Recurrent Radial Basis Function Research Articles

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.

Mitigating Peak Sidelobe Levels in Pulse Compression Radar using Artificial Neural Networks

In this paper, Artificial Neural Networks (ANNs) are being considered to obtain low sidelobe pattern for binary codes and thereby to improve the performance of pulse compression radar. Pulse compression is a popular technique used for improving range resolution in the radar systems. This paper proposes a new approach for Pulse Compression using various types of ANN networks like Multi-Layer Perception (MLP), Recursive Neural Networks (RNN), Radial Basis Function (RBF) and Recurrent Radial Basis Function (RRBF) and a special class of Feed-Forward Wavelet Neural Network (WNN) with one input layer, one output layer and one hidden layer are being considered. Networks of 13-bit Barker code and extended binary Barker codes of 35, 55 and 75 length codes were used for the implementation and thereby to improve the performance of pulse compression radar. WNN-based networks using Morlet and Sigmoid activation function in hidden and output layers respectively, a special class of Artificial Neural Network is considered in this paper. The performance metrics used are Peak Sidelobe Ratio (PSLR), Integrated Sidelobe Ratio (ISLR) and Signal-to-Sidelobe Ratio (SSR). Further the performance in terms of range and Doppler resolution is also presented in this paper. Better performance in terms of sidelobe reduction can be achieved with ANNs compared to Autocorrelation Function (ACF) called as matched filter. If the sidelobe values are high there is possibility of masking weaker return signals and there by detection becomes difficult. From this paper it can be established that RRBF gives better result than other ANN networks. Further, WNN gives the best performance even compared with RRBF in terms of sidelobe reduction in pulse compression radar.

Short-term forecasting of streamflow by integrating machine learning methods combined with metaheuristic algorithms

This paper aims to introduce an artificial intelligence approach to enhance short-term daily streamflow forecasts through the integration of machine learning (ML) techniques with meta-heuristic (MH) algorithms. To maximize performance, a comprehensive analysis involving the autocorrelation and partial autocorrelation functions of the observed streamflow was conducted to derive ten distinct input combinations, from which the most suitable set was selected for investigation. Subsequently, six distinct ML methods, namely, decision trees, support vector regression, long short-term memory, gated recurrent unit, multi-layer perceptron, and radial basis function (as the optimal input combination), were leveraged to predict one-day-ahead streamflow. The most promising outcomes from these six explored methods were synergistically amalgamated to enhance predictive precision. This amalgamation was then optimized by utilizing parameter values hyper-tuned by four different MH algorithms. The algorithms included the shuffled frog leaping algorithm, particle swarm optimization, ant colony optimization (ACO), and gray wolf optimization (GWO). In culmination, a case study centered around the “Wick” river in the UK was conducted to rigorously evaluate the performance of the proposed method, utilizing a range of statistical evaluation indices. The results underscored the efficacy of the proposed combined method in substantially refining streamflow predictions, exhibiting an impressive level of accuracy. Additionally, the outcomes emphasized that ACO and GWO stand out as the optimal algorithms for calibrating the parameters of the amalgamated model. For instance, the R2 values attained by the combined models optimized through the ACO and GWO algorithms were 0.69422 and 0.69444, respectively. These values notably surpass those observed in the initial models, substantiating the superiority of the applied optimization approaches.

Robust Adaptive Neural Network Tracking Control With Optimized Super-Twisting Sliding-Mode Technique for Induction Motor Drive System

This article proposes a robust adaptive supertwisting sliding-mode controller (STSMC) for high-precision IM drive. First, the STSMC is developed for controlling and stabilizing the IM. However, the control performance may be influenced due to exterior disorders along with parameter variations since the IM model is not accurately known during operation. Therefore, it is essential to estimate the lumped disturbance to strength the robustness of the STSMC using system model-based disturbance estimator. Second, to optimize the control performance, a robust adaptive neural-network tracking controller is developed to evade the constraints on knowing the disorders and uncertainties upper bounds. The RANTC combines an STSMC and a recurrent radial basis function network (RRBFN) estimators. The RRBFNs are employed to approximate the IM dynamics along with estimating the optimum super-twisting control algorithms online. The RRBFN training is developed via adaptive particle swarm optimization (APSO) algorithm to attain enhanced performance in less learning iterations, which is the critical issue in real-time applications. Third, to imitate the STSMC algorithms for preserving the robust control characteristics without the necessity of the IM parameters, a direct adaptive intelligent controller (DAIC) based on Takagi–Sugeno–Kang-type recurrent Petri fuzzy-neural-network is developed. Furthermore, the online adaptive laws are derived according to Lyapunov theory, so that the system stability can be assured. The validity of control schemes is verified by simulation and experimentation. The simulation and experimental results confirm the superiority of the STSMC-SMDE, RANTC, and DAIC schemes compared with STSMC irrespective of exterior disorders along with indefinite model uncertainties.

Modeling of laser aided direct metal deposition of stainless steel using supervised deep learning algorithms

Laser Direct Metal Deposition (LDMD) is a very promising additive manufacturing methodology which provides metal cladding layer over the substrate with good corrosion resistance, desired surface finish and very accurate geometry. In this work, an attempt has been made to develop a forward and reverse model of laser aided direct metal deposition utilizing deep learning algorithms. Forward model aims at predicting the deposited bead height and width from the known set of LDMD process parameters such as laser power, scanning velocity, and powder flow rate. Reverse modelling shows the effectiveness of each input parameter over the chosen response factors. Therefore, in the reverse modelling, the optimized input parameters values have been tried to predict to get the desired deposition characteristics during experimentation. Three different neural networks based deep learning architectures, namely, Multi-Layer Feed Forward Neural Network (MLFFNN), Recurrent Neural Networks (RNN) and Radial Basis Function Neural Network (RBFNN), have been put forward to develop the said predictive models. The supervised learning algorithms are used to train the neural networks. The performances of MLFFNN, RNN and RBFNN models are compared among themselves. The results show that all the models are capable of making better predictions and the models can be effectively used in shop floor in optimal selection of most influential parameters for the desired outputs.

Adaptive interval type-2 fuzzy recurrent RBFNN control design using ellipsoidal membership functions with application to MEMS gyroscope

In this article, a hybrid control approach is provided to control the micro-electro-mechanical system (MEMS) triaxial gyroscope as a multi-input multi-output (MIMO) system. Control design includes a fast non-singular terminal sliding mode control (FNTSMC) as a main part of the proposed hybrid control method and since the MEMS gyroscope performance is affected by parameter variations, quadrature errors, and external disturbances in the core of the main controller, adaptive interval type-2 recurrent fuzzy radial basis function neural network (IT2-RFRBF-NN) is employed to estimate the lumped uncertainties. The proposed hybrid approach has four main attributes: (1) it lies in the category of model-free control structures; (2) There is no negative power involved. Hence, the suggested method does not have the singularity problem; (3) to enhance the capability of the proposed method in the present of noise the ellipsoidal membership functions are employed to design adaptive IT2-RFRBF-NN; (4) the Fourier series expansion as a function approximation technique is efficiently used to online estimate the discontinuous component by establishing a soft switching in the proposed controller. With the help of the Lyapunov stability theory, guaranteeing the closed-loop control system stability by the suggested control design is confirmed. The findings of the simulations and comparison with other approaches confirm the superiority of the suggested hybrid approach.

A New Recurrent Radial Basis Function Network-based Model Predictive Control for a Power Plant Boiler Temperature Control

In this paper, a new radial basis function network-based model predictive control (RBFN-MPC) is presented to control the steam temperature of a power plant boiler. For the first time in this paper the Laguerre polynomials are used to obtain local boiler models based on different load modes. Recursive least square (RLS) method is used as observer of the Laguerre polynomials coefficient. Then a new locally recurrent radial basis function neural network with self-organizing mechanism is used to model these local transfer function and it used to estimate the boiler future behavior. The recurrent RBFN tracks system is dynamic online and updates the model. In this recurrent RBFN, the output of hidden layer nodes at the past moment is used in modelling, So the boiler model behaves exactly like a real boiler. Various uncertainties have been added to the boiler and these uncertainties are immediately recognized by the recurrent RBFN. In the simulation, the proposed method has been compared with traditional MPC (based on boiler mathematical model). Simulation results showed that the recurrent RBFN-based MPC perform better than mathematical model-based MPC. This is due to the neural network's online tracking of boiler dynamics, while in the traditional way the model is always constant. As the amount of uncertainty increases, the difference between our proposed method and existing methods can clearly be observed.

PMSM speed control based on intelligent sliding mode technique

PurposeThe purpose of this paper is to present a novel intelligent backstepping sliding mode control for an experimental permanent magnet synchronous motor.Design/methodology/approachA novel recurrent radial basis function network (RBFN) is used to is used to approximate unknown nonlinear functions in permanent magnet synchronous motor (PMSM) dynamics. Then, using the functions obtained from the neural network, it is possible to design a model-based and precise controller for PMSM using the immersive modeling method.FindingsExperimental results indicate the appropriate performance of the proposed method.Originality/valueThis paper presents a novel intelligent backstepping sliding mode control for an experimental permanent magnet synchronous motor. A novel recurrent RBFN is used to is used to approximate unknown nonlinear functions in PMSM dynamics.

Intelligent second‐order sliding mode control for permanent magnet linear synchronous motor servo systems with robust compensator

In this study, an intelligent second-order sliding mode control (SMC) method combining second-order SMC (SOSMC) and recurrent radial basis function neural network (RRBFNN) applicable to the permanent magnet linear synchronous motor (PMLSM) is proposed to achieve high-performance servo control fields. On the basis of a dynamic model of PMLSM and the SMC theory, the chattering problem in SMC is weakened and the tracking accuracy is improved by the design of SOSMC. As for the boundary of the uncertainty factors is difficult to obtain, the optimal performance of SOSMC is hard to achieve, the RRBFNN uncertainty observer is introduced for estimating the value of the uncertainty factors. Owing to the strong learning ability, the network parameters can be trained online. Besides, a robust compensator is developed to suppress the uncertainties such as approximation error, optimal parameter vector and higher Taylor series for further improving the robustness. Moreover, the adaptive learning algorithms are obtained by using the Lyapunov theorem to guarantee the asymptotical stability of the system. The experiments demonstrate that the proposed scheme provides high performance dynamic characteristics and strong robustness to uncertainties.

Effect of topology changes of neural network in classification of weld defects

Non destructive testing play vital role in weld assessments. Time of Flight Diffraction testing is one of the reliable ultrasonic testing and evaluation method, followed globally. In this paper, TOFD testing based automatic weld classification is proposed. Artificial neural Network based algorithm is proposed and architecture, network topology of the feed forward network, Cascade forward network, Elman recurrent network and Radial basis function network are discussed. The classification of weld defects are also analyzed, based on their performance metric, classification accuracy. It also focuses on model development, neural network paradigms, training and testing of the proposed model for the time scale feature set.

Ensemble models in forecasting financial markets

In this paper, we study an evolutionary framework for the optimization of various types of neural network structures and parameters. Three different evolutionary algorithms – the genetic algorithm (GA), differential evolution (DE) and the particle swarm optimizer (PSO) – are developed to optimize the structure and the parameters of three different types of neural network: multilayer perceptrons (MLPs), recurrent neural networks (RNNs) and radial basis function (RBF) neural networks. The motivation of this project is to present novel methodologies for the task of forecasting and trading financial indexes. More specifically, the trading and statistical performance of all models is investigated in a forecast simulation of the SPY and the QQQ exchange-traded funds (ETFs) time series over the period January 2006 to December 2015, using the last three years as out-of-sample testing. As it turns out, the RBF-PSO, RBF-DE and RBF-GA ensemble methodologies do remarkably well and outperform all of the other models.

Stream Flow Forecasting in Mahanadi River Basin using Artificial Neural Networks

Suspended sediment prediction is essential for wearing awayof soil and sedimentation at time of peakinundation period. Several kinds of neural networks have been projected in preceding papers for applications in hydrological events. This research intelligence focuses on assessment of applicability of Recurrent Neural Network (RNN) and Radial Basis Function Network (RBFN) for forecasting flow on daily basis at gauging station in Mahanadi river basin. Superlative performance is assessed on basis of RMSE, R2 which was attained by the precipitation and antecedent flow as model inputs. Based on performance value RNN gives prominent value as compare to RBFN. In case of RBFN three transfer function Tan-sig, Log-sig, purelin are utilized for evaluating model performance. While Tan-sig function used model gives extent value of R2 that is0.9614 and 0.9843 for training and testing phase respectively.

Adaptive Trajectory Tracking Control of a Cable-Driven Underwater Vehicle on a Tension Leg Platform

This paper focuses on the dynamic modeling, controller design, and simulation verification of a new cable-driven underwater vehicle model system, which is proposed for future application on a tension leg platform. Compared with conventional underwater vehicles, the proposed cable-driven underwater vehicle model system has a unique structure and subjects to not only unknown underwater disturbances but also time-varying nonlinear cable tractions. To achieve accurate and robust trajectory tracking control, a universal high-order nonlinear dynamic model is established with multisource uncertainties, and an integrated estimation-based adaptive backstepping terminal sliding mode controller is designed. The proposed controller utilizes the integrated estimation method to handle the multisource unknown uncertainties, where recurrent radial basis function neural network and disturbance observer are employed for the estimations of uncertainties, and adaptive robust methods are utilized for compensations of estimation errors. The backstepping terminal sliding mode control method is utilized to improve the tracking performance and converging rate. In addition, the issue of “explosion of complexity” occurred in a traditional backstepping design is tackled by an adaptive control method, and the input saturation problem is solved by anti-windup compensator. Based on the Lyapunov analysis, all closed-loop signals are proved to be uniformly ultimately bounded. The numerical simulations show that the developed controller is not only robust against environmental disturbances and adaptive to unknown time-varying uncertainties but also able to steer the trajectory tracking errors along the prescribed transient, thus leading to effective cable-driven underwater vehicle model system control.

Robust Adaptive Neural-Network Backstepping Control Design for High-Speed Permanent-Magnet Synchronous Motor Drives: Theory and Experiments

This paper presents a robust adaptive backstepping control (RABC) for high-speed permanent-magnet synchronous motor (HSPMSM) drive system. The proposed RABC achieves high performance operation by incorporating an ideal backstepping controller (IBC), a recurrent radial basis function neural network (RRBFNN) uncertainty observer, and a robust controller. The Lyapunov stability theorem is utilized to design the IBC as a position controller of the HSPMSM servo drive system. To enhance the disturbance rejection capability during parameter changes, certain information is needed within the backstepping control law so that the system performance would not sorely be affected. To mitigate the need for the lumped parameter uncertainties within the backstepping controller, an online adaptive observer based on RRBFNN is designed to estimate the nonlinear parameter uncertainties. Moreover, the robust controller is intended to retrieve the remaining of the RRBFNN approximation errors. To assure the stability of the proposed RABC, the Lyapunov stability analysis is used to derive the online adaptive control laws. The performance of the proposed RABC is verified by simulation and experimental analysis under different operating conditions and parameter uncertainties. The test results validate the effectiveness of the proposed RABC scheme to achieve preferable tracking performance regardless of external disturbances and parameter uncertainties.

Temporally local recurrent radial basis function network for modeling and adaptive control of nonlinear systems

In this paper, a novel temporally local recurrent radial basis function network for modeling and adaptive control of nonlinear systems is proposed. The proposed structure consists of recurrent hidden neurons having weighted self-feedback loops and a weighted linear feed-through from the input layer directly to the output layer neuron(s). The dynamic back-propagation algorithm is developed and used for updating the parameters of the proposed structure. To improve the performance of learning algorithm, discrete Lyapunov stability method is used to develop an adaptive learning rate scheme. This scheme ensures the faster convergence of the parameters and maintains the stability of the system. A total of 5 complex nonlinear systems are used to test and compare the performance of the proposed network with other neural network structures. The disturbance rejection tests are also carried out to check whether the proposed scheme is able to handle the external disturbance/noise signals effects or not. The obtained results show the efficacy of the proposed method.

An intelligent detection method for bulking sludge of wastewater treatment process

Prediction of bulking sludge is a matter of growing importance around the world. In this study, to detect bulking sludge of wastewater treatment process (WWTP), an intelligent detection method, using a self-organizing recurrent radial basis function neural network (SORRBFNN) and a cause variables identification (CVI) algorithm, was developed to detect the fault points and the fault variables of bulking sludge. For this intelligent detection method, first, the structure and parameters of SORRBFNN were updated by an information-oriented algorithm (IOA) and an improved Levenberg-Marquardt (LM) algorithm to improve the prediction accuracy of the sludge volume index (SVI) from the water qualities. Second, the CVI algorithm was designed to allow a quick revealing of the cause variables of bulking sludge with high accuracy. And the intelligent detection method was tested on the measured data from a real WWTP. Experimental results confirmed the attractiveness and effectiveness of the proposed intelligent detection method.

Forecasting ozone concentration levels using Box-Jenkins ARIMA modelling and artificial neural networks: A comparative study

An accurate forecasting of tropospheric ozone (O3) concentration is beneficial for strategic planning of air quality. In this study, various forecasting techniques are used to forecast the daily maximum O3 concentration levels at a monitoring station in the Klang Valley, Malaysia. The Box-Jenkins autoregressive integrated moving-average (ARIMA) approach and three types of neural network models, namely, back-propagation neural network, Elman recurrent neural network and radial basis function neural network are considered. The daily maximum data, spanning from 1 January 2011 to 7 August 2011, was obtained from the Department of Environment, Malaysia. The performance of the four methods in forecasting future values of ozone concentrations is evaluated based on three criteria, which are root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). The findings show that the Box-Jenkins approach outperformed the artificial neural network methods.

Nonlinear system modeling using a self-organizing recurrent radial basis function neural network

In this paper, an efficient self-organizing recurrent radial basis function neural network (RRBFNN), is developed for nonlinear system modeling. In RRBFNN, a two-steps learning approach is introduced during the learning process. In the first step, the objective is to find the optimal set of parameters using an improved Levenberg-Marquardt (LM) algorithm. In the second step, an efficient information-oriented algorithm (IOA), without any thresholds, is developed to optimize the structure of RRBFNN. The hidden neurons in this IOA-based RRBFNN (IOA-RRBFNN) are generated or pruned automatically to reduce the computational complexity and improve the generalization power. Meanwhile, a theoretical analysis on the learning convergence of IOA-RRBFNN is given in details. To demonstrate the merits of IOA-RRBFNN for modeling nonlinear systems, several benchmark problems and a real world application are present with comparisons against other existing methods. Some promising results are reported in this study, indicating that the proposed IOA-RRBFNN performs prediction accuracy in the case of fast learning speed and compact structure.

RECEIVER OPERATING CHARACTERISTICS MEASURE FOR THE RECOGNITION OF STUTTERING DYSFLUENCIES USING LINE SPECTRAL FREQUENCIES

Stuttering is a motor-speech disorder, having common features with other motor control disorders such as dystonia, Parkinson’s disease and Tourette’s syndrome. Stuttering results from complex interactions between factors such as motor, language, emotional and genetic. This study used Line Spectral Frequency (LSF) for the feature extraction, while using three classifiers for the identification purpose, Multilayer Perceptron (MLP), Recurrent Neural Network (RNN) and Radial Basis Function (RBF). The UCLASS (University College London Archive of Stuttered Speech) release 1 was used as database in this research. These recordings were from people of ages 12y11m to 19y5m, who were referred to clinics in London for assessment of their stuttering. The performance metrics used for interpreting the results are sensitivity, accuracy, precision and misclassification rate. Only M1 and M2 had below 100% sensitivity for RBF. The sensitivity of M1 was found to be between 40 & 60%, therefore categorized as moderate, while that of M2 falls between 60 & 80%, classed as substantial. Overall, RBF outperforms the two other classifiers, MLP and RNN for all the performance metrics considered.

Self-organization of a recurrent RBF neural network using an information-oriented algorithm

This paper investigates how to construct a recurrent radial basis function neural network (RRBFNN) by an information-oriented algorithm (IOA) and how to adjust the parameters by a gradient algorithm simultaneously. In this IOA-based RRBFNN (IOA-RRBFNN), the proposed IOA is used to calculate the information processing strength (IPS) of hidden neurons, such that the independent component contributions between the hidden neurons and output neurons can be extracted. Then, a novel self-organizing strategy is proposed to optimize the structure of RRBFNN based on the input IPS and output IPS of hidden neurons. Meanwhile, a gradient algorithm is developed to update the parameters of IOA-RRBFNN. The proposed IOA-RRBFNN can be used to organize the network structure and adjust the parameters to improve its performance. Finally, several examples are presented to illustrate the effectiveness of IOA-RRBFNN. The results demonstrate that the proposed IOA-RRBFNN is more competitive in solving the nonlinear system modeling problems compared with some existing methods.