• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.1
• /
• pp.47-57
• /
• 1992

Subject of this work is the application of neural networks for the signal(motor noise)recognition systems which detects motor failures and employs different signal(noise). Charaoteristics that re-sult from damaghe part and measure of motor construction during working. The four layers neural networks is applied to this examination. And consists of one input layer, two hidden layers, and one output layer, and learns by the back propagation algorithm.The results of this examination show that it the construction and the output power of the testmotor and learning motor are compatible, the damaged part of the testmotor are detected correctly in the system on the other hand, if the motors have different constrcotion but similar output power each other, mislesding results are obtained in this system.

• Smart Structures and Systems
• /
• v.5 no.4
• /
• pp.317-328
• /
• 2009

Current maintenance operations and integrity checks on a wide array of structures require personnel entry into normally-inaccessible or hazardous areas to perform necessary nondestructive inspections. To gain access for these inspections, structure must be disassembled and removed or personnel must be transported to remote locations. The use of in-situ sensors, coupled with remote interrogation, can be employed to overcome a myriad of inspection impediments stemming from accessibility limitations, complex geometries, the location and depth of hidden damage, and the isolated location of the structure. Furthermore, prevention of unexpected flaw growth and structural failure could be improved if on-board health monitoring systems were used to more regularly assess structural integrity. A research program has been completed to develop and validate Comparative Vacuum Monitoring (CVM) Sensors for surface crack detection. Statistical methods using one-sided tolerance intervals were employed to derive Probability of Detection (POD) levels for a wide array of application scenarios. Multi-year field tests were also conducted to study the deployment and long-term operation of CVM sensors on aircraft. This paper presents the quantitative crack detection capabilities of the CVM sensor, its performance in actual flight environments, and the prospects for structural health monitoring applications on aircraft and other civil structures.

• Nuclear Engineering and Technology
• /
• v.51 no.3
• /
• pp.723-730
• /
• 2019

Acquiring instrumentation signals generated from nuclear power plants (NPPs) is essential to maintain nuclear reactor integrity or to mitigate an abnormal state under normal operating conditions or severe accident circumstances. However, various safety-critical instrumentation signals from NPPs cannot be accurately measured on account of instrument degradation or failure under severe accident circumstances. Reactor vessel (RV) water level, which is an accident monitoring variable directly related to reactor cooling and prevention of core exposure, was predicted by applying a few signals to deep neural networks (DNNs) during severe accidents in NPPs. Signal data were obtained by simulating the postulated loss-of-coolant accidents at hot- and cold-legs, and steam generator tube rupture using modular accident analysis program code as actual NPP accidents rarely happen. To optimize the DNN model for RV water level prediction, a genetic algorithm was used to select the numbers of hidden layers and nodes. The proposed DNN model had a small root mean square error for RV water level prediction, and performed better than the cascaded fuzzy neural network model of the previous study. Consequently, the DNN model is considered to perform well enough to provide supporting information on the RV water level to operators.

• International Journal of Computer Science & Network Security
• /
• v.22 no.2
• /
• pp.232-240
• /
• 2022

To fulfill user expectations, the rapid evolution of software techniques and approaches has necessitated reliable and flawless software operations. Aging prediction in the software under operation is becoming a basic and unavoidable requirement for ensuring the systems' availability, reliability, and operations. In this paper, an improved evolutionary computing-driven extreme learning scheme (ECD-ELM) has been suggested for object-oriented software aging prediction. To perform aging prediction, we employed a variety of metrics, including program size, McCube complexity metrics, Halstead metrics, runtime failure event metrics, and some unique aging-related metrics (ARM). In our suggested paradigm, extracting OOP software metrics is done after pre-processing, which includes outlier detection and normalization. This technique improved our proposed system's ability to deal with instances with unbalanced biases and metrics. Further, different dimensional reduction and feature selection algorithms such as principal component analysis (PCA), linear discriminant analysis (LDA), and T-Test analysis have been applied. We have suggested a single hidden layer multi-feed forward neural network (SL-MFNN) based ELM, where an adaptive genetic algorithm (AGA) has been applied to estimate the weight and bias parameters for ELM learning. Unlike the traditional neural networks model, the implementation of GA-based ELM with LDA feature selection has outperformed other aging prediction approaches in terms of prediction accuracy, precision, recall, and F-measure. The results affirm that the implementation of outlier detection, normalization of imbalanced metrics, LDA-based feature selection, and GA-based ELM can be the reliable solution for object-oriented software aging prediction.

• International Journal of Korean Welding Society
• /
• v.1 no.2
• /
• pp.51-60
• /
• 2001

A prediction method for determining the welding residual stress by artificial neural network is proposed. A three-dimensional transient thermo-mechanical analysis has been performed for the $CO_2$ arc welding using the finite element method. The first part of numerical analysis performs a three-dimensional transient heat transfer analysis, and the second part then uses the results of the first part and performs a three-dimensional transient thermo-elastic-plastic analysis to compute transient and residual stresses in the weld. Data from the finite element method are used to train a back propagation neural network to predict the residual stress. Architecturally, the fully interconnected network consists of an input layer for the voltage and current, a hidden layer to accommodate the failure mechanism mapping, and an output layer for the residual stress. The trained network is then applied to the prediction of residual stress in the four specimens. It is concluded that the accuracy of the neural network predicting method is fully comparable with the accuracy achieved by the traditional predicting method.

• Industry Promotion Research
• /
• v.8 no.3
• /
• pp.153-162
• /
• 2023

Shen-Xiao-Zhan's 『Zi-Ping-Zhen-Quan』, which is called a commentary on Chart-Structure in MyungLiollgy, After selecting the Chart-Structure and classifying the good luck and bad luck of the case, the Phase-usage is set up according to the principle of Shun reverse. At this time, if two or more the sky symbol hidden in the ground of Monthly intertwine to form several Structure and become Adjunct-Structure, the subject of Structure must be finally known to set up Phase-usage and succeed Structure and failure can be judged. However, in 『Zi-Ping-Zhen-Quan』, only the structure and meaning of Adjunct-Structure were explained, and the method of determining the final subject of Adjunct-Structure was not described. This researcher reviewed various literatures for a study on selecting the subject of Adjunct-Structure, and compared and analyzed various actual cases of Adjunct-Structure by dividing them into Monthly and Chart-Structure. Common results related to the type of sign of the land that met with Monthly, the energy force of the sky sign projected from the sky symbol hidden underground in Monthly and the strength and weakness of the body were drawn. and the law was organized subjectively. It is believed that the results of this study will serve as an opportunity to reduce the confusion of Adjunct-Structure.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.6
• /
• pp.374-382
• /
• 2020

The purpose of this study is to improve the learning speed of an ammunition stockpile reliability classification artificial neural network model by proposing a normalization method that reduces the number of input variables based on the characteristic of Ammunition Stockpile Reliability Program (ASRP) data without loss of classification performance. Ammunition's performance requirements are specified in the Korea Defense Specification (KDS) and Ammunition Stockpile reliability Test Procedure (ASTP). Based on the characteristic of the ASRP data, input variables can be normalized to estimate the lot percent nonconforming or failure rate. To maintain the unitary hypercube condition of the input variables, min-max normalization method is also used. Area Under the ROC Curve (AUC) of general min-max normalization and proposed 2-step normalization is over 0.95 and speed-up for marching learning based on ASRP field data is improved 1.74 ~ 1.99 times depending on the numbers of training data and of hidden layer's node.

• Journal of Korean Foot and Ankle Society
• /
• v.8 no.1
• /
• pp.86-91
• /
• 2004

Purpose: To evaluate the methods and results of the surgical treatment in the trimalleolar fracture of the ankle. Materials and Methods: We analysed the results of the ankle trimalleolar fracture which were treated with open reduction and internal fixation from January 1999 till September 2003. There were 45 patients who had at least six months follow up, 16 men, and 29 women. We have analysed the mechanism of injury, methods of operation and postoperative complications. Results: The results were assessed on ankle AP, lateral and mortise X-rays and retrospective chart review. There were 30 supination-external rotation, 13 pronation-external rotation, 2 pronation-abduction in the mechanism of injury by Lauge-Hansen classification. Cases of the posterior malleolar fracture which involved more than 25% of the weight bearing surface were 7 (15.6%). Medial malleolar mono-fixation was done in 5 cases, fibular mono-fixation in 2 cases, bimalleolar fixation in 32 cases, trimalleolar fixation in 6 cases. 38 cases (84.4%) were good or excellent in clincal assessment and 39 cases (86.7%) were good or excellent in radiological assessment according to the criteria of the Meyer. There was no difference of results among the surgical treatment methods. Conclusion: The results of our study indicate that the rigid fixation with early ankle motion and weight bearing is needed in ankle trimalleolar fracture. But minimal fixation is not bad in slight displaced fracture. Both anterior approach and posterior approach were useful methods to stabilization the posterior malleolar fracture. And pre-operative evaluation to detect the hidden soft tissue injuries and fracture mechanism is very important to avoid the failure.

• Advances in aircraft and spacecraft science
• /
• v.4 no.5
• /
• pp.515-528
• /
• 2017

Since composite structures are widely used in structural engineering, delamination in such structures is an important issue of research. Delamination is one of a principal cause of failure in composites. In This study the electrical potential (EP) technique is applied to detect and locate delamination in basalt fiber reinforced polymer (FRP) laminate composite pipe by using electrical capacitance sensor (ECS). The proposed EP method is able to identify and localize hidden delamination inside composite layers without overlapping with other method data accumulated to achieve an overall identification of the delamination location/size in a composite, with high accuracy, easy and low-cost. Twelve electrodes are mounted on the outer surface of the pipe. Afterwards, the delamination is introduced into between the three layers (0º/90º/0º)s laminates pipe, split into twelve scenarios. The dielectric properties change in basalt FRP pipe is measured before and after delamination occurred using arrays of electrical contacts and the variation in capacitance values, capacitance change and node potential distribution are analyzed. Using these changes in electrical potential due to delamination, a finite element simulation model for delamination location/size detection is generated by ANSYS and MATLAB, which are combined to simulate sensor characteristic. Response surfaces method (RSM) are adopted as a tool for solving inverse problems to estimate delamination location/size from the measured electrical potential changes of all segments between electrodes. The results show good convergence between the finite element model (FEM) and estimated results. Also the results indicate that the proposed method successfully assesses the delamination location/size for basalt FRP laminate composite pipes. The illustrated results are in excellent agreement with the experimental results available in the literature, thus validating the accuracy and reliability of the proposed technique.

• Clinical and Experimental Pediatrics
• /
• v.54 no.5
• /
• pp.212-218
• /
• 2011

Purpose: The diagnosis of acute pyelonephritis (APN) is often difficult, as its clinical and biological manifestations are non-specific in children. If not treated quickly and adequately, however, APN may cause irreversible renal damage, possibly leading to hypertension and chronic renal failure. We were suspecting the diagnostic value of $^{99m}Tc$-dimercaptosuccinic acid (DMSA) scan by experiences and so compared the results of DMSA scan to those of multi-detector row computed tomography (MDCT). Methods: We retrospectively selected and analyzed 81 patients who were diagnosed as APN by MDCT during evaluation of their acute abdomen in emergency room and then received DMSA scan also for the diagnostic work-up of APN after admission. We evaluated the results of imaging studies and compared the diagnostic value of each method by age groups, <2 years (n=45) and ${\geq}$2 years (n=36). Results: Among total 81 patients with MDCT-proven APN, DMSA scan was diagnostic only in 55 children (68%), while the remaining 26 children (32%) showed false negative normal findings. These 26 patients were predominantly male and most of them, 19 (73.1%) were <2 years of age. Conclusion: DMSA scan holds obvious limitation compared to MDCT in depicting acute inflammatory lesions of kidney in children with APN, especially in early childhood less than 2 years of age. MDCT showed hidden lesions of APN, those were undetectable through DMSA scan in children.