• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.1
• /
• pp.171-177
• /
• 2021

In terms of distribution planning, accurate electric load prediction is one of the most important factors. The future load prediction has manually been performed by calculating the maximum electric load considering loads transfer/switching and multiplying it with the load increase rate. In here, the risk of human error is inherent and thus an automated maximum electric load forecasting system is required. Although there are many existing methods and techniques to predict future electric loads, such as regression analysis, many of them have limitations in reflecting the nonlinear characteristics of the electric load and the complexity due to Photovoltaics (PVs), Electric Vehicles (EVs), and etc. This study, therefore, proposes a method of predicting future electric loads on distribution lines by using Machine Learning (ML) method that can reflect the characteristics of these nonlinearities. In addition, predictive models were developed based on actual data collected at KEPCO's existing distribution lines and the adequacy of developed models was verified as well. Also, as the distribution planning has a direct bearing on the investment, and amount of investment has a direct bearing on the maximum electric load, various baseline such as maximum, lowest, median value that can assesses the adequacy and accuracy of proposed ML based electric load prediction methods were suggested.

• Smart Structures and Systems
• /
• v.33 no.4
• /
• pp.253-262
• /
• 2024

Current-based mechanical fault diagnosis is more convenient and low cost since additional sensors are not required. However, it is still challenging to achieve this goal due to the weak fault information in current signals. In this paper, a dual-loss convolutional neural network (DLCNN) is proposed to implement the intelligent bearing fault diagnosis via current signals. First, a novel similarity loss (SimL) function is developed, which is expected to maximize the intra-class similarity and minimize the inter-class similarity in the model optimization operation. In the loss function, a weight parameter is further introduced to achieve a balance and leverage the performance of SimL function. Second, the DLCNN model is constructed using the presented SimL and the cross-entropy loss. Finally, the two-phase current signals are fused and then fed into the DLCNN to provide more fault information. The proposed DLCNN is tested by experiment data, and the results confirm that the DLCNN achieves higher accuracy compared to the conventional CNN. Meanwhile, the feature visualization presents that the samples of different classes are separated well.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11b
• /
• pp.381-387
• /
• 2002

In this work, the dynamic characteristics of an oil-lubricated, short SFD with a central feeding groove are derived based on a theoretical analysis considering the effect of a groove. The validity of the analysis is investigated experimentally using an Active Magnetic Bearing (AMB) system as an exciter. For the theoretical solution, the fluid film forces of a grooved SFD are analytically derived so that the dynamic coefficients of a SFD are expressed in terms of its design parameters. For the experimental validation of the analysis, a test rig using AMB as an exciter is proposed to identify the dynamic characteristics of a short SFD with a central groove. As an exciter, the AMB represents a mechatronic device to levitate and position the test journal without any mechanical contact, to generate relative motions of the journal inside the tested SFD and to measure the generated displacements during experiments with fairly high accuracy. Using this test rig, experiments are extensively conducted with different clearance, which is one of the most important design parameters, in order to investigate its effect on the dynamic characteristics and the performance of SFDs. Damping and inertia coefficients of the SFD that are experimentally identified are compared with the analytical results to demonstrate the effectiveness of the analysis. It is also shown that AMB is an ideal device for tests of SFDs.

• Journal of Advanced Marine Engineering and Technology
• /
• v.40 no.4
• /
• pp.288-294
• /
• 2016

In modern ships, the shafting system often becomes stiff owing to the high engine power, whereas the hull structure becomes more flexible owing to optimization using high-tensile-strength thick steel plates; therefore, more sophisticated shaft alignments are required. In this study, strain gauge-based measurement was conducted under five vessel operating conditions and bearing reaction forces and hull deflections affecting shaft alignment were analyzed for a 50,000 dead weight tonnage oil/chemical tanker that has gained repute as an eco-friendly vessel in recent years. Furthermore, the analytical results from each technique-theoretical calculation, jacking ups, and strain gauges-were cross-checked against each other in order to enhance the degree of accuracy and reliability of the calculation.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.3
• /
• pp.218-227
• /
• 2017

In this paper, an algorithm to calculate both bearing and distance error for target detection and localization is proposed using the Cramer Rao lower bound to estimate the minium variance of their error in DOA (Direction Of Arrival) estimation. The performance of arrays in detection and localization depends on the accuracy of DOA, which is affected by a variation of SNR (Signal to Noise Ratio). The SNR is determined by sonar parameters such as a SL (Source Level), TL (Transmission Loss), NL (Noise Level), array shape and beam steering angle. For verification of the suggested method, a Monte Carlo simulation was performed to probabilistically calculate the bearing and distance error according to the SNR which varies with the relative position of the target in space and noise level.

• Tribology and Lubricants
• /
• v.31 no.6
• /
• pp.294-301
• /
• 2015

In this paper, we predict the rotordynamic force coefficients of tilting pad journal bearings (TPJBs) with rocker-back pivots, and we compare the predictions to recently published predictions and test data. The present TPJB model considers the rocker-back pivot stiffness calculated based on the Hertzian contact-stress theory, which is nonlinear with the application of a force . For the five-pad TPJB in load-between-pad and load-on-pad configurations, the predictions show the pressure- and film-thickness distributions, the deflection and stiffness of the individual pivots, and bearing stiffness and damping coefficients. The minimum film thickness and peak pressure occur at the bottom pad on which the applied load is directed. Because of the preload, the pres- sure is positive even at the upper pad in the opposite direction to the applied load. The pivot deflection and stiff- ness are maximum at the bottom pad that receives the heaviest pressure load. The predicted stiffness coefficients increase as the static load and rotor speed increase, while the damping coefficients decrease as the rotor speed increases, but increase as the static load increases. In general, the predicted stiffness coefficients agree well with the test data. The predicted damping coefficients overestimate the test data, particularly for large static loads. In general, the current predictive model considering the pivot stiffness improves the accuracy of the rotordynamic performance compared to previously reported models.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.6_2
• /
• pp.1119-1125
• /
• 2022

The depletion of resources and waste disposal caused by the continuous development of industry have emphasized the need to reduce consumption and production, recycle and reuse, and the importance of remanufacturing has increased in recent years. The spindle part of the aging planner miller, which is currently being remanufactured, is one of the factors that has the greatest impact on the performance of the machine tool. When designing the spindle part of the spindle shaft, there are considerations such as the configuration size bearing performance of the main shaft, but the diameter of the main shaft, the dangerous speed bearing, and the arrangement that affect the machining accuracy should be basically considered. As such, various studies have been conducted on the design of machine tool spindle spindles, but research on the reverse engineering of existing aging machine tool spindle spindles is poor. Reverse engineering is designing in the direction of improving performance by extracting specifications from already finished products, and first scanning the reverse engineered object through a 3D scanner, 3D modeling is performed based on the collected data, and then the process of deriving improvement plans by reverberating to improve performance by identifying wear and damage conditions is followed. Therefore, in this study, the purpose of this study is to provide data on reverse engineering by deriving improvement plans through optimal design for the bearing position of the aging planar Miller spindle spindle using central composite programming.

• Computers and Concrete
• /
• v.34 no.2
• /
• pp.151-168
• /
• 2024

This research aimed to appraise the effectiveness of four optimization approaches - cuckoo optimization algorithm (COA), multi-verse optimization (MVO), particle swarm optimization (PSO), and teaching-learning-based optimization (TLBO) - that were enhanced with an artificial neural network (ANN) in predicting the bearing capacity of shallow foundations located on cohesionless soils. The study utilized a database of 97 laboratory experiments, with 68 experiments for training data sets and 29 for testing data sets. The ANN algorithms were optimized by adjusting various variables, such as population size and number of neurons in each hidden layer, through trial-and-error techniques. Input parameters used for analysis included width, depth, geometry, unit weight, and angle of shearing resistance. After performing sensitivity analysis, it was determined that the optimized architecture for the ANN structure was 5×5×1. The study found that all four models demonstrated exceptional prediction performance: COA-MLP, MVO-MLP, PSO-MLP, and TLBO-MLP. It is worth noting that the MVO-MLP model exhibited superior accuracy in generating network outputs for predicting measured values compared to the other models. The training data sets showed R² and RMSE values of (0.07184 and 0.9819), (0.04536 and 0.9928), (0.09194 and 0.9702), and (0.04714 and 0.9923) for COA-MLP, MVO-MLP, PSO-MLP, and TLBO-MLP methods respectively. Similarly, the testing data sets produced R² and RMSE values of (0.08126 and 0.07218), (0.07218 and 0.9814), (0.10827 and 0.95764), and (0.09886 and 0.96481) for COA-MLP, MVO-MLP, PSO-MLP, and TLBO-MLP methods respectively.

• Journal of Ocean Engineering and Technology
• /
• v.3 no.2
• /
• pp.138-144
• /
• 1989

It has been very important in various industry fields to improve the fatigue strength characteristics of bearings such as bearing life, fatigue limit, etc., because such poor properties could result in shortening the machinery life as well as in decreasing the accuracy. However, no successful heat treatment criterion seems to be available at present. In this study, the effect of the $170^{\circ}C\times120min$ tempering cycles repeated after $380^{\circ}C\times80min$ oil quenching for $800^{\circ}C$ spheroidizing-annealed bearing steel (STB2) as base metal on the $120^{\circ}C$ high temperature rotary bending fatigue strength characteristics were investigated, including the effects on hardness, Charpy impact value and micro-structure, in order to seek for the best heat treatment condition finally. The important results obtained are as follows : 1) The optimal cycle of tempering so that the fatigue strength .sigma. could become the highest was the 4th cycle. And it is confirmed that this $\sigma_{F}$ is about 6 times more increased than that of base metal, and about 1.3 times more increased than the case of the 1 cycle tempered. 2) As a result of the investigation for the effects of tempering cycles on hardness, the hardness at the tempering number of 2 thru 5 cyles was not decreased severely ; only about 10% decrease from those of the quenched and 1 cycle tempered case. Such hardness is equivalent to $H_{R}$/C61-62 with no bad effect on anti-abrasion of bearing steel. 3) In the case of 2 thru 5 cycle tempering as well as 1 cycle tempering, the impact value was not so improved comparing with the case of quenching, but an increase of 5 to 10% could be expected at least. 4) It was experimentally confirmed that the control of the mechanical properties improvement such as fatigue strength and fatigue life for bearing steels could be possible by the number of tempering cycles.

• Journal of Ocean Engineering and Technology
• /
• v.3 no.2
• /
• pp.638-638
• /
• 1989

It has been very important in various industry fields to improve the fatigue strength characteristics of bearings such as bearing life, fatigue limit, etc., because such poor properties could result in shortening the machinery life as well as in decreasing the accuracy. However, no successful heat treatment criterion seems to be available at present. In this study, the effect of the $170^{\circ}C\times120min$ tempering cycles repeated after $380^{\circ}C\times80min$ oil quenching for $800^{\circ}C$ spheroidizing-annealed bearing steel (STB2) as base metal on the $120^{\circ}C$ high temperature rotary bending fatigue strength characteristics were investigated, including the effects on hardness, Charpy impact value and micro-structure, in order to seek for the best heat treatment condition finally. The important results obtained are as follows : 1) The optimal cycle of tempering so that the fatigue strength .sigma. could become the highest was the 4th cycle. And it is confirmed that this $\sigma_{F}$ is about 6 times more increased than that of base metal, and about 1.3 times more increased than the case of the 1 cycle tempered. 2) As a result of the investigation for the effects of tempering cycles on hardness, the hardness at the tempering number of 2 thru 5 cyles was not decreased severely ; only about 10% decrease from those of the quenched and 1 cycle tempered case. Such hardness is equivalent to $H_{R}$/C61-62 with no bad effect on anti-abrasion of bearing steel. 3) In the case of 2 thru 5 cycle tempering as well as 1 cycle tempering, the impact value was not so improved comparing with the case of quenching, but an increase of 5 to 10% could be expected at least. 4) It was experimentally confirmed that the control of the mechanical properties improvement such as fatigue strength and fatigue life for bearing steels could be possible by the number of tempering cycles.