In this paper, the depth forecasting of eroded caves behind seawall model is proposed by using the back-propagation neural network combined the thermography analysis. The measured data of the depth of eroded caves behind seawall from the model experiments of sandbox and Cingcao seawall in Taiwan had been used to test the performance of the present model. From the results, it was found that the artificial neural network can efficiently forecast the depth of eroded caves behind a seawall using the four input factors, including the site temperature, humidity, thermograph area, and temperature difference
A seawall has been used to protect against the erosion of a coastal area and avoid coastal hazards. However, the action of a strong wave force or typhoon force often causes destruction of the seawall, causing, for example, eroded caves behind the seawall. This damage not only affects the resident's lives behind the seawall, but it also causes severe flooding in the coastal area. Therefore, an accurate, fast, safety inspection method is critical. Conventional inspection methods for evaluating the safety of the seawall have been often used in the past, such as periodical inspection, damage inspection and special inspection for different situations, but it is still difficult to identify the existence of eroded caves behind seawall. Thermography is a non-destructive test method that involves infrared imaging. Thermographic cameras detect radiation in the infrared range of the electromagnetic spectrum (roughly 900~14,000 nanometers or 0.9~14 μm) and produce images of that radiation. Since infrared radiation is emitted by all objects based on their temperatures, according to the black body radiation law, thermography makes it possible to see one''s environment with or without visible illumination.
