摘要
为提高冲击地压预测的效率和准确率,在分析冲击地压影响因素的基础上,提出了一种将遗传算法(GA)与极限学习机(ELM)相结合的冲击地压预测的新方法。为了避免ELM受输入权值矩阵和隐含层偏差随机性的影响,算法采用GA对ELM的输入权值矩阵和隐含层偏差进行优化,建立GA-ELM冲击地压预测模型。利用某矿冲击地压统计数据对该模型进行了实例分析,将ELM、SVM和BP算法预测结果与该模型进行了对比分析。结果表明:GA-ELM模型具有较高的预测精度,可以相对准确、有效地对冲击地压发生的可能性进行预测。
In order to improve the efficiency and accuracy of rock burst prediction , a new method combining ex-treme learning machine （ ELM） and genetic algorithm （ GA） for rock burst prediction was proposed based on analy-zing the influencing factors of rock burst .In order to avoid the influence on predicting effect of ELM by the random-ness of input weight matrix and hidden layer deviation , GA was used to optimize the input weight matrix and hidden layer deviation , and the GA-ELM model for rock burst prediction was built .Case analysis was made using statisti-cal data of a coal mine , and the prediction result was compared with ELM , SVM and BP .The results showed that the prediction on possibility of rock burst by GA-ELM model can be relatively accurate and effective .
出处
《中国安全生产科学技术》
CAS
CSCD
2014年第8期46-51,共6页
Journal of Safety Science and Technology
基金
国家自然科学基金项目(51274117)
