摘要
为提高单一BP神经网络预测精度,利用AdaBoost.R2集成学习算法,将单一BP(Back-Propagation)神经网络集成,并针对AdaBoost.R2集成BP网络的特点,提出了一种新的模型更新方法,在有效地实现模型更新的同时克服了传统更新方法的不足。将该新方法应用到抚顺老虎台矿冲击地压预报中,对冲击地压发生的主要因素进行了分析并将其作为模型的输入,使用AdaBoost.R2集成BP网络作为核心智能算法,建立了冲击地压预报模型,取得了较好的预测效果。
Aiming at the disadvantages of single BP net work, presented by using AdaBoost. R2 for improving the prediction an ensemble BP （Back- accuracy of single BP net work. A new updating method is proposed for the characters of ensemble BP net work based on AdaBoost. R2. The new method can update the model effectively and overcome the disadvantage of traditional updating methods. The new methods are used to predict the rock burst in Fushun Laohutai mine. The main influence factors for rock burst are analyzing detailed and used as the inputs of prediction model. The ensemble BP net work based on AdaBoost. R2 is used as intelligent algorithm. The prediction model for rock burst predicting has a good prediction accuracy.
出处
《吉林大学学报（信息科学版）》
CAS
2009年第1期79-84,共6页
Journal of Jilin University（Information Science Edition）
基金
吉林省科技发展计划基金资助项目(20040803)
