• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3608-3626
• /
• 2021

The detection of bolts is an important task in high-speed train inspection systems, and it is frequently performed to ensure the safety of trains. The difficulty of the vision-based bolt inspection system lies in small sample defect detection, which makes the end-to-end network ineffective. In this paper, the problem is resolved in two stages, which includes the detection network and cascaded classification networks. For small bolt detection, all bolts including defective bolts and normal bolts are put together for conducting annotation training, a new loss function and a new boundingbox selection based on the smallest axis-aligned convex set are proposed. These allow YOLOv3 network to obtain the accurate position and bounding box of the various bolts. The average precision has been greatly improved on PASCAL VOC, MS COCO and actual data set. After that, the Siamese network is employed for estimating the status of the bolts. Using the convolutional Siamese network, we are able to get strong results on few-shot classification. Extensive experiments and comparisons on actual data set show that the system outperforms state-of-the-art algorithms in bolt inspection.

• 한국지능시스템학회논문지
• /
• 제24권1호
• /
• pp.33-39
• /
• 2014

자동 주행 차량을 구현하기 위해서는 장애물 인식, 차선 인식 및 변경 등 많은 기능들이 필요하다. 본 논문에서는 자동차 주행에 필요한 '차선 인식'의 범위를 확장시킨 '색깔 인식' 개념을 도입 적용시키기 위해 3가지 코스를 주행하는 시스템을 구현하였다. RC car의 크기와 비례하게 축소 제작한 각 코스에서 주행에 필요한 검지선의 위치, 기울기 및 차량의 속도를 고려하여 조향 제어를 하였고, 브레이크 기능이 없는 RC car를 제어하기 위해 차량의 속도와 검지선의 위치를 고려하였다.

• 한국군사과학기술학회지
• /
• 제15권1호
• /
• pp.9-15
• /
• 2012

This paper shows an effective scanning trajectory for a mine detection device that is one of the mission equipments of unmanned ground vehicle. The mine detection device is composed of a mine-detection sensor, and a 4 DOF manipulator enabling sensor position control. There are three modes that manage the mine detection device: passive, semi-automatic, and automatic. The automatic mode is used the most. This paper suggests a scanning method that makes shape of 8. This method prevents missing target area and enhances scanning speed when the mine detection device scans the ground surface in automatic mode. The suggested method is verified by simulations and experiments.

• Journal of Electrical Engineering and Technology
• /
• 제13권4호
• /
• pp.1515-1527
• /
• 2018

This paper presents a sensorless speed control of IPMSM (Interior Permanent Magnet Synchronous Motor) using the high-frequency (HF) square wave injection method. In the proposed HF pulsating square wave injection method, injection voltage is applied into the estimated d-axis of rotor and high-frequency induced q-axis current is considered to estimate the rotor position. Conventional square wave injection methods may need complex demodulation process to find rotor position, while in the proposed method, an easy demodulation process based on the rising-falling edge of the injected voltage and carrier induced q-axis current is implemented, which needs less processing time and improves control bandwidth. Unlike some saliency-based sensorless methods, the proposed method uses maximum torque per ampere (MTPA) strategy, instead of zero d-axis command current strategy, to improve control performance. Furthermore, this paper directly uses resultant d-axis current to detect the magnet polarity and eliminates the need to add an extra pulse injection for magnet polarity detection. As experimental results show, the proposed method can quickly find initial rotor position and MTPA strategy helps to improve the control performance. The effectiveness of the proposed method and all theoretical concepts are verified by mathematical equations, simulation, and experimental tests.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1998년도 제13차 학술회의논문집
• /
• pp.496-500
• /
• 1998

Not merely running at the designated constant speed as the classical cruise control, the adaptive cruise control (ACC) maintains safe headway distance when the front is blocked by other vehicles. One of the most essential part of ACC System is the range sensor which can measure the position and speed of all objects in front continuously, ignore all irrelevant objects, distinguish vehicles in different lanes and lock on to the closest vehicle in the same lane. In this paper, the hierarchical object recognition algorithm (HORA) is proposed to process raw scanning laser data and acquire valid distance to target vehicle. HORA contains two principal concepts. First, the concept of life quantifies the reliability of range data to filter off the spurious detection and preserve the missing target position. Second, the concept of conformation checks the mobility of each obstacle and tracks the position shift. To estimate and predict the vehicle position Kalman filter is used. Repeatedly updated covariance matrix determines the bound of valid data. The algorithm is emulated on computer and tested on-line with our ACC vehicle.

• 전력전자학회논문지
• /
• 제5권4호
• /
• pp.343-351
• /
• 2000

본 논문에서는 정렬과 비정렬된 회전자 위치들에서 자화곡선들을 기본으로 한 SRM의 회전자 워치펑가 알고리즘을 제안한다. 자화곡선은 측정된 상 전압과 상 전류로부터 계산되어지고, 계산된 데이타는 회전자 위치검출을 위한 자화곡선의 입력으로 사용되어진다. 자화곡선은 비션형 특성해석에 적합한 퍼지 알고리즘으로 구생되어졌다. 종래의 지삭기반 퍼지제어기를 이용한 자속관측기가 SRM의 센서리스 제어를 얻기 위해 제시되었다. 최적 각을 선정하기 위한 방식이 회전자 위치검출을 위해 제시되었다. 제안된 알고리즘의 강인성이 시뮬레이션과 실험결과의 비교를 통해 입증되었다.

• 전기전자학회논문지
• /
• 제23권2호
• /
• pp.622-627
• /
• 2019

본 논문에서는 비대칭 공극을 갖는 단상 영구자석 동기 전동기의 센서리스 운전을 위한 초기 회전자 위치 검출 알고리즘을 제안한다. 일반적인 센서리스 운전 기법 중 역기전력 기반의 센서리스 제어는 영속 및 저속운전에서 역기전력 정보를 추정하기 어렵다. 이를 위해 오픈 루프 기동 기법이 필수적으로 요구되고 일정한 방향으로의 회전을 위해서는 회전자의 초기 위치 검출이 반드시 필요하다. 본 논문에서는 단상 영구자석 동기 전동기의 자기적 특성을 이용하여 고주파 전압 주입 신호에 옵셋 전압을 추가하여 회전자 자극을 검출하는 기법을 제안한다. 다수의 실험 결과를 통하여 제안된 알고리즘의 유효성과 유용성을 검증하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 B
• /
• pp.802-805
• /
• 2003

The aim of this paper is to provide a guide to those methods of train detection which are available, or are likely to become available, to the designer of train control or other relevant systems. In broad terms, train detection may be defined as the process of generating information which describes the location and movement of trains. Train detection information is difficult to define in isolation. Consider, for example, the train detection information required in a modern train control system. This may vary considerably : in a future high performance train control system, it might be necessary to know the precise position, direction of movement, speed, and possibly even the acceleration or braking, of all trains in the control area : in a less demanding application, it might be sufficient to know only the location of trains in terms of the occupation of sections of track.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2000년도 추계학술대회논문집
• /
• pp.219-225
• /
• 2000

The major movement block of the containers have range between apron and designation points on yard in container terminal. The yard tractor operated by human takes charge of its movement in conventional container terminal. In automated container terminal, AGV(Automated Guided Vehicle) has charge of the yard tractor's role and the navigation path is ordered from upper level control system. The automated container terminal facilities must have the docking system to guide landing line to have high speed travelling and precision positioning. The general method for docking system uses the vision system with CCD camera, infra red, and laser. This paper describes the detection of AGV's position and orientation using laser slit beam to develop docking system.

• 전기학회논문지
• /
• 제66권5호
• /
• pp.792-799
• /
• 2017

The real time unmanned monitoring system of an equipment's internal parts and condition requires the monitoring device to be able to stop at a set location on the rail. However, due to the slip between the driving surface and the roller, an error occurs between the actual position and the command position. In this paper, a method to compensate the position error due to the roller slip is proposed. A proximity sensor located at both ends of the rail detects the starting point and the maximum position pulse, linearly compensating the error between the angular position of the motor and the mechanically fixed starting and maximum position pulse of the rail in forward and reverse direction. Moreover, unlike the existing servo position controller, the motor adopts the position detection method of Hall sensor in BLDC (Brushless DC) and applies an algorithm for low-speed driving so that a stable position control is possible. The proposed rail guided unmanned monitoring system with driving slip compensator was tested to verify the effectiveness.