Diagnostic method by using vibration analysis for pump fault detection

Siano, Daniela; Panza, Maria Antonietta

doi:10.1016/j.egypro.2018.08.013

Cited by 44 publications

(21 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Rajakarunakaran et al [26] proposed a centrifugal pump fault detection using a feedforward network and a binary adaptive resonance network (ART1). Siano et al [27] proposed a method combining ANN and nonlinear regression to diagnose cavitation of time domain vibration signals. Nasiri et al [28] extracted features from the vibration signal of the centrifugal pump as the input of the neural network to detect cavitation.…”

Section: Introductionmentioning

confidence: 99%

An acoustic signal cavitation detection framework based on XGBoost with adaptive selection feature engineering

Sha,

Faber,

Gou

et al. 2022

Preprint

View full text Add to dashboard Cite

Valves are widely used in industrial and domestic pipeline systems. However, during their operation, they may suffer from the occurrence of the cavitation, which can cause loud noise, vibration and damage to the internal components of the valve. Therefore, monitoring the flow status inside valves is significantly beneficial to prevent the additional cost induced by cavitation. In this paper, a novel acoustic signal cavitation detection framework-based on XGBoost with adaptive selection feature engineering-is proposed. Firstly, a data augmentation method with non-overlapping sliding window (NOSW) is developed to solve small-sample problem involved in this study. Then, the each segmented piece of time-domain acoustic signal is transformed by fast Fourier transform (FFT) and its statistical features are extracted to be the input to the adaptive selection feature engineering (ASFE) procedure, where the adaptive feature aggregation and feature crosses are performed. Finally, with the selected features the XGBoost algorithm is trained for cavitation detection and tested on valve acoustic signal data provided by Samson AG (Frankfurt). Our method has achieved state-of-the-art results. The prediction performance on the binary classification (cavitation and no-cavitation) and the four-class classification (cavitation choked flow, constant cavitation, incipient cavitation and no-cavitation) are satisfactory and outperform the traditional XGBoost by 4.67% and 11.11% increase of the accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

An acoustic signal cavitation detection framework based on XGBoost with adaptive selection feature engineering

Sha,

Faber,

Gou

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Al-Tubi et al used genetic algorithms to adjust hidden layers of support vector machines to achieve fault diagnosis of centrifugal pumps [ 31 ]. Siano et al combined fast Fourier transform with an artificial neural network to achieve the online detection of pump cavitation [ 32 ]. For the fault diagnosis of the piston pump, Du et al built an integrated model and obtained the higher accuracy than the models for contrastive analysis.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Fault Diagnosis of Hydraulic Piston Pump Based on Wavelet Analysis and Improved AlexNet

Zhu

Wang

et al. 2021

Sensors

View full text Add to dashboard Cite

Hydraulic piston pump is the heart of hydraulic transmission system. On account of the limitations of traditional fault diagnosis in the dependence on expert experience knowledge and the extraction of fault features, it is of great meaning to explore the intelligent diagnosis methods of hydraulic piston pump. Motivated by deep learning theory, a novel intelligent fault diagnosis method for hydraulic piston pump is proposed via combining wavelet analysis with improved convolutional neural network (CNN). Compared with the classic AlexNet, the proposed method decreases the number of parameters and computational complexity by means of modifying the structure of network. The constructed model fully integrates the ability of wavelet analysis in feature extraction and the ability of CNN in deep learning. The proposed method is employed to extract the fault features from the measured vibration signals of the piston pump and realize the fault classification. The fault data are mainly from five different health states: central spring failure, sliding slipper wear, swash plate wear, loose slipper, and normal state, respectively. The results show that the proposed method can extract the characteristics of the vibration signals of the piston pump in multiple states, and effectively realize intelligent fault recognition. To further demonstrate the recognition property of the proposed model, different CNN models are used for comparisons, involving standard LeNet-5, improved 2D LeNet-5, and standard AlexNet. Compared with the models for contrastive analysis, the proposed method has the highest recognition accuracy, and the proposed model is more robust.

show abstract

“…Li et al [13] firstly developed the multivariate multiscale symbolic dynamic entropy (MvMSDE) to track the fault characteristics of a centrifugal pump from the measured synchronous multi-channel vibration signals, whose results could be selected as the input parameters of logistic regression (LR) for identification of fault types. Siano et al [14] used the artificial neural networks (ANN)-based non-linear autoregressive (NLAR) approach to predict pump system behavior, and further offer the online detection on any abnormal behavior changes caused by cavitation operations. The proposed method had high detection performance of incipient faults during pump operation.…”

Section: Introductionmentioning

confidence: 99%

Research on the Single-Value Indicators for Centrifugal Pump Based on Vibration Signals

Luo

Han

Yuan

et al. 2020

Sensors

View full text Add to dashboard Cite

Off-design operation conditions might not only seriously affect the internal flow status of a centrifugal pump, but also result in additional energy loss and potential mechanical damage. Therefore, early-stage monitoring and predication on off-design operation conditions for centrifugal pumps have become essential. Single-value indicators have favorable factors such as a smaller amount of calculation and easier identification. As a result, industries prefer the more straightforward approach: obtaining single-value indicators directly from the signals which could be easier compared with accepted standards. The possibility of applying the single-value indicators of vibration into operation condition monitoring for a centrifugal pump is studied theoretically and experimentally, which shows that the statistical features of vibration might be suitable for hydraulic instability detection for a centrifugal pump.

show abstract

Diagnostic method by using vibration analysis for pump fault detection

Cited by 44 publications

References 7 publications

An acoustic signal cavitation detection framework based on XGBoost with adaptive selection feature engineering

An acoustic signal cavitation detection framework based on XGBoost with adaptive selection feature engineering

Intelligent Fault Diagnosis of Hydraulic Piston Pump Based on Wavelet Analysis and Improved AlexNet

Research on the Single-Value Indicators for Centrifugal Pump Based on Vibration Signals

Contact Info

Product

Resources

About