Related Experiment Video
Updated: Aug 14, 2026
06:45
Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
Published on: October 28, 2022
Research on Vibration Signal Processing and Fault Diagnosis Algorithms for High-Pressure Quintuplex Pumps
Zewei Liu1, Yuanchen Zhu1, Zhigang Zhang1
1School of Mechanical Engineering, Sichuan University, Chengdu 610065, China.
Sensors (Basel, Switzerland)
|August 13, 2026
Summary
This study introduces VICA-DA-ViT, a novel framework for diagnosing faults in high-pressure quintuplex pumps. It enhances diagnostic accuracy by effectively handling vibration crosstalk and varying operating conditions, even with limited data.
Area of Science:
- Mechanical Engineering
- Signal Processing
- Artificial Intelligence
Background:
- High-pressure quintuplex pumps are crucial in oil and gas drilling.
- Fault diagnosis is challenging due to vibration crosstalk, operating condition variability, and limited labeled samples.
Purpose of the Study:
- To propose an integrated vibration-based diagnostic framework (VICA-DA-ViT) for robust fault diagnosis of high-pressure quintuplex pumps.
- To address challenges of inter-cylinder vibration crosstalk, operating-condition variability, and limited labeled samples.
Main Methods:
- Utilized VMD-FastICA for blind source separation to suppress crosstalk and extract discriminative vibration components.
- Applied angular-domain resampling and normalization to reduce speed-induced non-stationarity.
- Converted signals to 2D GAF-RP representations and employed a ViT-based domain-adaptive framework with domain-adversarial pretraining and sample pairing.
Main Results:
- The VICA-DA-ViT framework achieved an average cross-condition accuracy of 87.42% on a quintuplex pump dataset.
- Demonstrated superior performance compared to CD-Trans, outperforming it by 11.94% in cross-condition accuracy.
- Effectively improved the robustness of small-sample cross-condition fault diagnosis.
Conclusions:
- VICA-DA-ViT offers an effective solution for the challenging fault diagnosis of high-pressure quintuplex pumps.
- The integrated approach of signal decoupling, angular-domain alignment, and domain adaptation enhances cross-condition generalization.
- The framework shows significant potential for improving the reliability of oil and gas drilling operations.
