Search results
1 – 10 of 495Junfei Qiao, Gaitang Han, Honggui Han and Wei Chai
The purpose of this paper is to present an on-line modeling and controlling scheme based on the dynamic recurrent neural network for wastewater treatment system.
Abstract
Purpose
The purpose of this paper is to present an on-line modeling and controlling scheme based on the dynamic recurrent neural network for wastewater treatment system.
Design/methodology/approach
A control strategy based on rule adaptive recurrent neural network (RARFNN) is proposed in this paper to control the dissolved oxygen (DO) concentration and nitrate nitrogen (SNo) concentration. The structure of the RARFNN is self-organized by a rule adaptive algorithm, and the rule adaptive algorithm considers the overall information processing ability of neural network. Furthermore, a stability analysis method is given to prove the convergence of the proposed RARFNN.
Findings
By application in the control problem of wastewater treatment process (WWTP), results show that the proposed control method achieves better performance compared to other methods.
Originality/value
The proposed on-line modeling and controlling method uses the RARFNN to model and control the dynamic WWTP. The RARFNN can adjust its structure and parameters according to the changes of biochemical reactions and pollutant concentrations. And, the rule adaptive mechanism considers the overall information processing ability judgment of the neural network, which can ensure that the neural network contains the information of the biochemical reactions.
Details
Keywords
The purpose of this paper is to present a novel intelligent backstepping sliding mode control for an experimental permanent magnet synchronous motor.
Abstract
Purpose
The purpose of this paper is to present a novel intelligent backstepping sliding mode control for an experimental permanent magnet synchronous motor.
Design/methodology/approach
A 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.
Findings
Experimental results indicate the appropriate performance of the proposed method.
Originality/value
This 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.
Details
Keywords
The purpose of this paper is to develop a methodology for the stochastically asymptotic stability of fuzzy Markovian jumping neural networks with time-varying delay and…
Abstract
Purpose
The purpose of this paper is to develop a methodology for the stochastically asymptotic stability of fuzzy Markovian jumping neural networks with time-varying delay and continuously distributed delay in mean square.
Design/methodology/approach
The authors perform Briat Lemma, multiple integral approach and linear convex combination technique to investigate a class of fuzzy Markovian jumping neural networks with time-varying delay and continuously distributed delay. New sufficient criterion is established by linear matrix inequalities conditions.
Findings
It turns out that the obtained methods are easy to be verified and result in less conservative conditions than the existing literature. Two examples show the effectiveness of the proposed results.
Originality/value
The novelty of the proposed approach lies in establishing a new Wirtinger-based integral inequality and the use of the Lyapunov functional method, Briat Lemma, multiple integral approach and linear convex combination technique for stochastically asymptotic stability of fuzzy Markovian jumping neural networks with time-varying delay and continuously distributed delay in mean square.
Details
Keywords
Fouad Allouani, Djamel Boukhetala, Fares Boudjema and Gao Xiao-Zhi
The two main purposes of this paper are: first, the development of a new optimization algorithm called GHSACO by incorporating the global-best harmony search (GHS) which is a…
Abstract
Purpose
The two main purposes of this paper are: first, the development of a new optimization algorithm called GHSACO by incorporating the global-best harmony search (GHS) which is a stochastic optimization algorithm recently developed, with the ant colony optimization (ACO) algorithm. Second, design of a new indirect adaptive recurrent fuzzy-neural controller (IARFNNC) for uncertain nonlinear systems using the developed optimization method (GHSACO) and the concept of the supervisory controller.
Design/methodology/approach
The novel optimization method introduces a novel improvization process, which is different from that of the GHS in the following aspects: a modified harmony memory representation and conception. The use of a global random switching mechanism to monitor the choice between the ACO and GHS. An additional memory consideration selection rule using the ACO random proportional transition rule with a pheromone trail update mechanism. The developed optimization method is applied for parametric optimization of all recurrent fuzzy neural networks adaptive controller parameters. In addition, in order to guarantee that the system states are confined to the safe region, a supervisory controller is incorporated into the IARFNNC global structure.
Findings
First, to analyze the performance of GHSACO method and shows its effectiveness, some benchmark functions with different dimensions are used. Simulation results demonstrate that it can find significantly better solutions when compared with the Harmony Search (HS), GHS, improved HS (IHS) and conventional ACO algorithm. In addition, simulation results obtained using an example of nonlinear system shows clearly the feasibility and the applicability of the proposed control method and the superiority of the GHSACO method compared to the HS, its variants, particle swarm optimization, and genetic algorithms applied to the same problem.
Originality/value
The proposed new GHS algorithm is more efficient than the original HS method and its most known variants IHS and GHS. The proposed control method is applicable to any uncertain nonlinear system belongs in the class of systems treated in this paper.
Details
Keywords
Chih-Ming Hong, Cong-Hui Huang and Fu-Sheng Cheng
This paper aims to present the analysis, design and implementation of functional link-based recurrent fuzzy neural network (FLRFNN) for the control of variable-speed switched…
Abstract
Purpose
This paper aims to present the analysis, design and implementation of functional link-based recurrent fuzzy neural network (FLRFNN) for the control of variable-speed switched reluctance generator (SRG).
Design/methodology/approach
The node connecting weights of the FLRFNN are trained online by back-propagation (BP) algorithms. The proposed estimator requires less processing time than traditional methods and can be fully implemented using a low-cost digital signal processor (DSP) with MATLAB toolboxes. The DSP-based hybrid sensor presented in this paper can be applied to a wind energy-conversion system where the SRG is used as a variable-speed generator. The current transducer is used to monitor the energized current and proximity sensors for rotor salient.
Findings
The authors have found that optimal based on FLRFNN with Grey controller can resolve the regulation of the system with uncertainty model and unknown disturbances. This technique can maintain the system stability and reach the desired performance even with parameter uncertainties.
Originality/value
This design will improve the performance of SRG to operate more smoothly. This application is currently being studied because the SRG has well-known advantages such as robustness, low manufacturing cost and good size-to-power ratio. Performance of the proposed controller can offer better stability characteristics. Finally, the SRG has a very good efficiency in the whole operating range.
Details
Keywords
Lydie Myriam Marcelle Amelot, Ushad Subadar Agathee and Yuvraj Sunecher
This study constructs time series model, artificial neural networks (ANNs) and statistical topologies to examine the volatility and forecast foreign exchange rates. The Mauritian…
Abstract
Purpose
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.
Design/methodology/approach
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.
Findings
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.
Research limitations/implications
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.
Originality/value
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.
Details
Keywords
Ho Pham Huy Anh and Nguyen Tien Dat
The proposed Sliding Mode Control-Global Regressive Neural Network (SMC-GRNN) algorithm is an integration of Global Regressive Neural Network (GRNN) and Sliding Mode Control…
Abstract
Purpose
The proposed Sliding Mode Control-Global Regressive Neural Network (SMC-GRNN) algorithm is an integration of Global Regressive Neural Network (GRNN) and Sliding Mode Control (SMC). Through this integration, a novel structure of GRNN is designed to enable online and. This structure is then combined with SMC to develop a stable adaptive controller for a class of nonlinear multivariable uncertain dynamic systems.
Design/methodology/approach
In this study, a new hybrid (SMC-GRNN) control method is innovatively developed.
Findings
A novel structure of GRNN is designed that can be learned online and then be integrated with the SMC to develop a stable adaptive controller for a class of nonlinear uncertain systems. Furthermore, Lyapunov stability theory is utilized to ensure the hidden-output weighting values of SMC-GRNN adaptively updated in order to guarantee the stability of the closed-loop dynamic system. Eventually, two different numerical benchmark tests are employed to demonstrate the performance of the proposed controller.
Originality/value
A novel structure of GRNN is originally designed that can be learned online and then be integrated with the sliding mode SMC control to develop a stable adaptive controller for a class of nonlinear uncertain systems. Moreover, Lyapunov stability theory is innovatively utilized to ensure the hidden-output weighting values of SMC-GRNN adaptively updated in order to guarantee the stability of the closed-loop dynamic system.
Details
Keywords
Xianzhi Jiang, Zenghuai Wang, Chao Zhang and Liangliang Yang
– The main purpose of this paper is to enhance the control performance of the robotic arm by the controller of fuzzy neural network (FNN).
Abstract
Purpose
The main purpose of this paper is to enhance the control performance of the robotic arm by the controller of fuzzy neural network (FNN).
Design/methodology/approach
The robot system has characters of high order, time delay, time variation and serious nonlinearity. The classical PID controller cannot achieve satisfactory performance in control of such a complex system. This paper combined the fuzzy control with neural networks and established the FNN controller and applied it in control of the robot.
Findings
The experimental results showed that the FNN controller had excellent performances in position control of the rehabilitation robotic arm such as fast response, small overshoot and small vibration.
Research limitations/implications
This work is focused on the static FNN algorithm by updating the second and fifth layers of the membership functions. The performance can be improved further if the third layer (reasoning layer) can be updated online.
Originality/value
Based on a hierarchical structure of the FNN controller, this paper designed the FNN controller and applied it in control of the rehabilitation robot driven by pneumatic muscles.
Details
Keywords
Chun‐Fei Hsu, Chien‐Jung Chiu and Jang‐Zern Tsai
The proportional‐integral‐derivative (PID) controller has been a practical application in industry due to its simple architecture, being easily designed and its parameter tuning…
Abstract
Purpose
The proportional‐integral‐derivative (PID) controller has been a practical application in industry due to its simple architecture, being easily designed and its parameter tuning without complicated computation. However, the traditional PID controller usually needs some manual retuning before being used for practical application in industry. The purpose of this paper is to propose an auto‐tuning PID controller (ATPIDC) which can automatically tune the controller parameters based on the gradient descent method and the Lyapunov stability theorem. Finally, a field‐programmable gate array (FPGA) chip is adopted to implement the proposed ATPIDC scheme for possible low‐cost and high‐performance industrial applications, and it is applied to a DC servomotor to show its effectiveness.
Design/methodology/approach
To ensure the stability of the intelligent control system, a compensator usually should be designed. The most frequently used compensator is designed as a sliding‐mode control, which results in substantial chattering in the control effort. To tackle this problem, the proposed ATPIDC system is composed of a PID controller and a fuzzy compensator. The PID controller can automatically tune the gain factors of the controller gains based on the gradient descent method, and the fuzzy compensator is utilized to eliminate approximation error based on the Lyapunov stability theorem. The proposed fuzzy compensator not only can remove the chattering phenomena of conventional sliding‐mode control completely, but also can guarantee the stability of the closed‐loop system.
Findings
The proposed ATPIDC system is applied to a DC servomotor on a FPGA chip. The hardware implementation of the ATPIDC scheme is developed in a real‐time mode. Using the FPGA to implement, the ATPIDC system can achieve the characteristics of small size, fast execution speed and less memory. A comparison among the fuzzy sliding‐mode control, adaptive robust PID control and the proposed ATPIDC is made. Experimental results verify a better position tracking response can be achieved by the proposed ATPIDC method after control parameters training.
Originality/value
The proposed ATPIDC approach is interesting for the design of an intelligent control scheme. An on‐line parameter training methodology, using the gradient descent method and the Lyapunov stability theorem, is proposed to increase the learning capability. The experimental results verify the system stabilization, favorable tracking performance and no chattering phenomena can be achieved by using the proposed ATPIDC system. Also, the proposed ATPIDC methodology can be easily extended to other motors.
Details
Keywords
To improve the position tracking efficiency of the upper-limb rehabilitation robot for stroke hemiplegia patients, the optimization Learning rate of the membership function based…
Abstract
Purpose
To improve the position tracking efficiency of the upper-limb rehabilitation robot for stroke hemiplegia patients, the optimization Learning rate of the membership function based on the fuzzy impedance controller of the rehabilitation robot is propose.
Design/methodology/approach
First, the impaired limb’s damping and stiffness parameters for evaluating its physical recovery condition are online estimated by using weighted least squares method based on recursive algorithm. Second, the fuzzy impedance control with the rule has been designed with the optimal impedance parameters. Finally, the membership function learning rate online optimization strategy based on Takagi-Sugeno (TS) fuzzy impedance model was proposed to improve the position tracking speed of fuzzy impedance control.
Findings
This method provides a solution for improving the membership function learning rate of the fuzzy impedance controller of the upper limb rehabilitation robot. Compared with traditional TS fuzzy impedance controller in position control, the improved TS fuzzy impedance controller has reduced the overshoot stability time by 0.025 s, and the position error caused by simulating the thrust interference of the impaired limb has been reduced by 8.4%. This fact is verified by simulation and test.
Originality/value
The TS fuzzy impedance controller based on membership function online optimization learning strategy can effectively optimize control parameters and improve the position tracking speed of upper limb rehabilitation robots. This controller improves the auxiliary rehabilitation efficiency of the upper limb rehabilitation robot and ensures the stability of auxiliary rehabilitation training.
Details