Robust Fault Diagnosis for Drilling Machinery in Challenging Environments

To address the challenge of fault diagnosis in drilling machinery under complex working conditions, this paper proposes an anti-interference fault diagnosis model for drilling machinery named WTCA-BI. The model integrates the Wavelet Transform and Convolutional Autoencoder, combining them with the B...

Full description

Saved in:
Bibliographic Details
Main Authors: Cai, Jijing, Wang, Lina, Wen, Zhihao, Yang, Zijia, Wen, Long, Yuan, Junchao, Deng, Jiangtao, Fang, Kai
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Anti-Interference
BILSTM
Drilling
Drilling machines
Employee welfare
Fault diagnosis
Image reconstruction
Machinery
Noise
Time-frequency analysis
Wavelet transforms
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To address the challenge of fault diagnosis in drilling machinery under complex working conditions, this paper proposes an anti-interference fault diagnosis model for drilling machinery named WTCA-BI. The model integrates the Wavelet Transform and Convolutional Autoencoder, combining them with the Bidirectional Long Short-Term Memory (BILSTM). The Wavelet Transform converts the pressure time series containing fault information into time-frequency images, which helps in detecting fault frequency components. The Convolutional Autoencoder effectively reconstructs the critical features of the input by minimizing the difference between the input image and the reconstructed image from the decoder; these features are crucial for distinguishing between normal and faulty states. The combined use of the BILSTM network enables the diagnosis of faults in complex operational environments. The effectiveness of this model is validated through experiments with varying noise intensities. When subjected to a noise intensity of 0.9, the WTCABI model demonstrated an improvement in accuracy of 10.7% in comparison to existing fault diagnosis models.
ISSN:2770-2677
DOI:10.1109/SmartIoT62235.2024.00083