ArticlePublisher preview available

Fault diagnosis of three-cylinder mud pump based on transfer learning

IOP Publishing
Engineering Research Express
Authors:
Chang Yan
Chang Yan
Chang Yan
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Zhiliang Liu at University of Electronic Science and Technology of China
Zhiliang Liu
Feilong Liao
Feilong Liao
Feilong Liao
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Jiyang Zhang
Jiyang Zhang
Jiyang Zhang
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Show all 5 authorsHide
Read publisher preview
Download citation
To read the full-text of this research, you can request a copy directly from the authors.

Abstract and Figures

Mud pumps serve as vital components within the circulating system of oil drilling platforms, primarily facilitating the circulation of drilling fluid. With the rapid advancement of deep learning technology, there has been a growing focus on fault diagnosis techniques for mud pumps based on deep learning methodologies. However, existing deep learning approaches often struggle with fault diagnosis of mud pumps under varying operational conditions, as adjustments to the working conditions are necessary in real-time based on drilling depth. To address this challenge, this study introduces an enhanced transfer learning method for diagnosing faults in mud pumps across different operating conditions. Initially, the collected vibration data undergoes resampling to standardize frequency, followed by the utilization of the short-term autocorrelation method to discern phase information of signal impact. Leveraging this phase information, the signal is segmented into distinct segments with uniform phases, thereby minimizing distribution discrepancies between the source and target domains. Subsequently, the transformer is employed as a feature extractor for the model. Finally, a deep sub-domain adaptation network is employed to facilitate transfer from the source domain to the target domain. Validation of the proposed method was conducted using an experimental dataset, with results demonstrating its efficacy compared to other contemporary approaches.
Figures - available from: Engineering Research Express
This content is subject to copyright. Terms and conditions apply.
A preview of this full-text is provided by IOP Publishing.
Learn more
Content available from Engineering Research Express 
This content is subject to copyright. Terms and conditions apply.
Eng. Res. Express 6(2024)025516 https://doi.org/10.1088/2631-8695/ad4004
PAPER
Fault diagnosis of three-cylinder mud pump based on transfer
learning
Chang Yan
1
, Zhiliang Liu
1
, Feilong Liao
2
, Jiyang Zhang
1
and Menghang Dai
1
1
School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, People’s Republic
of China
2
Institute of Safety and Environmental Quality Supervision and Testing, CNPC Chuanqing Drilling Engineering Company Limited,
Guanghan, People’s Republic of China
E-mail: Zhiliang_Liu@uestc.edu.cn
Keywords: mud pump, fault diagnosis, transfer learning, multiple operating conditions
Abstract
Mud pumps serve as vital components within the circulating system of oil drilling platforms, primarily
facilitating the circulation of drilling fluid. With the rapid advancement of deep learning technology,
there has been a growing focus on fault diagnosis techniques for mud pumps based on deep learning
methodologies. However, existing deep learning approaches often struggle with fault diagnosis of
mud pumps under varying operational conditions, as adjustments to the working conditions are
necessary in real-time based on drilling depth. To address this challenge, this study introduces an
enhanced transfer learning method for diagnosing faults in mud pumps across different operating
conditions. Initially, the collected vibration data undergoes resampling to standardize frequency,
followed by the utilization of the short-term autocorrelation method to discern phase information of
signal impact. Leveraging this phase information, the signal is segmented into distinct segments with
uniform phases, thereby minimizing distribution discrepancies between the source and target
domains. Subsequently, the transformer is employed as a feature extractor for the model. Finally, a
deep sub-domain adaptation network is employed to facilitate transfer from the source domain to the
target domain. Validation of the proposed method was conducted using an experimental dataset, with
results demonstrating its efficacy compared to other contemporary approaches.
1. Introduction
The mud pump is an essential equipment for ensuring the required flow rate of the circulation system during
drilling. It extracts the drilling fluid from the mud tank and injects it into the well bottom through the drill rod,
removing the debris produced during the drilling process to the surface [1]. Due to a large amount of sediment
usually present in the mud and the high-pressure condition of the mud pump, the intake valve, discharge valve,
and piston of the mud pump are prone to failure, causing leakage of fluid and reducing the pressure generated by
the mud pump, thereby affecting the normal progress of drilling work. Although mud pumps are critical rig
equipment, their health monitoring currently still relies on human observation. This approach often fails to
detect pump damage at an early stage, resulting in non-productive time (NPT)and increased well construction
costs when pumps go down unexpectedly and catastrophically [2]. Therefore, fault diagnosis is of great
significance to improve production efficiency and reduce accident rates for complex mechanical systems [3].
Fault diagnosis of critical parts of the mud pump is of great significance for oil drilling [4].
To realize accurate fault diagnosis of the mud pump, many methods have been proposed. Under the
complex drilling working conditions, it is difficult to fully describe the working environment of the drilling
pump fluid end using a single signal source for achieving high fault diagnosis accuracy. Catalin Teodoriu et al [5]
utilize sound signals to detect Mud Pumps. Gang Li et al [6]propose a dual-source gramian angular (DS-GAF)
method to fuse vibration-strain signals to provide more fault information. By using the DS-GAF method, the
vibration-strain signals at the fluid end are fused and converted into a fault diagnosis image dataset. Fault
RECEIVED
7 December 2023
REVISED
24 March 2024
ACCEPTED FOR PUBLICATION
17 April 2024
PUBLISHED
29 April 2024
© 2024 IOP Publishing Ltd
ResearchGate has not been able to resolve any citations for this publication.
Modeling and Optimization of Piston Pumps for Drilling
Article
Full-text available
  • Apr 2023
This study highlights the operational and practical advantages of using triplex mud pump systems in favor of duplex systems to optimize drilling capabilities under specific operational conditions. Additionally, the material selection of the piston subassembly was analyzed and simulated under operational parameters in SolidWorks to determine the advantages of using HNBR over NBR elastomer materials.
View
Bearing fault diagnosis using transfer learning and optimized deep belief network
Article
Full-text available
Bearing is an important component in mechanical equipment. Its main function is to support the rotating mechanical body and reduce the friction coefficient and axial load. In the actual operating environment, the bearings are affected by complex working conditions and other factors. Therefore, it is very difficult to effectively obtain data that meets the conditions of independent and identical distribution of training data and test data, which result in unsatisfactory fault diagnosis results. As a transfer learning method, joint distribution adaptive (JDA) can effectively solve the learning problem of inconsistent distribution of training data and test data. In this paper, a new bearing fault diagnosis method based on JDA and deep belief network (DBN) with improved sparrow search algorithm (CWTSSA), namely JACADN is proposed. In the JACADN, the JDA is employed to carry out feature transfer between the source domain samples and target domain samples, that is, the source domain samples and target domain samples are mapped into the same feature space by the kernel function. Then the maximum mean difference is used as the metric to reduce the joint distribution difference between the samples in the two domains. Aiming at the parameter selection of the DBN, an improved sparrow search algorithm (CWTSSA) with global optimization ability is used to optimize the parameters of the DBN in order to construct an optimized DBN model. The obtained source domain samples and target domain samples are divided into training set and test set, which are input the optimized DBN to construct a bearing fault diagnosis model for improving the diagnosis accuracy. The effectiveness of the proposed method is verified by vibration data of QPZZ-II rotating machinery. The experimental results show that the proposed JACADN method can effectively improve the fault diagnosis accuracy of rolling bearings under variable operating conditions.
View
Field Validation of Scalable Condition-Based Maintenance (CBM) of Mud Pumps
Conference Paper
  • Mar 2023
Although mud pumps are critical rig equipment, their health monitoring currently still relies on human observation. This approach often fails to detect pump damage at an early stage, resulting in non-productive time (NPT) and increased well construction cost when pumps go down unexpectedly and catastrophically. Automated approaches to condition-based maintenance (CBM) of mud pumps to date have failed due to the lack of a generalized solution applicable to any pump type and/or operating conditions. This paper presents a field-validated generally applicable solution to mud pump CBM. Field tests were conducted during drilling operations in West Texas and Japan, to verify the feasibility of the developed pump CBM solution. An accelerometer and acoustic emission (AE) sensor were attached to pump modules, and data was collected during drilling operations. Anomaly detection deep-learning (DL) models were trained during run-time to pinpoint any abnormal behavior by the pump and its elements. The models were trained only with normal state data, and a damage score characterizing the extent of damage to the mud pump was calculated to identify the earliest signs of damage. The system correctly identifies the degradation of the pump and produces alerts to notify the rig crew of the damage level of key mud pump components. During the field tests, different hyper-parameters and features were compared to identify the most effective ones for identifying damage while at the same time delivering low false positive rates (i.e., false alarms during normal state pump operation). The developed CBM system thus provides a generalized solution for pump monitoring, capable of working for different pumps and different operating conditions, and only requires several hours of normal state data with no prior pump data information. This system eliminates the environmental, health and safety (EHS) concerns that can occur during human-based observations of mud pump health, and avoids unnecessary NPT associated with catastrophic pump failures. The final version of this system is expected to be a fully self-contained magnetically attachable box containing sensors and processor, generating simple indicators for recommending pro-active pump maintenance tasks when needed. This is the first successful attempt to validate a universally applicable DL-based CBM system for mud pumps in the field. The system allows more reliable continuous and automated pump monitoring by detecting damage in real-time, thereby enabling timely and pro-active mud pump maintenance and NPT avoidance.
View
Digital twin-driven partial domain adaptation network for intelligent fault diagnosis of rolling bearing
Article
  • Feb 2023
  • RELIAB ENG SYST SAFE
Fault diagnosis of rolling bearings has attracted extensive attention in industrial fields, which plays a vital role in guaranteeing the reliability, safety, and economical efficiency of mechanical systems. Traditional data-driven fault diagnosis methods require obtaining a dataset of full failure modes in advance as the training data. However, this kind of dataset is not always available in some critical industrial scenarios, which impairs the practicability of the data-driven fault diagnosis methods for various applications. A digital twin, which establishes a virtual representation of a physical entity to mirror its operating conditions, would make fault diagnosis of rolling bearings feasible when the fault data are insufficient. In this paper, we propose a novel digital twin-driven approach for implementing fault diagnosis of rolling bearings with insufficient training data. First, a dynamics-based virtual representation of rolling bearings is built to generate simulated data. Then, a Transformer-based network is developed to learn the knowledge of the simulated data for diagnostics. Meanwhile, a selective adversarial strategy is introduced to achieve cross-domain feature alignments in scenarios where the health conditions of the measured data are unknown. To this end, this study proposes a digital twin-driven fault diagnosis framework by using labeled simulated data and unlabeled measured data. The experimental results show that the proposed method can obtain high diagnostic performance when the real-world data is unlabeled and has unknown health conditions, proving that the proposed method has significant benefits for the health management of critical rolling bearings.
View
View
Universal source-free domain adaptation method for cross-domain fault diagnosis of machines
Article
  • May 2023
  • MECH SYST SIGNAL PR
Cross-domain machinery fault diagnosis aims to transfer enriched diagnosis knowledge from a labeled source domain to a new unlabeled target domain. Most existing methods assume that the prior information on the fault modes of the target domain is known in advance. However, in engineering practice, prior knowledge of fault modes is rare in a new domain, in which there may be only partial source fault modes or some new fault modes. Furthermore, up to the present, almost all existing cross-domain fault diagnosis methods require the labeled source data during the model training process, which restricts their deployment on certain devices with limited computing resources. To this end, we propose a universal source-free domain adaptation method that can handle cross-domain fault diagnosis scenarios without access to the source data and is free of explicit assumptions about the target fault modes. More specifically, we develop a convolutional network with a Transformer as the attention module to extract discriminative feature information from the source data and then send the model and parameters to the target domain. In target domain training, we first propose a supervised contrastive learning strategy based on source class prototypes, which utilizes high-confident predictions to achieve source-free domain alignment and class alignment. Then, we also introduce a threshold-based entropy max-min loss to further align known class samples in the target domain or reject target outlier samples as an unknown class. Furthermore, we introduce self-supervised learning to further learn feature representations of the target domain to reduce the previous misclassification. A series of experiments on two rotating machine datasets demonstrate the effectiveness and practicability of the proposed method.
View
Transfer learning network for nuclear power plant fault diagnosis with unlabeled data under varying operating conditions
Article
  • May 2022
  • ENERGY
The performance of data-driven nuclear power plant fault diagnosis models trained by limited data cannot be guaranteed, the distribution discrepancy between training set (source domain) and test set (target domain) caused by varying operating conditions will seriously restrict their practical applications. To generalize the diagnostic knowledge learnt from labeled source domain to unlabeled target domain, a novel transfer learning method based on Maximum Mean Discrepancy (MMD) and Convolutional Neural Network (CNN) is proposed, which can reduce the domain discrepancy of the extracted features between source domain and target domain, by appending the MMD-based distribution discrepancy to the objective function of CNN. Numerical experiments with high-dimensional and strong-nonlinear complex nuclear power plant simulation data are conducted, results show that significant improvement in the diagnostic accuracy of target domain can be achieved on most transfer tasks. Besides, the influence of adopting different kernel functions (Linear kernel, Sigmoid kernel, Laplace kernel and Gaussian kernel) to calculate MMD is also studied, better transfer effect can be achieved when Gaussian kernel is used, including higher accuracy, faster convergence rate and less negative transfer. Overall, the proposed method is promising to expand the application scope of nuclear power plant intelligent fault diagnosis to varying operating conditions.
View
Passive Thermography Based Bearing Fault Diagnosis Using Transfer Learning With Varying Working Conditions
Article
  • Jan 2022
Bearing is one of the core components of any rotating machine, and its failure is widespread. This reason drives continuous monitoring and detecting bearing faults during machine operation to warn operators and prevent unforeseen damage. This paper proposes an intelligent Passive Thermography (PTG) based fault diagnosis technique for detection of bearing faults using Convolutional Neural Network (CNN) with Transfer Learning (TL) under varying working conditions. The validation of the proposed method has been done on three different datasets; bearing test rig dataset has been taken as a source domain data while Induction Motor (IM), and Machine Fault Simulator (MFS) datasets have been taken as target domain data. The proposed method enables and speeds up the training process of CNN towards accurate adaptation for fault diagnosis approach in the escalated time frame. The experimental results demonstrated that the suggested approach could successfully learn transferable characteristics from the source domain model, which can cope with the issue of limited availability of training data required for the target domain. The classification accuracy on the target domain dataset were varied in the range of 89 -95.4 % in the case of the IM dataset and 96.5-97.5% in the case of the MFS dataset. Moreover, it shows the benefits of the suggested method, which may be utilized as an effective non-invasive diagnostic tool for rotating machines to avoid unexpected system shutdowns.
View
A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: Theories, applications and challenges
Article
  • Mar 2022
  • MECH SYST SIGNAL PR
Deep Transfer Learning (DTL) is a new paradigm of machine learning, which can not only leverage the advantages of Deep Learning (DL) in feature representation, but also benefit from the superiority of Transfer Learning (TL) in knowledge transfer. As a result, DTL techniques can make DL-based fault diagnosis methods more reliable, robust and applicable, and they have been widely developed and investigated in the field of Intelligent Fault Diagnosis (IFD). Although several systematic and valuable review articles have been published on the topic of IFD, they summarized relevant research only from an algorithm perspective and overlooked practical applications in industry scenarios. Furthermore, a comprehensive review on DTL-based IFD methods is still lacking. From this insight, it is particularly important and more necessary to comprehensively survey the relevant publications of DTL-based IFD, which will help readers to conveniently understand the current state-of-the-art techniques and to quickly design an effective solution for solving IFD problems in practice. First, theoretical backgrounds of DTL are briefly introduced to present how the transfer learning techniques can be integrated with deep learning models. Then, major applications of DTL and their recent developments in the field of IFD are detailed and discussed. More importantly, suggestions on how to select DTL algorithms in practical applications, and some future challenges are shared. Finally, conclusions of this survey are given. At last, we have reason to believe that the works done in this article can provide convenience and inspiration for the researchers who want to devote their efforts in the progress and advance of IFD.
View
A systematic review of deep transfer learning for machinery fault diagnosis
Article
  • May 2020
  • NEUROCOMPUTING
With the popularization of the intelligent manufacturing, much attention has been paid in such intelligent computing methods as deep learning ones for machinery fault diagnosis. Thanks to the development of deep learning models, the interference of the human experience can be greatly reduced, and the fault diagnosis accuracy can also be increased under certain conditions. To improve the generalization ability of the intelligent fault diagnostics, the deep transfer learning consisting of both transfer learning and deep learning components was accordingly developed. This paper reviews the research progress of the deep transfer learning for the machinery fault diagnosis in recently years. It is summarizing, classifying and explaining many publications on this topic with discussing various deep transfer architectures and related theories. On this basis, this review expounds main achievements, challenges and future research of the deep transfer learning. This provides clear directions for the selection, design or implementation of the deep transfer learning architecture in the field of the machinery fault diagnostics.
View