• 한국공작기계학회논문집
• /
• 제17권4호
• /
• pp.112-118
• /
• 2008

In order to meet the optical performance in the process of the micro lens manufacturing with plastics, it is important to embody accuracy in shape and surface roughness to the intended design. Since it is difficult to machine exactly the mold core of lens fit to the designed shape, in this paper, a simple program using MATLAB is developed for shape correction of the mold core after first machining it. This program evaluates correction parameters(aspheric coefficients and curvature) and generates aspheric NC data for compensating the core surface in prior machining process. The program provides the way to manufacture plastic injection molding lens with aspheric shape of high precision, and is expected to be effective for correction and to shorten the processing time.

• Journal of international Conference on Electrical Machines and Systems
• /
• 제2권2호
• /
• pp.184-189
• /
• 2013

This paper proposes a method for improving the performance of a position sensorless control system for a slotless surface permanent magnet synchronous motor (SPMSM) in a very low-speed region. In position sensorless control based on a motor model, accurate motor parameters are required because parameter errors would affect position estimation accuracy. Therefore, online parameter identification is applied in the proposed system. The error between the reference voltage and the voltage applied to the motor is also affect position estimation accuracy and stability, thus it is compensated to ensure accuracy and stability of the sensorless control system. In this study, two voltage error compensation methods are used, and the effects of the compensation methods are discussed. The performance of the proposed sensorless control method is evaluated by experimental results.

• Journal of Electrical Engineering and Technology
• /
• 제12권3호
• /
• pp.1053-1063
• /
• 2017

Power prediction is critical to improve power efficiency in Smart Grids. Markov chain provides a useful tool for power prediction. With careful investigation of practical power datasets, we find an interesting phenomenon that the stochastic property of practical power datasets does not follow the Markov features. This mismatch affects the prediction accuracy if directly using Markov prediction methods. In this paper, we innovatively propose a spatial transform based data processing to alleviate this inconsistency. Furthermore, we propose an enhanced power prediction method, named by Spatial Mapping Markov-Difference (SMMD), to guarantee the prediction accuracy. In particular, SMMD adopts a second prediction adjustment based on the differential data to reduce the stochastic error. Experimental results validate that the proposed SMMD achieves an improvement in terms of the prediction accuracy with respect to state-of-the-art solutions.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 추계학술대회 논문집
• /
• pp.543-550
• /
• 2005

Recently, there are many studies for the micro-machining using Piezo actuator. However, because of its step by step motion, it is nearly impossible to increase the machining accuracy for a circular path. To increase the accuracy, it is well known that it is necessary the finer and synchronous movement for x-y axes. Therefore, this paper proposes an adaptive control for finer movement of the actuator, and realizes a synchronous control for the x-y axes. The experimental results show that the machining accuracy is remarkably improved.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.73.3-73
• /
• 2001

Finishing mill (FM) is set up with rolling conditions (rolling speed, rolling force, roll gap, etc.) calculated by a FSU (Finisher Setup) model considering the temperature, qualities and size of a transfer bar and a strip at the entry and exit of FM before the transfer bar is rolled through FM. If the accuracy of setup is low mass flow unbalance occurs, so that the accuracies of the strip thickness and width become lower or rolling operation fault occurs. Therefore, to enhance the performance of the FSU model and to improve mass flow and the thickness accuracy of a strip in the 7-stand finishing mill using a hot strip speed measurement system. This study is being performed. In this paper, the speed measurement system, a developed neural network for predicting ...

• Journal of Positioning, Navigation, and Timing
• /
• 제8권2호
• /
• pp.87-94
• /
• 2019

The Global Navigation Satellite System (GNSS) Real-Time Kinematic (RTK) positioning has been widely used in geodesy, surveying, and navigation fields. RTK can benefit enormously from the integration of multi-GNSS. In this study, we develop a GPS/BeiDou Navigation Satellite System (BDS) RTK integration algorithm for long baselines ranging from 128 km to 335 km in South Korea. The positioning performance with GPS/BDS RTK, GPS-only RTK, and BDS-only RTK is compared in terms of the positioning accuracy. An improvement of positioning accuracy over long baselines can be found with GPS/BDS RTK compared with that of GPS-only RTK and that of BDS-only RTK. The positioning accuracy of GPS/BDS RTK is better than 2 cm in the horizontal direction and better than 5 cm in the vertical direction. A lower Relative Dilution of Precision (RDOP) value with GPS/BDS integration can obtain a better positional precision for long baseline RTK positioning.

• Journal of Multimedia Information System
• /
• 제6권2호
• /
• pp.75-80
• /
• 2019

In machine learning, the performance of the system depends upon the nature of input data. The efficiency of the system improves when the behavior of the input data changes from un-normalized to normalized form. This paper experimentally demonstrated the performance of KNN, SVM, LDA and NB on Alzheimer's dataset. The dataset undertaken for the study consisted of 3 classes, i.e. Demented, Converted and Non-Demented. Analysis shows that LDA and NB gave an accuracy of 89.83% and 88.19% respectively in both the cases whereas the accuracy of KNN and SVM improved from 46.87% to 82.80% and 53.40% to 88.75% respectively when input data changed from un-normalized to normalized state. From the above results it was observed that KNN and SVM show significant improvement in classification accuracy on normalized data as compared to un-normalized data, whereas LDA and NB reflect no such change in their performance.

• 한국멀티미디어학회논문지
• /
• 제25권1호
• /
• pp.29-38
• /
• 2022

Although image compression is one of the essential technologies to transmit image data on a variety of surveillance and mobile healthcare applications, it causes unnecessary compression artifacts such as blocking and ringing artifacts by the lossy compression in the limited network bandwidth. Recently, image restoration methods using convolutional neural network (CNN) show the significant improvement of image quality from the compressed images. In this paper, we propose Image Denoising Convolutional Neural Networks (IDCNN) to reduce the compression artifacts for the purpose of improving the performance of object classification. In order to evaluate the classification accuracy, we used the ImageNet test dataset consisting of 50,000 natural images and measured the classification performance in terms of Top-1 and Top-5 accuracy. Experimental results show that the proposed IDCNN can improve Top-1 and Top-5 accuracy as high as 2.46% and 2.42%, respectively.

• 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.

• 한국정보통신학회논문지
• /
• 제23권11호
• /
• pp.1397-1406
• /
• 2019

신경학적 손상에 의한 언어장애인/비장애인 간의 일상적인 휴대폰 통화시 신경학적 손상으로 인한 발음의 정확도와 언어장애인의 발음 특징이 결합되어 원활한 의사소통을 저해하는 경우가 많다. 이러한 문제점을 개선하기 위하여 제한하는 방법은 언어장애인 특성에 맞춘 단어의 모호성(out of vocabulary) 개선과, 언어 장애인 구강 특성에 따른 어려운 발성 부분을 인위적으로 보정해주는 유도선이 포함된 MEMS(Micro Electro-mechanical System) Microphone 장치 개선이다. S/W적 개선은 도치기능이 포함된 결정트리이며, 연속어 특성을 감안하여 개선된 matrix-vector rnn 방법을 제시하였다. H/W와 S/W 특성을 감안하여 유사 사전을 만들어 원활한 의사소통을 위한 말명료도 향상에 기여하였다.