优化的GEP算法在爆破振动预测中的应用

摘要

Based on Principal Component Analysis and Gene Expression Programming, an optimum GEP algorithm is proposed and applied in the prediction of blasting vibration peak value and main frequency. In this algorithm, PCA method is used to preprocess the input data, the correlation among the inputs is eliminated, and then GEP is applied to construct the prediction model. The experiment results show that this algorithm is more accurate and stable than existing prediction algorithms.%结合主成分分析和基因表达式编程，提出了一种基于PCA的优化基因表达式编程的新算法，并将其应用在爆破振动峰值速度和主频率的预测。该算法首先利用主成份分析方法对影响爆破振动的参数进行预处理，有效地减少预测模型的输入量，消除输入数据间的相关性，而后通过基因表达式程序设计建立爆破振动预测模型。结果表明，基于PCA的优化基因表达式编程算法比BP神经网络等其他算法得到的结果具有更高的预测精度和稳定性。