Research on Reliability Evaluation of Scissor Lifting Structure Based on BP Neural Network

Abstract

In order to solve the problem that the reliability of scissor lift lifting mechanism is difficult to evaluate under large load, a method based on neural network for reliability evaluation of scissor lift mechanism is verified. Based on the static analysis of the scissor lift mechanism, three kinds of variable parameters, such as geometric parameters, material parameters and external loads, which affect the reliability of the scissor lift mechanism are determined. The response surface fitting is used to obtain the maximum deformation of some design variables. The influence trend, combined with the probability analysis method to control the influence of random variables on the maximum deformation of the lifting mechanism, obtain the reliability of the lifting mechanism of 45 sets of design variables under different values, and finally use BP-neural network to fit the design variables and reliability. The functional relationship between the two, establishes the reliability evaluation model of the scissor lift mechanism, and calculates the reliability of the scissor lift mechanism. The calculation results show that the maximum relative error of the reliability calculation result of the scissor lift mechanism is 2.1%, and the minimum error is 0.9%. It proves the feasibility of the neural network applied to the reliability evaluation of the scissor lift mechanism, and provides a new method and idea for the reliability evaluation of the scissor lift mechanism.