Fretting fatigue performance prediction method based on artificial neural network

Abstract

The invention discloses a fretting fatigue performance prediction method based on an artificial neural network, and the method comprises the steps: obtaining corresponding data parameters through a series of experiments; constructing a fretting fatigue numerical model and the artificial neural network; and according to the error between a prediction result of the artificial neural network and a fretting fatigue numerical calculation result, optimizing the artificial neural network by using a back propagation algorithm to achieve global optimum and finally complete accurate prediction of the fretting fatigue performance. According to the method, improvement is carried out on the basis of the existing artificial neural network to obtain the low-cost and globally optimal artificial neural network, and finally fretting fatigue performance prediction is carried out according to the improved artificial neural network. The problems of high cost and incapability of achieving global optimum when an existing artificial neural network is adopted to predict the fretting fatigue performance are solved, the experiment and numerical calculation cost is reduced, and the prediction precision is improved.

Description

Technical field: [0001] The invention relates to the technical field of artificial intelligence, in particular to a method for predicting fretting fatigue performance based on an artificial neural network. Background technique: [0002] Fretting refers to the relative tangential motion of extremely small amplitude that occurs between the contact surfaces under the action of alternating loads such as mechanical vibration and fatigue load. The above contact surfaces are nominally static. Although there is no strict definition for the displacement amplitude of fretting, it is generally considered that the amplitude is within 100 μm. The forms of fretting damage include fretting fatigue, fretting wear and fretting corrosion. Fretting fatigue refers to the relative movement of the contact surface caused by the deformation of a contact body subjected to external alternating fatigue stress. Compared with conventional fatigue without contact relationship, fretting increases the te...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is: to overcome the deficiencies of the existing technology, to obtain a low-cost and globally optimal artificial neural network by improving on the basis of the existing artificial neural network, and to solve the problem of using the existing artificial neural network to predict micro The high cost of dynamic fatigue performance and the problem of not being able to achieve the global optimum, the fretting fatigue performance prediction method based on artificial neural network to obtain high prediction accuracy

Images