基于CNN-RNN的氦检漏设备故障诊断研究

doi:10.13385/j.cnki.vacuum.2025.05.04

摘要/Abstract

摘要： 氦检漏设备在工业生产中广泛应用于检测微小泄漏,确保系统的安全性和可靠性。然而,由于设备的复杂性和工作环境的多变性,故障诊断变得尤为关键。本文提出了一种基于神经网络的氦检漏设备故障诊断方法,旨在提高故障检测的准确性和效率。首先,对设备运行数据进行采集和预处理,输入卷积神经网络（CNN）提取有效的特征向量并降维。然后,将特征输入循环神经网络（RNN）,捕捉数据的时序依赖关系。最后由激活函数输出故障分类结果。结果表明,所提出的CNN-RNN模型在多种故障类型下均表现出优异的诊断性能,在测试集上的分类准确率和召回率均达到99%以上,显著优于传统方法。此外,还探讨了模型的优化策略,包括超参数调优和模型层数选择,进一步提高了模型的准确率和泛化能力。

关键词: 氦检漏设备, 故障诊断, 神经网络, 超参数调优

Abstract: Helium leak detection equipment plays a crucial role in industrial production by identifying minor leaks, thereby ensuring the safety and reliability of systems. However, the complexity of the equipment and the variability of the operating environment pose significant challenges for fault diagnosis. This paper presents a novel fault diagnosis method for helium leak detection equipment based on neural networks, with the aim of enhancing the accuracy and efficiency of fault detection. The methodology involves several key steps. First, operational data from the equipment is collected and preprocessed. The data is then fed into a convolutional neural network (CNN) to extract meaningful feature vectors and reduce dimensionality. Subsequently, the extracted features are input into a recurrent neural network (RNN) to capture temporal dependencies. Finally, the fault classification results are generated using an appropriate activation function. The experimental results show that the proposed CNN-RNN model achieves excellent diagnostic performance across various fault types, with classification accuracy and recall exceeding 99% on the test set, which is significantly outperforming traditional methods. Furthermore, the optimization strategies were explored, such as hyperparameter tuning and model architecture selection, to further improve the model's accuracy and generalization capability.

Key words: helium leak detection equipment, fault diagnosis, neural network, hyperparameter tuning

中图分类号: TP277

瞿骑龙, 段垚, 张治军, 艾士义. 基于CNN-RNN的氦检漏设备故障诊断研究[J]. 真空, 2025, 62(5): 23-31.

QU Qilong, DUAN Yao, ZHANG Zhijun, AI Shiyi. Fault Diagnosis of Helium Leak Detection Equipment Based on CNN-RNN[J]. VACUUM, 2025, 62(5): 23-31.

参考文献

[1] 孙开磊,甄占昌,张聪,等.氦质谱检漏设备故障排除与维护保养[J].中国设备工程,2021(4):49-50.
[2] 谢承辉,王星,肖发厚,等.轴承故障模式与故障诊断方法综述[J/OL].计算机测量与控制, 2024: 1-11. (2024-10-22) [ 2024-11-04]. http://kns.cnki.net/kcms/detail/11.4762.TP.20241022.1013.004.html.
[3] 梁北辰,戴景民.偏最小二乘法在系统故障诊断中的应用[J].哈尔滨工业大学学报,2020,52(3):156-164.
[4] 吴棒,胡云鹏,陈乖乖,等.基于偏最小二乘法的冷水机组传感器故障检测[J].制冷技术,2023,43(6):20-26.
[5] 宋易盟,宋冰,侍洪波,等.基于多子空间加权移动窗主成分分析的全厂流程早期故障检测[J].浙江大学学报(工学版),2024,58(10):2076-2083.
[6] 孔祥玉,解建,罗家宇,等.基于改进高效偏最小二乘的质量相关故障诊断[J].控制理论与应用,2020,37(12):2645-2653.
[7] 郭金玉,王哲,李元.基于核熵独立成分分析的故障检测方法[J].化工学报,2022,73(8):3647-3658.
[8] ZHANG C, GUO Q X, LI Y.Fault detection in the tennessee eastman benchmark process using principal component difference based on k-nearest neighbors[J]. IEEE Access, 2020, 8: 49999-50009.
[9] LI C, LU P H, DONG G M, et al.Bearing fault diagnosis via robust PCA with nonconvex rank approximation[J]. IEEE Sensors Journal, 2024, 24(12): 19531-19542.
[10] DU B Y, KONG X Y, FENG X W.Generalized principal component analysis-based subspace decomposition of fault deviations and its application to fault reconstruction[J]. IEEE Access, 2020, 8: 34177-34186.
[11] 伍盛金,高金林,赖兴全,等. 基于DA-WGAN-SVM的水电机组小样本故障诊断[J]. 水电能源科学,2024,42(11):155-159.
[12] 王博,孙瑞阳,钱路,等.基于数字孪生和贝叶斯网络的液压启闭机故障诊断研究[J].人民珠江,2024,45(10):124-137.
[13] 佘勇,冯银汉,王燕兵.人工神经网络在汽车发动机故障诊断中的运用[J].南方农机,2021,52(13):114-115.
[14] SUN P C, LIU X F, LIN M, et al.Transmission line fault diagnosis method based on improved multiple SVM model[J]. IEEE Access, 2023, 11: 133825-133834.
[15] WANG C Y, PANG K Y, XU Y, et al.A linear integer programming model for fault diagnosis in active distribution systems with bi-directional fault monitoring devices installed[J]. IEEE Access, 2020, 8: 106452-106463.
[16] KORDESTANI M, SAMADI M F, SAIF M, et al.A new fault diagnosis of multifunctional spoiler system using integrated artificial neural network and discrete wavelet transform methods[J]. IEEE Sensors Journal, 2018, 18(12): 4990-5001.
[17] 彭辉,田程程,郑宇锋,等.基于深度置信网络的光伏发电阵列的故障诊断方法[J].海军工程大学学报,2024,36(3):7-14.
[18] 陈代俊,陈里里,董绍江. 基于VMD-CWT-CNN的滚动轴承故障诊断[J]. 机械强度,2023,45(6):1280-1285.
[19] 杜先君,邱小彧.基于改进LSTM神经网络的化工过程故障诊断[J].兰州理工大学学报,2023,49(6):72-79.
[20] ZHU D Q, CHENG X L, YANG L, et al.Information fusion fault diagnosis method for deep-sea human occupied vehicle thruster based on deep belief network[J]. IEEE Transactions on Cybernetics, 2021, 52(9): 9414-9427.
[21] YUAN W B, LI Z G, HE Y G, et al.Open-circuit fault diagnosis of NPC inverter based on improved 1-D CNN network[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 351071.
[22] HUANG Y, CHEN C H, HUANG C J.Motor fault detection and feature extraction using RNN-based variational autoencoder[J]. IEEE Access, 2019, 7: 139086-139096.
[23] WEN L, LI X Y, GAO L, et al.A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE Transactions on Industrial Electronics, 2018, 65(7): 5990-5998.
[24] LI G, WU J, DENG C, et al.Convolutional neural network-based bayesian gaussian mixture for intelligent fault diagnosis of rotating machinery[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 3517410.
[25] XUE Y H, YANG R, CHEN X H, et al.A novel local binary temporal convolutional neural network for bearing fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2023,72: 3525013.
[26] PENG D D, WANG H, LIU Z L, et al.Multibranch and multiscale CNN for fault diagnosis of wheelset bearings under strong noise and variable load condition[J]. IEEE Transactions on Industrial Informatics, 2020, 16(7): 4949-4960.
[27] ZHANG S T, SHAN T M, YOU Z J, et al.A novel SVD-SDP-CNN fault diagnosis method[C]//2024 IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC). Shijiazhuang, China: IEEE, 2024: 52-56.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed