紫外光谱水质分析仪中的支持向量机方法

Support Vector Machine for Ultraviolet Spectroscopic Water Quality Analyzers

紫外光谱水质分析仪的一个关键技术是如何建立紫外光谱数据与有机污染物浓度之间的数学模型 ,以及提高模型的外推能力。本研究基于统计学习理论的支持向量机方法 ,提出了有机污染物浓度与紫外光谱数据的建模方法。该方法具有较强的推广能力和全局最优的特点 ,得到的数学模型的预测能力明显改善 ,从而提高了紫外光谱水质分析仪的测量精度。实验表明 :该方法优越于目前在紫外光谱水质分析仪中常规采用的偏最小二乘算法。

How to describe the correlation between the water quality parameter such as chemical oxygen demand (COD), biochemical oxygen demand (BOD), total organic carbon (TOC) and the ultraviolet (UV) spectroscopy is important for the UV water quality analyzers. A novel modeling method based on support vector machine (SVM) is proposed for UV water spectroscopic water quality analyzers in this paper. The estimating model obtained by this method shows obvious improvement in predicting ability and measurement accuracy. The experimental results show the proposed method has obvious advantage over the classical method such as partial least square.