• Design & Manufacturing
• /
• v.16 no.4
• /
• pp.1-6
• /
• 2022

Fine blanking is a press processing technology that can process most of the product thickness into a smooth surface with a single stroke. In this fine blanking process, shear is an essential step. The punches and dies used in the shear are subjected to impacts of tens to hundreds of gravitational accelerations, depending on the type and thickness of the material. Therefore, among the components of the fine blanking mold (dies), punches and dies are the parts with the shortest lifespan. In the actual production site, various types of tool damage occur such as wear of the tool as well as sudden punch breakage. In this study, machine learning algorithms were used to predict these problems in advance. The dataset used in this paper consisted of the signal of the vibration sensor installed in the tool and the measured burr size (tool wear). Various features were extracted so that artificial intelligence can learn effectively from signals. It was trained with 5 features with excellent distinguishing performance, and the SVM algorithm performance was the best among 33 learning models. As a result of the research, the vibration signal at the time of imminent tool replacement was matched with an accuracy of more than 85%. It is expected that the results of this research will solve problems such as tool damage due to accidental punch breakage at the production site, and increase in maintenance costs due to prediction errors in punch exchange cycles due to wear.

• Transactions of Materials Processing
• /
• v.22 no.4
• /
• pp.204-215
• /
• 2013

As a pressure vessel, a small seamless aluminum liner with inner volume of about 6.75L is made from an initial billet material of AA6061-O. To produce the aluminum liner, warm forging including backward extrusion and head nosing was numerically simulated using a billet initially pre-heated to about $480^{\circ}C$. Compression tests on the billet material were performed at various temperatures and strain rates, and the measured mechanical properties were used in the numerical simulations. For the backward extrusion and the head nosing, the tool geometries were designed based on the desired configuration of the aluminum liner. Furthermore, the structural integrity of the tooling was evaluated to ensure adequate tool life. The seamless aluminum liner has an endurance limit of about 1.47MPa ($15Kg_f/cm^2$), estimated based on the required inner pressure. The results confirm that the small seamless aluminum liner of AA6061-O can be successfully made by using the two stage warm forging procedures without any bursting failures.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.14 no.10
• /
• pp.854-862
• /
• 2002

In the previous research, a simplified correlation method was developed as an easy prediction tool for comparing energy use of cooling plants. The purpose of this paper is to test the applicability of this method for economic evaluation with two zones of a 20-story commercial building in Seoul. The results of this method were compared with the DOE-2 simulation and actual measured data. Then, Comparisons of life cycle cost were carried out for three types of cooling plants. Testing of one zone showed good agreement of within 10% error in cooling energy use and within 2% error in LCC. But testing of the other zone indicated that the use of this method were invalid when input variables were used beyond its valid range.

• Interdisciplinary Bio Central
• /
• v.4 no.1
• /
• pp.2.1-2.7
• /
• 2012

Introduction: Histone deacetylases (HDAC) are a class of enzymes that remove acetyl groups from ${\varepsilon}$-N-acetyl lysine amino acids of histone proteins. Their action is opposite to that of histone acetyltransferase that adds acetyl groups to these lysines. Only few HDAC inhibitors are approved and used as anti-cancer therapeutics. Thus, discovery of new and potential HDAC inhibitors are necessary in the effective treatment of cancer. Materials and Methods: This study proposed a method using support vector machine (SVM) to classify HDAC8 inhibitors and non-inhibitors in early-phase virtual compound filtering and screening. The 100 experimentally known HDAC8 inhibitors including 52 inhibitors and 48 non-inhibitors were used in this study. A set of molecular descriptors was calculated for all compounds in the dataset using ADRIANA. Code of Molecular Networks. Different kernel functions available from SVM Tools of free support vector machine software and training and test sets of varying size were used in model generation and validation. Results and Conclusion: The best model obtained using kernel functions has shown 75% of accuracy on test set prediction. The other models have also displayed good prediction over the test set compounds. The results of this study can be used as simple and effective filters in the drug discovery process.

• Journal of agriculture & life science
• /
• v.46 no.3
• /
• pp.47-58
• /
• 2012

This study was carried out to develop assessment model for the optimal site prediction of Dendropanax morbifera, Evergreen broad-leaved trees in warm temperate zone according to climate change. It was created criterion for assessment model of the optimal site prediction by quantification method to possible analysis of quantitative and qualitative data, through study relationship between growth of tree and site environmental factors. A program of the optimal site prediction was developed using program version 3.2, an Avenue and Dialog Designer tool of ESRI as GIS(geographic information system) engine. Developed program applied to test accuracy of the optimal site prediction in study area of Wando, Jeollanam-do, having a various evergreen broad-leaved trees of warm temperate zone. In the results from analysis of the optimal site prediction on Dendropanax morbifera, the characteristics of optimal site were analyzed site environmental features with 401~500m of altitude, $15^{\circ}$ of slope, hillside of local topography, alluvium of deposit type, convex of slope type and south of aspect. The mapping area per grade of the optimal site prediction in the Dendropanax morbifera showed 1,487.2ha(25.4%) of class I, 1,020.3ha(17.4%) of class II, 2,231.8ha(38.2%) of class III and 1,110.5ha(19.0%) of class IV.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.4
• /
• pp.558-564
• /
• 2021

With the recent introduction of 5G, electromagnetic radiation sources are spreading throughout life, so it is necessary to establish a citizen-centered electromagnetic safety management system. In particular, the beamforming method of the 5G antenna increases the power density measurement of electromagnetic waves by more than 10 times when the wireless base station is installed, so it is unreasonable to determine the safety by physical measurement. Therefore, it is necessary to determine the presence or absence of electromagnetic wave safety in daily life through a predictive method by calculation through systematic model analysis. In this paper, in order to check the possibility of a 5G wireless base station using an electromagnetic wave numerical analysis tool as a way to solve this problem, we compared the measured values of the actual base stations and the predicted values through the prediction model to compare the reliability. A method of constructing a real-time base station electromagnetic wave strength prediction evaluation system combined with software was also proposed.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.13 no.6
• /
• pp.94-101
• /
• 2004

The purpose of this raper is to assess the benefits of frequency domain fatigue analysis and compare it with more conventional time domain techniques. The multi-body dynamic analysis, FE analysis and fatigue life prediction technique are applied for the frequency domain fatigue analysis. To obtain the dynamic load history used in the frequency domain fatigue analysis, the computer simulations running over typical road Profiles are carried out by utilizing vehicle dynamic model. The fatigue life estimation for the rear suspension system of small-sized passenger car is performed by using resonance durability analysis technique, and the estimation results are compared with the conventional quasi-static durability analysis results. For the pothole simulation, the percent changes, of the fatigue life between the two durability analysis techniques don't exceed 10%. But for the Belgian road simulation because of the resonance effect, the fatigue life using the resonance durability analysis technique are much smaller estimated than the quasi-static durability analysis results.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.553-581
• /
• 2022

Shortly after tunnel boring machine (TBM) was introduced in the tunneling industry, the use of TBM has surprisingly increased worldwide due to its performance together with the benefit of being safely and environmentally friendly. One of the main cost items in the TBM tunneling in rock and soil is changing damaged or worn cutters. It is because that the cutter change is a time-consuming and costly activity that can significantly reduce the TBM utilization and advance rate and has a major effect on the total time and cost of TBM tunneling projects. Therefore, the importance of accurately evaluating the cutter life can never be overemphasized. However, the prediction of cutter wear in soil, rock including mixed face is very complex and not yet fully clarified, subsequently keeping engineers busy around the world. Various prediction models for cutter wear have been developed and introduced, but these models almost usually produce highly variable results due to inherent uncertainties in the models. In this study, a case study of design and construction of disc cutter change is introduced and analyzed, rather than proposing a prediction model of cutter wear. As the disc cutter is strongly affected by the geological condition, TBM machine characteristic and operation, authors believe it is very hard to suggest a generalized prediction model given the uncertainties and limitations therefore it would be more practical to analyze a real case and provide a detailed discussion of the difference between prediction and result for the cutter change. By doing so, up-to-date idea about planning and execution of cutter change in practice can be promoted.

• Advances in aircraft and spacecraft science
• /
• v.4 no.1
• /
• pp.1-19
• /
• 2017

Fatigue life prediction of a multi-row countersunk riveted lap joint was performed numerically. The stress and strain conditions in a highly stressed substructure of the joint were analysed using a global/local finite element (FE) model coupling approach. After validation of the FE models using experimental strain measurements, the stress/strain condition in the local three-dimensional (3D) FE model was simulated under a fatigue loading condition. This local model involved multiple load cases with nonlinearity in material properties, geometric deformation, and contact boundary conditions. The resulting stresses and strains were used in the Smith-Watson-Topper (SWT) strain life equation to assess the fatigue "initiation life", defined as the life to a 0.5 mm deep crack. Effects of the rivet-hole clearance and rivet head deformation on the predicted fatigue life were identified, and good agreement in the fatigue life was obtained between the experimental and the numerical results. Further crack growth from a 0.5 mm crack to the first linkup of two adjacent cracks was evaluated using the NRC in-house tool, CanGROW. Good correlation in the fatigue life was also obtained between the experimental result and the crack growth analysis. The study shows that the selected methodology is promising for assessing the fatigue life for the lap joint, which is expected to improve research efficiency by reducing test quantity and cost.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.14 no.6
• /
• pp.17-23
• /
• 2006

Rubber materials have the nonlinear, large deformation and viscoelastic behavior. W.D. Kim et al. studied these characteristics through the static, fatigue, dynamic, aging and viscoelastic test. This paper discussed that the properties of engine mounting rubber, such as static stiffness, fatigue life and damping factor, are predicted based on CAE by using material properties acquired by the report of Kim et al. In result, the static stiffness of engine mounting rubber is predicted approximately in comparison with test value. Also, it was confirmed that the relationship of fatigue life and Green-Lagrange strain in specimen was the valid tool to predict the fatigue life of engine mounting rubber. From the results of transient viscoelastic analysis the damping factor changed rapidly at the range less than 8hz.