• 산업공학
• /
• 제10권3호
• /
• pp.125-132
• /
• 1997

We proposed a 2-step neural network approach for estimating machining parameters of electric discharge wire cut. The first step net, which is described as a backward neuro-estimation, is designed for estimating coarse cutting parameters while the second phase net, as a polishing forward neuro-estimation, is utilized for determining fine parameters. Sequential estimation procedure, based on backward and forward net, is performed using the net's approximation capability which is M to 1 and 1 to M mapping property. Experimental results an given to evaluate the accuracy of the proposed 2-step neuro-estimation.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1993년도 Proceedings of International Conference for Agricultural Machinery and Process Engineering
• /
• pp.1243-1253
• /
• 1993

Visual features of a mushroom(Lentinus Edodes L) are critical in sorting and grading as most agricultural products are. Because of its complex and various visual features, grading and sorting of mushrooms have been done manually by the human expert. Though actions involved in human grading looks simple, a decision making undereath the simple action comes form the results of the complex neural processing of the visual image. And processing details involved in the visual recognition of the human brain has not been fully investigated yet. Recently, however, an artificial neural network has drawn a great attention because of its functional capability as a partial substitute of the human brain. Since most agricultural products are not uniquely defined in its physical properties and do not have a well defined job structure, a research of the neuro-net based human like information processing toward the agricultural product and processing are widely open and promising. In this pape , neuro-net based grading and sorting system was developed for a mushroom . A computer vision system was utilized for extracting and quantifying the qualitative visual features of sampled mushrooms. The extracted visual features and their corresponding grades were used as input/output pairs for training the neural network and the trained results of the network were presented . The computer vision system used is composed of the IBM PC compatible 386DX, ITEX PFG frame grabber, B/W CCD camera , VGA color graphic monitor , and image output RGB monitor.

• 생물환경조절학회지
• /
• 제3권1호
• /
• pp.42-51
• /
• 1994

대다수 농산물과 마찬가지로 건조표고의 등급판정은 외관특징에 주로 의존한다. 표고 갓의 전후면에 걸친 복잡하고 다양한 외관특징들로 인하여 표고의 등급판정은 임의로 추출한 표고샘플에 대하여 전문가가 수작업으로 판정하고 있으며, 선별작업 역시 전적으로 수작업에 의존하고 있다. 단순한 반복작업으로 보이는 농산물의 등급판정은 사실 시각과 촉각을 위시한 고도의 감각신경계를 통하여 상호 복잡하게 얽혀 들어오는 정보를 지능적으로 처리하는 고기능의 작업이다. 농산물의 경우, 외관특성을 비롯한 물성은 종류별로 그 경계치를 일괄적으로 명확하게 규정할 수 없기 때문에 대개는 오차를 포함한 통계적 접근에 의하여 규정하고 있다. 따라서 농산작업에 있어서는 농산물 물성이 갖는 모호성을 효율적으로 처리할 수 있는 가변적인 작업구조 및 정보처리가 필수적으로 요구된다. 본 연구에서는 인간 뇌의 정보처리 기능을 부분적으로 구현할 수 있는 인공신경회로망을 컴퓨터 시각 시스템에 적용하여 단순 기하도형의 분류 및 표고의 등급판정을 성공적으로 수행하였다. 회로망 입력으로는 컴퓨터시각 시스템을 이용하여 건조표고의 정성적 외관특징을 자동으로 추출한 후 정량화한 특징점 값들을 이용하였다. 신경회로망의 학습은 표본 추출한 등급표고와 이들의 정량적 특징점 값들을 입출력 쌍으로 하여 수행하였다. 학습한 회로망의 등급판정 성능시험은 표본추출한 미지의 표고에 대한 컴퓨터 영상 특징점 값들을 입력하여 수행하였다.

• 수산해양기술연구
• /
• 제39권1호
• /
• pp.77-83
• /
• 2003

Autonomous mobile robots based on the Web have been already used in public places such as museums. There are many kinds of problems to be solved because of the limitation of Web and the dynamically changing environment. We present a methodology for intelligent mobile robot that demonstrates a certain degree of autonomy in navigation applications. In this paper, we focus on a mobile robot navigator equipped with neuro-fuzzy controller which perceives the environment, make decisions, and take actions. The neuro-fuzzy controller equipped with collision avoidance behavior and target trace behavior enables the mobile robot to navigate in dynamic environment from the start location to goal location. Most telerobotics system workable on the Web have used standard Internet techniques such as HTTP, CGI and Scripting languages. However, for mobile robot navigations, these tools have significant limitations. In our study, C# and ASP.NET are used for both the client and the server side programs because of their interactivity and quick responsibility. Two kinds of simulations are performed to verify our proposed method. Our approach is verified through computer simulations of collision avoidance and target trace.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.1173-1177
• /
• 1990

Cerebellar Model Linear Associator Net(CMLAN), a kind of neuro-net based adaptive control function generator, was applied to the problem of direct inverse calibration of three and six d.o.f. POMA 560 robot. Since CMLAN autonomously maps and generalizes a desired system function via learning on the sampled input/output pair nodes, CMLAN allows no knowledge in system modeling and other error sources. The CMLAN based direct inverse calibration avoids the complex procedure of identifying various system parameters such as geometric(kinematic) or nongeometric(dynamic) ones and generates the corresponding desired compensated joint commands directly to each joint for given target commands in the world coordinate. The generated net outputs automatically handles the effect of unknown system parameters and dynamic error sources. On-line sequential learning on the prespecified sampled nodes requires only the measurement of the corresponding tool tip locations for three d.o.f. manipulator but location and orientation for six d.o.f. manipulator. The proposed calibration procedure can be applied to any robot.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1996년도 International Conference on Agricultural Machinery Engineering Proceedings
• /
• pp.607-614
• /
• 1996

A computer vision based automatic intelligent sorting system for dried oak mushrooms has been developed. The developed system was composed of automatic devices for mushroom feeding and handling, two sets of computer vision system for grading , and computer with digital I/O board for PLC interface, and pneumatic actuators for the system control. Considering the efficiency of grading process and the real time on-line system implementation, grading was done sequentially at two consecutive independent stages using the captured image of either side. At the first stage, four grades of high quality categories were determined from the cap surface images and at the second stage 8 grades of medium and low quality categories were determined from the gill side images. The previously developed neuro-net based mushroom grading algorithm which allowed real time on-line processing was implemented and tested. Developed system revealed successful performance of sorting capability of approximate y 5, 000 mushrooms/hr per each line i.e. average 0.75 sec/mushroom with the grading accuracy of more than 88%.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1996년도 International Conference on Agricultural Machinery Engineering Proceedings
• /
• pp.773-779
• /
• 1996

Dried oak mushroom have complex and various visual features. Grading and sorting of dried oak mushrooms has been done by the human expert. Though actions involved in human grading looked simple, a decision making underneath the simple action comes from the result of the complex neural processing of the visual image. Through processing details involved in human visual recognition has not been fully investigated yet, it might say human can recognize objects via one of three ways such as extracting specific features or just image itself without extracting those features or in a combined manner. In most cases, extracting some special quantitative features from the camera image requires complex algorithms and processing of the gray level image requires the heavy computing load. This fact can be worse especially in dealing with nonuniform, irregular and fuzzy shaped agricultural products, resulting in poor performance because of the sensitiveness to the crisp criteria or specific ules set up by algorithms. Also restriction of the real time processing often forces to use binary segmentation but in that case some important information of the object can be lost. In this paper, the neuro net based real time recognition algorithm was proposed without extracting any visual feature but using only the directly captured raw gray images. Specially formated adaptable size of grids was proposed for the network input. The compensation of illumination was also done to accomodate the variable lighting environment. The proposed grading scheme showed very successful results.

• 한국정밀공학회지
• /
• 제15권2호
• /
• pp.7-13
• /
• 1998

This paper presents a methodology for determining machining conditions in Electric Discharge Wire-Cut. Unification of two phase neural network approach with an automatic generation of machining parameters is designed. The first phase neural network, which is 1 to M backward-mapping neural net, produces approximate machining conditions. Using approximate conditions, all possible conditions are newly created by the proposed automatic generation procedure. The second phase neural net, which is a M to 1 forward-mapping neural net, determines the best one among the generated candidates. Simulation results with ANN are given to verify that the presenting methodology could apply for determining machining parameters in Electric Discharge Wire-Cut.

• Nuclear Engineering and Technology
• /
• 제53권5호
• /
• pp.1612-1618
• /
• 2021

The fusion-barrier distribution is very sensitive to the structure of the colliding nuclei such as nuclear quadrupole and hexadecapole deformation parameters and their signs. If the nuclei that enter the fusion reaction are deformed, the barrier problem becomes complicated. Therefore the deformation parameters are taken into account in the calculations. In this study, Neuro-Fuzzy approach, ANFIS, method has been used for the estimation of ground-state quadrupole (𝜀₂) and hexadecapole (𝜀₄) deformation parameters for the nuclei. According to the results, the method is suitable for this task and one can confidently use it to obtain the data that is not available in the literature.

• 대한기계학회논문집
• /
• 제16권10호
• /
• pp.1833-1840
• /
• 1992

본 연구에서는 자동차의 발달에 따른 정비 전문가의 상대적인 능력 감퇴를 보 완하고 진단의 정확성을 높일 수 있도록 소음계측에 의한 인공 지능적 뉴로-퍼지 진단 기법을 연구하였다. 이를 위하여 진단결과에 영향을 미치는 많은 작용변수와 다양한 차량상태 등을 고려함으로서 보다 신뢰성 있는 결과를 산출해내기 위한 퍼지(fuzzy) 추론 방식의 판단법을 도입하였으며, 진단이 실패했을 경우나 입력된 데이터가 충분하 지 못할 경우에 시스템 자체의 지식을 확장시켜 나갈 수 있도록 해밍네트(hamming net )에 의한 패턴인식 기법을 적용하였다. 그리고 컴퓨터 시뮬레이션과 자동차를 대상 으로 고장진단 실험을 실시하여 기존의 진단기법과의 비교를 통한 뉴로-퍼지 진단기법 의 효율성과 알고리즘의 타당성을 검증하였다.