Advanced Materials Research Vols. 785-786

Abstract: Military materials delivery is new technology of logistics, and can help the army to easily and accurately deliver the military materials to every point to be guaranteed. Military materials delivery is gradually used; the optimization problem of the delivery process had been appeared. Genetic algorithm is imitate living creature environment in of a kind of orientation overall situation of the genetic, can be professional at solving complicated system or the huge problem. Thus, the paper firstly introduced the basic theory of military materials delivery, including the definition, principle, factors to set up the model of military materials delivery; then analyzed the process of genetic algorithm, using it to optimize the military materials delivery, example was given out.

Abstract: Many vertical handoff decision algorithms have not considered the impact of call dropping during the vertical handoff decision process. Besides, most of current multi-attribute vertical handoff algorithms cannot predict users’ specific circumstances dynamically. In this paper, we formulate the vertical handoff decision problem as a Markov decision process, with the objective of maximizing the expected total reward during the handoff procedure. A reward function is formulated to assess the service quality during each connection. The G1 and entropy methods are applied in an iterative way, by which we can work out a stationary deterministic policy. Numerical results demonstrate the superiority of our proposed algorithm compared with the existing methods.

Abstract: In order to measure lysozyme biomass activity concentration accurately and in real-time in the fermentation process of marine biological enzyme preparation, soft sensing with the nonlinear state-estimation based on SUKF has been used, the method uses KF framework, embedded in SUT. In fact the fermentation bacteria is lysozyme, which is fermented in a fermenter of KRH-100L according to process requirements. The statistical properties of variables through the nonlinear transformation has been calculated and the degradation effects of aggregation of high-dimensional and nonlinear fermentation model would be effectively settled in sample. By using σ-point set with symmetric sampling strategy, the mean points increased, according to the fermentation of priori information of each dimension mean. By using cross-validation method to select model parameters, compared with the support vector machine SVM with RBFNN algorithm, the experimental results show that the smallest root mean square statistical error of training and testing in soft Sensing with SUKF reduced by 2% or so.

Abstract: The article deals with determination of parameters for leakage of hazardous substances by using of computer programs ALOHA and EFFECTS PLUS. The calculated parameters are compared in a practical application for gas tanks with regard to limitation of these programs. There are compared the possibilities of using of this programs, particularly for determining the parameters of a very small leak to determine exactly areas with the potentially explosive atmospheres. In conclusion of the study are summarized the possibilities of using and the proposals of computer programs in case of leakage of propane from the tank.

Abstract: In this paper, we provide a partition of the roots of a class of transcendental equation by using τ-D decomposition ,where τ>0,a>0,b<0 and the coefficient b is fixed.According to the partition, one can determine the stability domain of the equilibrium and get a Hopf bifurcation diagram that can provide the Hopf bifurcation curves in the-parameter space, for one dimension delay differential equation .

Abstract: In mineral resources prediction and other research of geological variables, stability exactness of quantitative models concern modeling conditions, geological variables from model and the status of the variable. In traditional geological modeling process, variable support is measured under some contrains weight and this kind of weight is characterized by constant coefficients. Constant weight^[1] has some limitations due to structuredness and dependency of variable. For overcoming the inflexibility of constant weight, this paper proposes geological variable mathematics model basedd state variable vector. We revise existing form of state variable weight and provide logarithm state variable vector as measurement level of geological variable weight coefficients. According to 1:200000 scale geochemistry measured data from Baishan area, we calculate the samples unit connection degree based on exponent and logarithm state variable vector and compare the connection degree based on constant weight. The connection degree sorting has the similarity as a whole among them, but there is the obvious difference locally. We can conclude that geological variable weight function based on state variable vector is more flexible and fine.

Abstract: In this paper, a nonlinear system identification framework using parallel linear-plus-neural networks model is developed. The framework is established by combining a linear Laguerre filter model and a nonlinear neural networks (NN) model in a parallel structure. The main advantage of the proposed parallel model is that by having a linear model as the backbone of the overall structure, reasonable models will always be obtained. In addition, such structure provides great potential for further study on extrapolation benefits and control. Similar performance of proposed method with other conventional nonlinear models has been observed and reported, indicating the effectiveness of the proposed model in identifying nonlinear systems.

Abstract: To recognize small diver target from the dim special diver sonar images accurately, the Support Vector Machine method is used as classifier. According to the main characteristics of diver, five feature parameters, including Average-scale, Velocity, Shape, Direction, Included angle, are chosen as the input of characteristics vectors to train the net. And then the testing images are classified and identified. The experimental results show that accuracy rate of recognition reaches 94.5% for as many as 200 testing images. The experiment indicates that small object recognition from complex sonar images based on the right selection of feature parameters is of good performance by using the SVM method as well as good engineering foreground.

Abstract: Sensitivity analysis method can evaluate the importance of model input attributes. A multivariable sensitivity analysis method based on neural network connection weights and a calculation method of attributes correlation are proposed in this paper, and are applied to the research of attributes correlation. To verify the effectiveness of the proposed methods, this study employed a man-made example and a UCI-IRIS dataset to test the performance of the method. The results show that the sensitivity analysis method can really identify important and strong correlation attributes of model, and can simplify the model effectively, and can improve the accuracy of the model.

Abstract: The objective of this thesis is to make a position play for a billiard robot in a nine ball pool game by the Grey System Theory. The position play is the placement of the cue ball on the best position to the next planned shot. The robot is able to decide a shooting mode with a corresponding shooting strength from the developed data base of rebound paths of the cue ball. The rebound paths are calculated and recorded from four shooting modes (free shot, cushion shot, bank shot, kiss shot) with five different shooting strengths by the collision theory in a PC. The continuous position play is called the clean-table in the pool game. The moving path of object ball and cue ball are calculated by the collision theory. The grey decision making is developed to find out the best position of cue ball after shooting for the position play. The decision factors are the block ball, the shooting angle, the distance between the object ball and the pocket, and the distance between the object ball and the cue ball. The first priority of the position play is to choose the corresponding object ball and the rebound path of cue ball without any block ball. Then, the second priority is to choose the higher successful pocketing rate (large than 60%). Finally, the offensive decision is set up to make a position play by the Grey Decision-making Sub-system. The experimental results show this clean-table offensive system works very well in the pool game.