• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2005년도 추계학술대회 논문집
• /
• pp.160-163
• /
• 2005

The cute. race of CV(constant velocity) Joint is an important load-supporting automotive part, which transmits torque between the transmission gear box and driving wheel. The outer race is difficult to forge because its shape is very complicated and the required dimensional tolerances are very small. The forged CV Joint investigated in this study has six inner ball grooves requiring high operational accuracy. Therefore, the precise measurement of forged CV Joint is very important to guarantee the sound operation without noise and abnormal wear. In this study, unique in-situ measuring system designed specifically to measure the dimensional accuracy of six inner ball grooves of CV joint has been developed and implemented in shop environments. Newly developed system shows high measurement accuracy with simple operational sequence.

• 한국측량학회지
• /
• 제18권2호
• /
• pp.135-141
• /
• 2000

본 연구에서는 수치근접사진측량기법에 의한 DCS 420 디지털 카메라의 석재표면 거칠기 측정정확도 파악을 위하여 윈도우 환경의 Microsoft Visual basic 6.0으로 표면거칠기측정시스템을 구축하였다. 본 시스템을 통하여 거칠기가 거의 없는 이상적인 평면과 곡면인 돌의 표면 거칠기를 최소제곱법으로 기준면을 적용, 측정한 결과 $\pm$0.1 mm이하의 정확도로 측정할 수 있었다.

• 센서학회지
• /
• 제30권5호
• /
• pp.286-289
• /
• 2021

Image classification is one of the fundamental applications of computer vision. It enables a system to identify an object in an image. Recently, image classification applications have broadened their scope from computer applications to edge devices. The convolutional neural network (CNN) is the main class of deep learning neural networks that are widely used in computer tasks, and it delivers high accuracy. However, CNN algorithms use a large number of parameters and incur high computational costs, which hinder their implementation in edge hardware devices. To address this issue, this paper proposes a lightweight image classifier that provides good accuracy while using fewer parameters. The proposed image classifier diverts the input into three paths and utilizes different scales of receptive fields to extract more feature maps while using fewer parameters at the time of training. This results in the development of a model of small size. This model is tested on the CIFAR-10 dataset and achieves an accuracy of 90% using .26M parameters. This is better than the state-of-the-art models, and it can be implemented on edge devices.

• International Journal of Internet, Broadcasting and Communication
• /
• 제13권4호
• /
• pp.22-29
• /
• 2021

This study evaluates the accuracy of corrective feedback from Grammarly, an online grammar checker, on essays written by cyber university learners in terms of detected errors, suggested replacement forms, and false alarms.The results indicate that Grammarly has a high overall error detection rate of over 65%, being particularly strong at catching errors related to articles and prepositions. In addition, on the detected errors, Grammarly mostly provide accurate replacement forms and very rarely make false alarms. These findings suggest that Grammarly has high potential as a useful educational tool to complement the drawbacks of teacher feedback and to help learnersimprove grammatical accuracy in their written work. However, it is still premature to conclude that Grammarly can completely replace teacher feedback because it has the possibility (approximately 35%) of failing to detect errors and the limitationsin detecting errors in certain categories. Since the feedback from Grammarly is not entirely reliable, caution should be taken for successful integration of Grammarly in English writing classes. Teachers should make judicious decisions on when and how to use Grammarly, based on a keen awareness of Grammarly's strengths and limitations.

• Journal of information and communication convergence engineering
• /
• 제19권1호
• /
• pp.22-28
• /
• 2021

Convolutional neural networks (CNNs) are one of the most frequently used artificial intelligence techniques. Among CNN-based applications, small and timing-sensitive applications have emerged, which must be reliable to prevent severe accidents. However, as the small and timing-sensitive systems do not have sufficient system resources, they do not possess proper error protection schemes. In this paper, we propose MATE, which is a low-cost CNN weight error correction technique. Based on the observation that all mantissa bits are not closely related to the accuracy, MATE replaces some mantissa bits in the weight with error correction codes. Therefore, MATE can provide high data protection without requiring additional memory space or modifying the memory architecture. The experimental results demonstrate that MATE retains nearly the same accuracy as the ideal error-free case on erroneous DRAM and has approximately 60% accuracy, even with extremely high bit error rates.

• Smart Structures and Systems
• /
• 제28권6호
• /
• pp.779-789
• /
• 2021

Cracks in railway sleeper are an inevitable condition and has a significant influence on the safety of railway system. Although the technology of railway sleeper condition monitoring using machine learning (ML) models has been widely applied, the crack recognition accuracy is still in need of improvement. In this paper, a two-stage method using edge detection and convolutional neural network (CNN) is proposed to reduce the burden of computing for detecting cracks in railway sleepers with high accuracy. In the first stage, the edge detection is carried out by using the 3×3 neighborhood range algorithm to find out the possible crack areas, and a series of mathematical morphology operations are further used to eliminate the influence of noise targets to the edge detection results. In the second stage, a CNN model is employed to classify the results of edge detection. Through the analysis of abundant images of sleepers with cracks, it is proved that the cracks detected by the neighborhood range algorithm are superior to those detected by Sobel and Canny algorithms, which can be classified by proposed CNN model with high accuracy.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권3호
• /
• pp.118-121
• /
• 2023

Recently, green energy support policies have been announced around the world in accordance with environmental regulations, and asthe market grows rapidly, demand for batteries is also increasing. Therefore, various methodologies for battery diagnosis and recycling methods are being discussed, but current accurate life prediction of batteries has limitations due to the nonlinear form according to the internal structure or chemical change of the battery. In this paper, CS2 lithium-ion battery measurement data measured at the A. James Clark School of Engineering, University of Marylan was used to predict battery performance with high accuracy using a convolutional neural network (CNN) model among deep learning-based models. As a result, the battery performance was predicted with high accuracy. A data structure with a matrix of total data 3,931 ☓ 19 was designed as test data for the CS2 battery and checking the result values, the MAE was 0.8451, the RMSE was 1.3448, and the accuracy was 0.984, confirming excellent performance.

• Journal of Positioning, Navigation, and Timing
• /
• 제12권3호
• /
• pp.281-288
• /
• 2023

The International Maritime Organization (IMO) states that the recommended horizontal accuracy for coastal and offshore areas is 10 m, the Alert Limit (AL) is 25 m, the time to alert is 10 seconds, and the integrity risk (IR) is 10^-5 per three hours. For operations requiring high accuracy, such as tugs and pushers, icebreakers, and automated docking, the IMO dictates that a high level of positioning accuracy of less than one meter and a protection level of 0.25 meters (for automated docking) to 2.5 meters should be achieved. In this paper, we analyze a method of calculating the user-side protection level of the centimeter-level precision Global Navigation Satellite System (GNSS) that is being studied to provide augmentation information for the precision Positioning, Navigation and Timing (PNT) service. In addition, we analyze standardized integrity forms based on RTCM SC-134 to propose an integrity information form and generate a centimeter-level precise PNT service plan.

• 드라이브 ㆍ 컨트롤
• /
• 제20권4호
• /
• pp.54-63
• /
• 2023

High and intermittent loading cycles induce fatigue damage to transmission components, resulting in premature gearbox failure. To identify gearbox defects, numerous vibration-based diagnostics techniques, using several artificial intelligence (AI) algorithms, have recently been presented. In this paper, an optimized deep belief network (DBN) model for gearbox problem diagnosis was designed based on time-frequency visual pattern identification. To optimize the hyperparameters of the model, a particle swarm optimization (PSO) approach was integrated into the DBN. The proposed model was tested on two gearbox datasets: a wind turbine gearbox and an experimental gearbox. The optimized DBN model demonstrated strong and robust performance in classification accuracy. In addition, the accuracy of the generated datasets was compared using traditional ML and DL algorithms. Furthermore, the proposed model was evaluated on different partitions of the dataset. The results showed that, even with a small amount of sample data, the optimized DBN model achieved high accuracy in diagnosis.