Basis Function Neural Network Research Articles

A data-adaptive network design for the regional gravity field modelling using spherical radial basis functions

A high-precision regional gravity field model is significant in various geodesy applications. In the field of modelling regional gravity fields, the spherical radial basis functions (SRBFs) approach has recently gained widespread attention, while the modelling precision is primarily influenced by the base function network. In this study, we propose a method for constructing a data-adaptive network of SRBFs using a modified Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) algorithm, and the performance of the algorithm is verified by the observed gravity data in the Auvergne area. Furthermore, the turning point method is used to optimize the bandwidth of the basis function spectrum, which satisfies the demand for both high-precision gravity field and quasi-geoid modelling simultaneously. Numerical experimental results indicate that our algorithm has an accuracy of about 1.58 mGal in constructing the gravity field model and about 0.03 m in the regional quasi-geoid model. Compared to the existing methods, the number of SRBFs used for modelling has been reduced by 15.8%, and the time cost to determine the centre positions of SRBFs has been saved by 12.5%. Hence, the modified HDBSCAN algorithm presented here is a suitable design method for constructing the SRBF data adaptive network.

Distributed nonsingular terminal sliding mode control–based RBFNN for heterogeneous vehicular platoons with input saturation

In this paper, a distributed nonsingular terminal sliding mode control (NTSMC) is proposed for vehicular platoons subjected to nonlinear uncertainty, external disturbance, and input saturation. Due to the presence of input saturation, the platoon control becomes more complicated. However, only considering the impact of uncertainty on the system, input saturation will usually lead to a decline in the driving performance, even lead to string instability. First, the input saturation is compensated by a single parameter, which is simple and direct. The radial basis function neural network (RBFNN) based on disturbance observer is employed to compensate the nonlinear uncertainty and external disturbance, respectively. The basis function of neural network is only related to the velocity and acceleration of the leader. Therefore, the nonlinearity of the vehicle systems does not need to meet the matching conditions. Then, a distributed NTSMC is designed to realize the internal stability, which weakens the chattering of traditional sliding mode control (SMC) to some extent. In addition, the nonsingular problem in terminal sliding mode control (TSMC) is solved. The string stability is realized by employing a coupled sliding mode control (CSMC). Finally, simulation results demonstrate the effectiveness and feasibility of the proposed strategy.

Neuro‐Adaptive Finite Time Composite Fault Tolerant Control for Attitude Control Systems of Satellites

AbstractAn adaptive finite time composite fault tolerant control strategy based on an optimized neural network for Attitude control systems (ACSs) of satellites is proposed considering the state time‐varying delays, concurrent actuator and sensor faults, system uncertainties, modelable external disturbance and operating noise. An uncertain time‐varying state space model for ACSs of satellites is established, and sensor faults are equivalent to actuator‐like faults. A disturbance observer is designed for estimating the modelable external disturbance, and an improved dwarf mongoose optimization (DMO) algorithm based on the Levy flight distribution is utilized to optimize the basis function of hyperbasis function neural networks to better estimate the augmented actuator faults that include the actuator fault and the actuator‐like fault. Furthermore, an adaptive finite time composite fault‐tolerant controller is proposed, which includes the delay‐dependent feedback control law, disturbance estimation based‐disturbance compensation law and the adaptive fault compensation law based on the augmented fault estimation using the improved DMO‐hyper basis function neural network. The finite time boundness of the close‐loop dynamics to the uncertainties, operating noise, and augmented actuator faults and the robustness of the measurement to the uncertainties, operating noise and augmented actuator faults are analyzed, and the observer and controller design is formulated as the linear matrix inequalities. Simulation examples for ACSs in different working conditions are considered to exhibit the proposed method's effectiveness.

Incremental learning-based optimal design of BFN kernel for online spacecraft disturbance rejection control

Low earth orbit (LEO) space environment is glutted with unknown and uncertain disturbance, which impede the regular operation and dynamic stability of spacecraft. In recent decades, Basis Function Network (BFN) has attracted much attention benefiting from its potential adaptability for unknown dynamic disturbance. However, it also suffers from the shortcomings of parameter drift, under fitting and long time consuming, which restricts its applications in practical space missions. This paper proposes a new online network reconstruction algorithm, which enables BFN a better excitation effect and more rapid response with less time consumption. The algorithm selects less but more relevant basis functions than routine neural network to approximate the disturbance, which consequently helps to achieve a better characterization effect. Two BFN selection strategies based on iterative learning and batch learning are proposed to further increase the efficiency of online network reconstruction. Detailed theoretical derivation proves the feasibility of the new algorithm. Numerical simulation of a real space station shows that the algorithm has strong adaptability and time efficiency under the interference of structural uncertainty.

Analyzing the effect of normally distributed cooling channels on a photovoltaic thermal solar unit

Photovoltaic thermal (PVT) systems convert solar radiation into electrical and thermal energy while keeping the PV's temperature within a permissible range. This paper presents a numerical analysis of a novel normal cooling technique for the PV module and a new AI prediction model. It considers a cooling direction normal to the PV panel using rectangular cascade channels with two different orientations. This cascading of the flow inlet channels helps keep the inflow temperature as cold as possible along the PV panel. The numerical simulations are performed based on a flow rate range of 0.00024: 0.0012 LPM, insolation of 400: 1200 W/m2, convection coefficients of 5.48 and 20.7 W/m2.K, and ambient temperatures of 298 and 308 K. The proposed PVT system achieves a decrease in the cell's average temperature by 27K while improving the electrical, thermal, and overall efficiencies by 4.8%,59.5%, and 73.33%, respectively. The numerical database is used for building an ANN prediction model based on a radial base function neural network with Gorilla troops optimizer (RBFNN-GTO). The proposed RBFNN-GTO model is developed to predict the main performance parameters of the PVT which are thermal efficiency, electrical efficiency, overall efficiency, average temperature of the PV panel, and the model temperature un-uniformity. It achieves an overall correlation coefficient of 0.9997 concerning the numerical database and showed an average MSE of 5.4313E-4.

Neural Network-Based Hybrid Three-Dimensional Position Control for a Flapping Wing Aerial Vehicle.

This article presents a novel neural network-based hybrid mode-switching control strategy, which successfully stabilizes the flapping wing aerial vehicle (FWAV) to the desired 3-D position. First, a novel description for the dynamics, resolved in the proposed vertical frame, is proposed to facilitate further position loop controller design. Then, a radial base function neural network (RBFNN)-based adaptive control strategy is proposed, which employs a switching strategy to keep the system away from dangerous flight conditions and achieve efficient flight. The learning process of the neural network pauses, resumes, or alternates its update strategy when switching between different modes. Moreover, saturation functions and barrier Lyapunov functions (BLFs) are introduced to constrain the lateral velocity within proper ranges. The closed-loop system is theoretically guaranteed to be semiglobally uniformly ultimately bounded with arbitrarily small bound, based on Lyapunov techniques and hybrid system analysis. Finally, experimental results demonstrate the excellent reliability and efficiency of the proposed controller. Compared to existing works, the innovations are the put forward of the vertical frame and the cooperative switching learning and control strategies.

Adaptive Fast-Terminal Neuro-Sliding Mode Control for Robot Manipulators with Unknown Dynamics and Disturbances

This paper presents a novel adaptive fast-terminal neuro-sliding mode control (AFTN-SMC) for a two-link robot manipulator with unknown dynamics and external disturbances. The proposed controller is chattering-free and adaptive to the time-varying system uncertainties. Furthermore, the radial base function neural network (RBFNN) is employed to approximate the unknown state dynamics. The simulations have been completed in MATLAB, which illustrates the successful implementation of the proposed controller. The results showcased the effectiveness of the AFTN-SMC in achieving accurate tracking and stability, even in the presence of uncertainties and parameter variations. The incorporation of the RBFNN in the controller proved to be a valuable tool for approximating the unknown dynamics, enabling accurate estimation and control of the manipulator’s behavior. The research presented in this paper contributes to the advancement in control techniques for robot manipulators in diverse industrial and automation applications.

COVID-19 crisis and the efficiency of Indian banks: Have they weathered the storm?

The purpose of this study is to determine whether Indian banks were able to weather the COVID-19 storm. We estimate banks’ deposits-generating and operating efficiencies using a two-stage directional distance function-based network data envelopment analysis (DDF-NDEA) approach and seek to capture the immediate impact of COVID-19 on these efficiency measures by comparing their magnitudes in the pre-pandemic (2014/15–2019/20), just 1-year prior to the pandemic (2019/20), and during the pandemic year (2020/21) periods. The study looks at whether the impact of the COVID-19 pandemic was uniform across ownership types and size classes. The empirical findings suggest that the Indian banking system was resilient and withstood the immediate impact of the COVID-19 pandemic. During the study period, however, the large and medium-sized banks experienced some efficiency losses. By and large, regardless of bank group, banks have shown resilience to the shock of the global health pandemic and improvements in efficiency.

Design of Basin Irrigation System using Multilayer Perceptron and Radial Basic Function Methods

The common use of an artificial neural network model has been in water resources management and planning. The length, width, and discharge of a basin were measured in this study utilizing field data from 160 Dashti Hawler existing projects. Multilayer Perceptron (MLP) and Radial Basic Function (RBF) networks were employed in the basin irrigation assessment. Input factors included the soil type, the conveyance system effectiveness, and the root zone depth. 130 projects were used for calibration, while the remaining 30 were used for validation. When developing the basin irrigation system, the models’ aforementioned indicators’ performance was evaluated using the coefficient of determination (R2), mean absolute error (MAE), relative error (RE), and Nash Sutcliff efficiency (NSE). For the basin's length, width, and discharge, the (R2) values for the MLP model were determined to be 0.97, 0.97, and 0.96, respectively, whereas the corresponding values for the RBF model were 0.88, 0.89, and 0.89. Compared to the RBF model, the values of (MAE) for basin length, width, and discharge for the MLP model were determined to be 8.99, 8.52, and 42.58, respectively. However, the (NSE) values for the models mentioned above were 0.95, 0.96, and 0.94, as well as 0.65, 0.66, and 0.66 for the basin’s length, width, and discharge, respectively. When it comes to building the irrigation system for the basin, the MLP is more precise than RBF depending on the values of (R2), (MAE), and (NSE). Finally, the ANN approach uses additional design options quickly examine which model is computationally efficient.

A Study on the Design of Error-Based Adaptive Robust RBF Neural Network Back-Stepping Controller for 2-DOF Snake Robot’s Head

In this paper, we will propose the controller of a 2-DOF head in a snake robot for effective image data reading when the snake robot is driving, and present an error-based adaptive robust radial base function neural network back-stepping controller. The snake robot head system is a nonlinear system, and there are unmeasurable disturbances that occur while driving. To solve this problem, we use back-stepping controller and radial basis function neural network to compensate for unmeasurable disturbances to improve the steady state. In order to further compensate for the network approximation error that occurs during training or large signal changes, we use adaptive coefficients and error functions to approximate the network approximation error and design adaptive robust terms. Compared to the previous controller, the proposed controller can actively compensate for large signal changes and has the advantage of not generating residual input in a steady state. The proposed controller is based on Lyapunov function candidate to design an adaptive law and prove the system stability. The stability of the control system is proven through Lyapunov analysis and bounded. The proposed controller compared and verified the controller performance for two inputs through simulation and presented the efficiency of the controller.

Event-Triggered MFAC of Nonlinear NCSs Against Sensor Faults and DoS Attacks

The event-triggered model-free adaptive control (ET-MFAC) problem for nonlinear networked control systems (NNCSs) with presence of sensor faults and denial-of-service (DoS) attacks is investigated. The attack occured in sensor-to-controller networked channels is supposed to obey the Bernoulli distribution. While sensor faults are formulated as unknown functions which could be approximated by a radial basis function-based neural networks (RBF-NNs). Then an ET-MFAC algorithm is constructed to ensure the tracking performance under sensor faults and DoS attacks based on adaptive estimations. The designed control algorithm is independent with the system structure and only uses the system input and output data. An example with comparison is given to demonstrate the validity of the new ET-MFAC algorithm.

Response surface methods based in artificial intelligence for superstructure thermoeconomic optimization of waste heat recovery systems in a large internal combustion engine

In a large internal combustion diesel engine, less than half of the fuel energy is converted into useful energy, while the remaining energy is lost, mainly by the exhaust gases and cooling water. Thus, the implementation of waste heat recovery (WHR) systems has been one of the main research areas for increasing power, and reducing specific fuel consumption and pollutant emissions, which favors the improvement of these engines. Currently, there are two important challenges regarding the use of WHR systems in internal combustion diesel engines: (i) identifying the best technology, or combination of technologies, for the WHR in an internal combustion diesel engine from an economic point of view; and (ii) determining the ideal configuration and the best design parameters for the most suitable system. This paper proposes an optimization procedure for automatic selection of the most economically suitable WHR technology for a large internal combustion diesel engine, as well as the definition of its optimal configuration and ideal design parameters. For this, superstructures composed by the Organic Rankine Cycle (ORC), Kalina Cycle (KC), and Conventional Rankine Cycle (CRC) are modeled and optimized using a genetic algorithm. For the formulation of the thermoeconomic optimization problem—Mixed Integer Nonlinear Programming (MINLP)—the economic model of each component of the superstructures is evaluated and the objective function is proposed based on the specific cost. However, due to the complexity of the superstructure optimization problem, the use of the response surface method to solve this problem can become more attractive than the original modelling optimization. The superstructure optimization problem, as well as its thermodynamic modeling, economic modeling and response surfaces based on radial base function and artificial neural network, were solved using the programs Engineering Equation Solver (EES) and Octave. The results show that for a medium-sized superstructure (384 variables and 17 decision variables), despite the high computational effort, the use of the response surface method in the optimization problem proved to be more efficient than the original modelling optimization, and for a large superstructure (944 variables and 45 decision variables) it is only possible to solve the optimization problem using the response surface method. Furthermore, after the superstructure’s optimizations, the additional net power is produced by ORC through of the recovery waste heat from the exhaust gases mass flow and the cooling water mass flow provided by the diesel engine. The additional net power represents around 7% of the nominal net power.

Software Defect Prediction through Neural Network and Feature Selections

Software failure such as software defect causes billion of dollar loss every year. Software failure also affects billion of people worldwide. Inadequate software testing can cause software failure. To predict the software defect, this study proposed a model consisting of feature selection and classifications. The correlation base method was used for feature selection, and radial base function neural network (RBF) was used for classification. Also, for testing the proposed system, fourteen NASA data sets were used including CM1, JM1, KC1, KC2, KC3, KC4, MC1, MC2, MW1, PC1, PC2, PC3, PC4, and PC5. The data set was divided using the well-known K-cross-validation methods which were performed to divide the data set for training and testing the RBF. The RBF were trained and tested before and after feature selections. Precision, recall, F-measure, and accuracy are four methods used to evaluate the performance of the proposed methods. The precision obtained for the fourteen data sets was CM1, 94.01%; JM1, 85.18%; KC1, 83.24%; KC2, 81.27%; KC3, 79.30%; KC4, 85.29%; MC1, 99.89%; MC2, 73.27%; MW1, 90.90%; PC1, 98.79%; PC2, 100%; PC3, 95.67%; PC4, 95.12%; and PC5, 80.89%. Recall was as follows: CM1, 95.78%; JM1, 87.89%; KC1, 86.24%; KC2, 83.82%; KC3, 82.10%; KC4, 86.28%; MC1, 100%; MC2, 76.67%; MW1, 92.09%; PC1, 99.98%; PC2, 100%; PC3, 96.23%; PC4, 95.17%; and PC5, 81.80%. F-measure was as follows: CM1, 0.95; JM1, 0.87; KC1, 0.83; KC2, 0.82; KC3, 0.85; KC4, 0.86; MC1, 0.99; MC2, 0.76; MW1, 0.95; PC1, 0.99; PC2, 0.99; PC3, 0.97; PC4, 0.95; and PC5, 0.80. The accuracy obtained was as follows: CM1, 93.99%; JM1, 84.87%; KC1, 83.25%; KC2, 79.11%; KC3, 78.25%; KC4, 83.18%; MC1, 99.01%; MC2, 70.18%; MW1, 88.90%; PC1, 98.99%; PC2, 99.80%; PC3, 94.11%; PC4, 94.4%; and PC5, 79.02%. The proposed method results were compared with the result obtained from different methods. The proposed model obtained better results than other methods for data set CM1, KC4, MC1, PC1, PC2, PC3, PC4, and PC5.

Fault-tolerant trajectory tracking control of an unmanned marine vehicle via an adaptive non-singular fast terminal sliding mode control

In this paper, a novel finite-time fault-tolerant trajectory tracking controller is created to render a marine vehicle to enhance tracking performance in the presence of complex unknown variables, including model uncertainties, environmental disturbances, and actuator faults. An adaptive fault-tolerant finite-time sliding mode controller is designed by introducing adaptive control techniques, the non-singular fast terminal sliding mode (NSFTSM) function, and a radial base function (RBF) neural network. The radial base function neural network (RBFNN) is developed to eliminate the influences of model uncertainties and environmental disturbances. A fault compensation by integrating the adaption technique is designed to reduce the effects of actuator faults and approximation errors. Suffering from uncertainties and actuator faults, the proposed finite-time tracking controller can track the desired trajectory with high precision. Simulation results and compared simulations indicate the efficiency and superiority of the proposed controller.

Enhanced implicit function-based network for arbitrary-scale image super-resolution

With the great development of deep learning, the performance of single image super-resolution (SR) has achieved tremendous progress. As an emerging and promising branch of the SR task, the arbitrary-scale SR task is receiving increasing attention from researchers due to its efficiency and practicality. Although the recent work learning implicit image function opened a solution for arbitrary-scale image SR, its reconstructed images contained structural distortions caused by defective prediction of high-frequency textures. To overcome this problem and further improve the performance of arbitrary-scale image SR, we propose an effective arbitrary-scale SR network, namely, enhanced arbitrary-scale super-resolution, which achieves the arbitrary-scale SR task in a single model by introducing a local-global encoder and enhanced implicit image function. Unlike conventional SR methods, which only stack up convolutional blocks to extract the local feature, the local-global encoder has two branches in parallel, including the local feature branch and the global prior branch. The former effectively extracts the local feature from a low-resolution image and the latter extracts the global prior to assist in the high-resolution image reconstruction. Next, we redesigned an enhanced implicit image function in the form of a dual modulation multiplayer perceptron (MLP) by replacing the implicit image function with a vanilla MLP. Moreover, we introduce the spatial encoding to further reduce structural distortions of reconstructed images. Extensive experiments were conducted to evaluate the performance and demonstrate the superiority of our proposed model.

Design of a Non-Linear Observer for SOC of Lithium-Ion Battery Based on Neural Network

This paper presents a method for use in estimating the state of charge (SOC) of lithium-ion batteries which is based on an electrochemical impedance equivalent circuit model with a controlled source. Considering that the open-circuit voltage of a battery varies with the SOC, an equivalent circuit model with a controlled source is proposed which the voltage source and current source interact with each other. On this basis, the radial basis function (RBF) neural network is adopted to estimate the uncertainty in the battery model online, and a non-linear observer based on the radial basis function of the RBF neural network is designed to estimate the SOC of batteries. It is proved that the SOC estimation error is ultimately bounded by Lyapunov stability analysis, and the error bound can be arbitrarily small. The high accuracy and validity of the non-linear observer based on the RBF neural network in SOC estimation are verified with experimental simulation results. The SOC estimation results of the extended Kalman filter (EKF) are compared with the proposed method. It improves convergence speed and accuracy.

Design of Aging Smart Home Products Based on Radial Basis Function Speech Emotion Recognition.

The rapid development of computer technology and artificial intelligence is affecting people’s daily lives, where language is the most common way of communication in people’s daily life. To apply the emotion information contained in voice signals to artificial intelligence products after analysis, this article proposes a design based on voice emotion recognition for aging intelligent home products with RBF. The authors first aimed at a smart home design, and based on the problem of weak adaptability and learning ability of the aging population, a speech emotion recognition method based on a hybrid model of Hidden Markov/Radial Basis Function Neural Network (HMM/RBF) is proposed. This method combines the strong dynamic timing modeling capabilities of the HMM model and the strong classification decision-making ability of the RBF model, and by combining the two models, the speech emotion recognition rate is greatly improved. Furthermore, by introducing the concept of the dynamic optimal learning rate, the convergence speed of the network is reduced to 40.25s and the operation efficiency is optimized. Matlab’s simulation tests show that the recognition speed of the HMM/RBF hybrid model is 9.82–12.28% higher than that of the HMM model and the RBF model alone, confirming the accuracy and superiority of the algorithm and model.

Optimization of the Battery Pack Heat Dissipation Structure of a Battery-Type Loader

The development of a battery-type loader is an important research direction in the field of industrial mining equipment. In the energy system, the battery will inevitably encounter the problem of heat dissipation when using high-power electricity. In this study, we took the power battery pack of a 3 m3 battery-type underground loader as the research object. The influence of single factors, such as the position of the air outlet of the battery pack, the size of the air outlet, the width of the separator, and the reverse plate, on the heat dissipation characteristics of the battery pack were studied. Then, a prediction model between the structural parameters and temperature was established using a radial basis function (RBF) neural network. This prediction model was then used as an adaptation evaluation model for global optimization through the multiobjective particle swarm optimization (PSO) algorithm, using which the optimal combination of structural parameters was obtained. The maximum temperature of the battery pack after optimization was reduced by 22%, compared to that before optimization, and the average temperature was reduced by 12.5%. Overall, the heat dissipation effect significantly improved. The optimization results indicate that the method proposed in this paper is feasible for use in optimizing battery heat dissipation systems in electric vehicles, thus providing a reference for research related to battery pack heat dissipation.

Nonlinear modeling of industrial boiler NOx emissions

ABSTRACT Pollutant emissions into the atmosphere are recognized as a significant problem in fossil fuel combustion. The pollution emission measurement in industrial boilers is difficult and expensive but fundamental for monitoring and controlling. Frequently continuous emissions monitoring (CEM) system is out of service or useless due to obsolescence, high maintenance cost, and so on or simply is not installed. When a system for measuring pollutant emissions is not available, an alternative method must be employed to get the pollutant emission value. According to the black-box model approach, this article describes the nonlinear modeling of NOx emissions from a utility boiler. Bayesian-Gaussian (BG), multilayer perceptron (MLP), and Volterra polynomial basis functions (VPBF) neural networks are developed for model benchmarking. Experimental data from a utility boiler was acquired in order to model definition and evaluation. The models process three boiler variables oxygen excess, fuel mass flow and flue gas recirculation gates for NOx emission estimation. Models with BG show better performance than models with MLP and VPBF for NOx prediction. Implications: The technology to control NOx emissions generated by combustion operates under strict regulations. In order to reduce NOx emissions, theoretical models of NOx generation have been studied extensively, including nitrogen chemistry and the dynamic flow of gas particles which is very complex. The new technology trends would require the continuous measurement of high precision NOx emissions to achieve further reductions in NOx emissions. Currently, NOx emissions are measured by a Continuous Emission Monitoring system, which turns out to be extremely expensive and difficult to maintain, so alternative low-cost solutions are desirable. Our contribution shows how algorithms based on different artificial intelligence techniques are viable and quality alternatives for the measurement of continuous NOx emissions. The NOx emissions models based on IA algorithms are viable alternatives that have versatility and self-tuning capacity due to the fact that they are based on boiler operation parameters which have valuable information few explored nowadays.

Design Method of Intelligent Ropeway Type Line Changing Robot Based on Lifting Force Control and Synovial Film Controller

Aiming at the problems of low efficiency, reliability, and safety of manual construction for demolition of old lines, a design method of an intelligent ropeway type line changing robot based on lifting force control and synovial film controller is proposed. First, the mechanical model of robot load and line sag is established, and the sag of the overhead line where the robot is located is used to calculate the jacking force that the jacking device needs to provide to the robot. Then, by introducing the radial basis function (RBF) neural network adaptive algorithm into the synovial controller, an adaptive sliding mode position control algorithm based on the RBF neural network is designed to achieve high-precision motion control of the robot in complex operating environments. Finally, based on the compactness, weight, and reliability of the robot, the optimal design is carried out from four aspects of topology, size, shape and morphology, and the design scheme of the robot for wire removal is proposed, and the robot is produced. The developed robot and the other three robots are compared and analyzed under the same conditions through simulation experiments. The results show that the maximum operating time, maximum climbing angle, and maximum traveling speed of the robot developed in this study are all optimal, which are 45 min, 10°, and 1 m/s respectively, and the performance is better than the other three comparison algorithms.