Phase partition and identification based on kernel entropy component analysis and multi-class support vector machines-fireworks algorithm for multi-phase batch process fault diagnosis

Abstract

For the characteristics of nonlinear and multi-phase in the batch process, a self-adaptive multi-phase batch process fault diagnosis method is proposed in this paper. Firstly, kernel entropy component analysis (KECA) method is used to achieve multi-phase partition adaptively, which makes the process data mapped into the high-dimensional feature space and then constructs the core entropy and the angular structure similarity. Then a multi-phase KECA failure monitoring model is developed by using the angular structure similarity as the statistic, which is based on the partitioned phases and the effective failure features by the KECA feature extraction method. A multi-phase batch process fault diagnosis method, which applies the multi-class support vector machines (MSVM) and fireworks algorithm (FWA), is proposed to recognize each sub-phase fault diagnosis automatically. The effectiveness and advantages of the proposed multi-phase fault diagnosis method are illustrated with a case study on a fed-batch penicillin fermentation process.

Online Monitoring of Penicillin Manufacture Based on Production Variables and Metabolic Fluxes

“…The kernel PCA (KPCA) and multiway kernel PCA (MKPCA) methods have been proposed for the nonlinear time-varying process of the beer manufacturing process . Furthermore, considering nonlinear and multistage characteristics of the batch process, a multiclass support vector machine (MSVM) was proposed to realize the automatic identification of faults in substages …”

“…14 Furthermore, considering nonlinear and multistage characteristics of the batch process, a multiclass support vector machine (MSVM) was proposed to realize the automatic identification of faults in substages. 15 T h i s c o n t e n t i s To summarize, all of the above monitoring methods for the microbial manufacturing process only use macroscopic models and production variables. Whether model-based or data-driven, existing methods ignore metabolic mechanisms and internal variables.…”

Fault monitoring of batch process based on multi-stage optimization regularized neighborhood preserving embedding algorithm

“…At present, as the complexity of the production process increases and the scale continues to expand, the production process also contains vast safety risks and the probability of faults continues to grow (Lavanya et al, 2021; Prasanth, 2021). Therefore, real-time monitoring of process ensures that faults can be detected timely, and accurate fault detection has essential economic value and practical significance (Fu and Zhang, 2017; Jiang et al, 2020; Zhang et al, 2018, 2019, 2020).…”