非线性定标方法在炉渣成分分析中的应用

采用激光诱导击穿光谱技术对炉渣中的Ca、Mg含量进行了定量分析。由于炉渣成分复杂，建立的一元回归关系式往往得不到理想的结果，这时需要考虑多个自变量的回归分析问题。为了分析炉渣中Ca、Mg元素的含量，将炉渣中Mg、Ca、Fe、Si、Al的原子谱线强度以及Mg、Ca的离子谱线强度作为输入向量。由于不同谱线强度相差过大时，会使在计算出的权重系数中，不同谱线所占的比重大不相同。为了消除不同谱线强度差距过大的影响，对光谱强度进行标准化处理，把所有谱线强度的值放在了一个相似的范围。综合对比分析了非线性多元函数定标、BP神经网络定标以及径向基网络（RBF神经网络）定标在炉渣成分分析中的作用，并重点分析了RBF神经网络定标相对于传统非线性定标方法的优势。

Application of non-linear calibration method in analysis of slag composition

Contents of Ca and Mg in the slag are analyzed quantitatively with laser-induced breakdown spectroscopy (LIBS). Due to the complexity of the slag composition a regression relationship established often fails to get the desired result，this results in that the problem of multiple variable regression analysis must be considered. In order to analyze the contents of Ca and Mg in the slag, the Mg, Ca, Fe, Si, Al atomic line intensity and Mg, and Ca ion line intensity are used as the input vectors. However, when the absolute line intensity including strong spectral lines and weaker spectral lines are put together as the input vector, the influence of the former will cover up the latter. o spectral intensity needs treated first to place all the values of the line intensities in a similar range. The slag composition analysis are then performed and compared using three calibration methods like nonlinear multi-function，BP neural network and radial basis function (RBF) network. In addition, the advantage of the RBF neural network calibration relative to traditional non-linear calibration method is particularly emphasized.