A Transformer model to predict the remaining useful life of a fuel cell, which has demonstrated superior performance in analyzing time series data. The dataset was created from long-term performance evaluation experiments conducted in rated power mode, with measurements taken every 10 hours. We preprocessed the raw data using a moving average, allocating 70% for training and 30% for evaluation. The model's performance, evaluated through MAE, MSE, and MAPE, was excellent. The fuel cell's critical voltage, defined as 94.5% of its initial voltage, was measured at 0.719 V. During the experimental run, the actual critical time was 106.6 hours, while the model predicted 106.8 hours, resulting in a 0.19% error. Since the predictions were based on data collected up to 93 hours, the estimated remaining life was 13.8 hours.

In the case of TV products, space constraints and design requirements make it advantageous to use a worm gear that has a small volume and a self-locking function. Single enveloping worm gear teeth are classified as ZA, ZN, ZK, ZI, and ZC according to international standards. However, combining worm shafts and worm wheels with different tooth profiles can significantly worsen meshing transmission errors and reduce the lifespan of the worm gear. Despite these challenges, due to processing limitations, ease of manufacturing, and cost reduction, combinations of worm shafts and worm wheels with different tooth profiles are still considered. In this study, we confirmed the meshing transmission error for a worm gear that combined a ZA tooth shape worm shaft with a ZI tooth shape worm wheel. Additionally, we examined the contact stress and fatigue life characteristics of the material combinations using finite element analysis (FEM).

This study proposed a conditional generative adversarial network (cGAN) model for predicting steel plate deformation based on heating line positions in a line heating process. A database was constructed by performing finite element analysis (FEA) to establish relationships between heating line positions and deformation shapes. Deformation shapes were converted into color map images. Heating line positions were used as conditional labels for training and validating the proposed model.
During the training process, generator and discriminator loss values, along with MSE and R² metrics, converged stably, demonstrating that generated images closely resembled the actual data. Validation results showed that predicted deformation magnitudes had an average relative error of approximately 3% and a maximum error of less than 7%. These findings confirm that the proposed model can effectively predict steel plate deformation shapes based on heating line positions in the line heating process, making it a reliable predictive tool for this application.

Holonic Manufacturing Systems (HMSs) are regarded as a foundation of cyber-physical production systems as they enable computers to conduct intelligent process planning, scheduling, and control by endowing manufacturing components with autonomy and collaboration. In an HMS, autonomy is realized by specifying holons that represent virtual agents of manufacturing components, while collaboration is facilitated through a communication mechanism that enables data exchange and decision making throughout a holarchy of holons without human intervention. This study presents the development of a virtualized holon model and a predictive process planning procedure using the Asset Administration Shell (AAS), i.e., a standardized model that can identify digital representation of manufacturing components to ensure interoperability. Specifically, an AAS-based information model was proposed to define operator, machine, product, and order holons. In addition, a predictive process planning procedure based on the Contract Net Protocol was developed to automatically allocate tasks while predicting task execution times. This study can contribute to the designing of an AAS- domain specific information model for HMS to increase interoperability in the holon holarchy, exhibiting the feasibility of AAS applications in predictive process planning on HMS.

This paper proposes an algorithm to improve path planning and tracking performance for autonomous robots using a Four- Wheel Steering (4WS) system in constrained environments. Traditional Ackermann steering systems face limitations in narrow spaces, which the 4WS system aims to address. By extending the Hybrid A* algorithm to adapt to the unique characteristics of the 4WS system, and integrating it with Model Predictive Control, the study achieves efficient path planning and precise tracking in complex environments. A distinctive aspect of the proposed approach is its adaptive control strategy, dynamically switching between three modes—Normal driving, Pivot, and Parallel movement—based on the vehicle's motion state, thus enhancing both flexibility and efficiency. The algorithm's performance was validated through MATLAB simulations in a logistics warehouse setting, showing high path tracking accuracy in confined spaces. The study effectively demonstrates the feasibility of the proposed method in a simulated environment.

In continuous-process systems, failures of rolling-element bearings typically cause accidents, reduced productivity, and production-related financial losses. Therefore, predicting both the lifespan of rolling-element bearings and their replacement time is crucial for preventing machine system failures. Accordingly, numerous studies have reported various machine and deep learning classifiers for predicting the lifespan of bearings. However, these studies did not consider degradation trends of bearings. Thus, this study aimed to develop an algorithm to predict the lifespan of a bearing by considering its degradation trend. A vibration dataset of bearings was obtained at low and high speeds. Using a second-order curve-fitting model, various degradation patterns in the dataset were classified. Appropriate time-domain or frequency-domain feature variables applicable to the design of a classifier were determined according to classified patterns. In addition, the classifier was trained using multiple bidirectional long short-term memories. Finally, the performance of the developed classifier was verified experimentally.

With the recent development of 3D printing technology, various 3D printing materials have been developed and used. To utilize 3D-printed products with mechanical parts, studies on friction and wear characteristics according to relative motion between materials are required. However, tribology studies on 3D-printed materials are limited compared to those of the existing materials for mechanical parts. In this study, the frictional and wear characteristics are identified through a reciprocating wear test in non lubricated conditions between the Polylactic Acid (PLA) and Polyethylene Terephthalate Glycol (PETG) printed in the Fused Deposition Modeling (FDM) method. In the wear test between the same materials, the friction coefficient and wear rate were higher in the PLA than in the PETG, and PLA was deposited on the block due to high frictional heat. In the wear test of the PLA block and PETG bump, the wear of the PLA block decreased compared to the wear test between the same materials, but the wear of the PETG bump tended to increase. Therefore, it seems that the 3D-printed PETG may be more advantageous in terms of friction and wear than 3D-printed PLA during relative movement in a non lubricating condition.

Predicting fall risk is necessary for rescue and accident prevention in the elderly. In this study, deep learning regression models were used to predict the acceleration sum vector magnitude (SVM) peak value, which represents the risk of a fall. Twenty healthy adults (aged 22.0±1.9 years, height 164.9±5.9 cm, weight 61.4±17.1 kg) provided data for 14 common daily life activities (ADL) and 11 falls using IMU (Inertial Measurement Unit) sensors (Movella Dot, Netherlands) at the S2. The input data includes information from 0.7 to 0.2 seconds before the acceleration SVM peak, encompassing 6-axis IMU data, as well as acceleration SVM and angular velocity SVM, resulting in a total of 8 feature vectors used to model training. Data augmentations were applied to solve data imbalances. The data was split into a 4 : 1 ratio for training and testing. The models were trained using Mean Squared Error (MSE) and Mean Absolute Error (MAE). The deep learning model utilized 1D-CNN and LSTM. The model with data augmentation exhibited lower error values in both MAE (1.19 g) and MSE (2.93g²). Low-height falls showed lower predicted acceleration peak values, while ADLs like jumping and sitting showed higher predicted values, indicating higher risks.

Recently, the demand for electric vehicles is intensively increasing in accordance with environmental issues in automotive industries. Given that noise level from the electric vehicles is significantly lower than that from conventional vehicles with internal combustion engine, noise management has become more critical. Conventionally, glass run channel (GRC) is used to block the noise and contaminants from outside of vehicle. In this work, the friction and degradation characteristics of GRC with thermoplastic vulcanizate substrate were assessed. The tests were performed using the reciprocating tribo-tester developed to replicate the contact sliding between GRC and window glass. Also, the test conditions were determined in consideration of operating condition of GRC. As a result, the plastic deformation of the lips due to creep and wear of the slip coating deposited on the lip surface were found to be major degradation mechanisms. Furthermore, it was shown that the friction and degradation increased significantly due to the misalignment between GRC and window glass, associated with the significant increase in the reaction force. The results of this work provide fundamental understanding of the degradation characteristics of GRC, and therefore are expected to be useful for the design of GRC with improved performance.

Anomaly detection models using big data generated from facilities and equipment have been adopted for predictive maintenance in the manufacturing industry. When facility faults or defects occur, different patterns of abnormal data are shown owing to their component behaviors. By detecting these pattern changes, it is possible to determine whether a facility abnormality occurs. This study evaluated the anomaly detection results from a combined driving system consisting of three driving motors for about six months at a manufacturing site. The learning data with an autoencoder model for about a month at the beginning of vibration data collection and continuous monitoring of anomalies using reconstruction errors showed that a component defect occurred in one driving motor, and the reconstruction error increased progressively about three months earlier than a facility manager found the failure. In addition, the micro-electro-mechanical systems sensor showed high amplitude in the entire frequency domain when high reconstruction errors occurred. However, the integrated electronics piezoelectric sensor showed different patterns as high amplitude in a specific frequency domain. The results of this study will be helpful for detecting facility abnormalities in combined driving systems using vibration sensors.

The linear motion guideway (LM guide) is one of the key parts of precision motion and positioning, and it requires high straightness, form accuracy, stiffness, and surface quality. LM guides are actively used in manufacturing facilities for automobiles, aerospace, optics, semiconductors, robots, displays, and portable communication equipment. At present, most of LM guides are based on rolling contact, using either balls or rollers. Roller LM guides have been in high demand in recent years in various industrial fields that require high rigidity. In this study, the friction characteristics of ball and roller LM guides with the same rail width were compared, and friction behavior was analyzed. An experimental setup consisting of a driving unit, specimen, force sensor, and signal acquisition unit was constructed, and signals were collected under various conditions. Three lubrication conditions were used: no lubrication (dry surface), ISO-VG 32, and 68, and a wide feed-rate range from 1 to 100 mm/s was selected. The experimental results showed that the ball LM guide and the roller LM guide had significantly different friction characteristics, which were analyzed from the aspect of Stribeck curve components. In conclusion, friction behavior differed according to lubrication conditions in the no-payload state of the ball and roller LM guides, and the effect of lubrication conditions on friction behavior was shown.

For the hydraulic cylinder system of construction equipment to function normally, the hydraulic oil should not leak under high pressure, and the leakage begins with various seals of damage. The frictional heat caused by the reciprocating motion inside the cylinder increases the temperature of the oil, which affects the aging of the seal materials inside the cylinder, thereby accelerating seal damage. The purpose of this study is to confirm the effect of reducing heat generation by applying umbrellatype micro-dimples on the surface of a wear ring, and to find out the performance according to changes in shape and density of the dimples. Dimples were manufactured by injection molding and the core for injection was made by profile grinding processing. The structural safety of the wearing with dimples was examined by structural analysis, and the temperature changes of the dimple were measured during pin-on-disc friction experiments. It was confirmed that the dimple was effective in reducing the amount of heat generated, and the heat generation decreased as the size and density of the dimple increased.

The purpose of this study was to check the position classification prediction rate based on the movement data of field hockey players using the random forest algorithm. In order to achieve the purpose of this study, movement data were collected using wearable devices in 15 practice matches. The collected information was then analyzed using the Random Forest algorithm, one of the ensemble techniques, with Python, a high-level, general-purpose programming language. As a result of this study, first, the position classification prediction rate was 52.4±3.3% when data measured by GPS sensors were used. Second, when using the data measured by an inertial measurement unit (IMU) sensor, the position classification prediction rate was 50.8±2.4%. Third, when both Global Positioning System (GPS) and IMU data were used, the position classification prediction rate was 55.6±2.0%. As a result of the study, it showed that the prediction rate was the highest when both GPS and IMU data were used.

MXene is one of the most fascinating 2D materials owing to its great electrical properties and unique performance. Among various application areas, the performance of organic material adsorption has been highlighted with the growing interest in the biocompatible applications of MXene. Although previous research revealed that the huge surface area of this 2D nanomaterial could lead to superior organic material adsorption performance, surface functional groups were usually controlled by changing the pH, and the MXene was generally produced by HF etchant. In this study, a surface modification method of Ti₃C₂T_x MXene film was proposed to enhance organic material adsorption by irradiating the pulsed plasma electron beam (EB). Methylene blue (MB)-dispersed DI water was prepared, and pristine MXene was prepared at pH 7. The MB concentration was only reduced by 20% by pristine MXene. However, EB-treated MXene adsorbed about 75% of the MB within 20 min and over 90% within 80 min when the MXene film was ground to powder form. The results showed that the increased surface area and formation of hydrophilic functional groups successfully modified MB adsorption following EB irradiation under optimal processing conditions.