Neural-networks-based Modelling and a Fuzzy Neural Networks Controller of MCFC

Molten Carbonate Fuel Cells (MCFC) are produced with a highly efficient and clean power generation technology which will soon be widely utilized. The temperature characters of MCFC stack are briefly analyzed. A radial basis function (RBF) neural networks identification technology is applied to set up the temperature nonlinear model of MCFC stack, and the identification structure, algorithm and modeling training process are given in detail. A fuzzy controller of MCFC stack is designed. In order to improve its online control ability, a neural network trained by the I/O data of a fuzzy controller is designed. The neural networks can memorize and expand the inference rules of the fuzzy controller and substitute for the fuzzy controller to control MCFC stack online. A detailed design of the controller is given. The validity of MCFC stack modelling based on neural networks and the superior performance of the fuzzy neural networks controller are proved by Simulations.

Identification of nonlinear process described by neural fuzzy Hammerstein-Wiener model using multi-signal processing

In this study,a novel approach for nonlinear process identification via neural fuzzy-based Hammerstein-Wiener model with process disturbance by means of multi-signal processing is presented.The Hammerstein-Wiener model consists of three blocks where a dynamic linear block is sandwiched between two static nonlinear blocks.Multi-signal sources are designed for achieving identification separation of the Hammerstein-Wiener process.The correlation analysis theory is utilized for estimating unknown parameters of output nonlinearity and linear block using separable signals,thus the interference of process disturbance is solved.Furthermore,the immeasurable intermediate variable and immeasurable noise term in identification model is taken over by auxiliary model output and estimate residuals,and then auxiliary model-based recursive extended least squares parameter estimation algorithm is derived to calculate parameters of the input nonlinearity and noise model.Finally,convergence analysis of the suggested identification scheme is derived using stochastic process theory.The simulation results indicate that proposed identification approach yields high identification accuracy and has good robustness.

Adaptive-backstepping force/motion control for mobile-manipulator robot based on fuzzy CMAC neural networks

In this paper, an adaptive backstepping fuzzy cerebellar-model-articulation-control neural-networks control （ABFCNC） system for motion/force control of the mobile-manipulator robot （MMR） is proposed. By applying the ABFCNC in the tracking-position controller, the unknown dynamics and parameter variation problems of the MMR control system are relaxed. In addition, an adaptive robust compensator is proposed to eliminate uncertainties that consist of approximation errors, uncertain disturbances. Based on the tracking position-ABFCNC design, an adaptive robust control strategy is also developed for the nonholonomicconstraint force of the MMR. The design of adaptive-online learning algorithms is obtained by using the Lyapunov stability theorem. Therefore, the proposed method proves that it not only can guarantee the stability and robustness but also the tracking performances of the MMR control system. The effectiveness and robustness of the proposed control system are verified by comparative simulation results.

Fuzzy adaptive tracking control within the full envelope for an unmanned aerial vehicle

Motivated by the autopilot of an unmanned aerial vehicle（UAV） with a wide flight envelope span experiencing large parametric variations in the presence of uncertainties, a fuzzy adaptive tracking controller（FATC） is proposed. The controller consists of a fuzzy baseline controller and an adaptive increment, and the main highlight is that the fuzzy baseline controller and adaptation laws are both based on the fuzzy multiple Lyapunov function approach, which helps to reduce the conservatism for the large envelope and guarantees satisfactory tracking performances with strong robustness simultaneously within the whole envelope. The constraint condition of the fuzzy baseline controller is provided in the form of linear matrix inequality（LMI）, and it specifies the satisfactory tracking performances in the absence of uncertainties. The adaptive increment ensures the uniformly ultimately bounded（UUB） predication errors to recover satisfactory responses in the presence of uncertainties. Simulation results show that the proposed controller helps to achieve high-accuracy tracking of airspeed and altitude desirable commands with strong robustness to uncertainties throughout the entire flight envelope.

Identification of fractional order Hammerstein models based on mixed signals

An algorithm based on mixed signals is proposed,to solve the issues of low accuracy of identification algorithm,immeasurable intermediate variables of fractional order Hammerstein model,and how to determine the magnitude of fractional order.In this paper,a special mixed input signal is designed to separate the nonlinear and linear parts of the fractional order Hammerstein model so that each part can be identified independently.The nonlinear part is fitted by the neural fuzzy network model,which avoids the limitation of polynomial fitting and broadens the application range of nonlinear models.In addition,the multi-innovation Levenberg-Marquardt(MILM)algorithm and auxiliary recursive least square algorithm are innovatively integrated into the parameter identification algorithm of the fractional order Hammerstein model to obtain more accurate identification results.A simulation example is given to verify the accuracy and effectiveness of the proposed method.

Novel intelligent reasoning system for tool wear prediction and parameter optimization in intelligent milling

Accurate intelligent reasoning systems are vital for intelligent manufacturing.In this study,a new intelligent reasoning system was developed for milling processes to accurately predict tool wear and dynamically optimize machining parameters.The developed system consists of a self-learning algorithm with an improved particle swarm optimization(IPSO)learning algorithm,prediction model determined by an improved case-based reasoning(ICBR)method,and optimization model containing an improved adaptive neural fuzzy inference system(IANFIS)and IPSO.Experimental results showed that the IPSO algorithm exhibited the best global convergence performance.The ICBR method was observed to have a better performance in predicting tool wear than standard CBR methods.The IANFIS model,in combination with IPSO,enabled the optimization of multiple objectives,thus generating optimal milling parameters.This paper offers a practical approach to developing accurate intelligent reasoning systems for sustainable and intelligent manufacturing.