A predictive health management method and device, computer-readable storage medium

Abstract

The present application discloses a predictive health management PHM method and device, and a computer-readable storage medium. The method includes: acquiring data collected by a sensor, and dividing the acquired data into multiple data blocks by time sequence windowing; Multiple divided data blocks are extracted in parallel, and the features extracted by each thread are combined by category to obtain a combined feature data set; the obtained feature data set is used for health assessment, fault diagnosis or remaining life prediction. This application divides the time series windowing processing of the data collected by the sensor into multiple data blocks, and then performs parallel feature extraction to provide a health management platform that supports parallel computing, which improves the computing speed and information analysis capabilities of the PHM system on the equipment. Effectively guarantee the safe operation of equipment.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a predictive health management method and device, and a computer-readable storage medium. Background technique [0002] Prognostic and Health Management (PHM) is to use various advanced sensors to monitor equipment operating status parameters and characteristic signals in real time, use intelligent algorithms and models to evaluate equipment health status, predict remaining service life, diagnose fault types and A system that provides a series of fault maintenance decisions. PHM technology is the product of the combination of advanced diagnosis technology, testing technology and equipment maintenance management theory. Equipment users and maintenance personnel use the fault diagnosis capability of this technology to identify fault types, so as to adopt effective maintenance methods, effectively reduce fault risks, save equipment resources, and reduce economic losses ca...

AI Technical Summary

Problems solved by technology

[0003] However, in some fields, the system structure of equipment is usually relatively complex, involving a large number of key structural parts at the part level, component level, and machine level, resulting in complex and diverse damage and failure of the equipment structure, and uncertainties in the diagnosis process. Therefore, it is necessary to monitor multiple parts of the equipment in real time to ensure the safe operation of the equipment

The equipment PHM system implemented by the existing technology is often divided into two parts: the ground PHM system and the equipment PHM system. However, the equipment signal processing and information analysis capabilities of the equipment are limited, and only have the reliable recording ability of key data and local signal processing capabilities, which is complicated. The traditional fault diagnosis and health prediction methods are implemented on the ground PHM system, so that the fault diagnosis and maintenance suggestions of the equipment cannot be provided in real time or in a timely manner, resulting in delays or delays in guaranteeing the safe operation of the equipment

Images