基于信息增量矩阵的多阶段间歇过程质量预测

针对间歇过程划分阶段方法很少考虑过程的时序性和动态特性，易将时间上不连续但具有相似特征的样本划分到同一阶段，影响建模精确性的问题，提出一种基于信息增量矩阵-偏最小二乘（information increment matrix-partial least square，ⅡMPLS）的多阶段间歇过程质量预测方法。将历史三维数据沿批次方向展开为二维数据，将其切分成融合质量变量的扩展时间片，依据扩展时间片的信息增量使用滑动窗划分阶段，对各个阶段内数据建立PLS模型进行质量预测。该方法考虑变量之间的相关关系沿采样时刻的变化，利用信息增量捕获系统的动态特性并时序地划分阶段。青霉素仿真平台与大肠杆菌实际生产数据验证了方法的可行性和有效性。

Information increment matrix based quality prediction for multi-phase batch processes

A sequential quality prediction algorithm based on information increment matrix is proposed for multi-phase batch processes. It can overcome the limits of some phase partition algorithms, which cannot cope with the sequence and dynamics of the processes and may inevitably divide the samples with discontinuous time sequence but similar characteristics into the same phase. First, the 3D data is transformed into 2D data by batch-wise unfolding and splitted into extended time slices that equipped with quality variables. Then a sliding window is used to divide the sub-phases according to information increment of extended time slices. PLS models of each sub-phase constitute the global quality prediction strategy. The proposed algorithm takes the correlations among variables into consideration and uses information increment to capture the dynamics. The feasibility and effectiveness of the proposed algorithm are illustrated by a penicillin simulation platform and an industrial application of E. coli fermentation, respectively.