基于PSO-LSSVM的水松纸透气度软测量

Soft sensing of the tipping paper porosity based on PSO-LSSVM

针对打孔水松纸透气度检测问题,考虑到样本数据较少,相关性较强等因素,提出一种基于粒子群优化(Particle Swarm Optimization,PSO)算法优化最小二乘支持向量机(Least Squares Support Vector Machine,LSSVM)关键参数的软测量模型(PSO-LSSVM),用于拟合孔面积与水松纸透气度之间的关系,从而实现对水松纸透气度的检测。基于实际生产数据的仿真实验和算法比较验证了PSO-LSSVM的有效性。

For the problem of detection of tipping paper porosity testing, considering that the number of sample data is not enough and the correlation of sample data is strong, we put forward a soft Sensing model that optimizes key parameters of Least Squares Support Vector Machine（LSSVM） based on Particle Swarm Optimization（PSO）. This model fits the relationship of the area of hole and the tipping paper porosity to test porosity. Based on simulation experiments and comparing algorithm of actual production data, it is proved that the PSO-LSSVM is effective.