PURPOSES : The driver's ability to make a commitment has resulted in excessive force and a lack of commitment. To solve this problem, we are developing an algorithm that analyzes resolution in real-time by introducing IoT and informs drivers of the completion of compaction. METHODS : Real-time compaction was analyzed by installing accelerometers on the rollers. To evaluate the algorithms, we conducted an apparent density test. RESULTS : The algorithm data and apparent density test data showed similar trends. This means that the proposed algorithms are sufficiently reliable. However, a lack of data samples and the fact that only data prior to completion of the commitment were analyzed may indicate a lack of reliability. CONCLUSIONS : In subsequent studies, the number of samples will be increased and the data after completion of the commitment analyzed to increase reliability. Introducing a tachometer will prevent the TVL from falling sharply when the direction of the rollers' progress changes. In addition, it is also planned to upgrade the algorithms by researching cases in which the algorithms did not produce satisfactory results owing to problems such as temperature and speed.

Control performance of a smart tuned mass damper (TMD) mainly depends on control algorithms. A lot of control strategies have been proposed for semi-active control devices. Recently, machine learning begins to be applied to development of vibration control algorithm. In this study, a reinforcement learning among machine learning techniques was employed to develop a semi-active control algorithm for a smart TMD. The smart TMD was composed of magnetorheological damper in this study. For this purpose, an 11-story building structure with a smart TMD was selected to construct a reinforcement learning environment. A time history analysis of the example structure subject to earthquake excitation was conducted in the reinforcement learning procedure. Deep Q-network (DQN) among various reinforcement learning algorithms was used to make a learning agent. The command voltage sent to the MR damper is determined by the action produced by the DQN. Parametric studies on hyper-parameters of DQN were performed by numerical simulations. After appropriate training iteration of the DQN model with proper hyper-parameters, the DQN model for control of seismic responses of the example structure with smart TMD was developed. The developed DQN model can effectively control smart TMD to reduce seismic responses of the example structure.

본 연구는 화재진압 및 피난활동을 지원하는 딥러닝 기반의 알고리즘 개발에 관한 기초 연구로 선박 화재 시 연기감지기가 작동하기 전에 검출된 연기 데이터를 분석 및 활용하여 원격지까지 연기가 확산 되기 전에 연기 확산거리를 예측하는 것이 목적이다. 다음과 같은 절차에 따라 제안 알고리즘을 검토하였다. 첫 번째 단계로, 딥러닝 기반 객체 검출 알고리즘인 YOLO(You Only Look Once)모델에 화재시뮬레이션을 통하여 얻은 연기 영상을 적용하여 학습을 진행하였다. 학습된 YOLO모델의 mAP(mean Average Precision)은 98.71%로 측정되었으며, 9 FPS(Frames Per Second)의 처리 속도로 연기를 검출하였다. 두 번째 단계로 YOLO로부터 연기 형상이 추출된 경계 상자의 좌표값을 통해 연기 확산거리를 추정하였으며 이를 시계열 예측 알고리즘인 LSTM(Long Short-Term Memory)에 적용하여 학습을 진행하였다. 그 결과, 화재시뮬레이션으로부터 얻은 Fast 화재의 연기영상에서 경계 상자의 좌표값으로부터 추정한 화재발생~30초까지의 연기 확산거리 데이터를 LSTM 학습모델에 입력하여 31초~90초까지의 연기 확산거리 데이터를 예측하였다. 그리고 추정한 연기 확산거리와 예측한 연기 확산거리의 평균제곱근 오차는 2.74로 나타났다.

PURPOSES : This study verifies the appropriateness of the observed traffic volume using car navigation traffic volume data. METHODS : In this study, we developed an annual average daily traffic (AADT) estimation model that can verify the total amount of traffic by using navigation traffic volume data. In addition, a method to verify the appropriateness of the observed traffic volume was developed using time-based navigation traffic volume data that can check the characteristics of traffic volume at each point. RESULTS : As a result of the analysis of this study, it was found that 674 of the 697 short-duration survey spots of the freeways were appropriate and that 23 spots needed to be revised. CONCLUSIONS : As a result of the analysis of this study, it was found that there was a strong positive correlation between the observed traffic volume and the car navigation traffic volume. Thus, the appropriateness of the observed traffic was determined by verifying the total amount of observed traffic and the observed traffic volume by time.

In the study, a shape finding procedure for the tensegrity system model inspired by the movement pattern of animal backbone was presented. The proposed system is allowing a dynamic movement by introducing the concept of “saddle” for the variable tensegrity structure. Mathematical process and an algorithm for movable tensegrity to specified points were established. Several examples have applied with in established shape finding analysis procedure. The final tensegrity structures were determined well to a object shape.

Spot welding is a representative process in automotive welding and the application of intelligent systems is accelerating. In particular, in the case of welding electrode management, the timing of electrode wear and dressing was determined by continuous spot welding evaluation, however there is concerned that errors in welding equipment or processes may work in a complex manner. In this study, a dynamic resistance waveform sensing and image measurement system that greatly affects the nugget formation, which is important to the quality of spot welding, was fabricated and used. Based on the experimental data of the galvanized steel sheet, an electrode life prediction algorithm for electrode wear was derived through CNN(Convolutional Neural Network) model of machine learning training.

PURPOSES: This paper develops a new stochastic approach to analyze the pavement-vehicle interaction model with a certain roughness and elasticity for the pavement foundation, thereby accommodating the deflection of the pavement, and to identify the road subsidence zone represented with a sudden changes in the elasticity of the foundation. METHODS: In the proposed model, a quarter-car model was combined with a filtered white noise model of road roughness and a two-layer foundation (Euler-Bernoulli beam for the top surface and Winkler foundation to represent the sub-structure soil). An augmented state-space model for the subsystems was formulated. Then, because the input is White noise and the system is represented as a single system, the Lyapunov equation governing the covariance of the system’s response was solved to obtain a structurally weak zone index (WZI). RESULTS: The results showed that the WZI from the pavement-vehicle interaction model is sensitive enough to identify road subsidence. In particular, the WZI rapidly changed with a small change in foundation elasticity, indicating that the model has the potential to detect road subsidence in the early stage. CONCLUSIONS: Beacause of the simplicity of the calculation, the proposed approach has potential applications in managing road conditions while a vehicle travels along the road and detecting road subsidence using a device with an on-board computational capability, such as a smart phone.

More than 6,000 power tiller accidents occurred in 2015, accounting for 50% of all agricultural machinery accidents. Despite this, educational institutions for farmers are only conducting theoretical education due to lack of training systems with guaranteed safety. This study developed an object motion tracking algorithm enabling trainees to control a power tiller driving simulator while wearing a HMD(head mounted display) in order to provide safe hands-on training equipment. A power tiller driving simulator was built using encoders, proximity sensors and displacement sensors to detect the locations of various operating devices such as steering clutch, and a computer model for this simulator was designed. Center coordinate synchronization of the driving simulator and the computer model was achieved with a tracker, and the motion of the power tiller driving simulator was tracked by computing position coordinates and rotation angles of the simulator. The maximum distance error was 23mm, and there was no difficulty maneuvering the driving simulator while wearing an HMD, even at maximum distance error. This motion tracking algorithm is expected to be applicable to the development of mixed reality based power tiller driving simulators for training, contributing to the reduction of power tiller accidents.

본 연구에서는 인명구조활동을 지원하기 위한 피난동선예측 알고리즘 개발의 첫 단계로 피난동선예측 알고리즘의 개념을 정립 하고 그 타당성을 수치적으로 명확히 제시하였다. 제안하는 알고리즘은 평상시 선박내 모니터링 시스템으로부터 지속적으로 승객이동 데이터를 취득, 분석, 정형화하고, 재난발생시 이 데이터와 예측 툴을 활용해 도출한 승선자의 피난동선예측 정보를 구조자에게 제공하여 인명피해를 최소화시키는 프로세스로 요약할 수 있다. 피난훈련을 통해 피난특성 데이터를 취득하였고 이를 기존 인명피난예측 툴에 입력하여 피난특성을 예측한 결과, 예측 툴의 구조적 원인으로 인해 가시거리가 충분히 확보되고 피난경로를 충분히 숙지한 상황에서의 피난 시나리오(SN1)에서만 신뢰할 만한 예측결과가 도출되었다. 본 연구에서 제안하는 알고리즘의 타당성을 확인하기 위해 타 분야의 예측툴을 사용하여 피난특성을 예측한 결과, 제안 알고리즘이 구현될 경우 평균피난시간예측값과 피난동선(지점경유)예측값이 각각 0.6 ~ 6.9%, 0.6 ~ 3.6% 범위의 오차에서 실측값과 매우 유사한 경향을 보였다. 향후 선내 모니터링 데이터를 분석하고 이를 활용한 예측성능이 우수한 피난동선예측 알고리즘을 개발할 계획이다.

This paper describes a development of design tool for knowledge based engineering(KBE) that covers structural, aerodynamic, and optical analysis of large-scale telescope structures. A module of the commercial program Adaptive Modeling Language(AML) was used to develop a knowledge-based design tool that reflects the design of parameters for rapid design change and analysis. Through this study, it is proposed a design tool with a knowledge based engineering and a function based design technique. The knowledge based engineering design is good at frequent design changes, and it is effective to extract a core design behavior from previous designs. It is concluded that the developed tool can bring fair effects in implementing a time and cost-effective design environment.

Recently, thanks to emerging ICT (Information and Communication Technology) such as IoT (Internet of Things), wireless telecommunication, and various sensor technologies, the concept of connected car has been highlighted in the automotive industry. In the connected car technology, one application is to diagnose and predict the car status in a real-time way based on gathered data. To this end, it is necessary to develop the diagnostics/prognostics algorithms for a specific part or component in a car. The results of diagnostics and prognostics could provide drivers with useful information used for advanced maintenance policy such as condition-based maintenance. In this study, we have reviewed the relevant previous research works before developing detailed algorithms.