Search

Actual industrial processes often exhibit multimodal characteristics, and their data exhibit complex features, such as being dynamic, nonlinear, multimodal, and strongly coupled. Although many modeling approaches for process fault monitoring have been proposed in academia, due to the complexity of industrial data, challenges remain. Based on the concept of multimodal modeling, this paper proposes a multimodal process monitoring method based on the variable-length sliding window-mean augmented Dickey-Fuller (VLSW-MADF) test and dynamic locality-preserving principal component analysis (DLPPCA). In the offline stage, considering the fluctuation characteristics of data, the trend variables of data are extracted and input into VLSW-MADF for modal identification, and different modalities are modeled separately using DLPPCA. In the online monitoring phase, the previous moment's historical modal information is fully utilized, and modal identification is performed only when necessary to reduce computational cost. Finally, the proposed method is validated to be accurate and effective for modal identification, modeling, and online monitoring of multimodal processes in TE simulation and actual plant data. The proposed method improves the fault detection rate of multimodal process fault monitoring by about 14% compared to the classical DPCA method.

To establish the fingerprints of Xiasangju granules (with sugar and non-sugar forms) by HPLC, and provide reference for their identification and effective quality control. High performance liquid chromatography (HPLC) method was used to collect the fingerprints of 20 batches of non-sugar Xiasangju granules and 34 batches of sugar type Xiasangju granules. Their main different components were classified and screened by mode identification methods (principal component analysis, PCA, and orthogonal partial least squares discriminate analysis, OPLS-DA). The principal components were identified by comparing with reference standards. The fingerprints of Xiasangju granules (sugar type and non-sugar type) were established. PCA could not fully classify the two types of granules, while OPLS-DA could obviously classify these two different types of Xiasangju granules. Six components showed greatest difference between two types of granules, including salviaflaside, luteoloside and linarin. The developed mode identification method is helpful to control the overall quality of Xiasangju granules, and it provides an effective approach to quality evaluation., Competing Interests: The authors of this article and the planning committee members and staff have no relevant financial relationships with commercial interests to disclose., (Copyright© by the Chinese Pharmaceutical Association.)