Search results

The purpose of this paper is to improve the flexibility and tracking errors of the controllers-based neural networks (NNs) for mobile manipulator robot (MMR) in the presence of time-varying uncertainties.

The conventional backstepping force/motion control is developed by the wavelet fuzzy CMAC neural networks (WFCNNs) (for mobile-manipulator robot). The proposed WFCNNs are applied in the tracking-position-backstepping controller to deal with the uncertain dynamics of the controlled system. In addition, an adaptive robust compensator is proposed to eliminate the inevitable approximation errors, uncertain disturbances, and relax the requirement for prior knowledge of the controlled system. Besides, the position tracking controller, an adaptive robust constraint-force is also considered. The online-learning algorithms of the control parameters (WFCNNs, robust term and constraint-force controller) are obtained by using the Lyapunov stability theorem.

The design of the proposed method is determined by the Lyapunov theorem such that the stability and robustness of the control-system are guaranteed.

The WFCNNs are more the generalized networks that can overcome the constant out-weight problem of the conventional fuzzy cerebellar model articulation controller (FCMAC), or can converge faster, give smaller approximation errors and size of networks in comparison with FNNs/NNs. In addition, an intelligent-control system by inheriting the advantage of the conventional backstepping-control-system is proposed to achieve the high-position tracking for the MMR control system in the presence of uncertainties variation.

The purpose of this paper is to solve the tracking problem for free-floating space manipulators (FFSMs) in task space with parameter uncertainties and external disturbance.

In this paper, the novel cerebellar model articulation controller (CMAC) is designed with the feedback controller. More precisely, the parameter uncertainties in the FFSM are considered for achieving the robustness.

By using the dynamically equivalent model, the CMAC can be designed and trained with the desired performance, such that the prescribed trajectory can be followed accordingly. The simulation results are presented for illustrating the validity of the derived results.

Based on the designed CMAC, the tracking error would be approaching zero by choosing appropriate quantization level in CMAC and the corresponding learning rules can be tuned online.

This study constructs time series model, artificial neural networks (ANNs) and statistical topologies to examine the volatility and forecast foreign exchange rates. The Mauritian forex market has been utilized as a case study, and daily data for nominal spot rate (during a time period of five years spanning from 2014 to 2018) for EUR/MUR, GBP/MUR, CAD/MUR and AUD/MUR have been applied for the predictions.

Autoregressive integrated moving average (ARIMA) and generalized autoregressive conditional heteroskedasticity (GARCH) models are used as a basis for time series modelling for the analysis, along with the non-linear autoregressive network with exogenous inputs (NARX) neural network backpropagation algorithm utilizing different training functions, namely, Levenberg–Marquardt (LM), Bayesian regularization and scaled conjugate gradient (SCG) algorithms. The study also features a hybrid kernel principal component analysis (KPCA) using the support vector regression (SVR) algorithm as an additional statistical tool to conduct financial market forecasting modelling. Mean squared error (MSE) and root mean square error (RMSE) are employed as indicators for the performance of the models.

The results demonstrated that the GARCH model performed better in terms of volatility clustering and prediction compared to the ARIMA model. On the other hand, the NARX model indicated that LM and Bayesian regularization training algorithms are the most appropriate method of forecasting the different currency exchange rates as the MSE and RMSE seemed to be the lowest error compared to the other training functions. Meanwhile, the results reported that NARX and KPCA–SVR topologies outperformed the linear time series models due to the theory based on the structural risk minimization principle. Finally, the comparison between the NARX model and KPCA–SVR illustrated that the NARX model outperformed the statistical prediction model. Overall, the study deduced that the NARX topology achieves better prediction performance results compared to time series and statistical parameters.

The foreign exchange market is considered to be instable owing to uncertainties in the economic environment of any country and thus, accurate forecasting of foreign exchange rates is crucial for any foreign exchange activity. The study has an important economic implication as it will help researchers, investors, traders, speculators and financial analysts, users of financial news in banking and financial institutions, money changers, non-banking financial companies and stock exchange institutions in Mauritius to take investment decisions in terms of international portfolios. Moreover, currency rates instability might raise transaction costs and diminish the returns in terms of international trade. Exchange rate volatility raises the need to implement a highly organized risk management measures so as to disclose future trend and movement of the foreign currencies which could act as an essential guidance for foreign exchange participants. By this way, they will be more alert before conducting any forex transactions including hedging, asset pricing or any speculation activity, take corrective actions, thus preventing them from making any potential losses in the future and gain more profit.

This is one of the first studies applying artificial intelligence (AI) while making use of time series modelling, the NARX neural network backpropagation algorithm and hybrid KPCA–SVR to predict forex using multiple currencies in the foreign exchange market in Mauritius.

The purpose of this paper is to implement the hardware structure for radial basis function (RBF) neural network based on stochastic logic computation.

The hardware implementation of artificial neural networks (ANNs) has a complicated structure and is normally space consuming due to huge size of digital multiplication, addition/subtraction, non‐linear activation function, etc. Also the unavailability of ANN hardware at an attractive price limits its use for real time applications. In stochastic logic theory, the real numbers are converted to random streams of bits instead of a binary number. The performance of the proposed structure is analyzed using very high speed integrated circuit hardware description language.

Stochastic theory‐based arithmetic and logic approach provides a way to carry out complex computation with very simple hardware and very flexible design of the system. The Gaussian RBF for hidden layer neuron is employed using stochastic counter that reduces the hardware resources significantly. The number of hidden layer neurons in RBF neural network structure is adaptively varied to make it an intelligent system.

The paper outlines the stochastic neural computation on digital hardware for implementing radial basis neural network. The structure has considered the optimized usage of hardware resources.

The purpose of this paper is to develop a new inverse controller for servo‐system position tracking control based on neural network (NN) and model reference adaptive control (MRAC).

First, the model of general servo‐systems is analyzed. Then, a MRAC based on neural network control (NNC) is proposed with mathematical prove of stability. In addition, several simulation cases and experiments are listed to verify the usability of the control scheme.

This scheme consists of an MRAC, an online NN controller and a robust controller in velocity‐loop. For reducing influence which arose from modeling error, unknown model dynamics, parameter variation, and load changes, the NN controller is introduced to counteract the various influence mentioned above dynamically. MRAC, NNC, and robust controller adjust system to track the approximate velocity‐loop reference model. In this way, the position‐loop is not sensitive to the disturbance on velocity‐loop, and the whole velocity‐loop can be treated as a simple linear model when designing the other parts of the system. In addition, a novel inverse control method based on linear velocity signal filter is introduced to this scheme. In this case, the MRAC, NNC, and robust controller perform as an adaptive inverse controller, which keeps the velocity signal tracking the position loop controller output.

The paper presents a new inverse controller with NNC and MRAC which is practical and flexible.

The purpose of this paper is to effectively deal with querying of classification with membership.

The authors propose a scheme comprising a layer of Bloom filter for membership checking and a second layer based on neural network for dealing with the classification requirement.

Not only could false positives be dramatically decreased, but also classification could be achieved with the proposed scheme.

The experimental data were randomly generated instead of real‐world ones.

It is difficult to implement this scheme in a real‐world environment, such as the internet. Second, the neural network requires time to converge to a satisfactory level.

Internet ethic might be compromised by hackers once they find a way around the filtering mechanism.

The neural network was moditified and utilized for the first time to be suitable for our purpose. Second, the two‐layer design shows effectiveness.

Passivity theory is closely related to both electrical network and circuit analysis methods. The purpose of this paper is to try to establish some basic results on the uncertain discrete‐time fuzzy systems.

Applying the classical and effective Lyapunov function method and the powerful linear matrix inequality toolbox in MATLAB, the paper provides some sufficient conditions to verify the passivity of the uncertain discrete‐time fuzzy systems, or to passify such a system.

For uncertain discrete‐time fuzzy systems, its passivity can be easily verified numerically, and its passification can also be fulfilled.

A very effective and convenient criterion is provided to test the passivity of practical nonlinear discrete‐time system or to passify it.

This paper first treats this topic on uncertain discrete‐time fuzzy systems and obtains some important results.

This paper aims to experimentally evaluate the performance of a parallel hybrid propulsion system for use in small unmanned aerial vehicles (UAVs).

The objective is to combine all the individual components of the hybrid electric propulsion system (HEPS) into a modular test bench to characterize the performance of a parallel hybrid propulsion system, and to evaluate a rule-based controller based on the ideal operating line concept for the control of the power plant. Electric motor (EM) designed to supplement the power of the internal combustion engine (ICE) to reduce the overall fuel consumption, with the supervisory controller optimizing ICE torque.

The EM was able to supplement the power of the ICE to reduce fuel consumption, and proved the capability of acting as a generator to recharge the batteries drawing from ICE power. Furthermore, the controller showed that it is possible to reduce the fuel consumption with a HEPS when compared to its gasoline counterpart by running simulated representative UAV missions. The findings also highlighted the challenges to build and integrate the HEPS in small UAVs.

The modularity of the test bench allows each component to be changed to assess its impact on the performance of the system. This allows for further exploration and improvements of the HEPS in a controlled environment.

Notes that there are many areas where fine positioning of a robotic device carrying a specialized end‐effector is required. Describes a mechatronic wrist unit with fine motion capabilities for such applications. The wrist unit was designed as a four‐axis system with three revolute and one prismatic. The implementation is carried out in two stages. In the first stage, one prismatic axis and one revolute axis are implemented. Focuses attention on the underlying techniques for the development of this wrist unit given the requirements for weight and accuracy. Also describes the actuation mechanism and control strategies for the mechatronic wrist unit. Also presents the results of the experiments carried out for performance analysis.