• Textile Coloration and Finishing
• /
• v.35 no.1
• /
• pp.29-41
• /
• 2023

This study is about a hybrid lightweight cowl crossbeam structure with high rigidity and ability to absorb collision energy to support the cockpit module, which is an automobile interior part, and to absorb energy during a collision. It is a manufacturing process in which composite material bracket parts are inserted and injected into existing steel bars. When considering the mounting condition of a vehicle, the optimization of the fastening condition of the two parts and the mechanical properties of the composite material is acting as an important factor. Therefore, this study is about a composite material having a volume content of Polyamide(PA) and Glass Fiber used as a composite material for a composite material-metal hybrid cowl crossbeam. As a result of analyzing the physical properties of the PA/GF composite material, experimental data were obtained that can further enhance tensile strength and flexural strength by using PA66 rather than PA6 used as a base material for the composite material. And based on this, it contributed to securing the advantage of lightening by using high-stiffness composite material by improving the high disadvantage of the weight of the cowl crossbeam material, which was made only of existing metal materials.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.117-124
• /
• 2023

In the machine vision inspection equipment, diameter measurement is important process in inspection of cylindrical object. However, machine vision inspection equipment requires complex algorithm processing such as camera distortion correction and perspective distortion correction, and the increase in processing time and cost required for precise diameter measurement. In this paper, we proposed the algorithm for diameter measurement of cylindrical object using the laser displacement sensor. In order to fit circle for given four input outer points, grid search algorithms using root-mean-square error and mean-absolute error are applied and compared. To solve the limitations of the grid search algorithm, we finally apply the singular-value-decomposition based circle fitting algorithm. In order to compare the performance of the algorithms, we generated the pseudo data of the outer points of the cylindrical object and applied each algorithm. As a result of the experiment, the grid search using root-mean-square error confirmed stable measurement results, but it was confirmed that real-time processing was difficult as the execution time was 10.8059 second. The execution time of mean-absolute error algorithm was greatly improved as 0.3639 second, but there was no weight according to the distance, so the result of algorithm is abnormal. On the other hand, the singular-value-decomposition method was not affected by the grid and could not only obtain precise detection results, but also confirmed a very good execution time of 0.6 millisecond.

• Composites Research
• /
• v.36 no.4
• /
• pp.241-245
• /
• 2023

Aluminum (Al) and copper(Cu) are non-ferrous alloys with excellent electrical and thermal conductivity but have relatively lower mechanical properties than iron alloys. Stainless steel(STS), an iron alloy, is a high-strength industrial material due to its excellent mechanical properties and corrosion resistance compared to non-ferrous Al and Cu. In this research combined Al, Cu, and STS to fabricate as a functionally graded material (FGM) through a powder metallurgical process. The produced FGM exhibited lightweight and excellent surface hardness compared to copper and iron alloys and also showed higher thermal conductivity than single Al and STS materials.

• Steel and Composite Structures
• /
• v.42 no.1
• /
• pp.33-48
• /
• 2022

This paper researches a lightweight composite structure referred to as the Profiled Steel Sheeting Dry Board (PSSDB). It is fundamentally produced by connecting a Profiled Steel Sheeting to Dry Board using mechanical screws. It is mainly employed as floor panels. However, almost all studies have focused on researching the one-way structural performance. Therefore, this study focuses on the bending behaviour of the two-way PSSDB floor system using both of Finite Element (FE) and Experimental analysis. Four panels were used in the experimental tests, and a mild steel plate has been applied at the bottom for two panels. For the FE process, models were created using ABAQUS software. 4 parametric studies have been utilized to understand the system's influential elements. From the experimental tests, it was found that using Steel Plate shall optimize the two-way action of the system and depending on the type of dry board the improvement in stiffness may reach up to 38%. It was shown from the FE analysis that the dry board, profiled steel sheeting and steel plat can affect the system by up to 10 %, 17% and 3% respectively, while applying a uniform load demonstrate a better two-way action.

• Journal of Powder Materials
• /
• v.30 no.3
• /
• pp.262-267
• /
• 2023

Boron carbide (B₄C) is highly significant in the production of lightweight protective materials when added to aluminum owing to its exceptional mechanical properties. In this study, a method for fabricating Al-B₄C composites using high-energy ball milling and directed energy deposition (DED) is presented. Al-4 wt.% B4C composites were fabricated under 21 different laser conditions to analyze the microstructure and mechanical properties at different values of laser power and scan speeds. The composites fabricated at a laser power of 600 W and the same scan speed exhibited the highest hardness and generated the fewest pores. In contrast, the composites fabricated at a laser power of 1000 W exhibited the lowest hardness and generated a significant number of large pores. This can be explained by the influence of the microstructure on the energy density at different values of laser power.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.223-224
• /
• 2023

Optimal fleet management in the planning stage is one of the most critical activities that guarantee successful construction projects. In South Korea, the construction standard production rate database (CSPRD) is normally employed. However, when it comes to a trade-off problem that involves decision-making on optimal sets of equipment to perform a certain task, the method will require the planners' in-depth knowledge and experience regarding the target process and a time consuming estimation of the performance of every possible scenario must be conducted for the deduction of the optimal fleet management. On this account, this research paper proposes a lightweight method of using mixed integer nonlinear programming (MINLP) in multi-objective problems based on CSPRD-based mathematical equations to assist planners in the preplanning stage of choosing the optimal sets of types and size machinery to efficiently arrange the construction scheduling and budgeting.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.319-325
• /
• 2023

In this study, we proposed a method for hyperparameter optimization in the building and training of a deep learning model designed to process point cloud data collected by a millimeter-wave radar system. The primary aim of this study is to facilitate the deployment of a baseline model in resource-constrained IoT devices. We evaluated a RadHAR baseline deep learning model trained on a public dataset composed of point clouds representing five distinct human activities. Additionally, we introduced a coarse-to-fine hyperparameter optimization procedure, showing substantial potential to enhance model efficiency without compromising predictive performance. Experimental results show the feasibility of significantly reducing model size without adversely impacting performance. Specifically, the optimized model demonstrated a 3.3% improvement in classification accuracy despite a 16.8% reduction in number of parameters compared th the baseline model. In conclusion, this research offers valuable insights for the development of deep learning models for resource-constrained IoT devices, underscoring the potential of hyperparameter optimization and model size reduction strategies. This work contributes to enhancing the practicality and usability of deep learning models in real-world environments, where high levels of accuracy and efficiency in data processing and classification tasks are required.

• Steel and Composite Structures
• /
• v.49 no.6
• /
• pp.645-666
• /
• 2023

Due to the steadily declining supply of natural coarse aggregates, the concrete industry has shifted to substituting coarse aggregates generated from byproducts and industrial waste. Oil palm shell is a substantial waste product created during the production of palm oil (OPS). When considering the usage of OPSC, building engineers must consider its uniaxial compressive strength (UCS). Obtaining UCS is expensive and time-consuming, machine learning may help. This research established five innovative hybrid AI algorithms to predict UCS. Aquila optimizer (AO) is used with methods to discover optimum model parameters. Considered models are artificial neural network (AO - ANN), adaptive neuro-fuzzy inference system (AO - ANFIS), support vector regression (AO - SVR), random forest (AO - RF), and extreme gradient boosting (AO - XGB). To achieve this goal, a dataset of OPS-produced concrete specimens was compiled. The outputs depict that all five developed models have justifiable accuracy in UCS estimation process, showing the remarkable correlation between measured and estimated UCS and models' usefulness. All in all, findings depict that the proposed AO - XGB model performed more suitable than others in predicting UCS of OPSC (with R², RMSE, MAE, VAF and A_15-index at 0.9678, 1.4595, 1.1527, 97.6469, and 0.9077). The proposed model could be utilized in construction engineering to ensure enough mechanical workability of lightweight concrete and permit its safe usage for construction aims.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.774-776
• /
• 2024

The effective implementation of advanced speech recognition (ASR) systems necessitates the deployment of sophisticated keyword spotting models that are both responsive and resource-efficient. The initial local detection of user interactions is crucial as it allows for the selective transmission of audio data to cloud services, thereby reducing operational costs and mitigating privacy risks associated with continuous data streaming. In this paper, we address these needs and propose utilizing the Whisper-Tiny model with fine-tuning process to specifically recognize keywords from google speech dataset which includes 65000 audio clips of keyword commands. By adapting the model's encoder and appending a lightweight classification head, we ensure that it operates within the limited resource constraints of local devices. The proposed model achieves the notable test accuracy of 92.94%. This architecture demonstrates the efficiency as on-device model with stringent resources leading to enhanced accessibility in everyday speech recognition applications.

• The Research Journal of the Costume Culture
• /
• v.26 no.4
• /
• pp.503-518
• /
• 2018

The purpose of this study is to illustrate the design of safety suits based on energy-harvesting technology, particularly targeting street cleaners who must work at night with high mobility. The design focuses on applying lightweight energy-harvesting tools and illuminant into the wear. The design development reflects feedback from testers collected via survey constituting a key methodology. The development process has two main stages. Each stage uses a process of design prototyping, internal examination, test sampling, test wearing, and wearers' feedback via survey that consists of questions on visibility, wearing convenience, and washability. The first stage results show the design of safety suits with energy-harvested LED illuminant inserted and the survey results collected from street cleaners dressed in 4 sample and 80 actual suits in total. Improved based on the first-stage survey results, the second stage designs the suits with detachable energy-harvested EL tape. From these 5 sample and 30 actual second-stage suits, the additional survey indicates that this second-stage design facilitates more visibility and convenience in washing and wearing than the first-stage design. Accordingly, one can expect that this new design can apply not only to safety suits for night workers but also to handicapped or outdoor sportswear applications in the future.