Papers by Keyword: Normal Distribution

Abstract: This paper presents the press fit calculation that depends on different methods, the sizes of holes and shafts are quantities distributed according to the normal law, so the tolerance of the joint between the shaft and the hub is also distributed according to the normal law with two parameters: the mean value and the standard deviation. The paper also demonstrates the procedure and computer program for calculating the metal interference joints given by the probability method, thereby giving a chart of choosing tolerance depending on the applied load, simultaneously calculating the interference joints by the min-max method, and comparing it with the probability method, etc. Calculation by the probability method gives more reasonable working parameters. Along with the interference fit parameters, the consideration of materials is mentioned as well.

Abstract: The use of parallel manipulators in industrial is growing. Among key advantages of parallel manipulators versus their serial counterparts, is their improved end-effector positioning accuracy than open-loop mechanism. However, undesirable dimensional tolerance and joint clearance can decrease the positioning accuracy of the end-effector. In this article, Taguchi method is applied to a 3-PSP parallel manipulator to determine how dimensional tolerance and joint clearance affects the accuracy of its end effector. Because of random nature of dimensional tolerance, it is assumed that actual value of all kinematic parameters are normally distributed. Taguchi method is then used and effect of tolerance on accuracy for each of the manipulator kinematics parameters is obtained. Finally, a tolerance set resulting in best accuracy is predicted by the Taguchi method. This tolerance is verified with a new set of experiment.

Abstract: It’s very important for the traffic flow theory, the traffic management and control, and the programming and design of roads to master the law of speed. And the most intuitive form is the speed distribution to describe the law. Based on the maximum entropy principle, this paper proposes a model which can generate the speed distribution curves only with the observed date. And the availability of this method has been proved by the example analysis. The fact has also been found that fitting with maximum entropy distribution is better than with normal distribution in peak hour and is worse than it in off peak hour, but the difference is not great. This model does not need assumptions. Moreover it has a simple calculation and a strong practicability. So this paper makes a contribution to the study of the speed distribution.

Abstract: The probability distribution of electrical characteristic parameters of semiconductor device is an important reference which is used to analyze the reliability and quality consistency of devices. These distributions are considered as normal distribution at home and abroad. This paper utilized mature GaAs MESFET low noise amplifier as analytic sample which is volume production and wide application, and used high-precision Agilent B1505A device analyzer to test main electrical characteristics of 408 samples. After the distribution generation of test results, the Skewness-Kurtosis method was used to analyze probability distributions of the results. At last, the conclusion of distribution of measuring parameter is non-normal distribution was educed.

Abstract: In this paper, the experimental of pore diameter distribution characteristics of spunbond and meltblown composite nonwoven is carried out by using of gas bubble method. The influence of 7 kinds of wetting liquid to measurement results is studied, including of Galwick, Porefil, Silpore, Silwick, Dimethyl silicone, Isopropanol and Alcohol. The results show that wetting liquids of Galwick, Silwick and Dimethyl silicone can obtain the consistent value of pore diameter, meanwhile, have nearly normal distribution characteristics of pore diameter. Therefore, the wetting liquids of Galwick, Silwick and Dimethyl silicone are ideal wetting liquid for nonwoven. While the other four kinds of wetting liquid measurement results vary greatly, and don’t show normal distribution, they are not suitable as the wetting liquid of nonwoven by gas bubble method.

Abstract: In the paper a production model with failures is presented where successive failure-free times are supposed to have normal distributions and are followed by normally distributed times of repairs. Unknown parameters of distributions are estimated using e.g. empirical moments approach. Predictions of unknown parameters are done using classical regression method. Having Mean Time To First Failure, and Mean Time of Repair a disturbance robust predictive schedule is generated using rule: Minimal Impact of Disturbed Operation on the Schedule. If a machine's failure-free time is not successfully predicted reactive schedule is generated using criterion: Minimal Impact of Rescheduled Operation on the Schedule.

Abstract: Cut angle is one of the best important parameters of chimney demolished by controlled blasting. The suitable angle is effected by a lot of factors. But mechanical principle is not entirely clear. The theoretical value of angle is usually designed by experience formula . At the same time, the factual angle made by blasting is also fuzzy and random. So in this paper, the formula to calculate fuzzy reliability of cut angle is derived according to fuzzy reliability theory. It provides an credible parameter for engineering blasting designer. Linear memberships function is adopted for theory value of cut angle and the factual blasting angle is a random variable which is suggested to be normally distributed. At last, an engineering example is given to verify the method of this paper.

Abstract: This article introduced the 6 sigma management and 6 sigma level. The key point is to explain 3.4DPMO how to calculate. And,it also introduced the important means of six sigma management. At last,it shows the application of six sigma.

Abstract: This paper presents the use of statistical-probabilistic method in determining pile bearing capacities over a number of driven piles. Four dynamic formulas were employed to estimate pile bearing capacity including modified ENR, Hiley, Navy – McKay and Danish. We investigated the final setting data of 47 concrete piles with 600 mm diameter in the construction projects of New Naval Engineering Building Hasanuddin University. Based on the data, pile bearing capacity were computed and then analyzed statistically. Goodness of fit with Kolmogorov-Smirnov and Shapiro-Wilk were used to fit the probability distribution function (PDF) of the pile bearing capacity data to the PDF model. It was found that the pile bearing capacity estimated using ENR is more uniform with 506 tons average pile capacity and 6.4% COV, while that with Hiley and Danish are less various with 252 tons and 346 tons average pile capacity, and 14.7% and 16.6% COV respectively. Navy-McKay was found to have 465.8 tons average pile capacity with higher variability of 44.08%. A 90% Probability of pile bearing capacity estimated by ENR is 535 tons, or 1.17 times the upper bound, and 1.4 times the lower bound of pile capacity measured by pile driving analyzer (PDA). In comparison, 90% probability estimated by Danish is 420 tons or 0.93 times and 0.92 of the upper and lower bound of pile capacity measured by PDA, respectively. The Navy-McKay seeems to be overestimated whereas Hiley is underestimated.

Abstract: The net profit of the enterprise is the balance of total corporate profits after income tax, mainly from business and enterprise project investment, but preferential tax policies of the countries have an important role in the corporate R&D investment field, also to bring great gains. This paper focuses on the current situation of China's R&D analysis and multiple regression model to carry out R&D investment related empirical analysis of industries and enterprises in Shanghai in 2011, and eventually come to optimize the system of tax incentives for R&D investment with positive feedback.