Search

This article presents a study on the neurobiological control of voluntary movements for anthropomorphic robotic systems. A corticospinal neural network model has been developed to control joint trajectories in multi-fingered robotic hands. The proposed neural network simulates cortical and spinal areas, as well as the connectivity between them, during the execution of voluntary movements similar to those performed by humans or monkeys. Furthermore, this neural connection allows for the interpretation of functional roles in the motor areas of the brain. The proposed neural control system is tested on the fingers of a robotic hand, which is driven by agonist–antagonist tendons and actuators designed to accurately emulate complex muscular functionality. The experimental results show that the corticospinal controller produces key properties of biological movement control, such as bell-shaped asymmetric velocity profiles and the ability to compensate for disturbances. Movements are dynamically compensated for through sensory feedback. Based on the experimental results, it is concluded that the proposed biologically inspired adaptive neural control system is robust, reliable, and adaptable to robotic platforms with diverse biomechanics and degrees of freedom. The corticospinal network successfully integrates biological concepts with engineering control theory for the generation of functional movement. This research significantly contributes to improving our understanding of neuromotor control in both animals and humans, thus paving the way towards a new frontier in the field of neurobiological control of anthropomorphic robotic systems. [ABSTRACT FROM AUTHOR]

With the continuous development and progress of wireless self-organizing network communication technology, how to carry out long-distance cooperative control of multiple intelligences under the framework of an air–ground integrated wireless high-mobility self-organizing network has become a hot and difficult topic that needs to be solved urgently. This paper takes the air–ground integrated wireless high-mobility self-organizing network system as the basic framework and focuses on solving the long-distance cooperative fault-tolerant control of multi-intelligent bodies and the topological stability of a wireless mobile self-organizing network. To solve the above problems, a direct neural network with a robust adaptive fault-tolerant controller is designed in this paper. By constructing a symmetric population neural network model and combining it with the Lyapunov stabilization criterion, the system feedback matrix K has the ability of autonomous adaptive learning, and symmetrically distorts, rotates, or scales the training data to instantly adjust the system's fault-tolerant corrections and adaptive adjusting factors to resist the unknown disturbances and faults, to achieve the goals of multi-intelligent body stable control and the stable operation of a wireless high-mobility self-organizing network topology. Simulation results show that with the feedback adjustment of the multi-system under the designed controller, the multi-system as a whole has good fault-tolerant performance and autonomous learning approximation performance, and the tracking error asymptotically converges to zero. The experimental results show that the multi-flight subsystems fly stably, the air–ground integrated wireless high-mobility self-organizing network topology has good stability performance, and the maximum relative improvement of the topology stability performance is 50%. [ABSTRACT FROM AUTHOR]

Memristors have several chaotic dynamic models and have been used successfully in various fields, including secure communication systems, information storage, and artificial neural networks. The memristor-based four-dimensional chaotic (FDMC) systems generate unpredictable and intricate time domain signals. Parameter fluctuations in the FDMC system may give birth to chaos, making it difficult to suppress. Stabilizing chaos in the FDMC system improves the circuit's performance. This paper synthesizes a novel time-efficient chatter-free nonlinear robust adaptive control (NLRAC) technique that stabilizes chaos in the FDMC system affected by time-varying unknown bounded exogenous disturbances and model uncertainties. The proposed NLRAC strategy decimates the time-varying unknown bounded exogenous disturbances and model uncertainties effects; it establishes a faster, smoother state-variable trajectories convergence to the zero vicinity. The theoretical analysis and mathematical proofs are based on the Lyapunov stability technique. Computer simulation results show that the proposed NLRAC technique effectively brings the FDMC system's state-variable trajectories to zero with reduced fluctuations for control input signals and state-variable trajectories. This feedback controller's attribute enhances closed-loop stability performance, improves precision, and reduces risk overshoot. The paper includes comparative computer simulation results to endorse the proposed controller performance. [ABSTRACT FROM AUTHOR]

In this paper, by introducing memristive connections and inertial term into quaternion‐valued neural networks, the quaternion‐valued inertial memristive neural networks (QVIMNNs) is proposed. Based on the adaptive control strategy, the synchronization problem of the QVIMNNs is analyzed in this work. Two different assumption for activation functions are considered in this work; new criteria for global synchronization are then derived by designing novel adaptive controllers and update laws. Lastly, numerical examples are given to verify the results obtained in this work. [ABSTRACT FROM AUTHOR]

Electrical drive systems are commonly applied for the mechanisms of precise movement, where having a high-quality position and high-quality speed control is especially valuable. Very often, the mechanical part of these systems reveals resonant properties that are related to the limited stiffness of the interconnection between subsequent parts of the mechanism. In most cases, this sort of system may be described as a model of several linked masses. If only the structure of the mechanical part is known and the corresponding parameters are constant and identified, the demanded control quality may be obtained using a properly tuned ADRC or PID controller equipped with appropriate anti-resonance filtration. However, if the parameters of the mechanical part are variant, adaptive control may be considered as a solution. In this paper, artificial neural network (ANN) is considered to be a speed controller and its training method assures adaptation to the unknown mechanical parameters. The paper is particularly focused on a three-mass system, which possesses, due to its structure, two resonant frequencies. The unique property of the analyzed system is the application of drive units at both ends of the system, so that the controller has the ability to influence the resonant system from both sides. The coordination of the drive unit is performed by the aforementioned ANN, from which two outputs affect the drive units independently. The derivation of the mathematical model is followed by its implementation in a computer simulation and finally the evaluation in a dedicated laboratory setup, the construction of which is also presented in the paper. [ABSTRACT FROM AUTHOR]

Robotic systems have experienced exponential growth in their utilization for manufacturing applications over recent decades. Control systems responsible for executing desired robot motion planning face increasingly stringent performance requirements. These demands encompass high precision, efficiency, stability, robustness, ease of use, and simplicity of the user interface. Furthermore, diverse modern manufacturing applications primarily employ robotic systems within disturbed operating scenarios. This paper presents a novel neural motion-tracking control scheme for mobile manipulation robotic systems. Dynamic position output error feedback and B–Spline artificial neural networks are integrated in the design process of the introduced adaptive robust control strategy to perform efficient and robust tracking of motion-planning trajectories in robotic systems. Integration of artificial neural networks demonstrates performance improvements in the control scheme while effectively addressing common issues encountered in manufacturing environments. Parametric uncertainty, unmodeled dynamics, and unknown disturbance torque terms represent some adverse influences to be compensated for by the robust control scheme. Several case studies prove the robustness of the adaptive neural control scheme in highly coupled nonlinear six-degree-of-freedom mobile manipulation robotic systems. Case studies provide valuable insights and validate the efficacy of the proposed adaptive multivariable control scheme in manufacturing applications. [ABSTRACT FROM AUTHOR]

Biological motor control is versatile, efficient, and depends on proprioceptive feedback. Muscles are flexible and undergo continuous changes, requiring distributed adaptive control mechanisms that continuously account for the body's state. The canonical role of proprioception is representing the body state. We hypothesize that the proprioceptive system could also be critical for high-level tasks such as action recognition. To test this theory, we pursued a task-driven modeling approach, which allowed us to isolate the study of proprioception. We generated a large synthetic dataset of human arm trajectories tracing characters of the Latin alphabet in 3D space, together with muscle activities obtained from a musculoskeletal model and model-based muscle spindle activity. Next, we compared two classes of tasks: trajectory decoding and action recognition, which allowed us to train hierarchical models to decode either the position and velocity of the end-effector of one's posture or the character (action) identity from the spindle firing patterns. We found that artificial neural networks could robustly solve both tasks, and the networks' units show tuning properties similar to neurons in the primate somatosensory cortex and the brainstem. Remarkably, we found uniformly distributed directional selective units only with the action-recognition-trained models and not the trajectory-decoding-trained models. This suggests that proprioceptive encoding is additionally associated with higher-level functions such as action recognition and therefore provides new, experimentally testable hypotheses of how proprioception aids in adaptive motor control. [ABSTRACT FROM AUTHOR]

This research focuses on designing a min–max robust control based on a neural dynamic programming approach using a class of continuous differential neural networks (DNNs). The proposed controller solves the robust optimization of a proposed cost function that depends on the trajectories of a system with an uncertain mathematical model satisfying a class of non-linear perturbed systems. The dynamic programming min–max formulation enables robust control concerning bounded modelling uncertainties and disturbances. The Hamilton–Jacobi–Bellman (HJB) equation's value function, approximated by a DNN, permits to estimate the closed-loop formulation of the controller. The controller design is based on an estimated state trajectory with the worst possible uncertainties/perturbations that provide the degree of robustness using the proposed controller. The class of learning laws for the time-varying weights in the DNN is produced by studying the HJB partial differential equation. The controller uses the solution of the obtained learning laws and a time-varying Riccati equation. A recurrent algorithm based on the Kiefer–Wolfowitz method leads to adjusting the initial conditions for the weights to satisfy the final condition of the given cost function. The robust control suggested in this work is evaluated using a numerical example confirming the optimizing solution based on the DNN approximate for Bellman's value function. [ABSTRACT FROM AUTHOR]

In this article, a butterfly-like Prandtl–Ishlinskii (PI) hysteresis model and a novel neural network based adaptive implicit inverse control scheme to describe and control the butterfly-like hysteresis are proposed. The main contributions are: 1) a butterfly-like PI model is developed for the purpose of predicting the hysteresis effects and the model is feasible for controller design; 2) an implicit inverse control scheme especially for mitigating the butterfly-like hysteresis is implemented, which avoids the construction of the direct inverse of the butterfly-like PI model; 3) an adaptive implicit inverse control approach, which integrates the neural network and the implicit inverse technique into the output-feedback control is developed for eliminating the butterfly-like hysteresis and an arbitrarily small $L_{\infty }$ norm of tracking error is achieved. The proposed modeling and control methods are validated experimentally via the dielectric elastomer actuator based motion control platform. [ABSTRACT FROM AUTHOR]

Complex neural network structures may not be appropriate for adaptive control applications, as large number of variable adaptive parameters have to be updated in each time step, thus increasing the computational burden, which makes the real-time implementation of the controller difficult. In this study, the ability of the neural networks to approximate non-linear dynamic systems is used to derive a neuro-based adaptive control with minimalistic architecture. A linear neural identifier is devised, which emulates a local linear model of the system by online adjustment of its parameters. Stability and optimal rate of convergence is ensured through an adaptive learning rate, determined using Lyapunov stability theorems. The novelty of the control scheme lies in its minimalistic neural structure comprising of a single-linear neuron and, therefore, does not impose excessive computational burden on the system, making it feasible for real-time application. To assert our claims, benchmark examples from different domains are used to illustrate the effectiveness of the proposed controller. The neuro-controller is used in a water-lift plant to control the height of the water in a storage tank. Another example of a moving cart holding an inverted pendulum, an inherently unstable system that forms the basis of the robot-control mechanism, is also used. The controller is also tested on a complex non-linear higher-order power system to enhance stability by effectively damping the electromechanical oscillations. The superior performance of the controller is demonstrated by comparing with other recently reported controllers. Additional advantages of the proposed scheme include model-free control and requirement of only local measurements. The proposed method has potential applications in control problems that require adaptability, computational simplicity, and quick response. [ABSTRACT FROM AUTHOR]

This article presents an effective method to address the tracking control problem arising in uncertain switched high-order nonlinear system in strict-feedback form. The system under consideration contains unknown functions, which causally make the asymptotic tracking performance difficult to be achieved. By adopting the adding a power integrator approach in the framework of backstepping, a novel tracking controller is developed to guarantee an asymptotic tracking performance in the presence of the approximation error cased by neural networks (NNs) under arbitrary switching. The main contributions lie in: 1) the article for the first time embeds the backstepping technique in designing a kind of discontinuous controller with proportional integral (PI) compensation and 2) with the help of Filippov’s theory, a new defined system described by differential inclusions can be first obtained by taking some transformations, and then a novel nonsmooth Lyapunov function approach along with its upper right Dini derivative technique is applied to complete the construction of the discontinuous controller. Finally, two simulation examples are exhibited to verify the validity of the proposed design techniques. [ABSTRACT FROM AUTHOR]

Compared with stochastic differential equations (SDEs) driven by white noise, random differential equations (RDEs) generated by colored noise are claimed to be more practical. This article considers reduced-order high-gain observer (ROHGO)-based neural tracking control on random nonlinear systems having output delay. In order to foster the design and analysis, the estimated states and the estimation errors are scaled by the high gain of the observer. Based on neural network (NN) approximation and state observation, an adaptive controller is designed for the overall system using the backstepping method. It is proved that all the closed-loop signals are bounded almost surely, letting alone the tracking error. By tuning the related design parameters, the asymptotic tracking error could be regulated arbitrarily small. Within the best of our knowledge, this article serves as the first attempt for NN-based control on RDE systems. Finally, the validity of main results is confirmed by a simulation example. [ABSTRACT FROM AUTHOR]

This article presents an adaptive control framework for dynamically reconfigurable battery (DRB) systems based on the deep reinforcement learning method. The proposed adaptive control framework relies on deep Q-network to learn the DRB system operations. By utilizing its model-free nature, the proposed framework can significantly reduce the complexity of building experiences or expert models for DRB systems as well as improve battery operating time by ensuring cell balancing. Extensive simulation and experimental study has been carried out with data gathered from a real-world DRB testbed, and the results show the effectiveness and efficiency of the proposed control framework. [ABSTRACT FROM AUTHOR]

This article considers the problem of adaptive prescribed performance tracking control via slow switching for a general class of uncertain switched nonlinear systems (SNSs) with unmodeled dynamics (UDs) and nonstrict-feedback structure. The UDs are not in their form of the input-to-state practical stability and their state information is unmeasurable. By reassigning the function variables, the coupling effects between UDs and the prescribed performance function are eliminated through the iterative process. In virtue of the neural networks (NNs) approximation capability, a novel adaptive backstepping procedure is proposed without adding extra first-order filters. By choosing an appropriate slow switching law, all the signals of the closed-loop system are bounded, and the system output tracks the reference signal with a prescribed performance level (PPL). [ABSTRACT FROM AUTHOR]

This article aims at proposing an adaptive neural control strategy for a class of nonlinear time-delay systems with input delays and unknown control directions. Different from previous researches that investigated delays and constraints separately, the novelty of this article lies in that it simultaneously considers delays (state and input delays) and input constraints (magnitude and rate constraints) for a class of uncertain nonlinear systems. In this article, the uncertain states and input delays are handled by integrating a constructed auxiliary system that functions as an observer with neural networks (NNs), with which the adverse effects caused by the uncertain states and input delays can be approximated and compensated. By involving smooth hyperbolic tangent functions in the designed auxiliary system, the problem of magnitude and rate constraints of the control input is fully addressed. Then, the backstepping technique runs through the entire control designing process, which allows the designed adaptive neural control strategy to handle the input constraints and delays at the same time. Furthermore, Nussbaum functions are employed to resolve the problem of unknown control directions. Due to the introduction of an input-driven filter, only the output of the system is required to be measured as the control feedback, which promotes the applicability of the designed controller. Under the proposed control scheme, semiglobal, uniform, and ultimate boundedness of all signals of the closed-loop system is realized with uncertain control directions, input and state delays, and guaranteed magnitude and rate constraints of control inputs. Finally, simulation results are illustrated to verify the effectiveness of the presented control method. [ABSTRACT FROM AUTHOR]

Teaching evaluation is a crucial measure to improve the quality of education. It is essential to formulate a scientific and reasonable evaluation system for teaching in colleges and universities. Teaching is a dynamic process, which makes it challenging to evaluate it comprehensively. However, as a new technology, the artificial neural network has the characteristics of nonlinear processing, adaptive learning, and high fault tolerance for various evaluation problems. This article first analyzes the current status of physical education and proposes solutions that comprehensively improve the quality of physical education in colleges and other institutions. It also suggests that a scientific evaluation of teaching in colleges provides a better feedback, incentives, and guidance, respectively. A model for the quality evaluation of physical education in colleges is established using artificial neural network. This model quantifies the concept of teaching evaluation index into actual data as its input, and teaching effect as output. The use of artificial neural network framework maps the input with output using an internally configured decision support system. Furthermore, it uses relevant software to conduct empirical research. The results show that this model enhances the quality of teaching evaluation, which not only overcomes the subjective factors of experts in the evaluation process but also produces satisfactory evaluation result. [ABSTRACT FROM AUTHOR]

Meta-learning is a branch of machine learning which trains neural network models to synthesize a wide variety of data in order to rapidly solve new problems. In process control, many systems have similar and well-understood dynamics, which suggests it is feasible to create a generalizable controller through meta-learning. In this work, we formulate a meta reinforcement learning (meta-RL) control strategy that can be used to tune proportional–integral controllers. Our meta-RL agent has a recurrent structure that accumulates "context" to learn a system's dynamics through a hidden state variable in closed-loop. This architecture enables the agent to automatically adapt to changes in the process dynamics. In tests reported here, the meta-RL agent was trained entirely offline on first order plus time delay systems, and produced excellent results on novel systems drawn from the same distribution of process dynamics used for training. A key design element is the ability to leverage model-based information offline during training in simulated environments while maintaining a model-free policy structure for interacting with novel processes where there is uncertainty regarding the true process dynamics. Meta-learning is a promising approach for constructing sample-efficient intelligent controllers. • An expert agent recognizes and controls any process in a large class. • Offline training leads to sample-efficient online operation and adaptation. • The online agent adapts automatically as plant characteristics drift. • The agent adjusts PI parameters instead of directly actuating the plant. • meta-RL design generalizes to various plant and controller structures. [ABSTRACT FROM AUTHOR]

This article discusses the evolution of control strategies in the field of drying technology, specifically focusing on the application of artificial intelligence (AI) for intelligent drying. The article highlights the importance of setting specific objectives, such as energy efficiency and product quality, in order to optimize drying strategies. It traces the historical development of drying strategies from primitive open-air drying to industrial drying methods, and discusses the challenges faced in controlling drying processes. The article also explores the potential of multi-objective optimization and adaptive control strategies, which utilize AI technologies to monitor and adjust drying parameters in real-time. The integration of machine vision and machine learning is identified as a promising approach to improve the efficiency of industrial drying systems. [Extracted from the article]

In this article, the model‐based event‐triggered neural learning control problem is investigated for a class of discrete‐time strict‐feedback systems. First, with the case of sufficient network resources, an adaptive neural controller is designed with a new neural weight update law, which avoids the n$$ n $$‐step delay of traditional adaptive neural control methods. The proposed controller performs the tracking control task while ensuring that the radial basis function neural network can accurately identify the unknown system nonlinear dynamics and the estimated neural weights can converge to their ideal values. Second, with the case of limited network resources, the convergent neural weights can be reused to construct the neural network model, event‐trigger conditions, and the neural learning controller, which can improve the tracking control performance and save the communication resources. Especially, compared with the traditional event‐triggered adaptive neural controller, the neural learning controller can reduce the burden of online calculations since the constant neural weights are used to construct the neural network model and trigger conditions. For the proposed control scheme, simulation results are given to verify its effectiveness. [ABSTRACT FROM AUTHOR]

This article develops a self-triggered adaptive neural network (NN) tracking controller for a class of continuous-time nonlinear systems, that is, input constrained and with unknown drift and input dynamics. Since the drift and input dynamics are both unknown, an NN is built within a self-triggered update paradigm to approximate the unknown tracking control. The error derivative used in the weight update algorithm is derived using a robust exact differentiator technique. To address input constraints, an auxiliary compensator is designed for the unimplemented control effort. Through rigorous Lyapunov analyses, we can guarantee that all the tracking and weight errors are uniformly ultimately bounded. Finally, to show the effectiveness of the proposed control performance, simulation results of a two-link robot are provided and analyzed. [ABSTRACT FROM AUTHOR]

With the rise of Erhu teaching in recent years, a large number of people have joined the team to learn Erhu playing. However, due to the high cost of teaching and the unique one-to-one teaching mode between teachers and students, Erhu education resources are very scarce. Learning Erhu performance has become a luxury activity. Nowadays, with the rise of artificial intelligence, computer music is developing rapidly. Music has two important aspects: composition and performance. Different kinds of instruments convey different styles, and players inject different rhythms and dynamics into their performance, thus producing rich expressive force. The development of image style conversion, which opens people's evaluation of music performance, is an important issue in many fields of artificial intelligence (it is also known as intelligence, machine intelligence, referring to the intelligence shown by the machine made by people. Usually, artificial intelligence refers to the technique of presenting human intelligence through ordinary computer programs). For an Erhu song, there are various factors that affect its effectiveness, and there are many indexes to evaluate it, such as sense of rhythm, expressive force, musical sense, style, and so on. Using a computer to simulate the evaluation process is essential to find out the mathematical relationship between the factors that affect the performance of music and the evaluation indexes. Neural network is a kind of mathematical model proposed by simulating the way of thinking of human brain in artificial intelligence. It has the advantages of not having strict requirements on data distribution, nonlinear data processing method, strong robustness, and dynamics and is very suitable for the mathematical model of evaluation system. In addition, the neural network also has a strong theoretical basis, and their application in various industries has developed basically mature. This paper tries to introduce a deep neural network mathematical model into the evaluation system of Erhu performance, and the experimental results prove the reliability and practicality of the method in this paper. It can provide a method basis and theoretical reference for evaluation of Erhu performance effect. [ABSTRACT FROM AUTHOR]

A recurrent wavelet first-order neural network (RWFONN) is proposed to select a desired attractor in a multistable erbium-doped fiber laser (EDFL). A filtered error algorithm is used to classify coexisting EDFL states and train RWFONN. The design of the intracavity laser power controller is developed according to the RWFONN states with the block control linearization technique and the super-twisting control algorithm. Closed-loop stability analysis is performed using the boundedness of synaptic weights. The efficiency of the control method is demonstrated through numerical simulations. [ABSTRACT FROM AUTHOR]

An adaptive deep neural network is used in an inverse system identification setting to approximate the inverse of a nonlinear plant with the aim of constituting the plant controller by copying to the latter the weights and architecture of the converging deep neural network. This deep learning (DL) approach to the adaptive inverse control (AIC) problem is shown to outperform the adaptive filtering techniques and algorithms normally used in adaptive control, especially when in nonlinear plants. The deeper the controller, the better the inverse function approximation, provided that the nonlinear plant has an inverse and that this inverse can be approximated. Simulation results prove the feasibility of this DL-based adaptive inverse control scheme. The DL-based AIC system is robust to nonlinear plant parameter changes in that the plant output reassumes the value of the reference signal considerably faster than with the adaptive filter counterpart of the deep neural network. The settling and rise times of the step response are shown to improve in the DL-based AIC system. [ABSTRACT FROM AUTHOR]

This article investigates optimal control problem for a class of discrete-time (DT) nonlinear systems with unknown dynamics. With the help of a broad learning system (BLS), a novel online adaptive dynamic programming (ADP) controller is presented. First, to approximate the unknown system dynamics, an approximator based on BLS is presented. The connection weights are calculated by the data of the system by using the ridge regression algorithm. Then, two BLSs are adopted to approximate the optimal cost function and optimal control law, respectively. The connection weights of these two BLSs are updated using the given weights tuning law at each sampling instant. The proposed optimal controller is proved to ensure that all the system states and estimation errors are uniform ultimate bounded. Finally, simulation examples are carried out to further demonstrate the effectiveness of the proposed BLS-based approximator and optimal controller. [ABSTRACT FROM AUTHOR]

Summary: This article focuses on the adaptive asymptotic learning tracking control problem of nonlinear systems with full state constraints. First, an adaptive neural network tracking algorithm is proposed which combines a time‐varying feedback element and robust compensation feedback element in the form of smooth function to guarantee that output signal tracks the reference signal asymptotically. Apart from this, a time‐varying integral barrier Lyapunov function is utilized to ensure that the system states are always kept in the constraint region. Furthermore, the event‐triggered mechanism is designed to efficiently reduce unnecessary transmissions. Compared with the other literatures, the original state constraint problem is directly solved by the proposed adaptive control algorithm. Finally, simulation is included to validate the built theoretical results. [ABSTRACT FROM AUTHOR]

Since the variable-order fractional systems show more complex characteristics and more degrees of freedom due to time-varying fractional derivatives, we introduce a variable-order fractional Hopfield-like neural network in this paper. First, the properties and dynamical behavior of the system are studied. The variable-order derivative's effects on the system's behavior are investigated through the Lyapunov exponents and bifurcation diagram; an emerging Feigenbaum tree of period-4 bubble is observed, which appears with the creation and annihilation of periodic orbits. A general basin of attraction for the fractional-order neural network is presented, demonstrating that its dynamical behaviors are extremely sensitive to initial conditions resulting in different periodic orbits and chaotic attractors' coexistence. After that, an adaptive control scheme is proposed for the variable-order fractional system. Through Lyapunov theorem and Barbalat's Lemma, the system's convergence and stability under the proposed control scheme are proven. The main advantages of the proposed controller are its guaranteed stability, robustness against uncertainties, and simplicity. Finally, the synchronization results are presented. Numerical simulations show the excellent performance of the proposed controller for the variable-order fractional Hopfield-like neural network. [ABSTRACT FROM AUTHOR]

This paper presents an adaptive control system for coordinated metro operations with flexible train composition by using a multi-agent deep reinforcement learning (MADRL) approach. The control problem is formulated as a Markov decision process (MDP) with multiple agents regulating different service lines in a metro network with passenger transfer. To ensure the overall computational effectiveness and stability of the control system, we adopt an actor–critic reinforcement learning framework in which each control agent is associated with a critic function for estimating future system states and an actor function deriving local operational decisions. The critics and actors in the MADRL are represented by multi-layer artificial neural networks (ANNs). A multi-agent deep deterministic policy gradient (MADDPG) algorithm is developed for training the actor and critic ANNs through successive simulated transitions over the entire metro network. The developed framework is tested with a real-world scenario in Bakerloo and Victoria Lines of London Underground, UK. Experiment results demonstrate that the proposed method can outperform previous centralized optimization and distributed control approaches in terms of solution quality and performance achieved. Further analysis shows the merits of MADRL for coordinated service regulation with flexible train composition. This study contributes to real-time coordinated metro network services with flexible train composition and advanced optimization techniques. • An adaptive rail transit control system with passengers' transfers and flexible train composition. • A novel modeling and optimization framework based on multi-agent deep reinforcement learning. • A computational framework with 'decentralized execution and centralized training' for effectiveness and stability. • Case study demonstrating the system efficiency and computational effectiveness of proposed algorithm over previous methods. [ABSTRACT FROM AUTHOR]

Unlike the traditional path following being lack of virtual-reality interaction, this paper investigates the parallel path following control problem of cyber–physical maritime autonomous surface ships. By integrating an artificial system, computational experiments, and parallel execution, a parallel path following control method is proposed to achieve the interaction between virtual space and real space. Specifically, a deep neural predictor based on deep neural networks through dual time-scale adaptation is proposed to establish the artificial system such that the real-time synchronization between the artificial system and actual system is realized. In the computational experiments, a parallel path following control law is developed based on the recovered information from deep neural predictor. In the parallel execution, the parallel control law is used to drive both the artificial system and the actual system simultaneously. Finally, by using the cascade theory, it is proven that the entire parallel path following control system is input-to-state stable and all signals are uniformly ultimately bounded. Simulation results demonstrate the effectiveness and reliability of the proposed parallel path following control method. • A parallel control method is proposed for path following based on ACP approach. • Deep neural predictor is proposed to establish the artificial MASS system. • A dual time-scale deep neural networks is proposed to realize the real-time synchronization between the artificial system and actual system. [ABSTRACT FROM AUTHOR]

As a typical underactuated mechanical system, offshore ship-mounted cranes are widely used to carry out the tasks of transferring cargos from one ship to another in the marine environment. Different from land-fixed cranes as well as traditional harbor cranes, offshore ship-to-ship crane systems work in two noninertial (ship) frames, while the target locations of the cargos are also inevitably influenced by the movements of the target ship. Besides, various external disturbances, which are caused by persistent sea waves, sea winds, or currents, etc., bring much more challenges to the control task of offshore ship-to-ship crane systems. To properly address these practical problems, in this article, we propose an increased adaptive neural network (NN)-based anti-swing tracking control strategy for such coordinated offshore crane systems, with a ship-motion prediction algorithm suggested to generate the target trajectories for cargos, and an adaptive NN proposed to deal with complicated unknown wave-induced disturbances. Bounded tracking performance is also guaranteed through a complete Lyapunov-based stability analysis. To the best of our knowledge, without any simplification of the original nonlinear dynamics, this article provides a high-performance adaptive control approach to deal with the anti-interference tracking control problem for offshore ship-to-ship crane systems, which are subjected to trajectories uncertainties as well as unknown wave motions disturbances. Furthermore, comparative hardware experimental results are presented to demonstrate the efficiency of the proposed control method. [ABSTRACT FROM AUTHOR]

This article investigates the tracking problem of an uncertain $n$ -link robot manipulator with guaranteed safety and performance. To tackle parametric uncertainties, the torque filtering-augmented concurrent learning (CL) method is introduced for online identification of the unknown system without requirements of joints acceleration. By using CL, the parameter convergence is guaranteed by exploiting the current and historical data simultaneously. This technique enjoys practicability compared with common methods that need to incorporate external noises to satisfy the persistence of excitation condition for the parameter convergence. Based on the estimated model, we design a barrier Lyapunov function (BLF)-based adaptive control law by the backstepping technique and Lyapunov analysis. By ensuring the boundness of the BLF, the system output and the tracking error are proved to lie in the safety set and performance set, respectively. Numerical simulation results and experiment tests validate the proposed strategy. [ABSTRACT FROM AUTHOR]

A water supply system is considered an essential service to the population as it is about providing an essential good for life. This system typically consists of several sensors, transducers, pumps, etc., and some of these elements have high costs and/or complex installation. The indirect measurement of a quantity can be used to obtain a desired variable, dispensing with the use of a specific sensor in the plant. Among the contributions of this technique is the design of the pressure controller using the adaptive control, as well as the use of an artificial neural network for the construction of nonlinear models using inherent system parameters such as pressure, engine rotation frequency and control valve angle, with the purpose of estimating the flow. Among the various contributions of the research, we can highlight the suppression in the acquisition of physical flow meters, the elimination of physical installation and others. The validation was carried out through tests in an experimental bench located in the Laboratory of Energy and Hydraulic Efficiency in Sanitation of the Federal University of Paraiba. The results of the soft sensor were compared with those of an electromagnetic flux sensor, obtaining a maximum error of 10%. [ABSTRACT FROM AUTHOR]

This article considers the Nussbaum gain adaptive control issue for a type of nonlinear systems, in which some sophisticated and challenging problems, such as periodic disturbances, dead zone output, and unknown control direction are addressed. The Fourier series expansion and radial basis function neural network are incorporated into a function approximator to model time-varying-disturbed function with a known period in nonlinear systems. To deal with the problems of the dead zone output and unknown control direction, the Nussbaum-type function is recommended in the design of the control algorithm. Applying the Lyapunov stability theory and backstepping technique, the proposed control strategy ensures that the tracking error is pulled back to a small neighborhood of origin and all closed-loop signals are bounded. Finally, simulation results are presented to show the availability and validity of the analysis approach. [ABSTRACT FROM AUTHOR]

The paper demonstrates an enhancement in the mobile robot's performance during trajectory tracking with static obstacles. An adaptive artificial neural network (ANN) control methodology with online tuning evolutionary slice genetic algorithm is used for the motion control of the nonlinear dynamics mobile robot system. This paper aims at locating the optimal path from the starting point to the target point and designing an ANN trajectory tracking control methodology. The algorithm is simulated with fixed-global environment obstacles to demonstate the effectiveness of the ANN controller and the evolutionary optimization algorithm in terms of the shortest path length generated and the minimum number of the evaluation cost function calculated. The simulation results illustrate that the ANN controller's parameters are obtained quickly, generating smooth wheels' torque actions for the mobile robot platform with a minimum cost function evolution that lead to minimize the tracking error to approximately zero with no oscillation in the responses. [ABSTRACT FROM AUTHOR]

A debutanizer column located at a refinery in Malaysia produces LPG as its top product and light naphtha as its bottom product. Control of the product compositions of the column is very important to maintain the desired purities. The current control design of the debutanizer column is based on the classical proportional integral derivative approach, which has been found to be less effective in controlling the variations in the column as the process is characterized by strong nonlinear and uncertain dynamics. Here, intelligent control based on an adaptive neuro‐fuzzy inference system (ANFIS) is investigated and compared against an artificial neural network, for the special case of limited training data of the industrial debutanizer column. The ANFIS‐based controller outperforms the other control configurations for both set point tracking and disturbance rejection cases and has better generalization performance even when trained with limited data samples. [ABSTRACT FROM AUTHOR]