。传统山洪预报预警方法主要依赖于基于物理机制的水文-水动力山洪过程模拟,然而这种方法计算复杂耗时较长,难以满足山洪的短时临近预测需求。以浙江临安仁里村为例,在水文-水动力物理模拟所产生的8378条降雨时序和对应山洪淹没时空序列数据集的基础上,以基于卷积门控循环单元(convolutional gated recurrent unit convGRU)的深度神经网络作为核心,构建山洪时空序列预测代理模型。该模型通过输入过去24小时降雨观测时序和未来6小时的降雨预报时序,可实现未来6小时山洪淹没时空演变过程的快速预测。代理模型在测试集中能可靠地预测未来逐小时的山洪淹没范围、最大淹没深度以及淹没位置,未来6小时预测的可决系数均值为0.96,且预测速度平均比物理模拟快15625倍。这表明该代理模型能够捕捉物理模拟中降雨到山洪的复杂映射关系,实现目标区域山洪的快速预测,为山洪预警及应急响应决策制定提供有力的模型基础。
