Papers by Keyword: Weibull Distribution

Abstract: Integral inference method for multi-state type-Ⅱcensored data is presented, which is used to evaluate the rupture life of composite material. The best unbiased estimators for the model parameters, the standard deviation and their covariance are also given. The confidence limits of the acceleration equation and the confidence intervals of percentiles for Weibull distribution are discussed in detail. According to the presented method, the experimental information of accelerated rupture life is fully exploited, and the cross information among test data in different stresses are analyzed as an integration.So its information quantity is much bigger than traditional group test method. The method provides a feasible and effective approach to rupture life evaluation and reliability estimation of composite material.

Abstract: In the field of electric appliances’ reliability, the constant-stress accelerated-life-test is commonly used to test the reliability of electric appliances. A new analysis method based on constructed data is introduced to analyze the constant-stress accelerated-life-test data of electric appliances under Weibull distribution. The correlation between shape parameter and characteristic life is took into account and the estimated value of characteristic life is modified, which increase the model fitting optimization and improve the analysis precision. Moreover, the method avoids table lookup and is easy to be realized by computer software in the application of reliability engineering for electric appliances.

Abstract: Based on the experiments on milling the 3Cr-1Mo-1/4Vsteel which is the main part of the large chemical equipment hydrogenation reactor with several types of different grooves milling inserts, we have experiment study on the impact disrepair. Using the Orthogonal experimental design method, we have cutting experiments on machining the high-strength steel with several types of different grooves milling inserts, and find out the difference of the impact disrepair invalidation types among them. Based on the plentiful and systemic impact disrepair experiments, we build the impact disrepair life cumulating distribution function mathematic model by the mathematics statistic method. We have contrast analysis of the impact disrepair average lives among these types of milling inserts, and the different grooves milling inserts are optimized. All these studies provide the theoretic and experimental bases for solving the cutter disrepair which is the key problem in the actual production and groove optimization.

Abstract: Adaptive neuro-fuzzy inference system[1] is an advanced algorithm to estimate important parameters based on limited available information. We conducted a specific analysis about this algorithm to validate our viewpoint compared with Weibull distribution[2], and rear-axle bumper was used for our experiment. The experimental results indicate that ANFIS can be more precise than Weibull distribution and more close to the real circumstances. According to the root mean square root that decreases to a relatively low value, we could infer that ANFIS is a good approach to estimate all data based on the limited given samples.

Abstract: When sequential compliance method is used for Weibull distributions, the shape parameter is usually considered to be fixed. However, because of the life of products are determined by many factors, the shape parameter is variational in practice, that is to say, the shape parameter in the criterions is different from that in the practice. In this paper, the changes of acceptance and rejection probability are researched by the influence of shape parameter changes. Finally, by means of simulation test, changes on the shape parameter affecting on the probability of acceptance and rejection are quantitatively analyzed. As a result, the larger the gap on the shape parameter in the criterions and in the practice is, the larger the gap on the producer’s risk and the consumer’s risk.

Abstract: In order to find the distribution law of coal fragmentation, mathematic model of size distribution was built according to fractal theory. Based on this, the experiments of impactive crash were carried out under different impact rate and different Protodikonov's hardness. The comparison between Weibull distribution and fractal distribution was done so as to find the relationship between the influence parameters and the coal fragmentation characteristic index, the coal fragmentation degree coefficient and the fractal dimension. The results indicate that both two types of distribution functions are suitable for the distribution discipline of coal fragmentation, but the relationship of the coal fragmentation degree and impact parameter is not reacted correctly by the coal fragmentation characteristic index and coal fragmentation degree coefficient in the Weibull distribution while the coal fragmentation degree could be expressed by the fractal dimension in fractal distribution. The relationships between the fractal dimension and the rate, the Protodikonov's hardness of coal are linear.

Abstract: Based on the theory of maximum likelihood estimation, a set of nonlinear equations is first derived for determination of parameters of Weibull distribution. To speed up convergence, an efficient algorithm is proposed for solving the parameters. Further, a large-span roof structure is taken to demonstrate the proposed method. It is proved that the responses of a nonlinear structure have non-Gaussian properties under the excitation of non-Gaussian stochastic wind pressure field. By Weibull distribution fitting, the maximum and minimum values of structural response with a certain assurance rate are computed, and the results are compared with those obtained from normal distribution.

Abstract: Natural fibers of plant origin are finding non-traditional applications as reinforcement of composite materials. The mechanical properties of fibers exhibit considerable scatter, being affected by the natural variability in plant as well as the damage accumulated during processing. For bast fibers, the primary damage mode is kink bands – zones of misaligned cellulose microfibrils extending across the fiber and oriented roughly perpendicularly to its axis. Another feature typical for natural fibers and contributing to the scatter of fiber strength is the variability of diameter along a fiber length and among the fibers. An analytical expression for the distribution of the longitudinal tensile strength of bast fibers has been derived, accounting for the strength variability of intact fibers and the effect of kink bands. Upon determining the relevant parameters from fiber damage and geometry characteristics by means of optical microscopy, the theoretical strength distribution function has been found to agree reasonably well with the test results of elementary flax fibers.

Abstract: Extruded insulation is a major kind of insulation used in power cable. It is significant to evaluate extruded insulation lifetime suffered from electrical aging, which can improve the reliability of power cable. In this paper, a step-stress test method is used in accelerated life tests and Weibull model is used to statistic analysis for the mean lifetime of several samples under the same voltage value, and then the least square method is used to calculate the parameter of Weibull distribution. This paper uses inverse power function to fit test data and calculate voltage endurance coefficients. Constant-stress test data is also used as the counterpart of that measured by the step-stress test. It is indicated that the test voltages of step-stress test are more easily selected than that of constant tests and the data of the former is less scattered and the result is more reliable.

Abstract: The graphite nodule count and size distribution are important structural parameters in the quantitative characterization of the microstructure of ductile cast irons. In several cases, it is observed that local surface damages (cracks or microchip formations) are generated by the final manufacturing process (superfinishing operation), and these defects are originated basically from the hidden (invisible) graphite nodules located directly below surface. Based on measured data obtained by an image analyzer, a stereological model and a simulation algorithm have been developed to analyse the correspondances between the graphite morphology and the defect formation. This method makes it possible to establish a correlation between the microstructure parameters and the occurrence of local surface defects on ductile cast iron components.