Papers by Keyword: Weibull Distribution

Abstract: It is difficult to estimate the parameters of Weibull distribution model using maximum likelihood estimation based on particle swarm optimization (PSO) theory for which is easy to fall into premature and needs more variables, ant colony algorithm theory was introduced into maximum likelihood method, and a parameter estimation method based on ant colony algorithm theory was proposed, an example was simulated to verify the feasibility and effectiveness of this method by comparing with ant colony algorithm and PSO.This template explains and demonstrates how to prepare your camera-ready paper for Trans Tech Publications. The best is to read these instructions and follow the outline of this text.

Abstract: Interval-censored data result from incomplete observation of random variable when the values are known only to lie in an interval, instead of being observed exactly. The method of Maximum Likelihood Estimation is used to assess the parameters of the supposed distribution. Unlike in case of Weibull distribution, for regular test schedule of exponentially distributed data a closed formula is derived. Due to surprising simplicity the derived formula is open to direct interpretation in terms of observed input information.

Abstract: The Type-II generalized progressively hybrid censored scheme with masked data is presented. Based on masked system lifetime data, using the expectation maximization algorithm and the Quasi-Newton method, we obtain the Maximum Likelihood Estimation (MLE) of the components distribution parameters in the Weibull case. Finally, Monte Carlo simulation is presented to illustrate the effect.

Abstract: When the device is inspected only once, there are only two possible statuses either functioning or failed at the time of inspection. In this paper, we consider a series system consisting of two components with lifetimes following weibull distributions and a competing risks model is used to study the series system for quantal-response data. Based on the quantal-response data, the maximum likelihood estimates of parameters of weibull distribution are derived. The model is illustrated using a practical numerical example of two-component series products, and the statistical properties of the maximum likelihood estimators were studied via Monte Carlo simulation under three-stage inspected scheme for various sampling sizes. This study verified that the model is practical. This research results can be applied to the reliability analysis of one-shot products with Weibull components lifetime distribution and the stockpile storage performance test.

Abstract: It is difficult to estimate the parameters of Weibull distribution model using Maximum Likelihood Estimation based on Ant Colony Algorithm (ACA) or Particle Swarm Optimization theory (PSO) for which is easy to fall into premature and needs more variables, thus Fruit Fly Optimization Algorithm (FOA) theory is introduced into maximum likelihood estimation, and a parameter estimation method based on FOA theory is proposed, an example has been simulated to verify the feasibility and effectiveness of this method by comparing with ACA and PSO.

Abstract: Aiming at the test of Aero-engine bearing is expensive, small sample without failure, and bearing life obeys Weibull distribution, small sample data is introduced in order to estimate the reliability of bearing with the method of Bayesian point estimation. The weighted least squares method is utilized to estimate the shape and scale parameters of Weibull distribution in the case of no failure. The bearing cumulative failure function, failure rate and average life can be gotten. Finally, the bearing experiment data is used to verify the validity of the small sample evaluation. It is proved that the method has an important value for the replacement and maintenance of Aero-engine bearing.

Abstract: Frame is the main bearing component of bogie and the reliability of which directly affects the performance and safety of the locomotive. Survival analysis is used for reliability analysis of bogie frame to solve uncertain life time problem. It turns out that the best life distribution model is three-parameter Weibull distribution. A prediction model of failure rate composed of PSO-BP is came up with to predict the failure rate of bogie frame accurately.

Abstract: The red ceramic pieces Campos-RJ degrade easily when they are in the built environment. With the intention to reduce the degradation in these pieces, was introduced petroleum coke in red ceramic. Petroleum coke is a solid fossil fuel, black in color and about granular form. With percentage of 0%, 0.5%, 1% and 1.5% clay added to the coke were obtained is prismatic ceramic samples. After drying at 110 ° C, fired at 800°C and 900°C and carried out at accelerated degradation in the laboratory by degradation equipment, obtaining the technological properties and Weibull distributions before and after degradation in the samples. The 900°C gave the highest Weibull modulus (m = 12.50) compared with the firing pieces at 800°C. The results show that the incorporation of 0.5% of petroleum coke improves the Weibull modulus of the degraded material.

Abstract: The aim of this work was of evaluate the introduction of petroleum coke in a red ceramic. Petroleum coke is a solid fossil fuel, petroleum derivative, of black color and granular form approximately, obtaining as a byproduct from distillation of petroleum, by the process called "cracking" heat. This product represents from 5% to 10% of the total oil in the refinery. With percentage of 0%, 0.5%, 1% and 1.5% coke added into clay were obtained ceramic pieces. After drying at 110°C and firing at 750°C, 800°C and 850°C, were obtained the mechanical and physical properties and the Weibull distribution, used to evaluate the failure probability of the material. The results show the influence of petroleum coke in ceramics, suggesting introduce 1% of coke at 800oC, when the Weibull modulus reaches value 9 (m=9).

Abstract: The quality of powder of non-metal materials directly relates to the force exerted on grinding roller, while the force on grinding roller relates to the thickness of the material layer. The uneven pressure distribution between the roller and material layer is caused by the drum-shaped characteristics of vertical mill grinding roller. This paper studies the pressure distribution of roller in compacted zones, established mathematical models of pressure distribution analysis, and provides a theoretical basis for improving the vertical mill production process as well as yield and quality of the powder.