• Journal of Korean Neurosurgical Society
• /
• 제66권1호
• /
• pp.53-62
• /
• 2023

Objective : Deep learning is a machine learning approach based on artificial neural network training, and object detection algorithm using deep learning is used as the most powerful tool in image analysis. We analyzed and evaluated the diagnostic performance of a deep learning algorithm to identify skull fractures in plain radiographic images and investigated its clinical applicability. Methods : A total of 2026 plain radiographic images of the skull (fracture, 991; normal, 1035) were obtained from 741 patients. The RetinaNet architecture was used as a deep learning model. Precision, recall, and average precision were measured to evaluate the deep learning algorithm's diagnostic performance. Results : In ResNet-152, the average precision for intersection over union (IOU) 0.1, 0.3, and 0.5, were 0.7240, 0.6698, and 0.3687, respectively. When the intersection over union (IOU) and confidence threshold were 0.1, the precision was 0.7292, and the recall was 0.7650. When the IOU threshold was 0.1, and the confidence threshold was 0.6, the true and false rates were 82.9% and 17.1%, respectively. There were significant differences in the true/false and false-positive/false-negative ratios between the anterior-posterior, towne, and both lateral views (p=0.032 and p=0.003). Objects detected in false positives had vascular grooves and suture lines. In false negatives, the detection performance of the diastatic fractures, fractures crossing the suture line, and fractures around the vascular grooves and orbit was poor. Conclusion : The object detection algorithm applied with deep learning is expected to be a valuable tool in diagnosing skull fractures.

• 대한기계학회논문집A
• /
• 제24권2호
• /
• pp.386-393
• /
• 2000

Fracture mechanics analysis (FMA) is an essential work for integrity evaluation of nuclear power plant. The flaws inspected by In-Service Inspection(ISI) should be confirmed by FMA for the decision of the operation status of stop or continuance. The basic data for FMA are the stress of the interested area. The purpose of this research is to develop a system which can obtain stress data efficiently based on various database. Mesh generation program generates mesh using MSC/PATRAN and provides input file for finite element analysis according to the databases (shape, dimension, transient and material). The stress data from the finite element analysis are stored to be stress database so that it can be applied to FMA. As an example, the system developed by this study is applied to pressurizer nozzle and confirmed to be a useful tool for efficient FMA.

• 대한기계학회논문집A
• /
• 제24권4호
• /
• pp.955-962
• /
• 2000

Scanning Probe Microscope (SPM) such as Scanning Tunneling Microscope (STM) and Atomic Force Microscope (AFM) was shown to be the powerful tool for nano-scale characterization of a fracture surface . AFM was used to study cross sectional profiles and dimensions of fatigue striations in 2017-T351 aluminum alloy. Their widths (SW) and heights (SH) were measured from the cross sectional profiles of three-dimension AFM images. The following results that will be helpful to understand the fatigue crack growth mechanism were obtained. (1) Coincidence of the crack growth rate with the striation width was found down to the growth rate of 10-5 mm/cycle. (2) The relation of SH=0.085(SW)1.2 was obtained. (3) The ratio of the striation height to its width SH/SW did not depend on the stress intensity factor range K and the stress ratio R. (4) Not only the SW but also the SH changed linearly with the crack tip opening displacement (CTOD) when plotted in log-log scale. From these results, the applicability of the AFM to nano-fractography is discussed.

• Clinics in Shoulder and Elbow
• /
• 제7권1호
• /
• pp.14-22
• /
• 2004

Purpose: To evaluate a usefulness of the simple radiograph in the patients with chronic shoulder pain 50 years and older. Material and method: 1152 patients with chronic shoulder pain and 100 asymptomatic individuals were involved in this study. All patients were 50 years and older. We excluded patients who had a history of fracture or dislocation. Radiographic interpretation was performed on a shoulder AP view, an axillary view and a supraspinatus outlet view. For statistical analysis, a chi-square test was performed. A p value of <0.05 was considered statistically significant. Results: Abnormal radiologic findings were identified in 369(32%) out of 1152 patients with a shoulder pain: greater tuberosity sclerosis, acromial sclerosis, subacromial osteophytes are common abnormal radiologic findings. A rotator cuff tear or impingement syndrome was identified on a final diagnosis in 61(85.2%) out of the 76 patients with radiologic abnormalities in both greater tuberosity and acromion (p<0.05). Abnormal radiologic findings were identified in 18% of the asymptomatic individuals. Conclusion: Simple radiographic analysis is an important primary diagnostic tool in patients (50 years and old) with chronic shoulder pain.

• 대한기계학회논문집A
• /
• 제24권6호
• /
• pp.1616-1623
• /
• 2000

A diaphragm spring is an important component of a clutch assembly, characteristics of which depends largely on that of a diaphragm spring. A diaphragm spring is subject to high stress concentration in driving condition, which frequently causes cracks and fracture around finger area. In this paper, behavior of a diaphragm spring is analysed by finite element method to calculate sensitivity of design parameters, which is used to perform optimal design of diaphragm spring shape. As an object function, hoop stresses are taken and minimized to improve durability. Characteristics of the diaphragm is used as equality constraint to maintain the original design purpose and sequential linear programming(SLP) is utilized as an optimization tool. With optimized design, it is verified that concentrated stress is decreased maintaining release load characteristic.

• 한국공작기계학회논문집
• /
• 제14권3호
• /
• pp.87-95
• /
• 2005

The object of this study is to investigate the effect of joinability by using acoustic emission(AE) signals and doing a pattern recognition for weld heat affected zone(HAZ) in tensile testing. This study was carried out an SWS 490A high tension steel for electric shielded metal arc welding(SMAW), $CO_2$ gas arc welding and TIG welding. And correspondingly, the root openings are 3, 4 and 2.8mm. The results of the tensile test of weld HAZ come out electric shield arc welding $>\;CO_2$ gas arc welding > TIG welding in case of single welding. It is believed that this is a phenomenon where difference of its root opening or base metal thickness. Also, the technique of AE is ideally suited to study variables which control time and stress dependent fracture or damage process in metallic materials.

• 한국공작기계학회논문집
• /
• 제13권4호
• /
• pp.16-22
• /
• 2004

Shape optimization was performed to obtain the precise shape of cutouts including the internal shape of cutouts in laminated composite plates by three dimensional modeling using solid element. The volume control of the growth-strain method was implemented and the distributed parameter chosen as Tsai-Hill fracture index for shape optimization. The volume control of the growth-strain method makes Tsai-Hill failure index at each element uniform in laminated composites under the initial volume. Then shapes optimized by Tsai-Hill failure index were compared with those of the initial shapes for the various load conditions and cutouts. The following conclusions were obtained in this study (1) It was found that growth-strain method was applied efficiently to shape optimization of three dimensional cutouts in a laminated composite plate, (2) The optimal shapes on the various load conditions and cutouts were obtained, (3) The maximum Tsai-Hill failure index was reduced up to 67% when shape optimization was performed under the initial volume by volume control of growth-strain method.

• 한국공작기계학회논문집
• /
• 제15권5호
• /
• pp.104-113
• /
• 2006

The main objective of this study is to investigate the effect of compounded welding by using acoustic emission (AE) signals and doing a source location for weld heat affected zone (HAZ) through tensile testing. This study was carried out an SWS 490A high strength steel for electric shield metal arc welding, SMAW; $CO_2$ gas metal arc welding, GMAW($CO_2$); and gas tungsten arc welding, GTAW/TIG. Data displays are based on the measured parameters of the AE signals, along with environmental variables such as time and load. For instance, Gutenberg-Richter magnitude-frequency relationship (G-R MFR) offers useful b-value in data analysis. Namely event identification, source location gives the X- and Y-coordinates of the AE source. And K-means clustering analysis by Euclidean distance confirmed that was powerful to source location. Generally, strength of welded metal zone was stronger than strength of base metal. As the result, confirmed certainly that fracture is produced in HAZ instead of welded metal zone from source location.

• 한국생산제조학회지
• /
• 제26권4호
• /
• pp.378-386
• /
• 2017

Friction stir welding was performed using six welding conditions to evaluate the mechanical properties and microstructure of the welded zone based on its temperature change in the extruded plate of magnesium alloy AZ61. The welded zone temperature was measured using a thermocouple, and the maximum temperature ranges for the advancing and retreating sides were approximately $210-315^{\circ}C$ and $254-339^{\circ}C$, respectively. Depending on the welding conditions, a temperature difference of more than $100^{\circ}C$ was observed. In addition, the maximum yield strength and maximum tensile strength of the welded component was 84.4% and 96.9%, respectively, of those of the base material. For the temperatures exceeding $300^{\circ}C$, oxidation defects occurred in the weld zone, which decreased the mechanical strength of the weld zone. The microstructure and texture confirmed that fracture occurred because of the grain size deviation of the welding tool and the severe anisotropy of the texture of the welded joints.

• 한국압력기기공학회 논문집
• /
• 제9권1호
• /
• pp.62-69
• /
• 2013

A probabilistic assessment code, PRO-LOCA ver. 3.7 which was developed in an international co-operative research program, PARTRIDGE was evaluated by conducting sensitivity analysis. The effect of some variables such as simulation methods (adaptive sampling, iteration numbers, weld residual stress model), crack features(Poisson's arrival rate, maximum numbers of cracks, initial flaw size, fabrication flaws), operating and loading conditions(temperature, primary bending stress, earthquake strength and frequency), and inspection model(inspection intervals, detectable leak rate) on the failure probabilities of a surge line nozzle was investigated. The results of sensitivity analysis shows the remaining problems of the PRO-LOCA code such as the instability of adaptive sampling and unexpected trend of failure probabilities at an early stage.