Adversarial Fault Detector Guided by One-Class Learning for a Multistage Centrifugal Pump

Cabrera, Diego; Villacís, Mauricio Leonardo; Cerrada, Mariela; Sánchez, René–Vinicio; Li, Chuan; Sancho, Fernando; Long, Jianyu; Estupinan, Edgar Alberto

doi:10.1109/tmech.2022.3226347

Cited by 6 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GFs in the spectrum show an imbalance, which is an important feature for identifying IDs in the CP. The GFs can be calculated using Equation (6).…”

Section: Comparison Of the Proposed Cpfi With Traditional Featuresmentioning

confidence: 99%

See 1 more Smart Citation

A Technique for Centrifugal Pump Fault Detection and Identification Based on a Novel Fault-Specific Mann–Whitney Test

Ahmad,

Kim,

Kim

2023

Sensors

View full text Add to dashboard Cite

This work presents a technique for fault detection and identification in centrifugal pumps (CPs) using a novel fault-specific Mann–Whitney test (FSU Test) and K-nearest neighbor (KNN) classification algorithm. Traditional fault indicators, such as the mean, peak, root mean square, and impulse factor, lack sensitivity in detecting incipient faults. Furthermore, for defect identification, supervised models rely on pre-existing knowledge about pump defects for training purposes. To address these concerns, a new centrifugal pump fault indicator (CPFI) that does not rely on previous knowledge is developed based on a novel fault-specific Mann–Whitney test. The new fault indicator is obtained by decomposing the vibration signature (VS) of the centrifugal pump hierarchically into its respective time-frequency representation using the wavelet packet transform (WPT) in the first step. The node containing the fault-specific frequency band is selected, and the Mann–Whitney test statistic is calculated from it. The combination of hierarchical decomposition of the vibration signal for fault-specific frequency band selection and the Mann–Whitney test form the new fault-specific Mann–Whitney test. The test output statistic yields the centrifugal pump fault indicator, which shows sensitivity toward the health condition of the centrifugal pump. This indicator changes according to the working conditions of the centrifugal pump. To further enhance fault detection, a new effect ratio (ER) is introduced. The KNN algorithm is employed to classify the fault type, resulting in promising improvements in fault classification accuracy, particularly under variable operating conditions.

show abstract

“…The GFs in the spectrum show an imbalance, which is an important feature for identifying IDs in the CP. The GFs can be calculated using Equation (6).…”

Section: Comparison Of the Proposed Cpfi With Traditional Featuresmentioning

confidence: 99%

“…In contrast, SFs in the CP progressively affect the operating efficiency. These defects can be very dangerous, as they may not be noticed by humans [6]. Therefore, the development of a technique based on artificial intelligence (AI) for early detection and identification of SFs could be very advantageous.…”

Section: Introductionmentioning

confidence: 99%

A Technique for Centrifugal Pump Fault Detection and Identification Based on a Novel Fault-Specific Mann–Whitney Test

Ahmad,

Kim,

Kim

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Another method by Ahmad et al [27] for diagnosing faults in multistage centrifugal pumps (MCPs) involved using informative ratio principal component analysis (Ir-PCA) on features from the vibration signal's fault-specific frequency band, which was then classified using the KNN algorithm. Cabrera et al [28] developed an innovative fault detection model, designed for cyclo-stationary machines with limited data, and initially employed an unsupervised generative adversarial network (GAN) to model vibration signals. Siddique et al developed a novel hybrid technique that merges the STFT and CWT scalograms, aiming to advance the detection of leaks in pipeline systems [29].…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis in Centrifugal Pumps: A Dual-Scalogram Approach with Convolution Autoencoder and Artificial Neural Network

Zaman,

Ahmad,

Kim

2024

Sensors

View full text Add to dashboard Cite

This paper proposes a new fault diagnosis method for centrifugal pumps by combining signal processing with deep learning techniques. Centrifugal pumps facilitate fluid transport through the energy generated by the impeller. Throughout the operation, variations in the fluid pressure at the pump’s inlet may impact the generalization of traditional machine learning models trained on raw statistical features. To address this concern, first, vibration signals are collected from centrifugal pumps, followed by the application of a lowpass filter to isolate frequencies indicative of faults. These signals are then subjected to a continuous wavelet transform and Stockwell transform, generating two distinct time–frequency scalograms. The Sobel filter is employed to further highlight essential features within these scalograms. For feature extraction, this approach employs two parallel convolutional autoencoders, each tailored for a specific scalogram type. Subsequently, extracted features are merged into a unified feature pool, which forms the basis for training a two-layer artificial neural network, with the aim of achieving accurate fault classification. The proposed method is validated using three distinct datasets obtained from the centrifugal pump under varying inlet fluid pressures. The results demonstrate classification accuracies of 100%, 99.2%, and 98.8% for each dataset, surpassing the accuracies achieved by the reference comparison methods.

show abstract

A self-supervised leak detection method for natural gas gathering pipelines considering unlabeled multi-class non-leak data

Zuo,

Zhang,

et al. 2024

Computers in Industry

View full text Add to dashboard Cite

Adversarial Fault Detector Guided by One-Class Learning for a Multistage Centrifugal Pump

Cited by 6 publications

References 29 publications

A Technique for Centrifugal Pump Fault Detection and Identification Based on a Novel Fault-Specific Mann–Whitney Test

A Technique for Centrifugal Pump Fault Detection and Identification Based on a Novel Fault-Specific Mann–Whitney Test

Fault Diagnosis in Centrifugal Pumps: A Dual-Scalogram Approach with Convolution Autoencoder and Artificial Neural Network

A self-supervised leak detection method for natural gas gathering pipelines considering unlabeled multi-class non-leak data

Contact Info

Product

Resources

About