期刊
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH
卷 60, 期 1, 页码 387-398出版社
AMER CHEMICAL SOC
DOI: 10.1021/acs.iecr.0c02256
关键词
-
资金
- National Natural Science Foundation of China [61822308]
- Shandong Province Natural Science Foundation [JQ201812]
- Program for Entrepreneurial and Innovative Leading Talents of Qingdao [19-3-2-4-zhc]
The proposed Neural Component Analysis (NCA) combines artificial neural networks (ANN) with principal component analysis (PCA) to address the common nonlinearity in industrial processes. NCA, with a similar network structure as ANN and utilizing the gradient descent method for training, successfully extracts uncorrelated components from the process data with PCA's dimension reduction strategy, and constructs statistical indices for process monitoring, showing superior performance compared to other nonlinear approaches in simulation tests.
Nonlinearity is extremely common in industrial processes. For handling the nonlinearity problem, this paper combines artificial neural networks (ANN) with principal component analysis (PCA) and proposes a new neural component analysis (NCA). NCA has a similar network structure as ANN and adopts the gradient descent method for training, hence it has the same nonlinear fitting ability as ANN. Furthermore, NCA adopts PCA's dimension reduction strategy to extract the uncorrelated components from the process data and constructs statistical indices for process monitoring. The simulation test results show that NCA can successfully extract the uncorrelated components from the nonlinear process data, and it has better performance than other nonlinear approaches.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据