Reliability Sensitivity Analysis Of Mechanical Parts With The Local Stress Concentration

In the practical engineering, the damage and destroy of the structure often occur at the stress concentration position, therefore, it becomes very important for stress concentration factors (SCF) to be determined. The expression of stress concentration factors can be solved difficultly using theoretical methods, and so experimental methods are applied widely. Applying experimental methods, the numerical solution can be obtained accurately, however, the explicit expression of stress concentration factors can't be given directly and which will bring some difficulties for the farther reliability analysis and design. Thereby, it is necessary to seek the approximate method that can give the formulation of stress concentration factors with simple form and nice precision on the base of the experiment data. An important purpose of determining the stress concentration factors is that the stress concentration factors will be combined with the modern design method and applied to the practical engineering structure. In the study of the local stress concentration, more attention has been focused on the confirmation of stress concentration factors at present, and has been seldom done on the corresponding reliability problem in the world. However, in the reliability. For the stress concentration is an important factor that affects the mechanical parts reliability, the research of the corresponding reliability problem has an important theoretic and engineering practical significance in the case of the stress concentration. In this study, NN technique and the reliability theory have been combined, mechanical parts reliability sensitivity analysis and methods are given for the structure with local stress concentration.Reliability (optimize) technology has been applying into each field of themechanical engineering at present, and even the field of structure design intensity and lifespan analysis, select material (the select of component and heat treatment technology etc) and failure analysis etc, obviously, the most optimally reliability problem of the production will touch the using of resource and energy sources in reason. Because the most optimally reliability design could get the production, which have the smaller volume, the lighter weight, the little material consume, the little working man-hour and reasonable reliability. When the reliability analysis of mechanical components is done, the influence degree of the mechanical part failure by each factor is different, so it has a very important significance on the reliability sensitivity analysis of mechanical part. Reliability sensitivity analysis of mechanical part has the important application in the aspects of the reliability design and maintain, reliability optimize design, reliability maintenance etc. If some factor has more influence to mechanical components failure, then it should be controlled severely in the process of the design and manufacture to make it change smaller, which can ensure the mechanical components have enough safety and reliability; Contrarily, if the influence of some factor's variability is insignificant, then it can be deal with as ascertain value in the process of mechanical components reliability design, which can reduce the numbers of the random variable. In this paper, reliability sensitivity be studied to reflect this uncertainty, a reliability sensitivity method be put forward to ensure the effect on the reliability of engineering machinery components due to the change of design parameter, consequently, the reasonable and necessary theoretical foundation be offered for mechanical components design, manufacture, using and evaluation.Neural network (NN) is a complex network system consists of many nerve cells with different structure. The form and function of each nerve center is simple, but the network system could realize different complex functions. Because NN is a complex non-linear dynamics system with many fine characteristics, such as self-organizing, self-adapting and self-learning abilities, and so NN has been used successfully in different studies.On the basis of the structural reliability research actuality, in the structure reliability problem considered in the case of the stress concentration, neuralnetwork technology is applied to the reliability sensitivity analysis field in the paper. And the NN with Back Propagation (BP) algorithm is adopted, because it is the most adult and is used widely in practical engineering. BP neural network could approach any continuous function and gain higher simulation precision. At present, more attention has been given in the stress concentration problem, and modern structural reliability theory and neural network technique have been developed rapidly. But it is difficult for the structural reliability to be solved in the case of the stress concentration. Neural network (NN) technique has been used in this paper to simulate the relationship between the basic random variables and the stress concentration factors, and the explicit expression of the stress concentration factors can be obtained directly. On the basis of this, the expression of the stress concentration factors given by NN technique and the reliability theory have been combined to calculate the reliability and reliability sensitivity using MCS to solve the structural reliability sensitivity problems in the case of the stress concentration, and then the corresponding methods of reliability analysis have been presented.