• Composites Research
• /
• v.32 no.1
• /
• pp.21-28
• /
• 2019

Recently, according to environmental regulations, the automobile industry has been conducting various research on the use of composite materials to increase fuel efficiency. However, there has not been much research on lightweight chassis components. Therefore, in this research, the purpose of this study is to apply composite materials to the sub-frame of chassis components to achieve equivalent levels of stiffness, strength, NVH performance and 50% lightweight compared to the steel sub-frame. First, the Natural frequency of steel and composite specimens was compared to the damping characteristics of composite materials. Then, in this study, the Lay-up Sequence was derived to maximize the stiffness and strength of the sub-frame by applying composite materials. And this lay-up Sequence is proposed to avoid heat shrinkage due to curing during manufacturing. This process was designed based on a FEM structural analysis, and a Natural frequency and frequency response function graph was confirmed based on a modal analysis. The prototype type composite sub-frame was manufactured based on the design and the F.E.M analysis was verified through a modal experiment. Furthermore, it was fitted to the actual vehicle to verify the natural frequency and the indoor noise vibration response, including idling and road noise. This result was confirmed to be equivalent to the steel sub-frame. Finally, the composite sub-frame weight was confirmed to be about 50% of the steel sub-frame.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.21 no.3
• /
• pp.419-432
• /
• 2019

Most of deep learning model training was proceeded by supervised learning, which is to train labeling data composed by inputs and corresponding outputs. Labeling data was directly generated manually, so labeling accuracy of data is relatively high. However, it requires heavy efforts in securing data because of cost and time. Additionally, the main goal of supervised learning is to improve detection performance for 'True Positive' data but not to reduce occurrence of 'False Positive' data. In this paper, the occurrence of unpredictable 'False Positive' appears by trained modes with labeling data and 'True Positive' data in monitoring of deep learning-based CCTV accident detection system, which is under operation at a tunnel monitoring center. Those types of 'False Positive' to 'fire' or 'person' objects were frequently taking place for lights of working vehicle, reflecting sunlight at tunnel entrance, long black feature which occurs to the part of lane or car, etc. To solve this problem, a deep learning model was developed by simultaneously training the 'False Positive' data generated in the field and the labeling data. As a result, in comparison with the model that was trained only by the existing labeling data, the re-inference performance with respect to the labeling data was improved. In addition, re-inference of the 'False Positive' data shows that the number of 'False Positive' for the persons were more reduced in case of training model including many 'False Positive' data. By training of the 'False Positive' data, the capability of field application of the deep learning model was improved automatically.

• Journal of Aerospace System Engineering
• /
• v.16 no.2
• /
• pp.63-72
• /
• 2022

As interest in microsatellites increases, research has been actively conducted recently on the performance and use, as well as the orbital design and deployment techniques, for the microsatellite constellations. The purpose of this study was to investigate orbital deployment techniques using thrust and differential atmospheric drag control (DADC) for the Walker-delta constellation. When using thrust, the time and thrust required for orbital deployment vary, depending on the separation speed and direction of the satellite with respect to the launch vehicle. A control strategy to complete the orbital deployment with limited performance of the propulsion system is suggested and it was analyzed. As a result, the relationship between the deployment period and the total thrust consumption was derived. It takes a relatively longer deployment time using differential air drag rather than consuming thrusts. It was verified that the satellites can be deployed only with differential air drag at a general orbit of a microsatellite constellation. The conclusion of this study suggests that the deployment strategy in this paper can be used for the microsatellite constellation.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.103-116
• /
• 2022

The South Korean Ministry of Land, Infrastructure, and Transport designated seven automated driving test beds required to evaluate vehicle performance every year for the expansion of mobility services based on automated driving. As a fundamental study, we suggested a necessary example of evaluating the performance with a satisfaction survey for the services before the evaluation. First, we surveyed the perception of automated driving services of users and the public in Sejong-si, South Korea. The survey showed that the users had a higher level of awareness of automated driving technology and intention to use it than the public. Second, the satisfaction survey was conducted on demand-responsive public transportation and automated driving service users. Notably, using the Wilcoxon Rank Sum Test, among the non-parametric statistical analysis methods, we found that safety-related factors affected the overall satisfaction of users of automated driving services. On the other hand, in the case of the demand-responsive public transportation service users, factors related to service convenience affected overall satisfaction. Hence, the results of these surveys are expected to be used as basic data and guidelines to improve the quality of automated driving services and policy establishment.

• Geophysics and Geophysical Exploration
• /
• v.26 no.4
• /
• pp.171-184
• /
• 2023

Machine learning (ML)-based cavity detection using a large amount of survey data obtained from vehicle-mounted ground penetrating radar (GPR) has been actively studied to identify underground cavities. However, only simple image processing techniques have been used for preprocessing the ML input, and many conventional seismic and GPR data processing techniques, which have been used for decades, have not been fully exploited. In this study, based on the idea that a cavity can be identified using diffraction, we applied ML-based diffraction separation to GPR data to increase the accuracy of cavity detection using the YOLO v5 model. The original ML-based seismic diffraction separation technique was modified, and the separated diffraction image was used as the input to train the cavity detection model. The performance of the proposed method was verified using public GPR data released by the Seoul Metropolitan Government. Underground cavities and objects were more accurately detected using separated diffraction images. In the future, the proposed method can be useful in various fields in which GPR surveys are used.

• Journal of Aerospace System Engineering
• /
• v.18 no.1
• /
• pp.53-63
• /
• 2024

Adopting an engine igniter with high efficiency and ignition performance is essential for reliable operation of liquid rocket engines. In this study, we developed a spark torch igniter for a 450 N-scale methane-oxygen liquid rocket engine by conducting numerical analyses, igniter manufacturing and validation. Specifically, we conducted a parametric study for maximizing the enthalpy at the igniter exit, specifically by adjusting the mass flow rate, nozzle area ratio, fuel-oxidizer mixture ratio, and the igniter length-to-diameter. The heat transferred via the igniter nozzle exit was computed using 3-dimensional numerical simulations. We also manufactured and tested the igniter based on a deduced design to confirm ignition performance of the designed spark torch igniter. The igniter developed through this study could contribute to the development of practical propulsion systems such as upper-stage engines of small launch vehicles.

• Smart Media Journal
• /
• v.13 no.2
• /
• pp.52-61
• /
• 2024

In the shipyard, aerial images are acquired at regular intervals using Unmanned Aerial Vehicles (UAVs) for the management of external storage yards. These images are then investigated by humans to manage the status of the storage yards. This method requires a significant amount of time and manpower especially for large areas. In this paper, we propose an automated management technology based on a semantic segmentation foundation model to address these challenges and accurately assess the status of external storage yards. In addition, as there is insufficient publicly available dataset for external storage yards, we collected a small-scale dataset for external storage yards objects and equipment. Using this dataset, we fine-tune an object detector and extract initial object candidates. They are utilized as prompts for the Segment Anything Model(SAM) to obtain precise semantic segmentation results. Furthermore, to facilitate continuous storage yards dataset collection, we propose a training data generation pipeline using SAM. Our proposed method has achieved 4.00%p higher performance compared to those of previous semantic segmentation methods on average. Specifically, our method has achieved 5.08% higher performance than that of SegFormer.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.3
• /
• pp.111-121
• /
• 2024

Recently, thanks to the development of artificial intelligence technologies such as image recognition, research on unmanned aerial vehicles is being actively conducted. In particular, related research is increasing in the field of military drones, which costs a lot to foster professional pilot personnel, and one of them is the study of an intelligent framework for autonomous mission performance of reconnaissance drones. In this study, we tried to design an intelligent framework for unmanned aerial vehicles using the methodology of designing an intelligent framework for service robots. For the autonomous mission performance of unmanned aerial vehicles, the intelligent framework and unmanned aerial vehicle module must be smoothly linked. However, it was difficult to provide interworking for drones using periodic message protocols with model-based interfaces of intelligent frameworks for existing service robots. First, the message model lacked expressive power for periodic message protocols, followed by the problem that interoperability of asynchronous data exchange methods of periodic message protocols and intelligent frameworks was not provided. To solve this problem, this paper proposes a message model extension method for message periodic description to secure the model's expressive power for the periodic message model, and proposes periodic and asynchronous data exchange methods using the extended model to provide interoperability of different data exchange methods.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.37 no.4
• /
• pp.233-241
• /
• 2024

In this study, finite element analyses of coated steel pipes were conducted to research the development of sensing-based monitoring smart pipes. The coated steel pipes underwent a chemical coating pretreatment process that used modified polyethylene on both the inside and outside surfaces. Furthermore, the steel pipes were designed to minimize damage during the expansion process by incorporating connecting parts. To evaluate structural performance under various loads, four loading conditions were established: static structural analysis by earth pressure, fatigue life evaluation by vehicle load, and resistance to water leakage under both tensile and compressive loads. The analysis estimated a higher fatigue life for the developed steel pipe, compared with that of a steel pipe using ready-made epoxy coatings and joints. In addition, an average maximum displacement reduction of 56.1% and a maximum stress reduction of 61.2% were confirmed under identical conditions and diameters, thereby verifying the safety of the connecting parts of the developed coated steel pipe. Furthermore, the results of stress distribution contour analyses revealed superior water leakage resistance at the fastening parts, compared with the centers of the pipes.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.47-73
• /
• 2020

KTX rolling stocks are a system consisting of several machines, electrical devices, and components. The maintenance of the rolling stocks requires considerable expertise and experience of maintenance workers. In the event of a rolling stock failure, the knowledge and experience of the maintainer will result in a difference in the quality of the time and work to solve the problem. So, the resulting availability of the vehicle will vary. Although problem solving is generally based on fault manuals, experienced and skilled professionals can quickly diagnose and take actions by applying personal know-how. Since this knowledge exists in a tacit form, it is difficult to pass it on completely to a successor, and there have been studies that have developed a case-based rolling stock expert system to turn it into a data-driven one. Nonetheless, research on the most commonly used KTX rolling stock on the main-line or the development of a system that extracts text meanings and searches for similar cases is still lacking. Therefore, this study proposes an intelligence supporting system that provides an action guide for emerging failures by using the know-how of these rolling stocks maintenance experts as an example of problem solving. For this purpose, the case base was constructed by collecting the rolling stocks failure data generated from 2015 to 2017, and the integrated dictionary was constructed separately through the case base to include the essential terminology and failure codes in consideration of the specialty of the railway rolling stock sector. Based on a deployed case base, a new failure was retrieved from past cases and the top three most similar failure cases were extracted to propose the actual actions of these cases as a diagnostic guide. In this study, various dimensionality reduction measures were applied to calculate similarity by taking into account the meaningful relationship of failure details in order to compensate for the limitations of the method of searching cases by keyword matching in rolling stock failure expert system studies using case-based reasoning in the precedent case-based expert system studies, and their usefulness was verified through experiments. Among the various dimensionality reduction techniques, similar cases were retrieved by applying three algorithms: Non-negative Matrix Factorization(NMF), Latent Semantic Analysis(LSA), and Doc2Vec to extract the characteristics of the failure and measure the cosine distance between the vectors. The precision, recall, and F-measure methods were used to assess the performance of the proposed actions. To compare the performance of dimensionality reduction techniques, the analysis of variance confirmed that the performance differences of the five algorithms were statistically significant, with a comparison between the algorithm that randomly extracts failure cases with identical failure codes and the algorithm that applies cosine similarity directly based on words. In addition, optimal techniques were derived for practical application by verifying differences in performance depending on the number of dimensions for dimensionality reduction. The analysis showed that the performance of the cosine similarity was higher than that of the dimension using Non-negative Matrix Factorization(NMF) and Latent Semantic Analysis(LSA) and the performance of algorithm using Doc2Vec was the highest. Furthermore, in terms of dimensionality reduction techniques, the larger the number of dimensions at the appropriate level, the better the performance was found. Through this study, we confirmed the usefulness of effective methods of extracting characteristics of data and converting unstructured data when applying case-based reasoning based on which most of the attributes are texted in the special field of KTX rolling stock. Text mining is a trend where studies are being conducted for use in many areas, but studies using such text data are still lacking in an environment where there are a number of specialized terms and limited access to data, such as the one we want to use in this study. In this regard, it is significant that the study first presented an intelligent diagnostic system that suggested action by searching for a case by applying text mining techniques to extract the characteristics of the failure to complement keyword-based case searches. It is expected that this will provide implications as basic study for developing diagnostic systems that can be used immediately on the site.