In this article, a continuous terminal sliding mode control algorithm is proposed for servo motor systems. A novel full-order terminal sliding mode surface is proposed based on the bilimit homogeneous property, such that the sliding motion is finite-time stable independent of the system's initial condition. A new continuous terminal sliding mode control algorithm is proposed to guarantee that the system states reach the sliding surface in finite-time. Not only the robustness is guaranteed by the proposed controller but also the continuity makes the control algorithm more suitable for the servo mechanical systems. Finally, a numerical example is presented to depict the advantages of the proposed control algorithm. An application in the rotary servo system is done to validate the effectiveness of the proposed control strategy.

In high-power electronic industrial systems, constant power loads (CPLs) can affect the system performance or even cause instability due to its inherent negative impedance characteristics. Regarding this control issue, model predictive control (MPC) methods are generally applied into DC/DC converters feeding CPLs, aiming to achieve satisfactory control performance. However, they are mostly based on a fixed horizon design, whose optimal performance may be far from the desired one due to the change of operating conditions, e.g., different variation levels of CPLs. In this context, a novel generalized dynamic predictive control (GDPC) strategy employing a simple self-tuning horizon mechanism is proposed for the first time, allowing the controller to adaptively optimize the system transient-time performance even under largely-varied operating conditions. Firstly, a disturbance observer is utilized to reconstruct the lumped disturbances within the system, which are subsequently brought into the control design through feedforward compensation loops. Secondly, an adaptive horizon is introduced into the generalized predictive control (GPC) design and rigorous stability analysis based on Lyapunov theorem is given. The effectiveness and performance improvement of the proposed regulation methodology is verified by both simulation and experimental studies in reference to the double-loop PI control and a benchmark GPC algorithm.

For the DC/DC boost converter feeding constant power loads (CPLs), improving its dynamic characteristics and guaranteeing the output voltage stability have aroused much attention from the power electronics society in recent years. This paper proposes an optimal output regulation strategy by fusing a robust stabilization strategy with deep reinforcement learning (DRL). Firstly, by employing the high-order sliding mode observer (HOSMO) to estimate the uncertainties of the system, then we are able to realize a fast performance recovery ability via feedforward compensation loops. Secondly, the deep deterministic policy gradient (DDPG) is trained to adaptively adjust the control coefficients. Thirdly, the stability analysis is given to guarantee the large-signal stability of the control system. In order to evaluate the strength and effectiveness of the proposed adaptive method, experiments are conducted in this paper on a DC microgrid platform.

The Industrial Internet of Things (IIoT) promotes the deep integration of new-generation communication technologies and industrial ecology. However, the popularity of computing and the proliferation of equipment scale make it a meaningful challenge to provide reasonable resource allocation for task offloading. Therefore, this article proposes a novel two-stage coordinated, distributed, and online multidomain virtual network embedding algorithm based on deep reinforcement learning (DRL)-assisted federated learning (FL) for task offloading in the IIoT. We model the IIoT as a dynamic multidomain structure and deploy local DRL servers in each factory domain combined with the distributed paradigm of FL to reduce the local resource fragmentation. Through local and global cooperation, the IIoT environment is controlled in a fine and macroscopic manner. In addition, the mechanisms of FL ensure the privacy of participant data. Finally, a comprehensive evaluation demonstrates the clear superiority of the proposed algorithm, which improves the long-term offloading revenue, resource utilization, and task offloading success rate by average 17.66%, 5.97%, and 4.52% compared to baselines, respectively.

The tracking for discrete systems is discussed by designing two kinds of multilayered iterative learning schemes with cooperative-antagonistic interactions in this paper. The definition of the signed graph is presented and iterative learning schemes are then designed to be multilayered and have cooperative-antagonistic interactions. Moreover, considering the limited bandwidth of information storage, the state information of these controllers is updated in light of previous learning iterations but not just dependent on the last iteration. Two simple criteria are addressed to discuss the tracking of discrete systems with multilayered and cooperative-antagonistic iterative schemes. The simulation results are shown to demonstrate the validity of the given criteria.

Dynamic traffic monitoring is a critical part of industrial communication network cybersecurity, which can be used to analyze traffic behavior and identify anomalies. In this paper, industrial networks are modeled by a dynamic fluid-flow model of TCP behavior. The model can be described as a class of systems with unmeasurable states. In the system, anomalies and normal variants are represented by the queuing dynamics of additional traffic flow (ATF) and can be considered as a disturbance. The novel contributions are described as follows: (1) a novel continuous terminal sliding-mode observer (TSMO) is proposed for such systems to estimate the disturbance for traffic monitoring; (2) in TSMO, a novel output injection strategy is proposed using the finite-time stability theory to speed up convergence of the internal dynamics; and (3) a full-order sliding-mode-based mechanism is developed to generate a smooth output injection signal for real-time estimations, which is directly used for anomaly detection. To verify the effectiveness of the proposed approach, the real traffic profiles from the Center for Applied Internet Data Analysis (CAIDA) DDoS attack datasets are used.