Applied Mechanics and Materials Vols. 568-570

Abstract: Combined with quantum computing and genetic algorithm, quantum genetic algorithm (QGA) shows considerable ability of parallelism. Experiments have shown that QGA performs quite well on TSP, job shop problem and some other typical combinatorial optimization problems. The other problems like nutritional diet which can be transformed into specific combinational optimization problem also can be solved through QGA smoothly. This paper sums up the main points of QGA for general combinatorial optimization problems. These points such as modeling of the problem, qubit decoding and rotation strategy are useful to enhance the convergence speed of QGA and avoid premature at the same time.

Abstract: The construction of the user model for achieving accurate personalized learning recommendation has an important role. The paper described the user model construction method based on ontology for multimedia video teaching resources in the field of agriculture. The concept and evolution of the ontology, user modeling technology and agriculture video ontology construction method is given, and the user model is realized and validated by experiment at last.

Abstract: In this paper, we propose an analysis refine scheme based on data fusion towards some existing problems in data analysis of intelligent transportation systems .This method constructed the data into a plurality of time-series according to the characteristics of each attribute data. Providing an objective scientific basis for dynamic traffic management through intelligent analysis of traffic information based on the gray advantage analysis among data and system model of Intelligent Traffic Information decision support and auxiliary decision analysis.

Abstract: After the European and American countries put forward the modular design in the 1950s, and it become a hot topic again in 2013. Modular design make a well experience for product form design, but it also has its limitation. because of Genetic Algorithm (GA) has the superiority of optimizing and solving, This paper proposes a modular, hierarchical product modelling design based on GA, Using iterative repeated optimization genetic operators to make product modeling design to achieve an optimal form.

Abstract: Using the wide area information of the IED, the identification faulty components network is constructed based on RBF neural network. Using the state information collected by line IED as the input vector, training samples matrix of identification faulty components network is established to train RBF neural network of faulty components identification, and to test the recognition network using the sample matrix under random failure, and then the faulty line IED can be identified, the faulty components can be determined. Experiments show that the new algorithm based on RBF has higher accuracy rate and better fault-tolerant.

Abstract: To resolve the problem of no guidance about how to set the values of numerical meta-parameters and difficulty to achieve optimization of Deep Boltzmann Machines, genetic algorithms are used to develop an automatic optimizing method named GA-RBMs (Genetic Algorithm-Restricted Boltzmann Machines) for this model’s aided design. Based on the Restricted Boltzmann Machines’ features and evaluation function, a genetic algorithm is designed and realizes the global search of satisfied structure. We also initialize the network’s weights to determine the number of visible units and hidden units. The experiments were conducted on MNIST digits handwritten datasets. The results proved that this optimization reduced the dimension of visible units and improved the performance of feature extracted by Deep Boltzmann Machines. The network optimized has good generalization performance and meets the demand of Deep Boltzmann Machines’ aided design.

Abstract: Detecting community structure from complex networks has triggered considerable attention in several application domains. This paper proposes a new community detection method based on improved genetic algorithm (named CDIGA), which tries to find the best community structure by maximizing the network modularity. String encoding is used to realize genetic representation. Parts of nodes assign their community identifiers to all of their neighbors to ensure the convergence of the algorithm and eliminate unnecessary iterations when initial population is created. Crossover operator and mutation operator are improved too, one-way crossover strategy is introduced to crossover process, the Connect validity of mutation node is ensured in mutation process. We compared it with three other algorithms in computer generated networks and real world networks, Experiment Results show that the improved algorithm is highly effective for discovering community structure.

Abstract: The study shows overfeed sewing shrinkage was not linear relationship with physical property and garment sewing process parameter. It chose simulation arm of light wool fabrics to do overfeed sewing experiment, and selected seven characteristic values such as connection length of long fabric, connection length ratio flexural-tensile modulus ratio, relaxation shrinkage and wet expansion rate of long and short fabric, and applied artificial neural network to forecast overfeed sewing shrinkage of light wool fabrics. Compared with actual result, the error of predicted result was lesser. The foundation of prediction model is significant for woolen mill to develop a set of interactive software and extend application.

Abstract: Individual civil building intelligent project design is the process of using the artificial intelligence Agent technology in simulation the three logical relationship of building user, bubbles, streamline. Divided by bubbles, streamline generation and adjustment, bubbles divided again, streamline refinement and adjustment, until the last bubble becomes a specific room, streamline into specific hall gallery, generate the corresponding construction main body structure finally change into figure according to national building drawing standards, so completed the design of intelligent optimization and scheme evaluation with real-time interaction. Intelligent design process is an innovation in the field of computer aided architectural design, shorten the design time and improve the design efficiency.

Abstract: With the scale of grid-connected wind farms increasing, accurate forecast of ultra-short-term wind speed and wind power is very important to the stable operation of power systems. This paper presents a dynamic selective neural network ensemble (DSNNE) forecast method, which makes use of K nearest neighbor algorithm to collect the generalization errors of certain different BP neural networks and RBF neural networks into a performance matrix and then the neural networks with low local generalization errors are dynamically selected and locally dynamic averaging is applied to the neural networks in order to conduct the final results of the ensemble. Then this method is applied to realize the wind speed and power ultra-short-term advance forecast, taking the wind speed and wind turbine power output from a wind farm in China as the original data. The research results show that DSNNE improves the generalization ability of the neural network system and the prediction accuracy of wind power and wind speed significantly. It proves the validity and effectiveness of the DSNNE with controlling the biggest mean relative error of 2 minutes ahead wind power and wind speed forecast as low as 25% and 16% respectively.