• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2011년도 전력전자학술대회
• /
• pp.316-317
• /
• 2011

Recently, many industrial electric vehicles have been developed using various ac-motor drive technologies including field oriented vector control. Generally, a magnetic encoder is installed to have resistance to vibration and dust, and it is cost-effective. However, it is difficult to get an accurate rotor speed for high performance of vector control, because a resolution of the magnetic encoder is low and its phase accuracy is poor. In order to overcome this hardware problem, this study proposes a speed measurement algorithm using moving window for low-resolution magnetic encoder. This algorithm is experimentally tested and successfully applied to traction application of industrial electric vehicle.

• 디지털융복합연구
• /
• 제19권6호
• /
• pp.251-258
• /
• 2021

본 논문에서는 U-Net 기반의 semantic segmentation 방법에서 정확도를 향상시키기 위해 residual learning을 활용한 인코더-디코더 구조의 모델을 제안하였다. U-Net은 딥러닝 기반의 semantic segmentation 방법이며 자율주행 자동차, 의료 영상 분석과 같은 응용 분야에서 주로 사용된다. 기존 U-Net은 인코더의 얕은 구조로 인해 특징 압축 과정에서 손실이 발생한다. 특징 손실은 객체의 클래스 분류에 필요한 context 정보 부족을 초래하고 segmentation 정확도를 감소시키는 문제가 있다. 이를 개선하기 위해 제안하는 방법은 기존 U-Net에 특징 손실과 기울기 소실 문제를 방지하는데 효과적인 residual learning을 활용한 인코더를 통해 context 정보를 효율적으로 추출하였다. 또한, 인코더에서 down-sampling 연산을 줄여 특징맵에 포함된 공간 정보의 손실을 개선하였다. 제안하는 방법은 Cityscapes 데이터셋 실험에서 기존 U-Net 방법에 비해 segmentation 결과가 약 12% 향상되었다.

• 대한기계학회논문집A
• /
• 제29권5호
• /
• pp.770-776
• /
• 2005

The gains fur NC controller parameter are fixed when the controller is combined with a machine. However, the characteristics of controller could be changed as it has being used by the machine or other environmental conditions. Those result in that the tool positioning accuracy is influenced. The loading torque in servo motor influences on the tool positioning accuracy and it is controlled by the parameter gains. It is required to analyze the torque variation with angular positioning accuracy of the servo motor. This study focus on a measuring method and device for verifying angular positioning accuracy of NC servo motor. We used a high resolution An converter for acquiring analogue signal of rotary encoder in servo motor. The positional accuracy for a nominal tool path, which is generated by the combination of axial movements (X,Y,Z), is analyzed with the servo motor torque. The current variation signal is acquired at the power line using a hall sensor and converted to the loading torque of servo motor. The method of measurement and analysis proposed in this study will be used for determining the gains of parameter in NC controller. This gain tuning is also necessary when the controller is set up at a machine.

• 한국ITS학회 논문지
• /
• 제19권2호
• /
• pp.89-103
• /
• 2020

고령화 사회에 접어들면서 거동이 어려운 장애인과 고령자의 개인 교통수단에 대한 수요가 증가하고 있다. 실제로 2017년 기준 전국 전동보장구 보급수는 9만여 대로 지속해서 증가하는 추세다. 하지만 장애인 및 고령자의 판단 능력과 조정 능력은 정상인보다 상대적으로 차이가 있는 관계로 주행 중 사고 발생의 가능성이 크다. 다양한 사고의 원인 중 하나는 도로 노면상태의 불균형으로 인해 개인 이동 수단 조향 제어의 간섭이다. 본 논문에서는 이 같은 사고를 예방하고자 도로 노면 상태를 고속으로 인지할 수 있는 암호화 형식 의미론적 분할 알고리즘을 소개한다. 이를 위하여 도로 노면 파손이 포함된 1,500여 장의 학습용 데이터와 150여 장의 테스트용 데이터를 새롭게 구성하였다. 그리고 이를 활용하여 기존의 Encoder와 Decoder 단계로 구성된 Auto-encoder 방식과 달리 Encoder 단계로 이루어진 심층 신경망을 제안하였다. 이 심층 신경망은 기존의 방식과 비교했을 때 평균 정확도(Mean Accuracy)는 4.45% 증가하였고 파라미터는 59.2% 감소하였으며 연산 속도는 11.9% 향상되었다. 이 같은 고속 알고리즘을 활용하여 안전한 개인 이동 수단이 확대 적용되길 기대한다.

• 대한임베디드공학회논문지
• /
• 제12권4호
• /
• pp.213-221
• /
• 2017

Utilizing the existing polishing robot prevents unrestricted change of direction, driving, and identification of driving pathway. To overcome this barrier, driving mechaism has been designed with Omniwheels with encoders and RSSI method of beacon system has been utilized to identify the driving path by position recognition. Due to the wheel characteristics, the Omniwheel mobile robot generates greater slip than the conventional mobile robot, which reduces its driving accuracy. Therefore, to improve the driving accuracy, the localization is conducted through the fusion of encoder and RSSI of beacon data to compensate for the errors caused by Dead Reckoning and inaccuracy of sensors. Finally, the localization accuracies of the proposed and conventional indoor localization method are compared to show effectiveness of the proposed driving control for a polishing robot.

• 한국정밀공학회지
• /
• 제17권12호
• /
• pp.61-67
• /
• 2000

In switched reluctance motor(SRM) drive, it is necessary to synchronize the stator phase excitation with the rotor position. Therefore the rotor position information is an essential. Usually optical encoders or resolvers are used to provide the rotor position information. These sensors are expensive and are not suitable for high speed operation. In general, the accuracy of the switching angle is dependent upon the resolution of the encoder and the sampling period of the microprocessor. But the region of high speed, switching angles are fluctuated back and forth from the preset values, which are cause by the sampling period of the microprocessor. Therefore, the low cost linear encoder suitable for the practical and stable SRM drive is proposed and the control algorithm to provide the switching signals using the simple digital logic circuit is also presented in this paper. It is verified from the experiments that the proposed encoder and logic controller can be a powerful candidate for the practical low cost SRM drive.

• 제어로봇시스템학회논문지
• /
• 제8권4호
• /
• pp.319-326
• /
• 2002

In switched reluctance motor(SRM) drive, it is important to synchronize the stator phase excitation with the rotor position; therefore, the information about rotor position is essential. Generally, optical encoders or resolvers are used to provide the information. However, these sensors are expensive and are not suitable for high-speed operation. The accuracy of the switching angles is dependent upon the resolution of the encoder and the sampling period of the microprocessor. In the high-speed region, switching angles are fluctuated back and forth out of the preset value, which is caused by the sampling period of the microprocessor. In this paper, a low cost linear encoder suitable far the practical and stable SRM drive is proposed and also the control algorithm to generate the switching signals using a simple digital logic is presented. The validity of the proposed linear encoder with a proper logic controller is verified through the experiments.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 학술대회 논문집 전문대학교육위원
• /
• pp.127-133
• /
• 2001

In SRM drive, the ON OFF angles of each phase switch should be accurately controlled in order to control the torque and speed stably. The accuracy of the switching angles is dependent upon the resolution of the encoder and the sampling period of the microprocessor, that are used to provide the information of the rotor position and to control the SRM power circuit, respectively. However, as the speed increases, the amount of the switching angle deviation from the preset values is also increased. Therefore, the low cost encoder suitable for the practical and stable SRM drive is proposed and the control algorithm to provide the switching signals using the simple digital logic circuit is also presented in this paper. As a result, a stable high speed SRM drive can be achieved by the high resolution switching angle control and it is verified from the experiments that the proposed encoder and logic controller can be a powerful candidate for the practical low cost SRM drive.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 1997년도 전력전자학술대회 논문집
• /
• pp.182-187
• /
• 1997

In this paper, a instantaneous speed measurement method using a three phase sinusoidal encoder is described and it's simulations are developed. The proposed method can easily detect the AC motor speed by using that the encoder is propotion to the AC motor speed. The performance of proposed method is confirmed by computer simulation and experiment results. The high accuracy of the optimum control system, AC motor speed detection is designed and proposed.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.33.4-33
• /
• 2002

Recently, number of navigation system using GPS and other complementary sensor has been developed to offer high-position accuracy. In this paper, we developed navigation system for mobile robot integrating GPS and DR sensor information provided by fiber optic gyroscopes and encoder information. In the case of short-term applications, integrating this encoder and gyroscope through Kalman filter reliable positioning can be obtained. And for the long-term applications we developed GPS/DR Integration algorithm using Kalman filter