A Centrifugal Pump Fault Diagnosis Framework Based on Supervised Contrastive Learning

Ahmad, Sajjad; Ahmad, Zahoor; Kim, Jong‐Myon

doi:10.3390/s22176448

Cited by 15 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, fault diagnosis in other fields also has referential significance, such as high-speed trains [12][13][14][15] and centrifugal pumps. Ahmad S et al [16] extracted fault-related discriminant features from kurtogram images. Ullah N et al [17] proposed a fault diagnosis framework based on wavelet coherence analysis and deep learning.…”

Section: Introductionmentioning

confidence: 99%

Method for Fault Diagnosis of Track Circuits Based on a Time–Frequency Intelligent Network

Peng,

Liu

2024

Electronics

View full text Add to dashboard Cite

In response to the limitations posed by noise interference in complex environments and the narrow focus of existing diagnosis methods for jointless track circuit faults, an innovative approach is put forward in this study. It involves the application of the continuous wavelet transform (CWT) for signal preprocessing, along with the integration of a deep belief network (DBN) and a genetic algorithm (GA) to improve the least-squares support vector machine (LSSVM) model for intelligent time–frequency fault diagnosis. Initially, the raw induced voltage signals are transformed using continuous wavelet transformation resulting in wavelet time–frequency representations that combine temporal and spectral information. Subsequently, these time–frequency representations are fed into the deep belief networks, which perform semi-supervised dimensionality reduction and feature extraction, thereby uncovering distinct fault characteristics in the track circuit. Finally, the genetic algorithms are employed to improve the kernel function and penalty factor parameters of the least-squares support vector machine, thus establishing an optimal DBN-GA-LSSVM diagnostic model. Experimental validation demonstrates the effectiveness of the proposed time–frequency intelligent network model by leveraging the advantages of deep belief networks in hierarchical feature extraction and the superior performance of the least-squares support vector machine in addressing high-dimensional pattern recognition problems with limited samples. The achieved accuracy rate on the testing dataset reaches an impressive 99.6%. Consequently, this comprehensive approach provides a viable solution for data-driven track circuit fault diagnosis.

show abstract

Section: Introductionmentioning

confidence: 99%

Method for Fault Diagnosis of Track Circuits Based on a Time–Frequency Intelligent Network

Peng,

Liu

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Ahmad et al [32] introduced a three-phase technique involving the Walsh Transform, raw statistical features, and cosine linear discriminant analysis (CLDA) for fault classification in CP vibration signatures. Sajjad et al [33] proposed a technique for fault classification in CP that involves computing kurtogram spectra, utilizing a convolution encoder, and implementing a linear classifier for fault visualization and classification. Kuang et al [34] identified the vibration source in mechanical specimens using wavelet coherence and Fourier coherence.…”

Section: Introductionmentioning

confidence: 99%

An Intelligent Framework for Fault Diagnosis of Centrifugal Pump Leveraging Wavelet Coherence Analysis and Deep Learning

Ullah,

Ahmad,

Siddique

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

This paper proposes an intelligent framework for the fault diagnosis of centrifugal pumps (CPs) based on wavelet coherence analysis (WCA) and deep learning (DL). The fault-related impulses in the CP vibration signal are often attenuated due to the background interference noises, thus affecting the sensitivity of the traditional statistical features towards faults. Furthermore, extracting health-sensitive information from the vibration signal needs human expertise and background knowledge. To extract CP health-sensitive features autonomously from the vibration signals, the proposed approach initially selects a healthy baseline signal. The wavelet coherence analysis is then computed between the healthy baseline signal and the signal obtained from a CP under different operating conditions, yielding coherograms. WCA is a signal processing technique that is used to measure the degree of linear correlation between two signals as a function of frequency. The coherograms carry information about the CP vulnerability towards the faults as the color intensity in the coherograms changes according to the change in CP health conditions. To utilize the changes in the coherograms due to the health conditions of the CP, they are provided to a Convolution Neural Network (CNN) and a Convolution Autoencoder (CAE) for the extraction of discriminant CP health-sensitive information autonomously. The CAE extracts global variations from the coherograms, and the CNN extracts local variations related to CP health. This information is combined into a single latent space vector. To identify the health conditions of the CP, the latent space vector is classified using an Artificial Neural Network (ANN). The proposed method identifies faults in the CP with higher accuracy as compared to already existing methods when it is tested on the vibration signals acquired from real-world industrial CPs.

show abstract

“…Current studies have been able to obtain speed fluctuation information in the frequency domain, time-frequency domain, or angle domain, but it is difficult to recover the time-domain waveform features of an IASF, which can effectively correspond to the angle to reveal the health status and fault evolution laws of components [22]. Yu et al [23] proposed a synchronous extraction transform (SET).…”

Section: Introductionmentioning

confidence: 99%

A Hydraulic Axial Piston Pump Fault Diagnosis Based on Instantaneous Angular Speed under Non-Stationary Conditions

Liu,

Meng,

Zhou

et al. 2023

Lubricants

View full text Add to dashboard Cite

Due to the intense noise interference in hydraulic systems, it is extremely difficult to detect component faults through vibration signals. Diagnostic performance is also constrained by highly time-varying and non-stationary operating conditions. This study proposes to use instantaneous angular speed (IAS) signals that are both operational and state parameters as sources of information. Firstly, the instantaneous angular speed fluctuation (IASF) of a piston pump is analyzed theoretically, and it is concluded that its fluctuating components contain the health status information of the components. The IASF can then be obtained by subtracting the speed trend term from IAS signals obtained via a magneto-electric speed sensor. A synchro-extraction of the normal S transform (SNST) is proposed to process it via line-pass filtering. Finally, the filtered and reconstructed IASF signal is utilized to draw a two-dimensional polar coordinate map online. A non-stationary-condition test is carried out on the test platform to monitor the morphological characteristics of the valve plate under normal, slight, and severe wear conditions. The polar plot shows significant increases in speed fluctuations and oscillation times within a range from 180° to 270°. The relevant research results reflect that the IAS signal can provide a new method for monitoring the operating status of and conducting fault diagnoses for hydraulic equipment.

show abstract

A Centrifugal Pump Fault Diagnosis Framework Based on Supervised Contrastive Learning

Cited by 15 publications

References 31 publications

Method for Fault Diagnosis of Track Circuits Based on a Time–Frequency Intelligent Network

Method for Fault Diagnosis of Track Circuits Based on a Time–Frequency Intelligent Network

An Intelligent Framework for Fault Diagnosis of Centrifugal Pump Leveraging Wavelet Coherence Analysis and Deep Learning

A Hydraulic Axial Piston Pump Fault Diagnosis Based on Instantaneous Angular Speed under Non-Stationary Conditions

Contact Info

Product

Resources

About