Method and device for predicting remaining life of mechanical equipment

Abstract

The invention discloses a method and device for predicting the remaining life of mechanical equipment. The method includes the steps of obtaining status data corresponding to each status parameter ofthe mechanical equipment within a preset time period, wherein the status parameters are preset; obtaining an intermediate prediction result according to the status data corresponding to each status parameter and a single-layer perceptron model, wherein the single-layer perceptron model is preset; predicating the remaining life of the mechanical equipment according to the intermediate prediction result and a remaining life prediction back propagation neural network model, wherein the remaining life prediction back propagation neural network model is established in advance. The device is used for executing the method. The method and device for predicting the remaining life of the mechanical equipment have the advantages that since the remaining life of the mechanical equipment is predicatedby combining the single-layer perceptron model and the back propagation neural network model, the accuracy of predicating the remaining life of the mechanical equipment is improved.

Description

Technical field [0001] The invention relates to the technical field of mechanical equipment, in particular to a method and device for predicting the remaining life of mechanical equipment. Background technique [0002] Mechanical equipment is composed of various components. During long-term operation of mechanical equipment, components will gradually wear and age, and the remaining life will gradually decrease, which will eventually lead to the shutdown of mechanical equipment or even safety accidents. Unreasonable replacement of components will cause waste Therefore, correct prediction of the remaining life of mechanical equipment is of great significance for ensuring the safe operation of mechanical equipment and improving economic benefits. [0003] In the prior art, methods for estimating the remaining life of mechanical equipment can be divided into three categories: remaining life estimation based on physical models, remaining life estimation based on knowledge models, and re...

AI Technical Summary

Problems solved by technology

However, because the collected data often have highly nonlinear characteristics, the data-driven model is usually difficult to converge, or it is easy to fall into a local optimal situation, and the obtained prediction results are not accurate enough.

Images