基于谱幅融合广义健康指数的可解释装备退化评估优化模型研究进展

doi:10.3901/JME.2024.18.001

机械工程学报 ›› 2024, Vol. 60 ›› Issue (18): 1-16.doi: 10.3901/JME.2024.18.001

扫码分享

基于谱幅融合广义健康指数的可解释装备退化评估优化模型研究进展

严彤彤^1,2, 王冬^1,2, 彭志科^2,3, 雷亚国⁴

1. 上海交通大学机械与动力工程学院上海 200240;
2. 上海交通大学机械系统与振动国家重点实验室上海 200240;
3. 宁夏大学机械工程学院宁夏 750021;
4. 西安交通大学现代设计及转子轴承系统教育部重点实验室西安 710049

收稿日期:2023-10-22 修回日期:2024-03-13 出版日期:2024-09-20 发布日期:2024-11-15
作者简介:严彤彤,女,1997年出生,博士研究生。主要研究方向为基于数据融合的性能退化优化建模和健康指数构建。E-mail:yantongtong@sjtu.edu.cn
王冬(通信作者),男,1984年出生,博士,副教授,博士研究生导师。主要研究方向包括智能运维与大数据分析、故障特征提取的理论基础研究、退化建模数学优化模型、寿命预测统计概率模型、机械信号处理和统计学习。E-mail:dongwang4-c@sjtu.edu.cn
基金资助:
国家重点研发计划(2022YFB3402100)和国家自然科学基金(52475112，12121002)资助项目。

Advances in Interpretable Machine Degradation Assessment Optimization Models Based on Spectral Amplitude Fusion Aided Generalized Health Indices

YAN Tongtong^1,2, WANG Dong^1,2, PENG Zhike^2,3, LEI Yaguo⁴

1. School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240;
2. State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200240;
3. School of Mechanical Engineering, Ningxia University, Ningxia 750021;
4. Key Laboratory of Education Ministry for Modern Design and Rotor-bearing System, Xi'an Jiaotong University, Xi'an 710049

Received:2023-10-22 Revised:2024-03-13 Online:2024-09-20 Published:2024-11-15

摘要/Abstract

摘要： 针对装备全生命周期退化评估所需的健康指数存在构建过程繁琐且未考虑退化特性、构建模型和学习权重物理难解释、退化趋势可分性和单调性不显著以及难以同步实现装备状态监测、早期故障诊断和退化评估等问题，总结近年来基于谱幅融合广义健康指数的可解释装备退化评估优化模型研究成果，探讨基于退化特性和故障特征稀疏性的两类典型可解释广义健康指数权重优化模型及其应用效果。该类优化模型核心思想是将谱幅(如频域幅值或包络谱域幅值)加权和定义为广义健康指数，然后基于可分性、单调性等退化特性和故障特征稀疏特性推导出相关的多种广义健康指数权重凸优化模型。与现有模型相比，所提出的基于谱幅融合广义健康指数的可解释装备性能退化评估优化模型具有以下特点：① 仅需工程常用的傅里叶变换或希尔伯特变换作为原始数据预处理方法，避免使用复杂信号处理算法及其参数优化过程；② 广义健康指数权重凸优化模型构造来源于退化特性和故障特征稀疏性的凸优化描述，因此权重优化模型具有可解释性和全局最优解；③ 优化的谱幅权重具备频域故障物理可解释性，谱幅权重可定位信息频率带并揭示故障特征频率来支撑广义健康指数退化评估合理性；④ 基于谱幅加权的广义健康指数可同时实现装备状态监测、故障诊断和退化评估三重目的，利于高效实施装备智能运维。最后，对基于谱幅融合广义健康指数的未来研究方向进行充分探讨。

关键词: 广义健康指数, 谱幅融合, 退化特性, 稀疏性, 装备退化评估, 凸优化

Abstract: Since health indices required for machine full lifecycle degradation assessment have problems such as cumbersome construction process, difficulty in explaining model construction and learning weights physically, insignificant separability and monotonicity of degradation trends, and difficulty in synchronously implementing machine condition monitoring, early fault diagnosis, and degradation assessment, research progresses of interpretable machine degradation assessment optimization models based on spectral amplitude fusion aided generalized health indices in recent years are summarized and two kinds of typical interpretable generalized health index weight optimization models based on degradation properties and fault feature sparsity and their application effects are explored. The core idea of this type of optimization models is to define the weighted sum of spectral amplitudes (such as amplitudes in the frequency domain or the envelope spectral domain) as a generalized health index, and then derive various generalized health index weight convex optimization models based on the degradation properties such as separability and monotonicity, as well as the sparsity properties of fault features. Compared with existing models, the proposed interpretable machine performance degradation assessment optimization models based on spectral amplitude fusion aided generalized health indices has the following characteristics：① only the commonly used Fourier transform or Hilbert transform in engineering are required as raw data preprocessing methods, avoiding the use of complex signal processing algorithms and parameter optimization processes; ② the construction of generalized health index weight convex optimization models comes from the convex optimization description of degradation properties and the sparsity description of fault features, so various weight optimization models have interpretability and unique global optimal solutions; ③ optimized spectral amplitude weights have physical fault interpretability in the frequency domain, which can locate informative frequency bands and reveal fault feature frequencies to support the rationality of generalized health indices for degradation assessment; ④ generalized health indices based on spectral amplitude weighting can simultaneously achieve the triple goals of machine condition monitoring, fault diagnosis, and degradation assessment, which is conducive to efficient implementation of intelligent machine operation and maintenance. Finally, some future research directions of generalized health indices based on spectral amplitude fusion are fully explored.

Key words: generalized health indices, spectral amplitude fusion, degradation properties, sparsity properties, machine degradation assessment, convex optimization

中图分类号:

TH17

严彤彤, 王冬, 彭志科, 雷亚国. 基于谱幅融合广义健康指数的可解释装备退化评估优化模型研究进展[J]. 机械工程学报, 2024, 60(18): 1-16.

YAN Tongtong, WANG Dong, PENG Zhike, LEI Yaguo. Advances in Interpretable Machine Degradation Assessment Optimization Models Based on Spectral Amplitude Fusion Aided Generalized Health Indices[J]. Journal of Mechanical Engineering, 2024, 60(18): 1-16.

参考文献

[1] 魏发远，谢朝阳，孙昌璞，等. 长贮装备性能退化评估刍议[J]. 机械工程学报，2020，56(16)：262-272. WEI Fayuan，XIE Chaoyang，SUN Changpu. Evaluation of performance degradation of long storage equipment[J]. Journal of Mechanical Engineering，2020，56(16)：262-272.
[2] 朱朔，白瑞林，刘秦川. 基于果蝇优化算法-小波支持向量数据描述的滚动轴承性能退化评估[J].中国机械工程，2018，29(5)：602-608. ZHU Shuo，BAI Ruilin，LIU Qinchuan. Performance degradation evaluation of rolling bearings based on fruit fly optimization algorithm and wavelet support vector data description[J]. China Mechanical Engineering，2018，29(5)：602-608
[3] 雷亚国，贾峰，孔德同，等. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报，2018，54(5)：94-104. LEI Yaguo，JIA Feng，KONG Detong，et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering，2018，54(5)：94-104.
[4] 谢雨洁，肖友刚，王田天，等. 基于异常检测的轴承退化阶段识别方法[J].中南大学学报，2022，53(5)：1740-1749. XIE Yujie，XIAO Yougang，WANG Tiantian. Bearing degradation stage identification method based on anomaly detection[J]. Journal of Central South University，2022，53(5)：1740-1749
[5] 董绍江，裴雪武，汤宝平，等. 基于FNER性能退化指标及IDRSN的滚动轴承寿命状态识别方法[J]. 机械工程学报，2021，57(15)：105-115. DONG Shaojiang，PEI Xuewu，TANG Baoping. Method for identifying the service life status of rolling bearings based on FNER performance degradation index and IDRSN[J]. Journal of Mechanical Engineering，2021，57(15)：105-115
[6] 黄海凤，高宏力，李丹，等. 滚动轴承早期性能退化评估技术研究[J]. 机械科学与技术，2017，36(11)：1771-1777. HUANG Haifeng，GAO Hongli，LI Dan. Research on early performance degradation evaluation technology for rolling bearings[J]. Mechanical Science and Technology，2017，36(11)：1771-1777.
[7] LI N，LEI Y，LIN J，et al. An improved exponential model for predicting remaining useful life of rolling element bearings[J]. IEEE Transactions on Industrial Electronics，2015，62(12)：7762-7773.
[8] YAN R，LIU Y，GAO R X. Permutation entropy：A nonlinear statistical measure for status characterization of rotary machines[J]. Mechanical Systems and Signal Processing，2012，29(29)：474-484.
[9] 王庆锋，李中，许述剑，等. 基于故障案例学习的设备健康评价方法研究[J]. 机械工程学报，2020，56(20)：28-37. WANG Qingfeng，LI Zhong，XU Shujian，et al. Research on equipment health evaluation method based on fault case learning[J]. Journal of Mechanical Engineering，2020，56(20)：28-37.
[10] KLAUSEN A，KHANG H，ROBBERSMYR K，et al. Sparse and flexible convex-hull representation for machine degradation modeling[J]. IEEE Transactions on Reliability，2022，72(1)：1-10.
[11] AN D，CHOI J，KIM N H. Remaining useful life prediction of rolling element bearings using degradation feature based on amplitude decrease at specific frequencies[J]. Structural Health Monitoring，2017，72(5)：1095-1109.
[12] LI W，QIN M，ZHU Z，et al. Health monitoring of rolling element bearing using a spectrum searching strategy[J]. Journal of Vibroengineering，2017，19(6)：4231-4246.
[13] WANG L，PAN J，SHAO Y，et al. Two new kurtosis-based similarity evaluation indicators for grinding chatter diagnosis under non-stationary working conditions[J]. Measurement，2021，176(2)：109215.
[14] GUO L，LEI Y，LI N，et al. Machinery health indicator construction based on convolutional neural networks considering trend burr[J]. Neurocomputing，2018，292(292)：142-150.
[15] 章立军，刘博，张彬，等. 基于时频图像融合的轴承性能退化特征提取[J]. 机械工程学报，2013，49(22)：53-58. ZHANG Lijun，LIU Bo，ZHANG Bin. Feature extraction method of bearing performance degradation based on time-frequency image fusion[J]. Journal of Mechanical Engineering，2013，49(22)：53-58.
[16] CHEN L，XU G，ZHANG S，et al. Health indicator construction of machinery based on end-to-end trainable convolution recurrent neural networks[J]. Journal of Manufacturing Systems，2020，54(54)：1-11.
[17] CHEN D，QIN Y，WANG Y，et al. Health indicator construction by quadratic function-based deep convolutional auto-encoder and its application into bearing RUL prediction[J]. ISA Transactions，2020，114(114)：44-56.
[18] LIM C，KIM S，SEO Y，et al. Feature extraction for bearing prognostics using weighted correlation of fault frequencies over cycles[J]. Structural Health Monitoring，2020，19(6)：1808-1820.
[19] LEI Y，LI N，GUO L，et al. Machinery health prognostics：A systematic review from data acquisition to RUL prediction[J]. Mechanical Systems and Signal Processing，2018，104：799-834.
[20] MOCHAMMAD S，NOH Y，KANG Y. Bearing fault degradation modeling based on multitime windows fusion unsupervised health indicator[J]. IEEE Sensors Journal，2023，23(17)：19623-19634.
[21] 王奉涛，陈旭涛，闫达文，等. 流形模糊C均值方法及其在滚动轴承性能退化评估中的应用[J]. 机械工程学报，2016，52(15)：59-64. WANG Fengtao，CHEN Xutao，YAN Dawen. Fuzzy C-means using manifold learning and its application to rolling bearing performance degradation assessment[J]. Journal of Mechanical Engineering，2016，52(15)：59-64.
[22] CHEN Z，ZHU H，FAN L，et al. Health indicator similarity analysis-based adaptive degradation trend detection for bearing time-to-failure prediction[J]. Electronics，2023，12(7)：1569-1578.
[23] COCCONCELLI M，STROZZI M，CAVALAGLIO J，et al. Detectivity：A combination of Hjorth’s parameters for condition monitoring of ball bearings[J]. Mechanical Systems and Signal Processing，2022，164：108247.
[24] GUO W，LI X，WAN X. A novel approach to bearing prognostics based on impulse-driven measures，improved morphological filter and practical health indicator construction[J]. Reliability Engineering & System Safety，2023，238：109451.
[25] CHEN Z，GUO R，LIN Z，et al. A data-driven health monitoring method using multiobjective optimization and stacked autoencoder based health indicator[J]. IEEE Transactions on Industrial Informatics，2021，17(9)：6379-6389.
[26] LI X，JIANG H，XIONG X，et al. Rolling bearing health prognosis using a modified health index based hierarchical gated recurrent unit network[J]. Mechanism and Machine Theory，2019，133(133)：229-249.
[27] CHEN Z，XIA T，ZHOU D，et al. A Health index construction framework for prognostics based on feature fusion and constrained optimization[J]. IEEE Transactions on Instrumentation and Measurement，2021，70(70)：1-15.
[28] QIN Y，ZHOU J，CHEN D. Unsupervised health indicator construction by a novel degradation-trend-constrained variational autoencoder and its applications[J]. IEEE/ASME Transactions on Mechatronics，2021，27(3)：1447-1456.
[29] YANG J，YIN S，CHANF Y，et al. An efficient method for monitoring degradation and predicting the remaining useful life of mechanical rotating components[J]. IEEE Transactions on Instrumentation and Measurement，2020，70：1-14.
[30] ZHOU H，HUANG X，GUANG W，et al. Construction of health indicators for condition monitoring of rotating machinery：A review of the research[J]. Expert Systems with Applications，2022，203：117297.
[31] WANG D，TSUI K，MIAO Q. Prognostics and health management：A review of vibration based bearing and gear health indicators[J]. IEEE Access，2018，6：665-676.
[32] QIU G，GU Y，CHEN J. Selective health indicator for bearings ensemble remaining useful life prediction with genetic algorithm and Weibull proportional hazards model[J]. Measurement，2022，150：107097.
[33] LIAO L. Discovering prognostic features using genetic programming in remaining useful life prediction[J]. IEEE Transactions on Industrial Electronics，2014，61(5)：2464-2472.
[34] GUO L，LI N，JIA F，et al. A recurrent neural network based health indicator for remaining useful life prediction of bearings[J]. Neurocomputing，2017，240：98-109.
[35] XU F，HUANG Z，YANG F，et al. Constructing a health indicator for roller bearings by using a stacked auto-encoder with an exponential function to eliminate concussion[J]. Applied Soft Computing，2020，89(5)：106119.
[36] PARK J，KIM S，CHOI J H，et al. Frequency energy shift method for bearing fault prognosis using microphone sensor[J]. Mechanical Systems and Signal Processing，2021，147：107068.
[37] YAN T，WANG D，XIA T，et al. A generic framework for degradation modeling based on fusion of spectrum amplitudes[J]. IEEE Transactions on Automation Science and Engineering，2020(99)：1-12.
[38] YAN T，WANG D，XIA T，et al. Online piecewise convex-optimization interpretable weight learning for machine life cycle performance assessment[J]. IEEE Trans Neural Netw Learn Syst.，2022(6)：1-13.
[39] YAN T，WANG D，ZHENG M，et al. Fisher’s discriminant ratio based health indicator for locating informative frequency bands for machine performance degradation assessment[J]. Mechanical Systems and Signal Processing，2022，162：108053.
[40] LIU K，GEBRAEEL N Z，SHI J. A data-level fusion model for developing composite health indices for degradation modeling and prognostic analysis[J]. IEEE Transactions on Automation Science and Engineering，2013，10(3)：652-664.
[41] WANG D，MIAO Q，ZHOU Q，et al. An intelligent prognostic system for gear performance degradation assessment and remaining useful life estimation[J]. Journal of Vibration and Acoustics，2015，137(2)：1-12.
[42] MEEKER W Q，ESCOBAR L. Statistical methods for reliability data[J]. Technometrics，63(3)：437-440.
[43] TSUI K L，NAN C，QIANG Z，et al. Prognostics and health management：A review on data driven approaches[J]. Mathematical Problems in Engineering，2015(6)：1-17.
[44] SI X S，WANG W，HU C H，et al. Remaining useful life estimation based on a nonlinear diffusion degradation process[J]. IEEE Transactions on Reliability，2012，61(1)：50-67.
[45] MEEKER W，LUVALLE M J. An accelerated life test model based on reliability kinetics[J]. Technometrics，1995，37(2)：133-46.
[46] YAN T，WANG D，XIA T，et al. New shapeness property and its convex optimization model for interpretable machine degradation modeling[J]. IEEE Transactions on Reliability，2022，72(2)：703-715.
[47] 雷亚国，韩天宇，王彪，等. XJTU-SY滚动轴承加速寿命试验数据集解读[J]. 机械工程学报，2019，55(16)：1-6. LEI Yaguo，HAN Tianyu，WANG Biao，et al. XJTU-SY rolling element bearing accelerated life test datasets：a tutorial[J]. Journal of Mechanical Engineering，2019，55(16)：1-6.
[48] KONG X，YANG J. Remaining useful life prediction of rolling bearings based on RMS-MAVE and dynamic exponential regression model[J]. IEEE Access，2019，7(7)：169705-169714.
[49] KIM M，SONG C，LIU K. A generic health index approach for multisensor degradation modeling and sensor selection[J]. IEEE Transactions on Automation Science and Engineering，2019，16(3)：1426-1437.
[50] YAN T，WANG D，HOU B，et al. Generic framework for integration of first prediction time detection with machine degradation modelling from frequency domain[J]. IEEE Transactions on Reliability，2021，71(4)：1-13.
[51] LIU K，CHEHADE A，SONG C. Optimize the signal quality of the composite health index via data fusion for degradation modeling and prognostic analysis[J]. IEEE Transactions on Automation Science and Engineering，2017，14(3)：1504-1514.
[52] YAN T，WANG D，KONG J Z，et al. Definition of signal-to-noise ratio of health indicators and its analytic optimization for machine performance degradation assessment[J]. IEEE Transactions on Instrumentation and Measurement，2021，70(70)：1-16.
[53] ANTONI J，BORGHESANI P. A statistical methodology for the design of condition indicators[J]. Mechanical Systems and Signal Processing，2019，114(114)：290-327.
[54] ZENG M，YANG Y，ZHENG J，et al. Maximum margin classification based on flexible convex hulls for fault diagnosis of roller bearings[J]. Mechanical Systems and Signal Processing，2016，66-67：533-545.
[55] ZENG M，YANG Y，ZHENG J，et al. Maximum margin classification based on flexible convex hulls[J]. Neurocomputing，2015，149：957-965.
[56] YAN T，WANG Y，XIA T，et al. Sparse and flexible convex-hull representation for machine degradation modeling[J]. IEEE Transactions on Reliability，2022，72(1)：1-10.
[57] YAN T，WANG D，XIA T，et al. Entropy-maximization oriented interpretable health indicators for locating informative fault frequencies for machine health monitoring[J]. Mechanical Systems and Signal Processing，2023，198：110461.
[58] ANTONI J. The infogram：Entropic evidence of the signature of repetitive transients[J]. Mechanical Systems and Signal Processing，2016，74(1)：73-94.
[59] WANG D，PENG Z，XI L，The sum of weighted normalized square envelope：A unified framework for kurtosis，negative entropy，Gini index and smoothness index for machine health monitoring[J]. Mechanical Systems and Signal Processing，2020，140：106725.
[60] YAN T，WANG D，SUN S，et al. Novel sparse representation degradation modeling for locating informative frequency bands for Machine performance degradation assessment[J]. Mechanical Systems and Signal Processing，2022，179：109372.

基于谱幅融合广义健康指数的可解释装备退化评估优化模型研究进展

Advances in Interpretable Machine Degradation Assessment Optimization Models Based on Spectral Amplitude Fusion Aided Generalized Health Indices

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	刘鹏, 贾寒冰, 张雷, 王震坡. 结构化道路下智能汽车自主换道轨迹规划研究[J]. 机械工程学报, 2023, 59(24): 271-281.
[2]	黄伟国, 李仕俊, 毛磊, 马玉强, 王俊, 沈长青, 阙红波, 朱忠奎. 多源稀疏优化方法研究及其在齿轮箱复合故障检测中的应用[J]. 机械工程学报, 2021, 57(7): 87-99.
[3]	滕儒民, 李玉鑫, 王欣, 赵哲. 基于凸优化的举高消防车时间最优轨迹规划[J]. 机械工程学报, 2019, 55(6): 138-144.
[4]	宋传学, 周放, 肖峰, 常成, 邵玉龙. 基于凸优化的车载复合电源参数匹配[J]. 机械工程学报, 2017, 53(16): 44-51.