• Title/Summary/Keyword: neural network.

Search Result 11,766, Processing Time 0.043 seconds

High Performance of Induction Motor Drive with HAl Controller (HAI 제어기에 의한 유도전동기 드라이브의 고성능 제어)

  • Nam, Su-Myeong;Choi, Jung-Sik;Ko, Jae-Sub;Chung, Dong-Hwa
    • Proceedings of the KIEE Conference
    • /
    • 2005.10b
    • /
    • pp.570-572
    • /
    • 2005
  • This paper is proposed adaptive hybrid artificial intelligent(HAI) controller for high performance of induction motor drive. The design of this algorithm based on fuzzy-neural network(FNN) controller that is implemented using fuzzy control and neural network. This controller uses fuzzy rule as training patterns of a neural network. Also, this controller uses the back-propagation method to adjust the weights between the neurons of neural network in order to minimize the error between the command output and actual output. A model reference adaptive scheme is proposed in which the adaptation mechanism is executed by fuzzy logic based on the error and change of error measured between the motor speed and output of a reference model. The control performance of the adaptive FNN controller is evaluated by analysis for various operating conditions. The results of experiment prove that the proposed control system has strong high performance and robustness to parameter variation, and steady-state accuracy and transient response.

  • PDF

An Neural Network Direct Controller For Nonlinear Systems (신경망을 이용한 비선형 동적 시스템의 최적 제어에 관한 연구)

  • Jeon, Jeong-Chay;Lee, Hyung-Chung;Ryu, In-Ho;Kim, Hee-Sook
    • Proceedings of the KIEE Conference
    • /
    • 2004.07d
    • /
    • pp.2498-2500
    • /
    • 2004
  • In this paper, a direct controller for nonlinear plants using a neural network is presented. The controller is composed of an approximate controller and a neural network auxiliary controller. The approximate controller gives the rough control and the neural network controller gives the complementary signal to further reduce the output tracking error. This method does not put too much restriction on the type of nonlinear plant to be controlled. In this method, a RBF neural network is trained and the system has a stable performance for the inputs it has been trained for. Simulation results show that it is very effective and can realize a satisfactory control of the nonlinear system.

  • PDF

A Study on the Diagnosis of Cutting Tool States Using Cutting Conditions and Cutting Force Parameters(II) -Decision Making- (절삭조건과 절삭력 파라메타를 이용한 공구상태 진단에 관한 연구(II) -의사결정 -)

  • 정진용;서남섭
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.15 no.4
    • /
    • pp.105-110
    • /
    • 1998
  • In this study, statistical and neural network methods were used to recognize the cutting tool states. This system employed the tool dynamometer and cutting force signals which are processed from the tool dynamometer sensor using linear discriminent function. To learn the necessary input/output mapping for turning operation diagnosis, the weights and thresholds of the neural network were adjusted according to the error back propagation method during off-line training. The cutting conditions, cutting force ratios and statistical values(standard deviation, coefficient of variation) attained from the cutting force signals were used as the inputs to the neural network. Through the suggested neural network a cutting tool states may be successfully diagnosed.

  • PDF

Estimation of Hardened Depth in Laser Surface Hardening Processes Using Neural Networks (레이저 표면경화공정에서 신경회로망을 이용한 경화층깊이 추정)

  • 박영준;조형석;한유희
    • Transactions of the Korean Society of Mechanical Engineers
    • /
    • v.19 no.8
    • /
    • pp.1907-1914
    • /
    • 1995
  • An on-line measurement of the workpiece hardened depth in laser surface hardening processes is very much difficult to achieve, since the hardening process occurs in depth wise direction. In this paper, the hardened depth is estimated using a multilayered neural network. Input data of the neural network are the surface temperatures at arbitrary chosen five surface points, laser power and traveling speed of laser beam torch. To simulate the actual hardening process, a finite difference method(FDM) is used to model the process. Since this model yields the calculation results of the temperature distribution around the workpiece volume in the vicinity of the laser torch, this model is used to obtain the network's training data and laser to evaluate the performance of the neural network estimator. The simulation results show that the proposed scheme can be used to estimate the hardened depth with reasonable accuracy.

Shape Optimization of Cut-Off in Multiblade Fan/Scroll System Using CFD and Neural Network (신경망 기법을 이용한 다익 홴/스크롤 시스템의 컷오프 최적화)

  • Han, S.Y.;Maeng, J.S.;Yoo, D.H.
    • Proceedings of the KSME Conference
    • /
    • 2001.11b
    • /
    • pp.365-370
    • /
    • 2001
  • In order to minimize unstable flow occurred at a multiblade fan/scroll system, optimal angle and shape of cut-off was determined by using two-dimensional turbulent fluid field analyses and neural network. The results of CFD analyses were used for learning as data of input and output of neural network. After learning neural network optimization process was accomplished for design variables, the angle and the shape of cut-off, in the design domain. As a result of optimization, the optimal angle and shape were obtained as 71 and 0.092 times the outer diameter of impeller, respectively, which are very similar values to previous studies. Finally, it was verified that the fluid field is very stable for optimal angle and shape of cut-off by two-dimensional CFD analysis.

  • PDF

Automatic Recognition System for Number Plate of Car using Multi Neural Network (다중 신경망을 이용한 차량 번호판의 자동인식 시스템)

  • Park, S.H.;Choi, G.J.;Ahn, D.S.
    • Journal of Power System Engineering
    • /
    • v.5 no.2
    • /
    • pp.93-99
    • /
    • 2001
  • This paper presents the automatic recognition system for car number plate. In our country, two types of number plate pattern is used. The one is old type of number plate, the other is new type of number plate. To recognize both new and old type number plates, the system must have flexibility. Therefore, in this paper, automatic recognition system is developed by use of the neural network for good adaptation, good generalization, and modulation. And because the number plate is made of three codes, the multi neural network consists of three networks. Neural network is teamed by GDR(Generalized Delta learning Rule) and it is verified the effectiveness of the method through experimental results.

  • PDF

Predicting the subjective loudness of floor impact noise in apartment building using neural network analysis (Neural Network Analysis를 이용한 공동주택 바닥충격음의 주관적 라우드니스 예측)

  • You, Byoung-Cheol;Jeon, Jin-Yong;Cho, Moon-Jae
    • Proceedings of the Korean Society for Noise and Vibration Engineering Conference
    • /
    • 2002.11a
    • /
    • pp.351.1-351
    • /
    • 2002
  • In this research, the relationship between physical measurements and subjective evaluations of floor impact noise in apartment building was quantified by applying the neural network analysis due to its complex and nonlinear characteristics. The neural network analysis was undertaken by setting up L-value, inverse A index, Zwicker parameters and ACF/IACF factors, as input data, which came from the measurements at real suites of apartment building having various sound insulations. (omitted)

  • PDF

A study on the computer aided testing and adjustment system utilizing artificial neural network

  • Koo, Young-Mo;Woo, Kwang-Bang
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 1992.10b
    • /
    • pp.65-69
    • /
    • 1992
  • In this paper, an implementation of neuro-controller with an application of artificial neural network for an adjustment and tuning process for the completed electronics devices is presented. Multi-layer neural network model is employed with the learning method of error back-propagation. For the intelligent control of adjustment and tuning process, the neural network emulator (NNE) and the neural network controller(NNC) are developed. Computer simulation reveals that the intelligent controllers designed can function very effectively as tools for computer aided adjustment system. The applications of the controllers to the real systems are also demonstrated.

  • PDF

A neuro-fuzzy adaptive controller

  • Chung, Hee-Tae;Lee, Hyun-Cheol;Jeon, Gi-Joon
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 1992.10b
    • /
    • pp.261-264
    • /
    • 1992
  • This paper proposes a neuro-fuzzy adaptive controller which includes the procedure of initializing the identification neural network(INN) and that of learning the control neural network(CNN). The identification neural network is initialized with the informations of the plant which are obtained by a fuzzy controller and the control neural network is trained by the weight informations of the identification neural network during on-line operation.

  • PDF

Design and Implementation of Routing System Using Artificial Neural Network

  • Kim, Jun-Yeong;Kim, Seog-Gyu
    • Journal of the Korea Society of Computer and Information
    • /
    • v.22 no.12
    • /
    • pp.137-143
    • /
    • 2017
  • In this paper, we propose optimal route searching algorithm using ANN(Artificial Neural Network) and implement route searching system. Our proposed scheme shows that the route using artificial neural network is almost same as the route using Dijkstra's algorithm but the time in our propose algorithm is shorter than that of existing Dijkstra's algorithm. Proposed route searching method using artificial neural network has better performance than exiting route searching method because it use several weight value in making different routes. Through simulation, we show that our proposed routing system improves the performance and reduces time to make route irrespective of the number of hidden layers.