High-order Neural Networks Research Articles

Anti-periodicity on high-order inertial Hopfield neural networks involving mixed delays

This paper deals with a class of high-order inertial Hopfield neural networks involving mixed delays. Utilizing differential inequality techniques and the Lyapunov function method, we obtain a sufficient assertion to ensure the existence and global exponential stability of anti-periodic solutions of the proposed networks. Moreover, an example with a numerical simulation is furnished to illustrate the effectiveness and feasibility of the theoretical results.

Real-time neural control of all-terrain tracked robots with unknown dynamics and network communication delays

This work focuses on the design of an intelligent controller that is a considerably large challenge for cyber-physical systems. The proposed controller can deal with unknown dynamics, actuator saturation, unknown external and internal disturbances, unknown communication delays and packet losses. Such a controller is designed using a discrete-time approach based on inverse optimal control and a recurrent high-order neural network identifier. The applicability of the proposed scheme is shown through real-time results using a tracked robot platform controlled through a wireless network under different network scenarios.

State estimation for discrete-time high-order neural networks with time-varying delays

This paper focuses on state estimation problem for discrete-time high-order neural networks with time-varying delays. First, the delay-dependent global exponential stability criterion of the error system is derived. Then, the state observer is designed by using the generalized inverse theory of matrices. Last, two numerical examples are given to illustrate the validity of the theoretical results. The method proposed in this paper has two advantages: (i) it is directly based on the definitions of global exponential stability and Moore–Penrose inverse of matrix, which avoids the construction of Lyapunov–Krasovskii functional; (ii) the obtained stability criteria contain only several simple matrix inequalities, which are easier to solve. More valuable, this paper fills in the gaps in designing state observers for discrete-time high-order neural network models.

Real-time Neural Inverse Optimal Control for Low-Voltage Rid-Through enhancement of Double Fed Induction Generator based Wind Turbines

The Low-Voltage Ride-Through (LVRT) capacity of the Doubly Fed Induction Generator (DFIG) is one of the important requirements to ensure power systems stability, incorporating wind energy. While traditional control schemes present inappropriate performances under disturbances, this paper introduces a novel Neural Inverse Optimal Control (N-IOC) scheme for LVRT capacity enhancing. The developed controller is synthesized using recurrent high order neural network, which is utilized to build-up the DFIG and the DC-link dynamics. Based on such identifier, the proposed N-IOC is synthesized. This controller is experimentally validated on 1∕4 HP DFIG prototype considering various grid disturbances. Results illustrate the proposed controller effectiveness for LVRT enhancement without required decomposition process and/or any additional device.

High-order Fuzzy Neural Network Algorithm in the Application of Inner Mongolia Grassland Scenic Tourist Traffic Prediction Research

High-order Fuzzy Neural Network Algorithm in the Application of Inner Mongolia Grassland Scenic Tourist Traffic Prediction Research

Adaptive neural tracking control of stochastic nonaffine nonlinear switched systems with unknown backlash-like hysteresis

This paper is concerned with the tracking control problem for a class of switched nonaffine stochastic nonlinear systems in completely nonaffine form and nonlower-triangular structure, with unknown backlash-like hysteresis involved, and a novel adaptive neural tracking control scheme, based on backstepping design, is proposed. To eliminate the problem of complexity explosion, dynamic surface control (DSC) technique is incorporated into the backstepping design procedure, such that the process of controller design becomes much simpler. High-order neural networks (HONNs) are employed to approximate the lumped unknown nonlinear functions, and only one adaptive parameter is required to be updated. Stability analysis shows that the proposed scheme guarantees all the closed-loop error signals are semi-globally uniformly ultimately bounded in the 4th-moment or mean square, and the system output can converge to an arbitrary small neighbourhood of the given trajectory. Finally, simulation results are presented to verify the effectiveness of the proposed approach.

An Autonomous Path Controller in a System on Chip for Shrimp Robot

This paper presents a path planning and trajectory tracking system for a BlueBotics Shrimp III®, which is an articulate mobile robot for rough terrain navigation. The system includes a decentralized neural inverse optimal controller, an inverse kinematic model, and a path-planning algorithm. The motor control is obtained based on a discrete-time recurrent high order neural network trained with an extended Kalman filter, and an inverse optimal controller designed without solving the Hamilton Jacobi Bellman equation. To operate the whole system in a real-time application, a Xilinx Zynq® System on Chip (SoC) is used. This implementation allows for a good performance and fast calculations in real-time, in a way that the robot can explore and navigate autonomously in unstructured environments. Therefore, this paper presents the design and implementation of a real-time system for robot navigation that integrates, in a Xilinx Zynq® System on Chip, algorithms of neural control, image processing, path planning, and inverse kinematics and trajectory tracking.

Stability and Synchronization of a Fractional Neutral Higher-Order Neural Network System

Abstract We discuss the stability and synchronization of some neural network systems with more than one feature. They are of higher-order, of fractional order and also involving delays of neutral type. Each one of these features presents substantial difficulties to overcome. We prove stability and synchronization of Mittag-Leffler type. This rate is fairly reasonable in case of fractional order. This leads us to prove a neutral fractional version of the well-known Halanay inequality which is interesting by itself. Another feature of the present work is the treatment of unbounded activation functions. The condition of uniform boundedness of the activation functions was commonly used in the literature.

Global exponential stability on anti-periodic solutions in proportional delayed HIHNNs

ABSTRACT This article mainly explores a class of proportional delayed high-order inertial Hopfield neural networks (HIHNNs) with time-varying coefficients. Without using the reduced-order method, by combining Lyapunov function method with differential inequality approach, some sufficient criteria on the existence of anti-periodic solutions including its uniqueness and exponential stability are built up. The obtained results provide us some lights for designing a stable HIHNNs and complement some earlier publications. In addition, simulations show that the theoretical anti-periodic dynamics are in excellent agreement with the numerically observed behaviour.

Improved spotted hyena optimizer with space transformational search for training pi‐sigma higher order neural network

AbstractSpotted hyena optimizer (SHO) is a recently developed swarm‐based algorithm in the field of metaheuristic research, for solving realistic engineering design constraint and unconstrained difficulties. To resolve complicated nonlinear physical world tasks, at times, SHO reveals deprived performance concerning to explorative strength. So, to enhance the explorative strength along with exploitation in the search region, an attempt has been made by proposing the enhanced version of classical SHO. The suggested method is designated as space transformation search (STS)‐SHO. In STS‐SHO, a new evolutionary technique named as STS technique has been incorporated with original SHO. The suggested method has been assessed by IEEE CEC 2017 benchmark problems. The efficacy of the said method has been proven by using standard measures such as given performance metrics in CEC 2017, complexity analysis, convergence analysis, and statistical implications. Further as real‐world application, the said algorithm has been applied to train pi‐sigma neural network by means of 13 benchmark datasets considered from UCI depository. From the article it can be concluded that the suggested method STS‐SHO is an effective and trustworthy algorithm, which has the ability to resolve real‐life optimization complications.

A Modified Weight Optimization for Artificial Higher Order Neural Networks in Physical Time Series

Many methods and approaches have been proposed for analyzing and forecasting time series data. There are different Neural Network (NN) variations for specific tasks (e.g., Deep Learning, Recurrent Neural Networks, etc.). Time series forecasting are a crucial component of many important applications, from stock markets to energy load forecasts. Recently, Swarm Intelligence (SI) techniques including Cuckoo Search (CS) have been established as one of the most practical approaches in optimizing parameters for time series forecasting. Several modifications to the CS have been made, including Modified Cuckoo Search (MCS) that adjusts the parameters of the current CS, to improve algorithmic convergence rates. Therefore, motivated by the advantages of these MCSs, we use the enhanced MCS known as the Modified Cuckoo Search-Markov Chain Monté Carlo (MCS-MCMC) learning algorithm for weight optimization in Higher Order Neural Networks (HONN) models. The Lévy flight function in the MCS is replaced with Markov Chain Monté Carlo (MCMC) since it can reduce the complexity in generating the objective function. In order to prove that the MCS-MCMC is suitable for forecasting, its performance was compared with the standard Multilayer Perceptron (MLP), standard Pi-Sigma Neural Network (PSNN), Pi-Sigma Neural Network-Modified Cuckoo Search (PSNN-MCS), Pi-Sigma Neural Network-Markov Chain Monté Carlo (PSNN-MCMC), standard Functional Link Neural Network (FLNN), Functional Link Neural Network-Modified Cuckoo Search (FLNN-MCS) and Functional Link Neural Network-Markov Chain Monté Carlo (FLNN-MCMC) on various physical time series and benchmark dataset in terms of accuracy. The simulation results prove that the HONN-based model combined with the MCS-MCMC learning algorithm outperforms the accuracy in the range of 0.007% to 0.079% for three (3) physical time series datasets.

Improving normalization method of higher-order neural network in the forecasting of oil production

One of the challenges in the oil industry is to predict well production in the absence of frequent flow measurement. Many researches have been done to develop production forecasting in the petroleum area. One of the machine learning approach utilizing higher-order neural network (HONN) have been introduced in the previous study. In this study, research focus on normalization impact to the HONN model, specifically for univariate time-series dataset. Normalization is key aspect in the pre-processing stage, moreover in neural network model.

Secondary Control of Microgrids via Neural Inverse Optimal Distributed Cooperative Control

In this paper, a new control scheme of secondary voltage and frequency control based on a discrete-time neural inverse optimal distributed cooperative structure is proposed for islanded microgrids. A neural adaptive secondary controller for each distributed generator is developed to achieve the desired goals. The proposed controllers are composed of an on-line neural identification scheme on the basis of a recurrent high-order neural network using the extended Kalman filter and a nonlinear control strategy. Additionally, the proposed control scheme does not require information of all installed distributed generators neither a distributed generator model, which improves reliability. The proposed controllers are validated through simulation for an islanded AC microgrid.

Global Exponential Stability Criteria for Proportional Delay High-Order Neural Networks: A Hyper-Exponential Stability Technique

A new method is presented for stability analysis of proportional delay high-order neural networks. The network model is first transformed into a system with a constant time delay and unbounded time-varying coefficients, and then it is proven that the former is globally exponentially stable if and only if the laster is globally hyper-exponentially stable. The global hyper-exponential stability criteria of the laster are investigated by employing the generalized Halanay inequality and constructing a novel Lyapunov function that can avoid the computation of upper-right derivative. From which, the global exponential stability criteria of the former are derived. To illustrate the advantages of this proposed method, numerical simulation examples are given. Compared with the existing results, the contributions of this paper lie in: (i) An Lyapunov function different from ones in literature is constructed; (ii) The derived global exponential stability criteria possess simple forms, which are easy to verify; and (iii) The concept of hyper-exponential stability is proposed. The proposed method is also available to multi-proportional delay neural networks.

High-Order Sliding Modes Based On-Line Training Algorithm for Recurrent High-Order Neural Networks

Abstract This work presents a discrete on-line training algorithm for recurrent high-order neural networks (RHONN). The proposed training algorithm is based on the arbitrary order differentiators of high-order sliding modes (HOSM) theory. Due to HOSM-based differentiators can approximate derivatives in finite time, the proposed training algorithm avoids the compute of the derivatives, unlike conventional training algorithms. The proposed HOSM-based algorithm is implemented for the training of a RHONN identifier, and its performance is compared with the results using the extended Kalman filter (EKF) training algorithm. Results of a implementation of the identifier for the Lorenz system and an implementation of the identifier for a tracked robot using experimental data are presented.

The General Higher-Order Neural Network Model and Its Application to the Archive Retrieval in Modern Guangdong Customs Archives

Because of the unique attributes of archive information, it is challenging to manage and effectively retrieve archive information in the archive information management practice. This paper designs and develops the first general higher-order Neural Network Model for archives. Based on the analysis of the correlation, the relevance of the weight model, the study of technical methods about the core weight, the direction weight retrieval, and the statistical ranking of the results, this paper designs a corresponding archive information analysis system. Finally, this paper adopts the B/S development model by applying the relevance ranking weight algorithm into the comprehensive archive retrieval activities, which not only enhances the intelligence and efficiency of the archive retrieval, but also can act as a standard example to demonstrate informatization construction for archive management. This paper compares this algorithm with two other existing retrieval algorithms and verifies the practicability of the relevance algorithm by evaluating the algorithm and the default retrieval algorithm using the NDCG evaluation method.

Robust neural tracking control for switched nonaffine stochastic nonlinear systems with unknown control directions and backlash-like hysteresis

This paper is concerned with the tracking control problem for a class of switched stochastic nonlinear systems in nonaffine form with both unknown control directions and unknown backlash-like hysteresis, and a novel neural tracking control scheme is proposed based on backstepping technique and Nussbaum function. Dynamic surface control (DSC) is adopted to overcome the problem of complexity explosion of the traditional backstepping design. High-order neural networks (HONNs) are utilized to approximate the lumped unknown nonlinear functions, and only one adaptive parameter needs to be updated. Stability analysis shows all closed-loop error signals are semi-globally uniformly ultimately bounded in the fourth-moment (or mean square), and the system tracking error is ensured to converge to a small neighborhood of zero. Finally, simulation results illustrate the effectiveness of the proposed scheme.

Discrete-time high-order neural network identifier trained with high-order sliding mode observer and unscented Kalman filter

This paper presents a method to identify an unknown discrete-time nonlinear system, using high-order neural networks and high-order sliding mode algorithms, which may be subject to internal and external disturbances. Based on the information obtained from available system states, a high-order neural network model is proposed to approximate the system dynamics. Neural network weights are trained by means of the unscented Kalman filter and high-order sliding mode observer. A simulation example is included to illustrate effectiveness of the proposed scheme.

Neural sliding-mode pinning control for output synchronization for uncertain general complex networks

A novel approach for output synchronization for uncertain general complex networks with non-identical nodes is proposed. This goal can be solved applying to a small fraction of network nodes (pinned ones) a neural controller; this controller is composed of an on-line identifier based on a recurrent high-order neural network, and a sliding-mode controller. An illustrative example is included, which is composed of a network of ten nodes, with different self-dynamics, illustrating the effectiveness and good performance of the proposed control scheme.

Improving Microgrid Low-Voltage Ride-Through Capacity Using Neural Control

In this article, a neural sliding-mode linearization controller is proposed to regulate the generated active and reactive power for each distributed energy resource in a microgrid. The developed controller is based on recurrent high-order neural network identification, trained online with an extended Kalman filter learning algorithm. Based on such neural identification, adequate models of the microgrid generation units are obtained even in the presence of grid disturbances, which helps the proposed controller to reject disturbances, to ensure stability, and to operate the renewable energy sources under different grid scenarios. The proposed microgrid is composed of a wind power system, a solar power system, a battery bank, and a load demand. In addition, the microgrid under study is interconnected to an IEEE nine-bus system. The whole system is simulated in real time using the Opal-RT (OP5600) simulator. Real-time simulation results illustrate the effectiveness of the proposed control scheme to achieve trajectory tracking of the distributed energy resources active and reactive power even in the presence of grid disturbances.