Aiming at the characteristics which variable air volume air conditioning system is multi-variable, nonlinear and uncertain system, normal fuzzy neural network is hard to meet the requirements which dynamic control of multi-variable. In this paper, we put forward a recursive neural network predictive control strategy based on wavelet neural network model. Through recursive wavelet neural network...

The current paper investigates the influence of packet losses in network control systems (NCS’s) using the model predictive control (MPC) strategy. The study focuses on two main network packet losses due to sensor to controller and controller to actuator along the communication paths. A new Markov-based method is employed to recursively estimate the probability of time delay in controller to ac...

the prediction of the joint angle position, especially during tremor bursts, can be useful for detecting, tracking, and forecasting tremors. thus, this research proposes a new model for predicting the wrist joint position during rhythmic bursts and inter‑burst intervals. since a tremor is an approximately rhythmic and roughly sinusoidal movement, neural oscillators have been selected to underli...

in this paper standing balance control of a biped with toe-joint is presented. the model consists of an inverted pendulum as the upper body and the foot contains toe-joint. the biped is actuated by two torques at ankle-joint and toe-joint to regulate the upper body in upright position. to model the interaction between foot and the ground, configuration constraints are defined and utilized. to s...

background : underweight as a public health problem in young women is associated with nutritional deficiencies, menstrual irregularity, eating disorders, reduced fertility, etc. since resting metabolic rate (rmr) is a necessary compo-nent in the development of nutrition support therapy, therefore we determined the accuracy of commonly used pre-dictive equations against rmr measured by indirect ...

this article deals with the issues associated with developing a new design methodology for the nonlinear model-predictive control (mpc) of a chemical plant. a combination of multiple neural networks is selected and used to model a nonlinear multi-input multi-output (mimo) process with time delays.  an optimization procedure for a neural mpc algorithm based on this model is then developed. the p...

conclusions according to the appearance of the purple line in most of the cases and its high sensitivity and specificity, we can use it as a non-invasive complementary method for clinical assessment of labor progress. results the purple line appeared in 75.3% of women during the active phase of labor. appearance of the purple line in the prediction of labor progress had 90.2% sensitivity, 45.3%...

This article presents predictive modeling of nonlinear guided wave propagation for structural health monitoring using both finite element method and analytical approach. In our study, the nonlinearity of the guided waves is generated by interaction with a nonlinear breathing crack. Two nonlinear finite element method techniques are used to simulate the breathing crack: (a) element activation/de...

We introduce a new hybrid Genetic Programming (GP) based method for timeseries prediction in predictive control applications. Our method combines existing state-of-the-art analytical models from predictive control with a modern typed graph GP system. The main idea is to pre-structure the GP search space with existing analytical models to improve prediction accuracy. We apply our method to a dif...

In this study, the optimal control problem of nonlinear parabolic partial differential equations (PDEs) is investigated. Optimal control of nonlinear PDEs is an open problem with applications that include fluid, thermal, biological, and chemically-reacting systems. Model predictive control with a fast numerical solution method has been well established to solve the optimal control problem of no...