This paper presents a constrained optimal adaptive control strategy for formation control in nonlinear multi-agent systems (MASs) using a data-driven approach. In contrast to traditional methods that require detailed system models, the proposed method employs Locally Linearized Dynamic Models (LLDMs), in which key parameters as Pseudo-Partial Derivatives (PPDs) are estimated adaptively from input–output data. This removes the need for explicit mathematical modeling and broadens the method’s applicability to uncertain systems. To address actuator limitations and reduce control effort, a performance criterion incorporating control constraints is defined, and the problem is reformulated as a Constrained Quadratic Program (CQP) with control increments as optimization variables. A Projection Recurrent Neural Network (PRNN) is developed to solve this CQP in real time, which ensures convergence of the numerical optimizer and guarantees closed-loop stability using Lyapunov analysis and singular value approach. The proposed algorithm achieves robust, model-free formation control, explicitly manages input constraints, and enables fast convergence. Simulation results show that this approach outperforms existing data-driven methods under uncertainty, which demonstrates its potential for applications in multi-agent system applications.

Controlling jerk in industrial systems under disturbances and uncertainties presents significant technical challenges. This article introduces a novel hierarchical sliding mode control system with adaptive disturbance compensation for rapid acceleration tracking in fluid power systems. The study focuses on acceleration tracking during jerk motion in a hybrid electro-hydraulic-pneumatic actuator. To achieve high precision and robustness, an inverse sequence of cascaded sliding modes is constructed to generate reference signals for the intermediate subsystems. A neural adaptive estimator is proposed to approximate both gradual and rapidly changing lumped disturbances. By employing Lyapunov theory, the asymptotic stability of the sliding functions and the convergence of the adaptive estimation are ensured. The effectiveness of the proposed approach is validated through numerical simulations and experiments on a real-world hybrid fluid power system.

This study investigates the presence of positive solutions for a new category of coupled systems characterized by k-dimensional fractional differential inclusions that utilize the p-Laplacian operator. The analysis is conducted under specific initial and boundary conditions that ensure the mathematical soundness of the model. Due to these systems’ intricate nature and nonlinearity, conventional analytical techniques may not be readily applicable. To address these difficulties, we apply a fixed-point theorem on a cone, which is instrumental in demonstrating the existence of positive solutions within our framework. To enhance our findings, we develop two iterative sequences that help us converge towards an approximate solution. These sequences are meticulously crafted to refine the solution space while upholding the required mathematical rigor. This iterative methodology ensures that our approach remains computationally viable while yielding significant approximations for practical use. Moreover, we establish appropriate conditions on the nonlinear components to ensure the efficacy of our method in producing solutions that meet both theoretical and computational standards. A specific numerical example underscores the importance of our results and showcases the practical relevance of our theoretical conclusions.

The paper introduces a novel nonlinear adaptive robust model-free time delay control technique for an autonomous underwater vehicle with prior unknown dynamics. The proposed method is designed without system dynamic parameters or model identification. Firstly, the freely selected time delay estimation mechanism is utilized to estimate external disturbances and unknown modeling dynamics by using one-step delayed input-output data. Secondly, the control forces and moments are derived from the estimated values and a nonsingular terminal sliding surface, ensuring finite-time convergence of the tracking errors. Next, a novel nonlinear adaptive gain rule is proposed to enhance the fast adaptation and robustness of the system. The stability is then proved by Lyapunov theorem, resulting in the system being uniformly ultimately bounded. Finally, the proposed approach is experimentally validated on a Speedgoat-Pixhawk hardware-in-the-loop platform in comparison with existing methods.

This paper presents an augmented computed-torque control (A-CTC) scheme for 6-DoF industrial manipulators operating under model uncertainty and external disturbances. The proposed controller combines a nominal computed torque law with an additional torque-domain residual damping term to compensate for modeling errors and unmodeled friction while preserving the baseline tracking structure. A Lyapunov-based analysis is developed for the resulting closed-loop system, and bounded output constraints are imposed on the residual term to support input-to-state stability and bounded tracking errors. The method is evaluated in simulation against PD feedforward (PD-ff) and sliding mode control (SMC) over multiple trajectories and disturbance scenarios. Across 30 randomized trials, A-CTC reduces joint-space RMSE by approximately 12.8%, end-effector RMSE by 13.0%, and disturbance-settling time by 32.4% compared with PD-ff, while increasing RMS torque by only 4.5%. Compared with SMC, A-CTC achieves lower joint-space and end-effector RMSE by 7.4% and 4.1%, respectively, while reducing RMS torque by 40.0% and saturation time by 54.5%. Additional simulation studies, including gain-sensitivity analysis, Jacobian conditioning assessment, and impulse response tests, further support a favorable accuracy-effort trade-off and improved disturbance rejection. The present results are based on simulation and will be validated experimentally in future work.

The pitch angle regulation of wind turbine (WT) plants faces serious challenges due to the nonlinear behavior of these systems and remarkable moment of inertia, along with stochastic changes in wind speed. In this paper, an adaptive pitch angle control based on fractional order model predictive control (FOMPC) is developed for variable speed of WT under full load region to regulate the rotor speed and to limit the output power. In particular, the deep state-action-reward-state-action (SARSA) is utilized to tune critical parameters of FOMPC, which is useful to stabilize rotor speed by adapting to the changes of turbulent wind conditions. By defining a reward function based on the specific goals of WT systems, the deep neural networks (DNNs) of the SARSA agent learn an effective policy for stabilizing the wind turbine, adjusting the FOMPC-based pitch angle control in response to varying wind conditions to capture the maximum output. By utilizing the training capability of DNNs, the FOMPC controller can dynamically respond to the changes in the WT system. The deployment of deep SARSA makes the intelligent controller to automatically learn and implement optimal control strategies in complex, dynamic environments, enhancing overall system performance and resilience. For comparison purposes, three other pitch angle controllers including the basic model predictive control (MPC), gain scheduling proportional-integral (GSPI) controller, and proportional-integral (PI) controller were also designed for the case-study. The feasibility of designed pitch angle controllers for WT stabilization was verified under two different operation conditions: normal and extreme stochastic wind circumstances. Dynamic responses and numerical analysis confirmed the suggested FOMPC-based deep SARSA agent can provide superior transient behavior and a higher level of robustness than the MPC, GSPI, and PI controller when the WT system is working at full load region.

Quadrotor unmanned aerial vehicles have become very popular for doing numerous tasks; however, due to their small size and weight, they are very sensitive to parameter uncertainties and external disturbances. In this paper, a new robust fault-tolerant approach is introduced to track the attitude trajectory of a quadrotor in finite time that suffers from stochastic actuator faults, system parameter uncertainties, and unknown external disturbances. Furthermore, the effects of time-varying input delay are considered in the control input. Based on the Lyapunov-Krasovskii functional approach, two theorems are given to derive some delay-dependent conditions regarding the design of a controller that guarantees the finite-time contractive stability of the attitude tracking error system with the prescribed H-infinity performance index. This means that the tracking error states converge to a defined bound within a fixed time interval which is smaller than the initial state bound, and the acceptable H-infinity disturbance attenuation level is achieved. Finally, the proposed method is applied to a quadrotor facing the external disturbance and stochastic actuator fault. The simulation results verify the effectiveness and superiority of the proposed control scheme as compared to the asymptotic stability approach and the finite-time boundedness stability model.

The Twin Hybrid Autonomous Underwater Vehicle (THAUV) is an underwater monitoring system consisting of a twin buoyant body and a fixed wing mounted between them. It is equipped with two propeller thrusters and a pair of elevators at the aft end. As a new type of underwater vehicle, it combines the long endurance of an underwater glider (UG), the high-speed maneuverability of an autonomous underwater vehicle (AUV), and the ability to carry larger payloads. In this paper, the motion equations of the THAUV are established, and its simulation model is developed using SIMULINK. Computational fluid dynamics (CFD) is further employed to identify hydrodynamic parameters under different elevator size conditions. A case study is conducted to analyze the effects of three different widths of elevators on glide performance, including gliding speed, pitching angle, and gliding trajectory. CFD results show that when the elevator deflection angle is zero, the hydrodynamic forces acting on the THAUV increase as the elevator width increases under identical angle of attack and velocity conditions. Under CFD conditions with fixed angle of attack and flow velocity, the sensitivity of the hydrodynamic characteristics to elevator deflection became significantly more pronounced. Increasing the elevator deflection angle led to substantial growth in the generated hydrodynamic forces. Motion simulations further show that increasing the elevator deflection angle enhances the THAUV’s gliding performance. Comparative results also reveal that glide performance improves with larger elevator width.

Wheeled mobile robots (WMRs) have become increasingly vital role in modern industries. This research proposes a novel finite-time prescribed performance sliding mode control (SMC) algorithm for the trajectory tracking of WMRs under effects of wheel slipping, wheel skidding, and external disturbances. The proposed approach consists of two key components. First, a novel sliding surface is proposed based on a prescribed performance function (PPF) and a non-singular fast terminal sliding function (NFTSF), referred to as PP-NFTSF. The proposed PP-NFTSF ensures that tracking errors converge to zero in finite time, while the PPF and a transformed error function ensure stability throughout the robot's operation by maintaining error states within predefined bounds. This framework ensures boundaries around zero, thus guaranteeing that the position tracking error will be zero when the transformed error reaches zero. Second, a novel finite-time non-singular fast terminal SMC (NFTSMC) law with prescribed performance tracking errors, referred to as FPP-NFTSMC, is proposed. This control law incorporates a second-order algorithm to generate a continuous control signal, effectively minimizing the chattering phenomenon of SMC. Overall, the proposed control method maintains all the advantages of PPF, NFTSMC, and the second-order algorithm, achieving high position tracking performance, decreasing the chattering phenomenon, obtaining finite-time convergence, guaranteeing tracking error within the boundary of the PPF, and robustness. To illustrate the stability and finite-time convergence of the WMR systems, a proof using the Lyapunov stability theory is performed. The effectiveness of the proposed control method is validated using two working scenarios: tracking straight and U-shaped trajectories for a 4-WMR.

Recently interval type-3 (IT3) fuzzy logic systems (FLSs) are applied for various high-noisy problems. However, in most presented IT3-FLSs: (1) To convert the output T3 fuzzy sets (FSs) into a crisp value just the simple weighted average type-reductions are used that these approaches weakness the main concept of IT3-FSs; (2) The secondary memberships and number, rule format, number of FSs and α -cuts are constant in existing IT3-FLSs; (3) One of the main properties of IT3-FSs is that the upper bound (UB) and lower bound (LB) of the footprint of uncertainty (FOU) are fuzzy numbers. However, in existing FSs, it is hard to determine an uncertainty bound for UB and LB of FOU. In this paper, new type-reduction and a new learning technique are introduced. The main contributions are as follows. (1) A type-reduction based on the theorem of uncertainty bounds is developed. The suggested method has no iterative computations, and it is much closer to the Karnik-Mendel technique. (2) A new type-3 (T3) fuzzy set with triangular secondary membership, and simple interval fuzzy bounds for UB and LB of FOU is introduced and formulated. (3) A new self-structuring technique based on Invasive Weed Optimization (IWO) is suggested for optimizing rule numbers, the format of rules, the level of α -cuts, the secondary membership, the center of FSs, and the rule parameters. (4) By several simulations on modeling of real-world data, applied control applications, and statistical analyses, the effectiveness of the schemed FLS and learning strategy is verified.

In the field of biomedical engineering, the issue of drug delivery constitutes a multifaceted and demanding endeavor for healthcare professionals. The intravenous administration of pharmacological agents to patients and the normalization of average arterial blood pressure (AABP) to desired thresholds represents a prevalent approach employed within clinical settings. The automated closed-loop infusion of vasoactive drugs for the purpose of modulating blood pressure (BP) in patients suffering from acute hypertension has been the focus of rigorous investigation in recent years. In previous works where model-based and fuzzy controllers are used to control AABP, model-based controllers rely on the precise mathematical model, while fuzzy controllers entail complexity due to rule sets. To overcome these challenges, this paper presents an adaptive closed-loop drug delivery system to control AABP by adjusting the infusion rate, as well as a communication time delay (CTD) for analyzing the wireless connectivity and interruption in transferring feedback data as a new insight. Firstly, a nonlinear backstepping controller (NBC) is developed to control AABP by continuously adjusting vasoactive drugs using real-time feedback. Secondly, a model-free deep reinforcement learning (MF-DRL) algorithm is integrated into the NBC to adjust dynamically the coefficients of the controller. Besides the various analyses such as normal condition (without CTD strategy), stability, and hybrid noise, a CTD analysis is implemented to illustrate the functionality of the system in a wireless manner and interruption in real-time feedback data.

Fractional-order four-wing (FO 4-wing) systems are of significant importance due to their complex dynamics and wide-ranging applications in secure communications, encryption, and nonlinear circuit design, making their control and stabilization a critical area of study. In this research, a novel model-free finite-time flexible sliding mode control (FTF-SMC) strategy is developed for the stabilization of a particular category of hyperchaotic FO 4-wing systems, which are subject to unknown uncertainties and input saturation constraints. The proposed approach leverages fractional-order Lyapunov stability theory to design a flexible sliding mode controller capable of effectively addressing the chaotic dynamics of FO 4-wing systems and ensuring finite-time convergence. Initially, a dynamic sliding surface is formulated to accommodate system variations. Following this, a robust model-free control law is designed to counteract uncertainties and input saturation effects. The finite-time stability of both the sliding surface and the control scheme is rigorously proven. The control strategy eliminates the need for explicit system models by exploiting the norm-bounded characteristics of chaotic system states. To optimize the parameters of the model-free FTF-SMC, a deep reinforcement learning framework based on the adaptive dynamic programming (ADP) algorithm is employed. The ADP agent utilizes two neural networks (NNs)—action NN and critic NN—aiming to obtain the optimal policy by maximizing a predefined reward function. This ensures that the sliding motion satisfies the reachability condition within a finite time frame. The effectiveness of the proposed methodology is validated through comprehensive simulations, numerical case studies, and comparative analyses.

Objectives: This study presents a novel closed-loop Artificial Pancreas System (cl-PAS) intended to adjust blood glucose (BG) levels and insulin dosage in diabetic patients in real-time. Methods and Novelty: To achieve this, a nonlinear active disturbance rejection controller (NADRC) has been created to control BG levels by managing insulin concentrations while simultaneously eliminating outside uncertainties and unidentified input dynamics. A deep stochastic policy optimization (DSPO) has been incorporated into the main system in the next step to offer real-time updates of the coefficients of the suggested controller and enhance the system's resilience and adaptability. A second deep neural network serves as the value function in the implemented strategy, estimating the expected return for a given state-action pair. The policy function in the strategy translates states to actions. DSPO is able to train effective control policies in high-dimensional, continuous state and action spaces, especially physiological systems, by updating the value networks and the policy simultaneously. Findings: Many tests are performed to determine whether the developed approach is functional in managing the insulin infusion rate to regulate BG under various conditions. These tests include: (1) Normal condition, (2) robustness analysis (applying to new cases), (3) condition of multiple meal consumption, and (4) Conditions involving uncertainties and disruptions. Comparative evaluations and statistical analyses with alternative and prior methodologies demonstrate the average improvement of 64.90% for patient 1, 59.49% for patient 2, and 64.17% for patient 3 over other approaches.

In this paper, a low voltage (LV) distribution network with a high-penetration wind turbine (WT) generation unit is effectively configured to enhance network reliability and operational efficiency. The randomness of WT units is alleviated by the battery energy storage (BES) with an advanced reinforcement learning-based control approach. In particular, a coordinated control mechanism is designed to adjust the charge/discharge of BES using an integration of the local droop-based control strategy and a distributed controller to preserve the voltages of the feeder in a pre-defined range. To do this, an ultra-local model control scheme is developed for control of the weighted consensus control (WCC) and the dynamic consensus control (DCC) to regulate storage participation. The maximum entropy regularization (MER)-based reinforcement learning with multi-neural networks is adopted for effective coordination of WCC and DCC. The integration of these components leads to the efficient development of BES capability to stabilize output voltage. In the MER-learning, the agent aims to find the optimal policy using the entropy factor in such a way that obtains the maximum capacity of battery storage units. A reward function is defined based on the requirements of voltage regulation in the battery storage unit to train the deep neural networks of MER-learning. The comparative analysis under various typical scenarios of the LV network is accomplished. The results indicate that the proposed scheme (designed by MER-learning) can ensure system stability under communication failures and various load increase scenarios. The study also investigates the impact of different BES coordination strategies on charge/discharge behavior, showing that the proposed method achieves superior voltage regulation and load-sharing compared to conventional model predictive control (MPC) and proportional-integral (PI) controllers.

The high penetration of sustainable energy resources (SERs) into the hybrid Micro-grid system (HMGS) is equipped with AC/DC/DC power converters to connect such generation units to the bus. Since these power electronic interfaces do not have rotational mass, the HMGS's inertia will be reduced accordingly. This study introduces the concept of a virtual frequency controller (VFC) in the energy storage systems (ESSs) employed in a low-inertia HMGS under high penetration of SERs. This paper introduces a new approach to adaptive VFC for low-inertia HMGSs which includes three major innovations: (1) implementation of a high-order extended disturbance observer (HOEDO) for real-time estimation and compensation of unknown dynamics and SER-induced disturbances; (2) applying the deep learning deep sequential action-value learning (SAVL) algorithm to adjust the parameters of the controller-observer in an unsupervised fashion to adapt to system variability and uncertainties without a priori models; and (3) the inclusion of virtual rotor dynamics emulation during primary and secondary control loops to enhance responsiveness akin to synchronous generators. By maximizing a cumulative reward function, the agents of deep SAVL are trained in such a way that the controller is adaptively designed according to SERs/load variations. By deploying the training capability of deep neural networks, the suggested adaptive VFC technique improves the system's inertia and damping features under high-penetration of SERs. Moreover, comparative responses of the suggested adaptive VFC controller with conventional virtual inertia control (CVIC) controlled by model predictive control (MPC), fractional-order proportional-integral-derivative (FOPID) control, the conventional virtual inertia and virtual damping control-based PI controller, and CVIC-based two-layer multiple MPC (TLMMPC) methods infer that the suggested scheme not only exhibits more suppressed fluctuations but also demonstrates a faster response to the dynamic variations.

In leader-follower (L-F) multi-robot systems deployed in dynamic environments, achieving task-space consensus is challenging due to the presence of actuator faults, deception attacks, and uncertainties. This paper presents a resilient control framework designed to ensure task-space consensus in multiple Euler -Lagrange system (ELS) while addressing these critical issues. The proposed approach combines an adaptive consensus controller to ensure coordinated control, an observer-based mechanism to detect and mitigate deception attacks, and an Interval Type-2 Fuzzy Logic Controller (IT2FLC) to effectively manage faults and uncertainties. To guarantee system stability and convergence, a Lyapunov-based analysis is conducted. Extensive simulations are performed in a network of four two-degree-of-freedom robotic manipulators to evaluate the proposed method compared with L-F consensus controller (LFCC) for multiple uncertain ELS and resilient consensus control (RCC) for network robotic manipulators under actuator faults and deception attack. The results show that in noiseless conditions, the proposed controller achieves up to 8.40% root mean square error (RMSE) reduction compared to baseline controllers. Under noisy conditions, it significantly outperforms LFCC and RCC, and improvements across all robots and axes with reductions ranging from 22.13% to 73.30%. That demonstrates the effectiveness of proposed method in maintaining consensus, enhancing resilience, and ensuring reliable operation under dynamic and uncertain conditions.

The design and analysis of a new wave actuator for boats is presented in this paper. The wave actuator is installed beneath the boat hull and converts the hydrodynamic forces generated by rising waves on the boat into translational thrusting forces. The wave actuator consists of a flexible water tank, revolving springs, and inlet/outlet nozzles to enable passive wave-driven thrust generation without intermediate energy conversion. The compressed water in the tank of the wave actuator is expelled by the wave pressure exerted on the actuator, and the water thrust out of the nozzles propels the boat forward. The dynamics and hydrodynamics of the new wave actuator are newly modelled using second-order differential equations in this paper. The hydrodynamics of the boat with the wave actuator is mathematically analyzed, and the energy conversion capability of the wave actuator is analyzed. The results demonstrate that at a wave frequency of 0.3 Hz, the system achieves a cruising speed of 6.098 m/s and a high energy conversion efficiency of 67.9%. These findings highlight the actuator’s potential for efficient and sustainable marine propulsion in regular sea conditions.

-The integration of diverse distributed energy resources is increasingly being enabled by shipboard microgrids (Sb mu GSs) as a promising solution to address the challenges posed by evolving maritime power systems toward decentralized and sustainable architectures. Open communication networks have been recently integrated with sustainable energy resources (SERs) for secure operation, regulation, and management of modern maritime power systems. However, deploying such emerging technologies introduces some faults and delays in communication channels which degrades the performance of marine power systems. This paper focuses on the development of a robust maritime controller-based nonlinear integral-backstepping (NI-BSC) for frequency stabilization of Sb mu GSs with high penetration of SERs, non-sensitive loads, and battery systems. Particularly, the double deep Q-learning (DDQL) is developed to adaptively design the NI-BSC and dynamically respond to the frequency stabilization challenges of Sb mu GS. By maximizing a long-term reinforcement signal, the neural networks (NNs) of DDQL (i.e., evaluation and target neural networks) are trained to reduce frequency fluctuations of Sb mu GS considering communication delays. The considered topology of Sb mu GS utilizes a separate maritime controller to regulate the solid-oxide fuel cell (SOFC) and thermostatic loads (heat pumps and freezer) while providing the possibility for sustainable units (e.g., wave energy and solar energy) to generate their maximum power. To conduct more realistic examinations, several typical scenarios of shipboard microgrids are carried out in a real-time setup. The real-time simulation outcomes reveal that the controller designed by DDQL outperforms the existing methodologies such as optimal controller, backstepping controller, and model-free sliding mode control, with an improvement in dynamic behaviors ranging from 54.57 % to 74.17 %.

This study introduces a novel control framework based on the Takagi–Sugeno–Kang wavelet fuzzy neural network, integrating brain imitated network and cerebellar network. The proposed controller demonstrates high robustness, making it an excellent candidate for handling intricate nonlinear dynamics, effectively mapping input–output relationships and efficiently learning from data. To enhance its performance, the controller’s parameters are fine-tuned using Lyapunov stability theory. Compared to existing approaches, the proposed model exhibits superior learning capabilities and achieves outstanding performance metrics. Furthermore, the study applies this synchronization technique to the secure transmission of medical images. By encrypting a medical image into a chaotic trajectory before transmission, the system ensures data security. On the receiving end, the original image is successfully reconstructed using chaotic trajectory synchronization. Experimental results confirm the effectiveness and reliability of the proposed neural network model, as well as the encryption and decryption process. Specifically, the average_RMSE of the Takagi–Sugeno–Kang fuzzy wavelet brain cerebral controller (TFWBCC) method is 2.004 times smaller than the cerebellar model articulation controller (CMAC) method, 1.923 times smaller than the RCMAC method, 1.8829 times smaller than the TSKCMAC method, and 1.8153 times smaller than the brain emotional learning controller (BELC) method.

Path-tracking and lane-keeping efficiency of driverless cars remain critical characteristics of the efficient and safe deployment of such vehicles in future intelligent transportation systems. This study introduces a robust type-3 (T3) fuzzy controller implementation for the path-tracking task of driverless cars during critical driving conditions and subject to exogenous disturbances. Unlike many existing control paradigms, the proposed scheme is independent of the parameter information and assumes the system dynamics are unknown and non-linear. Control inputs are constructed to improve robustness by eliminating the error bounds while ensuring stability by leveraging the Lyapunov stability theorem and Barbalat's lemma. Also, a predicate scheme based on non-linear predictive control technique is introduced to enhance the lateral displacement. Based on the obtained results, the schemed controller exhibits competitive effectiveness in path-tracking tasks, and strong efficiency under various road conditions, parametric uncertainties, and unknown disturbances. This study introduces a robust type-3 fuzzy neural controller implementation for the path-tracking task of driverless cars during critical driving conditions and subject to exogenous disturbances.image