摘要
研究并建立矿区地表下沉系数的智能预测模型。将粒子群优化(PSO)和回归支持向量机(SVM)方法进行融合。采用PSO算法优化SVM回归估计参数,在简要分析影响地表下沉因素的基础上,建立了基于PSO优化参数的SVM(PSO-SVM)矿区地表下沉系数智能预测模型。以我国典型的地表移动观测站资料作为学习训练样本和测试样本,将计算结果与实际值进行了对比分析,并与改进BP神经网络算法的预测结果进行了比较。结果表明:PSO-SVM方法计算地表下沉系数是可行的,收敛速度更快,计算精度更高。为地表下沉系数的计算探索了一种可行的方法。
In order to investigate and construct an intelligent model for calculating surface subsidence coefficients in mining areas, a new method by combining particle swarm optimization algorithm （PSO） and support vector machine （SVM） regression method is presented, In this method, the PSO algorithm is used to optimize the parameters of SVM regression. An intelligent calculation model for surface subsidence coefficient using this hybrid PSO-SVM algorithm is constructed based on the analysis of impact factors. Typical data of surface moving observation stations is used as learning and test samples. Comparison analysis is made between calculated values generated by PSO-SVM method and observed values, and the performance of the proposed method is also compared to that of improved BP neural network. Results indicate that PSO-SVM calculation model has higher precision. A new calculation method for surface subsidence coefficient in mining areas is provided.
出处
《辽宁工程技术大学学报（自然科学版）》
CAS
北大核心
2008年第3期365-367,共3页
Journal of Liaoning Technical University (Natural Science)
基金
国家自然科学基金资助项目(50471046)
关键词
地表下沉系数
粒子群优化
支持向量机
回归
surface subsidence coefficient
particle swarm optimization
support vector machine
regression
