A dynamic CNN for nonlinear dynamic feature learning in soft sensor modeling of industrial process data

Hierarchical local nonlinear dynamic feature learning is of great importance for soft sensor modeling in process industry. Convolutional neural network (CNN) is an excellent local feature extractor that is suitable for process data representation. In this paper, a dynamic CNN (DCNN) strategy is desi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Control engineering practice Ročník 104; s. 104614
Hlavní autoři: Yuan, Xiaofeng, Qi, Shuaibin, Wang, Yalin, Xia, Haibing
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.11.2020
Témata:
Convolutional Neural Network (CNN)
Deep learning
Quality prediction
Soft sensor
Deep learning
Soft sensor
Quality prediction
Convolutional Neural Network (CNN)
ISSN:0967-0661
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Hierarchical local nonlinear dynamic feature learning is of great importance for soft sensor modeling in process industry. Convolutional neural network (CNN) is an excellent local feature extractor that is suitable for process data representation. In this paper, a dynamic CNN (DCNN) strategy is designed to learn hierarchical local nonlinear dynamic features for soft sensor modeling. In DCNN, each 1D process sample is dynamically augmented into 2D data sample with lagged unlabeled process variables, which contains both spatial cross-correlations and temporal auto-correlations. Then, the convolutional and pooling layers are alternately utilized to extract the local nonlinear spatial–temporal feature from the 2D sample data matrix. Moreover, the principle is analyzed for DCNN on how it can learn the local nonlinear spatial–temporal feature from the network. The effectiveness of proposed DCNN is verified on an industrial hydrocracking process.
ISSN:0967-0661
DOI:10.1016/j.conengprac.2020.104614