Neural Network Controller Research Articles

Identification and Control of Flexible Joint Robots Based on a Composite-Learning Optimal Bounded Ellipsoid Algorithm and Prescribe Performance Control Technique

This paper presents an indirect adaptive neural network (NN) control algorithm tailored for flexible joint robots (FJRs), aimed at achieving desired transient and steady-state performance. To simplify the controller design process, the original higher-order system is decomposed into two lower-order subsystems using the singular perturbation technique (SPT). NNs are then employed to reconstruct the aggregated uncertainties. An adaptive prescribed performance control (PPC) strategy and a continuous terminal sliding mode control strategy are introduced for the reduced slow subsystem and fast subsystem, respectively, to guarantee a specified convergence speed and steady-state accuracy for the closed-loop system. Additionally, a composite-learning optimal bounded ellipsoid algorithm (OBE)-based identification scheme is proposed to update the NN weights, where the tracking errors of the reduced slow and fast subsystems are integrated into the learning algorithm to enhance the identification and tracking performance. The stability of the closed-loop system is rigorously established using the Lyapunov approach. Simulations demonstrate the effectiveness of the proposed identification and control schemes.

Application of Fuzzy Control and Neural Network Control in the Commercial Development of Sustainable Energy System

Sustainable energy systems (SESs) occupy a prominent position in the modern global energy landscape. The purpose of this study is to explore the application of fuzzy control and neural network control in photovoltaic systems to improve the power generation efficiency and stability of the system. By establishing the mathematical model of a photovoltaic system, the nonlinear and uncertain characteristics of photovoltaic system are considered. Fuzzy control and neural network control are used to control the system, and their performance is verified by experiments. The experimental results show that under the conditions of low light and moderate temperature, the fuzzy neural network control achieves a 3.33% improvement in power generation efficiency compared with the single control strategy. Meanwhile, the system can still maintain relatively stable operation under different environmental conditions under this comprehensive control. This shows that fuzzy neural network control has significant advantages in improving power generation efficiency and provides beneficial technical support and guidance for the commercial development of SESs.

Disturbance rejection control method of agricultural quadrotor based on adaptive neural network

In order to solve the problem of stability of agricultural quadrotor working, its controller designing is the first priority. Therefore, this paper makes an attempt to use the Radial Basis Function (RBF) neural network adaptive method combined with sliding mode control to control its height channel. Validation of the efficacy of the RBF neural network in control is conducted through simulation experiments utilizing quadrotor parameters. The application of the method to the control of agricultural quadrotor has laid a theoretical foundation. At the same time, through simulation experiments, it is concluded in theory that the RBF neural network can have a good prediction and elimination effect on the interference during the flight, and the change of the time constant will not affect the control effect of the aircraft. Notably, abrupt changes in time constant indicate UAV motor malfunction. Simulation results affirm the efficacy of the proposed control method in regulating UAV altitude and addressing sudden faults. Real-world experimentation reveals that even when UAV propellers sustain damage to a certain extent, altitude control and hover capabilities remain intact. These findings provide a solid groundwork for subsequent altitude control endeavors in agricultural quadrotor operations, while also offering innovative avenues for advancing the field.

Asymptotic Stability Analysis and Stabilization Control for General Fractional-Order Neural Networks via an Unified Lyapunov Function

Asymptotic Stability Analysis and Stabilization Control for General Fractional-Order Neural Networks via an Unified Lyapunov Function

Design and Assessment of Integrated Wind-Biomass Hybrid Renewable Energy System and Blackout Hazards in the Power System Using Arelu-Ann

Introduction:: A hybrid power generating system, which is mostly meant for its reliable performance to meet the current energy demand, is a renowned renewable energy. To overcome issues like the inability to handle the blackout problem, avoidance of renewable factors, and frequency instability of the power grid, a Hybrid Power Generation System (HPGS) utilizing biomass and wind is proposed in this paper. Method:: With the combination of controllers as well as inverters and blackout controllers, this work aims to maximize power with minimum cost. The DC-DC converter controlled by Renyi’s Quadratic Entropy-Based Neuro Proportional-Integral-Derivative (RQEB-NPID) and the inverter under the control of the Volt/VAR controller are utilized as a major contribution. Result:: This, in turn reduces the frequency instability problem. Moreover, the renewable factor is considered for reducing the cost of energy using the Pythagorean Fuzzy-based Equilibrium Optimizer (PF-EO)-based inverter. Next, by utilizing the Attention-based Rectified Linear Unitactivated Artificial Neural Network (ARELU-ANN) controller, the blackout problem that interrupts the power supply to the load is eliminated with the highest accuracy of 7.69%. Conclusion:: Also, the proposed ARELU-ANN attained the highest specificity and precision of 9.80% and 6.17 %, respectively. Lastly, a comparative analysis is performed, which demonstrates that the proposed solution is optimum for supplying maximum energy at the least cost.

Improved Test Fixture for Collecting Microcontact Performance and Reliability Data

Microelectromechanical systems (MEMS) ohmic contact switches are considered to be a promising candidate for wireless communication applications. The longevity of MEMS switches is directly related to the reliability and performance of microcontacts. In this work, an improved microcontact test fixture with high actuation rates (KHz) and highly precise position control (nm) and force (nN) control was developed. Here, we collected microcontact performance data from initial contact tests (ICT) and microcontact reliability data from cold switched tests (CST). To perform these tests with our test fixture, we fabricated MEMS microcontact test structures with relatively high Young’s modulus electroplated Nickel (Ni)-based, fixed–fixed beam structure with Au/RuO2 bimetallic microcontacts. These structures were characterized for forces ranging from 200–1000 µN in ICT tests. In a CST test, the tested microcontact survived more than 200 million cycles at a 1 KHz cycle rate, with a stable contact resistance value ranging between 3.8–5.2 Ω. These experiments validate the potentiality of our microcontact test fixture, and will facilitate further investigation on advanced microcontacts to enhance the MEMS switch’s reliability.

Event-Triggered Adaptive Neural Network Control for State-Constrained Pure-Feedback Fractional-Order Nonlinear Systems with Input Delay and Saturation

In this research, the adaptive event-triggered neural network controller design problem is investigated for a class of state-constrained pure-feedback fractional-order nonlinear systems (FONSs) with external disturbances, unknown actuator saturation, and input delay. An auxiliary compensation function based on the integral function of the input signal is presented to handle input delay. The barrier Lyapunov function (BLF) is utilized to deal with state constraints, and the event-triggered strategy is applied to overcome the communication burden from the limited communication resources. By the utilization of a backstepping scheme and radial basis function neural network, an adaptive event-triggered neural state-feedback stabilization controller is constructed, in which the fractional-order dynamic surface filters are employed to reduce the computational burden from the recursive procedure. It is proven that with the fractional-order Lyapunov analysis, all the solutions of the closed-loop system are bounded, and the tracking error can converge to a small interval around the zero, while the state constraint is satisfied and the Zeno behavior can be strictly ruled out. Two examples are finally given to show the effectiveness of the proposed control strategy.

Noise-tolerant zeroing neural network control for a novel compliant actuator in lower-limb exoskeletons

Noise-tolerant zeroing neural network control for a novel compliant actuator in lower-limb exoskeletons

Comparative study of controllers in battery energy storage system integrated with doubly fed induction generator-based wind energy conversion system for power quality improvement

This study presents a comparative analysis of controllers in a Battery Energy Storage System (BESS) integrated with a Doubly Fed Induction Generator (DFIG)-based Wind Energy Conversion System (WECS) aimed at improving power quality. The research background introduces the challenges associated with integrating renewable energy sources into the grid, emphasizing the intermittent nature of wind energy and its impact on power quality. Existing detailed problems, including voltage and frequency fluctuations, and grid instability, are outlined, highlighting the need for effective control strategies to mitigate these issues. The paper's contribution lies in evaluating and comparing different control techniques for BESS integration, including Proportional-Integral (PI) control, Fuzzy Logic (FL), and Artificial Neural Network (ANN) control. Through simulation studies conducted in MATLAB/Simulink, the effectiveness of each controller in regulating rotor current, rotor and stator power, voltage stability, state of charge (SoC) and grid synchronization is assessed. The findings provide valuable insights into the optimal controller selection for enhancing power quality in DFIG-based WECS with integrated energy storage systems, contributing to the advancement of renewable energy integration and grid stability.

Adaptive neural network control of robotic manipulators with input constraints and without velocity measurements

AbstractThis paper addresses the trajectory tracking problem for a class of uncertain manipulator systems under the effect of external disturbances. The main challenges lie in the input constraints and the lack of measurements of joint velocities. An extend‐state‐observer is utilized to estimate the velocity signals; then, a neural‐network‐based adaptive controller is proposed to solve the problem, where a term based on the nominal model is included to enhance the tracking ability, and the effect of uncertainties and disturbances are compensated by a neural‐network term. Compared with the existing methods, the main distinctive features of the presented approach are: (i) The control law is guaranteed to be bounded by design, instead of directly bounded by a saturation function. (ii) The trade‐off between the performance and robustness of the presented controller can be easily tuned by a parameter that depends on the size of model uncertainties and external disturbances. By virtue of the Lyapunov theorem, the convergence properties of the proposed controller are rigorously proved. The performance of the controller is validated via both simulations and experiments conducted on a two‐degree‐of‐freedom robot manipulator.

Neural Network Robust Control Based on Computed Torque for Lower Limb Exoskeleton

The lower limb exoskeletons are used to assist wearers in various scenarios such as medical and industrial settings. Complex modeling errors of the exoskeleton in different application scenarios pose challenges to the robustness and stability of its control algorithm. The Radial Basis Function (RBF) neural network is used widely to compensate for modeling errors. In order to solve the problem that the current RBF neural network controllers cannot guarantee the asymptotic stability, a neural network robust control algorithm based on computed torque method is proposed in this paper, focusing on trajectory tracking. It innovatively incorporates the robust adaptive term while introducing the RBF neural network term, improving the compensation ability for modeling errors. The stability of the algorithm is proved by Lyapunov method, and the effectiveness of the robust adaptive term is verified by the simulation. Experiments wearing the exoskeleton under different walking speeds and scenarios were carried out, and the results show that the absolute value of tracking errors of the hip and knee joints of the exoskeleton are consistently less than 1.5°and 2.5°, respectively. The proposed control algorithm effectively compensates for modeling errors and exhibits high robustness.

Full-state constraints and input backlash–based neural network control of a 2-DOF helicopter system

This paper introduces an adaptive neural network compensatory control approach designed for a 2-degree-of-freedom (2-DOF) helicopter system facing challenges such as input backlash and state constraints. The proposed methodology leverages a radial basis function (RBF) neural network to effectively approximate system uncertainties, mitigating the impact of nonlinear dynamics on control performance. To address the presence of nonlinear input backlash, a compensation technique is introduced to enhance the smoothness of input signals. In addition, for enhanced system safety, a barrier Lyapunov function is integrated to impose restrictions on position and velocity states, resulting in constrained control. Through a rigorous analysis using the Lyapunov direct method, this paper demonstrates the effectiveness of the proposed approach in achieving bounded stability of the system. The validation of the approach is further established through the presentation of simulation and experimental results, showcasing its effectiveness and feasibility in real-world applications.

Practical fixed-time neural control for MIMO non-strict feedback nonlinear systems: an adaptive neural network approach

ABSTRACT This paper studies the non-singular practical fixed-time neural adaptive control issues for multi-input and multi-output (MIMO) nonlinear systems with non-strict feedback form. Neural networks (NN) are used to estimate the unknown nonlinearities and deal with the problem of an algebraic loop. Under the framework of the backstepping control design, a practical fixed-time adaptive NN control method is developed by using the adding power integration technology. According to the Lyapunov function theory, it is proved that the closed-loop system is practical fixed-time stable, and the system can track the desired reference signal within a fixed time. Finally, the proposed practical fixed-time control method is applied to a multi-motor control platform, which proves the effectiveness of the control method.

Anti-Offset Multicoil Underwater Wireless Power Transfer Based on a BP Neural Network

Autonomous underwater vehicles (AUVs) are now widely used in both civilian and military applications; however, wireless charging underwater often faces difficulties such as disturbances from ocean currents and errors in device positioning, making proper alignment of the charging devices challenging. Misalignment between the primary and secondary coils can significantly impact the efficiency and power of the wireless charging system energy transfer. To address the issue of misalignment in wireless charging systems, this paper proposes a multiple transfer coil wireless power transfer (MTCWPT) system based on backpropagation (BP) neural network control combined with nonsingular terminal sliding mode control (NTSMC) to enhance further the system robustness and efficiency. To achieve WPT in the ocean, a coil shielding case structure was equipped. In displacement experiments, the proposed multi-transmitting coil system could achieve stable power transfer of 40 W and efficiency of over 78.5% within a displacement range of 8 cm. The system robustness was also validated. This paper presents a new AUV energy supply solution based on MTCWPT. The proposed MTCWPT system can significantly improve the navigation performance of AUVs.

TLBO trained an ANN-based DG integrated Shunt Active Power Filter to Improve Power Quality

In terms of power quality, the rising number of nonlinear loads in modern use has caused warning signs for power system and power engineering professionals. Every day, utilities have to deal with harmonic distortion caused by a growing number of non-linear power electronic equipment. To keep the system's power supply in good condition, a shunt active filter is used to filter out unwanted harmonics in the signal. This study presents a practical and low-cost method for reducing harmonics and enhancing distribution network power quality by means of the use of PV-integrated Shunt Active Power Filters (SAPF). With a teaching-learning-based optimized artificial neural network controller (TLBO-ANN) and the required DC power is extracted from the PV module. SAPF's TLBO-ANN algorithms are intended to increase system performance by reducing total harmonic distortion (THD). Here, the research work was performed in three stages to mitigate grid current harmonics. The first-stage SAPF system comprises a three-prong voltage source converter and uses DC power derived from photovoltaic panels. The P&O algorithm is used to get the maximum power out of a photovoltaic array. In the second stage, the BBO algorithm is used to fine-tune a conventional PI controller, resulting in values for and that increase the controller's performance. Furthermore, it is intended to use the BBO-PI controller's input and output values as training data for the ANN controller. This ANN controller is currently being tuned with the TLBO algorithm to find optimal values for the weight and bias parameters. In the third stage, the converter in PV-SAPF will inject the active power required by the load by using active current control theory, which means the inverter of SAPF is working like DG as well as the active power filter. Employing MATLAB simulations, we concluded that the proposed method is extremely adaptable and highly efficient in lowering harmonic currents that are brought on by non-linear loads.

Neural network controller of a gas turbine plant low emission combustor

Neural network controller of a gas turbine plant low emission combustor

Implementation of a hybrid neural network control technique to a cascaded MLI based SAPF

This paper presents a naïve back propagation (NBP) based icos∅\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$i\\cos \\emptyset$$\\end{document} technique implemented to a cascaded multilevel inverter (MLI) based shunt active power filter (SAPF). The recommended control algorithm is applied to extract the fundamental component of load current and to decide the compensating current reference for harmonic elimination. The performance of the SAPF using the proposed NBP-based icos∅\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$i\\cos \\emptyset$$\\end{document} technique is compared with another two classical control techniques, such as, id-iq\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$i_{d} - i_{q}$$\\end{document} technique and icos∅\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$i\\cos \\emptyset$$\\end{document} technique. The accuracy of the proposed control technique depends on the tuned estimation of active and reactive weights. The performance study of the proposed SAPF with the proposed control technique is investigated under non-linear conditions, with balanced and unbalanced loading conditions. The results reveal that the recommended SAPF is efficient enough to reduce the harmonics from the source current with smooth variation in DC link voltage. The effectiveness of the proposed method is validated by simulation using MATLAB Simulink, and the real-time results are also validated by the experimental setup.

Design of Solar Energy Based System Using Artificial Neural Network Controller

A key component of energy generation and the safe operation of the electrical system is solar energy. The solar energy system for producing the required voltage is presented in this paper. It is managed by an artificial neural network (ANN) controller, which performs significantly better than a conventional PI controller. It aids in lowering the system's total harmonic distortion (THD). The sole PI controller, which produces an erratic output response, is utilized in conventional wind turbines. It is swapped out in the suggested system for an ANN controller, which offers smooth voltage and current response. Two inputs and two outputs are used in the system's development. Six pulse-fired IGBTs that reduce excess voltage and current in the circuit operate this system. The MATLAB/Simulink tool was used to create the results, which were shown to be superior to traditional results. To regulate the impact of a variable power factor, an output variable load is connected. Every outcome has been validated and confirmed to be superior than traditional outcomes.

Event‐triggered adaptive estimated inverse neural network control of uncertain nonlinear systems with unknown hysteresis effects

AbstractThis article investigates an event‐triggered adaptive estimated inverse control scheme for uncertain nonlinear systems with hysteresis effects, parametric uncertainties, and unknown disturbances. An online estimated inverse hysteresis compensation mechanism is developed, in which an adaptive technique is designed to obtain the value of unknown hysteresis parameters. Compared with common approaches, its biggest advantage lies in the fact that it eliminates the need for experimental determination of hysteresis parameters, thereby reducing time‐consuming offline identification work and enhance the compatibility of the proposed method. Additionally, an adaptive radial basis functions neural network is applied to approximate the unknown disturbances, and its weight coefficients, along with unknown system parameters, are estimated by means of the adaptive method. Furthermore, the introduction of relative threshold event‐triggered control significantly reduces communication costs resulting from the hysteresis compensation. Through Lyapunov analysis, the proposed controller guarantees all signals are bounded and the errors are convergent. Numerical simulation results demonstrate the superiority of the developed controller.

Application of Multilayer Neural Networks for Controlling a Line-Following Robot in Robotic Competitions

The paper presents an approach for controlling a line-following robot using artificial intelligence algorithms. This study aims to evaluate and validate the design and implementation of a competitive line-following robot based on multilayer neural networks for controlling the torque on the wheels and regulating the movements. The configuration of the line-following Robot consists of a chassis with a set of infrared sensors that can detect the line on the track and provide input data to the neural network. The performance of the line-following Robot on a running track with different configurations is then evaluated. The results show that the line-following Robot responded more efficiently with an artificial neural network control algorithm than a PID control or fuzzy control algorithm. At the same time, the reaction and correction time of the Robot to errors on the track is earlier by about 0.1 seconds. In conclusion, the capabilities of a neural network allow the line-following Robot to adapt to environmental conditions and overcome obstacles on the track more effectively.