Applied Mechanics and Materials Vols. 373-375

Abstract: To systematically harmonize the conflict between selective pressure and population diversity in estimation of distribution algorithms, an improved estimation of distribution algorithms based on the minimal free energy (IEDA) is proposed in this paper. IEDA conforms to the principle of minimal free energy in simulating the competitive mechanism between energy and entropy in annealing process, in which population diversity is measured by similarity entropy and the minimum free energy is simulated with an efficient and effective competition by free energy component. Through solving some typical numerical optimization problems, satisfactory results were achieved, which showed that IEDA was a preferable algorithm to avoid the premature convergence effectively and reduce the cost in search to some extent.

Abstract: With the fast development of the hospital information system, the hospital database has accumulated vast amounts of management and clinical medical data. Therefore, we establish the hospital information platform to integrate the various resource of information in hospital and make the effective development and utilization, so that we can construct a data analysis platform which focuses on the patients clinical diagnosis information and the management information for hospital. In this respect, this paper introduces the business intelligence technology into the hospital information statistical field, and sets up the business intelligence system which focusing on the integration of business data and assistant decision support analysis.

Abstract: Wind turbine transmission system with abundant fault feature and variable types, the vibration signal was a carrier of fault features and it can reflect most of the fault information in the wind turbine transmission system. As there were a large number of transient and non-stationary signals accompany with the vibration signals, so wavelet packet transform was adopted for feature extraction. As RBF Neural network has a strong nonlinear mapping ability and self-adaptability, so it was introduced to the diagnosis system for network training, the neural networks structure and learning algorithm was presented, which could enhance the accuracy of diagnosis. The two-level neural networks recognition method was proposed, first level for fault classification and second level for fault diagnosis. The example shows that this method can be effectively applied to transmission system of wind turbine fault diagnosis with wavelet packet algorithm for fault feature extraction and RBF neural network for pattern recognition.

Abstract: The particle swarm optimization algorithm was improved in this paper, a novel self-adaption dynamic sub-swarms hybrid particle swarm optimization algorithm is proposed, in this algorithm, subgroup partition method based on dynamic clustering of particle adaptive value is adopted to divide particle group to different capability sub-group, then execute different optimize strategy to different subgroup, simultaneity, inertial weight and accelerating coefficient are adaptive set, through contacting adjustment of parameter with sub-group capability, the particle mode method and intersect and aberrance strategy of double deck are designed, The experimental results show that the algorithm has simple programming, good robust capability and strong optimizing capability which established the foundation of task planning of multi-UAV Cooperative.

Abstract: The weapon and equipment system of systems (WESoS) construction risk analysis is great significance to enhance decision-making and management level of information technology WESoS construction. The concept of "entropy" in the information engineering is using to calculate the entropy, and the entropy weight is used to fix subjective weight, after that Combining ideal point method to evaluate and select the schemes, the best decision of WESoS construction is get. The model is of impersonality and in reason, which provided a simple and practical method for construction risk evaluation of WESoS.

Abstract: Camshift tracking algorithm is based on probability distribution of color , it is susceptible to be interfered by the same color in the background, which will lead to the failure of the target tracking. To overcome this problem it presented an improved Camshift tracking algorithm. It combined background subtraction method with three frame difference method to detect target, got rectangular characteristic parameters of the motion target area as the Camshift initialization parameters, replaced the general Camshift algorithm which is based on color feature. Experimental results show that Camshift algorithm combining the background subtraction method with three frame difference method can meet the requirements of the real-time and stability to a certain extent.

Abstract: The selection and the evaluation of demonstration engineering project of housing are a complex analysis process, many projects are involved, evaluation index system are complicated, the requirements of scientific, advanced, efficiency and fairness are failed to meet with the traditional decision method. Multi-dimensional network decision support system are constructed in this paper, the construction scheme of knowledge base, model base and data warehouse are made a detailed description, the technical method of system construction are made clearly. The new decision services support is provided to select and evaluate to the demonstration project.

Abstract: The article, based on satisfying robustness of the system and put forward the objective function of time-domain performance and dynamic characteristics, introduced genetic operators into Particle Swarm Optimization. The algorithm improve the diversity of particles by selection and hybridization operations and strengthen the excellent characteristics of particles in the swarm by introducing crossover and mutation genes, which can avoid bog down into local optima and premature convergence and enhance searching efficiency. The simulation results indicate that when the algorithm is applied to the optimization of PID controller parameters of servo system of grinding wheel rack of MKS8332A CNC camshaft grinder, its performance is better than the single Genetic Algorithms or Particle Swarm Optimization, and it can also satisfy the demand of rapidity, stability and robustness.

Abstract: We propose a modified particle swarm optimization (PSO) algorithm named SPSO for the global optimization problems. In SPSO, we introduce the crossover operator in order to increase the diversity of the swarm. The crossover operator is contracted by forming a simplex. The crossover operator is used if the diversity of the swarm is below a threshold (denoted h_low) and continues until the diversity reaches the required value (h_high). The six test problems are used for numerical study. Numerical results indicate that the proposed algorithm is better than some existing PSO.

Abstract: This paper discusses training structure and procedure about inversible system of neural network. Subsequently, selection of training sample is focused on. Finally, the paper proposes some principles and ways to obtain training sample of inversible system.