Author(s)

Fan Zhang, XiuLi Wang^*

Affiliation(s)

Research Center of Fluid Machinery Engineering and Technology, Jiangsu University, Zhenjiang 212013, Jiangsu, China.

Corresponding Author

XiuLi Wang

ABSTRACT

As one of the most critical power devices in industrial systems, the operational status of centrifugal pumps directly affects system safety, reliability, and economic efficiency. To address the limitations of traditional diagnostic methods—such as reliance on manual feature extraction and poor generalization—this paper provides a comprehensive review of recent advances in deep learning-based fault diagnosis and intelligent operation and maintenance (O&M) of centrifugal pumps. It first outlines the theoretical foundations and representative deep learning models, including convolutional neural networks (CNN), recurrent neural networks (RNN/LSTM/GRU), residual networks (ResNet), graph neural networks (GCN), and Transformers, and discusses their applications in cross-condition diagnosis, remaining useful life (RUL) prediction, and intelligent O&M. Furthermore, it summarizes the progress in key enabling technologies such as multi-sensor data fusion, transfer learning, self-supervised and meta-learning, physics-informed feature alignment, and digital twins, which significantly enhance diagnostic accuracy, robustness, and generalization. Studies indicate that deep learning-based approaches outperform traditional methods in automatic feature extraction, domain adaptation, and decision optimization, thus enabling the shift from passive monitoring to proactive maintenance. Nevertheless, challenges remain regarding data scarcity and labeling difficulty, limited model interpretability and generalization, and real-time computational constraints. Future research directions include: developing few-shot and self-supervised learning to alleviate data dependency; integrating physical knowledge with deep learning to improve interpretability and trustworthiness; designing lightweight models suitable for edge deployment; and advancing digital twin-driven lifecycle management and predictive maintenance. This review provides a systematic reference and future outlook for research and industrial applications of intelligent fault diagnosis and maintenance of centrifugal pumps.

KEYWORDS

Deep learning; Centrifugal pump fault diagnosis; Transfer learning; Multi-source data fusion; Intelligent operation and maintenance; Digital twin

CITE THIS PAPER

Fan Zhang, XiuLi Wang. Deep learning-based fault diagnosis and intelligent operation of centrifugal pumps: models, challenges, and perspectives. Journal of Manufacturing Science and Mechanical Engineering. 2025, 3(1): 37-52. DOI: https://doi.org/10.61784/msme3019.

REFERENCES

[1] Guo J, Wan J L, Yang Y, et al. A deep feature learning method for remaining useful life prediction of drilling pumps. Energy, 2023, 282: 128442.

[2] Nan L, Wang Y, Chen D, et al. A novel energy performance prediction approach towards parametric modeling of a centrifugal pump in the design process. Water, 2023, 15(10): 1951.

[3] Siddique M F, Ullah S, Kim J M. A deep learning approach for fault diagnosis in centrifugal pumps through wavelet coherent analysis and S-transform scalograms with CNN-KAN. Computers, Materials & Continua, 2025, 84(2).

[4] Zaman W, Ahmad Z, Kim J M. Fault diagnosis in centrifugal pumps: A dual-scalogram approach with convolution autoencoder and artificial neural network. Sensors, 2024, 24(3): 851.

[5] Yan C, Liu Z, Liao F, et al. Fault diagnosis of three-cylinder mud pump based on transfer learning. Engineering Research Express, 2024, 6(2): 025516.

[6] Zheng J, Liao J, Zhu Y. Two-stage multi-channel fault detection and remaining useful life prediction model of internal gear pumps based on Robust-ResNet. Sensors, 2023, 23(5): 2395.

[7] Alguliyev R, Imamverdiyev Y, Sukhostat L. Intelligent diagnosis of petroleum equipment faults using a deep hybrid model. SN Applied Sciences, 2020, 2(5): 924.

[8] Kumar D, Dewangan A, Tiwari R, et al. Identification of inlet pipe blockage level in centrifugal pump over a range of speeds by deep learning algorithm using multi-source data. Measurement, 2021, 186: 110146.

[9] Li J, Shao J, Wang W, et al. An evolutional deep learning method based on multi-feature fusion for fault diagnosis in sucker rod pumping system. Alexandria Engineering Journal, 2023, 66: 343-355.

[10] Akpudo U E, Hur J W. A CEEMDAN-assisted deep learning model for the RUL estimation of solenoid pumps. Electronics, 2021, 10(17): 2054.

[11] Ding Y, Ma L, Ma J, et al. Intelligent fault diagnosis for rotating machinery using deep Q-network based health state classification: A deep reinforcement learning approach. Advanced Engineering Informatics, 2019, 42: 100977.

[12] Li X, Xie L, Deng B, et al. Deep dynamic high-order graph convolutional network for wear fault diagnosis of hydrodynamic mechanical seal. Reliability Engineering & System Safety, 2024, 247: 110117.

[13] Manikandan S, Duraivelu K. Vibration-based fault diagnosis of broken impeller and mechanical seal failure in industrial mono-block centrifugal pumps using deep convolutional neural network. Journal of Vibration Engineering & Technologies, 2023, 11(1): 141-152.

[14] Zhang F, Li Y, Shan D, et al. An improved fault diagnosis approach for pumps based on neural networks with improved adaptive activation function. Processes, 2023, 11(9): 2540.

[15] Kumar A, Gandhi C P, Zhou Y, et al. Improved deep convolution neural network (CNN) for the identification of defects in the centrifugal pump using acoustic images. Applied Acoustics, 2020, 167: 107399.

[16] Khalid S, Jo S H, Shah S Y, et al. Artificial intelligence-driven prognostics and health management for centrifugal pumps: A comprehensive review. Actuators, 2024, 13(12): 514.

[17] Lu J, Zhou Y, Ge Y, et al. Research into prediction method for pressure pulsations in a centrifugal pump based on variational mode decomposition–particle swarm optimization and hybrid deep learning models. Sensors, 2024, 24(13): 4196.

[18] Guo J, Yang Y, Li H, et al. A parallel deep neural network for intelligent fault diagnosis of drilling pumps. Engineering Applications of Artificial Intelligence, 2024, 133: 108071.

[19] Singh V, Gangsar P, Porwal R, et al. Artificial intelligence application in fault diagnostics of rotating industrial machines: A state-of-the-art review. Journal of Intelligent Manufacturing, 2023, 34(3): 931-960.

[20] Xu W, Wang Z, Zhou Z, et al. Wear state assessment of external gear pump based on system-level hybrid digital twin. Mechanical Systems and Signal Processing, 2024, 209: 111123.

[21] Klingebiel J, Salamon M, Bogdanov P, et al. Towards maximum efficiency in heat pump operation: Self-optimizing defrost initiation control using deep reinforcement learning. Energy and Buildings, 2023, 297: 113397.

[22] Bang J, Di Marco P, Shin H, et al. Deep transfer learning-based fault diagnosis using wavelet transform for limited data. Applied Sciences, 2022, 12(15): 7450.

[23] Hasan M J, Rai A, Ahmad Z, et al. A fault diagnosis framework for centrifugal pumps by scalogram-based imaging and deep learning. IEEE Access, 2021, 9: 58052-58066.

[24] Prasshanth C V, Venkatesh S N, Mahanta T K, et al. Deep learning for fault diagnosis of monoblock centrifugal pumps: A Hilbert–Huang transform approach. International Journal of System Assurance Engineering and Management, 2024: 1-14.

[25] Wei Y, Liu H, Wei M, et al. A fault diagnosis method for dry vacuum pump bearing based on finite element simulation with deep transfer learning. IEEE Access, 2025.

[26] Bie F, Du T, Lyu F, et al. An integrated approach based on improved CEEMDAN and LSTM deep learning neural network for fault diagnosis of reciprocating pump. IEEE Access, 2021, 9: 23301-23310.

[27] Dai M, Liu Z, Wang J, et al. Physics-driven feature alignment combined with dynamic distribution adaptation for three-cylinder drilling pump cross-speed fault diagnosis. Reliability Engineering & System Safety, 2024, 251: 110369.

[28] Wu Y, Feng Z, Liang J, et al. Fault diagnosis algorithm of beam pumping unit based on transfer learning and DenseNet model. Applied Sciences, 2022, 12(21): 11091.

[29] Li C, Liu X, Wang H, et al. Fault diagnosis method for centrifugal pumps in nuclear power plants based on a multi-scale convolutional self-attention network. Sensors, 2025, 25(5): 1589.

[30] He R, Dai Y, Lu J, et al. Developing ladder network for intelligent evaluation system: Case of remaining useful life prediction for centrifugal pumps. Reliability Engineering & System Safety, 2018, 180: 385-393.

[31] Song Y, Zhang T, Liu Q, et al. Cavitation identification method of centrifugal pumps based on signal demodulation and EfficientNet. Arabian Journal for Science and Engineering, 2025, 50(12): 8779-8793.

[32] Liu Z, Xiao H, Zhang T, et al. A fault diagnosis framework for waterjet propulsion pump based on supervised autoencoder and large language model. Machines, 2025, 13(8): 698.

[33] Gong F, Tong S, Du C, et al. A fault diagnosis model of an electric submersible pump based on mechanism knowledge. Sensors, 2025, 25(8): 2444.

[34] Zhu H, Yu H, Sun Q, et al. Deep learning-based performance prediction of electric submersible pumps under viscous and gas–liquid flow conditions. Machines, 2025, 13(2): 135.

[35] Ahmad S, Ahmad Z, Kim J M, et al. A centrifugal pump fault diagnosis framework based on supervised contrastive learning. Sensors, 2022, 22(17): 6448.

[36] Xia M, Shao H, Williams D, et al. Intelligent fault diagnosis of machinery using digital twin-assisted deep transfer learning. Reliability Engineering & System Safety, 2021, 215: 107938.

[37] Gong F, Tong S, Du C, et al. Named entity recognition in the field of small sample electric submersible pump based on FLAT. Applied Sciences, 2025, 15(5).

[38] Ullah N, Ahmad Z, Siddique M F, et al. An intelligent framework for fault diagnosis of centrifugal pump leveraging wavelet coherence analysis and deep learning. Sensors, 2023, 23(21): 8850.

[39] Meng F, Shi Z, Song Y, et al. The DMF: fault diagnosis of diaphragm pumps based on deep learning and multi-source information fusion. Processes, 2024, 12(3): 468.

[40] Tang S, Yuan S, Zhu Y, et al. Deep learning-based intelligent fault diagnosis methods toward rotating machinery. IEEE Access, 2019, 8: 9335-9346.

[41] Dave G S, Pandhare A P, Kulkarni A P, et al. Innovative data techniques for centrifugal pump optimization with machine learning and AI model. PLOS One, 2025, 20(6): e0325952.

[42] Chennai Viswanathan P, Venkatesh S N, Dhanasekaran S, et al. Deep learning for enhanced fault diagnosis of monoblock centrifugal pumps: spectrogram-based analysis. Machines, 2023, 11(9): 874.

[43] Prosvirin A E, Ahmad Z, Kim J M, et al. Global and local feature extraction using a convolutional autoencoder and neural networks for diagnosing centrifugal pump mechanical faults. IEEE Access, 2021, 9: 65838-65854.

[44] Wei J, Gao X, et al. Fault diagnosis of sucker rod pump based on deep-broad learning using motor data. IEEE Access, 2020, 8: 222562-222571.

[45] Konieczny J, Latas W, Stojek J, et al. Classification of wear state for a positive displacement pump using deep machine learning. Energies, 2023, 16(3): 1408.

[46] Medina R, Sánchez R V, Cabrera D, et al. Scale-fractal detrended fluctuation analysis for fault diagnosis of a centrifugal pump and a reciprocating compressor. Sensors, 2024, 24(2).