基于RS-GWO-GRNN的充填管道失效风险研究
|
摘要
为克服充填管道失效风险评判指标间的复杂性,传统方法预测精度低及适用性差等缺陷,提出基于粗糙集(RS)和灰狼优化(GWO)算法融合广义回归神经网络(GRNN)的充填管道失效风险评价模型。选取10项风险评价指标,通过属性约简提取影响充填管道失效的主要风险因素,运用GWO优化GRNN的参数,构建预测模型,以国内某具体矿山充填系统为例进行实证研究,结果表明:与其它预测模型相比,RS-GWO-GRNN模型的预测精度更高,泛化能力更强,为充填管道失效风险研究提供了新思路,具有较好的借鉴意义。
In order to overcome the complexity of the evaluation index of failure risk for backfill pipeline and the defects of traditional methods such as low prediction accuracy and poor applicability,the paper presents a new method of backfill pipeline failure risk assessment model called generalized regression neural network(GRNN)based on rough set(RS)and GWO algorithm.Ten risk evaluation indexes were selected,the main risk factors affecting filling pipeline failure were extracted through attribute reduction,and GWO was used to optimize the parameters of GRNN to build a forecasting model,taking a specific domestic mine filling system as an example for empirical research.The results show that compared with other prediction models,RS-GWO-GRNN model has higher prediction accuracy and stronger generalization ability,which provides a new idea for the research on the risk of backfill pipeline failure with good reference significance.
In order to overcome the complexity of the evaluation index of failure risk for backfill pipeline and the defects of traditional methods such as low prediction accuracy and poor applicability,the paper presents a new method of backfill pipeline failure risk assessment model called generalized regression neural network(GRNN)based on rough set(RS)and GWO algorithm.Ten risk evaluation indexes were selected,the main risk factors affecting filling pipeline failure were extracted through attribute reduction,and GWO was used to optimize the parameters of GRNN to build a forecasting model,taking a specific domestic mine filling system as an example for empirical research.The results show that compared with other prediction models,RS-GWO-GRNN model has higher prediction accuracy and stronger generalization ability,which provides a new idea for the research on the risk of backfill pipeline failure with good reference significance.
引文
[1]王新民,古德生,张钦礼.深井矿山充填理论与管道输送技术[M].长沙:中南大学出版社,2010:1-6.WANG Xinmin,GU Desheng,ZHANG Qinli.Theory of backfill activity and pipeline transportation technology of backfill in deep mines[M].Changsha:Central South University Press,2010:1-6.
[2]张钦礼,周碧辉,王新民,等.充填管道失效风险性预测精度研究[J].中南大学学报(自然科学版),2014,45(8):2805-2811.ZHANG Qinli,ZHOU Bihui,WANG Xinmin,et al.Invalidation prediction precision of filling pipeline[J].Journal of Central South University(Science and Technology),2014,45(8):2805-2811.
[3]薛希龙,王新民,张钦礼.充填管道磨损风险评估的组合权重与可变模糊耦合模型[J].中南大学学报(自然科学版),2016,47(11):3752-3758.XUE Xilong,WANG Xinmin,ZHANG Qinli.An integrated model of combination weights and variable fuzzy on evaluating backfill pipeline wear risk[J].Journal of Central South University(Science and Technology),2016,47(11):3752-3758.
[4]王新民,王石,鄢德波,等.基于未确知测度理论的充填管道堵塞风险性评价[J].中国安全科学学报,2012,22(4):151-156.WANG Xinmin,WANG Shi,YAN Debo,et al.Risk assessment on blocking of filling pipeline based on uncertainty measurement theory[J].China Safety Science Journal,2012,22(4):151-156.
[5]史秀志,范玉乾,尚雪义.基于PCA-BP神经网络模型的充填体强度预测[J].黄金科学技术,2016,24(3):64-69.SHI Xiuzhi,FAN Yuqian,SHANG Xueyi.Strength prediction of filling body based on PCA and BP neural networks[J].Gold Science and Technology,2016,24(3):64-69.
[6]张钦礼,王兢,王新民.基于核主成分分析与PSO-SVM的充填管道失效风险性分级评价模型[J].黄金科学技术,2017,25(3):70-76.ZHANG Qinli,WANG Jing,WANG Xinmin.Failure risk assessment model of filling pipeline based on KPCAand PSO-SVM[J].Gold Science and Technology,2017,25(3):70-76.
[7]李冬辉,尹海燕,郑博文.基于MFOA-GRNN模型的年电力负荷预测[J].电网技术,2018(2):585-590.LI Donghui,YIN Haiyan,ZHENG Bowen.An annual load forecasting model based on generalized regression neural network withmulti-swarm fruit fly optimization algorithm[J].Power System Technology,2018(2):585-590.
[8]ZHANG Y,LIU L,TIAN J,et al.Intent recognition of a lower limb prosthesis based on multi-source information and general regression neural network[J].Journal of Computational&Theoretical Nanoscience,2016,13(11):8956-8962.
[9]骆正山,王文辉,王小完,等.基于RS-PSO-GRNN的埋地管道土壤腐蚀预测[J].材料保护,2018,51(8):47-52,79.LUO Zhengshan,WANG Wenhui,WANG Xiaowan,et al.Soil corrosion prediction of buried pipeline based on the model of RS-PSO-GRNN[J].Materials Protection,2018,51(8):47-52,79.
[10]GU H Y.Risk evaluation of gas pipeline based on rough set[J].Applied Mechanics&Materials,2014,443:258-262.
[11]YANG X,FU G,ZHANG Y,et al.A naive bayesian wind power interval prediction approach based on rough set attribute reduction and weight optimization[J].Energies,2017,10(11):1-15.
[12]LI W D,YANG X,LI H,et al.Hybrid forecasting approach based on GRNN neural network and SVRmachine for electricity demand forecasting[J].Energies,2017,10(1):44.
[13]RODRíGUEZ L,CASTILLO O,SORIA J,et al.A fuzzy hierarchical operator in the grey wolf optimizer algorithm[J].Applied Soft Computing,2017(57):315-328.
[14]过江,张碧肖.基于PCA与BP神经网络的充填管道失效风险评估[J].黄金科学技术,2015,23(5):66-71.GUO Jiang,ZHANG Bixiao.Invalidation risk evaluation of backfill pipe based on PCA and BPneuralnetwork[J].Gold Science and Technology,2015,23(5):66-71.
[15]杨志强,陈得信,高谦,等.金川矿山混合充填料浆环管试验系统与管输特性研究[J].有色金属工程,2017,7(1):64-70.YANG Zhiqiang,CHEN Dexin,GAO Qian,et al.Loop test system for the mixing filling slurry and research on pipelining characteristic in Jinchuan[J].Nonferrous Metals Engineering,2017,7(1):64-70.
[16]杨啸,杨志强,高谦,等.混合充填骨料胶结充填强度试验与最优配比决策研究[J].岩土力学,2016,37(增刊2):635-641.YANG Xiao,YANG Zhiqiang,GAO Qian,et al.Cemented filling strength test and optimal proportion decision of mixed filling aggregate[J].Rock and Soil Mechanics,2016,37(S2):635-641.
[17]王新民,高瑞文,胡威,等.充填管道堵塞风险预测模型[J].中南大学学报(自然科学版),2013,44(11):4604-4610.WANG Xinmin,GAO Ruiwen,HU Wei,etal.Risk prediction model of filling pipeline blockage[J].Journal of Central South University(Science and Technology),2013,44(11):4604-4610.
[2]张钦礼,周碧辉,王新民,等.充填管道失效风险性预测精度研究[J].中南大学学报(自然科学版),2014,45(8):2805-2811.ZHANG Qinli,ZHOU Bihui,WANG Xinmin,et al.Invalidation prediction precision of filling pipeline[J].Journal of Central South University(Science and Technology),2014,45(8):2805-2811.
[3]薛希龙,王新民,张钦礼.充填管道磨损风险评估的组合权重与可变模糊耦合模型[J].中南大学学报(自然科学版),2016,47(11):3752-3758.XUE Xilong,WANG Xinmin,ZHANG Qinli.An integrated model of combination weights and variable fuzzy on evaluating backfill pipeline wear risk[J].Journal of Central South University(Science and Technology),2016,47(11):3752-3758.
[4]王新民,王石,鄢德波,等.基于未确知测度理论的充填管道堵塞风险性评价[J].中国安全科学学报,2012,22(4):151-156.WANG Xinmin,WANG Shi,YAN Debo,et al.Risk assessment on blocking of filling pipeline based on uncertainty measurement theory[J].China Safety Science Journal,2012,22(4):151-156.
[5]史秀志,范玉乾,尚雪义.基于PCA-BP神经网络模型的充填体强度预测[J].黄金科学技术,2016,24(3):64-69.SHI Xiuzhi,FAN Yuqian,SHANG Xueyi.Strength prediction of filling body based on PCA and BP neural networks[J].Gold Science and Technology,2016,24(3):64-69.
[6]张钦礼,王兢,王新民.基于核主成分分析与PSO-SVM的充填管道失效风险性分级评价模型[J].黄金科学技术,2017,25(3):70-76.ZHANG Qinli,WANG Jing,WANG Xinmin.Failure risk assessment model of filling pipeline based on KPCAand PSO-SVM[J].Gold Science and Technology,2017,25(3):70-76.
[7]李冬辉,尹海燕,郑博文.基于MFOA-GRNN模型的年电力负荷预测[J].电网技术,2018(2):585-590.LI Donghui,YIN Haiyan,ZHENG Bowen.An annual load forecasting model based on generalized regression neural network withmulti-swarm fruit fly optimization algorithm[J].Power System Technology,2018(2):585-590.
[8]ZHANG Y,LIU L,TIAN J,et al.Intent recognition of a lower limb prosthesis based on multi-source information and general regression neural network[J].Journal of Computational&Theoretical Nanoscience,2016,13(11):8956-8962.
[9]骆正山,王文辉,王小完,等.基于RS-PSO-GRNN的埋地管道土壤腐蚀预测[J].材料保护,2018,51(8):47-52,79.LUO Zhengshan,WANG Wenhui,WANG Xiaowan,et al.Soil corrosion prediction of buried pipeline based on the model of RS-PSO-GRNN[J].Materials Protection,2018,51(8):47-52,79.
[10]GU H Y.Risk evaluation of gas pipeline based on rough set[J].Applied Mechanics&Materials,2014,443:258-262.
[11]YANG X,FU G,ZHANG Y,et al.A naive bayesian wind power interval prediction approach based on rough set attribute reduction and weight optimization[J].Energies,2017,10(11):1-15.
[12]LI W D,YANG X,LI H,et al.Hybrid forecasting approach based on GRNN neural network and SVRmachine for electricity demand forecasting[J].Energies,2017,10(1):44.
[13]RODRíGUEZ L,CASTILLO O,SORIA J,et al.A fuzzy hierarchical operator in the grey wolf optimizer algorithm[J].Applied Soft Computing,2017(57):315-328.
[14]过江,张碧肖.基于PCA与BP神经网络的充填管道失效风险评估[J].黄金科学技术,2015,23(5):66-71.GUO Jiang,ZHANG Bixiao.Invalidation risk evaluation of backfill pipe based on PCA and BPneuralnetwork[J].Gold Science and Technology,2015,23(5):66-71.
[15]杨志强,陈得信,高谦,等.金川矿山混合充填料浆环管试验系统与管输特性研究[J].有色金属工程,2017,7(1):64-70.YANG Zhiqiang,CHEN Dexin,GAO Qian,et al.Loop test system for the mixing filling slurry and research on pipelining characteristic in Jinchuan[J].Nonferrous Metals Engineering,2017,7(1):64-70.
[16]杨啸,杨志强,高谦,等.混合充填骨料胶结充填强度试验与最优配比决策研究[J].岩土力学,2016,37(增刊2):635-641.YANG Xiao,YANG Zhiqiang,GAO Qian,et al.Cemented filling strength test and optimal proportion decision of mixed filling aggregate[J].Rock and Soil Mechanics,2016,37(S2):635-641.
[17]王新民,高瑞文,胡威,等.充填管道堵塞风险预测模型[J].中南大学学报(自然科学版),2013,44(11):4604-4610.WANG Xinmin,GAO Ruiwen,HU Wei,etal.Risk prediction model of filling pipeline blockage[J].Journal of Central South University(Science and Technology),2013,44(11):4604-4610.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |