Tianyou Chai

This article investigates the adaptive optimal output-feedback control problem for discrete-time multiagent linear systems. An adaptive dynamic programming (ADP) algorithm, hybrid iteration (HI), is proposed to solve the adaptive optimal output-feedback control problem. The primary contribution of this work is the advancement of an approach to addressing adaptive optimal output regulation problems for multiagent systems via output-feedback control. Unlike existing ADP-based strategies, such as policy iteration (PI) and value iteration (VI), the proposed output-feedback HI strategy learns the optimal output-feedback control policy over two phases. In the first phase, a data-driven scheme is deployed to learn an admissible output-feedback control policy based on online data. In the second phase, given the admissible control policy, the optimal output-feedback control policy is learned via PI with an accelerated convergence rate. Illustrative examples demonstrating the effectiveness of the proposed output-feedback HI approach to controlling systems with slow and fast dynamics, including long and short time scales (or time constants), respectively, are provided and studied. In this regard, experimental results from rapid control prototyping of a permanent-magnet DC motor drive utilizing a DC–DC buck converter (as an example of a system with slow dynamics, or equivalently, with long time scales) are presented. Additionally, testing results from power hardware-in-the-loop simulations of a modern microgrid utilizing inverter-based resources (as an example of a system with fast dynamics, or equivalently, with short time scales) reveal the efficacy and practicality of the proposed ADP-based adaptive optimal output regulation employing HI.

Sensor drift, which is the deviation of measurements over time, can compromise controller performance and cause system instability. To address this challenge, this article proposes a proactive fault-tolerant control strategy for distributed parameter systems. The proposed strategy is based on a time-varying spatiotemporal model that captures system dynamics. The initial phase of this research involves designing an adaptive observer-based detector to identify the temporal and spatial locations of fault occurrences accurately. Subsequently, a joint state-and-fault estimator is developed to accurately reconstruct the fault profile, even in the presence of strong state-fault coupling. The controller provides real-time corrections based on the estimation results. A rigorous stability analysis of the closed-loop system is provided, and the effectiveness of the controller is validated through experiments involving two distinct fault scenarios.

The process of controlling the outlet temperature in ethylene cracking furnaces exhibits notable nonlinearity. Variations in feedstock and fuel properties prevent accurate modeling, resulting in suboptimal performance of predictive functional control in practical implementations. This research analyzes the causal linkage between outlet temperature and fuel gas flow rate. A mechanism model is derived along with its input–output characteristics, and the controlled object is represented as a composite state-space system combining a linear model with unmodeled dynamics. By using the available unmodeled dynamics values from the previous time and the tracking errors caused by their increment, a state-space compensation performance index for unmodeled dynamics is designed. This index is based on the closed-loop system established by a predictive functional controller developed for the linear model. An innovative compensation strategy is developed to mitigate unmodeled dynamics’ impact on the closed-loop system, resulting in an improved predictive functional control approach for ethylene cracking furnace temperature regulation. The closed-loop system’s input–output relationship is formulated, and system stability and convergence are rigorously analyzed. Experimental validation at a petrochemical plant in Northeast China demonstrates that the proposed method reduces the mean squared error by 48.72% and the integrated absolute error by 30.52% when compared to the current method.

Due to the influence of fluctuations in the particle size and throughput of ore from the upstream crushing stage, variations in the return flow of unqualified particles during grinding, and the frequent changes of unknown nonlinearities in the complex ore feeding process, it is difficult to apply existing disturbance-rejection control methods to control the feed rate within the target range. In this article, by utilizing the characteristic that the feed rate fluctuates around the target interval, a dynamic model of the feeding process is established. Based on the obtainable previous-time-step value of the unknown nonlinear dynamic system and the closed-loop tracking error generated by the unknown rate of change of this nonlinear system, and the PI closed-loop equation, a data-driven signal-compensator is designed by combining feedforward control with a one-step optimal control law. A signal-compensated PI controller is proposed. The performance index that minimizes the tracking error at each operating instant is introduced, and a concurrent-learning-driven optimal tuning method for parameters of both the PI controller and the compensator is proposed. Simulation and industrial application experiments demonstrate that the proposed control method is capable of controlling the tracking error within the target interval during the entire operational period.

The problem of global prescribed performance control (PPC) for the multi-input multi-output (MIMO) block-triangular systems with unknown nonlinearities and mismatched disturbances is investigated in this article. The design purposes lie in the independent prescribed settling times and the independent control gains. They cannot be fulfilled by the existing solutions and become more challenging under the radially unbounded system nonlinearities. Therefore, a novel global PPC strategy is developed in this article. Herein, a family of inverse-proportional-type performance functions is designed to independently prescribe the settling times for the tracking errors and the intermediate errors. Moreover, to verify the feasibility of the independent control gains, a unified performance analysis grounded on a barrier Lyapunov function with nonuniform weights and the proof by contradiction is conducted. In addition, the proposed approach preserves the fast and accurate tracking capacity and the unique simplicity of PPC, without approximation or identification. A pair of experiments on a 2-DOF serial flexible link robot is performed to validate the efficacy and advantages of the control approach.

Accurate decision-making for complex industrial processes is essential for improving resource utilization and optimizing operating conditions. However, current decision work-flows operate within a hierarchical closed loop between the operations layer and the process-control layer. Cross-layer transmission of objectives and constraints and feedback coupling can degrade performance; the effect is pronounced under nonstationary conditions or when objectives or constraints change. To address these challenges, we propose the Bi-level Evolving Neural Networks (BENNs) framework with four components: (i) a bi-level neural architecture that explicitly models cross-layer information flow and constraint propagation; (ii) a graph neural network-based structural similarity assessment that reduces redundant evaluations to improve search quality; (iii) an online evolving network strategy that adapts rapidly to process dynamics without extensive retraining; and (iv) a convex-hull knee-point-based compromise selection that encodes engineering preferences. Experiments on real mineral processing data and on the Tennessee Eastman Process (TEP) show improvements over baselines in prediction accuracy, performance retention, and adaptation speed, demonstrating the potential of BENNs for complex industrial settings.

Optimizing industrial thickening systems requires accurate supernatant interface height prediction. Existing methods struggle with complex dynamics and noise, limiting accuracy. This article proposes a novel hybrid deep learning framework that synergistically combines regression and classification methodologies to improve predictive performance. Specifically, a differential attention-enhanced long short-term memory network provides high-precision point prediction by capturing salient features and addressing uncertain time delays. Concurrently, a multiscale convolutional neural network with a convolutional block attention module extracts features and classifies trend direction. To integrate numerical and trend predictions, a trend-aware dynamic fusion mechanism is introduced, which explicitly ensures trend consistency and adaptively optimizes fusion weights using a deep deterministic policy gradient algorithm, yielding predictions accurate in value and reliable in direction. Real-world data from a large coal preparation plant demonstrates the superior performance of our prediction method compared to baseline methods. In addition, industrial experiments validate that the proposed model supports operator decision-making for the optimization and control of thickening systems.

Accurate real-time prediction in dynamic industrial systems is crucial for optimization and efficiency. This article introduces a novel intelligent monitoring framework leveraging proportional–integral–derivative (PID)-optimized deep learning for adaptive time–frequency forecasting to address the challenges posed by nonstationary industrial data. The proposed method uniquely integrates a channel-independent separable dynamic filter (CSDF) that adapts to real-time multivariate process variables, minimizing cross-channel interference. Furthermore, a closed-loop PID optimization strategy enhances the convergence and prediction accuracy of the deep learning model. The effectiveness of this framework is demonstrated through a case study in the prediction of cleaned coal calorific value, a vital parameter for optimizing coal preparation processes and improving energy efficiency. Industrial experiments in this application show that the proposed method achieves a significant 5.36% increase in forecast hit rate (FHR) compared to existing techniques, highlighting its potential for advanced monitoring and control in dynamic systems.