期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 33, 期 12, 页码 7682-7694出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2021.3086323
关键词
Nonlinear dynamical systems; Kernel; Process monitoring; Principal component analysis; State-space methods; Recurrent neural networks; Fault detection; Deep learning; dynamics; fault detection; nonlinear state-space models
类别
资金
- Young Scientists Fund of the National Natural Science Foundation of China [62003373]
- National Natural Science Foundation of China [U1911401]
- Ministry of Science and Technology, Taiwan, R.O.C. [MOST 109-2221-E-033-013-MY3]
The proposed process monitoring model uses deep neural networks to effectively handle the complexities of nonlinearity, dynamics, and uncertainties, outperforming other comparative methods by at least 10% in industrial experimental data.
Process complexities are characterized by strong nonlinearities, dynamics, and uncertainties. Monitoring such a complex process requires a high-quality model describing the corresponding nonlinear dynamic behavior. The proposed model is constructed using deep neural networks (DNNs) to represent the state transition and observation generation, both of which constitute a stochastic nonlinear state-space model. A new bidirectional recurrent neural network (RNN), creating a connection of the hidden layer between a forward RNN and a backward RNN, is proposed to generate the filtering estimation and the smoothing estimation of process states which further generate observations with DNN-based process models. The smoothing estimator and the process model are first learned offline with all collected samples. Then the filtering estimator is fine-tuned by the learned smoother and process models to achieve real-time monitoring since the filter state is estimated based on the past and the current observations. Two indices are designed based on the learned model for monitoring the process anomaly. The proposed process monitoring model can deal with complex nonlinearities, process dynamics, and process uncertainties, all of which can be very challenging for the existing methods, such as kernel mapping and stacked auto-encoder. Two case studies validate that the effectiveness of the proposed method outperforms the other comparative methods by at least 10% when using the averaged fault detection rate in the industrial experimental data.
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