Categorical regression mode based operating condition self-adaptive equipment health degree assessment method

Abstract

The invention discloses a categorical regression mode based operating condition self-adaptive equipment health degree assessment method. The method includes: acquiring operating state data, operatingcondition information data and design parameter data of each critical component of equipment; processing the operating state data to obtain a state characteristic database, and matching the operatingcondition information data to obtain an operating condition information database; establishing an operating condition recognition model and an operating condition self-adaptive compensation model forstate characteristic data and operating condition parameter data; on the basis of the models, sequentially performing operating condition classification and recognition and regression self-adaptive compensation processing to obtain operating condition desensitized characteristic data; calculating a health degree index of each component on the basis of the operating condition desensitized characteristic data; calculating and assessing integral equipment health degree on the basis of the health degree index of each component; predicting equipment remaining service life on the basis of the integral equipment health degree, the operating condition information data and the design parameter data. The method has advantages that effectiveness in self adaption to multi-operating-condition modes ofequipment, and accuracy in equipment health degree assessment and remaining service life prediction is improved.

Description

technical field [0001] The invention relates to the field of equipment health management and life prediction, in particular to an equipment health evaluation method based on classification and regression mode self-adaptive working conditions. Background technique [0002] In recent years, with the continuous improvement of the degree of automation in the manufacturing industry and the urgent need for flexible production, the structures, functions, tasks, and operating environments of equipment such as industrial robots have become more diverse and complex, thus affecting the stability and reliability of the equipment itself. The performance requirements are getting higher and higher. The traditional after-event maintenance and regular maintenance modes fail to effectively monitor and utilize the status information reflected by the equipment itself, and have many deficiencies in objectivity, timeliness, pertinence, and interpretability. Therefore, in the context of intellige...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of self-identification and accurate health evaluation of equipment under multiple working conditions in the prior

Images