Neural Network-based Control Research Articles

Neural network-based adaptive decentralized learning control for interconnected systems with input constraints

Neural network-based adaptive decentralized learning control for interconnected systems with input constraints

Neural Network-Based Control for Hybrid PV and Ternary Pumped-Storage Hydro Plants

The growth in renewable energy integration over the past few years, primarily fueled by the drop in capital cost, has revealed the requirement for more sustainable methods of integration. This paper presents a collocated hybrid plant consisting of solar photovoltaic (PV) and Ternary pumped-storage hydro (TPSH) and designs controls that integrate the PV plant such that the behavior and the controllability of the hybrid plant are similar to those of a conventional plant within operational constraints. The PV array control and hybrid plant control implement a neural–network-based framework to coordinate the response, de-loading, and curtailment of multiple arrays with the response of the TPSH. With the help of the designed controls, a symbiotic relationship is developed between the two energy resources, where the PV compensates for the TPSH nonlinearities and provides required speed of response, while the TPSH firms the PV system and allows the PV to be integrated using its existing infrastructure. Simulations demonstrate that the designed controls enable the PV system to track references, while the TPSH’s firming and shifting transforms the PV system into a base load plant for most of the day and extends its hours of operation.

Memory Augmented Neural Network-Based Intelligent Adaptive Fault Tolerant Control for a Class of Launch Vehicles Using Second-Order Disturbance Observer

This paper focuses on the MANN-based intelligent adaptive fault tolerant control for a class of launch vehicles. Firstly, the attitude dynamic model of the launch vehicles suffering from the actuator faults and disturbances has been formulated. Secondly, the second-order disturbance observer has been designed for the launch vehicle to achieve the exact estimation and compensation of the time-varying disturbances. Meanwhile, the MANN has been introduced as online approximator, suppressing the adverse influence of the unknown nonlinearities. Moreover, several adaptive laws have been proposed to achieve the quick response to the actuator faults and the update of the MANN weights. As a result, the MANN-based intelligent adaptive fault tolerant control structure has been constructed for the launch vehicles. It has been proven that all the signals in the closed-loop system are bounded. Simulation results demonstrate the desired performance and the advantages of the proposed control algorithm.

Bioprocess Control: Current Progress and Future Perspectives.

Typical bioprocess comprises of different unit operations wherein a near optimal environment is required for cells to grow, divide, and synthesize the desired product. However, bioprocess control caters to unique challenges that arise due to non-linearity, variability, and complexity of biotech processes. This article presents a review of modern control strategies employed in bioprocessing. Conventional control strategies (open loop, closed loop) along with modern control schemes such as fuzzy logic, model predictive control, adaptive control and neural network-based control are illustrated, and their effectiveness is highlighted. Furthermore, it is elucidated that bioprocess control is more than just automation, and includes aspects such as system architecture, software applications, hardware, and interfaces, all of which are optimized and compiled as per demand. This needs to be accomplished while keeping process requirement, production cost, market value of product, regulatory constraints, and data acquisition requirements in our purview. This article aims to offer an overview of the current best practices in bioprocess control, monitoring, and automation.

Adaptive neural output-feedback control for a class of output-constrained switched stochastic nonlinear systems

In this paper, a neural network-based adaptive output-feedback control problem is investigated for a class of output-constrained switched stochastic nonlinear systems. By introducing nonlinear mapping, the asymmetric and symmetric output constrained stochastic nonlinear system is transformed into a new system without any constraint. It is the first time that a switching system is used to convert symmetric and asymmetric output constraints in the same system. An adaptive neural output-feedback controller is developed based on the backstepping technique. A state observer is designed to estimate the unmeasurable system state signals. An adaptive controller is designed to ensure that the output tracking error converges to a small region of the origin. The control scheme ensures that all signals in the closed-loop systems are semi-global uniformly ultimately bounded. Results of simulation cases are presented to prove the effectiveness of the theoretical analysis.

Event-triggered Neural Network-Based Adaptive Control for a Class of Uncertain Nonlinear Systems

In the paper, an event triggering adaptive control method based on neural network (NN) is proposed for a class of uncertain nonlinear systems with external disturbances. In order to reduce the network resource utilization, a novel event-triggered condition by the Lyapunov approach is proposed. In addition, the NN controller and adaptive parameters determined by the Lyapunov stability method are updated only at triggered instants to reduce the amount of calculation. Only one NN is used as the controller in the entire system. The stability analysis results of the closed-loop system are obtained by the Lyapunov approach, which shows that all the signals in the systems with bounded disturbance are semi-globally bounded. Zeno behavior is avoided. Finally, the analytical design is confirmed by the simulation results on a two-link robotic manipulator.

Investigation on GaN HEMTs Based Three-Phase STATCOM with Hybrid Control Scheme.

The modern trend of decarbonization has encouraged intensive research on renewable energy (RE)-based distributed power generation (DG) and smart grid, where advanced electronic power interfaces are necessary for connecting the generator with power grids and various electrical systems. On the other hand, modern technologies such as Industry 4.0 and electrical vehicles (EV) have higher requirements for power converters than that of conventional applications. Consequently, the enhancement of power interfaces will play an important role in the future power generation and distribution systems as well as various industrial applications. It has been discovered that wide-bandgap (WBG) switching devices such as gallium nitride (GaN) high electron mobility transistors (HEMTs) and silicon carbide (SiC) metal-oxide-semiconductor field-effect transistors (MOSFETs) offer considerable potential for outperforming conventional silicon (Si) switching devices in terms of breakdown voltage, high temperature capability, switching speed, and conduction losses. This paper investigates the performance of a 2kVA three-phase static synchronous compensator (STATCOM) based on a GaN HEMTs-based voltage-source inverter (VSI) and a neural network-based hybrid control scheme. The proportional-integral (PI) controllers along with a radial basis function neural network (RBFNN) controller for fast reactive power control are designed in synchronous reference frame (SRF). Both simulation and hardware implementation are conducted. Results confirm that the proposed RBFNN assisted hybrid control scheme yields excellent dynamic performance in terms of various reactive power tracking control of the GaN HEMTs-based three-phase STATCOM system.

Artificial Neural network-based Controller for PEMFC based Distributed generation

Artificial Neural network-based Controller for PEMFC based Distributed generation

An Intelligent Approach to Active and Reactive Power Control in a Grid-Connected Solar Photovoltaic System

The increasing demand of electrical energy and environmental concerns are invigorating the use of renewable energy resources for power generation. Renewable energy resources can provide an attractive solution for present and future energy requirements. In this scenario, solar photovoltaic systems are becoming prominent and sustainable solutions with numerous advantages. However, the utilization of solar photovoltaic systems in distribution generation makes it mandatory to deploy efficient and organized control measures for integrating solar photovoltaic plants with the grid. In this paper, the control of grid-tied solar photovoltaic systems using a Kalman filter-based generalized neural network is presented with a variable step size perturb and observe-based maximum power point tracking controller to extract the maximum power from a solar photovoltaic plant. The presented system provides power-quality enhancement and supports a three-phase AC grid. The proposed approach extracts the load currents’ primary components for efficient harmonics elimination, synchronizes the system with the grid and provides a fast response during rapidly changing conditions. The results of the proposed control technique are also compared with the artificial neural network-based control technique for validation purposes. The proposed algorithm is found more suitable for using a smaller number of unknown weights and training patterns with reduced computational time.

Guidance and control methodologies for marine vehicles: A survey

Offshore mechatronics systems engineering has recently received high attentions in various sectors such as energy, transportation, etc. Specifically, offshore robotic vehicles have become challenging topics in terms of design, guidance, control and maintenance aspects. Based on these reasons, in this article, some recent developments on the guidance and control methodologies for marine robotic vehicles are surveyed. The application-oriented methodologies under consideration mainly include fuzzy-based control design approach, neural network-based control design scheme, dynamic surface control strategy, feedback control technique as well as sliding model control method, for instance. With the help of these methodologies, the developments on various guidance and robust control issues are reviewed in great detail. In practical engineering, guidance and control design problems are mainly addressed for the maneuvering, path following, trajectory tracking, formation control and consensus. In particular, the state of art of the solution to guidance and control issues for marine robotic vehicles under different control methodologies is addressed respectively. Finally, some latest research results in filtering and control design developments are introduced, some conclusions are drawn and several possible future research directions based on the latest results are pointed out.

Neural network-based fuzzy vibration controller for offshore platform with random time delay

A neural network-based fuzzy controller is proposed to attenuate the irregular wave-induced vibration of a steel-jacket offshore platform. Firstly, the offshore platform is modeled as a system with time-varying control delay under random wave forces. Secondly, disturbance rejection measures are taken in designing an optimal controller containing delayed states. Thirdly, neural networks are adopted to observe and restore the controlled system, in order to learn the delayed control law using instant state. Finally, fuzzy models are constructed for reducing the complexity in data collecting and neural network training. Trained with sample data from fuzzy models, the neuro-fuzzy observation system is able to reconstruct the control system, and the generalized neural network-based controller works efficiently in different delayed cases. It achieves better vibration-attenuating performance under uncertain control delay and random waves, when compared to existed optimal control laws and fuzzy controllers without neural networks. The main contributions of this paper are: 1) obtaining a neural network-based observer in state approximation; 2) designing a neural network-based controller based on fuzzy rules to cope with random control delay.

Weakly Supervised Reinforcement Learning for Autonomous Highway Driving via Virtual Safety Cages.

The use of neural networks and reinforcement learning has become increasingly popular in autonomous vehicle control. However, the opaqueness of the resulting control policies presents a significant barrier to deploying neural network-based control in autonomous vehicles. In this paper, we present a reinforcement learning based approach to autonomous vehicle longitudinal control, where the rule-based safety cages provide enhanced safety for the vehicle as well as weak supervision to the reinforcement learning agent. By guiding the agent to meaningful states and actions, this weak supervision improves the convergence during training and enhances the safety of the final trained policy. This rule-based supervisory controller has the further advantage of being fully interpretable, thereby enabling traditional validation and verification approaches to ensure the safety of the vehicle. We compare models with and without safety cages, as well as models with optimal and constrained model parameters, and show that the weak supervision consistently improves the safety of exploration, speed of convergence, and model performance. Additionally, we show that when the model parameters are constrained or sub-optimal, the safety cages can enable a model to learn a safe driving policy even when the model could not be trained to drive through reinforcement learning alone.

Augmenting human power by assistive robots: Application of adaptive neural networks

In this paper, we present a control scheme for robotic exoskeletons to gain the desired transparency for a wide range of tasks, which leads to the provision of sufficient support to the wearer in different situations. The main goal of the study was to evaluate the performance of adaptive neural networkbased controllers in gaining transparency for powerassist robots. As these devices experience a large dynamic change during handling different tasks/loads, we studied whether neural networks (NNs) can promptly learn the dynamics and provide sufficiently smooth commands to achieve the desired transparency. Our evaluations were performed through experiments conducted on an upperlimb robotic exoskeleton with unknown dynamics handling external loads. We tested a commonly used structure of NNs with different layers of adjustable weights and numbers of neurons. We also tested the smoothness of the system response and concluded that to gain natural and comfortable feeling the desired transparency needs to be selected in accordance with the task.

Model-Free High Order Sliding Mode Control with Finite-Time Tracking for Unmanned Underwater Vehicles

Several strategies to deal with the trajectory tracking problem of Unmanned Underwater Vehicles are encountered, from traditional controllers such as Proportional Integral Derivative (PID) or Lyapunov-based, to backstepping, sliding mode, and neural network approaches. However, most of them are model-based controllers where it is imperative to have an accurate knowledge of the vehicle hydrodynamic parameters. Despite some sliding mode and neural network-based controllers are reported as model-free, just a few of them consider a solution with finite-time convergence, which brings strong robustness and fast convergence compared with asymptotic or exponential solutions and it can also help to reduce the power consumption of the vehicle thrusters. This work aims to implement a model-free high-order sliding-mode controller and synthesize it with a time-base generator to achieve finite-time convergence. The time-base was included by parametrizing the control gain at the sliding surface. Numerical simulations validated the finite-time convergence of the controller for different time-bases even in the presence of high ocean currents. The performance of the obtained solution was also evaluated by the Root Mean Square (RMS) value of the control coefficients computed for the thrusters, as a parameter to measure the power consumption of the vehicle when following a trajectory. Computational results showed a reduction of up to 50% in the power consumption from the thrusters when compared with other solutions.

An ATC instruction processing-based trajectory prediction algorithm designing

The radiotelephony communication is a voice communication mode between air traffic service unit and aircraft currently. The control instruction is a kind of unstructured data, so that the automatic systems cannot use understand its semantic. If control instruction is regarded as a sort of special “natural language,” methods such as syntax analysis and sematic analysis can be adopted to generate the structured instruction. The correct recognition of the language must be important for the control instruction. However, the control instruction in Chinese is different from the general use of Chinese language in form, resulting in prepositions becoming important for semantic analysis. This paper proposes a deep neural network-based Chinese language control construction algorithm for the trajectory prediction. In particular, analysis of sematic characteristics of control instruction is realized by using cognitive linguistics theory and construction grammar theory. The control instruction is then designed by the semantic ontology. Based on the deep neural networks by considering the word sequence of instruction as the inputs. The test results have demonstrated the effectiveness of the proposed algorithm with a developed entity extracting model. (The results are quantified using the BiLSTM-LAN-CRF in detail.)

Neural Network Controlled Space Vector PWM for a High Power Factor Converter Under Perturbed Conditions

ABSTRACT This work demonstrates the application of neural network to optimize space vector pulse width modulation (SVPWM) for a neutral-point clamped rectifier especially for supply and load perturbations. Neural network is used here to obtain the exact switching time for the converter. The advantage of using neural network is to avoid complex mathematical computations for generating fast, best path, and shape of the reference vector. Learning algorithm for offline training of neural network is based on a well-performed model of modified SVPWM used to synthesize a linear functional relationship between perturbed condition parameters and the control gains. The offline training of neural network is repeated until the control gains as input parameters for the neural network-based model produce optimal results for each perturbed condition. The proposed neural network-based controller scheme is modeled in MATLAB/Simulink software. Simulation results show that the proposed algorithm implementation is simple and displays better performance under any supply and load conditions.

N 2 C: Neural Network Controller Design Using Behavioral Cloning

Modern vehicles communicate data to and from sensors, actuators, and electronic control units (ECUs) using Controller Area Network (CAN) bus, which operates on differential signaling. An autonomous ECU responsible for the execution of decision commands to an autonomous vehicle is developed by assimilating the information from the CAN bus. The conventional way of parsing the decision commands is motion planning, which uses a path tracking algorithm to evaluate the decision commands. This study focuses on designing a robust controller using behavioral cloning and motion planning of autonomous vehicle using a deep learning framework. In the first part of this study, we explore the pipeline of parsing decision commands from the path tracking algorithm to the controller and proposed a neural network-based controller ( N <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> C) using behavioral cloning. The proposed network predicts throttle, brake, and torque when trained with the manual driving data acquired from the CAN bus. The efficacy of the proposed method is demonstrated by comparing the accuracy with the Proportional-Derivative-Integral (PID) controller in conjunction with the path tracking algorithm (pure pursuit and model predictive control based path follower). The second part of this study complements N <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> C, in which an end-to-end neural network for predicting the speed and steering angle is proposed with image data as an input. The performance of the proposed frameworks are evaluated in real-time and on the Udacity dataset, showing better metric scores in the former and reliable prediction in the later case when compared with the state-of-the-art methods.

Neural Networks Based Shunt Hybrid Active Power Filter for Harmonic Elimination

The growing use of nonlinear devices is introducing harmonics in power system networks that result in distortion of current and voltage signals causing damage to power distribution systems. Therefore, in power systems, the elimination of harmonics is of great significance. This paper presents an efficient techno-economical approach to suppress harmonics and improve the power factor in power distribution networks using Shunt Hybrid Active Power Filters (SHAPF) based on neural network algorithms like Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Recurrent Neural Network (RNN). The objective of the proposed algorithms for SHAPF is to enhance system performance by reducing Total Harmonic Distortion (THD). In our filter design approach, we tested and compared conventional pq0 theory and neural networks to detect the harmonics present in the power system. Moreover, for the regulation of DC supply to the inverter of the SHAPF, the conventional PI controller and neural networks-based controllers are used and compared. The applicability of the proposed filter is tested for three different nonlinear load cases. The simulation results show that the neural networks-based filter control techniques satisfy all international standards with minimum current THD, neutral wire current elimination, and small DC voltage fluctuations for voltage regulation current. Furthermore, the three neural network architectures are tested and compared based on accuracy and computational complexity, with RNN outperforming the rest.

Long Short-term Memory Neural Network-based System Identification and Augmented Predictive Control of Piezoelectric Actuators for Precise Trajectory Tracking

Long Short-term Memory Neural Network-based System Identification and Augmented Predictive Control of Piezoelectric Actuators for Precise Trajectory Tracking

Оптимизация тихоходного синхронного генератора модульного типа и принцип реализации системы управления напряжением генератора на основе нейронной сети

A method for optimizing the parameters of a modular half-speed synchronous generator with permanent magnets (PMSG) and the generator voltage control system with a neural network-based algorithm are proposed. The basic design scheme of the modular half-speed PMSG is considered, which features a compact layout of the generator main parts, thereby ensuring the optimal use of the working volume, smaller sizes of the magnetic system, and smaller mass of the active materials used in manufacturing the machine. Owing to the simple and reliable design of the generator, its output parameters can be varied in a wide range with using standard electrical circuits for voltage stabilization and current rectification along with an additional voltage regulation unit. Owing to this feature, the design scheme of the considered generator has essential advantages over the existing analogs with a common cylindrical magnetic core. In view of these circumstances, the development of a high-efficient modular half-speed PMSG as an autonomous DC power source is of both scientific and practical interest; this generator can be used to supply power to a large range of electricity consumers located in rural areas, low-rise residential areas, military communities, allotments etc. In solving the problem of optimizing the generator’s magnetic system, the main electrical machine analysis equation is obtained. The optimal ratios of the winding wire mass to the mass of permanent magnets and of the PM height to the air gap value for achieving the maximum specific useful power output have been determined. An analytical correlation between the optimal design parameters of a half-speed modular PMSG and its power performance parameters has been established. The expediency to develop a neural network-based control system is shown. The number of load-bearing modules of the half-speed PMSG is determined depending on the wind velocity, load factor and the required output voltage. The neural network was trained on the examples of a training sample using a laboratory test bench. The neural network was implemented in the MatLab 2019b environment by constructing a synchronous generator simulation model in the Simulink software extension. The possibility of using the voltage control system of a half-speed modular PMSG with a microcontroller for operation of the neural network platform of the Arduino family (ArduinoDue) independently of the PC is shown.