Applied Mechanics and Materials Vols. 602-605

Abstract: A rapid quantification technique is developed and validated for nondestructively quantifying Vitamin C content of navel orange using NIR spectroscopy in conjunction with genetic algorithm (GA) and Gene expression programming (GEP) algorithm. The spectral are recorded in the NIR region using the fiber optic probe method. Four data points of the navel orange NIR are selected by genetic algorithm and GEP algorithm by cross validation. In our experiment, the correlative coefficient between predicted and measured values in the training group is 0.9206, and that of the validation group is 0.8994, the results show that the proposed method can be built to a concise easily computed model, which has feasible accuracy.

Abstract: According to prevention level of grain storage requirements and granary actual situation, a novel grain storage insect image for automatic identification algorithm was presented based on features point and stereo matching. Firstly, pyramid delaminating was used to preprocess target image. Then, image normalized could be obtained according to formula. Secondly, the SIFT features points could be extracted from reference image and target image. Finally, according to epipolar constraint and the straight line slope of pass through features matching points, The paper could be successful to automatic identify grain storage insect. The results of experiment with the really grain storage insect images shown the proposed algorithm was effective and could obtain high recognition rate.

Abstract: In the process of design and construction of tailings pond online safety monitoring system, There are often a series of problems such as the system structure is too complex, construction difficult, high maintenance cost etc. In order to change this situation, the design of tailings dam safety online monitoring system based on Zigbee wireless sensor network with self-healing function is unveiled, the system based on the concept of distributed acquisition, built Zigbee wireless sensor network, transmit the collected data wirelessly in the monitoring range of the tailing pond, play advantages of Zigbee technology in low power consumption and self-healing feature, and did data collection, storage, query and other operations in real-time, In this way, we could reduce the difficulty of construction, greatly improving the stability of the system communication, and can expansion or change the system conveniently, so as to meet the requirements of real-time monitoring the safety state of the tailings pond efficiently for long-term. Supported by: National Science and technology support program (2012BAK09B04、2012BAK09B03) the National High Technology Research and Development Program ("863"Program) of China (2011AA060406)International S&T Cooperation Program of China (ISTCP)( 2011DFA71990)

Abstract: To the background establishment in background difference method, a method is proposed to detect moving targets based on the improved Burendra algorithm. This method can accurately detect moving targets in the video images, meanwhile it can respond to the changes of background and light intensity in the scene in time, being with good real-time performance and robustness.

Abstract: To diagnose the fault that occurs in rotating machinery, a neural network diagnosis method based on an improved GA algorithm is proposed. In this diagnosis method, a case injected idea is introduced to improve the strong global search capability of traditional GA algorithm; and then the improved GA algorithm is used to optimize the parameters of neural network, fulfilling the training of neural network. Simulation result indicates that, the proposed diagnosis method has a good practicability in the field of fault diagnosis for rotating machinery.

Abstract: It is difficult to realize an accurate and reliable diagnosis in the rotating machinery. To solve this problem, a Wavelet Neural Network (WNN) diagnosis model based on EKF algorithm is proposed. In the model, EKF algorithm is introduced to optimize the parameters of WNN, and then the built WNN model is used to diagnose the faults of the rotating machinery. The experiment shows that, the proposed model has a good diagnosis capability in the field of the rotating machinery.

Abstract: Petrochemical pharmaceutical bio-fermentation industry, witch is characterized by the production press of the material inside the device sets experiencing recessive chemical processes. In industrial production process, some media usually easy to produce large foam, witch affect production, it must be detected the amount of foam in real time, to effectively eliminate the foam bubbles and control the processes of the physical and chemical reactions to ensure the efficient, orderly and safe conduct throughout the process .Foam is multi-interface, uneven density and unstable surface shape, each bubble has its own gas and liquid interface, many bubbles overlap together, with the various interfaces. Staggered and different angles, witch making it light-scattering, in order to obtain a clear picture of foam, and effectively obtain features of foam, shoot on goal from different angles, the captured images are compared and analyzed to choose the best camera angle. Morphological methods was introduced and used to extract the edge of bubbles in foam. This work proposed a improved Hough Transform (HT) to analyze round bubbles and detect each bubble.To detect whether the captured image is the foam image, this work also proposed calculating the density of bubbles in the captured image. The preliminary results showed that the algorithm is dynamic with high efficient.

Abstract: Fuzz testing is a software testing technique,which provides invalid, unexpected, or random data to the inputs of a computer program to test the robustness and security of procedures^[1]. For structured data like logging, the variant fuzz testing framework adopts a configuration file, apply traverse and stream processing to complete the structured fuzzing. This article starts with the features of the structured data, then introduces the design and implementation of the variant fuzz testing framework, including function modules, class structure, and logic processing. As a conclusion, this framework is compared with zzuf tool, and the advanced nature of this framework is elaborated.

Abstract: To realize video surveillance at any time and any place, a kind of video surveillance platform based on 3G smart phone was designed. In this paper, the general design scheme of video surveillance system was firstly introduced. Then, the surveillance software development method of smart phone client, the transmission mode and transmission protocol of surveillance video were also emphatically described. This system used SVAC which is kind of specifying surveillance video to meet security-monitoring demand. It used multi-image display to realized multi-channel video surveillance, and also used multi-thread to increase the running speed of software. Experimental results demonstrate that it can obtain stable real-time surveillance video.

Abstract: The idea of applying tunnel seismic advance exploration in coal mine geo-hazard detection is conducted in this paper. We successfully made a mine advance and side detection simultaneously with one-time shot seismic data by splitting the field seismic data using radon transformation, and we preceded mine seismic data processing and data interpretation was done to explain the phenomenon. We also introduce a case study in this paper which was carried out at Qinshui basin Yangmei No.5 mine field, and the detection results basically matched with out-crops, illustrating that our method can be one reference in mine geo-hazard detection.