A Batch Process Monitoring Method Using Two-Dimensional Localized Dynamic Support Vector Data Description

Abstract

In order to mine the local behavior and dynamic characteristic of batch process data for effective process monitoring, a two-dimensional localized dynamic support vector data description (TLDSVDD) method is proposed in this paper. The main contributions of the proposed method include three aspects. Firstly, considering that batch process variables may behave differently at each operation stage, a two-dimensional localization strategy is designed to mine the local behaviors of process data from the perspective of the variable dimension and the sample dimension. Secondly, for each local data segment, the slow feature analysis is applied to build the local dynamic sub-models, which can monitor the static and dynamic process changes simultaneously. Lastly, the model ensemble strategy based on Bayesian inference is employed and two holistic monitoring statistics are developed to indicate the process running status. The proposed method not only extracts the local process behaviors, but also determines whether the process fault belongs to the dynamic or static change. Finally, one case study on the simulated industrial batch process is carried out to exhibit the method performance.

Dynamic Batch Process Monitoring Based on Time-Slice Latent Variable Correlation Analysis

“…To deal with process dynamics, various dynamic process monitoring methods were proposed. − For dynamic batch processes, multiway dynamic monitoring methods were proposed, , among which dynamic MPCA, dynamic MPLS, and dynamic CCA methods are the most extensively used. , In order to mine dynamic characteristic of the batch process, a two-dimensional localized dynamic support vector data description method is proposed, and this method also mines the local behavior of process data well . In dynamic monitoring methods, the correlation in the time series is explored.…”

“… 23 , 24 In order to mine dynamic characteristic of the batch process, a two-dimensional localized dynamic support vector data description method is proposed, and this method also mines the local behavior of process data well. 25 In dynamic monitoring methods, the correlation in the time series is explored. To characterize the correlation in both the time and batch directions, two-dimensional monitoring models such as two-dimensional dynamic PCA and PLS were developed.…”