Advanced Materials Research Vols. 468-471

Abstract: Aiming at the current situation of wind turbine type selection in China, this paper has built a more scientific and systematic index system for comprehensive evaluation of wind turbine type selection, and also applied the Support Vector Regression machine evaluation model with parameters optimized by Genetic Algorithm. Through automatic global optimization for parameters, this model has reached an extremely high accuracy required for evaluation of type selection. Empirical analysis shows that the application of this model has a realistic popularized significance for improving the method of the wind turbine type selection and enhancing its efficiency.

Abstract: A novel blind image separation algorithm based on artificial bee colony algorithm was proposed. Negative entropy was chosen as the objective function for separation and the separation matrix was transformed using Givens rotation transform method and the number of variable need to be found reduced. Artificial bee colony algorithm was used for solving the objective function and the images could be separated successfully. Simulation results verify the validity of the method.

Abstract: Describes the working principle of hydraulic system elevator, established the power bond graph and the state equation of the energy release circuit, and the simulation results prove the feasibility of energy release circuit.

Abstract: According to the structure and working principle of hydro-viscous variable speed clutch, the energy equation of oil film between the friction discs is derived. After solving the pressure and velocity of oil film, the analytic solution of energy equation and the oil film temperature distribution is acquired. It is shown that the temperature rise of oil film is proportional to the square of angular speed difference and the forth power of friction disc radius, and is inversely proportional to the flow flux and the film thickness. The above conclusions have important significance to reasonably choose lubricant oil and the friction disc material, and ensure the normal work of hydro-viscous variable speed clutch.

Abstract: Classification and clustering of similar articles have gained a lot of importance in a time when we drown in information but are starved for knowledge. In this paper, we propose a novel index that uses termID obtained automatically to establish forward index. This method divides files by dictionary information of forward index and realizes the map between terms and files in order to establish efficient index. Later, if it were need to process information of term, it could only handle the corresponding documents.

Abstract: This paper is to present a novel design to predict the State of charge (SOC) of the batteries for the Electric Vehicles (EV) using a voltage descent model which has been built based on the analysis of adaptive fuzzy neural intelligent algorithm (AFNIA) and the charge/discharge experimental data of Electric Vehicle. In this design, an improved BP neural network has also been proposed to indicate the correlation between open circuit voltage and SOC. An experiment employed a Lateral Moving and In Situ Steering EV built by Shenzhen Polytechnic. The test and simulation results showed that the intelligent methods can accurately predict the SOC of lithium batteries. The combination of fuzzy control and neural network can achieve an effective way of predicting the SOC of batteries.

Abstract: It is difficult to build a strict mathematical model for WEDM due to the complication of the machining process and the nonlinear relation between process parameters and process targets. The neural network is suited to the modeling of complex system, because it has the functions of self-organized, self-learning and associative memory, and properties of distributed parallel type and high robustness. Therefore, this paper attempts to use the RBF neural network for the process modeling of WEDM.

Abstract: In this paper, we proposed a mathod for lumbar vertebra CT image segmentation based on the contourlet transform and artificial neural networks(ANNs). The proposed method consists of three portions. In the first part, contourlet transform is used to decompose the CT image to obtain the contourlet coefficients. In the second part, the self-organizing competitive artificial neural network is employed to optimize and extract the low frequency coefficients coefficients of contourlet transformation, reduce the number of coefficients greatly. The last part, the optimized coefficients are inverse contourlet transformed with the original coefficients,the segmented image is reconstructed. The experimental results show the accuracy of human lumbar vertebra CT image segmentation based on the proposed method is encouraged.

Abstract: This paper presents a novel pedestrian detection and recognition method based on a new photoelectric sensor layout for increasing the recognition rate and the recognition speed of the Automatic Gate Machine (AGM). First of all, a new sensors layout is designed. Next, by collecting the time and sequence of pedestrian breaking the rays of the sensors, an algorithm of combining the time sequence analysis and event analysis is developed to detect and judgment the legality of the pedestrians so that the gate of the AGM is either opened or closed. Then, the algorithm is implemented by software method and FPGA method respectively. Finally, the experiments on the prototype of AGM prove that the recognition rate and the recognition speed are increased effectively.

Abstract: The Donghe Sandstone formation (DS fm. for simplicity) presents an excellent thin condensate gas reservoir in LG34 well area, Tarim Basin. Unfortunately, drilling results show that the reservoir is thin, deeply buried (below 5000m) and mix lithologies. Pre-stack inversion and fluid identification is implemented in this area. The feasibility and validity of pre-stack inversion for this kind of reservoir is tested, since that application of pre-stack inversion in this area is for the first time. A new rock physics model is used for estimating rock velocities and elastic attributes, and cross-plots of Poisson's ratio (σ) again LambdaRho (λρ) is found to be more favorable for lithofacies identification. Then, pre-stack inversion which uses seismic data with careful amplitude processing is performed to predict the reservoir. The inversion results agree and tie with most wells, suggesting that the pre-stack inversion is viable process for this complex lithological reservoir prediction in the area.