基于GA-SVM的煤矿岩巷爆破效果智能预测
|
摘要
煤矿岩石巷道爆破效果预测对合理优化爆破参数、提高爆破效率具有重要意义。针对煤矿岩石巷道爆破效果影响因素多、难以进行爆破效果准确预测等关键技术难题,提出基于GASVM融合技术的爆破效果预测模型,实现爆破效果科学、合理预测。首先,基于综合分析、专家打分法等确定影响煤矿岩巷爆破效果关键指标;然后,根据不同矿区典型案例建立爆破效果预测样本库,并对样本进行数据处理;最后,将预测模型应用于实际工程,预测结果与爆破实际分类结果吻合。研究成果可为巷道爆破预测提供一种新思路。
Prediction of blasting effect of rock roadway in the coal mine is of great significance for rational optimization of blasting parameters and improvement of blasting efficiency. Aiming at the key technical problems such as many factors affecting the blasting effect of rock roadway in the coal mine,which are difficult to accurately predict the blasting effect,a prediction model of blasting effect based on GA-SVM fusion technology is proposed to realize scientific and reasonable prediction of blasting effect. Firstly,based on a comprehensive analysis and expert scoring method,the key impact indicators affecting the blasting effect of coal mine rock roadway were determined. Secondly,according to typical cases in different mining areas,the sample database of blasting effect prediction was established and the samples were processed. Thirty sets of data were used for training,and the other 12 groups were used for prediction,the prediction accuracy was about 92%. Finally,the prediction model has been applied to practical projects. The predicted results coincided with the actual classification of blasting. The research results can provide a new idea for roadway blasting prediction.
Prediction of blasting effect of rock roadway in the coal mine is of great significance for rational optimization of blasting parameters and improvement of blasting efficiency. Aiming at the key technical problems such as many factors affecting the blasting effect of rock roadway in the coal mine,which are difficult to accurately predict the blasting effect,a prediction model of blasting effect based on GA-SVM fusion technology is proposed to realize scientific and reasonable prediction of blasting effect. Firstly,based on a comprehensive analysis and expert scoring method,the key impact indicators affecting the blasting effect of coal mine rock roadway were determined. Secondly,according to typical cases in different mining areas,the sample database of blasting effect prediction was established and the samples were processed. Thirty sets of data were used for training,and the other 12 groups were used for prediction,the prediction accuracy was about 92%. Finally,the prediction model has been applied to practical projects. The predicted results coincided with the actual classification of blasting. The research results can provide a new idea for roadway blasting prediction.
引文
[1]郑玉建.煤矿巷道爆破效果人工神经网络预测研究[J].安徽建筑工业学院学报,2012,20(6):84-87.
[2]王宇涛,刘殿书,梁书锋,等.立井爆破效果预测及模糊综合评价[J].爆破,2014,31(3):10-14.
[3]王长友,唐又驰.光面爆破效果BP神经网络预测[J].辽宁工程技术大学学报,2005,24(1):73-75.
[4]杨学存,侯媛彬,洪卫林,等.基于参数优化支持向量机的煤泥输送管道压力预测[J].煤炭工程,2013,45(12):112-115.
[5]刘希亮,赵学胜,陆锋.基于GA-SVM的露天矿抛掷爆破抛掷率预测[J].煤炭学报,2012,37(12):1999-2005.
[6]Shen Zhong-jie.Remaining life predictions of rolling bearing based on relative features and multivariablc support vector machine[J].Journal of Mechanical Engineering,2013,48(2):183-189.
[7]郭明玮,赵宇宙,项俊平.基于支持向量机的目标检测算法综述[J].控制与决策,2014,29(2):193-200.
[8]王保建,张小丽,傅杨奥晓,等.优化支持向量机及其在智能故障诊断中的应用[J].振动、测试与诊断,2017,37(3):547-632.
[9]Vapnik V N,Vapnik V.Statistical learning theory[M].New York:Wiley,1998.
[10]张成梁,李蕾,董全成,等.基于GA-SVM模型的机采籽棉杂质识别[J].农业工程学报,2016,32(24):189-196.
[11]Holland,J.Adaptation in natural and artificial svstarns[M].Michigan:University of Michigan Press,1975.
[12]刘希亮,赵学胜,陆锋,等.基于GA-SVM的露天矿抛掷爆破抛掷率预测[J].煤炭学报,2012,37(12):1999-2005.
[13]Chang C C,Lin C J LIBSVM:a library for support vector machines[R].Taiwan:National Taiwan University,2001.
[14]林天舒.基于支持向量机煤矿巷道爆破参数智能优化关键技术研究[D].北京:中国矿业大学(北京),2017.
[2]王宇涛,刘殿书,梁书锋,等.立井爆破效果预测及模糊综合评价[J].爆破,2014,31(3):10-14.
[3]王长友,唐又驰.光面爆破效果BP神经网络预测[J].辽宁工程技术大学学报,2005,24(1):73-75.
[4]杨学存,侯媛彬,洪卫林,等.基于参数优化支持向量机的煤泥输送管道压力预测[J].煤炭工程,2013,45(12):112-115.
[5]刘希亮,赵学胜,陆锋.基于GA-SVM的露天矿抛掷爆破抛掷率预测[J].煤炭学报,2012,37(12):1999-2005.
[6]Shen Zhong-jie.Remaining life predictions of rolling bearing based on relative features and multivariablc support vector machine[J].Journal of Mechanical Engineering,2013,48(2):183-189.
[7]郭明玮,赵宇宙,项俊平.基于支持向量机的目标检测算法综述[J].控制与决策,2014,29(2):193-200.
[8]王保建,张小丽,傅杨奥晓,等.优化支持向量机及其在智能故障诊断中的应用[J].振动、测试与诊断,2017,37(3):547-632.
[9]Vapnik V N,Vapnik V.Statistical learning theory[M].New York:Wiley,1998.
[10]张成梁,李蕾,董全成,等.基于GA-SVM模型的机采籽棉杂质识别[J].农业工程学报,2016,32(24):189-196.
[11]Holland,J.Adaptation in natural and artificial svstarns[M].Michigan:University of Michigan Press,1975.
[12]刘希亮,赵学胜,陆锋,等.基于GA-SVM的露天矿抛掷爆破抛掷率预测[J].煤炭学报,2012,37(12):1999-2005.
[13]Chang C C,Lin C J LIBSVM:a library for support vector machines[R].Taiwan:National Taiwan University,2001.
[14]林天舒.基于支持向量机煤矿巷道爆破参数智能优化关键技术研究[D].北京:中国矿业大学(北京),2017.