High-order Neural Networks Research Articles

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.

Neural Robust Control for a Mobile Agent Leader–Follower System

A controller employing a combined new strategy of output feedback linearization and a recurrent high-order neural network (RHONN) adaptive approach for a mobile agent leader–follower system is presented. The controller structure is based on feedback linearization; then, a scheme of lumping uncertainties which are estimated via the RHONN is incorporated; with this estimate, the controller is able to produce a robust control action for mobile agents so they track a prescribed reference trajectory. Moreover, the nonlinear system part is transformed into a linearizable one; then, a specific function lumps all the nonlinearities, uncertain parameters, and unmodeled dynamics of the system; this overall function is estimated via the RHONN. Thus, both parametric uncertainties and unmodeled dynamics between agents can be compensated via the controller, and, subsequently, follower agents track the reference provided by the leader. The obtained controller is such that the estimation scheme is not based on high-gain controllers. Here, it is underlined that the main contribution consists of designing a nonlinear controller and combining it with an RHONN to estimate the nonlinear uncertainties in the leader–follower system. This control action includes robust features provided by the online recurrence and the nonlinear base of the neural network in which not general but specific parametric disturbances and unmodeled discrepancies are identified or compensated. For this control scheme, only nominal values of the system parameters are required, as well as the velocities of the agents. Numeric simulation of the model and designed tracking control are carried out in which the control law is applied to a two-wheeled differential mobile robot model, obtaining satisfactory results for tracking angular velocities of the wheels.

Clinical characteristics of post-stroke basal ganglia aphasia and the study of language-related white matter tracts based on diffusion spectrum imaging

BackgroundStroke often damages the basal ganglia, leading to atypical and transient aphasia, indicating that post-stroke basal ganglia aphasia (PSBGA) may be related to different anatomical structural damage and functional remodeling rehabilitation mechanisms. The basal ganglia contain dense white matter tracts (WMTs). Hence, damage to the functional tract may be an essential anatomical structural basis for the development of PSBGA. MethodsWe first analyzed the clinical characteristics of PSBGA in 28 patients and 15 healthy controls (HCs) using the Western Aphasia Battery and neuropsychological test batteries. Moreover, we investigated white matter injury during the acute stage using diffusion magnetic resonance imaging scans for differential tractography. Finally, we used multiple regression models in correlation tractography to analyze the relationship between various language functions and quantitative anisotropy (QA) of WMTs. ResultsCompared with HCs, patients with PSBGA showed lower scores for fluency, comprehension (auditory word recognition and sequential commands), naming (object naming and word fluency), reading comprehension of sentences, Mini-Mental State Examination, and Montreal Cognitive Assessment, along with increased scores in Hamilton Anxiety Scale-17 and Hamilton Depression Scale-17 within 7 days after stroke onset (P < 0.05). Differential tractography revealed that patients with PSBGA had damaged fibers, including in the body fibers of the corpus callosum, left cingulum bundles, left parietal aslant tracts, bilateral superior longitudinal fasciculus II, bilateral thalamic radiation tracts, left fornix, corpus callosum tapetum, and forceps major, compared with HCs (FDR < 0.02). Correlation tractography highlighted that better comprehension was correlated with a higher QA of the left inferior fronto-occipital fasciculus (IFOF), corpus callosum forceps minor, and left extreme capsule (FDR < 0.0083). Naming was positively associated with the QA of the left IFOF, forceps minor, left arcuate fasciculus, and uncinate fasciculus (UF) (FDR < 0.0083). Word fluency of naming was also positively associated with the QA of the forceps minor, left IFOF, and thalamic radiation tracts (FDR < 0.0083). Furthermore, reading was positively correlated with the QA of the forceps minor, left IFOF, and UF (FDR < 0.0083). ConclusionPSBGA is primarily characterized by significantly impaired word fluency of naming and preserved repetition abilities, as well as emotional and cognitive dysfunction. Damaged limbic pathways, dorsally located tracts in the left hemisphere, and left basal ganglia pathways are involved in PSBGA pathogenesis. The results of connectometry analysis further refine the current functional localization model of higher-order neural networks associated with language functions.

A Sigma-Pi-Sigma Neural Network Model with Graph Regularity Term

In recent years, Sigma-Pi-Sigma neural network (SPSNN) as a special kind of higher-order neural network has attracted wide attention for its fast convergence speed and good approximation ability. However, an inappropriate number of hidden layer neurons may also lead to model underfitting or overfitting, which affects the performance and generalization ability of the model. Therefore, we propose a Sigma-Pi-Sigma neural network with graph regularity by adding a graph regularity term to the network. The results show that the proposed algorithm performs well in terms of training accuracy, testing accuracy and efficiency.

Neural Sliding Mode Control of a Buck-Boost Converter Applied to a Regenerative Braking System for Electric Vehicles

This paper presents the design and simulation of a neural sliding mode controller (NSMC) for a regenerative braking system in an electric vehicle (EV). The NSMC regulates the required current and voltage of the bidirectional DC-DC buck–boost converter, an element of the auxiliary energy system (AES), to improve the state of charge (SOC) of the battery of the EV. The controller is based on a recurrent high-order neural network (RHONN) trained using the extended Kalman filter (EKF) and the unscented Kalman filter (UKF) as the tools to train the neural networks to obtain a higher SOC in the battery. The performance of the controller with the two training algorithms is compared with a proportional integral (PI) controller illustrating the differences and improvements obtained with the EKF and the UKF. Furthermore, robustness tests considering Gaussian noise and varying of parameters have demonstrated the outcome of the NSMC over a PI controller. The proposed controller is a new strategy with better results than the PI controller applied to the same buck–boost converter circuit, which can be used for the main energy system (MES) efficiency in an EV architecture.

Elitist-opposition-based artificial electric field algorithm for higher-order neural network optimization and financial time series forecasting

This study attempts to accelerate the learning ability of an artificial electric field algorithm (AEFA) by attributing it with two mechanisms: elitism and opposition-based learning. Elitism advances the convergence of the AEFA towards global optima by retaining the fine-tuned solutions obtained thus far, and opposition-based learning helps enhance its exploration ability. The new version of the AEFA, called elitist opposition leaning-based AEFA (EOAEFA), retains the properties of the basic AEFA while taking advantage of both elitism and opposition-based learning. Hence, the improved version attempts to reach optimum solutions by enabling the diversification of solutions with guaranteed convergence. Higher-order neural networks (HONNs) have single-layer adjustable parameters, fast learning, a robust fault tolerance, and good approximation ability compared with multilayer neural networks. They consider a higher order of input signals, increased the dimensionality of inputs through functional expansion and could thus discriminate between them. However, determining the number of expansion units in HONNs along with their associated parameters (i.e., weight and threshold) is a bottleneck in the design of such networks. Here, we used EOAEFA to design two HONNs, namely, a pi-sigma neural network and a functional link artificial neural network, called EOAEFA-PSNN and EOAEFA-FLN, respectively, in a fully automated manner. The proposed models were evaluated on financial time-series datasets, focusing on predicting four closing prices, four exchange rates, and three energy prices. Experiments, comparative studies, and statistical tests were conducted to establish the efficacy of the proposed approach.

Nozzle Shape Optimization based on Machine Learning using Higher Order Neural Networks

Nozzle Shape Optimization based on Machine Learning using Higher Order Neural Networks

A new Sigma-Pi-Sigma neural network based on $ L_1 $ and $ L_2 $ regularization and applications

&lt;abstract&gt;&lt;p&gt;As one type of the important higher-order neural networks developed in the last decade, the Sigma-Pi-Sigma neural network has more powerful nonlinear mapping capabilities compared with other popular neural networks. This paper is concerned with a new Sigma-Pi-Sigma neural network based on a $ L_1 $ and $ L_2 $ regularization batch gradient method, and the numerical experiments for classification and regression problems prove that the proposed algorithm is effective and has better properties comparing with other classical penalization methods. The proposed model combines the sparse solution tendency of $ L_1 $ norm and the high benefits in efficiency of the $ L_2 $ norm, which can regulate the complexity of a network and prevent overfitting. Also, the numerical oscillation, induced by the non-differentiability of $ L_1 $ plus $ L_2 $ regularization at the origin, can be eliminated by a smoothing technique to approximate the objective function.&lt;/p&gt;&lt;/abstract&gt;

Prediction of temperature field distribution in a gas turbine using a higher order neural network

This paper presents the prediction of temperature field distribution in a single annular section using an artificial neural network (ANN). This temperature distribution is non-uniform on the outer tube due to continuous natural convection and radiation caused by the homogeneous steady-state heating of the inner tube, which represents the hot gas flow path through the turbine. The outer tube represents the case of a gas turbine. This temperature is important for the electronic components attached to the engine or the overall engine deformation. The presented approach allows for a quick estimation of the temperature distribution without the need to perform time consuming computational fluid dynamics (CFD) simulations. This can greatly accelerate the design and development of gas turbines. A machine learning approach is applied to an extensive set of CFD simulations under different operating conditions and geometry setups.

A novel higher-order neural network framework based on motifs attention for identifying critical nodes

A novel higher-order neural network framework based on motifs attention for identifying critical nodes

High-Order Neural-Network-Based Multi-Model Nonlinear Adaptive Decoupling Control for Microclimate Environment of Plant Factory.

Plant factory is an important field of practice in smart agriculture which uses highly sophisticated equipment for precision regulation of the environment to ensure crop growth and development efficiently. Environmental factors, such as temperature and humidity, significantly impact crop production in a plant factory. Given the inherent complexities of dynamic models associated with plant factory environments, including strong coupling, strong nonlinearity and multi-disturbances, a nonlinear adaptive decoupling control approach utilizing a high-order neural network is proposed which consists of a linear decoupling controller, a nonlinear decoupling controller and a switching function. In this paper, the parameters of the controller depend on the generalized minimum variance control rate, and an adaptive algorithm is presented to deal with uncertainties in the system. In addition, a high-order neural network is utilized to estimate the unmolded nonlinear terms, consequently mitigating the impact of nonlinearity on the system. The simulation results show that the mean error and standard error of the traditional controller for temperature control are 0.3615 and 0.8425, respectively. In contrast, the proposed control strategy has made significant improvements in both indicators, with results of 0.1655 and 0.6665, respectively. For humidity control, the mean error and standard error of the traditional controller are 0.1475 and 0.441, respectively. In comparison, the proposed control strategy has greatly improved on both indicators, with results of 0.0221 and 0.1541, respectively. The above results indicate that even under complex conditions, the proposed control strategy is capable of enabling the system to quickly track set values and enhance control performance. Overall, precise temperature and humidity control in plant factories and smart agriculture can enhance production efficiency, product quality and resource utilization.

Neural Network Inverse Optimal Control of Ground Vehicles

In this paper an active controller for ground vehicles stability is presented. The objective of this controller is to force the vehicle to track a desired reference, ensuring safe driving conditions in the case of adhesion loss during hazardous maneuvers. To this aim, a nonlinear discrete-time inverse optimal control based on a neural network identification is designed, using a recurrent high order neural network (RHONN) trained by an Extended Kalman Filter. The RHONN ensures stability of the identification error, while the controller ensures the stability of the tracking errors. Moreover, a discrete-time reduced order state observer is utilized to reconstruct the lateral vehicle dynamic not usually available. For the control problem, the references of the lateral velocity and yaw rate are given by a dynamic system mimicking an ideal vehicle having not-decreasing tire lateral characteristics. The proposed approach avoids the identification of the Pacejka’s lateral parameters of the tires, so simplifying the input control determination. Moreover, an optimal control is proposed to optimize the actuator effort and power, usually bounded. Control gains are determined using optimal “nature-inspired" algorithms such as particle swarm optimization. Test maneuvers, performed through the full vehicle simulator CarSim®, have been used to test correctness, quality and performances of the observer, the neural identifier and the inverse optimal controller. Robustness of the reduced order discrete-time state observer is also discussed for different sample times. Finally, a fair comparison between optimal and non-optimal control schemes is presented, highlighting the numerical results obtained in simulation.

A Comprehensive Survey on Higher Order Neural Networks and Evolutionary Optimization Learning Algorithms in Financial Time Series Forecasting

A Comprehensive Survey on Higher Order Neural Networks and Evolutionary Optimization Learning Algorithms in Financial Time Series Forecasting

Online Learning-Informed Feedforward-Feedback Controller Synthesis for Path Tracking of Autonomous Vehicles

High-performance path tracking is a key technology for autonomous vehicles. Feedforward-feedback control architectures are suitable for accurate path tracking with adequate margins of stability. For system modelling in the feedforward component, the learning-based method has been proven to be a promising approach owing to its model-free framework. However, the offline-learned data model trained with collection data is confined by its feature space, resulting in insufficient generalization. As a solution, in this study, we introduce an online learning network – the recurrent high-order neural network (RHONN) – to characterize vehicle behaviors. The RHONN is used to feature vehicle behaviors in a timely manner with a high fidelity and flexible form. The equilibrium at the preview point on the desired path is found based on the online-identified RHONN model, and its induced steering angle is taken as the feedforward command. For the feedback steering controller, the preview point position-based control law incorporating the steady vehicle sideslip angle is adopted to enhance the stability performance. Finally, in the CarSim/Simulink environment, the performance of the designed RHONN-informed feedforward and feedback controller is validated in two typical scenarios – double-lane change and single-turn. The validation results reveal that the proposed approach offers better tracking accuracy in linear and nonlinear regions than other techniques. More notably, the average execution time (3.55 ms) is less than the sampling frequency of the controller (50 ms), which further confirms the applicability and efficiency of the proposed approach.

RHONN-Modeling-Based Predictive Safety Assessment and Torque Vectoring for Holistic Stabilization of Electrified Vehicles

Improving vehicle safety and reducing traffic accidents have always been of cardinal importance in vehicle dynamics control fields. A reasonable and comprehensive safety index that characterizes the vehicle's safe region is the most challenging aspect of research. With the linear dynamics model as the benchmark, this article uses the deviation of yaw rate and vehicle sideslip angle from the corresponding linear response as the lateral stability indices. Meanwhile, the maximum slip ratio of the driven wheels is selected as the longitudinal stability index. The <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">safety indicator</i> , a quantitative index featuring the safety degree of vehicle planar motions, is then inferred by a fuzzy inference system using the lateral and longitudinal stability indices. As such, the recurrent high-order neural network model predicts the vehicle states. Based on the predicted states, a safety indicator is then derived by using fuzzy inference system, which can assess the safety of a driver's control commands. In the case of an improper driving torque demand given by the driver, the torque correction process is immediately conducted to maintain the vehicle in a safe region. Finally, two typical scenarios—slippery curves and double lane changes in low friction roads—are simulated on the MATLAB/Simulink-CarSim cosimulation platform. The hardware-in-the-loop experiments are also conducted on a driving simulator test rig, validating the performance of the developed algorithms. The holistic stability performance of the in-wheel motor driven vehicle is thoroughly analyzed and compared using three existing methods. The simulation and experimental results validate the effectiveness and feasibility of the proposed method.

Impulsive Neural Control to Schedule Antivirals and Immunomodulators for COVID-19.

New SARS-CoV-2 variants escaping the effect of vaccines are an eminent threat. The use of antivirals to inhibit the viral replication cycle or immunomodulators to regulate host immune responses can help to tackle the viral infection at the host level. To evaluate the potential use of these therapies, we propose the application of an inverse optimal neural controller to a mathematical model that represents SARS-CoV-2 dynamics in the host. Antiviral effects and immune responses are considered as the control actions. The variability between infected hosts can be large, thus, the host infection dynamics are identified based on a Recurrent High-Order Neural Network (RHONN) trained with the Extended Kalman Filter (EKF). The performance of the control strategies is tested by employing a Monte Carlo analysis. Simulation results present different scenarios where potential antivirals and immunomodulators could reduce the viral load.

Sensor fault-tolerant control for a doubly fed induction generator in a smart grid

This study proposes a sensor fault-tolerant controller for a doubly fed induction generator connected to a smart grid. Mathematical models are the main tools for the synthesis of modern control systems; however, an accurate model for complex systems is not always available. Therefore, in this study, a recurrent high-order neural network trained with an extended Kalman filter is proposed to develop a mathematical model for a wind turbine with a doubly fed induction generator connected to a smart grid. The neural model is combined with a modified discrete-time sliding mode controller, which compensates for the presence of sensor faults on each of the state variables on both sides of the back-to-back converter. Real-time results are included to illustrate the effectiveness of the proposed scheme under five sensor faults.

A Deep Learning Method for the Detection and Compensation of Outlier Events in Stock Data

The stock price is a culmination of numerous factors that are not necessarily quantifiable and significantly affected by anomalies. The forecasting accuracy of stock prices is negatively affected by these anomalies. However, very few methods are available for detecting, modelling, and compensating for anomalies in financial time series given the critical roles of better management of funds and accurate forecasting of anomalies. Time series data are a data type that changes over a defined time interval. Each value in the data set has some relation to the previous values in the series. This attribute of time series data allows us to predict the values that will follow in the series. Typical prediction models are limited to following the patterns in the data set without being able to compensate for anomalous periods. This research will attempt to find a machine learning method to detect outliers and then compensate for these detections in the prediction made. This concept was previously unimplemented, and therefore, it will make use of theoretical work on market forecasting, outliers and their effects, and machine learning methods. The ideas implemented in the paper are based upon the efficient market hypothesis (EMH), in which the stock price reflects knowledge about the market. The EMH hypothesis cannot account for consumer sentiment towards a stock. This sentiment could produce anomalies in stock data that have a significant influence on the movement of the stock market. Therefore, the detection and compensation of outliers may improve the predictions made on stock movements. This paper proposes a deep learning method that consists of two sequential stages. The first stage is an outlier detection model based on a long short-term memory (LSTM) network auto-encoder that can determine if an outlier event has occurred and then create an associated value of this occurrence for the next stage. The second stage of the proposed method uses a higher-order neural network (HONN) model to make a prediction based on the output of the first stage and the stock time series data. Real stock data and standalone prediction models are used to validate this method. This method is superior at predicting stock time series data by compensating for outlier events. The improvement is quantifiable if the data set contains an adequate amount of anomalous periods. We may further apply the proposed method of compensating for outliers in combination with other financial time series prediction methods to offer further improvements and stability.

Approximate Output Regulation of Discrete-Time Stochastic Multiagent Systems Subject to Heterogeneous and Unknown Dynamics

The output regulation approach has been extensively applied for the cooperative control of heterogeneous multiagent systems (MASs) with known dynamics, but rarely for MASs subject to stochastic and unknown dynamics. One challenging problem is that it is still unclear how to construct the regulator equations of stochastic MASs with unknown dynamics for dynamic exosystem compensation. Toward this end, this article develops a novel distributed control scheme for the approximate output regulation of discrete-time stochastic MASs subject to heterogeneous and unknown nonlinear dynamics. A distributed observer is designed for the exosystem-state estimation of agents, based upon which nonlinear regulator equations are constructed for the feedforward control design, thereby achieving distributed exosystem compensation. A high-order neural network is deployed to approximately solve the nonlinear regulator equations with unknown nonlinearity, and an adaptive control law is developed for the approximate output regulation of discrete-time stochastic MASs. Stability analysis shows that the closed-loop system is semiglobally uniformly ultimately bounded. Simulation results demonstrate the effectiveness and efficiency of the proposed control law.

Hybrid physics-data-driven online modelling: Framework, methodology and application to electric vehicles

This paper proposes a novel hybrid physics-data-driven framework for system modelling by integrating a physical model and an online learning data model to improve model accuracy, interpretability, and generalization. Taking an in-wheel Motor Driven Vehicle (IMDV) as an example, two hybrid representations, i.e. the Dynamic Linearization Data Model (DLDM) and Recurrent High-Order Neural Network (RHONN) are introduced for the planar dynamics modelling of the electric vehicle. However, it is difficult to obtain the statistical information of the operation process and measurement noise when the weight vectors of the data-driven model is updated online. To address this issue, a H∞-based learning algorithm is adopted. The stability and convergence rate are elaborated and compared with an existing Extended Kalman Filter (EKF)-based method. Finally, we compare four methods, including the physics-based, data-based and two hybrid models, to evaluate their performances of modelling the IMDV’s dynamics. The feasibility test and comparison studies are conducted in simulations and on a Hardware-in-the-Loop (HiL) test rig. The results demonstrated that the proposed H∞-based hybrid method, which does not make any assumption on measurement noise, has better generalization ability and robustness in practical implementations, compared to other baseline methods.