Research on fault diagnosis of extracorporeal membrane oxygenation devices based on convolutional neural network and Chebyshev graph convolutional neural network_Journal of Biomedical Engineering

Authors：

XIA Kemiao ,  LIU Qinming , YE Chunming , WANG Yujie

School of Management, University of Shanghai for Science and Technology, Shanghai 200093, P. R. China;

Corresponding?author：

LIU Qinming, Email: lqm0531@163.com

Keywords：

Fault diagnosis; Convolutional neural network; Graph neural network; Multi-task learning; Extracorporeal membrane oxygenation

DOI：

10.7507/1001-5515.202506061

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

To address the issues of information imbalance and the difficulty in synergistically extracting global and local features during extracorporeal membrane oxygenation (ECMO) fault diagnosis, this paper proposes a model integrating Chebyshev graph convolutional neural networks (ChebyNet) with convolutional neural networks (CNN) (CNN-ChebyNet). This model is applied to ECMO fault diagnosis tasks to efficiently enhance feature extraction accuracy. Firstly, a graph symmetry processing mechanism is introduced into the ChebyNet framework to improve the balance of information flow between nodes. Secondly, by combining ChebyNet’s global modeling capability with CNN’s local temporal feature extraction ability, multidimensional representation of complex fault features is achieved. Finally, through multi-task learning node reconstruction and classification tasks, the perception of latent correlations among samples is enhanced. Experiments on the ECMO blood pump impeller assembly dataset demonstrate that the CNN-ChebyNet model achieves superior performance across multiple comparison methods, with an average diagnostic accuracy exceeding 99%, showcasing outstanding diagnostic capability and stability. Furthermore, ablation experiments validate the effectiveness of each model component in multi-fault identification. In summary, this study provides an effective and feasible technical solution for fault diagnosis in ECMO devices.

Citation： XIA Kemiao, LIU Qinming, YE Chunming, WANG Yujie. Research on fault diagnosis of extracorporeal membrane oxygenation devices based on convolutional neural network and Chebyshev graph convolutional neural network. Journal of Biomedical Engineering, 2026, 43(1): 170-177. doi: 10.7507/1001-5515.202506061 Copy

1.	陳艷, 王琪, 蔣佳旺. 基于數據挖掘技術的醫療設備故障監測與識別方法的探討與研究. 中國醫療設備, 2020, 35(8): 56-59.
2.	Wei Y, Liu H, Chen G, et al. Fault diagnosis of marine turbocharger system based on an unsupervised algorithm. Journal of Electrical Engineering & Technology, 2020, 15: 1331-1343.
3.	Yang Y, Liu A, Xin H, et al. Fault early warning of wind turbine gearbox based on multi-input support vector regression and improved ant lion optimization. Wind Energy, 2020, 24(8): 812-832.
4.	陸國強. 電力電子電路故障預測技術分析. 電子元器件與信息技術, 2021, 5(9): 51-52, 65.
5.	宋歡, 翟曉東, 馬玉敏, 等. 基于CNN和LSTM的設備剩余壽命預測方法研究//第31屆中國過程控制會議, 徐州: CPCC, 2020: 267.
6.	吳立金, 夏冉, 詹紅燕, 等. 基于深度學習的故障預測技術研究. 計算機測量與控制, 2018, 26(2): 9-12.
7.	Sun J, Xiao Z. Potential fault region detection in TFDS images based on convolutional neural network//International Symposium on Optoelectronic Technology and Application 2016, Infrared Technology and Applications, Beijing: SPIE, 2016, 10157: 384-391.
8.	Lee K B, Cheon S, Kim C O. A convolutional neural network for fault classification and diagnosis in semiconductor manufacturing processes. IEEE Transactions on Semiconductor Manufacturing, 2017, 30(2): 135-142.
9.	張詩慧, 種銀保, 肖晶晶, 等. 基于卷積神經網絡的醫療設備故障診斷研究//中國醫學裝備大會暨第 27 屆學術與技術交流年會, 蘇州: CAME, 2018: 7-11.
10.	劉香君, 郎朗, 張詩慧, 等. 基于長短時記憶網絡的醫療設備故障智能診斷研究. 生物醫學工程學雜志, 2021, 38(2): 361-368.
11.	方佩璽, 張姚昕, 趙媛. 基于PSO與BP神經網絡的磁共振成像設備故障診斷研究. 機械設計與制造工程, 2025, 54(1): 85-90.
12.	Liao J, Deng Y, Xie X, et al. Research on Chebyshev graph convolutional neural network modeling method for rotating equipment fault diagnosis under variable working conditions. Applied Sciences, 2024, 14(20): 9208.
13.	Du K, Wu D, Bao K, et al. Unconstrained wasserstein distance and multi-attention fusion convolutional neural network guided adversarial domain adaptation for cross-domain fault diagnosis of machines. Mechanical Systems and Signal Processing, 2025, 234: 112797.
14.	井衛云, 潘莉. 醫療設備故障自動檢測系統的設計. 醫療衛生裝備, 2018, 39(8): 23-26.
15.	孫元帥, 孔繁欽, 聶曉音, 等. 基于圖卷積和多傳感融合的跨設備故障診斷方法. 機械強度, 2024,(2024-12-31)[2025-12-11].
16.	Gao F, Zhang L, Wang W, et al. Named entity recognition for equipment fault diagnosis based on RoBERTa-wwm-ext and deep learning integration. Electronics, 2024, 13(19): 3935.
17.	龍村, 侯曉彤, 趙舉. ECMO: 體外膜肺氧合(第2版). 北京: 人民衛生出版社, 2016: 1-974.
18.	譚建華. 基于大數據分析的醫院機電設備故障診斷與維修的研究. 家電維修, 2024, 2024(7): 86-88.
19.	金紹志. 淺析現代化醫院設備管理的新趨勢. 中國衛生事業管理, 2006, 2006(10): 591-592.
20.	馮英, 孫琬婷, 孫娟, 等. 長程體外膜肺氧合支持的護理經驗體會. 甘肅醫藥, 2025, 44(4): 367-369.
21.	舒穎. GPS坐標時間序列粗差剔除方法比較分析. 導航定位學報, 2021, 9(4): 79-85.
22.	王文卿, 張小喬, 何霽, 等. 基于混合雙分支卷積神經網絡和圖卷積神經網絡的全色銳化方法. 智能系統學報, 2025, 20(3): 649-657.
23.	Yang F, Xu Q, Chen F. Active learning deep autoencoder model with importance sampling for reliability analysis. Applied Soft Computing, 2025, 180: 113428.
24.	McCloskey C, Abu-Omar Y, Bass J C, et al. Device profile of the integrated VitalFlow ECMO system. Expert Rev Med Devices, 2025, 22(5): 415-423.
25.	黃博, 李浩源, 陸斌, 等. 清華大學能源與動力工程系人工心臟研究進展. 清華大學學報(自然科學版), 2022, 62(4): 746-757.
26.	江負成. ECMO血泵用磁懸浮系統設計與控制. 深圳: 中國科學院大學(中國科學院深圳先進技術研究院), 2023.
27.	羅德生, 李龍倜, 楊寶義, 等. 失效模式和效應分析在優化ECMO護理流程管理中的應用. 湖北醫藥學院學報, 2022, 41(3): 300-303.
28.	任明仕, 董士勇, 申華, 等. 國產體外膜氧合設備的研發現狀和應用前景. 中國體外循環雜志, 2022, 20(6): 365-370.
29.	Goap A, Sarkar S, Roy A, et al. An IoT-based architectural framework for earthquake warning system using low-cost heterogeneous seismic sensors. Arabian Journal for Science and Engineering, 2025, 50(23): 1-16.
30.	Wang N, Zhou Q, Gao J, et al. Evaluating the efficacy of PCA and t-SNE in optimizing input features for groundwater level simulation using machine learning models. Environmental Earth Sciences, 2025, 84(12): 336.
31.	鄭笑雪. 基于t-SNE算法的多屬性降維技術. 石化技術, 2025, 32(6): 244-246.
32.	llaoui M, Hedjam R, Bouanane K, et al. Exploring non-negativity for improved manifold embedding: application to t-SNE. Knowledge-Based Systems, 2025, 330: 114547.
33.	Grisci I B, Ponta I M, Dorn M. Assessing feature scorer results on high-dimensional datasets with t-SNE. Neurocomputing, 2025, 652: 130561.
34.	Li T, Zhou Z, Li S, et al. The emerging graph neural networks for intelligent fault diagnostics and prognostics: a guideline and a benchmark study. Mechanical Systems and Signal Processing, 2022, 168: 108653.
35.	Han T, Xie W, Pei Z. Semi-supervised adversarial discriminative learning approach for intelligent fault diagnosis of wind turbine. Information Sciences, 2023, 648: 119496.

1. 陳艷, 王琪, 蔣佳旺. 基于數據挖掘技術的醫療設備故障監測與識別方法的探討與研究. 中國醫療設備, 2020, 35(8): 56-59.
2. Wei Y, Liu H, Chen G, et al. Fault diagnosis of marine turbocharger system based on an unsupervised algorithm. Journal of Electrical Engineering & Technology, 2020, 15: 1331-1343.
3. Yang Y, Liu A, Xin H, et al. Fault early warning of wind turbine gearbox based on multi-input support vector regression and improved ant lion optimization. Wind Energy, 2020, 24(8): 812-832.
4. 陸國強. 電力電子電路故障預測技術分析. 電子元器件與信息技術, 2021, 5(9): 51-52, 65.
5. 宋歡, 翟曉東, 馬玉敏, 等. 基于CNN和LSTM的設備剩余壽命預測方法研究//第31屆中國過程控制會議, 徐州: CPCC, 2020: 267.
6. 吳立金, 夏冉, 詹紅燕, 等. 基于深度學習的故障預測技術研究. 計算機測量與控制, 2018, 26(2): 9-12.
7. Sun J, Xiao Z. Potential fault region detection in TFDS images based on convolutional neural network//International Symposium on Optoelectronic Technology and Application 2016, Infrared Technology and Applications, Beijing: SPIE, 2016, 10157: 384-391.
8. Lee K B, Cheon S, Kim C O. A convolutional neural network for fault classification and diagnosis in semiconductor manufacturing processes. IEEE Transactions on Semiconductor Manufacturing, 2017, 30(2): 135-142.
9. 張詩慧, 種銀保, 肖晶晶, 等. 基于卷積神經網絡的醫療設備故障診斷研究//中國醫學裝備大會暨第 27 屆學術與技術交流年會, 蘇州: CAME, 2018: 7-11.
10. 劉香君, 郎朗, 張詩慧, 等. 基于長短時記憶網絡的醫療設備故障智能診斷研究. 生物醫學工程學雜志, 2021, 38(2): 361-368.
11. 方佩璽, 張姚昕, 趙媛. 基于PSO與BP神經網絡的磁共振成像設備故障診斷研究. 機械設計與制造工程, 2025, 54(1): 85-90.
12. Liao J, Deng Y, Xie X, et al. Research on Chebyshev graph convolutional neural network modeling method for rotating equipment fault diagnosis under variable working conditions. Applied Sciences, 2024, 14(20): 9208.
13. Du K, Wu D, Bao K, et al. Unconstrained wasserstein distance and multi-attention fusion convolutional neural network guided adversarial domain adaptation for cross-domain fault diagnosis of machines. Mechanical Systems and Signal Processing, 2025, 234: 112797.
14. 井衛云, 潘莉. 醫療設備故障自動檢測系統的設計. 醫療衛生裝備, 2018, 39(8): 23-26.
15. 孫元帥, 孔繁欽, 聶曉音, 等. 基于圖卷積和多傳感融合的跨設備故障診斷方法. 機械強度, 2024,(2024-12-31)[2025-12-11].
16. Gao F, Zhang L, Wang W, et al. Named entity recognition for equipment fault diagnosis based on RoBERTa-wwm-ext and deep learning integration. Electronics, 2024, 13(19): 3935.
17. 龍村, 侯曉彤, 趙舉. ECMO: 體外膜肺氧合(第2版). 北京: 人民衛生出版社, 2016: 1-974.
18. 譚建華. 基于大數據分析的醫院機電設備故障診斷與維修的研究. 家電維修, 2024, 2024(7): 86-88.
19. 金紹志. 淺析現代化醫院設備管理的新趨勢. 中國衛生事業管理, 2006, 2006(10): 591-592.
20. 馮英, 孫琬婷, 孫娟, 等. 長程體外膜肺氧合支持的護理經驗體會. 甘肅醫藥, 2025, 44(4): 367-369.
21. 舒穎. GPS坐標時間序列粗差剔除方法比較分析. 導航定位學報, 2021, 9(4): 79-85.
22. 王文卿, 張小喬, 何霽, 等. 基于混合雙分支卷積神經網絡和圖卷積神經網絡的全色銳化方法. 智能系統學報, 2025, 20(3): 649-657.
23. Yang F, Xu Q, Chen F. Active learning deep autoencoder model with importance sampling for reliability analysis. Applied Soft Computing, 2025, 180: 113428.
24. McCloskey C, Abu-Omar Y, Bass J C, et al. Device profile of the integrated VitalFlow ECMO system. Expert Rev Med Devices, 2025, 22(5): 415-423.
25. 黃博, 李浩源, 陸斌, 等. 清華大學能源與動力工程系人工心臟研究進展. 清華大學學報(自然科學版), 2022, 62(4): 746-757.
26. 江負成. ECMO血泵用磁懸浮系統設計與控制. 深圳: 中國科學院大學(中國科學院深圳先進技術研究院), 2023.
27. 羅德生, 李龍倜, 楊寶義, 等. 失效模式和效應分析在優化ECMO護理流程管理中的應用. 湖北醫藥學院學報, 2022, 41(3): 300-303.
28. 任明仕, 董士勇, 申華, 等. 國產體外膜氧合設備的研發現狀和應用前景. 中國體外循環雜志, 2022, 20(6): 365-370.
29. Goap A, Sarkar S, Roy A, et al. An IoT-based architectural framework for earthquake warning system using low-cost heterogeneous seismic sensors. Arabian Journal for Science and Engineering, 2025, 50(23): 1-16.
30. Wang N, Zhou Q, Gao J, et al. Evaluating the efficacy of PCA and t-SNE in optimizing input features for groundwater level simulation using machine learning models. Environmental Earth Sciences, 2025, 84(12): 336.
31. 鄭笑雪. 基于t-SNE算法的多屬性降維技術. 石化技術, 2025, 32(6): 244-246.
32. llaoui M, Hedjam R, Bouanane K, et al. Exploring non-negativity for improved manifold embedding: application to t-SNE. Knowledge-Based Systems, 2025, 330: 114547.
33. Grisci I B, Ponta I M, Dorn M. Assessing feature scorer results on high-dimensional datasets with t-SNE. Neurocomputing, 2025, 652: 130561.
34. Li T, Zhou Z, Li S, et al. The emerging graph neural networks for intelligent fault diagnostics and prognostics: a guideline and a benchmark study. Mechanical Systems and Signal Processing, 2022, 168: 108653.
35. Han T, Xie W, Pei Z. Semi-supervised adversarial discriminative learning approach for intelligent fault diagnosis of wind turbine. Information Sciences, 2023, 648: 119496.

Journal of Biomedical Engineering

Research on fault diagnosis of extracorporeal membrane oxygenation devices based on convolutional neural network and Chebyshev graph convolutional neural network

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content