Advanced Materials Research Vols. 605-607

Abstract: To solve the problem that large training samples and slow speed in diagnosing based on support vector classifier, a hybrid classification algorithm applying attribute reduction of rough set and classification principles of SVM to diagnose diseases was proposed. RS was used to preprocess the attributes on condition that no effective information was lost. Redundant attributes and conflicting objects from decision table was deleted. And the dimension and complexity in the process of SVM classification was reduced. Then it classifies and forecasts objects by SVM classifier, so as to achieve the diagnosis for case. Experiments show that it can improve the rate of diagnosis under the reasonable reducing accurate rating after RS reducing information, and can improve the speed of diagnosing diseases when SVM dealing with much disease information.

Abstract: Since our world is facing with the problem of short power supply, it would be helpful to control the power consumption with the supper low power-consuming digital pressure detector discussed in the paper. The detector is controlled with chip microcomputer MSP430, and its software and hardware design is given in this paper, and the inspection precision is proved to be 0.4 levels.

Abstract: Road load spectrum is not only the prerequisites of fatigue reliability analysis and test of AMT(Automated Manual Transmission) actuating mechanism, but also the input and boundary conditions of CAE(Computer Aided Engineering). Based on analysis of AMT motion and force, the measuring points of road load spectrum are determined, and the accelerometers and strain gauges are installed. Then the road load spectrum of AMT actuating mechanism is collected on Xiangfan Automobile Proving Ground according to related standards. At the same time the acquired road load spectrum is analyzed, such as pretreatment, repeatability checking and statistical analysis. The results indicate that the acquired road load spectrum is well reliable and repeatable, which provides effective basic data for design, analysis and verification of AMT actuating mechanism.

Abstract: According to the algorithms of traditional Linear Variable Differential Transformers (LVDTs) could not represent the performances of the Layer Wound Linear Variable Differential Transformers (Layer Wound LVDTs), new computational algorithms were presented in this paper. Based on magnetic circuit theory, the calculations for the Layer Wound LVDT’s magnetic circuit reluctance, self-inductance, mutual inductance, output voltage and sensitivity are provided. Simulation analysis and experimental tests were used to verify the calculations. The results show that the calculations and equations can accurately express the performance of the Layer Wound LVDTs.

Abstract: Near-infrared (NIR) spectroscopy combined with chemometrics methods has been investigated to discriminate type of honey. 147 NIR spectra of six floral origins of honey samples were collected within 4000~10000cm-1 spectral region. Spectral data were compressed using partial least squares (PLS). Back propagation neural networks (BPNN) models were constructed to distinguish the type of honey. Six spectral data pretreatments including first derivative, first derivatives followed by mean centering(MC), second derivatives, Savitzky-Golay smoothing, standard normal variate transformation (SNV) and multiplicative scattering correction (MSC) were compared to establish the optimal models for honey discrimination. Savitzky-Golay smoothing proved more effective than the other data pretreatments. BPNN models were developed within the full spectral region, 5303～6591cm-1 and 7012～10001cm-1, respectively. Results have shown that the highest(100%) classification rate was achieved within 5303～6591cm-1 wave range. Our results indicated that NIR spectroscopy with chemometrics techniques can be applied to classify rapidly honeys of different floral origin.

Abstract: In aquaculture, the dissolved oxygen volume in water has a significant impact on fish growth and development, which should be monitored. In order to improve the monitoring results, the mathematical model of the dissolved oxygen monitoring system has been built. The PID controller has been designed with the Simulink software and its parameters have been optimized with the nonlinear control design module of the software. After the simulation analysis on the system, the system is stable. The optimized system has smaller overshoot and faster response, and gets a better control. The modeling and simulation of the dissolved oxygen monitoring system in aquaculture has laid an important basis on analysis of the system and has accumulated experiences for the practical application.

Abstract: In order to improve the precision and efficiency of the size measurement of mechanical parts, in this paper the size measurement of mechanical parts based on image processing system is designed , and the digital image processing is applied, meanwhile, geometric characteristics of the mechanical parts are extracted by this system ,then the geometric parameter can be measured. From the results we can see that this new technique guarantees the accurate measurement of linear parts and porous parts.

Abstract: To realize timely and reliable diagnosis of the cotton mite disease, the leaves image features of mite disease were extracted by using computer image processing technology. First the average value and variance of the hue H and G/R as the color features were extracted by the histogram. Secondly, the entropy and inertia value were extracted by the algorithm of co- matrix. Then, according to the binary images of leaves for mite disease, two morphological features of leaf lesion, such as circularity and elongation were extracted. Experiments results indicated that the characteristic values could distinguish the cotton mite disease leaves and normal leaves better. The method which was applied to diagnose the cotton mite disease would improve the accuracy of disease identification and achieve effective governance of cotton mite disease.

Abstract: Commonly referring to the flow velocity is surface mean velocity which evenly be distributed along the circular cross section of pipe. But the pipe velocity measured by ultrasonic flowmeter is linear mean velocity along ultrasonic transmission routes. They are different, so must be corrected. Using the hydrodynamics theory, this paper deduced the equation of flow correction coefficient in laminar flow condition and turbulent flow condition, and dynamically dealt with flow correction coefficient, finally analyzed and evaluated correction curves. The results indicate that this paper can accurately calibrate the ultrasonic flow and get the satisfactory measurement results.

Abstract: To measure optical parameters of biological tissues, support vector machine was adopted. The diffuse reflected light on the surface of the biological tissue corresponding to optical characteristic parameters of human tissue were obtained by Monte Carlo simulation. The nonlinear relationship model had been established between the diffuse reflected light and the optical parameters. The optical parameters were obtained by the support vector machine and the diffuse reflected light. That were compared with the given values of the same sample, and they were coherent basically. It was shown that support vector machine used to measure optical parameters had a high accuracy.