Wentao Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Wentao Tang has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Prodromos Daoutidis
Department of Chemical Engineering and Material Science University of Minnesota 55455 Minneapolis MN United States
6 shared publications - Ilias Mitrai
McKetta Department of Chemical Engineering The University of Texas at Austin Austin Texas USA
2 shared publications - Moritz Woelk2 shared publications
Prodromos Daoutidis
2 shared publicationsAndres Lizano‐Villalobos
Cain Department of Chemical Engineering Louisiana State University Baton Rouge Louisiana USA
1 shared publication- Andrew Allman
Department of Chemical Engineering University of Michigan Ann Arbor Michigan USA
1 shared publication
Latest Publications
- 27 October 2026
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 217
A constrained symbolic regression approach for Lyapunov function discovery
- 27 October 2026
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 217
A constrained symbolic regression approach for Lyapunov function discovery
- Open Access
- 25 April 2026
- Published by Elsevier in Journal of Process Control
- Vol. 163
Neural Luenberger state observer for nonautonomous nonlinear systems
- 25 April 2026
- Published by Elsevier in Journal of Process Control
- Vol. 163
Open AccessNeural Luenberger state observer for nonautonomous nonlinear systems
- 8 April 2026
- Published by Wiley in AIChE Journal
- Vol. 72 (7)
Machine learning‐based optimal control for colloidal self‐assembly
Achieving precise control of colloidal self‐assembly into specific patterns remains a longstanding challenge due to the complex process dynamics. Recently, machine learning‐based state representation and reinforcement learning‐based control strategies have started to accumulate popularity in the field, showing great potential as an automatable and generalizable approach to producing patterned colloidal assembly. In this work, we proposed a machine learning‐based optimal control framework, combining unsupervised learning and graph convolutional neural network for state representation with deep reinforcement learning‐based optimal control policy calculation, to provide a data‐driven control strategy that can potentially be generalized to other many‐body self‐assembly systems. With Brownian Dynamics simulations, we demonstrated its superior performance as compared to traditional order parameter‐based state description, and its efficacy in obtaining ordered two‐dimensional spherical colloidal self‐assembly in an electric field‐mediated system with an actual success rate of 97%.
- 8 April 2026
- Published by Wiley in AIChE Journal
- Vol. 72 (7)
Machine learning‐based optimal control for colloidal self‐assembly
Achieving precise control of colloidal self‐assembly into specific patterns remains a longstanding challenge due to the complex process dynamics. Recently, machine learning‐based state representation and reinforcement learning‐based control strategies have started to accumulate popularity in the field, showing great potential as an automatable and generalizable approach to producing patterned colloidal assembly. In this work, we proposed a machine learning‐based optimal control framework, combining unsupervised learning and graph convolutional neural network for state representation with deep reinforcement learning‐based optimal control policy calculation, to provide a data‐driven control strategy that can potentially be generalized to other many‐body self‐assembly systems. With Brownian Dynamics simulations, we demonstrated its superior performance as compared to traditional order parameter‐based state description, and its efficacy in obtaining ordered two‐dimensional spherical colloidal self‐assembly in an electric field‐mediated system with an actual success rate of 97%.
- Open Access
- 8 September 2025
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 204
Identification of noisy Koopman models
- 8 September 2025
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 204
Open AccessIdentification of noisy Koopman models
- Open Access
- 13 May 2025
- Published by Wiley in AIChE Journal
- Vol. 71 (8)
Process Resilience under Optimal Data Injection Attacks
In this article, we study the resilience of process systems in an information‐theoretic framework, from the perspective of an attacker capable of optimally constructing data injection attacks. The attack aims to distract the stationary distributions of process variables and stay stealthy, simultaneously. The problem is formulated as designing a multivariate Gaussian distribution to maximize the Kullback‐Leibler divergence between the stationary distributions of states and state estimates under attacks and without attacks, while minimizing that between the distributions of sensor measurements. When the attacker has limited access to sensors, sparse attacks are proposed by incorporating a sparsity constraint. We conduct theoretical analysis on the convexity of the attack construction problem and present a greedy algorithm, which enables systematic assessment of measurement vulnerability, thereby offering insights into the inherent resilience of process systems. We numerically evaluate the performance of proposed constructions on a two‐reactor process.
- 13 May 2025
- Published by Wiley in AIChE Journal
- Vol. 71 (8)
Open AccessProcess Resilience under Optimal Data Injection Attacks
In this article, we study the resilience of process systems in an information‐theoretic framework, from the perspective of an attacker capable of optimally constructing data injection attacks. The attack aims to distract the stationary distributions of process variables and stay stealthy, simultaneously. The problem is formulated as designing a multivariate Gaussian distribution to maximize the Kullback‐Leibler divergence between the stationary distributions of states and state estimates under attacks and without attacks, while minimizing that between the distributions of sensor measurements. When the attacker has limited access to sensors, sparse attacks are proposed by incorporating a sparsity constraint. We conduct theoretical analysis on the convexity of the attack construction problem and present a greedy algorithm, which enables systematic assessment of measurement vulnerability, thereby offering insights into the inherent resilience of process systems. We numerically evaluate the performance of proposed constructions on a two‐reactor process.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7277-7284
Optimal Design of Control-Lyapunov Functions by Semi-Infinite Stochastic Programming
Lyapunov-based control is a common method to enforce closed-loop stability of nonlinear systems, where the choice of a control-Lyapunov function has a strong impact on the resulting performance. In this paper, we propose a generic semi-infinite stochastic programming formulation for the optimal control-Lyapunov function design problem and discuss its various specializations. Specifically, the expected performance evaluated on simulated trajectories under different scenarios is optimized subject to infinite constraints on stability and performance specifications. A stochastic proximal primal-dual algorithm is introduced to find a stationary solution of such a semi-infinite stochastic programming problem. The proposed method is illustrated by a chemical reactor case study.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7277-7284
Optimal Design of Control-Lyapunov Functions by Semi-Infinite Stochastic Programming
Lyapunov-based control is a common method to enforce closed-loop stability of nonlinear systems, where the choice of a control-Lyapunov function has a strong impact on the resulting performance. In this paper, we propose a generic semi-infinite stochastic programming formulation for the optimal control-Lyapunov function design problem and discuss its various specializations. Specifically, the expected performance evaluated on simulated trajectories under different scenarios is optimized subject to infinite constraints on stability and performance specifications. A stochastic proximal primal-dual algorithm is introduced to find a stationary solution of such a semi-infinite stochastic programming problem. The proposed method is illustrated by a chemical reactor case study.
- 28 August 2023
- Published by Wiley in AIChE Journal
- Vol. 69 (12)
Data‐driven state observation for nonlinear systems based on online learning
For controlling nonlinear processes represented by state‐space models, a state observer is needed to estimate the states from the trajectories of measured variables. While model‐based observer synthesis is traditionally challenging due to the difficulty of solving pertinent partial differential equations, this article proposes an efficient model‐free, data‐driven approach for state observation, which is suitable for data‐driven nonlinear control without accurate nonlinear models. Specifically, by using a Chen–Fliess series representation of the observer dynamics, state observation is endowed with an online least squares regression formulation that can be solved by gradient flow with performance guarantees. When the target state trajectories for regression are unavailable, by exploiting the Kazantzis–Kravaris/Luenberger observer structure, state observation is reduced to a dimensionality reduction problem amenable to an online implementation of kernel principal component analysis. The proposed approach is demonstrated by a limit cycle dynamics and a chaotic system.
- 28 August 2023
- Published by Wiley in AIChE Journal
- Vol. 69 (12)
Data‐driven state observation for nonlinear systems based on online learning
For controlling nonlinear processes represented by state‐space models, a state observer is needed to estimate the states from the trajectories of measured variables. While model‐based observer synthesis is traditionally challenging due to the difficulty of solving pertinent partial differential equations, this article proposes an efficient model‐free, data‐driven approach for state observation, which is suitable for data‐driven nonlinear control without accurate nonlinear models. Specifically, by using a Chen–Fliess series representation of the observer dynamics, state observation is endowed with an online least squares regression formulation that can be solved by gradient flow with performance guarantees. When the target state trajectories for regression are unavailable, by exploiting the Kazantzis–Kravaris/Luenberger observer structure, state observation is reduced to a dimensionality reduction problem amenable to an online implementation of kernel principal component analysis. The proposed approach is demonstrated by a limit cycle dynamics and a chaotic system.
- Open Access
- 10 May 2023
- Published by Wiley
Data-Driven State Observation for Nonlinear Systems based on Online Learning
This paper considers the problem of state observation for nonlinear dynamics. While model-based observer synthesis is difficult due to the need of solving partial differential equations, this work proposes an efficient model-free, data-driven approach based on online learning. Specifically, by considering the observer dynamics as a Chen-Fliess series, the estimation of its coefficients has a least squares formulation. Since the series converges only locally, the coefficients are recursively updated, resulting in an online optimization scheme driven by instantaneous gradients. When the state trajectories are available, the online least squares guarantees an ultimate upper bound of average observation error proportional to the average variation of states. In the realistic situations where the states cannot be measured, the immersed linear dynamics based on the Kazantzis-Kravaris/Luenberger structure is assigned, followed by online kernel principal component analysis for dimensionality reduction. The proposed approach is demonstrated by a limit cycle dynamics and a chaotic system.
- 10 May 2023
- Published by Wiley
Open AccessData-Driven State Observation for Nonlinear Systems based on Online Learning
This paper considers the problem of state observation for nonlinear dynamics. While model-based observer synthesis is difficult due to the need of solving partial differential equations, this work proposes an efficient model-free, data-driven approach based on online learning. Specifically, by considering the observer dynamics as a Chen-Fliess series, the estimation of its coefficients has a least squares formulation. Since the series converges only locally, the coefficients are recursively updated, resulting in an online optimization scheme driven by instantaneous gradients. When the state trajectories are available, the online least squares guarantees an ultimate upper bound of average observation error proportional to the average variation of states. In the realistic situations where the states cannot be measured, the immersed linear dynamics based on the Kazantzis-Kravaris/Luenberger structure is assigned, followed by online kernel principal component analysis for dimensionality reduction. The proposed approach is demonstrated by a limit cycle dynamics and a chaotic system.
- 30 August 2021
- Published by Wiley in AIChE Journal
- Vol. 68 (6)
Stochastic blockmodeling for learning the structure of optimization problems
Decomposition‐based solution algorithms for optimization problems depend on the underlying latent block structure of the problem. Methods for detecting this structure are currently lacking. In this article, we propose stochastic blockmodeling (SBM) as a systematic framework for learning the underlying block structure in generic optimization problems. SBM is a generative graph model in which nodes belong to some blocks and the interconnections among the nodes are stochastically dependent on their block affiliations. Hence, through parametric statistical inference, the interconnection patterns underlying optimization problems can be estimated. For benchmark optimization problems, we show that SBM can reveal the underlying block structure and that the estimated blocks can be used as the basis for decomposition‐based solution algorithms which can reach an optimum or bound estimates in reduced computational time. Finally, we present a general software platform for automated block structure detection and decomposition‐based solution following distributed and hierarchical optimization approaches.
- 30 August 2021
- Published by Wiley in AIChE Journal
- Vol. 68 (6)
Stochastic blockmodeling for learning the structure of optimization problems
Decomposition‐based solution algorithms for optimization problems depend on the underlying latent block structure of the problem. Methods for detecting this structure are currently lacking. In this article, we propose stochastic blockmodeling (SBM) as a systematic framework for learning the underlying block structure in generic optimization problems. SBM is a generative graph model in which nodes belong to some blocks and the interconnections among the nodes are stochastically dependent on their block affiliations. Hence, through parametric statistical inference, the interconnection patterns underlying optimization problems can be estimated. For benchmark optimization problems, we show that SBM can reveal the underlying block structure and that the estimated blocks can be used as the basis for decomposition‐based solution algorithms which can reach an optimum or bound estimates in reduced computational time. Finally, we present a general software platform for automated block structure detection and decomposition‐based solution following distributed and hierarchical optimization approaches.