Coal bursts involve the sudden, violent ejection of coal or rock into the mine workings. They are a particular hazard because they typically occur without warning. During the past 2 years three US coal miners were kil...Coal bursts involve the sudden, violent ejection of coal or rock into the mine workings. They are a particular hazard because they typically occur without warning. During the past 2 years three US coal miners were killed in two coal bursts, following a 6-year period during which there were zero burst fatalities. This paper puts the US experience in the context of worldwide research into coal bursts. It focuses on two major longwall mining coalfields which have struggled with bursts for decades. The Utah experience displays many of the ＂classic＂ burst characteristics, including deep cover, strong roof and floor rock, and a direct association between bursts and mining activity. In Colorado, the longwalls of the North Fork Valley （NFV） also work at great depth, but their roof and floor strengths are moderate, and most bursts have occurred during entry development or in headgates, bleeders, or other outby locations. The NFV bursts also are more likely to be associated with geologic structures and large magnitude seismic events. The paper provides a detailed case history to illustrate the experience in each of these coalfields. The paper closes with a brief discussion of how US longwalls have managed the burst risk.展开更多
In the goal optimization and control optimization process the problems with common artificial neural network algorithm are unsure convergence, insufficient post-training network precision, and slow training speed, in ...In the goal optimization and control optimization process the problems with common artificial neural network algorithm are unsure convergence, insufficient post-training network precision, and slow training speed, in which partial minimum value question tends to occur. This paper conducted an in-depth study on the causes of the limi-tations of the algorithm, presented a rapid artificial neural network algorithm, which is characterized by integrating multiple algorithms and by using their complementary advan-tages. The salient feature of the method is self-organization, which can effectively prevent the optimized results from tending to be partial minimum values. Overall optimization can be achieved with this method, goal function can be searched for in overall scope. With op-timization control of coal mine ventilator as a practical application, the paper proves that by integrating multiple artificial neural network algorithms, best control optimization and goal optimized can be achieved.展开更多
文摘Coal bursts involve the sudden, violent ejection of coal or rock into the mine workings. They are a particular hazard because they typically occur without warning. During the past 2 years three US coal miners were killed in two coal bursts, following a 6-year period during which there were zero burst fatalities. This paper puts the US experience in the context of worldwide research into coal bursts. It focuses on two major longwall mining coalfields which have struggled with bursts for decades. The Utah experience displays many of the ＂classic＂ burst characteristics, including deep cover, strong roof and floor rock, and a direct association between bursts and mining activity. In Colorado, the longwalls of the North Fork Valley （NFV） also work at great depth, but their roof and floor strengths are moderate, and most bursts have occurred during entry development or in headgates, bleeders, or other outby locations. The NFV bursts also are more likely to be associated with geologic structures and large magnitude seismic events. The paper provides a detailed case history to illustrate the experience in each of these coalfields. The paper closes with a brief discussion of how US longwalls have managed the burst risk.
基金Supported by the Science Foundation of the Liaoning Province(2004C011)
文摘In the goal optimization and control optimization process the problems with common artificial neural network algorithm are unsure convergence, insufficient post-training network precision, and slow training speed, in which partial minimum value question tends to occur. This paper conducted an in-depth study on the causes of the limi-tations of the algorithm, presented a rapid artificial neural network algorithm, which is characterized by integrating multiple algorithms and by using their complementary advan-tages. The salient feature of the method is self-organization, which can effectively prevent the optimized results from tending to be partial minimum values. Overall optimization can be achieved with this method, goal function can be searched for in overall scope. With op-timization control of coal mine ventilator as a practical application, the paper proves that by integrating multiple artificial neural network algorithms, best control optimization and goal optimized can be achieved.
