Fault detection method of electric-hydraulic servo actuator for non-equal interval data
-
摘要:
故障检测技术是保障电液伺服机构(EHSA)安全稳定运行的重要技术。由于电液伺服机构存在检测次数有限、检测时间间隔不相等的问题，直接运用这类检测数据结合现有算法对其进行故障检测可能导致模型性能下降、检测准确率降低。为解决该问题，提出一种基于非等间隔数据的电液伺服机构故障检测方法。运用M-H算法结合同批次不同设备的电液伺服机构历史检测数据，将设备的历史检测数据等间隔化；运用核主成分分析(KPCA)方法分析主成分之间的差异，构建统计量，进行故障检测，利用贡献图法分析故障相关指标。所提方法在数据不等间隔且数量有限的情况下，具有较高的故障检测率。通过某型电液伺服机构的历史检测数据，验证了所提方法的有效性。
Abstract:Fault detection technology is an important technology to ensure the safe and stable operation of the electric-hydraulic servo actuator (EHSA). Owing to the electro-hydraulic servo mechanism’s issues with unequal detection time intervals and limited detection times, utilizing such detection data directly in conjunction with the current algorithm to identify EHSA failure may result in decreased detection accuracy and model performance. In order to solve this kind of problem, a fault detection method of an electro-hydraulic servo mechanism based on non-equal interval data was proposed. First, the historical detection data of the equipment was isolated by combining the historical detection data of electro-hydraulic servo mechanisms of various devices in the same batch using the M-H algorithm. Second, the contribution graph approach was utilized to examine the fault-related indicators after statistics were constructed using the kernel principal components analysis (KPCA) method, which analyzed the discrepancies between principal components and served as the basis for fault identification. When the number is limited and the data are not evenly spaced, the suggested approach has a high defect identification rate. The effectiveness of the method is verified by the historical detection data of a certain type of electro-hydraulic servo system.
-
图 6 基于线性插补法的数据等间隔化结果
Figure 6. Results of equal interval data based on linear interpolation method
图 7 基于线性插补法的数据等间隔化结果概率密度分布
Figure 7. Probability density distribution of data equidistantization results based on linear interpolation method
图 9 部分指标检测数据等间隔处理前后自相关系数
Figure 9. Autocorrelation coefficient before and after interval processing of some index detection data
图 10 部分指标检测数据概率密度分布
Figure 10. Probability distribution of partial index detection data
表 1 常见故障及其检测指标的体现
Table 1. Embodiment of common faults and their detection indicators
部件 主要故障原因 主要指标体现 电机 受潮或多余物堆积等 绝缘检查不通过 电枢润滑条件劣化 电机电流过大 油泵 泵入口压力低、
油密封性差、
泵流量不足等建压时间过长 频率特性相位滞后过大 暂态特性时间过长 油密封检查不通过 蓄能器 活塞密封圈故障 充气压力小于标准值 非工作状态油面电压过高 建压时间过长 外密封性故障 油密封检查不通过 增压
油箱油箱密封性不佳导致泄漏 非工作状态油面电压过低 非工作状态泵入口压力过小 油箱加压弹簧或活塞故障 非工作状态泵入口压力过小 反馈
电位计电阻性能劣化 零位电压过大 电位计分阻之差过大 电液
伺服阀
及作动筒活塞故障、
反馈电位计故障、
作动筒故障、
力矩马达故障、
滑阀故障、
喷嘴挡板阀故障零位电压过大 最大摆角过小 位置特性相对误差过大 暂态特性时间过长 频率特性相位滞后过大 回环宽度过大 
下载: 导出CSV
表 2 差异分析
Table 2. Variance analysis
缺失率/% （z, p） 线性插补法 M-H算法 10 （0, 0.9160 ）（0, 0.9844 ）20 （0, 0.8670 ）（0, 0.9499 ）30 （0, 0.8355 ）（0, 0.8908 ）40 （0, 0.7799 ）（0, 0.8225 ）50 （0, 0.6454 ）（0, 0.7765 ）
下载: 导出CSV
-
[1] 胡昌华, 马清亮, 郑建飞. 导弹测试与发射控制技术[M]. 北京: 国防工业出版社, 2010.Hu C H, Ma Q L, Zheng J F. Test and launch control technology for missile[M]. Beijing: National Defense Industry Press, 2010(in Chinese). [2] 潘昌忠, 何广, 李智靖, 等. 不确定电液伺服系统的时变输出约束自适应滤波控制[J]. 北京航空航天大学学报, 2024, 50(6): 1819-1828.Pan C Z, He G, Li Z J, et al. Adaptive filtered control for uncertain electro-hydraulic servo systems with time-varying output constraints[J]. Journal of Beijing University of Aeronautics and Astronautics, 2024, 50(6): 1819-1828(in Chinese). [3] 郭新平, 汪成文, 刘华, 等. 基于扩张状态观测器的泵控电液伺服系统滑模控制[J]. 北京航空航天大学学报, 2020, 46(6): 1159-1168.Guo X P, Wang C W, Liu H, et al. Extended-state-observer based sliding mode control for pump-controlled electro-hydraulic servo system[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(6): 1159-1168(in Chinese). [4] Guo R, Sui J. Remaining useful life prognostics for the electrohydraulic servo actuator using Hellinger distance-based particle filter[J]. IEEE Transactions on Instrumentation and Measurement, 2019, 69(4): 1148-1158. [5] Phan V, Ahn K. Fault-tolerant control for an electro-hydraulic servo system with sensor fault compensation and disturbance rejection[J]. Nonlinear Dynamics, 2023, 111(11): 10131-10146. [6] 黄旭星, 李爽, 杨彬, 等. 人工智能在航天器制导与控制中的应用综述[J]. 航空学报, 2021, 42(4): 106-121.Huang X X, L1 S, Yang B, et al. Spacecraft guidance and control based on artificial intelligence: review[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4): 106-121(in Chinese). [7] 王学进, 董海迪, 王淅娜. 一种便携式导弹电液伺服机构动态测试系统设计[J]. 计算机测量与控制, 2024, 32(5): 172-177.Wang X J, Dong H D, Wang X N. Design of dynamic test system for portable missile electro-hydraulic servo mechanism[J]. Computer Measurement& Control, 2024, 32(5): 172-177 (in Chinese). [8] 张磊, 卢文忠, 刘丙杰, 等. 导弹电液伺服机构故障诊断专家系统的设计研究[J]. 计算机测量与控制, 2013, 21(12): 3284-3286.Zhang L, Lu W Z, Liu B J, et al. Application research of fault diagnostic expert system on missile electro-hydraulic servo mechanism[J]. Computer Measurement & Control, 2013, 21(12): 3284-3286(in Chinese). [9] Gao W, Sun P, Ai C, et al. Multisource electrohydraulic servo valve fault status diagnostic algorithm based on a message propagation mechanism[J]. Measurement Science and Technology, 2023, 34(5): 055302. [10] 陈雷. 某型电液伺服系统故障维修探析[J]. 现代制造技术与装备, 2020, 56(7): 168-169.Chen L. Analysis of fault maintenance of a certain electro-hydraulic servo system[J]. Modern Manufacturing Technology and Equipmen, 2020, 56(7): 168-169(in Chinese). [11] Shahkar S, Khorasani K. A multidimensional Bayesian methodology for diagnosis, prognosis, and health monitoring of electrohydraulic servo valves[J]. IEEE Transactions on Control Systems Technology, 2021, 30(3): 931-943. [12] 梁伟阁, 张钢, 王健, 等. 复杂机械设备健康状态预测方法研究综述[J]. 兵器装备工程学报, 2022, 43(7): 67-77.Liang W G, Zhang G, Wang J, et al. A review on health state assessment and remaining useful life prediction of mechanical equipment under intelligent manufacturinglJ]. Journal of Ordnance Equipment Engineering, 2022, 43(7): 67-77(in Chinese). [13] Vettoruzzo A, Bouguelia M R, Vanschoren J, et al. Advances and challenges in meta-learning: a technical review[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(7): 4763-4779. [14] Altaleb A, Chauveau D. Bayesian analysis of the Logit model and comparison of two Metropolis-Hastings strategies[J]. Computational Statistics & Data Analysis, 2002, 39(1): 137-152. [15] Roberts G, Rosenthal J. Optimal scaling for various Metropolis-Hastings algorithms[J]. Statistical Science, 2001, 6(4): 351-367. [16] Schölkopf B, Smola A, Müller K. Kernel principal component analysis[C]//Proceedings of the International Conference on Artificial Neural Networks. Berlin: Springer, 1997: 583-588. [17] Liu L, Liu J, Wang H, et al. A multivariate monitoring method based on kernel principal component analysis and dual control chart[J]. Journal of Process Control, 2023, 127: 102994. [18] 聂小辉, 金磊. 核主元分析在航天器飞轮自主故障诊断的应用[J]. 北京航空航天大学学报, 2023, 49(8): 2119-2128.Nie X H, Jin L. Application of kernel principal component analysis in autonomous fault diagnosis for spacecraft flywheel[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(8): 2119-2128(in Chinese). [19] Goyal N. Structure specified optimal robust H∞ loop shaping control of multivariable electro-hydraulic servo system using GA and PSO[J]. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 2015, 4(6): 4991-4998. [20] 卢红影, 李昌, 曲颖, 等. 电液伺服机构设计关键特性识别方法研究[J]. 重庆理工大学学报(自然科学), 2020, 34(4): 95-100.Lu H Y, Li C, Qu Y, et al. Study on key design characteristics identification method of electro-hydraulic servo mechanism[J]. Journal of Chongqing University of Technology (Natural Science), 2020, 34(4): 95-100(in Chinese). [21] 陈兴根, 潘骏, 陈文华, 等. 电液伺服机构故障树分析[J]. 机电工程, 2009, 26(4): 25-27.Chen X G, Pan J, Chen W H, et al. Fault tree analysis of electro-hydraulic servo mechanism[J]. Journal of Mechanical & Electrical Engineering, 2009, 26(4): 25-27(in Chinese). [22] Li J, Kong L, Liang H, et al. Review of development and characteristics research on electro-hydraulic servo system[J]. Recent Patents on Engineering, 2024, 18(6): 140-154. -
下载:
点击查看大图
计量
- 文章访问数: 356
- HTML全文浏览量: 166
- PDF下载量: 25
- 被引次数: 0
