• 제목/요약/키워드: Constant Variance

검색결과 182건 처리시간 0.028초

시불변 학습계수와 이진 강화 함수를 가진 자기 조직화 형상지도 신경회로망의 동적특성 (The dynamics of self-organizing feature map with constant learning rate and binary reinforcement function)

  • 석진욱;조성원
    • 제어로봇시스템학회논문지
    • /
    • 제2권2호
    • /
    • pp.108-114
    • /
    • 1996
  • We present proofs of the stability and convergence of Self-organizing feature map (SOFM) neural network with time-invarient learning rate and binary reinforcement function. One of the major problems in Self-organizing feature map neural network concerns with learning rate-"Kalman Filter" gain in stochsatic control field which is monotone decreasing function and converges to 0 for satisfying minimum variance property. In this paper, we show that the stability and convergence of Self-organizing feature map neural network with time-invariant learning rate. The analysis of the proposed algorithm shows that the stability and convergence is guranteed with exponentially stable and weak convergence properties as well.s as well.

  • PDF

전류 패턴의 설계가 가능한 SOA Dimming Driver에 관한 연구 (A Study on SOA Dimming Driver with Current Pattern Design Capability)

  • 이주찬;엄진섭
    • 조명전기설비학회논문지
    • /
    • 제27권2호
    • /
    • pp.22-28
    • /
    • 2013
  • In this paper, the low cost SOA Dimming Driver which consisted of LabVIEW programming part capable of current pattern design, DAQ module for analog voltage output, and voltage to current converter has realized. The output current(possible to 3A) from the Driver was clearly constant without ripple and also showed no variance until 1mA unit for a long time operation. The proposed low cost Driver can replace the previous high cost SOA Drivers for wavelength swept lasers fully and provide the convenience and safety of auto-supplying a designed current pattern.

MCCARD: MONTE CARLO CODE FOR ADVANCED REACTOR DESIGN AND ANALYSIS

  • Shim, Hyung-Jin;Han, Beom-Seok;Jung, Jong-Sung;Park, Ho-Jin;Kim, Chang-Hyo
    • Nuclear Engineering and Technology
    • /
    • 제44권2호
    • /
    • pp.161-176
    • /
    • 2012
  • McCARD is a Monte Carlo (MC) neutron-photon transport simulation code. It has been developed exclusively for the neutronics design of nuclear reactors and fuel systems. It is capable of performing the whole-core neutronics calculations, the reactor fuel burnup analysis, the few group diffusion theory constant generation, sensitivity and uncertainty (S/U) analysis, and uncertainty propagation analysis. It has some special features such as the anterior convergence diagnostics, real variance estimation, neutronics analysis with temperature feedback, $B_1$ theory-augmented few group constants generation, kinetics parameter generation and MC S/U analysis based on the use of adjoint flux. This paper describes the theoretical basis of these features and validation calculations for both neutronics benchmark problems and commercial PWR reactors in operation.

Optimal Designs of Partially Constant-Stress Life Testing For Three-Component Mixed Systems

  • Park, Hee-Chang;Jeng, Kwang-Man;Kim, Min-Hwan
    • 한국데이터정보과학회:학술대회논문집
    • /
    • 한국데이터정보과학회 2002년도 춘계학술대회
    • /
    • pp.155-167
    • /
    • 2002
  • In this paper we consider optimal designs of partially constant-stress life testing which is deviced for three-component mixed systems with the considerably long time. Mixed systems are jointed serial system with parallel system. Test items are run at both use condition and accelerated condition until a specified censoring time. The optimal criterion for the sample-proportion allocated to accelerated condition is to minimized asymptotic variance of the maximum likelihood estimators of the acceleration factor and hazard rates.

  • PDF

조명의 조도 및 색온도 제어에 의한 실내 두 공간의 공간감 변화 (A Study on the Sense of Continuity between Two Rooms by Adjusting the Illuminance and The Color Temperature of Lighting)

  • 윤혜림
    • 한국실내디자인학회논문집
    • /
    • 제33호
    • /
    • pp.83-89
    • /
    • 2002
  • This paper describes the experiments to examine the sense of continuity produced by lighting between physically separated spaces. Tolerable limits of illuminance were measured for providing a sense of continuity between two rooms connected by a window. In the experiments the illuminance and color of lighting of the subjects room were changed while those of the other room were kept constant. The results show that the observers could certainly determine the range of optimum illuminance for them to recognize continuity, and the variance of the results between observers is very small. Moreover, the tolerable range of illuminance was almost constant as far as the color difference was less than some critical value. This finding would be helpful in designing a lighting system for providing a sense of continuity.

균일진폭 하중하에서의 확률론적 균열진전 수명해석 (A Stochastic Analysis of Crack Propagation Life under Constant Amplitude Loading)

  • 윤한용;양영순;윤장호
    • 대한기계학회논문집
    • /
    • 제16권9호
    • /
    • pp.1691-1699
    • /
    • 1992
  • The experimental results of fatigue crack propagation under constant amplitude loading show that intra-and inter-specimen variability exist. In this paper, a stochastic model for the estimation of mean and variance of crack propagation life is presented To take into account the intra-specimen variability, the material resistance against crack propagation is treated as an 1-dimensional spatial stochastic process, i. e. random field, varying along the propagation path. For the inter-specimen variability, C in paris equation is assumed to be a random variable. Compared with experimental results reported, the present method well estimate the variation in fatigue crack propagation life. And it is confirmed that the thicker the specimen thickness is, the less the variation of propagation life is.

다단계 재고시스템에서의 서비스수준에 관한 연구 (Service level in multiechelon Inventory systems)

  • 어윤양
    • 수산경영론집
    • /
    • 제30권2호
    • /
    • pp.25-37
    • /
    • 1999
  • Some multi echelon inventory systems carry perishable products. The value of these product reduces as the period of time they spend in the system. In this paper We derive the necessary condition to determine optimal quantity, service level for a perishable product. The systems considered consist of two echelons and carry single item. To determine the optimal order quantity, the demand is assumed to be constant, the holding costs may be different in the echelons, and it allows no shortages. I assumed the price of product decreases by negative exponential function. To determine service level, following assumptions used in the model ㆍlead time is constant. ㆍdemand is normal distribution. ㆍthe product starts to perish at the second echelon. Service level is computed for different levels of lead times and for different variance of demands and for different price functions. The experimental results indicate that the service level in cost is a function of service level in demand and perishability of product. Results of the models exhibit that perishability and the age of the product are critical to determine the lot sizing and service level.

  • PDF

브라운 운동을 따르는 열화현상을 이용한 일정스트레스 가속수명시험의 최적설계 (Optimal Design of Constant Stress Accelerated Life Tests Using Degradation Phenomenon Based on a Brownian Motion)

  • 서순근;김갑석;하천수
    • 품질경영학회지
    • /
    • 제26권1호
    • /
    • pp.74-87
    • /
    • 1998
  • This study considers optimal design of accelerated life tests under constant stress using that the first passage time to cross a critical boundary through amount of accumulated degradation has an inverse Gaussian distribution when the degradation process follows to a Brownian motion with positive drift of log linear function of stress. Optimum plans for Type I censoring are derived by minimizing the asymptotic variance of estimated quantiles at the use stress. Sensitivity analyses are also conducted to see how sensitive the optimality criterion is with respect to the uncertainties involved in the guessed values.

  • PDF

성능특성치의 열화가 와이블 분포를 따를 때 가속열화시험을 활용한 신뢰성 샘플링검사계획의 개발 (Development of Reliability Acceptance Sampling Plan for the Case where the Degradation Quantity of the Performance Characteristic follows Weibull Distribution based on the Accelerated Degradation Test)

  • 임헌상;박재훈;성시일
    • 한국신뢰성학회지:신뢰성응용연구
    • /
    • 제18권2호
    • /
    • pp.122-129
    • /
    • 2018
  • Purpose: This article develops an optimal reliability acceptance sampling plan for the case where the degradation quantity of the performance characteristic follows Weibull distribution. Method: For developing reliability acceptance sampling plans, the sample size and the acceptance constant are determined based on the accelerated characteristic of the test condition and the product. Results: The sample size and the acceptance constant are provided such that the constraints of the producer and the consumer risks are satisfied. Conclusion: Reliability acceptance sampling plans based on the accelerated degradation test method can be used for the quality control within a resonable amount of cost and time. In this article. an optimal reliability sampling plans are newly developed for this purpose.

Simulation of the Shifted Poisson Distribution with an Application to the CEV Model

  • Kang, Chulmin
    • Management Science and Financial Engineering
    • /
    • 제20권1호
    • /
    • pp.27-32
    • /
    • 2014
  • This paper introduces three different simulation algorithms of the shifted Poisson distribution. The first algorithm is the inverse transform method, the second is the rejection sampling, and the third is gamma-Poisson hierarchy sampling. Three algorithms have different regions of parameters at which they are efficient. We numerically compare those algorithms with different sets of parameters. As an application, we give a simulation method of the constant elasticity of variance model.