• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.6
• /
• pp.38-44
• /
• 2019

A Convolution Neural Network(CNN) model was utilized to detect surface cracks in asphalt concrete pavements. The CNN used for this study consists of five layers with 3×3 convolution filter and 2×2 pooling kernel. Pavement surface crack images collected by automated road surveying equipment was used for the training and testing of the CNN. The performance of the CNN was evaluated using the accuracy, precision, recall, missing rate, and over rate of the surface crack detection. The CNN trained with the largest amount of data shows more than 96.6% of the accuracy, precision, and recall as well as less than 3.4% of the missing rate and the over rate.

• International Journal of Highway Engineering
• /
• v.10 no.2
• /
• pp.1-13
• /
• 2008

This study presents a case study of condition evaluation of various asphalt pavement sections to estimate performance lives. The pavement surface conditions including cracking and rutting are first evaluated using a automatic pavement analyzer, ARAN. HPCI(Highway Pavement Condition Index) values are estimated using the pavement surface distress data. It is observed from the pavement distress survey that the major distress type of the sections is top-down cracking. The modulus value of each pavement layer is back-calculated from the defection data obtained from a FWD(Falling Weight Deflectometer) and compared with the laboratory measured dynamic modulus values. Remaining lives of the various pavement sections are estimated based on a mechanistic-empirical approach and AAHTO 1993 design guide. The structural capacities of the all pavement sections based on the two approaches are strong enough to maintain the pavement sections for the rest of design life. Since the major distress type is top-down cracking, the remaining lives of the pavement sections are estimated based on HPCI and existing performance database of highway pavements. To evaluate the causes of premature pavement distress, various material properties, such as air void, asphalt binder content, aggregate gradation, dynamic modulus and fatigue resistance, are measured from the field cores. It is impossible to accurately estimate the binder contents of field samples using the ignition method. It is concluded from the laboratory tests that the premature top down cracking is mainly due to insufficient compaction and inadequate aggregate gradation.

• International Journal of Highway Engineering
• /
• v.14 no.2
• /
• pp.11-17
• /
• 2012

This research describes how to predict a model of the tensile strain related to the fatigue cracking performance of several asphalt concrete structures through design of experiments(e.g., Response Surface Methodology) and harmony search(HS) algorithm. The axisymmetric analysis program of finite element method, which is the KICTPAVE, was used to determine the strain level at the interface layer between asphalt layer and lean concrete layer. Once the training database set of various strain levels was constructed under the several condition of layer stiffnesses and thicknesses in the asphalt concrete structures, the data set was trained through the HS algorithm in order to determine the regression coefficients defined based on a response surface methodology. Furthermore, the testing set, which was not used for the training procedure of HS algorithm, was also constructed in order to evaluate whether the regression coefficients of a prediction model can be appropriately applied for other cases in asphalt concrete structures.

• International Journal of Highway Engineering
• /
• v.3 no.4 s.10
• /
• pp.137-146
• /
• 2001

Pavement distresses are one of the most important data for pavement management systems. Inspection machines and its related programs have been used for operating tools in PMS developed in advanced countries. In Korea imported machines and programs for the length price ale utilized to get information of pavement condition from the field This study is launched for developing the program which can detect cracks on asphalt pavement due to many drawbacks in current PMS operation such as improper maintenance work and long resting period when it was broken. The focus of this study is to define principles to analyze pavement surface with digital image processing techniques, to test property of pavement images and to suggest an algorithm that reduces noises at test. To test images, the camera attached on the Automatic Road Analyser(ARAN) was used. Through the FFT images, histogram and statistical values of pavement images, it was found that the images had many noises with high-frequency components against general images, and it was difficult to subdivide pavement images into background or crack. Through several testing with various filters for noise reduction a 3X3 median filter was suggested to reduce noises effectively.

• International Journal of Highway Engineering
• /
• v.11 no.2
• /
• pp.111-120
• /
• 2009

This paper presents a fundamental findings of the functional and structural performance of the porous asphalt concrete coated with MMA resin. To evaluate the structural performance, cantabro, wheel tracking, moisture sensitivity and indirect tensile fatigue tests are performed. The tests results show that the cantabro loss is reduced three times and fatigue resistance is significantly increased after the specimens are coated with MMA resin. However there are little changes in the rutting and moisture damage resistances before and after the coating. Air voids, permeability and BPT(British Pendulum Test) tests are conducted to study the functional performance. It is observed form the tests that the air voids and permeability are slightly decreased after the coating. However, the changes in the air voids and permeability are negligible. The skid resistance of the coated specimens is lower than reference specimens. However, the skid resistance is maintained beyond the level of the reference specimens when silica sands are chipped on top of the coated surface.

• International Journal of Highway Engineering
• /
• v.12 no.3
• /
• pp.27-35
• /
• 2010

Asphalt Plug Joint(APJ) is an buried expansion joint that enabling the smooth connection of expansion gap and road pavement by filling the gap with bituminous mixture of 20% bitumen and 80% aggregate by weight, so it secures evenness and expansion or contraction using the material's properties. Although APJ is designed to have a 6-7 year lifecycle, there are some cases where it is damaged within the first six months. This early damage cause traffic congestion due to frequent repair works, and social cost exceeding the installation cost of the joint. So, in this research, we have developed a new system of Buried Folding Lattice Joint(BFLJ) which can overcome the disadvantages of APJ, and have analyzed and compared it's performance with the conventional APJ through experiment with specimens. As a result of the experiment, APJ had crack formation on both ends of the gap plate, spreading to the surface of the expansion joint. With this result, we can conclude that the reason for early damage is the tension failure due to the concentration of strain in the asphalt mixture along the end of gap plate and the debonding along the joint section. In contrast, the newly developed BFLJ induced even transformation in the joint by applying moving stud and high performance material, and resolved APJ's disadvantage of strain concentration. Therefore, it could be seen that the newly developed BFLJ could overcome the disadvantages of APJ and prevent early damage.