Health assessment method for diesel engine main bearing

Abstract

The invention discloses a health assessment method for a diesel engine main bearing, and the method comprises the steps of collecting vibration signals of the main bearing under different faults, and obtaining a visual phase trajectory diagram through phase-space reconstruction and main vector projection; building a deep convolutional neural network model; labeling various fault phase trajectory diagrams, creating a training set, and inputting the training set into the model for learning; when the cross entropy loss function is minimum, stopping iteration, and storing the diagnosis model; on the other hand, collecting vibration signals of various fault main bearings in different health states, calculating and counting the maximum Lyapunov exponent mean value, and using the maximum Lyapunov exponent mean value as a health assessment standard. During evaluation, health evaluation is carried out according to a corresponding health evaluation standard on the basis of a principle of proximity aiming at the fault type. According to the invention, on-line comprehensive monitoring of the service state of the main bearing can be realized, the maintenance mode of the main bearing can be promoted from regular replacement to condition-based maintenance, and the economic benefit can be obviously improved.

Description

technical field [0001] The invention relates to a fault diagnosis method of a diesel engine, in particular to a health assessment method of a main bearing of a diesel engine. Background technique [0002] The main bearing of a diesel engine is subjected to alternating loads during operation, resulting in uneven oil film distribution, and a thin oil film can easily induce bearing failure. Abnormal main bearing failure will seriously reduce the efficiency of the diesel engine, increase fuel consumption, and threaten the reliable service of the diesel engine. Therefore, it is particularly important to carry out fault diagnosis and health assessment on the main bearing. This will help promote condition-based maintenance of main bearings, strengthen maintenance decision-making assistance, and significantly improve economic benefits. [0003] The main bearing of a diesel engine is a rotating machine, and it will generate highly nonlinear and non-stationary state signals during o...

AI Technical Summary

Problems solved by technology

Existing fault diagnosis of diesel engine main bearings is restricted by variable working conditions and strong noise and high vibration working environments. On the premise of balancing calculation efficiency and result accuracy, only relatively rough main fault types of main bearings can be obtained. For The determination of the detailed status of the severity of the fault, the specific state of the main bearing under different fault types, etc. has not yet been resolved

Images