Froth image features of coal flotation have been extracted and studied by neighboring grey level dependence matrix, spatial grey level dependence matrix and grey level histogram. In this paper, a basic algorithm of un...Froth image features of coal flotation have been extracted and studied by neighboring grey level dependence matrix, spatial grey level dependence matrix and grey level histogram. In this paper, a basic algorithm of unsupervised learning pattern classification is presented, and coal flotation froth images are classified by means of self organizing map (SOM). By extracting features from 51 flotation froth images with laboratory column, four types of froth images are classified. The correct rate of SOM cluster is satisfactory. And a good relationship of froth type with average ash content is also observed.展开更多
By using the matrix theory, a 5 parameter grinding mathematical model is established. Based on the properties of feed coal and requirements for size distribution of final product, the model gives the required grinding...By using the matrix theory, a 5 parameter grinding mathematical model is established. Based on the properties of feed coal and requirements for size distribution of final product, the model gives the required grinding probability for various particles and corresponding ball size distribution. By using this model, 3 different sizes of ball mill are designed and put into commercial use for coal water fuel. The forecasted ball mill capacity, the particle sizes and particle size distribution as well as the coal water fuel quality parameters are all in line with industrial operation results, which have proved the suitability of the model.展开更多
Two different grinding processes were examined to determine the effect grinding has on the quality of a CWS. A series of slurries was prepared from Australian (Au) and Chinese (YZ) coals. Both types of coal were groun...Two different grinding processes were examined to determine the effect grinding has on the quality of a CWS. A series of slurries was prepared from Australian (Au) and Chinese (YZ) coals. Both types of coal were ground by a Chinese (CUMT) and an Australian (JK) grinding process. The performance tests of the prepared CWS showed that fluidity of all slurries was acceptable. The concentration of the CWS from YZ coal ground by the CUMT grinding process was higher than when the JK grinding process was used. The highest concentration was 70.14% in this case. The concentration of the CWS prepared from Au coal by the JK grinding process was higher than when the CUMT grinding process was used. The highest con- centration in this case was 70.97%. These differences are caused by the particle size distribution devel- oped during the different grinding processes.展开更多
基金National Natural Science Foundation of China( 5 99740 32 )
文摘Froth image features of coal flotation have been extracted and studied by neighboring grey level dependence matrix, spatial grey level dependence matrix and grey level histogram. In this paper, a basic algorithm of unsupervised learning pattern classification is presented, and coal flotation froth images are classified by means of self organizing map (SOM). By extracting features from 51 flotation froth images with laboratory column, four types of froth images are classified. The correct rate of SOM cluster is satisfactory. And a good relationship of froth type with average ash content is also observed.
文摘By using the matrix theory, a 5 parameter grinding mathematical model is established. Based on the properties of feed coal and requirements for size distribution of final product, the model gives the required grinding probability for various particles and corresponding ball size distribution. By using this model, 3 different sizes of ball mill are designed and put into commercial use for coal water fuel. The forecasted ball mill capacity, the particle sizes and particle size distribution as well as the coal water fuel quality parameters are all in line with industrial operation results, which have proved the suitability of the model.
基金This project received funding from the Australian governmentas part of the Asia-Pacific Partnership on Clean Development and Climate
文摘Two different grinding processes were examined to determine the effect grinding has on the quality of a CWS. A series of slurries was prepared from Australian (Au) and Chinese (YZ) coals. Both types of coal were ground by a Chinese (CUMT) and an Australian (JK) grinding process. The performance tests of the prepared CWS showed that fluidity of all slurries was acceptable. The concentration of the CWS from YZ coal ground by the CUMT grinding process was higher than when the JK grinding process was used. The highest concentration was 70.14% in this case. The concentration of the CWS prepared from Au coal by the JK grinding process was higher than when the CUMT grinding process was used. The highest con- centration in this case was 70.97%. These differences are caused by the particle size distribution devel- oped during the different grinding processes.
