The net present value (NPV) is generally used in accept-or-reject decisions in engineering projects. Although the internal rate of return (IRR) is a highly complex and arbitrary process, it can reach the same conclusion as the NPV criterion. However, neither the NPV nor the IRR indicates how much money should be invested and how much profit can be made from an investment during a project. In this study, based on the reasons why the NPV and IRR cannot correctly measure the profitability of an investment, the must-have profitability measurement characteristics of an engineering project are presented.

Today, we are living in an era of city. Many cities around the world are exposed and vulnerable to natural disasters and environmental pollution due to rapid urbanization and population concentration. Most of these city problems occur in space and as a solution to all these problems, Digital Twin is continuouslybeing introduced. A digital urban space infrastructure and multi-dimensional spatial data analysis are required to effectively solve and deal with various city problems. One of problem in land administration aspect, to change ownership and get a permit take a long time. In order to improve this situation, digital twin concept is proposed. It’s operation and management became possible as the information systems took a transition from paper to computerized files, from files to integrated databases, from two-dimensional to three-dimensional data, and as transition took place, the need for a virtual urban space or "DigitalTwin" that can integrate distributed urban data into one came to fore. In this study, the new preprocess was suggested to use Digital Twin concept in order to reduce time line and to make an efficient work process for land administration.

Agrophotovoltaic (APV) system is an integrated system producing crops as well as solar energy. Because crop production underneath Photovoltaic (PV) modules requires delicate management of crops, smart farming equipment such as real-time remote monitoring sensors (e.g., thermometers, irradiance sensors, and soil moisture sensors) is installed in the APV system. This study aims at introducing a simulation-based decision support system (DSS) for smart farming in an APV system. The proposed DSS is devised to provide a mobile application service, satellite image processing, real-time data monitoring, and simulation-based performance estimation. Particularly, an agent-based simulation (ABS) is used to mimic functions of an APV system so that a data-driven function and digital twin environment are implemented in the proposed system. The ABS model is validated with field data collected from an actual APV system at the Jeollanamdo Agricultural Research and Extension Services in South Korea. As a result, farmers and engineers enable to efficiently produce solar energy without causing harmful impact on regular crop production underneath PV modules. In addition, the proposed system will contribute to enhancement of the digital twin technology in the field of agriculture.

Recently, most software development uses object-oriented method. The core of object-oriented method is class, and encaptualition and inheritance structure based on class improves development efficiency. However, if the method is encapsulated, it can be developed more effectively. In this paper, we examine the differences and effects from existing methods when encapsulating a method by applying the Template Method Pattern.

Currently, agriculture in Korea is facing a manpower shortage due to a decrease in the population and an aging workforce. Involving disabled people in agriculture as a solution to the problem of manpower shortage in agriculture can help both farmers and people with disabilities. For this, it is necessary to develop agricultural tools that disabled people can use in agricultural activities. This study tried to design agricultural work equipment for the disabled by applying a design technique using a digital human body model. To this end, in this study, a human body model for the disabled was created using anthropometric data for the disabled. After that, the agricultural work simulation using human body models was used to identify the problems in agricultural work of the disabled, and design supplementation was performed to solve the problems. As a result, design dimensions such as the height of the farm work bench for the disabled, the length of the fruit harvester, the length of the sprayer, and the height of the starter switch were determined. This study has significance in that the digital human body model-based design method was applied to the design of agricultural work equipment for the disabled.

Recently, supercomputers have entered the era of exascale beyond petascale. Overcoming the exascale barrier, which is the biggest problem with a large number of computing nodes and energy efficiency, was possible by using GPUs for computation in artificial intelligence, machine learning, and various high-performance computations. As evidenced by this, seven out of the ten world’s highest performing supercomputers are heterogeneous computing systems using GPUs. Accordingly, we developed a tool that can easily and conveniently monitor multiple vendors GPUs to support heterogeneous computing systems that are widely used in artificial intelligence and high-performance computations.

사출성형공정은 열가소성 수지를 가열하여 유동상태로 만들어 금형의 공동부에 가압 주입한 후에 금형 내에서 냉각시키는 공정으로, 금형의 공동모양과 동일한 제품을 만드는 방법이다. 대량생산이 가능하고, 복잡한 모양이 가능한 공정으로, 수지온도, 금형온도, 사출속도, 압력 등 다양한 요소들이 제품의 품질에 영향을 미친다. 제조현장에서 수집되는 데이터는 양품과 관련된 데이터는 많은 반면, 불량품과 관련된 데이터는 적어서 데이터불균형이 심각하다. 이러한 데이터불균형을 효율적으로 해결하기 위하여 언더샘플링, 오버샘플링, 복합샘플링 등이 적용되고 있다. 본 연구에서는 랜덤오버샘플링(ROS), 소수 클래스 오버 샘플링(SMOTE), ADASTN 등의 소수클래스의 데이터를 다수클래스만큼 증폭시키는 오버샘플링 기법을 활용하고, 데이터마이닝 기법을 활용하여 품질예측을 하고자 한다.

The The purpose of this study is to establish evaluation criteria for the purchase of electric vehicles and to present an evaluation model using quantitative scales for evaluation factors. This study was limited to the study of purchasing factors related to electric vehicles, and the spatial scope was limited to potential buyers in their 20s to 50s living in the Daejeon area. Based on the survey, the factors affecting the purchase factors (energy economics, image, performance, maintenance, price) were examined using the AHP method, and the priorities were analyzed to determine how much influence these factors have on the purchase of electric vehicles. In addition, in order to verify the logical consistency of the survey items, a consistency ratio test (c) was conducted. Through this study, priority considerations for the purchase of electric vehicles were presented, and information on future consumer interest in electric vehicles was conducted. It is judged to be able to provide an opportunity to provide various services for each layer.

When developing a new motor, a high-speed load test is performed using dynamo equipment to calculate the efficiency of the developed motor using the collected dynamo data. When connecting the test motor and the dynamo used as a load, abnormal noise and vibration may occur in the test equipment rotating at high speed due to misalignment of the connecting shaft and looseness of the connection, which may lead to a safety accident. In this study, three vibration sensors are attached to the surface of bearing parts of the test motor to measure the vibration value, and statistics such as kurtosis, skewness, and percentiles are obtained in order to clearly express the pattern of the measurement data. With these statistics, machine learning models are developed. The developed model in this way can be used as a diagnostic system that can detect abnormal conditions of the motor test equipment through monitoring the motor vibration data during the motor test.

Anomaly detection for each industrial machine is recognized as one of the essential techniques for machine condition monitoring and preventive maintenance. Anomaly detection of industrial machinery relies on various diagonal data from equipped sensors, such as temperature, pressure, electric current, vibration, and sound, to name a few. Among these data, sound data are easy to collect in the factory due to the relatively low installation cost of microphones to existing facilities. We develop a real time anomalous sound detection (ASD) system with the use of Autoencoder (AE) models in the industrial environments. The proposed processing pipeline makes use of the audio features extracted from the streaming audio signal captured by a single-channel microphone. The pipeline trains AE model by the collected normal sound. In real factory applications, the reconstruction error generated by the trained AE model with new input sound streaming is calculated to measure the degree of abnormality of the sound event. The sound is identified as anomalous if the reconstruction error exceeds the preset threshold. In our experiment on the CNC milling machining, the proposed system shows 0.9877 area under curve (AUC) score.

한국통합물류협회의 발표에 따르면, 2021년도 국내 총 택배 물량은 33억 7천만 개로 전년대비 7.59% 증가했고 매출액은 8조 5,800억 원으로 전년대비 14.6% 증가한 것으로 나타났으며 이러한 증가추세는 향후 지속될 것으로 전망된다. 이러한 택배 물량을 처리함에 있어 작업자는 대표적인 근골격계 부담작업에 노출되어 각종 근골격계 질환 유발 및 능률 저하가 갈수록 심화되고 있는 상황이다. 이에 따라 최신 통신네트워크 기술을 기반으로 하여 작업자와 자율주행 무인 운반차(Automated Guided Vehicle, AGV) 그리고 로봇의 협업을 지원하기 위한 기술개발에 대한 관심이 고조되고 있다. 본 연구에서는 LTE / 5G와 같은 최신 통신네트워크 환경 하에서 물류센터에서 자율주행하면서 택배의 상/하차 작업을 수행하는 Horizontal Scissor Lift를 갖는 AGV를 개발하고 택배 분류작업을 수행하는 로봇이 AGV와 협업을 가능하도록 하여 물류 집하 및 분배 작업이 통합된 물류 자동화 플랫폼을 구축한다. 본 물류 자동화 플랫폼은 자율 주행하면서 택배를 상/하차 하는 Scissor Lift-type AGV, 택배 분류를 위한 로봇, 다수의 AGV의 충돌을 방지하고 작업지시 및 작업상태 확인, 작업결과 피드백 등의 실시간 모니터링을 위한 관제 시스템 등으로 구성된다. 특히, 본 논문에서는 Horizontal Scissor Lift를 갖는 AGV의 구체적인 설계 및 해석결과를 제시하고, AGV 시제품에 대해 이동속도, 긴급 제동거리 및 위치정밀도에 대한 성능 평가를 수행함으로써 개발되는 AGV 시스템의 성능을 검증한다.

The purpose of this study is to develop a pH measurement system capable of measuring the acidity of saliva to check the change in pH level in saliva during driving and to detect whether fatigue is affected. When the pH level is checked at rest and operation, and oxygen concentration is supplied additionally, it will be verified whether the fatigue is reduced. It is reported that the pH level in saliva is divided into stages from 0 to 14, and the lower the value based on step 7, the higher the fatigue, and the lower the fatigue. In particular, in enclosed vehicles, drowsiness and fatigue due to increased carbon dioxide have increased, leading to a major cause of traffic accidents. Therefore, fatigue may be detected in advance by analyzing fatigue through a change in pH level by supplying oxygen during operation. The electromotive force generated by the existing itself is a level of several mV to develop a pH measurement system, so it is developed by expanding it to a range that can be measured using a readout circuit. In the experiment, 13 male experimenters in their 20s measured pH levels in resting and driving conditions. After 20 minutes of rest, the process of inhaling oxygen for 20 minutes was repeated three times. The oxygen concentration used in the experiment was 21% oxygen and 30% oxygen concentration in the atmospheric state, and in the oxygen supply method, a triangular flask was directly connected to the subject’s nose and then oxygen was supplied. As a result of collecting and analyzing saliva after rest and operation, it was confirmed that the pH level tended to decrease in the operating state. In addition, as a result of increasing the pH level when the oxygen concentration is 30% more than 21%, it is confirmed that fatigue tends to decrease as the oxygen concentration increases. Therefore, it was possible to confirm a significant change in fatigue by analyzing the pH level of saliva through this pH measurement system. This study can be used as a fatigue test in various environments through simple pH measurement.

Synthetic Aperture Radar (SAR) images are affected by noise called speckle, which is very severe and may hinder image exploitation. Despeckling is an important task that aims to remove such noise so as to improve the accuracy of all downstream image processing tasks. Many different schemes have been proposed for the restoration of SAR images. Among the different possible approaches, methods based on convolutional neural networks(CNNs) have recently shown to reach state-of-the-art performance for SAR image restoration. DnCNN(DeNoising Convolutional Neural Network) is one of the most widely used neural network architecture embedded in baseline SAR image despeckling methods. In military applications of SAR satellite image, fast processing is the most critical factor except the precision rate of the recognition. In this paper, we propose an improved DnCNN architecture for faster SAR image despeckling. The experimental results on real-world SAR images show that our proposed method takes faster processing time than the original DnCNN architecture without despeckling performance downgrade. Subjective visual inspection demonstrates that the proposed method has great potential in preserving the image signal details and suppressing speckle noise.

현대 사회가 복잡해지고 기술이 진보하면서 하나의 제품을 설계할 때 단일 특성이 아닌 다 특성을 갖는 제품을 설계하는 것이 요구되고 있다. 다 특성 설계 최적화 문제에서는 설계 변수의 최적값이 특성별로 다르게 되는 현상이 발생하고 이에 따라 하나의 특성에 대한 결과값이 좋아지면 다른 특성에 대한 결과값이 나빠지는 경우에 대해서 trade-off가 필요하다. 따라서 다 특성을 갖는 제품 설계 시 각각의 특성에 대한 성능을 최대화할 수 있는 효율적인 설계 방법의 필요성이 중요한 문제로 떠오르고 있다. 다 특성을 갖는 제품을 설계하는 연구는 오래전부터 중요한 문제로 인식되어 왔는데, 단일 특성에 대해 성능을 최대화하며 강건한 설계를 할 수 있는 다구치 기법과 다기준/다특성 의사 결정 방법인 TOPSIS(Technique for Order of Preference by Similarity to Ideal Solution), GRA(Grey relational analysis), PCA(Principle Component Analysis), Fuzzy Logic System을 통합한 연구들이 진행되어 왔다. 하지만 기존 연구들은 각각의 설계 대안들에 대해 다 특성 결과값에 대한 점수를 통합하여 종합 점수를 비교해 최적의 설계안을 도출할 뿐 설계자의 호감도에 대한 정보는 설계에 반영하지 못한다. 따라서 본 연구에서는 다구치 기법을 기반으로 각각의 특성들에 대한 설계자의 서로 다른 호감도를 함수로써 표현하여 강건성과 함께 설계자의 호감도를 동시에 설계에 반영할 수 있는 방법을 제안한다.