摘要：

针对过程监控数据的非线性特点，提出了一种基于核偏最小二乘（KPLS）的监控方法。KPLS方法是将原始输入数据通过核函数映射到高维特征空间，然后在高维特征空间再进行偏最小二乘（PLS）运算。与线性PLS相比，KPLS方法能充分利用样本空间信息，建立起输入输出变量之间的非线性关系。与其他非线性PLS方法不同，KPLS方法只需要进行线性运算，从而避免非线性优化问题。在对过程进行监控时，首先采用KPLS方法建立模型，得到得分向量，然后计算出T²和SPE统计量及其相应的控制限。Tennessee Eastman(TE)模型上的仿真研究结果表明，所提方法比线性PLS

Abstract:

To handle the nonlinear problem for process monitoring, a new technique based on kernel partial least squares(KPLS)is developed.KPLS is an improved partial least squares(PLS)method, and its main idea is to first map the input space into a high-dimensional feature space via a nonlinear kernel function and then to use the standard PLS in that feature space.Compared to linear PLS, KPLS can make full use of the sample space information, and effectively capture the nonlinear relationship between input variables and output variables.Different from other nonlinear PLS, KPLS requires only linear algebra and does not involve any nonlinear optimization.For process data, firstly KPLS was used to derive regression model and got the score vectors, and then two statistics, T² and SPE, and corresponding control limits were calculated.A case study of the Tennessee-Eastman(TE)process illustrated that the proposed approach showed superior process monitoring performance compared to linear PLS.