• Journal of the Korea Safety Management & Science
• /
• v.23 no.4
• /
• pp.93-104
• /
• 2021

In this paper, we propose a method for diagnosing overload and working load of collaborative robots through performance analysis of machine learning algorithms. To this end, an experiment was conducted to perform pick & place operation while changing the payload weight of a cooperative robot with a payload capacity of 10 kg. In this experiment, motor torque, position, and speed data generated from the robot controller were collected, and as a result of t-test and f-test, different characteristics were found for each weight based on a payload of 10 kg. In addition, to predict overload and working load from the collected data, machine learning algorithms such as Neural Network, Decision Tree, Random Forest, and Gradient Boosting models were used for experiments. As a result of the experiment, the neural network with more than 99.6% of explanatory power showed the best performance in prediction and classification. The practical contribution of the proposed study is that it suggests a method to collect data required for analysis from the robot without attaching additional sensors to the collaborative robot and the usefulness of a machine learning algorithm for diagnosing robot overload and working load.

• Ocean Systems Engineering
• /
• v.13 no.1
• /
• pp.43-55
• /
• 2023

In this study, the SCFs in tubular T-joints stiffened with external ring under axial load are studied and discussed. After verification of the present numerical model with the results of several available experimental tests, 156 FE models were generated and analyzed to parametrically evaluate the effect of the joint geometry and the ring geometry on the SCFs. Results indicated that the SCF of the stiffened T-joints at crown point can be down to 24% of the SCF of the corresponding un-reinforced joint at the same point. Also, the effect of the ring on the SCF at saddle point is more remarkable than the effect of the ring on the SCF at crown point. Moreover, against un-reinforced joints under axial load, the SCF at saddle point of the stiffened joint is smaller than the SCF at crown point of that stiffened joint. The ring results in the redistribution of stresses in the ring and metal substrate. Also, the effect of the ring thickness on the decrease of the SCFs is slight and can be ignored. In final step, the geometric parameters affecting the SCFs of the stiffened T-joints are analyzed by multiple nonlinear regression analyses. An accurate formula is proposed for determining the SCFs.

• Computers and Concrete
• /
• v.33 no.3
• /
• pp.285-299
• /
• 2024

Recently, many engineering computations have realized their digital transformation to Machine Learning (ML)-based systems. Predicting the behavior of a structure, which is mainly computed with structural analysis software, is an essential step before construction for efficient structural analysis. Especially in the seismic-based design procedure of the structures, predicting the lateral load capacity of reinforced concrete (RC) columns is a vital factor. In this study, a novel ML-based model is proposed to predict the maximum lateral load capacity of RC columns under varying axial loads or cyclic loadings. The proposed model is generated with a Deep Neural Network (DNN) and compared with traditional ML techniques as well as a popular commercial structural analysis software. In the design and test phases of the proposed model, 319 columns with rectangular and square cross-sections are incorporated. In this study, 33 parameters are used to predict the maximum lateral load capacity of each RC column. While some traditional ML techniques perform better prediction than the compared commercial software, the proposed DNN model provides the best prediction results within the analysis. The experimental results reveal the fact that the performance of the proposed DNN model can definitely be used for other engineering purposes as well.

• Journal of Korean Society on Water Environment
• /
• v.34 no.1
• /
• pp.33-45
• /
• 2018

In this study, we discussed the application of Watershed model and Load Duration Curves (LDC) in Total Water Load Management System. The Flow Duration Curves (FDC) and the LDC were generated using the results of the daily HSPF model and analyzed on monthly or yearly flow duration variability, and non-point pollutant discharge loads by entire flow conditions. As a result of the calibration and verification of the HSPF model, both the flow and the water quality were appropriately simulated. The simulated values were used to generate the Flow Duration Curve and the Load Duration Curve, and then the excess rate by entire flow conditions was analyzed. The point and non-point pollutant discharge loads for entire flow conditions were calculated. It is possible to evaluate the variability of water quality in specific flow duration through the curves reflecting the flow duration variability and to confirm the characteristics of the pollutant source. For a more scientific Total Water Load Management System, it is necessary to switch from a current system to a system that can take into account the entire flow conditions. For this, the application of the watershed model and load duration curve is considered to be the best alternative.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.8
• /
• pp.535-544
• /
• 2018

As the spread of mobile devices equipped with various sensors and high-quality wireless network communications functionsexpands, the amount of spatio-temporal data generated from mobile devices in various service fields is rapidly increasing. In conventional research into processing a large amount of real-time spatio-temporal streams, it is very difficult to apply a Hadoop-based spatial big data system, designed to be a batch processing platform, to a real-time service for spatio-temporal data streams. This paper extends the MapReduce online framework to support real-time query processing for continuous-input, spatio-temporal data streams, and proposes a load management method to distribute overloads for efficient query processing. The proposed scheme shows a dynamic load balancing method for the nodes based on the inflow rate and the load factor of the input data based on the space partition. Experiments show that it is possible to support efficient query processing by distributing the spatial data stream in the corresponding area to the shared resources when load management in a specific area is required.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.29 no.8
• /
• pp.419-428
• /
• 2017

In this study, energy loss due to ventilation load in the dock system was analyzed through simulation. Also, flow generated in the dock system of the warehouse was measured using manufactured measuring devices. Numerical simulation was conducted by simulating the most common picking tasks by examining the actual working environment. Incompressible and unsteady turbulent flows were assumed, and the turbulence model was the k-e standard model. Proper grid was selected through grid dependency test. Measurement was conducted using Honeywell and Vaisala sensors, and flow and temperature inside the warehouse were measured and compared with simulation results to validate simulation. When comparing amount of loss occurring in two hours and amount of loss occurring in 15 minutes, docking time of the former was eight times longer but energy loss was 3.8 times lower. Ventilation load occurring during the initial period after opening docking system accounted for a large proportion of total ventilation load. Also, comparing the load when the dock was closed and the load when the truck was parked, ventilation load was significantly higher than load due to heat conduction from the wall. Therefore, in improving the docking system, it is effective to reduce the gap by improving compatibility of the docking system and truck, rather than wall material.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.1
• /
• pp.83-88
• /
• 2013

Progressive collapse is a chain reaction of failures propagating throughout a portion of a structure that is disproportionate to the original local failure. When column members are subjected to unexpected load (compression load), they will buckle if the applied load is greater than the critical load that induces buckling. The post-buckling strength of the columns will decrease rapidly, but if there is enough residual strength, the members will absorb the potential energy generated by the impact load to prevent progressive collapse. Thus, it is necessary to identify the relationship of the load-deformation of a column member in the progressive collapse of a structure up to final collapse. In this study, we carried out nonlinear FEM analysis and based on deflection theory, we investigated the load-deformation relationship of H-section steel columns when both ends were fixed.

• Journal of Korean Society of Steel Construction
• /
• v.12 no.3 s.46
• /
• pp.269-279
• /
• 2000

It is much expected that steel bridges, which have been damaged by increase of vehicle load and corrosion, need repair or strengthening. In this paper, the stress generated by repair welding under loading are analyzed by three dimensional elasto-plastic analyses. The longer and deeper repair weld line bocemes, the larger the magnitude of transient stress becomes. The magnitude of transient stress generated by repair welding under loading $({\sigma}_y/3,\;{\sigma}_a)$ is similar to summation of stresses generated by repair welding and loading. The longer repair weld line ratio(1/b) becomes, the larger the magnitude of transient stress generated by repair welding under loading bocomes. And, the longer repair weld line ratio(1/b) becomes, the larger the magnitude of in-plane displacement generated by repair welding under loading$({\sigma}_y/3,\;{\sigma}_a)$.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.1
• /
• pp.60-71
• /
• 2019

Electrical power supply is needed to operate the radar system in the field. In addition, it should not cause performance deterioration under the environmental factors due to characteristics of military equipment, and should not cause malfunction due to electromagnetic waves generated in radar, and then should not cause malfunction in radar equipment. Therefore, By applying a permanent magnet to the rotor of the generator, light weighting and high efficiency of generator were achieved. As a result, electrical performance test of the generator, the rated output power was 80.8 kW, the maximum output power was 88.1 kW, and the output power efficiency was 98.1 % under the full load condition. When the load capacity of the generator was changed from no load to full load, the maximum voltage variation was 3.6 % and the frequency variation was 0.3 %. As a result of the transient response test for measuring the output power of the generator according to the load characteristics change, the maximum voltage variation of 7.9 %, frequency variation of 0.5 % were confirmed, and the transient response time was 2.1 seconds. Environmental tests were conducted in accordance with MIL-STD-810G and MIL-STD-461F to evaluate the operability of the generator groups. Normal operation of radar system generator group was confirmed under high temperature and low temperature environment conditions. Electromagnetic tests were conducted to check if electromagnetic wave generated from both radar system and generator group in operation caused any performance deterioration to each other. As a result, it was confirmed that the performance deterioration due to electromagnetic wave inflow, radiation, and conduction did not occur. It is expected that it should be possible to provide high efficiency power supply and stable power supply by applying to various military system as well as radar system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.205-209
• /
• 2015

The economic losses resulted from the accident in the power cables at the power station is not only huge but also requires a great amount of time and expenses to restore to the former condition. In order to prevent these, it is necessary to invent and apply a technique to expect and prevent the accidents. In order to measure insulation resistances of power cables in operation, we derived the relations between load current and temperature. By analyzing data obtained from our measuring equipments, we showed the expected time to change deteriorated cables before accident occurs. We present a result of our study on the effects of the load current on lifetime of 6.6 kV cable systems in operation. With the current flowing through the load of the cable a heat is generated reducing the lifetime of the cable. In order to find out the effect of load current on the lifetime of cable systems, we applied the lifetime theory to the development of two equipments to measure insulation resistance and current of cable systems in operation.