摘要：AbstractMulti-block multivariate statistical methods have been developed to extract useful information from process and quality data in the era of big data, where process variables are partitioned into several meaningful blocks. However, most of these methods did not consider cross-correlations among divided blocks, which leads to inferior monitoring performance. In this article, a block-aware factorization machine (BAFM) algorithm is proposed to exploit information from process and quality data. In BAFM, quality data are first classified into normal and abnormal labels with principal component analysis based quality monitoring framework. Afterwards, a block number is attached to each process variable, and the interactions among different variables (both within and cross blocks) are learned through latent variables, which is supervised by the classified quality labels. Apart from the variable relation within the same block, BAFM also incorporates the block information; thus, both inner and cross correlations are constructed. The monitoring framework based on BAFM is developed, and its effectiveness and superiority are demonstrated through the Tennessee Eastman process.
