• Journal of the Korean Society for Precision Engineering
• /
• v.6 no.2
• /
• pp.77-87
• /
• 1989

This study is carried out to estimate the influence of cutting speed on the dynamic stability of a drilling machine. The theoretical stabilityu chart is constructed by using the measurd dynamic characteristics of the drilling machine. The critical cutting width and speed predicted from the stability chart show excellent agreements with those measured. Therefore it is confirmed that the analysis technique used in this study is useful for the prediction of the dynamic instability and improvement of the dynamic characteristics of drilling machines.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2012.04a
• /
• pp.188-189
• /
• 2012

• Proceedings of the KSR Conference
• /
• 2002.10a
• /
• pp.376-381
• /
• 2002

In this study, we have analyzed the cost of korea high-speed rail project. The predicted cost in planning phase and adjustment data to 5th year are collected. Then, predicted cost is compared with adjustment in year/item/system base. We make a project history table for criteria to review project history and research ＆ development activity. We have developed CBS(cost breakdown structure) and allocated adjustment data to them. It is shown that cost prediction related to research St development activity in planning phase is relatively correct.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.3D
• /
• pp.223-229
• /
• 2012

Skid resistance is defined as the friction between pavement surfaces and vehicle tires. Lower skid resistances were observed as the vehicle speeds the water film thicknesses were increased according to the analysis results using computer modeling. The lift force is calculated from the analysis results and depends on vehicle speeds and the water film thickness. A modified IFI(international friction index) skid resistance prediction model was developed to reduce the differences between the IFI resistance prediction model and the actual skid resistance. The correlation analysis results between the IFI prediction model and the actual skid resistance revealed that the $R^2$ using the modified IFI prediction model was 0.64 whereas the $R^2$ using the conventional IFI prediction model was 0.49. This presents the modified prediction model is better than the conventional one. An improved precise prediction model is to be obtained if water film thicknesses are considered in the modified prediction model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.4
• /
• pp.767-773
• /
• 2017

In this paper, we propose a design of Intra prediction angular mode decision for HEVC encoder. Intra prediction coding of HEVC is a method for predicting a current block by referring to samples reconstructed around a current block. Intra prediction supports a total of 35 modes with 1 DC mode, 1 Planar mode, and 33 Angular modes. Intra prediction coding of HEVC works by performing all 35 modes for efficient encoding. However, in order to process all of the 35 modes, the computational complexity and operational time required are high. Therefore, this paper proposes comparing the difference in the value of the original pixel, using an algorithm that determines angular mode efficiently. This new algorithm reduces the Hardware size. The hardware which is proposed was designed using Verilog HDL and was implemented in 65nm technology. Its gate count is 14.9K and operating speed is 2GHz.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.3
• /
• pp.149-155
• /
• 2021

Early warning systems for weather risk management in the agricultural sector have been developed to predict potential wind damage to crops. These systems take into account the daily maximum wind speed to determine the critical wind speed that causes fruit drops and provide the weather risk information to farmers. In an effort to increase the accuracy of wind risk predictions, an artificial neural network for binary classification was implemented. In the present study, the daily wind speed and other weather data, which were measured at weather stations at sites of interest in Jeollabuk-do and Jeollanam-do as well as Gyeongsangbuk- do and part of Gyeongsangnam- do provinces in 2019, were used for training the neural network. These weather stations include 210 synoptic and automated weather stations operated by the Korean Meteorological Administration (KMA). The wind speed data collected at the same locations between January 1 and December 12, 2020 were used to validate the neural network model. The data collected from December 13, 2020 to February 18, 2021 were used to evaluate the wind risk prediction performance before and after the use of the artificial neural network. The critical wind speed of damage risk was determined to be 11 m/s, which is the wind speed reported to cause fruit drops and damages. Furthermore, the maximum wind speeds were expressed using Weibull distribution probability density function for warning of wind damage. It was found that the accuracy of wind damage risk prediction was improved from 65.36% to 93.62% after re-classification using the artificial neural network. Nevertheless, the error rate also increased from 13.46% to 37.64%, as well. It is likely that the machine learning approach used in the present study would benefit case studies where no prediction by risk warning systems becomes a relatively serious issue.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.20 no.6
• /
• pp.56-64
• /
• 2016

Damage of sea-crossing bridge by ship collision is related to estimate frequencies of overloading due to impact, and bridge accordingly must be designed to satisfy related acceptance criteria. Another important aspect is the management on increment of collision risk during the service period. In this study, related plan, main span length, air draft clearance and collision risk are analyzed for the interim assessment of Incheon Bridge focusing on the ship collision problem. In particular, for the increment of collision risk, the optimized navigation speed is proposed by reviewing the research findings and navigation guidelines etc. as a temporary expedient. Also basic procedure for reasonable prediction of target vessel and passage is established and probabilistic prediction method to embrace the uncertainty of the prediction is proposed as a fundamental solution. It is necessary to conduct further research on collision risk management and promptly carry out interim assessments of other marine bridges.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.2
• /
• pp.890-903
• /
• 2017

The problem of determining a smooth and collision-free path with maximum possible speed for a Mobile Robot (MR) which is chasing a moving target in a dynamic environment is addressed in this paper. Genetic Network Programming with Reinforcement Learning (GNP-RL) has several important features over other evolutionary algorithms such as it combines offline and online learning on the one hand, and it combines diversified and intensified search on the other hand, but it was used in solving the problem of MR navigation in static environment only. This paper presents GNP-RL based on predicting collision positions as a first attempt to apply it for MR navigation in dynamic environment. The combination between features of the proposed collision prediction and that of GNP-RL provides safe navigation (effective obstacle avoidance) in dynamic environment, smooth movement, and reducing the obstacle avoidance latency time. Simulation in dynamic environment is used to evaluate the performance of collision prediction based GNP-RL compared with that of two state-of-the art navigation approaches, namely, Q-Learning (QL) and Artificial Potential Field (APF). The simulation results show that the proposed GNP-RL outperforms both QL and APF in terms of smooth movement and safer navigation. In addition, it outperforms APF in terms of preserving maximum possible speed during obstacle avoidance.

• Safety and Health at Work
• /
• v.2 no.3
• /
• pp.236-242
• /
• 2011

Objectives: To determine the feasibility of predicting static and dynamic peak back-compressive forces based on (1) static back compressive force values at the lift origin and destination and (2) lifting speed. Methods: Ten male subjects performed symmetric mid-sagittal floor-to-shoulder, floor-to-waist, and waist-to-shoulder lifts at three different speeds (slow, medium, and fast), and with two different loads (light and heavy). Two-dimensional kinematics and kinetics were captured. Linear regression analyses were used to develop prediction equations, the amount of predictability, and significance for static and dynamic peak back-compressive forces based on a static origin and destination average (SODA) backcompressive force. Results: Static and dynamic peak back-compressive forces were highly predicted by the SODA, with R2 values ranging from 0.830 to 0.947. Slopes were significantly different between slow and fast lifting speeds (p < 0.05) for the dynamic peak prediction equations. The slope of the regression line for static prediction was significantly greater than one with a significant positive intercept value. Conclusion: SODA under-predict both static and dynamic peak back-compressive force values. Peak values are highly predictable and could be readily determined using back-compressive force assessments at the origin and destination of a lifting task. This could be valuable for enhancing job design and analysis in the workplace and for large-scale studies where a full analysis of each lifting task is not feasible.

• Phonetics and Speech Sciences
• /
• v.13 no.3
• /
• pp.71-78
• /
• 2021

Most neural-network-based speech synthesis models utilize neural vocoders to convert mel-scaled spectrograms into high-quality, human-like voices. However, neural vocoders combined with mel-scaled spectrogram prediction models demand considerable computer memory and time during the training phase and are subject to slow inference speeds in an environment where GPU is not used. This problem does not arise in linear spectrogram prediction models, as they do not use neural vocoders, but these models suffer from low voice quality. As a solution, this paper proposes a Tacotron 2 and Transformer-based linear spectrogram prediction model that produces high-quality speech and does not use neural vocoders. Experiments suggest that this model can serve as the foundation of a high-quality text-to-speech model with fast inference speed.