Applied Mechanics and Materials Vols. 602-605

Abstract: This paper based on the scattering principle of lubricating oil to light, designed the plan of making use of near-infrared light to monitor automobile lubricating oil, and hereby it to monitor the deteriorated condition of lubricating oil. Experiments show that: this kind of technology for monitoring automobile lubricating oil can satisfy the deterioration condition monitor demand of automobile lubricating oil, and give the instructions of the lubricating oil deterioration degree, so we can decide whether the lubricating oil can continue to use according to it. This method changed the traditional conditions that replace the lubricating oil according to time or the driving mileage, it realized replacing lubricating oil according to the quality, thus it makes the lubricating oil obtain the reasonable economy service life, and guaranteed the good lubrication condition of vehicles.

Abstract: Spectrum analysis technology and advanced sensors can identify and estimate the plant growth and the press from environment. It can also estimate the weight of plant dry matter or predicted yield, process monitoring and management of greenhouse production quantitative and scientific. This paper focuses on the design of plant growth test instrument. The normal operation of the whole system is completed by two parts of software and hardware. The hardware is the foundation of the whole system, and the software is designed according to hardware. Software is the soul of the system, and the whole system work scheduling by it.

Abstract: Based on the data source problems of intrusion detection evaluation and the feature of OpenFlow capable of providing flexible network control, this paper studies the real data evaluation model based on the software-defined network, and makes program implementation over the model-based intrusion detection evaluation system, and then uses the network to simulate this model. The experimental result shows that the model is feasible and effective.

Abstract: An approach to the recognition of airport runways in SAR imagery was presented. According to the trait of the SAR imagery, firstly some kinds of methods in correlative yawp control were compared to each other, and then based on the interpretation analysis of airport runways in SAR imagery, the lines were detected ,the image was repaired and the redundant lines were got rid of according to themorphologic operation and confidence level ,the runways were detected finally .Many experiments show that the method can recognize the runways exactly and quickly in SAR imagery.

Abstract: Using STC89C58 MCU as the core, through the acceleration sensor and a humidity sensor for the monitoring the displacement of underground conditions, to simply realize real-time monitoring function of the displacement of underground. Introduces the working principle and software/hardware system design. The experimental results show that, the system has stable operation, achieved the expected goals.

Abstract: To describe the complex nonlinear characteristics of a system accurately, a Wavelet Neural Network (WNN) identification model based on Artificial Fish Swarm (AFS) algorithm is proposed. In the identification model, AFS algorithm is introduced to optimize the parameters combination of the network for the satisfactory WNN model. The simulation shows that, the proposed method is a good nonlinear identification capability, and is feasible to identify the nonlinear system.

Abstract: The paper designs a kind of nuclear explosion infrasonic signal acquisition equipment and brings forward a pretreatment way. Based on μC/OS and digital circuit of FPGA+ADC, the paper realizes signal acquisition, storage and transmission of infrasound, which is from 0Hz to 20Hz. And according to the characteristics of nuclear infrasonic signal, mean removal, bandpass filter and normalization are used for signal pretreatment. Experiments proved that the signal acquired from acquisition equipment can be used for identification of nuclear explosion.

Abstract: The segment sensitivity for various pressure sensors is obtained by implementing the static and dynamic calibrations for three types of pressure sensors, i.e., CY-YD-202, CY-YD-205 and CY-YD-203T, and the average absolute value of relative errors for sensors is obtained by measuring the dynamic high-frequency signal, which provides the basis for correct selection of pressure sensor during the test.

Abstract: In recent years, Internet traffic classification using machine learning is a hot topic, and supervised learning methods which contain Support Vector Machine were used to identify Internet traffic in many papers. The supervised learning methods need many instances which have been labeled to train classifying model, but it is difficult to label the instances because many traffic have been encrypted. Labeled instances and unlabeled instances can be used by semi-supervised learning methods to train the classifying model, so that it is very fit for p2p traffic identification. Transductive support vector machine is one of the typical semi-supervised learning methods. Based on theoretic analyzing and experiment, we compared the accuracy of TSVM and SVM. The experiment results show that the semi-supervised methods have some advantages on identification of p2p traffic.

Abstract: The highway’s traffic accident often occurred because of the influence of fog and other inclement weather, which caused very big loss to people's life and property. Therefore, all-weather real-time monitoring, analysis and effective early warning to the atmosphere along the highway visibility condition has an important significance. In the paper, the intelligent monitoring and warning system of expressway fog is introduced in details. The result shows that the system has high precision and reliability.