Haipeng Pan

Comprehensive optimization of batch process based on particle swarm optimization algorithm

Based on Iterative Particle Swarm Optimization (PSO) Algorithm, comprehensive optimization problem of batch process is discussed in this paper. Batch process optimization problems in general to product concentration as optimization goal, if optimization object is changed to the sum of the product concentration, the reciprocal of reaction time and the reciprocal of energy loss and then optimization method will be more complex. Based on the iterative particle swarm optimization algorithm, optimal solution is obtained by searching for optimal trajectory. Results of study are applied to classical chemical reaction cases. Simulation results show that this algorithm is better than single objective algorithm in speed of optimization and efficient use of energy.

Image quality assessment based on the correlativity and the discrete wavelet transform

A novel image quality assessment is proposed based on the characteristics of wavelet coefficients of images and the correlativity in this paper. Firstly, the reference image and the distorted images are decomposed into several levels by means of the wavelet transform respectively. Secondly, the approximation and detail coefficients of the reference image are as the reference sequences and the approximation and detail coefficients of the distorted images are as the comparative sequences respectively. And the correlativity values are calculated between the reference sequences and the comparative sequences respectively. Moreover, the image quality assessment matrix of every distorted image can be constructed based on the correlativity values and the image quality can be assessed. The algorithm makes full use of perfect integral comparison mechanism of the correlativity and the well matching of discrete wavelet transform with multi-channel model of human visual system. The experimental results show that the proposed algorithm can not only evaluate the integral and detail quality of image fidelity accurately but also bears more consistency with the human visual system than the traditional method PSNR.

Variable Weighted Combination Forecasting Model Based on Genetic Algorithm and Artificial Neural Network

In this paper, the variable weight combination forecasting approach which both uses genetic algorithm with global searching ability and uses neural network with nonlinear mapping ability is put forward. First, the weight coefficients are gained by means of adaptive genetic algorithm. Second, the neural network is trained by weight -obtained and the intending weighted values are predicted further. The method has character that whole weighted values is positive and the summation of weight values at same time equals to 1. At last, the variable weight combination forecasting model is built and applied into forecasting total consumption expenditure in Shanghai GDP . Simulation shows the effectiveness of the proposed approach.

GM(1,1) Model - Ameliorated Based on Genetic Algorithm and Its Application

In this paper, first, the method of enhancing smooth degree of original data sequence by function transformation is studied and some transformation functions are presented. Second, original data sequence is transformed by means of function transformation. Third, the mechanism of GM(1,1)-ameliorated model based on adaptive genetic algorithm (AGA) is proposed and the steps of modeling is explained in detail . At last, the method is applied in building the model of Chinese country per-capita housing areas. The results of example show the effectiveness of the proposed approach.

Sliding mode control for nonlinear system with hysteresis based on RBFNN approximation

Piezoelectric actuators (PEAs) are wildly used in high-precision nanopositioning systems. however, the inherent hysteresis nonlinearity seriously degrades the tracking performance. Bouc-Wen model is employed to describe the hysteresis in this paper. The radial basis function neural network(RBFNN) is adopted for the online approximation of disturbance-like term separated from Bouc-Wen model, which transforms the time-varying term into the learning of RBFNN weight matrix. An adaptive multiple-surface sliding mode controller is developed by Lyapunov function, and the tracking error can be converged into the preselected boundary layer. The simulation results validate the effectiveness of the proposed control approach.

A kind of wall-climbing robot based on wireless communication among multi-processors

In this paper, a kind of wall-climbing robot based on wireless communication among multi-processors is introduced. Base on multi-processors controlled system, mechanical structure, electronic hardware construction and software designing are proposed respectively. Positioning and path planning are illustrated in detail. Furthermore, communicate protocol is proposed for data exchange through wireless transformation. The robot achieves high precise and excellent performance which could be applied in many fields such as shipbuilding and ship recycling.

Distillation decoupling control system based on self-tuning fuzzy immune PI algorithm

Energy consumption in the process of distillation in industrial production accounts for about 30% of the total industrial consumption. So the improvement of distillation control method has important practical significance. Distillation control system is a kind of typical coupling system. In this paper, a parameter self-tuning fuzzy immune PI method for multi-variable coupling systems is presented based on the analysis of influences of immune mechanism, fuzzy control and PI method on controlled systems. Fuzzy immune PI controllers were designed according to the coupling system construction, and parameter values of the controller were adjusted online. Independent fuzzy controllers are devised to identify control input u, which achieves good results of dynamic performance. Furthermore, controllers are designed independently, which makes the controllers design job easier. Then, the proposed structure is used in the simulation of industrial plants. Results of simulation show that the proposed method has better controlling effects and superior performance.

Notice of Retraction A new Variable Arguments PID controller based on improved Immune Algorithm

Aiming at engineering application, parameter selection in conventional PID control of a typical nonlinear plant with time-varying large delay in the complex production technology is a difficult optimization problem, and the Genetic Algorithm(GA) tends to fall into local optimum, the paper put forward a new optimal control strategy of Variable Arguments PID controller. In order to overcome the shortage of the traditional Immune Algorithm and Genetic Algorithm, get a better performance for the variable arguments PID control, this paper, aims to improve several special formulas, such as antibody fitness, expected reproduction probability and selected probability, presents an improved Artificial Immune Algorithm with the elitism reservation and elitism crossover strategy(AIAE). Both computer simulation and field application in nonlinear system with large time delay show that, the variable arguments PID controller based on AIAE has a quite good disturbance resistance and a strong robustness.