Applied Mechanics and Materials Vols. 411-414

Abstract: The effective classification of manufacturing resources is the premise of the manufacturing resource modeling and is the important part of virtual manufacturing. In this paper, the hybrid clustering algorithm based on genetic algorithm and genetic Fuzzy C-Means is proposed to cluster the machine tools and the features which the machine tool can processed are regarded as the grouping principle. By this means, the optimum number of optimal cluster and the optimal clusters can be obtained at the same time dynamically. The manufaturing resource clustering can provide information support for the manufacturing resources modeling and manufacturability evaluation and reduce the searching space of processing equipments.

Abstract: Due to many of the clustering algorithms based on GAs suffer from degeneracy and are easy to fall in local optima, a novel dynamic genetic algorithm for clustering problems (DGA) is proposed. The algorithm adopted the variable length coding to represent individuals and processed the parallel crossover operation in the subpopulation with individuals of the same length, which allows the DGA algorithm clustering to explore the search space more effectively and can automatically obtain the proper number of clusters and the proper partition from a given data set; the algorithm used the dynamic crossover probability and adaptive mutation probability, which prevented the dynamic clustering algorithm from getting stuck at a local optimal solution. The clustering results in the experiments on three artificial data sets and two real-life data sets show that the DGA algorithm derives better performance and higher accuracy on clustering problems.

Abstract: The flowshop scheduling problem with limited waiting time constraints widely exists in the production process featured by high temperature and continuity. The constraints require that the waiting time of any job between two consecutive machines is not greater than a given upper bound. In this paper, the problem with two-machine settings and the objective of makespan is studied. First, a lower bound and some characters of minimum makespan are analyzed. Further, a solving idea is suggested by a transformation into an asymmetry TSP. Based on these characteristics and the solving idea, a neighborhood search algorithm embedding a modified Lin-Kernighan heuristic is presented for the problem. Numerical results demonstrated the effectiveness and efficiency of the algorithm.

Abstract: With consideration of three important product types, cold trip, hot strip, and slab, this paper concentrates on the integrated surplus products matching problem (ISPMP) in iron and steel enterprises. A mathematical model is built to maximize satisfied demand and the amount of fulfilled orders while minimizing total involved cost. A PSO based algorithm is proposed into which a neighborhood search procedure is embedded to speed up the convergence. The computational tests show that the hybrid algorithm has good performance.

Abstract: An algorithm based on free search is proposed for the combinatorial optimization problems. In this algorithm, a feasible solution is converted into a full permutation of all the elements and a transformation of one solution into another solution can be interpreted the transformation of one permutation into another permutation. Then, the algorithm is combined with intersection elimination. The discrete free search algorithm greatly improves the convergence rate of the search process and enhances the quality of the results. The experiment results on TSP standard data show that the performance of the proposed algorithm is increased by about 2.7% than that of the genetic algorithm.

Abstract: Drivers affective states will transfer along with environmental changes during driving. The changes can affect directly drivers manipulation. The affective state is represented mainly as drivers propensity. It plays a significant role for researching the active driving and auto-driving systems to reveal the transformation mechanism of drivers propensity exactly in complex environment. Data of drivers propensity can be collected and analyzed through driving experiments in different two-lane environments from the angle of environmental change, especially evolution of vehicle group. It reveals transformation mechanism of drivers propensity under different environment conditions. Verification results show that the predictive outcomes which are gotten by transformation rule are consistent with that of real-time recognition. It also shows that the transformation mechanism revealed in this paper is scientific and reasonable.

Abstract: Usually it is taken grant that we achieve the maximal profit and the minimal risk in industry, agriculture, economic activities and social life. It is an important problem in a decision-making process on how to balance profit and risk and find out practical decision-making ways. This paper builds a decision-theoretic model which can balance profit and risk and provide a heuristic search algorithm of the attribute reduction. This algorithm takes the profit and cost as the heuristic function and outputs an optimal attribute set. At last, the example shows that the proposed algorithm is correct and efficient.

Abstract: This paper presents a rule-based model to deal with the long distance reordering of Chinese special sentences. In this model, we firstly identify special prepositions and their syntax levels. After that, sentences are parsed and transformed to be much closer to English word order with reordering rules. We evaluate our method within a patent MT system, which shows a great advantage over reordering with statistical methods. With the presented reordering model, the performance of patent machine translation of Chinese special sentences is effectually improved.

Abstract: To improve model accuracy,tabu search is introduced to Gene Expression Programming (GEP) and impoves GEPs local search ability, Gene Expression Programming Based on Parallel Tabu Search (PTS-GEP) is proposed. In PTS-GEP, the research conducts experiment over the data from previously reported research and compares the result to two other algorithms namely simple GEP, UC-GEP. The results demonstrate the optimal performance of PTS-GEP in model accuracy.

Abstract: When approximating nonlinear functions, standard BP algorithms and traditional improved BP algorithms have low convergence rate and tend to be stuck in local minimums. In this paper, standard BP algorithm is improved by numerical optimization algorithm. Firstly, the principle of Levenberg-Marquardt algorithm is introduced. Secondly, to test its approximation performance, LMBP neural network is programmed via MATLAB7.0 taking specific nonlinear function as an example. Thirdly, its approximation result is compared with those of standard BP algorithm and adaptive learning rate algorithm. Simulation results indicate that compared with standard BP algorithm and adaptive learning rate algorithm, LMBP algorithm overcomes deficiencies ranging from poor convergence ability, prolonged convergence time, increasing iteration steps to nonconvergence. Thus with its good approximation ability, LMBP algorithm is the most suitable for medium-sized networks.