• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.287-292
• /
• 2003

The ability of robot is being various and complex. The robot is utilizing distance, image data and voice data for sensing its circumstance. This paper suggests the 2-layer fuzzy control as the algorithm that control robot with various sensor information. In a obstacle avoidance, it utilizes many range finders and classifies them into 3parts(front, left, right). In 3 sub-controllers, the controller executes fuzzy conference. And then it executes combined control with a combination of outputs of 3 sub-controllers in the second step. The text compares the 2-layer fuzzy controller with the hierarchical fuzzy controller that has analogous structure. And the performance of the 2-layer fuzzy controller is confirmed by application this controller to robot following, simulation to each other and real experiment.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.11
• /
• pp.28-36
• /
• 2020

As many types of magnetic sensors are widely applied in various industries, the analysis and processing of magnetic sensor data need to be accurate. On the other hand, owing to the complexity of the magnetic field line caused by a moving magnet, the magnetic data generated by magnetic sensors are unpredictably nonlinear. Many industry systems using magnetic sensors have struggled with the nonlinear nature of magnetic sensor data. To reduce the effect of the nonlinearity, they have the target objects fixed firmly. Therefore, to collect accurate and reliable data, considerable efforts have been made to resolve the issues with the expensive tools and systems required. Through this paper, to tackle the issues, the data analysis and methodologies, including intelligent algorithms, are presented for the wrist rehabilitation system using magnetic sensors while being implemented without using expensive tools or systems. On processing magnetic sensor data, this paper adopted an intelligent algorithm, fuzzy logic, and compared the performance of other algorithms for comparison.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.498-501
• /
• 2004

본 논문에서는 엘리베이터의 제어 신호들과 액추에이터들을 동작시키기 위한 릴레이 그리고 액츄에이터의 동작을 센서와 포토 커플러를 이용하여 샘플링 한다. 제안하는 시스템에서는 예외적인 상황에서 오류가 발생하는 사례를 퍼지 데이터베이스로 구성하고 산출된 엘리베이터에러를 최종적으로 엘리베이터 관리자에게 통보함으로써 사고 발생 시 즉각적인 대책과 인명피해에 대한 빠른 구조 활동을 계획할 수 있도록 한다. 시스템에 사용된 알고리즘은 제어 신호를 입력으로 한 퍼지 if-then rule 이며, 관리자와의 통신은 Bluetooth를 통하여 Embedded Server에 신호를 전송하고 최종적으로 Embedded Server에서 인터넷 IP를 통하여 관리자에게 에러 발생 여부를 통보하게 된다. 인터넷 IP를 활용함으로써 거리의 제약이 사라지고 실시간으로 엘리베이터의 상태를 파악 할 수 있게 된다. 궁극적으로 승객의 안전과 편의를 도모하기 위해 본 논문의 시스템이 제안되었다.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.5
• /
• pp.84-92
• /
• 2000

Recently, the progress of industrialization has been taken concern of material handling automation. So for, the conveyor belt has been popular for material handling. However, this system has many disadvantages such as the space, cost, etc. In this paper, a new navigation algorithm using fuzzy is introduced. The mobile robot follows a line installed on the roads. These informations are inputted with three approximate sensors. These obtained informations are analyzed with fuzzy control technique fur autonomous steering. Therefore, unlike existing systems, high reliability is guaranteed under bad environment conditions. The installation and maintenance of a line is easily made at lower cost. This developed mobile robot can be applied to material handling automation in manufacturing system, hospital, inter-office document del ivory.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2002.05a
• /
• pp.871-877
• /
• 2002

현재 공작기계의 상당부분에서 자동화 및 무인화가 이루어지고 있는 추세이며, 이러한 대부분의 산업시설들과 기계류에는 회전체 부품들을 가지고 있다. 이들 부품들에서 베어링(Bearing)은 절대적으로 매우 중요한 부분을 차지하고 있으며, 만일 회전축시스템(Rotor System)에 베어링의심각한 이상은 시스템이 정지되는 사태를 불러일으킬 수도 있다. 따라서 이상에 대한 조기 감지의 역할은 전체 시스템의 향상뿐만 아니라, 비용이나 시간적인 측면에서도 크나큰 이익을 가져다 줄 수 있다. 지금까지 이러한 회전축시스템에 대한 다양한 이상진단을 시도하여 왔으며 앞으로도 많은 종류의 이상진단이 이루어지리라 생각한다. 이런 다양한 형태의 이상진단은 시스템에서 추출되는 데이터를 여러 가지 기법과 추출하는 센서의 특징을 파악하여 이상진단 알고리즘을 수립하는 과정을 망라하게 된다. 특히 이상진단 알고리즘에는 측정된 데이터의 불확실성을 감안한 이론이 적용되어야 한다. 본 연구에서는 회전축시스템의 베어링에 대한 이상진단을 통계적 기법, Fuzzy Clustering, Neural network과 Neuro-fuzzy를 이용한 기법과의 상호비교를 통해서 여러 종류의 이상을 구분하는 작업수행을 연구하고자 한다.

• Journal of Internet Computing and Services
• /
• v.13 no.5
• /
• pp.21-31
• /
• 2012

Threat Evaluation(TE) which has air intelligence attained by identifying friend or foe evaluates the target's threat degree, so it provides information to Weapon Assignment(WA) step. Most of TE data are passed by sensor measured values, but existing techniques(fuzzy, bayesian network, and so on) have many weaknesses that erroneous linkages and missing data may fall into confusion in decision making. Therefore we need to efficient Threat Evaluation system that can refine various sensor data's linkages and calculate reliable threat values under unpredictable war situations. In this paper, we suggest new threat evaluation system based on information fusion JDL model, and it is principle that combine fuzzy which is favorable to refine ambiguous relationships with bayesian network useful to inference battled situation having insufficient evidence and to use learning algorithm. Finally, the system's performance by getting threat evaluation on an air defense scenario is presented.

• Journal of Bio-Environment Control
• /
• v.20 no.3
• /
• pp.169-175
• /
• 2011

The adaptive neuro-fuzzy inference system (ANFIS) based automatic control system framework was proposed for integrated environment management of ubiquitous plant factory which can collect information of crop cultivation environment and monitor it in real-time by using various environment sensors. Installed wireless sensor nodes, based on the sensor network, collect the growing condition's information such as temperature, humidity, $CO_2$, and the control system is to monitor the control devices by using ANFIS. The proposed automatic control system provides that users can control all equipments installed on the plant factory directly or remotely and the equipments can be controlled automatically when the measured values such as temperature, humidity, $CO_2$, and illuminance deviated from the decent criteria. In addition, the better quality of the agricultural products can be gained through the proposed automatic control system for plant factory.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.5
• /
• pp.648-654
• /
• 2004

The Mass Flow Controller(MFC) has become crucial in semiconductor manufacturing equipments. It is an important element because the quality and the yield of a semiconductor process are decided by the accurate flow control of gas. Therefore, the demand for implementing the high speed and the highly accurate control of MFCs has been increasing. It is hard to find an article of the control algorithm applied to MFCs. But, it is known that commercially available MFCs adopt PID control algorithms. Particularly, when the system detects the flow by way of heat transfer, the MFC control problem includes the slow response and the nonlinearity. In this paper, MFC control algorithm with a superior performance to the conventional PID algorithm is discussed and the superiority is demonstrated through the experiment. A fuzzy controller was utilized in order to compensate the nonlinearity and the slow response, and the performance is compared with that of an MFC currently available in the market. The control system, in this paper, consists of a personal computer, the data acquisition board and the control algorithm carried out by LabWindows/CVI program on the PC. In addition, a method of estimating the actual flow from the sensor output with the slow response is presented. In conclusion, according to the result of the experiment, the proposed algorithm shows better accuracy and is faster than the conventional controller.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.1
• /
• pp.88-91
• /
• 2010

In this paper, We are composed the position recognition and speed control using the moving robot in the shield Room with a RF Module and Ultrasonic Sensors. Double look up tables are selected a reference value/duty ratio. The moving robot with the dual fuzzy rules which can decrease a Conversion time than basic fuzzy control rules at start point and curve region. Also, a changing times of double look up table are rise at specific points b1,c1,d1 in the e-${\Delta}e$ phase plane and the one of the look up table is used which for increase rising time at transition area, the other used for rapidly conversion to the reference value. We verified that a dual fuzzy control rules get the good response compare with the basic fuzzy control rule.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.5
• /
• pp.86-94
• /
• 2008

In this paper proposed the solar tracking system to use a fuzzy based on PC in of order to increase an output of the PV(Photovoltaic) array. The solar tracking system operated two DC motors driving by signal of photo sensor. The control of dual axes is not an easy task due to nonlinear dynamics and unavailability of the parameters. Recently, artificial intelligent control of the fuzzy control, neural-network and genetic algorithm etc. have been studies. The fuzzy control made a nonlinear dynamics to well perform and had a robust and highly efficient characteristic about a parameter variable as well as a nonlinear characteristic. Hence the fuzzy control was used to perform the tracking system after comparing with error values of setting-up, nonlinear altitude and azimuth. In this paper designed a fuzzy controller for improving output of PV array and evaluated comparison with efficient of conventional PI controller. The data which were obtained by experiment were able to show a validity of the proposed controller.