A Method for Reliability Characterization and State Recognition of Oil Uncertain State

Abstract

A method for reliability characterization and state identification of oil uncertain state, normalizing oil monitoring data to obtain oil index monitoring data; according to the property state of oil, it is divided into N from good to bad state level; perform fuzzy evaluation on the monitoring data of oil indicators; assign probability to the evaluation results to obtain the joint probability that an attribute belongs to each state level, and finally form a comprehensive attribute state, that is, the fuzzy membership degree; As the evidence of evidence inference ER, the uncertainty of each piece of evidence is calculated according to the weight of different attribute states, and the evidence inference ER algorithm is used to realize the reliability characterization of the oil uncertainty state; For the identification of the oil state, the invention solves the problems of difficulty in characterizing the oil state and large uncertainty of the evaluation result due to inconsistent multi-index information in the process of multi-index oil monitoring.

Description

technical field [0001] The invention belongs to the technical field of oil state monitoring, and in particular relates to a method for reliability characterization and state identification of an uncertain state of oil. Background technique [0002] The oil state is the basis for equipment health assessment. By monitoring the oil information to reflect the state of the machine, it can provide predictive judgment and forward-looking decision-making for the early failure state of the machine, and is the first line of defense to prevent the deterioration of the equipment state. However, a single indicator only reflects part of the oil information, and the comprehensive oil information cannot be represented by one or a small number of indicators. Therefore, it is of great significance to study the multi-indicator oil monitoring technology. [0003] Oil monitoring is to provide equipment status information by monitoring the continuous operation of the friction system and the compr...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the above-mentioned defects in the prior art, the object of the present invention is to provide a method for the reliability characterization and state identification of the uncertain state of the oil, obtain the reliability value of the oil state through evidence synthesis and reasoning, and pass the reliability threshold Setting and judgment of uncertainty to solve the problem that the oil state is difficult to characterize and identify during the oil monitoring process. Specifically, the oil monitoring index data is classified according to different attribute categories, and realized based on fuzzy mathematics and probability statistics methods For the fuzzy evaluation of different types of attribute states, the reliability representation of the uncertain state of oil is realized by applying the evidence reasoning (ER) method, and the state identification of oil is realized by constructing corresponding judgment standards, which solves the problem of multi-index oil monitoring. , due to the inconsistency of multi-index information, it is difficult to characterize the oil state and the uncertainty of the evaluation results is large

Images