• Computers and Concrete
• /
• v.5 no.6
• /
• pp.573-597
• /
• 2008

Among artificial intelligence-based computational techniques, adaptive neuro-fuzzy inference systems (ANFIS) are particularly suitable for modelling complex systems with known input-output data sets. Such systems can be efficient in modelling non-linear, complex and ambiguous behaviour of cement-based materials undergoing single, dual or multiple damage factors of different forms (chemical, physical and structural). Due to the well-known complexity of sulfate attack on cement-based materials, the current work investigates the use of ANFIS to model the behaviour of a wide range of self-consolidating concrete (SCC) mixture designs under various high-concentration sodium sulfate exposure regimes including full immersion, wetting-drying, partial immersion, freezing-thawing, and cyclic cold-hot conditions with or without sustained flexural loading. Three ANFIS models have been developed to predict the expansion, reduction in elastic dynamic modulus, and starting time of failure of the tested SCC specimens under the various high-concentration sodium sulfate exposure regimes. A fuzzy inference system was also developed to predict the level of aggression of environmental conditions associated with very severe sodium sulfate attack based on temperature, relative humidity and degree of wetting-drying. The results show that predictions of the ANFIS and fuzzy inference systems were rational and accurate, with errors not exceeding 5%. Sensitivity analyses showed that the trends of results given by the models had good agreement with actual experimental results and with thermal, mineralogical and micro-analytical studies.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.17 no.5
• /
• pp.113-121
• /
• 2013

The road icing forecast and snow detection system using state evaluation algorithm of multi sensor optimizes snow melting system to control spread time and amount of chemical spread application This system operates integrated of contact/non-contact sensor and infrared camera. The state evaluation algorithm of the system evaluates road freezing danger condition and snowfall condition (snowfall intensity also) using acquired data such as temperature/humidity, moisture detection and result of image signal processing from field video footage. In the field experiment, it proved excellent and reliable evaluated result of snowfall state detection rate of 89% and wet state detection rate of 94%.

• Journal of the Korea Concrete Institute
• /
• v.15 no.4
• /
• pp.529-540
• /
• 2003

Recently, the researches on the durability design of concrete structures have been studied. As the examples, models to evaluate the service life prediction of the structure have been developed. The purpose of this article is to develop the model for predicting remaining service life. The final aim is to provide the user time for repairing the concrete structures. In addition, it makes possible to maintain the concrete structure economically. 70 reservoirs out of the inland concrete structures were selected and concrete structures of their components were surveyed. Two methods were used for measuring carbonation; TG/DTA method and Phenolphtalein indicator and, the value of pH was measured by the pH meter, After deriving correlations of calcium carbonate and used year, duration from completion year to 2002, pH value, and concrete cover depth the model was developed for predicting remaining service life by measuring data as small as possible. The conventional models had been developed on the basis of experiment data obtained from the restricted lab environment like as carbon gas exposure. On the other hand this model was developed on the basis of measuring data obtained from the real field that the complex deterioration actions are occurred such as freezing and thawing, carbonation, steel corrosion, and so on. The reliability of the developed model will be evaluated high in this point and this model can help to maintain concrete structures economically by providing the manager time to repair the deteriorated concrete structures in site of facility management.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.4
• /
• pp.156-172
• /
• 2020

The purpose of this study was to predict road surface temperature using high-resolution solar radiation data. The road surface temperature prediction model (RSTPM) was applied to predict road surface temperature; this model was developed based on the heat-balance method. In addition, using SOLWEIG (SOlar and LongWave Environmental Irradiance Geometry-model), the shadow patterns caused by the terrain effects were analyzed, and high-resolution solar radiation data with 10 m spatial resolution were calculated. To increase the accuracy of the shadow patterns and solar radiation, the day that was modeled had minimal effects from fog, clouds, and precipitation. As a result, shadow areas lasted for a long time at the entrance and exit of a tunnel, and in a high-altitude area. Furthermore, solar radiation clearly decreased in areas affected by shadows, which was reflected in the predicted road surface temperatures. It was confirmed that the road surface temperature should be high at topographically open points and relatively low at higher altitude points. The results of this study could be used to forecast the freezing of sections of road surfaces in winter, and to inform decision making by road managers and drivers.

• Journal of the Korean Society for Railway
• /
• v.11 no.5
• /
• pp.441-448
• /
• 2008

Increasing urban sprawl and climate changes have been causing unexpected high-intensity rainfall events. Thus there are needs to enhance conventional disaster management system for comprehensive actions to secure safety. Therefore long-term and comprehensive flood management plans need to be well established. Recently torrential snowfall are occurring frequently, causing have snow traffic jams on the road. To secure safety and on-time operation of the Bi-modal tram system, well-structured disaster management system capable of analyzing the show pack melt/freezing due to unexpected snowfall are needed. To secure safety of the Bi-modal tram system due to torrential snow-fall, the snow melt simulation capability was investigated. The snow accumulation and snow melt were measured to validate the SWMM snow melt component. It showed that there was a good agreement between measured snow melt data and the simulated ones. Therefore, the Bi-modal tram disaster management system will be able to predict snow melt reasonably well to secure safety of the Bi-modal tram system during the winter. The Bi-modal tram disaster management system can be used to identify top priority area for know removal within the tram route in case of torrential snowfall to secure on-time operation of the tram. Also it can be used for detour route in the tram networks based on the disaster management system prediction.