露天矿行车事故预测方法及应用
|
摘要
为有效解决露天矿山行车事故预测模型建模时,易受小样本数据、离群数据规模影响,导致模型精度损失、算法抗噪容差能力及收敛速度下降等问题,提出一种基于二次惩罚项修正(PTS)的改进支持向量回归机模型(WLSSVR)。根据训练样本的数据分布特性,研究了服从露天矿山现实应用场景的二次惩罚项,进一步提高回归机模型的抗噪容差能力;考虑非线性预测模型影响因子选择困难的问题,研究了数据降维及因子分析方法,并将主成分分析方法引入到输入数据预处理算法中,以保证算法可得到理想的输入;针对传统回归机模型易受核参数选择影响,易导致模型早熟和收敛速度慢等问题,研究了粒子群惯性因子、学习因子的自适应迭代形式,提出了一种应用改进粒子群算法优化回归机模型核参数的方法。以露天矿行车事故频次预测为例,进行了预测和对比实验。实验结果表明:引入PTS模型的测试集预测结果明显优于不采用PTS策略的预测结果。这说明,应用文中提出的二次惩罚策略和参数优化算法对复杂系统的事故预测问题研究是可行且有效的。
To effectively solve the problems of the accuracy loss of prediction models for traffic accident prediction of open-pit mines,the decrease of the algorithm's capability of anti-noise tolerance and convergence rate caused by small sample data and outliers,we propose a modified support vector regression model based on penalized trimmed squares(PTS).According to the data distribution characteristics of the training samples,the penalized trimmed squares submitted to the application scenario of open-pit mine is studied to improve the anti-noise tolerance capability of the regression model.In consideration of the difficulties of the nonlinear prediction model impact factor selection,the method of principal component analysis is introduced into the preprocessing algorithm to reduce the data dimension and ensure that the algorithm can get ideal input data.In view of the problems of premature and slow convergence speed caused by the nuclear parameter selection,the inertial factor and the learning factor of particle swarm are studied and an improved particle swarm algorithm to optimize nuclear parameters regression of the model is proposed.The prediction and comparison experiments are carried out in the case of the accident frequency prediction of open-pit mine.The experimental results show that the test set prediction results of the PTS model are better than those without the PTS policy model.This indicates that the modified penalized trimmed squares strategy and parameter optimization algorithm proposed in this paper is feasible and effective for the study of accident prediction of complex systems.
To effectively solve the problems of the accuracy loss of prediction models for traffic accident prediction of open-pit mines,the decrease of the algorithm's capability of anti-noise tolerance and convergence rate caused by small sample data and outliers,we propose a modified support vector regression model based on penalized trimmed squares(PTS).According to the data distribution characteristics of the training samples,the penalized trimmed squares submitted to the application scenario of open-pit mine is studied to improve the anti-noise tolerance capability of the regression model.In consideration of the difficulties of the nonlinear prediction model impact factor selection,the method of principal component analysis is introduced into the preprocessing algorithm to reduce the data dimension and ensure that the algorithm can get ideal input data.In view of the problems of premature and slow convergence speed caused by the nuclear parameter selection,the inertial factor and the learning factor of particle swarm are studied and an improved particle swarm algorithm to optimize nuclear parameters regression of the model is proposed.The prediction and comparison experiments are carried out in the case of the accident frequency prediction of open-pit mine.The experimental results show that the test set prediction results of the PTS model are better than those without the PTS policy model.This indicates that the modified penalized trimmed squares strategy and parameter optimization algorithm proposed in this paper is feasible and effective for the study of accident prediction of complex systems.
引文
[1]骆中洲,吴亚平,温思龙.露天矿事故分析与预测及安全信息管理[J].化工矿山技术,1992(5):4-8.LUO Zhongzhou,WU Yaping,WEN Silong.Accident analysis and prediction and information system of safety management in surface mine[J].Chemical Mining Technology,1992(5):4-8.(in Chinese)
[2]周荣义,钟岸,任竞舟,等.基于主成分分析和神经网络的事故预测方法及应用[J].中国安全科学学报,2013,23(7):55-60.ZHOU Rongyi,ZHONG An,REN Jingzhou,et al.An accident forecasting method of ANN based on PCA and its application[J].China Safety Science Journal,2013,23(7):55-60.(in Chinese)
[3]李明洋,姜福川.基于最小二乘法的灰色GM(1,1)改进模型在非煤矿山事故预测中的应用[J].中国安全生产科学技术,2013,9(11):83-90.LI Mingyang,JIANG Fuchuan.Improved gray GM(1,1)model in the non-coal mine accident prediction based on the methed of least square[J].Journal of Safety Science and Technology,2013,9(11):83-90.(in Chinese)
[4]顾晓叶,于殿宝,朱玉生,等.事故预测数学模型的研究与实践[J].中国安全科学学报,2009,19(12):23-27,204.GU Xiaoye,YU Dianbao,ZHU Yusheng,et al.Research and practice of accident prediction mathematicalmodels[J].China Safety Science Journal,2009,19(12):23-27,204.(in Chinese)
[5]孙轶轩,邵春福,计寻,等.基于ARIMA与信息粒化SVR组合模型的交通事故时序预测[J].清华大学学报(自然科学版),2014,54(3):348-353,359.SUN Yixuan,SHAO Chunfu,JI Xun,et al.Urban traffic accident time series prediction model based on combination of ARIMA and information granulation SVR[J].Journal of Tsinghua University(ScienceandTechnology),2014,54(3):348-353,359.(in Chinese)
[6]赵玲,许宏科,程鸿亮.基于最优加权组合模型的道路交通事故预测[J].计算机工程与应用,2013,49(24):11-15.ZHAO Ling,XU Hongke,CHENG Hongliang.Road traffic accidents prediction based on optimal weighted combinedmodel[J].Computer Engineering and Applications,2013,49(24):11-15.(in Chinese)
[7]彭小玲.支持向量机技术在海上船舶交通事故预测中的应用[J].舰船科学技术,2018,40(2):55-57.PENG Xiaoling.Research on ship traffic accident prediction using state vector machine[J].Ship Science and Technology,2018,40(2):55-57.(in Chinese)
[8]宋传平,王鹏飞,李涛.基于GM(1,1)模型的军用车辆交通事故预测研究[J].中国安全科学学报,2010,20(11):52-55.SONG Chuanping,WANG Pengfei,LI Tao.Forecast of military vehicle traffic accidents based on GM(1,1)model[J].China Safety Science Journal,2010,20(11):52-55.(in Chinese)
[9]朱志洁,张宏伟,韩军,等.基于PCA-BP神经网络的煤与瓦斯突出预测研究[J].中国安全科学学报,2013,23(4):45-50.ZHU Zhijie,ZHANG Hongwei,HAN Jun,et al.Prediction of coal and gas outburst based on PCA-BP neural network[J].China Safety Science Journal,2013,23(4):45-50.(in Chinese)
[10]李建刚,白润才,刘光伟,等.露天矿行车事故频次的灰色预测[J].辽宁工程技术大学学报(自然科学版),2005,24(z1):6-8.LI Jiangang,BAI Runcai,LIU Guangwei,et al.Grey forecast of travel accident frequency in open-pit mine[J].Journal of Liaoning Technical University(Natural Science Edition),2005,24(z1):6-8.(in Chinese)
[11]付华,訾海,孟祥云,等.一种EKF-WLS-SVR与混沌时间序列分析的瓦斯动态预测新方法[J].传感技术学报,2015,28(1):126-131.FU Hua,ZI Hai,MENG Xiangyun,et al.A new method of mine gas dynamic prediction based on EKF-WLS-SVR and chaotic time series analysis[J].Chinese Journal of Sensors and Actuators,2015,28(1):126-131.(in Chinese)
[12]Schuldt C,Laptev I,Caputo B.Recognizing human actions:alocal SVM approach[C]∥Proceedings of the 17th International Conference on Pattern Recognition,2004.ICPR 2004,26-26Aug 2004.Cambridge,UK,2004:32-36.
[13]Cherkassky V,Ma Y Q.Practical selection of SVM parameters and noise estimation for SVM regression[J].Neural Networks,2004,17(1):113-126.
[14]Zioutas G,Avramidis A.Deleting outliers in robust regression with mixed integer programming[J].Acta Mathematicae Applicatae Sinica,English Series,2005,21(2):323-334.
[15]Zioutas G,Avramidis A,Pitsoulis L.Penalized trimmed squares and a modification of support vectors for unmasking outliers in linear regression[J].REVSTAT,2007,5(1):115-136.
[16]Zioutas G,Pitsoulis L,Avramidis A.Quadratic mixed integer programming and support vectors for deleting outliers in robust regression[J].Annals of Operations Research,2009,166(1):339-353.
[17]Avramidis A,Zioutas G.Locally and globally robust penalized trimmed squares regression[J].Simulation Modelling Practice and Theory,2011,19(1):148-160.
[18]王少群,张晓明.高速公路交通事故概率预测方法研究[J].价值工程,2014,33(13):67-68.WANG Shaoqun,ZHANG Xiaoming.Probability forecast method for freeway traffic accidents[J].Value Engineering,2014,33(13):67-68.(in Chinese)
[19]Tsuang M T,Boor M,Fleming J A.Psychiatric aspects of traffic accidents[J].AmericanJournal of Psychiatry,1985,142(5):538-546.
[20]张军,杨维平,杨立功,等.模糊综合评判在露天矿安全评价中的应用[J].安全与环境学报,2011,11(6):259-263.ZHANG Jun,YANG Weiping,YANG Ligong,et al.Comprehensive fuzzy evaluation method and its application to the open-air mine safety forecasting[J].Journal of Safety and Environment,2011,11(6):259-263.(in Chinese)
[21]贾水库.大型露天矿运输安全控制与预警系统[J].北京科技大学学报,2009,31(5):542-546.JIA Shuiku.Pre-warning and control system of transport safety in alarge-scale surface mine[J].Journal of University of Science and Technology Beijing,2009,31(5):542-546.(in Chinese)
[22]Brown S D.Book reviews:introduction to multivariate statistical analysis inchemometrics[J].Applied Spectroscopy,2010,64(4):112A.
[23]Egeren L F.Multivariate statistical analysis[J].Psychophysiology,1973,10(5):517-532.
[2]周荣义,钟岸,任竞舟,等.基于主成分分析和神经网络的事故预测方法及应用[J].中国安全科学学报,2013,23(7):55-60.ZHOU Rongyi,ZHONG An,REN Jingzhou,et al.An accident forecasting method of ANN based on PCA and its application[J].China Safety Science Journal,2013,23(7):55-60.(in Chinese)
[3]李明洋,姜福川.基于最小二乘法的灰色GM(1,1)改进模型在非煤矿山事故预测中的应用[J].中国安全生产科学技术,2013,9(11):83-90.LI Mingyang,JIANG Fuchuan.Improved gray GM(1,1)model in the non-coal mine accident prediction based on the methed of least square[J].Journal of Safety Science and Technology,2013,9(11):83-90.(in Chinese)
[4]顾晓叶,于殿宝,朱玉生,等.事故预测数学模型的研究与实践[J].中国安全科学学报,2009,19(12):23-27,204.GU Xiaoye,YU Dianbao,ZHU Yusheng,et al.Research and practice of accident prediction mathematicalmodels[J].China Safety Science Journal,2009,19(12):23-27,204.(in Chinese)
[5]孙轶轩,邵春福,计寻,等.基于ARIMA与信息粒化SVR组合模型的交通事故时序预测[J].清华大学学报(自然科学版),2014,54(3):348-353,359.SUN Yixuan,SHAO Chunfu,JI Xun,et al.Urban traffic accident time series prediction model based on combination of ARIMA and information granulation SVR[J].Journal of Tsinghua University(ScienceandTechnology),2014,54(3):348-353,359.(in Chinese)
[6]赵玲,许宏科,程鸿亮.基于最优加权组合模型的道路交通事故预测[J].计算机工程与应用,2013,49(24):11-15.ZHAO Ling,XU Hongke,CHENG Hongliang.Road traffic accidents prediction based on optimal weighted combinedmodel[J].Computer Engineering and Applications,2013,49(24):11-15.(in Chinese)
[7]彭小玲.支持向量机技术在海上船舶交通事故预测中的应用[J].舰船科学技术,2018,40(2):55-57.PENG Xiaoling.Research on ship traffic accident prediction using state vector machine[J].Ship Science and Technology,2018,40(2):55-57.(in Chinese)
[8]宋传平,王鹏飞,李涛.基于GM(1,1)模型的军用车辆交通事故预测研究[J].中国安全科学学报,2010,20(11):52-55.SONG Chuanping,WANG Pengfei,LI Tao.Forecast of military vehicle traffic accidents based on GM(1,1)model[J].China Safety Science Journal,2010,20(11):52-55.(in Chinese)
[9]朱志洁,张宏伟,韩军,等.基于PCA-BP神经网络的煤与瓦斯突出预测研究[J].中国安全科学学报,2013,23(4):45-50.ZHU Zhijie,ZHANG Hongwei,HAN Jun,et al.Prediction of coal and gas outburst based on PCA-BP neural network[J].China Safety Science Journal,2013,23(4):45-50.(in Chinese)
[10]李建刚,白润才,刘光伟,等.露天矿行车事故频次的灰色预测[J].辽宁工程技术大学学报(自然科学版),2005,24(z1):6-8.LI Jiangang,BAI Runcai,LIU Guangwei,et al.Grey forecast of travel accident frequency in open-pit mine[J].Journal of Liaoning Technical University(Natural Science Edition),2005,24(z1):6-8.(in Chinese)
[11]付华,訾海,孟祥云,等.一种EKF-WLS-SVR与混沌时间序列分析的瓦斯动态预测新方法[J].传感技术学报,2015,28(1):126-131.FU Hua,ZI Hai,MENG Xiangyun,et al.A new method of mine gas dynamic prediction based on EKF-WLS-SVR and chaotic time series analysis[J].Chinese Journal of Sensors and Actuators,2015,28(1):126-131.(in Chinese)
[12]Schuldt C,Laptev I,Caputo B.Recognizing human actions:alocal SVM approach[C]∥Proceedings of the 17th International Conference on Pattern Recognition,2004.ICPR 2004,26-26Aug 2004.Cambridge,UK,2004:32-36.
[13]Cherkassky V,Ma Y Q.Practical selection of SVM parameters and noise estimation for SVM regression[J].Neural Networks,2004,17(1):113-126.
[14]Zioutas G,Avramidis A.Deleting outliers in robust regression with mixed integer programming[J].Acta Mathematicae Applicatae Sinica,English Series,2005,21(2):323-334.
[15]Zioutas G,Avramidis A,Pitsoulis L.Penalized trimmed squares and a modification of support vectors for unmasking outliers in linear regression[J].REVSTAT,2007,5(1):115-136.
[16]Zioutas G,Pitsoulis L,Avramidis A.Quadratic mixed integer programming and support vectors for deleting outliers in robust regression[J].Annals of Operations Research,2009,166(1):339-353.
[17]Avramidis A,Zioutas G.Locally and globally robust penalized trimmed squares regression[J].Simulation Modelling Practice and Theory,2011,19(1):148-160.
[18]王少群,张晓明.高速公路交通事故概率预测方法研究[J].价值工程,2014,33(13):67-68.WANG Shaoqun,ZHANG Xiaoming.Probability forecast method for freeway traffic accidents[J].Value Engineering,2014,33(13):67-68.(in Chinese)
[19]Tsuang M T,Boor M,Fleming J A.Psychiatric aspects of traffic accidents[J].AmericanJournal of Psychiatry,1985,142(5):538-546.
[20]张军,杨维平,杨立功,等.模糊综合评判在露天矿安全评价中的应用[J].安全与环境学报,2011,11(6):259-263.ZHANG Jun,YANG Weiping,YANG Ligong,et al.Comprehensive fuzzy evaluation method and its application to the open-air mine safety forecasting[J].Journal of Safety and Environment,2011,11(6):259-263.(in Chinese)
[21]贾水库.大型露天矿运输安全控制与预警系统[J].北京科技大学学报,2009,31(5):542-546.JIA Shuiku.Pre-warning and control system of transport safety in alarge-scale surface mine[J].Journal of University of Science and Technology Beijing,2009,31(5):542-546.(in Chinese)
[22]Brown S D.Book reviews:introduction to multivariate statistical analysis inchemometrics[J].Applied Spectroscopy,2010,64(4):112A.
[23]Egeren L F.Multivariate statistical analysis[J].Psychophysiology,1973,10(5):517-532.