Shield tunneling machine cutter fault analysis and diagnosis method

Abstract

The invention discloses a shield tunneling machine cutter fault analysis and diagnosis method. The method comprises the following steps: S1, obtaining fault data of a shield tunneling machine cutter; s2, performing noise reduction processing on the acquired fault data based on empirical mode decomposition and Hilbert transform; s3, performing feature extraction and separation on the fault data after noise reduction processing based on an independent component analysis method to obtain a plurality of independent feature vectors; and S4, performing fault diagnosis on the plurality of independent feature vectors based on a pre-trained ADCS-ELM network, and outputting a fault diagnosis result. According to the invention, fault signals can be effectively extracted, and fault types can be accurately diagnosed.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis of large-scale electromechanical-hydraulic equipment, and more particularly to a method for analyzing and diagnosing the fault of a shield machine tool. Background technique [0002] For the shield machine, the hydraulic system is one of its most important core components, and it is also the main driving force for the shield machine's propulsion. When the hydraulic system fails, the shield machine needs to be shut down, which will cause huge economic losses and safety problems. Moreover, the hydraulic system is a nonlinear system, and the fault signal of the nonlinear system is often a complex signal that is non-Gaussian, non-stationary, and strongly coupled, which makes it difficult to accurately extract and identify the fault features, especially in the case of strong interference and multiple working conditions. The problem is particularly acute. [0003] At present, the failure of th...

AI Technical Summary

Problems solved by technology

When the hydraulic system fails, the shield machine needs to be shut down, which will cause huge economic losses and safety problems

Moreover, the hydraulic system is a nonlinear system, and the fault signals of the nonlinear system are often non-Gaussian, non-stationary, and strongly coupled complex signals, which makes it difficult to accurately extract and identify fault features, especially in the case of strong interference and multiple working conditions. The problem is particularly prominent

[0003] At present, the failure of the hydraulic system of the shield machine is mainly concentrated on the leakage of hydraulic components, the viscosity of the oil is too high or too low, and the failure of the solenoid valve.

Existing technologies only focus on one of fault location detection and fault severity identification, which cannot meet the requirements of intelligent diagnosis

Images