Method for evaluating healthy condition of mechanical device

Abstract

The invention discloses a method for evaluating a healthy condition of a mechanical device. State data of main components on a mechanical device are collected by a sensor; feature extraction is performed to obtain the feature parameters; noise data and fault data are extracted by using an outlier detection algorithm and only the fault dare are stored; dimension reduction processing is carried outto obtain a feature vector for final evaluation; and carrying out state evaluation of the state, a self-organizing mapping neural network model is established based on health state data and failure state data, rate impact factors of each group of to-be-evaluated data are calculated by an entropy weight theory, and the rate impact factors are introduced into a neural network to carry out health factor calculation. Therefore, comprehensive state assessment of the mechanical device is realized; the basis is provided for health maintenance of the mechanical device; and unnecessary economic lossesare avoided.

Description

technical field [0001] The invention belongs to the application field of intelligent system technology, and in particular relates to a method for evaluating the health status of mechanical equipment. Background technique [0002] At present, intelligent manufacturing has become a research hotspot in the modern manufacturing industry. Production equipment is developing towards intelligence. The workshop production process is highly complex and time-varying. Current equipment status diagnosis mostly relies on manual on-site analysis, and fault diagnosis is completed through expert experience and knowledge. . However, this diagnosis has the following problems: [0003] (1) It is difficult to form a general system diagnosis model; [0004] (2) The operating data is not fully utilized; [0005] (3) It can only guarantee that the equipment can continue to operate, but it is impossible to predict how long it can work normally, and it is impossible to predict the state of the equ...

AI Technical Summary

Problems solved by technology

[0003] (1) It is difficult to form a general system diagnosis model;

[0004] (2) The operating data is not fully utilized;

[0005] (3) It can only guarantee that the equipment can continue to operate, but it is impossible to predict how long it can work normally, and it is impossible to predict the state of the equipment in the early stage of the failure

However, the current research on state assessment lacks a method for weight decision-making

A common method is to give weights based on experience, but these weights cannot reflect the rate of change of attribute data

Images