Deep neural network based recursive feature learning for nonlinear dynamic process monitoring

Abstract

The data collected from modern industrial processes always have nonlinear and dynamic characteristics. The recently developed deep neural network method, stacked denoising auto‐encoder (SDAE), can extract robust nonlinear latent variables from data against noise. However, it leaves the dynamic relationship unconsidered. To solve this problem, a novel algorithm named the recursive stacked denoising auto‐encoder (RSDAE) is proposed. To learn the dynamic relationship, the RSDAE focuses on the predictability of the latent variables in the recurrence to contain the most dynamic variations. After the dynamic variations are extracted by the RSDAE, there is little autocorrelation left in the residuals. Then, the residuals can be monitored by principal component analysis (PCA). For the purpose of process monitoring, corresponding fault detection statistics are developed based on the RSDAE. Finally, a numerical case and the Tennessee Eastman process benchmark are used to demonstrate the effectiveness of the proposed algorithm.

Quality-Driven Autoencoder for Nonlinear Quality-Related and Process-Related Fault Detection Based on Least-Squares Regularization and Enhanced Statistics

“…To understand the process and implement control and monitoring strategies, two sets of variables, including 41 measurements (XMEAS (1)−(41)) and 11 analyzed components (XMV (1)−( 11)), are collected. More details about this process can be found in ref 34. In this study, XMEAS (1)− (22) and XMV (1)−( 11) are selected as the process variables (i.e.,x 1 ,x 2 , . .…”

Issue Highlights

“…The process can be monitored from three different aspects. [3] Effect of Substrate Geometry and Flow Condition on the Turbulence Generation After a Monolith Ivan Cornejo, Petr Nikrityuk, Robert E. Hayes Catalytic honeycomb substrates are modelled as a continuum to overcome computational limitations. That approach is quite convenient for systematic research; however, it requires the use of a series of source terms to account for the solid-fluid interactions.…”

“…For monitoring the dynamic and static performance of the system better, the original space is divided into dynamic principal space, static principal space, and the residual space. The process can be monitored from three different aspects …”

Temporal-Spatial Neighborhood Enhanced Sparse Autoencoder for Nonlinear Dynamic Process Monitoring

“…Stacked sparse autoencoders (SSAE) can build deep models by stacking multiple AEs to extract deeper and more important features from the data. For dealing with the nonlinear dynamic characteristics of the process, Zhu et al [16] proposed a recursive stacked denoising autoencoder (RSDAE) to extract nonlinear dynamic features and static features and successfully applied them to fault detection. Compared with the kernel method [17], which requires designing the kernel function artificially, the characteristics of deep neural network automatic learning parameters to extract features make it a popular method to deal with the problem of fault detection in nonlinear processes [18,19].…”