基于动态粗糙集和支持向量机的振动参量预报

为了有效控制爆破振动效应，基于粗糙集和支持向量机，建立了爆破振动参量的预报模型。该模型首先在粗糙集理论指导下利用粒子群算法快速实现属性的动态离散过程，再根据最优粒子建立决策表，通过重要度分析进行次要属性和冗余数据剔除，最后用支持向量机训练余下数据和验证新样本。经工程试验验证，该模型能够同时分析定量因素和孔径、抛掷方向等定性参量对质点振动加速度峰值的重要程度，约简之后的数据有利于支持向量机预报精度的提高。

Prediction of blasting vibration parameter based on rough set with dynamic discretization and support vector machine

Rough set theory (RS) can mine useful information from a large number of data and generate decision rules without prior knowledge. support vector machines (SVM) have good classification performances and good capabilities of fault-tolerance and generalization.To effectively control blasting vibration effect, a prediction model of the blasting vibration parameters based on Rough Sets and Support Vector Machines was established. Particle Swarm algorithm (PS) makes come true the dynamically discrete process of attributes. According to the decision table by the optimal particle, less important attributes and data were reduced, then SVM was trained and established for prediction. The model can analyze the important degree of both quantitative and qualitative factors such as hole diameter and cast direction to peak vibration acceleration value, and the improvement of prediction accuracy is verified by testing data.