Advanced Materials Research Vols. 490-495

Abstract: To ensure the rotary electromechanical equipment injection pump unit safe and stable operation, status assessment parameters should be predicted used by appropriate prediction model. This paper presents a genetic algorithm optimization neural network prediction model based on mean function new information-weighted theory (MWGANN prediction model). MWGANN prediction model can optimize the neural network structure parameters and improve the prediction accuracy and prediction timeliness by using the recency difference of time series data. Collecting large rotating injection pump unit vibration intensity time series in the industrial site, MWGANN prediction model and GANN prediction model are applied to predict trend. The results show that MWGANN model achieved good results in prediction accuracy and prediction timeliness.

Abstract: weighted geometric means combination forecasting is a kind of nonlinear combination forecasting model. Based on absolute of grey incidence, a weighted geometric means combination forecasting model is proposed. Superior combination forecasting, dominant forecasting method and redundant degree are put forward. Under certain conditions the sufficient condition of existence of non-inferior combination and superior combination forecasting are discussed, redundant information is pointed out in a judging theorem.

Abstract: In this paper, The authors briefly Analyzed the process parameters on the effect of quartz nano-powder preparation. used orthogonal experiment to study the test method of quartz nano-powders prepared by ball milling, applicated artificial neural network technology to build a prediction model of powder parameters based on BP network and optimized the BP network weights and improved the prediction model of quartz particle size based on BP network by using the global search capability of genetic algorithm . This study showed that the model has higher accuracy and realize acceptable prediction of powder particle size.

Abstract: The location and direction precision is passive acoustic technology of important technical index. Put forward a double-equilateral-triangle array of six elements. According to passive acoustic theory for the location algorithm. Azimuth and elevation Angle is deduced, and the distance of the error formula, through the simulation test, the time delay estimation error analysis of the influence of the location precision. Simulation results show that: double-equilateral-triangle array eliminates the sound velocity and the formation parameters diagonal coordinates estimation precision effect, which have practical significance.

Abstract: Open Computer Numerical Control system (Open CNC) based on PC and the Windows operating system has been a major developing direction and a research focus of the current numerical control technology. At present, there have been all kinds of the Open CNC systems with high-speed and precision servo control boards, but they are too expensive. Therefore, developing an economical and practical motion controller is great significant for middle and small numerical control system

Abstract: Naive Bayes classification algorithm is an effective simple classification algorithm. Most researches in traditional Naive Bayes classification focus on the improvement of the classification algorithm, ignoring the selection of training data which has a great effect on the performance of classifier. And so a method is proposed to optimize the selection of training data in this paper. Adopting this method, the noisy instances in training data are eliminated by user-defined effectiveness threshold, improving the performance of classifier. Experimental results on large-scale data show that our approach significantly outperforms the baseline classifier.

Abstract: Based on Rough Sets (RS), a novel effective video summarization representation was proposed for video analysis in compressed domain. Firstly, DCT coefficients and DC coefficients are extracted from original video image sequences, so an Information System can construct with DC coefficients. Then, Information System is reduced by attributes reduction theory of RS, the representation of the video frame is achieved by reduced DC coefficients. Finally, the reduced Information System can be achieved. Since the Core of Information System contained all major video information in video sequences, which banished the redundant video frame, so it can be considered as the efficient summarization representation. Compared to conventional or existing algorithm, the algorithm enjoys following advantages. (1) Only a subset of video frames considered during video analysis, so it can avoid the computational complexity. (2) The video summarization representation becomes more scientific and efficient than previous methods. (3) According to the reduced frame number, the algorithm can extract hierarchical dynamic video summarization representation.

Abstract: The planar non- circle curve component’s relative rotative movement was anaysised in this paper, Because the pure mathematics model applies with difficulty in the real issue , With equal interval angle line replaced the smooth contour curve, A simplified mathematical model about movement was establishde, Compare with theory result, the simplified mathematical model could give a right result when the angle intervalδ<3 and the speed is 3~5mm/s. the model could be used in the processing of plane non-circular curve profile parts and induction quenching.

Abstract: In this paper, the design scheme of a Measurement and Control(M&C) system based on AT91RM9200 is proposed. For expanding the test functions, based on the AT91RM9200 control platform the GPIB interface is added in the platform. With the EMAC interface, the automatic test function on multiple communication channels is realized on the GPIB test bus and Ethernet. In this paper, the Modular architecture is used to design the hardware platform. While in the design of the software, the real-time multitasking function of RTOS is combined with the task processing methods corresponding to the interruptions to make the design , building and reusing of tasks more convenient. So that the whole test system can be more common and scalable.

Abstract: As to the vehicle visual detection and tracking problem in IDASWs (Intelligent Driver-Assistance and Safety Warning System), this paper proposed a way of a good effect. Firstly use vehicle’s bottom shadow feature and identified lane result to determine the searching region. Then use template matching algorithm based on vehicle’s tail shape to realize detecting and tracking. Experimental results show that the algorithm can effectively detect and track the preceding vehicle from the video sequence, reaching robust and real-time requirements