Nonlinear state estimation is a useful approach to the monitoring of industrial (polymerization) processes. This paper investigates how this approach can be followed to the development of a soft sensor of the product quality (melt index). The bottleneck of the successful application of advanced state estimation algorithms is the identification of models that can accurately describe the process....

An approach of iterative predictive learning control (IPLC) is studied with consideration to both precise train trajectory tracking and energy efficient operation. Through designing the predictive cost function, the IPLC approach for input-affine nonlinear systems is formulated and solved in this paper. Its application to train operation is detailed to compromise between punctuality and energy ...

in this research, using the modified compression field theory (mcft), a new truss based model is proposed to predict the behavior of reinforced concrete coupling beams with diagonal reinforcement. the model is able to consider the effects of shear and axial forces and bending moment, simultaneously. the proposed model includes a nonlinear shear spring, an axial spring, two inclined truss member...

 Fuzzy Cognitive Maps (FCM) is a technique to represent models of causal inference networks. Data driven FCM learning approach is a good way to model FCM. We present a hybrid FCM learning method that combines Nonlinear Hebbian Learning (NHL) and Extended Great Deluge Algorithm (EGDA), which has the efficiency of NHL and global optimization ability of EGDA. We propose using NHL to train FCM at ...

Hierarchical fuzzy neural networks can use less rules to model nonlinear system with high accuracy. But the normal training method for hierarchical fuzzy neural networks is very complex. In this paper we modify the backpropagation approach and employ a time-varying learning nte that is determined from input-output data and model stnicture. Stable learning algorithms for the premise and the cons...

This paper presents a novel dynamic neural network (DNN) predictive control strategy based on modified particle swarm optimization (PSO) for long time delay nonlinear process. The proposed dynamic NN structure could approximate to the actual system model and obtain the pure delay time exactly. An improved version of the original PSO is put forward to train the parameters of NN to enhance the co...

The purpose of this paper is to studying nonlinear k-ε turbulence models and its advantages in internal combustion engines, since the standard k-ε model is incapable of representing the anisotropy of turbulence intensities and fails to express the Reynolds stresses adequately in rotating flows. Therefore, this model is not only incapable of expressing the anisotropy of turbulence in an engine c...

This paper uses the linear quadratic Gaussian with loop transfer recovery (LQG/LTR) control system design method to obtain a level control system for a low-pressure feedwater heater train. The control system performance and stability robustness are evaluated for a given set of system design specifications. The tools for analysis are the return ratio, return difference, and inverse return differ...