Advanced Materials Research Vol. 952

Abstract: Rice is an important food crop in the world, which provides a strong guarantee for our country's food security strategy policy. As one of the major rice producing areas, the degree of mechanization of rice cultivation is not high, especially in rice seedling, there is not a high degree of automation, a lot of manpower and resources are consumed, it is not suitable for factory work. Based on this, Rice seedlings factory intelligent control system has been researched on the paper. The system can automatically capture the growth of rice seedlings light intensity, temperature etc, and numerical analysis. The indoor self-propelled sprinklers, ventilation and heating systems, carbon dioxide generator and an outdoor shade cloth of the device operation are controlled based on established data. In order to achieve optimal conditions for the growth of rice seedlings, seedlings for large-scale factory, improve efficiency and cost savings.

Abstract: The circumferential welding and the straight seam welding at all position can be realizable by using welding crawl equipment for all position together with the flexible metal band track. The properties of the control system play a decisive role on the welding quality. The program controlling system based on PLC, the drive system for controlling system DC motor and the digital showing system has been developed in present work. The experiments show that the whole system is stable and effective and its control precision can meet the requirement of welding process.

Abstract: Control system of microcomputer controlled electro-hydraulic servo rock three triaxial test instrument adopts closed loop control and the control strategy is based on PID control. Because the conventional PID control cannot meet the control accuracy and stability of system, the intelligent fuzzy controller is introduced to realize the automatic processing in control process. The fuzzy PID controller's design procedure is given to determine the fuzzy domain, fuzzy rules, calculating the reference method and defuzzification process of membership function.

Abstract: The automatic control system is one of the most important parts of improve cold rolling strip precision and increase the automate level. The improved cold strip mill process control system has been developed and successfully applied to several new cold strip production lines. This paper introduces the Key Technical Features and New Technology of the system include the system architecture, hardware configuration and new control algorithms, etc. System operation and actual production proves that the system has the features of shorter commissioning time, convenient maintenance, high reliability, high automatic level and control precision.

Abstract: It is well known that learning from demonstration has many attractive points for both learner and teacher. However, the quality of such learning depends crucially from the system of understanding of human demonstrations. In this paper, we consider an approach to design intelligent avatars for robot learning from demonstration. Also, we present experimental results for intelligent avatar mediated learning from demonstration.

Abstract: The different low temperature electrical characteristics of insulating materials, which plays an important role in superconducting power equipment, has attracted extensive attention. The cryogenic control system is applied to the independent development of superconducting electrical characteristics of insulating materials testing device. And it is designed on the basis of LabVIEW, for the test of the electrical characteristics of the insulation materials in special environment such as cryogenic temperature and vacuum. The system which uses DC source as a heat source and G-M refrigerator as a cold source, uses PID algorithm to control the heat source with the cold source so as to achieve closed-loop control. The system can make the temperature of sample from room temperature down to 6.0K within three hours and control the temperature of sample in the range of 6.0K-300.0K. The system enables temperature error not more than ± 0.5K for a long time and provides a reliable low-temperature environment which is used for study of the electrical characteristics of the insulation materials in different cryogenic temperature and vacuum environment.

Abstract: A hybrid modeling algorithm based on partial least squares and neural network (BP algorithm) is proposed. First it extracts the feature from the original sample sets by partial least squares mehtod, and then the neural network regression using the extraction sets obtained is performed. Thus the hybrid modeling algorithm has the ability of feature extraction. The experiments results on the properties of engineering materials shows that the proposed hybrid algorithm can effectively modeling the properties of engineering materials with merits of dimensions reduction, elimination of noise and multiple correlations between independent variables.

Abstract: To improve the level of aviation safety management and decision-making, an aviation unsafe event model based on neural network trained by an improved Particle Swarm Optimization (PSO) algorithm is proposed. First a gradient acceleration idea is introduced in standard PSO algorithm to improve the search efficiency, and then the improved PSO algorithm is used to optimize the parameters of neural network, finishing the training of model. An actual example on unsafe event data of an airline shows that the proposed method can achieve a good prediction effect.

Abstract: In order to improve the modeling ability for nonlinear system, an Elman modeling method based on Particle Swarm Optimization (PSO) algorithm is proposed. It uses PSO algorithm to optimize the parameters of Elman network. The simulation result shows that the proposed hybrid method combined Elman with PSO algorithm has a good modeling performance with fast training rate for complex nonlinear system.

Abstract: To improve the prediction of properties of engineering materials, a Relevance Vector Machine (RVM) regression algorithm based on Kernel Partial Least Squares (KPLS) is proposed. In the algorithm, firstly execute the feature extraction from the original samples using KPLS, and then use obtained feature to realize RVM regression. The simulation shows that the hybrid regression algorithm can effectively reduce the difficulty on RVM modeling and has a wide application in prediction of properties of engineering materials.