지난 10년간 국내 고속도로의 관리 대상 구조물 수는 2013년 8,302개소에서 2023년 11,054개소로 약 25% 증가했다. 특히, 공용 20~30년 미만의 교량이 전체 교량의 약 40%를 차지하고 있으며, 이들 교량의 노후화가 향후 10년 내 집중적으로 발생할 것으로 예상 된다. 이에 따라 유지관리 비용이 급격히 증가할 것으로 전망된다. 효율적인 자산관리를 위해서는 상태평가 결과를 바탕으로 예측모델 을 적용하여 구조물의 성능과 생애주기 비용을 예측하는 것이 중요하다. 그러나, 유지관리에 따른 구조물 성능향상과 열화모델 적용 등 다양한 변수를 고려한 예측모델 적용할 때, 인력점검의 한계와 점검자의 주관적 판단에 따른 점검오차를 최소해야만 개별 구조물 의 현재 상태에 대한 정확한 평가가 가능할 것이다. 이와 관련하여 본 연구에서는 자산관리 개선을 위한 추진전략과 상태평가 신뢰성 확보를 위한 신기술 적용방안을 제시하고자 한다. 따라서, 교량 자산가치평가 정확도 향상을 위해 BIM(Building Information Modeling) 모델 제작 및 손상평가 AI(Artificial Intelligence) 기술을 적용한 ‘BIM 기반 외관조사망도 자동생성 시스템’을 통해 인력점검의 한계와 점검오차로 인한 문제를 개선하고자 하며, 점검/진단 자동화 기술을 구조물 유지관리 업무 시스템에 연계하여 손상정도를 시계열로 모 니터링하고, 최적 보수시기 및 공법 선정 의사결정에 활용할 수 있으며, 보수·보강 비용 및 조치편익을 분석하여 유지관리 사업계획 수립 시 활용할 수 있을 것으로 판단된다. 향후 ‘점검/진단 자동화 시스템‘을 고속도로 자산관리에 시범적으로 적용하여 실제 현장 점 검자의 사용성 검증과 시스템 운영방안 수립을 통해 효율적 자산관리를 위한 도로관리자의 의사결정을 지원할 수 있을 것으로 기대한다.

We introduce the technology required todevelop a bracket process for installing and verifying FRT bumper sensors for passenger cars. Establish and demonstrate process automation through actual design and manufaturing. We conduct quality inspection of the production process using artificial intelligence and develop technology to automatically detect good and defective products and increase the reliability of the process

Considering the difficulties of the manufacturing industry by improving production efficiency in the era of high wages and aging in domestic automation facilities, automation facilities are considered an irreversible trend, but many serious related disasters are occurring due to the problems of increasing automation facilities due to the enlargement of manufacturing processes, line-up, and automation. The purpose of this study is to review the usage conditions and safety measures for industrial robots that are experiencing serious industrial accidents and are expected to continue to increase in facilities among automation facilities at the automation industrial site and propose ways to ensure the fundamental safety of the facilities at all times The suggestions are as follows. The purpose is to prevent safety accidents in advance by applying safety door aids to industrial sites and installing additional safety devices in safety slide door lock systems applied to safety fence doors of new and already installed facilities to detach safety keys and ensure that workers carry them at all times.

This study selected two labor-intensive processes in harsh environments among domestic food production processes. It analyzed their improvement effectiveness using 3-dimensional (3D) simulation. The selected processes were the “frozen storage source transfer and dismantling process” (Case 1) and the “heavily loaded box transfer process” (Case 2). The layout, process sequence, man-hours, and output of each process were measured during a visit to a real food manufacturing factory. Based on the data measured, the 3D simulation model was visually analyzed to evaluate the operational processes. The number of workers, work rate, and throughput were also used as comparison and verification indicators before and after the improvement. The throughput of Case 1 and Case 2 increased by 44.8% and 69.7%, respectively, compared to the previous one, while the utilization rate showed high values despite the decrease, confirming that the actual selected process alone is a high-fatigue and high-risk process for workers. As a result of this study, it was determined that 3D simulation can provide a visual comparison to assess whether the actual process improvement has been accurately designed and implemented. Additionally, it was confirmed that preliminary verification of the process improvement is achievable.

This paper describes the development and operation of an autonomous robotic system designed for pyroprocess automation. The unique challenges of pyroprocess automation, such as the need for a highly dry atmosphere to handle materials like chloride, are addressed through this system. For the experiments, a specialized dehumidifier and dry mock-up facility were designed to produce dry air condition. Performances of dry air conditioning for the various simulated situations were evaluated, including assessing worker access within a mock-up to determine the system’s feasibility. To enable automation, containers used for processing materials were modified to fit the gripper system of the gantry robot. The loading and unloading of materials in each equipment were automated to connect them with the robotic system. This gantry robot primarily utilized macro motions to approach waypoints containing process materials, reducing the need for precise approach motions. Its tapered jaw design allowed it to grip target objects even with imperfect positioning. The robot’s motions were programmed initially using a robot simulator for positioning and motion planning, and real-world accuracy was tested in a dry mock-up facility using the OPC platform. Finally, the paper discusses the potential application of XR (eXtended Reality) technology in this context, which could enhance the robot’s operation and provide valuable insights into the automation process. Further analysis of XR technology’s feasibility and benefits for this specific pyroprocess automation system are presented.

Recently, in the case of the root industry, although it is a basic industry that forms the basis of manufacturing competitiveness, there continues to be a shortage of manpower due to reasons such as dangerous working environments, industrial economic difficulties, and low wage systems. In addition, the demand for automation of production lines using robots is increasing due to a shrinking labor market due to a decrease in the working population due to aging, higher wages, shorter working hours, and limitations of foreign workers. In this study, a system was developed to automate the injection molding process for producing ball valves for automobiles by applying robot system. The applied process flow consists of alignment and insertion of insert parts, and removal, transfer, and loading of the product after injection molding, which is currently performed manually. Through the application of the developed robot automation system, the cycle time was improved by more than 30% and the defect rate was reduced by more than 70%.

Technological breakthroughs, combined with the demographic challenges of an aging population and the aftermath of the COVID-19 pandemic, spur new business opportunities in the service robot industry. From a management perspective, these technologies are positively evaluated in terms of increasing productivity, new business opportunities, and financial benefits (Belanche et al., 2020). However, although automation and robotics have already gained attention in the tourism and hospitality industry, research on their use in restaurants and the customer's attitude toward these new service solutions is still limited (Berezina et al., 2019; Ivanov et al., 2019; Kuo et al., 2017).

Radioactive waste can be classified according to the concentration level for radionuclides, and the disposal method is different through the level. Gamma analysis is inevitably performed to determine the concentration of radioactive waste, and when a large amount of radioactive waste is generated, such as decommissioning nuclear facilities, it takes a lot of time to analyze samples. The performance of a lot of analysis can cause human errors and workload. In general, gamma analysis is performed using by HPGe detector. Recently, for convenience of analysis, commercial automatic sample changers applicable to the HPGe detectors were developed. The automatic sample changers generate individual analysis reports for each sample. In this study, gamma analysis procedure was improved using the application of the automatic sample changer and the automated data parsing using by Python. The application of automatic sample changers and data parsing technique can solve the problems. The human errors were reduced to 0% compared to the previous method by improving the gamma analysis procedure, and working time were also dramatically reduced. This automation of analysis procedure will contribute to reducing the burden of analysis work and reducing human errors through various improvements.

Concrete radioactive waste is divided into surface-contaminated concrete and activated concrete, and although the generation rate varies depending on the operating conditions of the nuclear power plant, it is reported that the amount of surface-contaminated concrete generated is greater. It is reported in the ‘US-NRC Inventory Report’ that 99% of radionuclides in surface-contaminated concrete are distributed within 1 mm of the surface. Since concrete radioactive waste accounts for a large amount of generation after metal radioactive waste, it is necessary to reduce the amount of radioactive waste disposal by applying appropriate treatment techniques to surface-contaminated concrete. In this study, a similar contamination environment work space with the size of 5.4 (W) × 3.6 (L) × 2.5 (H) [m] in which concrete specimens can be fixed on the wall and floor was established. And an integrated decontamination equipment was verified the automation performance for ‘location accuracy’, ‘radioactive contamination level measurement’ and ‘concrete surface laser scabbling’. It was confirmed that the average was 8.3 [mm] in the evaluation of the ‘location accuracy’ for the remote control and movement of the integrated decontamination equipment. For performance verification of ‘radioactive contamination level measurement’ and ‘laser scabbling’, it were used that size of 30×30×8 [cm] ordinary concrete specimens and concrete radioactively contaminated with Co-60 below the regulatory exemption concentration. ‘Radioactive contamination level measurement’ is measured as much as the set range, divied and display the measured values in different colors on the map of the control program. Ordinary concrete specimens are 0.066~0.089 μ Sv/hr, and contaminated concrete specimens are 0.107~0.121 μ Sv/hr, and it was confirmed that they are expressed in different colors on the map. For ‘laser scabbling’, the performance according to the laser scabbling speed and reproducibility with ordinary concrete specimens was verified. As a result, a weight change of up to 1.48 kg was confirmed. Contaminated concrete specimens were subjected to a direct method using a surface contamination detector and an indirect method using a smear paper to measure surface contamination before and after scabbling, and the debris generated after scabbling was analyzed using HPGe.

Recently, the development of computer vision with deep learning has made object detection using images applicable to diverse fields, such as medical care, manufacturing, and transportation. The manufacturing industry is saving time and money by applying computer vision technology to detect defects or issues that may occur during the manufacturing and inspection process. Annotations of collected images and their location information are required for computer vision technology. However, manually labeling large amounts of images is time-consuming, expensive, and can vary among workers, which may affect annotation quality and cause inaccurate performance. This paper proposes a process that can automatically collect annotations and location information for images using eXplainable AI, without manual annotation. If applied to the manufacturing industry, this process is thought to save the time and cost required for image annotation collection and collect relatively high-quality annotation information.

Thin-film shape technology is recognized for its core technology to enhance the technology of LCD, PDP, semiconductor manufacturing processes, hard disks and optical disks, and is widely used to form coated thin films of products. In addition, resistance (electron beam filament) technology for heating is used to manufacture filament for ion implants used in semiconductor manufacturing processes. By establishing an electronic beam filament production system and developing seven specifications of electronic beam filament, it is contributing to improving trade dynamics and increasing exports to Japan through localized media of theoretical imports to domestic companies. In this study, CAE analysis was performed after setting electron beam filament specification and development objectives, facilities and fabrication for electron beam filament production, electron beam filament JIG & fixture design and fabrication followed by electron beam filament prototype. Then, the automation and complete inspection equipment of the previously developed electronic beam filament manufacturing facilities was developed and researched to mass-produce them, to analyze and modify prototypes, design and manufacture automation facilities, and finally, to design and manufacture the complete inspection equipment. In this paper, design and manufacture of electronic beam filament automation facilities for mass production were dealted with.

During the decommissioning of nuclear facilities, 3D digital model that precisely describes the work environment can expedite the accomplishment of the work. Thus, the workers’ exposure to radiation is minimized and the safety risk to the workers is reduced, while precluding inadvertent effects on the environment. However, it is common that the 3D model does not exist for legacy nuclear facilities as most of the initial design drawings are 2D drawings and even some of the 2D drawings are missing. Even in the case that all of the 2D drawings are intact, these initial design drawings need to be updated using asbuilt data because facilities get modified through years of operation. In those cases, 3D scanning can be a good option to quickly and accurately generate a structure’s actual 3D geometric information. 3D scanning is a technique used to capture the shape of an object in the form of point cloud. Point cloud is a collection of large number of points on the external surfaces of objects measured by 3D scanners. The conversion of point cloud to 3D digital model is a labor-intensive process as a human worker needs to recognize objects in the point cloud and convert the objects into 3D model, even though some of the conversion process can be automated by using commercial software packages. With the aim of full automation of scan-to-3D-model process, deep learning techniques that take point cloud as input and generate corresponding 3D model have been studies recently. This paper introduces an efficient scan simulation method. The simulator generates synthetic point cloud data used to train deep learning models for classifying reactor parts in robotic nuclear decommissioning system. The simulator is built by implementing a ray-casting mechanism using a python library called ‘Pycaster’. In order to improve the speed of simulation, multiprocessing is applied. This paper describes the ray casting simulation mechanism and compares the in-house scan simulator with an open source sensor simulation package called Blensor.

This thesis relates to developing an index drilling automation system that quickly and efficiently processes a hole in a product by a rotating robot arm and transfer devices. Static structural analysis was performed using the ANSYS Mechanical program to evaluate the structural stability of the system. According to the research, the equivalent stress value is low overall, and the minimum safety factor is 4.42, so it seems structurally safe. This system will significantly help improve productivity through unmanned work as it can control and set the drill and index simultaneously on the control panel in conjunction with the training.