• Computers and Concrete
• /
• v.34 no.2
• /
• pp.247-265
• /
• 2024

Measuring the fracture toughness of concrete in laboratory settings is challenging due to various factors, such as complex sample preparation procedures, the requirement for precise instruments, potential sample failure, and the brittleness of the samples. Therefore, there is an urgent need to develop innovative and more effective tools to overcome these limitations. Supervised learning methods offer promising solutions. This study introduces seven machine learning algorithms for predicting concrete's effective fracture toughness (K-eff). The models were trained using 560 datasets obtained from the central straight notched Brazilian disc (CSNBD) test. The concrete samples used in the experiments contained micro silica and powdered stone, which are commonly used additives in the construction industry. The study considered six input parameters that affect concrete's K-eff, including concrete type, sample diameter, sample thickness, crack length, force, and angle of initial crack. All the algorithms demonstrated high accuracy on both the training and testing datasets, with R² values ranging from 0.9456 to 0.9999 and root mean squared error (RMSE) values ranging from 0.000004 to 0.009287. After evaluating their performance, the gated recurrent unit (GRU) algorithm showed the highest predictive accuracy. The ranking of the applied models, from highest to lowest performance in predicting the K-eff of concrete, was as follows: GRU, LSTM, RNN, SFL, ELM, LSSVM, and GEP. In conclusion, it is recommended to use supervised learning models, specifically GRU, for precise estimation of concrete's K-eff. This approach allows engineers to save significant time and costs associated with the CSNBD test. This research contributes to the field by introducing a reliable tool for accurately predicting the K-eff of concrete, enabling efficient decision-making in various engineering applications.

• Restorative Dentistry and Endodontics
• /
• v.13 no.2
• /
• pp.337-348
• /
• 1988

The purpose of this study was to examine the fracture strength and characteristics of teeth with MOD cavity preparation. Freshly extracted sound maxillary premolars were cleaned and stored in normal saline solution $37^{\circ}C$ for 72 hours before experiments. The roots of teeth were embedded in a self-curing resin, and the exposed crown were maintained in a vertical position by a modelling wax in a brass ring. The MOD cavities were prepared with No. 57 carbide bur under high speed to a depth of 2.0mm and a width of 2.0mm(Fig.1). All the prepared teeth specimens were divided into 7 groups according to the mode of cavity form and restorative materials (Table 1, 2): Group I, unpreapred, intact teeth as control Group II, prepared cavity without restoration Group III, prepared teeth restored with amalgam Group IV, prepared teeth restored with composite resin (P-10) Group V, prepared teeth with beveled enamel margins restored with composite resin (P-10) Group VI, prepared teeth restored with light-cured composite resin (P-30) Group VII, prepard teeth with beveled enamel margins restored with light-cured composite resin (P-30) After placement of restorations, all of the specimens were stored in water at $37^{\circ}C$ for 72 hours before testing. All of the specimens were tested on the Instron Universal Testing machine (No. 6025) in order to evaluate the strength of fracture. One metal ball 5.0mm in diameter contacting the specimens parallel to the occlusal surface was used to in this study (Fig. 1). The fracture characteristics of the specimens were examined with naked eye and in the scanning electron microscope (JSM-20). The results obtained from this study were as follows: 1. The mean fracture strength was the highest in group VI and that in group II was the lowest. 2. The progress of crack of teeth propagated into the pulp cavity. 3. In case of the group of the restored teeth, the crack occurred to be accompanied with cuspal fracture. 4. The crack of restored teeth was initiated along the pulpo-axial line angle of the cavity.

• Journal of Korean Society of Forest Science
• /
• v.108 no.2
• /
• pp.233-240
• /
• 2019

The aim of this study was to provide basic data that could identify and help prevent a slow-moving landslide using an analysis of the relationship between below-ground characteristics and water from three slow-moving landslide areas in Pohang, Gyeongsangbuk-do, South Korea. Surface surveys, resistivity, seismic exploration, well logging, and boring surveys were conducted in the three areas. The main direction of discontinuous surface was matched with the slope direction of the three landslides. The results indicatedthat slow-moving landslides might occur in the direction of the slope. Underground water was distributed within the crush zones within the three landslide areas and flowed along the tensile cracks. There was a significant difference (p<0.01) between the mean angle of the tensile cracks and that of the underground waterflow (p=0.8019). These results indicated that the progress of a slow-moving landslide can be forecast by monitoring the location and flow of underground water within a known slow-moving landslide area.