Based on the Fourier transform, a new shape descriptor was proposed to represent the flame image. By employing the shape descriptor as the input, the flame image recognition was studied by the methods of the artificia...Based on the Fourier transform, a new shape descriptor was proposed to represent the flame image. By employing the shape descriptor as the input, the flame image recognition was studied by the methods of the artificial neural network(ANN) and the support vector machine(SVM) respectively. And the recognition experiments were carried out by using flame image data sampled from an alumina rotary kiln to evaluate their effectiveness. The results show that the two recognition methods can achieve good results, which verify the effectiveness of the shape descriptor. The highest recognition rate is 88.83% for SVM and 87.38% for ANN, which means that the performance of the SVM is better than that of the ANN.展开更多
Successfully developed an innovative process of direct reduction of cold bound pellets from iron ore concentrate with a coal based rotary kiln, in comparison with the traditional direct reduction of fired oxide pellet...Successfully developed an innovative process of direct reduction of cold bound pellets from iron ore concentrate with a coal based rotary kiln, in comparison with the traditional direct reduction of fired oxide pellets in coal based rotary kilns , possesses such advantages as: shorter flowsheet, lower capital investment, greater economic profit, good quality of direct reduced iron. The key technologies , such as the composite binder and corresponding feasible techniques were employed in practice. A mill utilizing this process and with an annual capacity of 50 thousand ton DRI has been put into operation.展开更多
A 3-D numerical simulation with CFX software on physical field of multi-air channel coal burner in rotary kiln was carried out. The effects of various operational and structural parameters on flame feature and tempera...A 3-D numerical simulation with CFX software on physical field of multi-air channel coal burner in rotary kiln was carried out. The effects of various operational and structural parameters on flame feature and temperature distribution were investigated. A thermal measurement was conducted on a rotary kiln (4.5m in diameter, 90m in length) with four-air channel coal burner to determine the boundary conditions and to verify the simulation results. The calculation result shows that the distribution of velocity near burner exit is saddle-like; recirculation zones near nozzle and wall are useful for mixture primary air with coal and high temperature fume. A little central airflow can avoid coal backing up and cool nozzle. Adjusting the ratio of internal airflow to outer airflow is an effective and major means to regulate flame and temperature distribution in sintering region. Large whirlcone angle can intensify disturbution range at flame root to accelerate ignition and mixture. Large coal size can reduce high temperature region and result in coal combusting insufficiently. Too much combustion air will lengthen flame and increase heat loss.展开更多
According to the pulverized coal combustion flame image texture features of the rotary-kiln oxide pellets sintering process,a combustion working condition recognition method based on the generalized learning vector(GL...According to the pulverized coal combustion flame image texture features of the rotary-kiln oxide pellets sintering process,a combustion working condition recognition method based on the generalized learning vector(GLVQ) neural network is proposed.Firstly,the numerical flame image is analyzed to extract texture features,such as energy,entropy and inertia,based on grey-level co-occurrence matrix(GLCM) to provide qualitative information on the changes in the visual appearance of the flame.Then the kernel principal component analysis(KPCA) method is adopted to deduct the input vector with high dimensionality so as to reduce the GLVQ target dimension and network scale greatly.Finally,the GLVQ neural network is trained by using the normalized texture feature data.The test results show that the proposed KPCA-GLVQ classifer has an excellent performance on training speed and correct recognition rate,and it meets the requirement for real-time combustion working condition recognition for the rotary kiln process.展开更多
基金Project(60634020) supported by the National Natural Science Foundation of China
文摘Based on the Fourier transform, a new shape descriptor was proposed to represent the flame image. By employing the shape descriptor as the input, the flame image recognition was studied by the methods of the artificial neural network(ANN) and the support vector machine(SVM) respectively. And the recognition experiments were carried out by using flame image data sampled from an alumina rotary kiln to evaluate their effectiveness. The results show that the two recognition methods can achieve good results, which verify the effectiveness of the shape descriptor. The highest recognition rate is 88.83% for SVM and 87.38% for ANN, which means that the performance of the SVM is better than that of the ANN.
基金The Key Project of the 9th Five year Plan of Ministry of Science andTechnology!(No .960 40 2 0 2A)the Foundation for Unive
文摘Successfully developed an innovative process of direct reduction of cold bound pellets from iron ore concentrate with a coal based rotary kiln, in comparison with the traditional direct reduction of fired oxide pellets in coal based rotary kilns , possesses such advantages as: shorter flowsheet, lower capital investment, greater economic profit, good quality of direct reduced iron. The key technologies , such as the composite binder and corresponding feasible techniques were employed in practice. A mill utilizing this process and with an annual capacity of 50 thousand ton DRI has been put into operation.
文摘A 3-D numerical simulation with CFX software on physical field of multi-air channel coal burner in rotary kiln was carried out. The effects of various operational and structural parameters on flame feature and temperature distribution were investigated. A thermal measurement was conducted on a rotary kiln (4.5m in diameter, 90m in length) with four-air channel coal burner to determine the boundary conditions and to verify the simulation results. The calculation result shows that the distribution of velocity near burner exit is saddle-like; recirculation zones near nozzle and wall are useful for mixture primary air with coal and high temperature fume. A little central airflow can avoid coal backing up and cool nozzle. Adjusting the ratio of internal airflow to outer airflow is an effective and major means to regulate flame and temperature distribution in sintering region. Large whirlcone angle can intensify disturbution range at flame root to accelerate ignition and mixture. Large coal size can reduce high temperature region and result in coal combusting insufficiently. Too much combustion air will lengthen flame and increase heat loss.
基金supported by China Postdoctoral Science Foundation(No.20110491510)Program for Liaoning Excellent Talents in University(No.LJQ2011027)+1 种基金Anshan Science and Technology Project(No.2011MS11)Special Research Foundation of University of Science and Technology of Liaoning(No.2011zx10)
文摘According to the pulverized coal combustion flame image texture features of the rotary-kiln oxide pellets sintering process,a combustion working condition recognition method based on the generalized learning vector(GLVQ) neural network is proposed.Firstly,the numerical flame image is analyzed to extract texture features,such as energy,entropy and inertia,based on grey-level co-occurrence matrix(GLCM) to provide qualitative information on the changes in the visual appearance of the flame.Then the kernel principal component analysis(KPCA) method is adopted to deduct the input vector with high dimensionality so as to reduce the GLVQ target dimension and network scale greatly.Finally,the GLVQ neural network is trained by using the normalized texture feature data.The test results show that the proposed KPCA-GLVQ classifer has an excellent performance on training speed and correct recognition rate,and it meets the requirement for real-time combustion working condition recognition for the rotary kiln process.
