Keke Huang’s research while affiliated with Central South University and other places

In the field of science and engineering, identifying the nonlinear dynamics of systems from data is a significant yet challenging task. In practice, the collected data are often contaminated by noise, which often severely reduce the accuracy of the identification results. To address the issue of inaccurate identification induced by non-stationary noise in data, this paper proposes a method called weighted ℓ1-regularized and insensitive loss function-based sparse identification of dynamics. Specifically, the robust identification problem is formulated using a sparse identification mathematical model that takes into account the presence of non-stationary noise in a quantitative manner. Then, a novel weighted ℓ1-regularized and insensitive loss function is proposed to account for the nature of non-stationary noise. Compared to traditional loss functions like least squares and least absolute deviation, the proposed method can mitigate the adverse effects of non-stationary noise and better promote the sparsity of results, thereby enhancing the accuracy of identification. Third, to overcome the non-smooth nature of the objective function induced by the inclusion of loss and regularization terms, a smooth approximation of the non-smooth objective function is presented, and the alternating direction multiplier method is utilized to develop an efficient optimization algorithm. Finally, the robustness of the proposed method is verified by extensive experiments under different types of nonlinear dynamical systems. Compared to some state-of-the-art methods, the proposed method achieves better identification accuracy.

At present, network model is a general framework for the representation of complex system, and its structure is the fundamental and prerequisite for control and other applications of networked system. Due to the advent of Big Data era, the network structure scale is expanding sharply. Obviously, the traditional centralized reconstruction methods require high-performance computing resources and can hardly be suitable in practice. Therefore, it is a challenge to reconstruct large-scale networks with limited resources. To resolve the problem, a distributed local reconstruction method is proposed for unweighted networks. Specifically, the local reconstruction problems of nodes are distributed to multiple computing units. ADMM is introduced for compressed sensing framework to decompose the complex reconstruction problem into multiple subproblems, so it can reduce the high requirement of computing resources. Through parallel computing, network reconstruction subproblems are solved simultaneously. In addition, to further guarantee the reconstruction accuracy, a binary constraint is introduced based on the characteristics obtained by analyzing the network structure. Finally, extensive experiments are conducted to demonstrate the superiority of the proposed method. Compared with some state-of-the-art methods, the proposed method can reconstruct networks of different scales and types with limited computing resources, and it is accurate and robust against noise.

In this study, we propose a dynamics-learning multirate estimation approach to perceive the quality-related indices (QRIs) of the feeding solution of a unit process. A quality-related index for estimation is an intermediate technical indicator between a unit process and a proceeding unit process; hence, the estimation problem is formulated as a two-stage estimation problem utilizing the production data of both unit processes. Dynamics-learning bidirectional long short-term memory (BiLSTM) with different inputs for the forward and backward layers is proposed to manage the input data from the different unit processes. In the dynamics-learning BiLSTM, a cycle control gate is added in the memory cell to learn the dynamics of the QRIs, thereby enabling a high-rate estimation under multirate conditions. A Bayesian estimation model is then combined with the dynamics-learning BiLSTM model to manage the process delay. Ablation and comparative experiments are conducted to evaluate the feasibility and effectiveness of the proposed estimation approach. The experimental results illustrate the performance and high-rate estimation ability of the proposed approach.

With the digital transformation of process manufacturing, identifying the system model from process data and then applying to predictive control has become the most dominant approach in process control. However, the controlled plant often operates under changing operating conditions. What is more, there are often unknown operating conditions such as first appearance operating conditions, which make traditional predictive control methods based on identified model difficult to adapt to changing operating conditions. Moreover, the control accuracy is low during operating condition switching. To solve these problems, this article proposes an error-triggered adaptive sparse identification for predictive control (ETASI4PC) method. Specifically, an initial model is established based on sparse identification. Then, a prediction error-triggered mechanism is proposed to monitor operating condition changes in real time. Next, the previously identified model is updated with the fewest modifications by identifying parameter change, structural change, and combination of changes in the dynamical equations, thus achieving precise control to multiple operating conditions. Considering the problem of low control accuracy during the operating condition switching, a novel elastic feedback correction strategy is proposed to significantly improve the control accuracy in the transition period and ensure accurate control under full operating conditions. To verify the superiority of the proposed method, a numerical simulation case and a continuous stirred tank reactor (CSTR) case are designed. Compared with some state-of-the-art methods, the proposed method can rapidly adapt to frequent changes in operating conditions, and it can achieve real-time control effects even for unknown operating conditions such as first appearance operating conditions.

To realize the optimal control of the zinc leaching process, an accurate mathematical model is necessary. However, the modeling of zinc leaching process faces the challenges of complex reaction rate, low data quality and error transmission of cascade modeling. To solve these problems, a hybrid model of mass-concentration conservation and neural network (MCCNN) is proposed. First, the method of integral regularization is introduced to process data and reduce the influence of measurement noise. Then, a model based on mass-concentration conservation mechanism model and data-driven model is proposed to build sub-models of each unit, which can solve the problems of insufficient data and complex reaction rate. Finally, a parallel error compensation structure is proposed to alleviate the error transfer caused by the cascade of sub-models. This hybrid framework provides a feasible and effective solution for zinc leaching process modeling, and its effect is verified by numerical simulation and zinc leaching process case.

Roaster furnace is a large-scale equipment in zinc smelting process, which plays an significant role in safety production and enviromental protection. An accurate digital twin of roaster furnace can help to explore the influence of control parameters and serve as a test platform to verify the effectiveness of control strategies. However, the traditional thermodynamics cannot be used for dynamic modeling, and inability to measure key data greatly affects the accuracy of kinetic modeling. Therefore, this paper establishes a novel digital twin of zinc roaster furnace based on knowledge-guided variable-mass thermodynamics. First, based on the integration of mechanism analysis for mass balance and energy balance, a dynamic modeling method is proposed. Then, particle swarm optimization (PSO) algorithm is introduced to optimize the parameters of conversion rates guided by knowledge. Finally, by connecting the dynamic model with distributed control system (DCS) through OPC communication protocol, a digital twin of roaster furnace is constructed. Extensive experiments show that the simulation results of the digital twin roughly agree with the actual industrial data under steady and dynamic working conditions, and the application of the digital twin on the performance analysis of control parameters and testing of control strategies can provide guidance for the optimal control of roaster furnace.