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.

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%.

This study focuses on the development of a Last-Mile delivery service using unmanned vehicles to deliver goods directly to the end consumer utilizing drones to perform autonomous delivery missions and an image-based precision landing algorithm for handoff to a robot in an intermediate facility. As the logistics market continues to grow rapidly, parcel volumes increase exponentially each year. However, due to low delivery fees, the workload of delivery personnel is increasing, resulting in a decrease in the quality of delivery services. To address this issue, the research team conducted a study on a Last-Mile delivery service using unmanned vehicles and conducted research on the necessary technologies for drone-based goods transportation in this paper. The flight scenario begins with the drone carrying the goods from a pickup location to the rooftop of a building where the final delivery destination is located. There is a handoff facility on the rooftop of the building, and a marker on the roof must be accurately landed upon. The mission is complete once the goods are delivered and the drone returns to its original location. The research team developed a mission planning algorithm to perform the above scenario automatically and constructed an algorithm to recognize the marker through a camera sensor and achieve a precision landing. The performance of the developed system has been verified through multiple trial operations within ETRI.

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.

In an automotive plant, an automated storage and retrieval system (ASRS) synchronizes material handling flows from a part production line to an auto-assembly line. The part production line transfers parts on small-/large-sized pallets. The products on pallets are temporarily stored on the ASRS, and the ASRS retrieves the products upon request from the auto-assembly line. Each ASRS aisle is equipped with narrow-/wide-width racks for two pallet sizes. An ASRS aisle with narrow-/wide-width racks improves both storage space utilization and crane utilization while requiring delicate ASRS aisle design, i.e., the locations of the narrow-/wide-width racks in an ASRS aisle, and proper operation policies affect the ASRS performance over demand fluctuations. We focus on operation policies involving a common storage zone using wide-width racks for two pallet sizes and a storage-retrieval job-change for a crane based on assembly-line batch size. We model a discrete-event simulation model and conduct extensive experiments to evaluate operation policies. The simulation results address the best ASRS aisle design and suggest the most effective operation policies for the aisle design.

Recently, many studies are being conducted to extract emotion from text and verify its information power in the field of finance, along with the recent development of big data analysis technology. A number of prior studies use pre-defined sentiment dictionaries or machine learning methods to extract sentiment from the financial documents. However, both methods have the disadvantage of being labor-intensive and subjective because it requires a manual sentiment learning process. In this study, we developed a financial sentiment dictionary that automatically extracts sentiment from the body text of analyst reports by using modified Bayes rule and verified the performance of the model through a binary classification model which predicts actual stock price movements. As a result of the prediction, it was found that the proposed financial dictionary from this research has about 4% better predictive power for actual stock price movements than the representative Loughran and McDonald’s (2011) financial dictionary. The sentiment extraction method proposed in this study enables efficient and objective judgment because it automatically learns the sentiment of words using both the change in target price and the cumulative abnormal returns. In addition, the dictionary can be easily updated by re-calculating conditional probabilities. The results of this study are expected to be readily expandable and applicable not only to analyst reports, but also to financial field texts such as performance reports, IR reports, press articles, and social media.

The structural analysis module is an essential part of any integrated structural system. Diverse integrated systems today require, from the analysis module, efficient real-time responses to real-time input such as earthquake signals, extreme weather-related forces, and man-made accidents. An integrated system may also be for the entire life span of a civil structure conceived during the initial conception, developed throughout various design stages, effectively used in construction, and utilized during usage and maintenance. All these integrated systems’ essential part is the structural analysis module, which must be automated and computationally efficient so that responses may be almost immediate. The finite element method is often used for structural analysis, and for automation, many effective finite element meshes must be automatically generated for a given analysis. A computationally efficient finite element mesh generation scheme based on the r-h method of mesh refinement using strain deviations from the values at the Gauss points as error estimates from the previous mesh is described. Shape factors are used to sort out overly distorted elements. A standard cantilever beam analyzed by four-node plane stress elements is used as an example to show the effectiveness of the automated algorithm for a time-domain dynamic analysis. Although recent developments in computer hardware and software have made many new applications in integrated structural systems possible, structural analysis still needs to be executed efficiently in real-time. The algorithm applies to diverse integrated systems, including nonlinear analyses and general dynamic problems in earthquake engineering.

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.

The management of algal bloom is essential for the proper management of water supply systems and to maintain the safety of drinking water. Chlorophyll-a(Chl-a) is a commonly used indicator to represent the algal concentration. In recent years, advanced machine learning models have been increasingly used to predict Chl-a in freshwater systems. Machine learning models show good performance in various fields, while the process of model development requires considerable labor and time by experts. Automated machine learning(auto ML) is an emerging field of machine learning study. Auto ML is used to develop machine learning models while minimizing the time and labor required in the model development process. This study developed an auto ML to predict Chl-a using auto sklearn, one of most widely used open source auto ML algorithms. The model performance was compared with other two popular ensemble machine learning models, random forest(RF) and XGBoost(XGB). The model performance was evaluated using three indices, root mean squared error, root mean squared error-observation standard deviation ratio(RSR) and Nash-Sutcliffe coefficient of efficiency. The RSR of auto ML, RF, and XGB were 0.659, 0.684 and 0.638, respectively. The results shows that auto ML outperforms RF, and XGB shows better prediction performance than auto ML, while the differences between model performances were not significant. Shapley value analysis, an explainable machine learning algorithm, was used to provide quantitative interpretation about the model prediction of auto ML developed in this study. The results of this study present the possible applicability of auto ML for the prediction of water quality.