基于时序数据灰度图像的氦检漏设备故障诊断方法研究

doi:10.13385/j.cnki.vacuum.2025.06.10

摘要/Abstract

摘要： 氦检漏设备传统故障诊断方法存在无法直观表示故障特征、严重依赖专家经验而准确性有限的问题。针对氦检漏设备传感器数据,提出了一种结合卷积神经网络（CNN）的时间序列图像生成方案,对故障数据进行数据驱动分析和故障分类,从而更准确地诊断故障。首先将一维时间序列信号转换为灰度图像进行形象化表达,以适应不同的氦检漏设备故障诊断场景,然后对LeNet-5 CNN模型进行优化,设计了计算速度更快、识别精度最大化的LeNet-5s CNN模型,并提出了复杂检测任务下的双模型检测方法,最后通过实验验证了算法的有效性。结果表明,模型优化后识别精确度有一定提升,双模型检测方法对复杂检测任务下的三类故障都有较好的识别性能。

关键词: 氦检漏设备, 时序数据, 数据处理, 故障诊断, 分类, 深度学习

Abstract: Traditional fault diagnosis methods for helium leak detection equipment provide limited accuracy due to the inability to intuitively represent fault characteristics and heavy reliance on experts. A time series image generation scheme combined with the convolutional neural networks (CNN) is proposed for the sensor data of helium leak detection equipment, which performs data-driven analysis and fault classification on the fault data. Thereby, the faults of helium leak detection equipment can be diagnosed more accurately. Firstly, a more intuitive grayscale transformation was proposed to convert one-dimensional time series signals into grayscale images for visual representation, in order to adapt to different helium leak detection equipment fault diagnosis scenarios. Then, the LeNet-5 CNN model was optimized, and LeNet-5s CNN model with faster computing speed was designed to maximize recognition accuracy, and a dual model detection method was proposed for complex detection tasks. Finally, the effectiveness of the algorithms was verified through experiments. The results show that the improved model has a certain improvement in accuracy compared to the pre-improved one, and the dual model detection method has good recognition performance for all three types of faults in this complex detection task.

Key words: helium leak detection equipment, time series data, data processing, fault diagnosis, classification, deep learning

中图分类号: TP391.4

瞿骑龙, 戴城, 张治军, 艾士义. 基于时序数据灰度图像的氦检漏设备故障诊断方法研究[J]. 真空, 2025, 62(6): 70-79.

QU Qilong, DAI Cheng, ZHANG Zhijun, AI Shiyi. Research on Fault Diagnosis Method of Helium Leak Detection Equipment Based on Gray Scale Images of Time Series Data[J]. VACUUM, 2025, 62(6): 70-79.

参考文献

[1] 李卫平,江国焱,罗炜,等.真空氦检漏技术在ITER项目中的应用[J].无损检测,2023,45(6):1-6.
[2] 胡茂中,白国云.低充氦浓度氦质谱检漏技术应用研究[J].真空科学与技术学报,2011,31(2):208-211.
[3] 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.
[4] 陈思翼. 车用空调智能车间氦检漏设备信息建模及云端接入技术[D]. 重庆:重庆邮电大学,2018.
[5] GAO Z, CECATI C, DING S X.A survey of fault diagnosis and fault-tolerant techniques—Part I: fault diagnosis with model-based and signal-based approaches[J]. IEEE transactions on industrial electronics, 2015, 62(6): 3757-3767.
[6] TANG L, TIAN H, HUANG H, et al.A survey of mechanical fault diagnosis based on audio signal analysis[J]. Measurement, 2023, 220: 113294.
[7] 何擎. 氦质谱检漏仪灯丝脆断故障的研究与解决[J].真空电子技术,2017(4):55-57.
[8] JIANG Y, YIN S, KAYNAK O.Optimized design of parity relation-based residual generator for fault detection: data-driven approaches[J]. IEEE Transactions on Industrial Informatics, 2020, 17(2): 1449-1458.
[9] DAI X, GAO Z.From model, signal to knowledge: a data-driven perspective of fault detection and diagnosis[J]. IEEE Transactions on Industrial Informatics, 2013, 9(4): 2226-2238.
[10] HAN C, CHANG W, YUAN F, et al.A process fault detection method based on PCA and linear regression[C]//2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT). Nanjing, China: IEEE, 2023: 451-455.
[11] YAN G, CHEN J, BAI Y, et al.A survey on fault diagnosis approaches for rolling bearings of railway vehicles[J]. Processes, 2022, 10(4): 724.
[12] ZHANG Q, GAO J, DONG H, et al.WPD and DE/BBO-RBFNN for solution of rolling bearing fault diagnosis[J]. Neurocomputing, 2018, 312: 27-33.
[13] ZHANG X, LIANG Y, ZHOU J.A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM[J]. Measurement, 2015, 69: 164-179.
[14] HU Q, SI X S, QIN A S, et al.Machinery fault diagnosis scheme using redefined dimensionless indicators and mRMR feature selection[J]. IEEE Access, 2020, 8: 40313-40326.
[15] XU Y, ZHANG K, MA C, et al.An adaptive spectrum segmentation method to optimize empirical wavelet transform for rolling bearings fault diagnosis[J]. IEEE Access, 2019, 7: 30437-30456.
[16] Yang C Y, Wu T Y.Diagnostics of gear deterioration using EEMD approach and PCA process[J]. Measurement, 2015, 61: 75-87.
[17] YANG T, PEN H, WANG Z, et al.Feature knowledge based fault detection of induction motors through the analysis of stator current data[J]. IEEE Transactions on instrumentation and Measurement, 2016, 65(3): 549-558.
[18] LEI Y, YANG B, JIANG X, et al.Applications of machine learning to machine fault diagnosis: a review and roadmap[J]. Mechanical systems and signal processing, 2020, 138: 106587.
[19] SUNAL C E, DYO V, VELISAVLJEVIC V.Review of machine learning based fault detection for centrifugal pump induction motors[J]. IEEE access, 2022,10:71344-71355.
[20] 黄开基,杨华.基于深度学习特征的二维图像匹配算法综述[J].计算机工程,2024,50(10):16-34.
[21] 胡海彬,刘仁鑫,刘日龙,等.卷积神经网络在机械故障诊断中的应用综述[J].机械工程与自动化,2024,(4):221-223.
[22] 赵小强,罗维兰.改进卷积Lenet-5神经网络的轴承故障诊断方法[J].电子测量与仪器学报,2022,36(6):113-125.
[23] 刘涛,麻德权.基于CBAM-CNN的涡旋压缩机故障诊断[J].振动.测试与诊断,2024,44(5):900-906.
[24] 罗丫,葛可可,袁晓文,等.基于分段位移激励函数的贯穿式故障建模及滚动轴承振动特性分析[J].工程设计学报,2025,32(1):112-120.
[25] 张腾. 不平衡数据集均衡化方法研究及其应用[D].北京:中国石油大学, 2018.
[26] 张雷,王光华,曹磊,等.基于GAN模型与随机森林算法的保护系统智能状态评价与预警[J].电力科学与技术学报,2021,36(6):104-112.
[27] ZOHREVAND A, IMANI Z.An empirical study of the performance of different optimizers in the deep neural networks[C]//2022 International Conference on Machine Vision and Image Processing (MVIP). Ahvaz, Iran: IEEE, 2022: 1-5.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed