In order to predict the process window of laser powder bed fusion (LPBF) for printing metallic components, the calculation of volumetric energy density (VED) has been widely calculated for controlling process parameters. However, because it is assumed that the process parameters contribute equally to heat input, the VED still has limitation for predicting the process window of LPBF-processed materials. In this study, an explainable machine learning (xML) approach was adopted to predict and understand the contribution of each process parameter to defect evolution in Ti alloys in the LPBF process. Various ML models were trained, and the Shapley additive explanation method was adopted to quantify the importance of each process parameter. This study can offer effective guidelines for fine-tuning process parameters to fabricate high-quality products using LPBF.

Gamma Reality Inc. (GRI) provides real-time, mobile 3D radiation mapping, data fusion, and visualization technologies for applications ranging from nuclear power and decommissioning to emergency response. The GRI-LAMP is a compact, multi-sensor system weighing about 10 lbs (4.5 kg). LAMP is fully mobile, provides 360 degree imaging (only limited by physical access to objects/area), and streams the 3D map fused with radiation data in real-time to the control tablet for immediate results that can quickly inform the user of potential hazards in the area or direct the user to the specific location where efforts should be focused. GRI systems are also remotely deployable on robotic platforms and are used on unmanned aerial vehicles (UAS), unmanned ground vehicles (UGV), as well as on manned vehicles and in handheld configurations. This deployment flexibility coupled with real-time data maximizes dose reduction opportunities and further enables dynamic operational planning, which can help reduce the costs of managing and maintaining operational nuclear power plants, as well as decontaminating, or decommissioning nuclear facilities. Applications include, but are not limited to, conducting regular radiation surveys, hotspot localization, shielding verification, radioactive waste shipment surveys, contamination mapping, and dose measurement. GRI’s solutions enable faster, safer, and more efficient radiation detection, mapping, and visualization of source terms and contamination. Commercially available LAMP versions include gamma-ray imaging, dual neutron and gamma mapping, and non-imaging gamma-ray mapping options.

사회기반 시설물의 노후화에 대응해 이상 징후를 파악하고 유지보수를 위한 최적의 의사결정을 내리기 위해선 디지털 기반 SOC 시설물 유지관리 시스템의 개발이 필수적인데, 디지털 SOC 시스템은 장기간 구조물 계측을 위한 IoT 센서 시스템과 축적 데이터 처 리를 위한 클라우드 컴퓨팅 기술을 요구한다. 본 연구에서는 구조물의 다물리량을 장기간 측정할 수 있는 IoT센서와 클라우드 컴퓨팅 을 위한 서버 시스템을 개발하였다. 개발 IoT센서는 총 3축 가속도 및 3채널의 변형률 측정이 가능하고 24비트의 높은 해상도로 정밀 한 데이터 수집을 수행한다. 또한 저전력 LTE-CAT M1 통신을 통해 데이터를 실시간으로 서버에 전송하여 별도의 중계기가 필요 없 는 장점이 있다. 개발된 클라우드 서버는 센서로부터 다물리량 데이터를 수신하고 가속도, 변형률 기반 변위 융합 알고리즘을 내장하 여 센서에서의 연산 없이 고성능 연산을 수행한다. 제안 방법의 검증은 2개소의 실제 교량에서 변위계와의 계측 결과 비교, 장기간 운 영 테스트를 통해 이뤄졌다.

전정색과 다중분광 위성영상으로부터 고해상도 컬러영상을 제작하는 융합기법에 대한 연구가 원격탐사 분야에서 활발하게 진행되어왔다. 기 개발된 많은 영상융합 기법들은 분광대체, 산술병합 그리고 공간영역 등 세 개의 범주로 구분될 수 있다. 본 연구는 기존 고해상도 위성에 비해 공간해상도와 분광해상도가 향상된 WorldView-2 위성에서 제공하는 전정색과 다중분광영상에 적용된 각 범주의 융합영상 결과물 특성을 색상과 공간정보 왜곡 측면에서 분석하였다. 색상정보의 왜곡을 평가하기 위해 평균차, 분산차 및 ERGAS 등의 정량지표를 산출하였고, 공간정보의 왜곡은 시각적 분석에 의해 평가하였다. 본 연구의 결과에 의하면 공간영역에 기초한 융합기법이 다른 범주의 융합에 비해 상대적으로 분광 및 공간정보의 왜곡이 적은 것으로 분석되었다. 따라서 공간영역에 기반한 융합영상은 대축척 주제도 뿐 아니라 온라인 영상지도 제작을 위해 적절한 입력자료로 활용될 것으로 기대된다.

When evaluating effectiveness of a program, there is a tendency to simply compare the performances of the treated before and after the program or to compare the differences in the performances of the treated and the untreated before-after the program. However, these ways of evaluating effectiveness have problems because they can’t account for environmental changes affecting the treated and/or effects coming from the differences between the treated and the untreated. Therefore, in this paper, panel data analysis (fixed effects model) is suggested as a means to overcome these problems and is utilized to evaluate the effectiveness of fusion technology program conducted by Ministry of Trade, Industry and Energy, Korea. As a result, it turns out that the program has definitely positive impacts on the beneficiary in terms of sales, R&D expenditure, and employment.

Fuzzy information representation of multi-source spatial data is applied to landslide hazard mapping. Information representation based on frequency ratio and non-parametric density estimation is used to construct fuzzy membership functions. Of particular interest is the representation of continuous data for preventing loss of information. The non-parametric density estimation method applied here is a Parzen window estimation that can directly use continuous data without any categorization procedure. The effect of the new continuous data representation method on the final integrated result is evaluated by a validation procedure. To illustrate the proposed scheme, a case study from Jangheung, Korea for landslide hazard mapping is presented. Analysis of the results indicates that the proposed methodology considerably improves prediction capabilities, as compared with the case in traditional continuous data representation.

실제증발산 자료를 융합하기 위한 Modified Kling-Gupta efficiency Fusion (KGF)방법을 제시하였고, 인공위성 및 재분석 증발산 자료인 Global Land Data Assimilation System (GLDAS), Global Land Evaporation Amsterdam Model (GLEAM), MODIS Global Evapotranspiration Project (MOD16)를 활용하여 Simple Taylor skill’s Score (STS)와 비교하였다. 한반도와 중국의 세가지 land cover type(i.e., cropland, grassland, forest)을 가진 flux tower에서 비교 검증을 실시하였다. 실제증발산의 융합 방법인 STS와 KGF로 계산된 가중치의 결과를 확인하면, cropland와 grassland에서 재분석 자료(GLDAS, GLEAM)가 높은 가중치 영향을 나타내지만, forest에서 융합 방법에 따라 가중치 영향이 다르게 나타났다. 전반적으로 실제증발산 융합 방법 적용 결과의 비교에서는 cropland에서는 융합에 사용된 자료에 비하여 높은 개선이 이뤄지지 않았지만, grassland와 forest 에서는 개선이 이뤄졌다. 두 방법 중 KGF의 결과가 STS의 결과에 비하여 약간 개선되는 결과를 나타내었다

The finite element (FE) model updating is a commonly used approach in civil engineering, enabling damage detection, design verification, and load capacity identification. In the FE model updating, acceleration responses are generally employed to determine modal properties of a structure, which are subsequently used to update the initial FE model. While the acceleration-based model updating has been successful in finding better approximations of the physical systems including material and sectional properties, the boundary conditions have been considered yet to be difficult to accurately estimate as the acceleration responses only correspond to translational degree-of-freedoms (DOF). Recent advancement in the sensor technology has enabled low-cost, high-precision gyroscopes that can be adopted in the FE model updating to provide angular information of a structure. This study proposes a FE model updating strategy based on data fusion of acceleration and angular velocity. The usage of both acceleration and angular velocity gives richer information than the sole use of acceleration, allowing the enhanced performance particularly in determining the boundary conditions. A numerical simulation on a simply supported beam is presented to demonstrate the proposed FE model updating approach.

This study proposes a FE model updating strategy based on data fusion of acceleration and angular velocity. The use of acceleration and angular velocity gives richer information than the sole use of acceleration, allowing the enhanced performance particularly in determining the boundary conditions. A numerical simulation is presented to demonstrate the proposed FE model updating approach using the data fusion.

A dynamic displacement estimation system is developed by integrating laser Doppler vibromter (LDV) and light detection and ranging (LiDAR). The system includes hardware level integration for simultaneous measurement of two devices and data fusion of two measurement signals based on Kalman filter smoothing algorithms. For hardware integration of two devices, the laser beam directions and the triggering of measurement of LDV and LiDAR are controlled on the level of built-in commands of the devices. The distance data sequentially measured by LiDAR is converted to dynamic displacement of high noise and low sampling rate, and fused with the velocity measured by LDV which has high sampling rate and low noise but accumulated bias error when integrated. Using the Kalman filter based data fusion algorithm, it is able to estimate dynamic displacement in which the drawbacks of two devices are effectively removed. The proposed system is applied to a dynamic loading test on a highway bridge and the performance is verified.

In prestressed concrete (PSC) bridges, structural damage such as concrete cracks is related to the shift of the neutral axis due to the reduction in tendon forces. As such, monitoring the tendon force is important to maintain PSC bridges and prolong its remaining life. However, measuring the tendon force of PSC bridges in service is challenging. This study proposes a data fusion-based tendon force monitoring method using acceleration and strain responses. The proposed approach is validated using a PSC bridge model in the Pukyung National University.

While displacement is valuable information regarding the behavior of structures, measuring displacement from large civil structures is often challenging and costly. This study develops an indirect displacement estimation method based on the multimetric data (i.e., acceleration and strain) that can estimate static as well as dynamic displacements. The approach is numerically validated on a simple-beam model with moving force

This paper proposes a low-complexity indoor localization method of mobile robot under the dynamic environment by fusing the landmark image information from an ordinary camera and the distance information from sensor nodes in an indoor environment, which is based on sensor network. Basically, the sensor network provides an effective method for the mobile robot to adapt to environmental changes and guides it across a geographical network area. To enhance the performance of localization, we used an ordinary CCD camera and the artificial landmarks, which are devised for self-localization. Experimental results show that the real-time localization of mobile robot can be achieved with robustness and accurateness using the proposed localization method.

We propose a optimal fusion method for localization of multiple robots utilizing correlation between GPS on each robot in common workspace. Each mobile robot in group collects position data from each odometer and GPS receiver and shares the position data with other robots. Then each robot utilizes position data of other robot for obtaining more precise estimation of own position. Because GPS data errors in common workspace have a close correlation, they contribute to improve localization accuracy of all robots in group. In this paper, we simulate proposed optimal fusion method of odometer and GPS through virtual robots and position data.