• Title/Summary/Keyword: Genetic gains

Search Result 117, Processing Time 0.028 seconds

Development of Genetic Algorithm for Robust Control of Mobile Robot (모바일 로봇의 견실제어를 위한 제네틱 알고리즘 개발)

  • 김홍래;배길호;정경규;한성현
    • Proceedings of the Korean Society of Machine Tool Engineers Conference
    • /
    • 2004.04a
    • /
    • pp.241-246
    • /
    • 2004
  • This paper proposed trajectory tracking control of mobile robot. Trajectory tracking control scheme are real coding genetic-algorithm and back-propergation algorithm. Control scheme ability experience proposed simulation. Stable tracking control problem of mobile robots have been studied in recent years. These studios have guaranteed stability of controller, but the performance of transient state has not been guaranteed. In some situations, constant gain controller shows overshoots and oscillations. So we introduce better control scheme using Real coding Genetic Algorithm(RCGA) and neural network. Using RCGA, we can find proper gains in several situations and these gains are generalized by neural network. The generalization power of neural network will give proper gain in untrained situation. Performance of proposed controller will verify numerical simulations and the results show better performance than constant gain controller.

  • PDF

Optimization of control parameters for speed control of a hydraulic motor using genetic algorithms (유전알리고즘을 이용한 유압모터의 속도제어파라메터 최적화)

  • Hyun, Jang-Hwan;Ahn, Chul-Hyun;Lee, Chung-Oh
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.14 no.9
    • /
    • pp.139-145
    • /
    • 1997
  • This study is concerned with the optimizing method of control parameters for a hydraulic speed control system by using genetic algorithms which are general purpose search algorithms based on natural evolution and genetics. It is shown that the genetic altorithms satisfactorily oiptimized control gains of the PI speed control system of an electrohydraulic servomotor and that optimization of control para- meters can be achived without much experience and knowledge for tuning. It is also shown that optimal gains may be determined from fitness distribution curves plotted in given gain spaces.

  • PDF

Optimal Control of Time and Energy for Mobile Robots Using Genetic Algorithm (유전알고리즘을 이용한 이동로봇의 시간 및 에너지 최적제어)

  • Park, Hyeon-jae;Park, Jin-hyun;Choi, Young-kiu
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.21 no.4
    • /
    • pp.688-697
    • /
    • 2017
  • It is very difficult to solve mathematically the optimal control problem for non - linear mobile robots to move to target points with minimum energy related to velocity, acceleration and angular velocity in minimum time. This paper proposes a method to obtain optimal control gains with which mobile robots move with minimum energy related to velocity, acceleration and angular velocity in minimum time using genetic algorithms. Mobile robots are non - linear systems so that their optimal control gains depend on initial positions. Hence initial positions are divided into some partition points and optimal control gains are obtained at each partition point with genetical algorithms. These optimal control gains are used to train neural networks that generate proper control gains at arbitrary initial position. Finally computer simulation studies have been conducted to verify the effectiveness of the method proposed in this paper.

A Design on Robust Model Following PD Control System Using Genetic Algorithm (유전 알고리즘을 이용한 강인한 모델 추종형 제어 시스템의 설계)

  • Cho, K.Y.;Hwang, H.J.;Kim, D.W.;Seo, J.I.;Lee, K.H.;Park, J.H.;Hwang, C.S.
    • Proceedings of the KIEE Conference
    • /
    • 1997.11a
    • /
    • pp.119-121
    • /
    • 1997
  • This paper suggests a design method of the robust model following PD control system using genetic algorithm. This PD control system is designed by applying genetic algorithm with reference model to the optimal determination of proportional and derivative gains that are given by PD servo controller. These proportional and derivative gains are optimized simultaneously in the search domain guaranteeing the robust stability of closed-loop system satisfying different stability margins. The effectiveness of this PD control system is verified by computer simulation.

  • PDF

Relationships between Distribution of Number of Transferable Embryos and Inbreeding Coefficient in a MOET Dairy Cattle Population

  • Terawaki, Y.;Asada, Y.
    • Asian-Australasian Journal of Animal Sciences
    • /
    • v.15 no.12
    • /
    • pp.1686-1689
    • /
    • 2002
  • Genetic gains and inbreeding coefficients in a Holstein MOET breeding population were predicted under different conditions relating to the distribution of the number of transferable embryos collected per flush using Monte Carlo simulation. The numbers of transferable embryos collected per flush were determined using five distributions (distributions 1, 3, 5, 7 and 9) with different aspects and similar means. Distributions 1, 3, 5, 7 and 9 were assumed to have gamma distribution's parameters ($\alpha$ and $\beta$) of (1 and 4.4), (3 and 1.47), (5 and 0.88), (7 and 0.63) and (9 and 0.49), respectively. Inbreeding rates were statistically significantly different among distributions but genetic gains were not. Relationships between inbreeding rates and variances of family size could be were clearly distinguished. The highest inbreeding coefficients were predicted in distribution 1 with the largest variance of family size, while distributions 5, 7 and 9 with smaller variance of family size had lower inbreeding coefficients.

Stabilization of Inverted Pendulum Using Neural Network with Genetic Algorithm

  • Jin, Dan;Kim, Kab-Il;Son, Young-I.
    • Proceedings of the KIEE Conference
    • /
    • 2003.11c
    • /
    • pp.425-428
    • /
    • 2003
  • In this paper, the stabilization of an inverted pendulum system is studied. Here, the PID control method is adopted to make the system stable. In order to adjust the PID gains, a three-layer neural network, which is based on the back propagation method, is used. Meanwhile, the time for training the neural network depends on the initial values of PID gains and connection weights. Hence, the genetic algorithm Is considered to shorten the time to find the desired values. Simulation results show the effectiveness of the proposed approach.

  • PDF

Estimation of Genetic Gains in Commercial Layer Breeding Population (상업용 난용종계 집단에서의 유전적 개량량 추정에 관한 연구)

  • 오봉국;최연호
    • Korean Journal of Poultry Science
    • /
    • v.17 no.4
    • /
    • pp.243-254
    • /
    • 1990
  • This study was carried out to investigate the effectiveness of the selection for commercial populations of layer chickens subjected to multiple objectives. For that purpose, predicted selection responses obtained from estimated genetic parameters and observed values were compared. Data for two layer pure lines, Line-w(Single Comb White Leghorn) and Line-B (brown layer) which have been maintained at the Mani Breeding Farm were collected from 1980 to 1985 during 5 generations. The annual genetic gains were estimated by the moth of selection index in retrospect on the basis of selection differentials, phenotypic and genetic variance-covariance for the traits considered. SM was found to be shorten by 1.67 days and 1.14 days per generation in Line-W and Line-B. EN300 and EN400 were found to be increased by 4.15 and 5.92 per generation in Line-W and 257 and 3.73 per generation in Line-B. The annual gains realized were found to be significantly different from expected gains predicted on the basis of the annual selection differentials and genetic parameters in later generations, but it could not be concluded that the differences were attributed to genetic effects.

  • PDF

Genetic Variation in Growth and Body Dimensions of Jersey and Limousin Cross Cattle. 2. Post-Weaning Dry and Wet Season Performance

  • Afolayan, R.A.;Pitchford, W.S.;Weatherly, A.W.;Bottema, C.D.K.
    • Asian-Australasian Journal of Animal Sciences
    • /
    • v.15 no.10
    • /
    • pp.1378-1385
    • /
    • 2002
  • The importance of direct genetic, maternal, heterosis and epistatic effects were examined on post-weaning weight, height, length, girth, fat depth and muscle (ratio of stifle to hip width) with dry and wet season gains in these traits. The breeds used were two pure breeds (Jersey and Limousin), the Limousin${\times}$Jersey $F_1$, and two backcrosses ($F_1{\times}$Jersey dams and $F_1{\times}$Limousin dams). Direct genetic effects were large (p<0.001) for all traits except for length. Jersey maternal effects were large for weight, girth, fat depth and muscle in the post-weaning wet season gains which is an evidence of the impact of Jersey dam on progeny beyond weaning. There were large heterosis effects on fat depth and muscle relative to other traits. Epistatic effects were observed for post-weaning performance in weight, girth, fat depth and muscle. There are indications that there were different genetic effects for post-weaning compared to preweaning growth traits. Thus, it could be hypothesized from this study that different quantitative trait loci (QTL) affect early and late growth in Jersey and Limousin cross cattle breeds. The follow up work will examine the different chromosomal gene effects on pre- and post-weaning growth.

GENETIC ALTERATIONS OF HUMAN ORAL CANCERS USING COMPARATIVE GENOMIC HYBRIDIZATION (Comparative genomic hybridization 기법을 이용한 인체 구강암의 유전자 변화에 대한 연구)

  • Lee, Myeong-Reoyl;Shim, Kwang-Sup;Lee, Young-Soo;Woo, Soon-Seop;Kong, Gu
    • Journal of the Korean Association of Oral and Maxillofacial Surgeons
    • /
    • v.26 no.3
    • /
    • pp.245-253
    • /
    • 2000
  • The development and progression of oral cancer is associated with an accumulation of multiple genetic alterations through the multistep processes. Comparative genomic hybridization(CGH), newly developed cytogenetic and molecular biologic technique, has been widely accepted as a useful method to allow the detection of genetic imbalance in solid tumors and the screening for chromosome sites frequently affected by gains or losses in DNA copy number. The authors examined 19 primary oral squamous cell carcinomas using CGH to identify altered chromosome regions that might contain novel oncogenes and tumor suppressor genes. Interrelationship between these genetic aberrations detected and major oncogenes and tumor suppressor genes previously recognized in carcinogenesis of oral cancers was studied. 1. Changes in DNA copy number were detected in 14 of 19 oral cancers (78.9%, mean: 5.58, range: $3{\sim}13$). High level amplification was present in 4 cases at 9p23, $12p21.1{\sim}q13.1$, 3q and $8q24{\sim}24.3$. Fourteen cases(78.9%, mean: 3.00, range: $1{\sim}8$) showed gains of DNA copy number and 12 cases(70.5%, mean: 2.58, range: $1{\sim}9$) revealed losses of DNA copy number. 2. The most common gains were detected on 3q(52.6%), 5p(21.0%), 8q(21.0%), 9p(21.0%), and 11q(21.0%). The losses of DNA copy number were frequently occurred at 9p(36.8%), 17q(36.8%), 13q(26.3%), 4p(21.0%) and 9p(21.0%). 3. The minimal common regions of gains were repeatedly observed at $3q24{\sim}26.7$, $3q27{\sim}29$, $1q22{\sim}31$, $5p12{\sim}13.3$, $8q23{\sim}24$, and 11q13.1-13.3. The minimal common regions of losses were detected at $9q11{\sim}21.3$, 17p31, $13q22{\sim}34$, and 14p16. 4. In comparison of CGH results with tumor stages, the lower stage group showed more frequent gain at 3q, 5q, 9p, and 14q, whereas gains at 1q($1q22{\sim}31$) and 11q($11q13.1{\sim}13.3$) were mainly detected in higher stage group. The loss at $13q22{\sim}34$ was exclusively detected in higher stage. The results indicate that the most frequent genetic alterations in the development of oral cancers were gains at $3q24{\sim}26.3$, $1q22{\sim}31$, and $5p12{\sim}13.3$ and losses at $9q11{\sim}21.3$, 17p31, and 13q. It is suggested that genetic alterations manifested as gains at $3q24{\sim}26.3$, $3q27{\sim}29$, $5p12{\sim}13.3$ and 5p are associated with the early progression of oral cancer. Gains at $1q22{\sim}31$ and $11q13.1{\sim}13.3$ and loss at 13q22-34 could be involved in the late progression of oral cancers.

  • PDF

An Optimal Control of the Crane System Using a Genetic Algorithm (유전알고리즘을 이용한 크레인 시스템의 최적제어)

  • 최형식
    • Journal of Advanced Marine Engineering and Technology
    • /
    • v.22 no.4
    • /
    • pp.498-504
    • /
    • 1998
  • This paper presents an optimal control algorithm for the overhead crane. To control the swing motion and the position tracking of the payload of the overhead crane a state feedback control algorithm is applied. by using a hybrid genetic algorithm the feedback gains of the state feedback is optimized to minimize the cost function composed of position errors and payload swing angle under unknown constant disturbances. Computer simulation is performed to demonstrate the effectiveness of the proposed control algorithm.

  • PDF