An equipment health state assessment and prediction method based on industrial big data

A health status and prediction method technology, applied in data processing applications, electrical digital data processing, digital data information retrieval, etc., to achieve the effect of scientific health status

CN109886430APending Publication Date: 2019-06-14TONGJI UNIV
8 Cites 18 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2019-06-14

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to an equipment health state assessment and prediction method based on industrial big data. The method comprises the following steps of S1, extracting sample data capable of representing the whole degradation process of equipment from an equipment state monitoring system; S2, performing effective preprocessing on the sample data; S3, constructing a distributed support vectordata description model based on the Spark platform, and extracting a normal sample set; S4, measuring the deviation degree of the current sample through the Euclidean distance, further converting thedeviation degree into a health degree value, and drawing a health degree curve; S5, constructing an equipment health degree single-step prediction model based on the Spark platform; and S6, further expanding the single-step prediction method of the equipment into multi-step prediction. Compared with the prior art, the invention relates to the equipment health assessment and prediction method, objectively and accurately assesses the health state of the monitored equipment, predicts the future degradation trend of the equipment, and provides a theoretical basis for the fault management and maintenance work of the subsequent equipment.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of equipment health management, in particular to a method for evaluating and predicting equipment health status based on industrial big data. Background technique

[0002] The performance of equipment will slowly decline with the increase of service time. Effectively evaluating and predicting the health status of equipment is of great significance for preventing failures and improving equipment reliability. Equipment health status evaluation refers to the health degree to describe the overall operation of the equipment, which is a comprehensive evaluation of the equipment operation status. Equipment health status prediction refers to mining the internal evolution law of equipment health to realize the advanced prediction of equipment health, which is convenient for equipment maintenance and management.

[0003] The equipment health assessment method commonly used in the industrial field is the health assess...

Examples

Embodiment

[0061] A method for evaluating and predicting equipment health status based on industrial big data described in this example, its calculation process is as follows figure 1 and image 3 , mainly including the following parts:

[0062] S1. First select several sets of relatively complete run-to-failure life cycle data from the equipment status data set, and select characteristic parameters that can represent the degradation state of the equipment and can be continuously monitored and recorded as the degradation variables of the equipment. Different types of industrial equipment can choose their own parameters to be monitored, mainly including speed, flow rate, pressure, temperature, power, current, etc.

[0063] S2. Perform effective data preprocessing for data-related degenerate variables, including normalization and feature reduction based on principal component analysis, and eliminate redundant variables in sample data;

[0064] Among them, the normalization adopts the max...