Radial Basis Function Neural Network Research Articles

Fixed-time event-triggered adaptive control of manipulator system with input deadzone and model uncertainty

There exist universal model uncertainty and input deadzone in mechatronic motion plant due to unknown model parameters and actuator physical feature, which will degrade the motion performance and stability. In this study, a fixed-time event-triggered adaptive control is proposed in n-DOF manipulator system to address these problems. Firstly, the dynamic model of n-DOF manipulator with joint friction and input deadzone is constructed by Lagrange technique. Then a radial basis function neural network (RBFNN) is designed to approximate uncertain dynamics. Meanwhile, an event-triggered mechanism (ETM) is used to reduce the control update frequency and to save the communication resource. Furthermore, an adaptive estimation law is adopted to compensate unknown input deadzone parameters. Based on backstepping iteration technique, a fixed-time convergent controller is presented to guarantee the system state errors convergence to zero neighborhood in finite time irrelevant to arbitrary initial state. Finally, the effectiveness of the proposed control scheme is verified by sufficient comparative simulation and experimental results.

Radial Basis Function Neural Network with ensemble clustering for modeling mathematics achievement in Indonesia based on cognitive and non-cognitive factors

Mathematics achievement could be influenced by cognitive and non-cognitive factors. The potential variable of cognitive factor is metacognition, whereas non-cognitive factors include Economic, Social, and Cultural Status (ESCS), resilience, life satisfaction, happiness, pride, fear, sadness, and gender. Those variables involve numerical and categorical data. For this reason, this study aims to apply the Radial Basis Function Neural Network (RBFNN) model with ensemble clustering to model the relation between cognitive and non-cognitive aspects and mathematics achievement. The RBFNN is a soft computing approach based on the neural network model and has been shown as an effective model and free of assumption. The ensemble clustering is a process in RBFNN modeling to capture the independent variables involving the numerical and categorical data. It employs K-means clustering for the numerical data and K-modes for categorical data and combines the results of those two methods. The data used in this study are published by PISA (Program for International Student Assessment) 2018. The results show that the RBFNN with ensemble clustering deliver good performance in modeling the students’ mathematics achievement based on the cognitive and non-cognitive factors in terms of prediction accuracy. Other than RBFNN model, the use of cognitive and non-cognitive factors involving in this study also contributes to the high accuracy prediction. This further emphasizes that these factors are good predictors of mathematic achievement. Additionally, we suggest the silhouette cluster validation in the clustering process, since it leads to the number of hidden neurons of the best RBFNN model.

Prediction of soil heavy metal contents in urban residential areas and the strength of deep learning: A case study of Beijing

Predicting soil heavy metal (SHM) content is crucial for understanding SHM pollution levels in urban residential areas and guide efforts to reduce pollution. However, current research indicates low SHM prediction accuracy in urban areas. Therefore, we employed a deep learning method (fully connected deep neural network) alongside four other methods (muti-layer perceptron, radial basis function neural network, multiple stepwise linear regression, and Kriging interpolation) to predict SHM content in the urban residential areas of Beijing and demonstrated the strength of deep learning in improving prediction accuracy. We found the contents of the evaluated heavy metals (Cd, Cu, Pb, and Zn) exhibited significant correlations with numerous other soil physicochemical properties and environmental factors. The prediction accuracy for Cu, Pb, and Zn contents was relatively high across different methods. Notably, deep learning showed considerable strength in predicting the contents of the four heavy metals, with the R2 for the test set of the model ranging from 0.75 to 0.91. Compared to other methods, deep learning achieved markedly higher prediction accuracy according to different accuracy evaluation indicators (e.g., deep learning showed increases in the cumulative R2 of the four heavy metals ranging from 53.16 % to 187.36 % compared to other methods). Our study indicates that deep learning can significantly improve SHM content prediction accuracy in urban areas and is highly applicable in urban residential areas with complex environmental influences.

Unmanned Floating Object Transportation Applying Multiple Dynamic Positioning Tugboats: A Novel Cooperative Control Algorithm

Abstract To promote the automation and intelligence of marine floating object transportation, this paper proposes a cooperative consensus control algorithm for multiple unmanned dynamic positioning (DP) tugboats to transport an unactuated floating structure object using cables. The major concept of present algorithm is to implement a leader-follower formation strategy among distributed tugboats, with the aim of effectively maneuvering the object by adjusting the relative position between the virtual leader and the object in a reasonable manner. A cooperative consensus controller is integrated into the feedback controller of each tugboat local DP system in order to facilitate cooperative coordination among tugboats in a formation. A customized DP system, which incorporates the radial basis function neural network supervisor control into the DP controller design and introduces nonlinear disturbance observer into the low-frequency motion state observer design, is proposed to address cable tension disturbances, and thus, the tracking performance of the DP tugboat is improved. Full-scale nonlinear time domain simulations are performed under variable environmental conditions, verifying the effectiveness of the proposed automatic towing control scheme.

Finite-time adaptive NN dynamic surface control for nonstrict nonlinear FOSs subject to input dead-zone and full-states constraints

This article focuses on a kind of nonstrict nonlinear fractional-order systems (FOSs) suffering from state constraints and dead-zone input. Meanwhile, a finite-time adaptive dynamic surface control (DSC) approach based on backstepping technology and approximation principle of radial basis function neural network (RBFNN) is developed. To overcome the problem of inherent computational complexity, a fractional-order filter is applied to approach the virtual controller and its fractional-order derivative in each step of the backstepping procedure. The barrier Lyapunov function (BLF) is employed to handle the state constraints, and finite-time stability criteria on the basis of fractional-order Lyapunov method are introduced to prove the finite-time convergence of the tracking error into a small region around the origin. It is shown that all the solutions of the closed-loop system are bounded, while the state constraints are satisfied within a predetermined finite time. Finally, two examples are provided to demonstrate the effectiveness of the presented control scheme.

Towards stable and efficient nitrogen removal in wastewater treatment processes via an adaptive neural network based sliding mode controller

Advanced controllers often offer an innovative solution to proper quality control in wastewater treatment processes (WWTPs). However, nonlinearity and uncertain disturbances usually make the conventional control strategies inadequate or impossible for the stable operations of WWTPs. To guarantee the stability of ammonia nitrogen concentration (SNH) control in WWTPs, a direct adaptive neural networks-based sliding mode control (ANNSMC) strategy has been proposed in this article. A sliding mode controller is designed and implemented with the help of an adaptive Neural Network (ANN), named Radial Basis Function Neural Network (RBFNN), which can approach the desired control law accurately. Also, the stability of a system installed with the ANNSMC is analyzed by using the Lyapunov theorem, which ensures system robustness and adaptability. Additionally, to deal with high energy consumption and low treatment efficiency problems in the wastewater denitrification processes, this paper proposes a dual-loop denitrification control strategy and validates it in the Benchmark Simulation Model No.2 (BSM2) platform. The strategy can strengthen the denitrification efficiency by collaborating the SNH with nitrate nitrogen (SNO) concentration in the WWTPs properly. The experimental results demonstrate that the proposed strategy can obtain remarkable stability and robustness, reducing energy consumption effectively compared with other standard and advanced control strategies.

Research on fixed-time time-varying formation of heterogeneous multi-agent systems based on tracking error observer under DoS attacks

In this paper, the fixed-time time-varying formation of heterogeneous multi-agent systems (MASs) based on tracking error observer under denial-of-service (DoS) attacks is investigated. Firstly, the dynamic pinning strategy is used to reconstruct the communication channel for the system that suffers from DoS attacks to prevent the discontinuous transmission information of the communication network from affecting MASs formation. Then, considering that the leader state is not available to each follower under DoS attacks, a fixed-time distributed observer without velocity information is constructed to estimate the tracking error between followers and the leader. Finally, adaptive radial basis function neural network (RBFNN) is used to approximate the unknown ensemble disturbances in the system, and the fixed-time time-varying formation scheme is designed with the constructed observer. The effectiveness of the proposed control algorithm is demonstrated by the numerical simulation.

Machine learning-based prediction of construction and demolition waste generation in developing countries: a case study.

Data is needed for making informed decisions regarding managing waste in the time of construction and demolition phases of buildings. However, data availability is very limited in most developing countries in the area of waste generation. The objective of this study is to employ an artificial intelligence (AI)-based approach to develop a reliable model for forecasting monthly construction and demolition waste (C&DW) generation in the case study of Tehran, Iran. We have trained different prediction models using various AI algorithms, including multilayer perceptron neural network, radial basis function neural network, support vector machines, and adaptive neuro-fuzzy inference system (ANFIS). According to the findings, all employed AI algorithms demonstrated high prediction performance for C&DW forecasting models. The ANFIS model, with R2 = 0.96 and RMSE = 0.04209, was identified as the model that better represented the observed values of C&DW generation. The better efficiency of the ANFIS model could be due to its effective enhancement of neural networks to model subjective variables based on fuzzy logic capabilities. The developed prediction model can be employed as an efficient tool for policy and decision-making for C&DW management by predicting waste quantities in the future.

Optimizing K-means clustering center selection with density-based spatial cluster in radial basis function neural network for load forecasting of smart solar microgrid

Optimizing K-means clustering center selection with density-based spatial cluster in radial basis function neural network for load forecasting of smart solar microgrid

Editorial

Dear Readers, It gives me great pleasure to announce the seventh regular issue of 2024. In this issue, 5 papers by 12 authors from 6 countries - Brazil, Ecuador, Germany, Iraq, Spain, Turkey - cover various topical aspects of computer science. In a continuous effort to further strengthen our journal, I would like to expand the editorial board: If you are a tenured associate professor or above with a strong publication record, you are welcome to apply to join our editorial board. We are also interested in high-quality proposals for special issues on new topics and trends. As always, I would like to thank all the authors for their sound research and the editorial board and guest reviewers for their extremely valuable review effort and suggestions for improvement. I also want to thank the readers for their interest in our articles, which is reflected in the consistently high number of user accesses and PDF downloads. These contributions, together with the generous support of the consortium members, maintain the quality of our journal. In the seventh regular issue, I am very pleased to present the following 5 accepted articles: Vinicius Bischoff and Kleinner Farias from Brazil report their study on a controlled experiment with 22 participants (15 students, 7 professionals) in which the correctness and the effort required for the integration of feature models were investigated. Abdulkadir Buldu, Kaplan Kaplan and Melih Kuncan from Turkey present their research on an assistive system based on EEG data and Continuous Wavelet Transform (CWT), which aims to reduce the life-threatening risk for epilepsy patients. In a collaboration between researchers from Ecuador and Spain, Darwin Alulema, Maximiliano Paredes-Velasco and Ricardo de Arriba Lasso report in their manuscript on the LESCA system, which performs adaptive content feedback through scaffolding and supports the development of high-level competencies. In another joint research between colleagues from Iraq and Germany, Anwar Mira and Olaf Hellwich present their approach to improve recognition capabilities by optimizing deep learning features for hand gesture image recognition. Specifically, they propose to enhance features of well-trained DNNs using an improved radial basis function (RBF) neural network, targeting recognition within individual gesture categories. And last but not least, Rasim Çekik and Mahmut Kaya from Turkey propose in their research a new performance metric to evaluate filter feature selection methods in text classification.  Enjoy Reading! Best regards,  Christian Gütl, Managing Editor 

An Embedded Neural Network Approach for Reinforcing Deep Learning: Advancing Hand Gesture Recognition

Deep neural networks (DNNs) can face limitations during training for recognition, motivating this study to improve recognition capabilities by optimizing deep learning features for hand gesture image recognition. We propose a novel approach that enhances features from well-trained DNNs using an improved radial basis function (RBF) neural network, targeting recognition within individual gesture categories. We achieve this by clustering images with a self-organizing map (SOM) network to identify optimal centers for RBF training. Our enhanced SOM, employing the Hassanat distance metric, outperforms the traditional K-Means method across a comparative analysis of various distance functions and the expanded number of cluster centers, accurately identifying hand gestures in images. Our training pipeline learns from hand gesture videos and static images, addressing the growing need for machines to interact with gestures. Despite challenges posed by gesture videos, such as sensitivity to hand pose sequences within a single gesture category and overlapping hand poses due to the high similarities and repetitions, our pipeline achieved significant enhancement without requiring time-related training data. We also improve the recognition of static hand pose images within the same category. Our work advances DNNs by integrating deep learning features and incorporating SOM for RBF training.

Neural learning fault-tolerant control of fuel cell–battery–ultracapacitor-based hybrid electric vehicle

This article investigates the energy management and control of a fuel cell hybrid electric vehicle (FCHEV) with parametric uncertainties and sensor faults. The FCHEV in this study consists of a fuel cell, battery, and ultracapacitor connected to the DC-bus via DC–DC power converters, while the DC-bus is connected to the AC motor which drives the electric vehicle via a DC–AC converter. To control the power transfer from the energy sources to the drivetrain, a finite-time fractional-order control is proposed to coordinate the DC–DC power converters. A radial basis function neural network (RBFNN) is employed to estimate and compensate for sensor faults and parametric uncertainties. A minimum learning parameter scheme is used to minimize the computational burden on the RBFNN. The main tasks of the proposed scheme are; tolerating faults and parametric uncertainties, delivering the required power to the load, voltage regulation of the DC-bus, tracking the reference currents for the battery, fuel cell, and ultracapacitor in a short finite time. The closed-loop system is guaranteed to be stable in finite time using the Lyapunov function. The simulation results highlight the validity of the presented control.

A detection method of Saposhnikovia divaricata seed vigor based on near-infrared spectral feature extraction

Saposhnikovia divaricata is an important Chinese herbal medicine, the rapid detection of seed vigor is of great significance and practical value for the breeding selection and cultivation production of Saposhnikovia divaricata varieties. It was difficult to solve the problem of rapid testing technology of Saposhnikovia divaricate seed of the shortcomings of traditional chemical testing methods, such as cumbersome operation, time-consuming, easy to cause seed damage, and so on. In this paper, a rapid method for detecting seed vigor was processed for the Saposhnikovia divaricata based on near-infrared spectral feature extraction. First, 612 sets of near-infrared spectral data were obtained using a Fourier transform near-infrared spectrometer, and randomly divided into a calibration set and prediction set according to the ratio of 3:1. Then, the spectral data were preprocessed by the multivariate scatter correction method (MSC), the successive projection algorithm (SPA) was used to extract the feature wave numbers of spectral data. A total of 5 feature wave numbers were selected from the original 1845 wave numbers, with a streamlining rate of 99.73 %. Finally, a detection method of seed vigor was constructed based on the radial basis function neural network (RBF) with 5 feature wave numbers as input data. A network structure of the model MSC-SPA-RBF is of type 5-48-3, the accuracy of seed vigor detection was 99.0 %, and the detection time was 0.0033 s. The result indicates that the established model is a fast, non-destructive, and accurate method for detecting seed vigor of Saposhnikovia divaricata, which provides a theoretical basis and technical support for the rapid detection of Saposhnikovia divaricata seed vigor.

Modeling and control of a novel mechatronic model of a 750 kW-FSWT with power-splitting transmission using RBF neural network: a bond graph approach

This work addresses issues that appear from wind turbines equipped with frequency converters and presents a new fixed-speed wind turbine (FSWT) concept based on a split power transmission, along with a Mechatronic Control Model. The wind turbine rotor drives the first transmission shaft, while a servomotor with variable speed powers the second input. The differential gear transmission output is linked to the electric grid through an asynchronous generator. To optimize the power extracted from the wind energy while minimizing excessive dynamic loads on the wind turbine, a mechatronic control model of a 750 kW-FSWT is applied using a proportional and integral controller (PI). The paper suggests employing neural networks and evolutionary algorithms for determining appropriate PI gains. For collective servomotor control of a 750 kW-FSWT, a radial basis function (RBF) neural networks based on PI controller is proposed. To acquire an optimum dataset for RBF training, the particle swarm optimization (PSO) evolutionary algorithm is harnessed. The robustness and effectiveness of the proposed model and controller are verified and confirmed through simulation results. Hands-on experience is conducted using the 20-sim software package.

Enhanced three-dimensional trajectory tracking control for AUVs in variable operating conditions using FMPC-FTTSMC

In addressing the variable operating conditions encountered in complex underwater tasks, an enhanced three-dimensional tracking control method is proposed for autonomous underwater vehicle (AUV) based on fuzzy model predictive control-finite time terminal sliding mode control (FMPC-FTTSMC). Firstly, to enhance adaptability to tasks and environments, fuzzy model predictive control method is designed to achieve precise three-dimensional trajectory tracking. Additionally, a fuzzy weight allocator is employed to enable AUV to autonomously adjust optimization strategies based on real-time states such as task type, speed, and distance from the seabed, thus better coping with changing conditions and improving the universality of the control method. Secondly, a dynamic controller is designed using the finite-time terminal sliding mode control method, combined with a finite-time radial basis function neural network (FTRBFNN) disturbance observer to accurately estimate disturbances. Finally, simulation results demonstrate that the proposed method effectively reduces optimization solving time compared to traditional model predictive control, achieves trajectory tracking control under various conditions, meets preset state constraints, and demonstrates excellent tracking accuracy and robustness.

Improved machine learning-based pitch controller for rated power generation in large-scale wind turbine

In variable speed and variable pitch large-scale wind turbines, the pitch controller plays a crucial role in optimizing power output near the rated value during wind speeds that exceed the rated threshold. Nevertheless, the erratic nature of wind speeds poses challenges to the pitch controller’s efficacy, leading to a decline in generator power. So, there has been a growing interest among researchers in the development of machine learning-based pitch controllers. This paper introduces an improved recurrent radial basis function neural network and its parameters were tuned using the modified particle swarm optimization algorithm to enhance neural network performance. The proposed controller is validated in a benchmark wind turbine and comparative analysis are conducted against existing controllers in the literature. Through a series of comprehensive studies, the proposed controller consistently outperforms its counterparts, particularly in achieving power output close to the rated value.

Chaotic libration and control of a space tether-sail system in Earth polar orbits with J2 perturbation

The recently proposed space tether-sail system could enable various interesting and important potential space missions thanks to its thin and long connecting tether and solar radiation pressure (SRP) force without consuming propellants. This paper focuses on nonlinear libration and its control of a tether-sail system in Earth polar orbits. Firstly, nonlinear coupled in-plane and out-of-plane dynamics of the system with a rigid mass-distributed tether and two point masses (a chief satellite and sail respectively) is established using the Lagrangian equation method. Secondly, the predicted occurrence of chaotic in- and out-of-plane librational motions is verified utilizing numerical tools such as presenting the time history of libration, the phase plane, the Poincaré section and power spectral density(PSD). Specifically, the paper investigates the sensitivity of nonlinear dynamical responses to initial values, focuses on the chaotic motion caused by the coupling between the in- and out-of-plane librations, the J2 perturbation of the Earth gravitational field and the small eccentricity of the orbits, also studies the nonlinear librational characteristics influenced by the initial mechanical energy (the Hamiltonian). Thirdly, chaotic librational motions will be controlled merely using modulatable SRP force by the sail propellantlessly. A sliding mode controller based on exponential approaching law is developed. To mitigate the effects of control torque saturation, an input compensator based on Radial Basis Function (RBF) neural network is designed. In addition, to address the cumbersome and inefficient manual tuning of control parameters for the sliding mode controller, a parameter tuning algorithm based on Learning Automata is designed. This algorithm is capable of tuning a high-quality set of controller parameters within 100 iterations. The effectiveness of the propellantless actuators for chaotic libration motion control and developed control algorithm is supported by numerical simulations.

Machine learning-assisted investigation of anisotropic elasticity in metallic alloys

This study aims to develop a machine learning (ML)-based method for predicting the elasticity tensor of anisotropic metallic alloys with 21 independent constants. In this respect, the elastic moduli of a batch of additive-manufactured specimens with various orientations, determined by Tait–Bryan angles, are utilized as input data, while the anisotropic elastic tensor are targeted for prediction. Our primary findings indicate the efficacy of the radial basis function neural network (RBFNN) as a robust ML model for elasticity tensor prediction. Notably, the model demonstrates slightly higher efficiency in predicting elasticity tensor components aligned with principal axes compared to off-diagonal components. Moreover, with increasing anisotropy, the model assigns greater contribution to shear and orthotropic components, optimizing prediction performance. Additionally, a case study using Inconel 718 further illustrates the model's effectiveness in capturing the elasticity tensor. Importantly, it is suggested that the proposed ML model offers advantages over experimental methods, such as impulse excitation-based procedures, and iterative numerical simulations, by reducing sample preparation requirements and saving time.

Finite-time funnel synchronization control based on distributed observer for multi-motor driving systems with input saturation

In this article, the finite-time synchronization control problem is developed for multi-motor driving systems with input saturation. A radial basis function (RBF) neural network is utilized to estimate the unknown uncertainties and the disturbances. In contrast to current control strategies, this study proposes a new approach that utilizes a finite-time distributed observer to estimate the reference signal and then uses the estimated signal to design a synchronization controller, which effectively separates the tracking problem from the synchronous controller design. Furthermore, a funnel function is constructed to actualize the state constraints and confine the synchronization error within a specified boundary. Then, a finite-time funnel control protocol is proposed to ensure that each motor follows the estimated reference signal. Eventually, we illustrate the effectiveness of the proposed method through a numerical example.

Finite-time prescribed performance tracking control for nonlinear time-delay systems with state constraints and actuator hysteresis

In this paper, the problem of adaptive neural network prescribed performance tracking control for a class of non-strict feedback time-delay systems constrained by full-state is studied. Radial basis function (RBF) neural networks (NNs) are integrated into the backstepping medium to deal with the uncertain functions and the barrier Lyapunov function (BLF) technique ensures that the state of the system does not exceed its limits. Subsequently, integrated with the Lyapunov–Krasovskii functional, the proposed control scheme makes the tracking errors converge to the preset region while the state constraint is not violated. Finally, the effectiveness of the scheme is supported by two simulation experiments.