본 연구는 데이터를 기반으로 한 인공지능 기계학습 기법을 활용하여 온실 내부온도 예측 시뮬레이션 모델을 개발을 수행 하였다. 온실 시스템의 내부온도 예측을 위해서 다양한 방법 이 연구됐지만, 가외 변인으로 인하여 기존 시뮬레이션 분석 방법은 낮은 정밀도의 문제점을 지니고 있다. 이러한 한계점 을 극복하기 위하여 최근 개발되고 있는 데이터 기반의 기계 학습을 활용하여 온실 내부온도 예측 모델 개발을 수행하였 다. 기계학습모델은 데이터 수집, 특성 분석, 학습을 통하여 개 발되며 매개변수와 학습방법에 따라 모델의 정확도가 크게 변 화된다. 따라서 데이터 특성에 따른 최적의 모델 도출방법이 필요하다. 모델 개발 결과 숨은층 증가에 따라 모델 정확도가 상승하였으며 최종적으로 GRU 알고리즘과 숨은층 6에서 r2 0.9848과 RMSE 0.5857℃로 최적 모델이 도출되었다. 본 연 구를 통하여 온실 외부 데이터를 활용하여 온실 내부온도 예 측 모델 개발이 가능함을 검증하였으며, 추후 다양한 온실데이 터에 적용 및 비교분석이 수행되어야 한다. 이후 한 단계 더 나아 가 기계학습모델 예측(predicted) 결과를 예보(forecasting)단 계로 개선하기 위해서 데이터 시간 길이(sequence length)에 따른 특성 분석 및 계절별 기후변화와 작물에 따른 사례별로 개발 모델을 관리하는 등의 다양한 추가 연구가 수행되어야 한다.

본 연구에서는 콘크리트 이미지에서 균열의 크기와 위치를 검출하는 알고리즘을 개발하였다. 균열은 총 9단계로 자 동 검출되었으며, 기본 기능은 매트랩 프로그램의 기능이었다. 5단계와 8단계에서는 균열 검출 정확도를 높이기 위해 사용자 알고리즘을 추가하였으며, 균열 영상과 비균열 영상을 각각 1,000개씩 사용하였다. 균열 이미지에서는 균열이 100% 검출됐지만 품질 측면에서 나쁘지 않은 결과를 제외하더라도 91.8%의 결과가 매우 양호했다. 또한, 균열되지 않은 이미지의 정확도도 94.7%로 매우 양호했다. 이에 본 연구에서 제시한 균열검출 알고리즘은 콘크리트 우물 균열의 위치와 크기를 검출할 수 있을 것으로 기대된다.

Recently, machine learning is widely used to solve optimization problems in various engineering fields. In this study, machine learning is applied to development of a control algorithm for a smart control device for reduction of seismic responses. For this purpose, Deep Q-network (DQN) out of reinforcement learning algorithms was employed to develop control algorithm. A single degree of freedom (SDOF) structure with a smart tuned mass damper (TMD) was used as an example structure. A smart TMD system was composed of MR (magnetorheological) damper instead of passive damper. Reward design of reinforcement learning mainly affects the control performance of the smart TMD. Various hyperparameters were investigated to optimize the control performance of DQN-based control algorithm. Usually, decrease of the time step for numerical simulation is desirable to increase the accuracy of simulation results. However, the numerical simulation results presented that decrease of the time step for reward calculation might decrease the control performance of DQN-based control algorithm. Therefore, a proper time step for reward calculation should be selected in a DQN training process.

The power of legacy media originated from material foundations, not contents. Legacy media has exercised its power through the control of means of publishing, namely rotary machines. Article 21 (3) of the Constitution reflects this. It states that “The standards of news service and broadcast facilities and matters necessary to ensure the functions of newspapers shall be determined by Act.” In the past, newspapers controlled production of information, publication of article, and distribution of newspaper. However, as big technology corporations virtually monopolized the news publishing and distribution process, the nature of legacy media has changed to be in charge of only production of information. The Constitutional Court of the Republic of Korea concluded, “Media diversity is an indispensable premise for democratic society based on pluralism.” However, as big technology corporations and algorithms intervened in news distribution, the market for diversity of opinions market has collapsed. The monopoly of the algorithm’s distribution of articles is unconstitutional. In order to realize diversity of public opinion in a new media environment, regulation must target an algorithm not a rotary press.

It is important to ensure worker’s safety from radiation hazard in decommissioning site. Real-time tracking of worker’s location is one of the factors necessary to detect radiation hazard in advance. In this study, the integrated algorithm for worker tracking has been developed to ensure the safety of workers. There are three essential techniques needed to track worker’s location, which are object detection, object tracking, and estimating location (stereo vision). Above all, object detection performance is most important factor in this study because the performance of tracking and estimating location is depended on worker detection level. YOLO (You Only Look Once version 5) model capable of real-time object detection was applied for worker detection. Among the various YOLO models, a model specialized for person detection was considered to maximize performance. This model showed good performance for distinguishing and detecting workers in various occlusion situations that are difficult to detect correctly. Deep SORT (Simple Online and Realtime Tracking) algorithm which uses deep learning technique has been considered for object tracking. Deep SORT is an algorithm that supplements the existing SORT method by utilizing the appearance information based on deep learning. It showed good tracking performance in the various occlusion situations. The last step is to estimate worker’s location (x-y-z coordinates). The stereo vision technique has been considered to estimate location. It predicts xyz location using two images obtained from stereo camera like human eyes. Two images are obtained from stereo camera and these images are rectified based on camera calibration information in the integrated algorithm. And then workers are detected from the two rectified images and the Deep SORT tracks workers based on worker’s position and appearance between previous frames and current frames. Two points of workers having same ID in two rectified images give xzy information by calculating depth estimation of stereo vision. The integrated algorithm developed in this study showed sufficient possibility to track workers in real time. It also showed fast speed to enable real-time application, showing about 0.08 sec per two frames to detect workers on a laptop with high-performance GPU (RTX 3080 laptop version). Therefore, it is expected that this algorithm can be sufficiently used to track workers in real decommissioning site by performing additional parameter optimization.

The amount of temporarily stored spent nuclear fuel in South Korea will be reaching saturation in a near future. Therefore, it is an urgent issue to construct a spent nuclear fuel storage system. In order to construct the storage system, some coastal environmental characteristics such as temperature, pH, and chemical composition of sea water in South Korea have to be evaluated and predicted because they can affect in deterioration of the storage system. However, in South Korea, the coastal environmental characteristics of area where the storage system is likely to be built are not well established until now. In this study, a time-series deep-learning algorithm is developed using the Long-Short Term Memory (LSTM) algorithm to predict and evaluate the coastal environmental characteristics based on the wellestablished data from Korea Meteorological Administration (KMA) and Ministry of Oceans and Fisheries (MOF). As a result, by developing the predictive model to evaluate the coastal environmental characteristics, we intend to apply it for site evaluation to construct the spent nuclear fuel storage system or many other applications related to the nuclear as well.

In order to effectively and efficiently apply safeguards to new nuclear facilities, it is recommended to apply safeguards-by-design concept. In evaluating the safeguards in the early stage of the design of a facility, it is essential to analyze the diversion path for nuclear materials. This study suggests a simple method which can generate diversion paths. The essential components constituting the diversion path were reviewed and the logical flow for systematically creating the diversion path was developed. The path generation algorithm is based on this components and logical flow as well as the initial information of the nuclear materials and material flows in a planned facilities. The results will be used to develop a program module which can systematically generate diversion paths using the event tree and fault tree method.

기술의 발전으로 스마트 선박과 관련된 다양한 연구가 진행되고 있으며, 기관실을 무인으로 순찰할 수 있는 기관실 순찰 로봇 도 이러한 연구 중의 하나이다. 순찰로봇은 인공지능을 통해 학습된 정보를 기반으로 기관실을 이동하며 기기 정상 유무 및 누수, 누유, 화재 등의 이상 유무를 파악한다. 기관실 순찰로봇에 관한 연구는 인공지능을 이용한 객체 검출에 관한 연구가 주로 진행되고 있으나, 순 찰로봇의 이동 및 제어에 관한 연구는 부족한 상황이다. 이는 순찰로봇이 객체를 검출하더라도 검출한 객체까지 이동할 방법이 없다는 문제를 야기한다. 이에 본 논문에서는 기관실 이상상황 발생 시 빠르게 이상 유무를 파악할 수 있는 기동성을 확보하기 위해, A* 알고리 즘을 적용하여 순찰로봇이 최단경로를 탐색할 수 있는지를 확인하였다. 라이다를 장착한 소형차를 이용하여 선박 기관실을 주행하며 데 이터를 얻어, SLAM으로 매핑하여 지도를 만들었다. 매핑한 지도에서 순찰로봇의 출발 지점과 목표 지점을 설정하고, A* 알고리즘을 적용 하여 출발 지점부터 목표 지점까지 최단 경로를 탐색하는지를 확인하였다. 시뮬레이션 결과 매핑된 지도에서 출발 지점부터 목표 지점까 지의 장애물을 회피하며 최단 경로를 잘 탐색함을 확인 할 수 있었으며, 기관실 순찰로봇에 적용하면 선박안전에 도움이 될 것으로 사료 된다.

The PoN (Proof of Nonce) distributed consensus algorithm basically uses a non-competitive consensus method that can guarantee an equal opportunity for all nodes to participate in the block generation process, and this method was expected to resolve the first trilemma of the blockchain, called the decentralization problem. However, the decentralization performance of the PoN distributed consensus algorithm can be greatly affected by the network transaction transmission delay characteristics of the nodes composing the block chain system. In particular, in the consensus process, differences in network node performance may significantly affect the composition of the congress and committee on a first-come, first-served basis. Therefore, in this paper, we presented a problem by analyzing the decentralization performance of the PoN distributed consensus algorithm, and suggested a fairness control algorithm using a learning-based probabilistic acceptance rule to improve it. In addition, we verified the superiority of the proposed algorithm by conducting a numerical experiment, while considering the block chain systems composed of various heterogeneous characteristic systems with different network transmission delay.

Strawberry is a stand-out cultivating fruit in Korea. The optimum production of strawberry is highly dependent on growing environment. Smart farm technology, and automatic monitoring and control system maintain a favorable environment for strawberry growth in greenhouses, as well as play an important role to improve production. Moreover, physiological parameters of strawberry plant and it is surrounding environment may allow to give an idea on production of strawberry. Therefore, this study intends to build a machine learning model to predict strawberry’s yield, cultivated in greenhouse. The environmental parameter like as temperature, humidity and CO2 and physiological parameters such as length of leaves, number of flowers and fruits and chlorophyll content of ‘Seolhyang’ (widely growing strawberry cultivar in Korea) were collected from three strawberry greenhouses located in Sacheon of Gyeongsangnam-do during the period of 2019-2020. A predictive model, Lasso regression was designed and validated through 5-fold cross-validation. The current study found that performance of the Lasso regression model is good to predict the number of flowers and fruits, when the MAPE value are 0.511 and 0.488, respectively during the model validation. Overall, the present study demonstrates that using AI based regression model may be convenient for farms and agricultural companies to predict yield of crops with fewer input attributes.

With the development of the global marine transportation industry, marine accidents frequently occur due to the complex and changeable climate environment, and maritime search and rescue work has thus received much attention. To improve marine search and rescue operations, an algorithm for environmental modeling and search path optimization based on an ant colony system is proposed. First, MAKLINK is selected to build an ecological model. Secondly, the relevant parameters of the ant colony system algorithm are established, and the search and rescue route is designed. Finally, simulations of the environmental model and route design are constructed in search and rescue waters in Zhoushan, Zhejiang Province, using MATLAB. Experimental results prove the validity of this algorithm.

본 연구는 도로 노면결빙 판정 알고리즘에 대해 알고리즘을 개선하고 실제 현장 측정 자료와 알고리즘 예측값을 비교하였을 때 알고리즘에 대한 적중률을 분석하였다. 분석을 위하여 포천시 신북면 금 동리의 도로 및 기상을 측정하였다. 알고리즘은 기존 도로 결빙 알고리즘을 선정하여 실제 결빙 조건 및 측정 수치에 맞춰 4차 알고리즘까지 개선하였다. 최종적으로 응결에 의한 결빙, 강수에 의한 결빙, 적설에 의한 결빙, 결빙상태의 지속, 풍속에 의한 결빙 5개의 알고리즘을 제작하였다. 포천 현장에서 알고리즘을 활용하여 예측할 경우 경우 결빙 적중률이 93.22%까지 개선되었다. 결빙 알고리즘에 대한 조합 비율에 대 해 도출하였을 때 응결에 의한 결빙과 결빙상태의 지속에 대한 알고리즘이 96%를 차지하였다.

현재 교량과 같은 토목구조물의 설계프로세스는 1차 설계 후 구조 검토를 수행하여 기준에 부적합할 경우 재설계하는 과정을 반복 하여 최종적인 성과품을 만드는 것이 일반적이다. 이러한 반복 과정은 설계에 소요되는 기간을 연장시키는 원인이 되며, 보다 수준 높 은 설계를 위해 투입되어야 할 고급 엔지니어링 인력을 기계적인 단순 반복 작업에 소모하고 있다. 이러한 문제는 설계 과정 자동화를 통하여 해결할 수 있으나, 설계 과정에서 사용되는 해석프로그램은 이러한 자동화에 가장 큰 장애요인이 되어 왔다. 본 연구에서는 기 존 설계 과정 중 반복작업을 대체하고자 강화학습 알고리즘과 외부 해석프로그램을 함께 제어할 수 있는 인터페이스를 포함한 교량 설계 프로세스에 대한 AI기반 자동화 시스템을 구축하였다. 이 연구를 통하여 구축된 시스템의 프로토타입은 2경간 RC라멘교를 대 상으로 제작하였다. 개발된 인터페이스 체계는 향후 최신 AI 및 타 형식의 교량설계 간 연계를 위한 기초기술로써 활용될 수 있을 것 으로 판단된다..