Neural Control Research Articles

Fixed-time prescribed performance control for nonlinear multi-agent systems with novel uncertainties

This paper addresses an approach to fixed-time prescribed performance control design for multi-agent systems with novel uncertainties, i.e., the uncertainties from system input powers, and a new neural backstepping control design is proposed such that the prescribed performance can be guaranteed within a fixed-time. Unlike existing adaptive results, the upper boundary of stability time is decided only by the design parameters and also is independent of the initial states of the system. By leveraging Lyapunov stability theory and graph theory, it is demonstrated that every follower agent can synchronize to the leader agent, and tracking errors converge to the origin’s neighborhood. Finally, the simulation results verify the effectiveness of the control strategy.

Artificial Neural Network-Based Hybrid Controller for Electric Vehicle Applications

Power management among different energy sources of electric vehicles (EV) is one of the complex issues during the transition from one to another. A specific control is modeled based on the current and speed range of the electric motor named as Measurement of Parameter-Based Controller (MPBC), which will play a key role during transition of energy sources as per the load requirement. Two bidirectional converters are utilized to control the pulse signals generated by the traditional controllers which are connected at the battery and Supercapacitors (SCap) ends, which are treated as passive sources of the system. The Controller's artificial neural network (ANN), fuzzy logic (FLC), and proportional-integral (PI) are utilized to generate the pulse signal to the switches present in the converters by load. Further, specific controller MPBC is combined with three controllers ANN/FLC/PI individually and obtained three separate hybrid controllers as per the proposed control technique. The MPBC+PI/FLC/ANN controller-based MATLAB/Simulink model was designed, and applied to the electric motor individually at different load conditions. This model considered three different power delivery states from the PV array and assessed the motor's performance under different load scenarios. Compare the three hybrid controllers' final results to find out which one is more effective than the others.

Steering-Angle Prediction and Controller Design Based on Improved YOLOv5 for Steering-by-Wire System.

A crucial role is played by steering-angle prediction in the control of autonomous vehicles (AVs). It mainly includes the prediction and control of the steering angle. However, the prediction accuracy and calculation efficiency of traditional YOLOv5 are limited. For the control of the steering angle, angular velocity is difficult to measure, and the angle control effect is affected by external disturbances and unknown friction. This paper proposes a lightweight steering angle prediction network model called YOLOv5Ms, based on YOLOv5, aiming to achieve accurate prediction while enhancing computational efficiency. Additionally, an adaptive output feedback control scheme with output constraints based on neural networks is proposed to regulate the predicted steering angle using the YOLOv5Ms algorithm effectively. Firstly, given that most lane-line data sets consist of simulated images and lack diversity, a novel lane data set derived from real roads is manually created to train the proposed network model. To improve real-time accuracy in steering-angle prediction and enhance effectiveness in steering control, we update the bounding box regression loss function with the generalized intersection over union (GIoU) to Shape-IoU_Loss as a better-converging regression loss function for bounding-box improvement. The YOLOv5Ms model achieves a 30.34% reduction in weight storage space while simultaneously improving accuracy by 7.38% compared to the YOLOv5s model. Furthermore, an adaptive output feedback control scheme with output constraints based on neural networks is introduced to regulate the predicted steering angle via YOLOv5Ms effectively. Moreover, utilizing the backstepping control method and introducing the Lyapunov barrier function enables us to design an adaptive neural network output feedback controller with output constraints. Finally, a strict stability analysis based on Lyapunov stability theory ensures the boundedness of all signals within the closed-loop system. Numerical simulations and experiments have shown that the proposed method provides a 39.16% better root mean squared error (RMSE) score than traditional backstepping control, and it achieves good estimation performance for angles, angular velocity, and unknown disturbances.

Comparative Study of Semi-Active Control Effectiveness of Structures on Soft Soil Using MR Damper: Shaking Table Investigation

The effect of soil-structure interaction (SSI) cannot be neglected in semi-active vibration control of structures located on soft soil. To investigate the mitigating effect of magnetorheological (MR) damper on the semi-active control of structures considering the SSI, shaking table tests were conducted to evaluate the performance of the MR damper-based semi-active control system for structures on soft soil. In addition to a novel fuzzy control method based on online learning deep neural network (OL-DFNN), various control strategies, including passive OFF, passive ON, ON–OFF and deep neural network fuzzy control (DFNN) were systematically evaluated. The test results showed that the OL-DFNN control method exhibited superior adaptability to varying ground motion and structural dynamic characteristics compared to the other control methods. In particular, the OL-DFNN controller effectively mitigated the peak displacement and root mean square displacement, outperforming the passive OFF, passive ON, ON–OFF and DFNN control strategies. The test results highlight the effectiveness of the OL-DFNN control method in addressing the challenges posed by dynamic and time-varying characteristics in structural vibration control systems considering SSI.

Brief History of the Uncontrolled Manifold Hypothesis and Its Role in Motor Control

BACKGROUND: The apparent problem of motor redundancy was replaced by the principle of abundance and turned into a theoretical framework and associated toolbox for exploration of performance-stabilizing synergies. AIM and METHOD: We review briefly the development of the main methods within the UCM framework and some of the main findings, both basic and clinical. The UCM framework is naturally merged with the theory of hierarchical movement control with spatial referent coordinates. RESULTS: The UCM framework has established itself as a productive framework for the analysis of movement control, in particular as related to stability of salient performance variables. It led to the discovery of novel phenomena such as trade-offs within hierarchical systems, anticipatory synergy adjustments, synergies within systems of different complexity from single muscles to the whole body. It has also led to promising results offering sensitive biomarkers to various neurological disorders. Recent experiments suggest the existence of three main levels of organization of performance-stabilizing synergies tentatively associated with cortical, subcortical, and spinal circuitry. CONCLUSION: Currently, this approach is in its adulthood. Further progress may be expected in focusing on spaces of neural control variables, developing the method for analysis across species, and expanding the range and depth of clinical studies.

Terra incognita of the uncontrolled manifold (UCM).

The review addresses the central concept of the uncontrolled manifold (UCM) hypothesis, which has become a major framework for analysis of performance-stabilizing motor synergies. The major goals are to summarize the status quo in the field and to ask new questions stimulating new studies. We focus on a few main questions: What is the UCM? What are the likely neural origins of the UCM? How is the UCM reflected in movement patterns? Are properties of the UCM similar in all directions? We contrast experience-based features of movements seen very soon after the movement initiation vs. those based on on-line sensory feedback signals. Further, we address a number of poorly explored issues such as the differences in characteristic times of processes within the UCM and orthogonal to the UCM space, the interplay between movement stability and optimality, the origin of preferred sharing patterns of performance variables across abundant sets of elements and of their inter-trial variability, problems with the UCM-based analysis in different spaces, and likely neurophysiological mechanisms contributing to the UCM formation. In particular, we focus on the UCM in spaces of hypothetical neural control variables, which we associate with the reciprocal and coactivation commands to the effectors. Analysis of performance-stabilizing synergies within the UCM framework in abundant spaces of kinetic, kinematic and electromyographic variables at the selected level of analysis may be practically useful. However, mapping findings in such studies onto neural control mechanisms has been challenging.

Neural Network Adaptive Inverse Control of Flexible Joint Space Manipulator Considering the Influence of Gravity.

With the aim of correcting the problem of trajectory tracking control of a flexible joint space manipulator in environments with different gravity, a neural network adaptive inverse control algorithm based on singular perturbation theory is proposed to resist the disturbance caused by system uncertainty. Firstly, the dynamic model of a flexible joint space manipulator with the influence of gravity is established, and then the system is divided into a fast subsystem and a slow subsystem using singular perturbation theory. The velocity feedback control rate is designed for the fast subsystem to suppress the elastic vibration caused by the joint flexibility. For the slow subsystem, the uncertain term and known term are separated by the inverse control algorithm, where the uncertain term is approximated online by the RBF neural network, and the robust control rate is designed to compensate for the approximation error. The simulation results show that the control method can not only effectively reduce the high-frequency vibration caused by the flexible joint but also resist the system disturbance so that a good track control effect is achieved.

Approximation-based adaptive two-bit-triggered bipartite tracking control for nonlinear networked MASs subject to periodic disturbances

PurposeThis paper aims to investigate the problem of adaptive bipartite tracking control in nonlinear networked multi-agent systems (MASs) under the influence of periodic disturbances. It considers both cooperative and competitive relationships among agents within the MASs.Design/methodology/approachIn response to the inherent limitations of practical systems regarding transmission resources, this paper introduces a novel approach. It addresses both control signal transmission and triggering conditions, presenting a two-bit-triggered control method aimed at conserving system transmission resources. Additionally, a command filter is incorporated to address the problem of complexity explosion. Furthermore, to model the uncertain nonlinear dynamics affected by time-varying periodic disturbances, this paper combines Fourier series expansion and radial basis function neural networks. Finally, the effectiveness of the proposed methodology is demonstrated through simulation results.FindingsBased on neural networks and command filter control method, an adaptive two-bit-triggered bipartite control strategy for nonlinear networked MASs is proposed.Originality/valueThe proposed control strategy effectively addresses the challenges of limited transmission resources, nonlinear dynamics and periodic disturbances in networked MASs. It guarantees the boundedness of all signals within the closed-loop system while also ensuring effective bipartite tracking performance.

Observer-based adaptive neural network control: the convergence properties analysis under the influence of persistent excitation level

Observer-based adaptive neural network control: the convergence properties analysis under the influence of persistent excitation level

Nonlinear Adaptive Neural Control of Power Converter‐Driven DC Motor System: Design and Experimental Validation

ABSTRACTThis article presents an intelligent adaptive neural control scheme to track the output speed trajectory in power converter‐driven DC motor system. The proposed technique integrates an adaptive polynomial‐neural network with a backstepping strategy to yield a robust control system for output tracking in DC motor. Such a unification of online neural network‐based estimation and adaptive control, results in effective regulation of the output across a wide load torque uncertainties, besides yielding a promising transient and steady‐state performance. The stability of the entire closed‐loop system is ensured through Lyapunov stability criterion. The efficacy of the proposed strategy is revealed through an extensive experimental investigation under various operating points during start‐up, step‐reference tracking, and external step‐load torque disturbances. The real‐time experimentation is conducted on a laboratory prototype of power converter‐driven DC motor of 200 W, using dspace DS1104 control board with MPC8240 processor. The results obtained confirm an improvement in the transient response of the output speed by significantly reducing the settling time to and yielding a steady state behavior with no peak over/undershoots during load disturbances, in contrast to other similar works presented in the literature intended for same the application.

Cluster formation tracking of networked perturbed robotic systems via hierarchical fixed-time neural adaptive approach

This paper investigates the fixed-time cluster formation tracking (CFT) problem for networked perturbed robotic systems (NPRSs) under directed graph information interaction, considering parametric uncertainties, external perturbations, and actuator input deadzone. To address this complex problem, a novel hierarchical fixed-time neural adaptive control algorithm is proposed based on a hierarchical fixed-time framework and a neural adaptive control strategy. The objective of this study is to achieve accurate CFT of NPRSs within a fixed time. Specifically, we design a distributed observer algorithm to estimate the states of the virtual leader within a fixed time accurately. By using these observers, a neural adaptive fixed-time controller is developed in the local control layer to ensure rapid and reliable system performance. Through the use of the Lyapunov argument, we derive sufficient conditions on the control parameters to guarantee the fixed-time stability of NPRSs. The theoretical results are eventually validated through numerical simulations, demonstrating the effectiveness and robustness of the proposed approach.

A multi-objective indirect neural adaptive processes control design for minimization of energy consumption: An experimental validation on a transesterification reactor

Nowadays, energy management environment is a very important issue that technologies have focused on in order to save costs and minimize energy waste. This objective can be achieved by means of an energy resource management approach through an appropriate optimization technique. However, energy savings can conflict with other objective functions, to solve the problem a multi-objective optimization that considers the minimization of the control energy can be adopted. In this paper, we propose to use a multi-objective indirect neural adaptive control concept for nonlinear systems with unknown dynamics. The control scheme consists of an adaptive instantaneous neural emulator and neural controller built on fully connected real-time recurrent learning networks (RTRL). The multi-objective particle swarm optimization (MOPSO) algorithm is used as a mechanism to find NE and NC adaptive learning rates that optimize the proposed objective functions: control energy minimization and closed-loop preservation. Comparative studies and experimental validation on a semi-batch reactor, used to generate cleaner biofuels, are performed to confirm the effectiveness of the proposed strategy.

Distributed Neural Adaptive Impedance Control for Cooperative Manipulation With Unknown Objects.

Existing cooperative manipulation methods for multiple manipulator systems usually assume that the grasp matrix and the desired trajectory of each manipulator are known in advance. In this work, distributed neural adaptive impedance control (AIC) strategies integrating fully distributed observers are proposed to remove both limitations. Specifically, two fully distributed finite-time observers are designed to estimate the actual and ideal states of the reference point without using global information. The estimates of the grasp matrix and the desired trajectory of each end-effector (EE) are then obtained by kinematic constraints and the estimates of the reference point's states. At the controller development, a distributed adaptive impedance model is established to achieve an adaptive trade-off between tracking performance and compliance. Then, distributed neural network (NN)-based tracking control strategies are developed to asymptotically realize the desired adaptive impedance dynamics in the presence of uncertainties. Additionally, a virtual energy tank (EK) is employed to interact with the impedance system to correct the adaptive impedance laws for system passivity. A simulation for four mobile manipulators tightly cooperative transport an unknown object is carried out to demonstrate the established results.

Enhanced predictive PDF control of stochastic distribution systems with neural network compensation and its application

Compared to the conventional control algorithms that use mean and variance as indicators, predictive probability density function (PDF) control can effectively handle the output PDF control problem of non-Gaussian stochastic distribution systems. However, the existing predictive PDF control method does not consider the construction error between output PDF and weight, thus the control performance is still unsatisfactory. Therefore, this paper proposes a new Enhanced Predictive PDF control method (En-PDF) to improve the output PDF control performance of stochastic distribution systems. The proposed method mainly consists of two parts: the predictive PDF control part and the neural network compensation control part aiming to reduce the bias of output PDF. First, the Radical Basis Functions (RBFs) are used to approximate the PDF of the stochastic systems output, and then a prediction model representing the relationship between input and weight is established using the subspace identification algorithm to design the predictive PDF control for the stochastic systems. Next, the Kullback-Leibler (KL) divergence is used to measure the similarity between the output PDF and the set PDF, combined with the weight error and compensation to design a new performance index. Based on this, the parameters of the neural network are adjusted using the gradient descent algorithm to obtain the optimal compensation, and the stability and tracking performance of the proposed algorithm are analyzed using inductive reasoning method. Finally, the predictive PDF control input with the compensation work together on the controlled plant to achieve high-performance control of the output PDF of non-Gaussian stochastic distribution systems. Both simulation experiments and physical control experiments validate the effectiveness and superiority of the proposed method.

A click-based electrocorticographic brain-computer interface enables long-term high-performance switch scan spelling.

Brain-computer interfaces (BCIs) can restore communication for movement- and/or speech-impaired individuals by enabling neural control of computer typing applications. Single command click detectors provide a basic yet highly functional capability. We sought to test the performance and long-term stability of click decoding using a chronically implanted high density electrocorticographic (ECoG) BCI with coverage of the sensorimotor cortex in a human clinical trial participant (ClinicalTrials.gov, NCT03567213) with amyotrophic lateral sclerosis. We trained the participant's click detector using a small amount of training data (<44 min across 4 days) collected up to 21 days prior to BCI use, and then tested it over a period of 90 days without any retraining or updating. Using a click detector to navigate a switch scanning speller interface, the study participant can maintain a median spelling rate of 10.2 characters per min. Though a transient reduction in signal power modulation can interrupt usage of a fixed model, a new click detector can achieve comparable performance despite being trained with even less data (<15 min, within 1 day). These results demonstrate that a click detector can be trained with a small ECoG dataset while retaining robust performance for extended periods, providing functional text-based communication to BCI users.

Exploring the link between comorbid insomnia and sleep apnea (COMISA) and erectile dysfunction: implications for male sexual health.

This review explores the interplay between comorbid insomnia and sleep apnea (COMISA) and erectile dysfunction (ED), 2 conditions that significantly impact men's health. COMISA, a recently recognized condition characterized by the coexistence of insomnia and obstructive sleep apnea, has been shown to disrupt sleep architecture and cause intermittent hypoxia. These disturbances are increasingly linked to the exacerbation of ED, a prevalent issue among men. Understanding the connection between COMISA and ED is crucial for developing integrated treatment approaches that address both sleep and sexual health. We aim to explore the epidemiological, physiological, and potential therapeutic intersections of COMISA and ED. This review sets out to develop a better understanding of the relationship between these conditions and to emphasize the need for an integrated diagnostic and therapeutic approach that addresses both sleep and sexual health. Through a comprehensive analysis, including a detailed examination of extant studies, we address the hormonal imbalances and alterations in neural pathways that collectively contribute to the complex pathophysiology of ED and how these are particularly susceptible to the concurrent presence of COMISA. Our analysis indicates that disruptions in sleep architecture and intermittent hypoxia associated with COMISA can exacerbate ED. Hormonal imbalances, endothelial dysfunction, autonomic imbalance, and increased inflammation and oxidative stress are key mechanisms through which COMISA influences ED. These factors collectively impair vascular health, reduce testosterone levels, disrupt neural control of erections, and contribute to the severity of ED. This review underscores the necessity for an integrated approach to diagnosis and therapy that considers both sleep and sexual health to improve overall outcomes. These insights should foster a deeper understanding of the relationship between COMISA and ED, encourage further research in this area, and potentially lead to the development of innovative treatment strategies to manage these closely intertwined health concerns.

Intelligent Robust Controllers Applied to an Auxiliary Energy System for Electric Vehicles

This paper presents two intelligent robust control strategies applied to manage the dynamics of a DC-DC bidirectional buck–boost converter, which is used in conjunction with a supercapacitor as an auxiliary energy system (AES) for regenerative braking in electric vehicles. The Neural Inverse Optimal Controller (NIOC) and the Neural Sliding Mode Controller (NSMC) utilize identifiers based on Recurrent High-Order Neural Networks (RHONNs) trained with the Extended Kalman Filter (EKF) to track voltage and current references from the converter circuit. Additionally, a driving cycle test tailored specifically for typical urban driving in electric vehicles (EVs) is implemented to validate the efficacy of the proposed controller and energy improvement strategy. The proposed NSMC and NIOC are compared with a PI controller; furthermore, an induction motor and its corresponding three-phase inverter are incorporated into the EV control scheme which is implemented in Matlab/Simulink using the “Simscape Electrical” toolbox. The Mean Squared Error (MSE) is computed to validate the performance of the neural controllers. Additionally, the improvement in the State of Charge (SOC) for an electric vehicle battery through the control of buck–boost converter dynamics is addressed. Finally, several robustness tests against parameter changes in the converter are conducted, along with their corresponding performance indices.

Semi-Active Suspension Design for Truck Using Pneumatic Spring Joining MR Fluid Damper Based on Neural Networks Controller

&lt;div&gt;In order to modify both stiffness and damping rates according to various road conditions, this research introduces a pneumatic spring in conjunction with a magnetorheological (MR) fluid damper as a single suspension unit for each wheel in the truck. Preventing weight transfer and improving riding comfort during braking, acceleration, and trajectory prediction are the main objectives. A two-axle truck has been used, consisting of three degrees of freedom for the sprung mass, including vertical, pitch, and roll motions, and four degrees of freedom for the unsprung masses, which have been redesigned according to the different types of springs and dampers. Pneumatic-controlled springs, often referred to as dynamic or classic models, replace laminated leaf springs commonly found in vehicles. Additionally, an MR damper replaces a hydraulic double-acting telescopic shock absorber. These models are studied to evaluate the effect of pneumatic spring parameters on truck dynamics. Pneumatic stiffness and the intended damping force are monitored by a recurrent neural network in conjunction with leveling control. This process provides the recommended voltage for the MR damper based on the Signum function damper controller. The performance of the suspension is assessed in the time and frequency domains for both step and random road excitations using vehicle dynamic parameters. Six suspension system configurations are compared with the air spring dynamic model integrated with the MR damper (Model 6), which is recommended as a suspension system for trucks. According to simulation data, when compared to alternative suspension systems, Model 6 significantly enhances both ride comfort and vehicle stability. Model 6 offers improvements in tire workload, truck path, tire–ground contact point during acceleration, braking efficiency, and stopping distance. Compared to previous controlled models, Model 6 also demonstrates zero steady-state offset and zero steady-state error.&lt;/div&gt;

Model-based PD neural network control for pipe crack sealing manipulator

This study focuses on the control of a pipe crack sealing manipulator (PCSM) for concrete pipe crack sealing, with the capability to maneuver through horizontal and vertical pipes. This PCSM is a tree-type robot with five different branches. Observation and simulation studies indicate that only the fifth branch of the PCSM effectively executed the repair operation. However, in real application, the movement of these links is hindered by disturbances and uncertainties, preventing them from behaving as intended. Hence, a robust control scheme is essential to effectively manage the links of a pipe crack sealing manipulator. To address this need, this study introduces a Model-based PD neural network control (MBPDNNC) algorithm, which is then compared against modal-based PD (MBPD), Sliding mode control (SMC) with constant plus proportional rate reaching Law (CPPRL), and super twisting SMC (STSMC). The simulation study reveals that MBPDNN is characterized by greater accuracy and less chattering compared to the contrast control methods. The main contribution of this work is the compensation of disturbance by updating the weight by using the Radial basis function neural network (RBFNN). Through observation, it is evident that the neural network yields more promising results in the presence of disturbances and uncertainties.

Control of an integrated first and second-generation continuous alcoholic fermentation process with cell recycling using model predictive control

This study explores controlling a first- and second-generation alcoholic fermentation process with cell recycling, modeled through algebraic differential equations (DAE) with constraints. It evaluates seven controller types: PI, PID, Model Predictive Control (MPC), Neural Network Model Predictive Control (NNMPC), Mixed Model Predictive Control (MMPC), Internal Model Control (IMC), and Linear Quadratic Regulator (LQR). Results show that, while PI and PID controllers can track setpoints, they exhibit slow responses and oscillations. In contrast, MPC controllers respond faster, with both MPC and MMPC demonstrating more robust dynamics, achieving a significant reduction in Integral of the Absolute Error (IAE) across various disturbances, notably an 87% reduction in regulatory scenarios. NNMPC outperforms PI and PID but exhibits overshoot and oscillations, and lacks robustness for servo-type problems. However, MMPC showcases comparable or superior performance to MPC, surpassing other controllers in robustness, especially the IMC and LQR in the regulatory problems. NNMPC maintains a simulation time of under 4 seconds, whereas MPC incurs a computational cost 1,000 times higher. Integrating NNMPC’s optimal increment as an initial estimate in MPC reduces computational time by up to 79.7%. These findings highlight the ANN’s effectiveness in addressing complex control challenges, especially when integrated with MPC. MMPC offers a superior balance between accuracy, robustness, and computational efficiency, serving as a promising solution for reducing computational costs in MPC-type controllers.