Search

For the problem of high intensity, low efficiency and poor accuracy in the artificial classification of navel oranges, a detection method is proposed based on machine vision technology. In defect detection, we analyze the color information of navel oranges surface, and obtain surface defect with a proper ratio of R/B and G/B. In the detection of color and luster, we calculate the texture information of the grayscale image, and propose three characteristics such as smoothness R, "consistency" measure U and entropy descriptor e. Finally, a hierarchical model is established based on BP neural network. The test results show that this method can be used for detecting the color and luster of navel orange with a high recognition rate.

This paper used the design method of EME high modulus HMA from France to carry out the mix design of EME2(0/14) HMA, and carried out Duriez test, HWTD, dynamic modulus test and low temperature bending test. The test result showed that this kind of HMA had excellent water resistance, high temperature rutting resistance, high dynamic modulus and low temperature cracking resistance. This EME high modulus HMA was applied in the test road on Qing Lin expressway.

This paper used one kind of organic additive LEADCAP to reduce the compacting temperature of SBS WMA mixture, and compared the WMA mixture compacted by superpave gyratory compactor (SGC) with HMA mixture to determine the compacting temperature of WMA mixture. Rutting test, low temperature bending test, freeze-thaw indirect tension test, Hamburg Wheel-Track test and dynamic modulus were carried out to evaluate the road performance of WMA mixed with LEASCAP. The test result showed that the WMA mixed with LEADCAP had well performed high temperature stability, low temperature stability, water stability, rutting cracking resistance, and high dynamic modulus, the compacting temperature were 127 °C, and affectively reduced the compacting temperature of SBS WMA mixture.

It has been commonly used normal distribution to describe the fatigue life of asphalt concrete. Because of the variability of the material itself and environmental conditions for test, experimental fatigue life datas obtained show a large discrete. Through a large number of laboratory tests and optimization of the strong representation of the data source, this paper verified distribution of the fatigue life of asphalt concrete in statistical in the use of two-parameter Weibull distribution theory and obtained fatigue life equation by regression under different failure probability.The results showed that: Weibull distribution theory can be used to describe asphalt concrete fatigue life distribution under the complicated conditions in a multi-factor.