The traditional least squares support vector regression（LS-SVR）model,using cross validation to determine the regularization parameter and kernel parameter,is time-consuming.We propose a Bayesian evidence framework t...The traditional least squares support vector regression（LS-SVR）model,using cross validation to determine the regularization parameter and kernel parameter,is time-consuming.We propose a Bayesian evidence framework to infer the LS-SVR model parameters.Three levels Bayesian inferences are used to determine the model parameters,regularization hyper-parameters and tune the nuclear parameters by model comparison.On this basis,we established Bayesian LS-SVR time-series gas forecasting models and provide steps for the algorithm.The gas outburst data of a Hebi 10th mine working face is used to validate the model.The optimal embedding dimension and delay time of the time series were obtained by the smallest differential entropy method.Finally,within a MATLAB7.1 environment,we used actual coal gas data to compare the traditional LS-SVR and the Bayesian LS-SVR with LS-SVMlab1.5 Toolbox simulation.The results show that the Bayesian framework of an LS-SVR significantly improves the speed and accuracy of the forecast.展开更多
Based on the important role in mine safety played by parameters of the first gas outburst, we propose a method of combining historic data, theoretical analysis and experimental research for the purpose of crit- ical v...Based on the important role in mine safety played by parameters of the first gas outburst, we propose a method of combining historic data, theoretical analysis and experimental research for the purpose of crit- ical values of gas parameters of the first gas outburst in a coal seam of the Xieqiao Mine. According to a characteristic analysis and a summary of the rules of coal and gas outbursts in the No.8 coal seam of a Hua- inan mine, we have investigated their effect on coal and gas outbursts in terms such as ground stress, gas, and coal structure. We have selected gas parameters and determined the critical values of each of the fol- lowing indices： gas content as 7.7 m^3/t, tectonic coal as 0.8 m thick, the absolute gas emission as 2 m3/min, the rate of change as 0.7 m3/min, the gas desorption index of a drilling chip KI as 0.26 mL/（g min^1/2） and the values of desorption indexes Ah2 as 200 Pa. From a verification of the production, the results indicate that application of each index and their critical values significantly improve the level of safety in the pro- duction process, relieve the burden upon the mine, save much labor and bring clear economic benefits.展开更多
The treatment of the Gacun complex Cu concentrate with high contents of Pb,Zn,Ag,etc by oxygen pressure acid leaching was studied.It is unusual that tetrahedrite,whose treatment was rarely studied,is the primary coppe...The treatment of the Gacun complex Cu concentrate with high contents of Pb,Zn,Ag,etc by oxygen pressure acid leaching was studied.It is unusual that tetrahedrite,whose treatment was rarely studied,is the primary copper mineral of the concentrates.Most of silver also occurs in the mineral.The optimum operating parameters of oxygen pressure acid leaching were established by conditional tests.Pilot scale test was carried out under the parameters,and the leaching rates of copper and zinc are as high as 97.10% and 89.83% while lead and silver are transformed into sulfate and sulfide respectively and stay in leaching residue.The copper and zinc in lixivium were reclaimed by extraction-electrowinning and purification-electrowinning,respectively,and the lead and silver in the residue were reclaimed separately by chloride leaching and thiourea leaching.The extraction rate of copper achieves 96%,and the leaching rates of lead and silver reach 90% and 95%,respectively.展开更多
基金Financial support for this work,provided by the National Natural Science Foundation of China(No.60974126)the Natural Science Foundation of Jiangsu Province(No.BK2009094)
文摘The traditional least squares support vector regression（LS-SVR）model,using cross validation to determine the regularization parameter and kernel parameter,is time-consuming.We propose a Bayesian evidence framework to infer the LS-SVR model parameters.Three levels Bayesian inferences are used to determine the model parameters,regularization hyper-parameters and tune the nuclear parameters by model comparison.On this basis,we established Bayesian LS-SVR time-series gas forecasting models and provide steps for the algorithm.The gas outburst data of a Hebi 10th mine working face is used to validate the model.The optimal embedding dimension and delay time of the time series were obtained by the smallest differential entropy method.Finally,within a MATLAB7.1 environment,we used actual coal gas data to compare the traditional LS-SVR and the Bayesian LS-SVR with LS-SVMlab1.5 Toolbox simulation.The results show that the Bayesian framework of an LS-SVR significantly improves the speed and accuracy of the forecast.
基金supported by the National Key Basic Research Program of China (No.2005CB 221501)the Innovation Scientists and Technicians Troop Construction Projects of Henan Province (No.084200510002)the Program for New Century Excellent Talents in University (No.NCET-07-0257)
文摘Based on the important role in mine safety played by parameters of the first gas outburst, we propose a method of combining historic data, theoretical analysis and experimental research for the purpose of crit- ical values of gas parameters of the first gas outburst in a coal seam of the Xieqiao Mine. According to a characteristic analysis and a summary of the rules of coal and gas outbursts in the No.8 coal seam of a Hua- inan mine, we have investigated their effect on coal and gas outbursts in terms such as ground stress, gas, and coal structure. We have selected gas parameters and determined the critical values of each of the fol- lowing indices： gas content as 7.7 m^3/t, tectonic coal as 0.8 m thick, the absolute gas emission as 2 m3/min, the rate of change as 0.7 m3/min, the gas desorption index of a drilling chip KI as 0.26 mL/（g min^1/2） and the values of desorption indexes Ah2 as 200 Pa. From a verification of the production, the results indicate that application of each index and their critical values significantly improve the level of safety in the pro- duction process, relieve the burden upon the mine, save much labor and bring clear economic benefits.
基金Project(2007BAB22B01) supported by the National Science and Technology Pillar Program during the 11th Five-year Plan Period of China
文摘The treatment of the Gacun complex Cu concentrate with high contents of Pb,Zn,Ag,etc by oxygen pressure acid leaching was studied.It is unusual that tetrahedrite,whose treatment was rarely studied,is the primary copper mineral of the concentrates.Most of silver also occurs in the mineral.The optimum operating parameters of oxygen pressure acid leaching were established by conditional tests.Pilot scale test was carried out under the parameters,and the leaching rates of copper and zinc are as high as 97.10% and 89.83% while lead and silver are transformed into sulfate and sulfide respectively and stay in leaching residue.The copper and zinc in lixivium were reclaimed by extraction-electrowinning and purification-electrowinning,respectively,and the lead and silver in the residue were reclaimed separately by chloride leaching and thiourea leaching.The extraction rate of copper achieves 96%,and the leaching rates of lead and silver reach 90% and 95%,respectively.
