Chao Shang

Novel Bayesian Framework for Dynamic Soft Sensor Based on Support Vector Machine With Finite Impulse Response

Conventional data-driven soft sensors commonly rely on the assumption that processes are operating at steady states. As chemical processes involve evident dynamics, conventional soft sensors may suffer from transient inaccuracy and poor robustness. In addition, the control performance is unsatisfactory when the outputs of soft sensors serve as the feedback signals for quality control. This brief develops a dynamic soft-sensing model combining finite impulse response and support vector machine to describe dynamic and nonlinear static relationships. The model parameters are then estimated within a Bayesian framework. The results from both the simulated and the industrial case show its superiority to conventional static models in terms of dynamic accuracy and practical applicability.

Extracting latent dynamics from process data for quality prediction and performance assessment via slow feature regression

Latent variable (LV) models such as partial least squares (PLS) have been widely used to derive low-dimensional subspaces and build regression models in process control problems, especially in quality prediction tasks. However, they are based on the assumption that industrial processes operate at steady states, thereby ignoring process dynamics. In this article, slow feature regression (SFR), a novel linear regression model with LV subspaces, is proposed, which consists of two steps. In the first step, slow features as LVs are extracted via slow feature analysis (SFA), a rising machine learning methodology. Different from classical LV models, SFA assumes LVs have slowly varying dynamics, which can be derived by analyzing the temporal structure within abundant process data. Owing to evident dynamics in industrial processes, slowness can be considered as a valid prior knowledge to utilize. In the second step, the slowest features are selected as a reasonable description of processes to further predict the product quality, which is also likely to be slowly varying. In addition to the Hotellings T2 statistic, a novel S2 index is proposed to evaluate the dynamic variations within processes and assess the real-time performance of the prediction model. The effectiveness of the SFR-based approach is demonstrated through an application in the Tennessee Eastman process.

Robust Proportional–Integral–Derivative (PID) Design for Parameter Uncertain Second-Order Plus Time Delay (SOPTD) Processes Based on Reference Model Approximation

To design robust PID controllers for second-order plus time delay (SOPTD) processes with parameter uncertainty, a reference model approximation method is proposed in this study. The central idea is to enable the frequency response of the PID controller to approximate that of a user-specified reference model. A convex hull is utilized to approximate the frequency template of the parameter uncertain process, and the maximum approximation error of the reference model among all candidate processes is bounded. To guarantee that the PID controller can well shape the closed-loop response of each candidate model to the reference model, a convex optimization problem is formulated to compute the PID parameters by minimizing the upper bound of the approximation error. Constraints on the closed-loop maximum sensitivity peak are imposed on the reference-model approximation problem for loop robustness. The proposed method is able to ensure balanced tracking performance and * Corresponding author at: Department of Automation, Tsinghua University, E-mail address: huangdx@tsinghua.edu.cn. 2 disturbance rejection performance through a proper specification of the reference model, and illustrative examples are presented to demonstrate the applicability.

Detecting and isolating plant-wide oscillations via slow feature analysis

This paper aims at detecting and isolating multiple sources of oscillations in control loops via slow feature analysis. The control loops in the process industries are usually coupled, and therefore disturbances can propagate to downstream process variables through energy or material flows and thus plant-wide disturbances arise. A significant portion of disturbances are oscillatory, and the root causes may be poor controller design or equipment faults such as valve stiction. It is important to find out locations of these oscillation sources so that further root cause diagnosis is possible. A new technique termed as slow feature analysis (SFA) is applied to detect plant-wide oscillations and isolate the sources at the loop level. SFA can recover slowly varying source signals from observed data. Since most oscillations in the process industries have low oscillatory frequencies, SFA is a very powerful tool to recover oscillation sources from observed process data. Two projection-based indices, CCI and CSI, are derived to investigate how the control loops are affected by the oscillations and isolate oscillation sources at the loop level. A simulation case study is presented to demonstrate the effectiveness of the proposed method.