Multimode process monitoring based on hierarchical mode identification and stacked denoising autoencoder

•A novel hierarchical mode identification strategy is proposed for multimode process.•An improved density peaks clustering algorithm called LDRSDPC is presented for achieving the transition mode identification.•A decision criterion combined with local density relation is constructed to automatically...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Chemical engineering science Ročník 253; s. 117556
Hlavní autoři:	Gao, Huihui, Wei, Chen, Huang, Wenjie, Gao, Xuejin
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 18.05.2022
Témata:	Density peaks clustering Gaussian mixture model Industrial process Mode identification Multimode process monitoring Stacked denoising autoencoder Mode identification Multimode process monitoring Stacked denoising autoencoder Gaussian mixture model Density peaks clustering Industrial process
ISSN:	0009-2509
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	•A novel hierarchical mode identification strategy is proposed for multimode process.•An improved density peaks clustering algorithm called LDRSDPC is presented for achieving the transition mode identification.•A decision criterion combined with local density relation is constructed to automatically determine the clustering center.•A numerical example and Tennessee Eastman process simulations are carried out to demonstrate the effectiveness. In modern plants, industrial processes generally operate under different modes, and reliable monitoring for such processes is highly important. One of the key challenges is how to accurately identify the various modes including steady modes and transitions modes. In this paper, a novel monitoring scheme based on hierarchical mode identification strategy and stacked denoising autoencoder (HMI-SDAE) is proposed for multimode processes. First, a novel mode division strategy called HMI is presented. In HMI, the Gaussian mixture model (GMM) is adopted to realize the preliminary identification of various modes by extracting the global distribution features of the variables. In this way, the whole multimode process is divided into multiple steady modes. An improved density peaks clustering algorithm based on local density relation search (LDRSDPC) is proposed to achieve the transition mode identification by fully utilizing the local distribution features of the process variables involved in any two adjacent steady modes and transition mode between them. A decision criterion combined with local density relation is constructed to automatically determine the clustering center. In this hierarchical way, multiple steady modes and transition modes are divided automatically and accurately. Secondly, the deep nonlinear features embedded in process variables are mined by SDAE, and the robust monitoring model is established for each steady mode. A monitoring statistic is constructed using the reconstruction error for detecting faults. The effectiveness and feasibility of the proposed HMI-SDAE monitoring scheme are illustrated with a numerical example and Tennessee Eastman (TE) process.
ISSN:	0009-2509
DOI:	10.1016/j.ces.2022.117556