Applied Mechanics and Materials Vol. 742

Abstract: Aiming at the path planning for intelligent vehicle in complex environment, local minimum problem is solved by the way of setting a virtual barrier point. And fuzzy controller is designed to make up some inherent shortcomings of artificial potential field method and safeguards the reliability of the path planning and path smoothness.

Abstract: According to the characteristics of the large equipment, electromagnetic interference, using neural network method is put forward a set of for large electronic equipment electromagnetic coupling and interference, the analysis of the expert system based on the large electronic equipment as analysis object, the common interference on the interference classification and coding, the BP neural network is constructed, using neural network, the inference mechanism of expert system for the optimization design, and test verification.

Abstract: This paper built a multi-objective optimization model and proposed an improved multi-objective particle swarm optimization algorithm called MPS²O ,which is based on Multiple Particle Swarm Co-evolutionary. The MPS²O algorithm has considerable potential for solving multi-objective optimization problems. Mathematical benchmark functions also shows that the proposed algorithm is an excellent Alternative for solving multi-objective optimization problems. Making full use of the research findings home and abroad, MPS²O has been chosen to be the coverage optimization strategy of the wireless sensor networks in Water Environment Monitoring System. Simulation results demonstrate that the MPS²O algorithm is more efficient than the PSO algorithm in solving this real-world problem.

Abstract: A two-step strategy was proposed to solve the problems that inefficiency and inaccuracy of function modules clustering for complex product. Firstly, the three principles were proposed that weldment simplification, outsourcing simplification and borrowed component reduction to preprocess and simplify complex product. Then the complex product preprocessed can be clustered into different function modules by using the advanced Immune Algorithm amalgamated with heuristic rule (R-Immunity). By comparing the efficiency, accuracy and robustness of function modules clustering among the Genetic Algorithm, the Immune Algorithm and the R-Immunity Algorithm, we consider that the R-Immunity Algorithm is more efficient and precise to solve the problems related to function modules clustering. Finally, starting with the structure properties of complex product, the clustering results were optimized for the purposes of reducing coupling between modules and satisfying configuration requirements of customer.

Abstract: The output of pressure sensor is affected by non-objection parameters in its application, its defect is the sensitivity to temperature. The method of the data fusion from the two sensors based on BP network can eliminate the side effect of temperatures and improve the accuracy and reliability for the pressure sensors. This method based on Levenberg-Marquardt algorithm of BP network has not only a simple network structure, but also a quick learning rate, showing a better prospect.

Abstract: Quality prediction is an important means of the quality management in modern spinning production. This paper proposed a yarn quality prediction model based on Genetic Algorithm and back propagation neural network to predict the yarn quality and optimize the process parameters. The main identification model parameters were optimized by using genetic algorithm, and the prediction performance of the model has been compared against that of the BP neural network model. The effectiveness and availability of the proposed model are verified with the use of actual production data.

Abstract: Stock investment is risky and beyond fixed rules to forecast precisely. In order to realize proper stocks selection from specified mathematical function model, principal component factor analysis is proposed to rebuild various stocks via its contribution rates so as to extract the principal component factors from the elimination of weak ones. According to the synthesis scoring and ranking, optimized stocks has been selected as valuable targets. Test from Genetic Algorithm to the ranking aforementioned indicates that the rationality and validity of the results.

Abstract: The method of make-to-order has gradually become the primary mode of production. It is an extremely important ability for enterprises to make production scheduling and response to the changes of customer demand agiely. Therefore, this paper mainly deals with how to evaluating order priority in the mode of make-to-order. For this question, an evaluation index system and a model of fuzzy mathematic system evaluation are established. Through empirical analysis, the model and evaluation system are found feasible and valid.

Abstract: Features of large text data mining methods method is avoided semantic analysis from the lexical, syntactic, but by means of statistical analysis and processing large text data, thus maximizing literally ignored similar semantic differences, adapt to network language characteristics. The results of our paper show that data mining algorithms may extract the information in this article can portray the characteristics of vocabulary specific user characteristics and make recommendations based on the characteristics of the user vocabulary.

Abstract: This paper investigates the exponential stability problem for a class of stochastic neural networks with leakage delay. By employing a suitable Lyapunov functional and stochastic stability theory technic, the sufficient conditions which make the stochastic neural networks system exponential mean square stable are proposed and proved. All results are expressed in terms of linear matrix inequalities (LMIs). Example and simulation are presented to show the effectiveness of the proposed method.