Performance degradation modeling of oxygen concentrators based on FCM-ARIMAX approach
-
摘要:
氧气浓缩器是构成飞机生命保障系统的重要机载部分，其性能退化数据具有多变量、强噪声等特点。针对氧气浓缩器寿命预测中存在单变量信息少、预测精度低的问题，考虑多维退化变量间的相关性筛选合适变量，通过在氧分压变量中引入影响因素氧体积分数，结合Hodrick Prescott (HP)滤波提取序列中的长期趋势，利用模糊C均值(FCM)方法对氧分压进行分段处理，建立多阶段动态回归模型。对氧气浓缩器进行退化建模，结果表明：与单变量的自回归滑动平均(ARIMA)模型、单阶段多变量ARIMA模型、多阶段动态回归模型相比，结合HP滤波的多变量ARIMA模型预测精度分别平均提升了98.20%、81.21%和77.87%。
Abstract:The oxygen concentrator is an important airborne part of the aircraft life support system, and its performance degradation data has the characteristics of multivariate and strong noise. In order to solve the problem of lack of univariate information and low prediction accuracy in the prediction of oxygen concentrator life, the correlation between multi-dimensional degradation variables was considered to select suitable variables. By introducing the influencing factor of oxygen concentration into the oxygen partial pressure variable, the long-term trend in the sequence was extracted with the Hodrick Prescott (HP) filter, and the fuzzy C-means (FCM) method was used to stage the oxygen partial pressure to establish a multi-stage dynamic regression model. Modeling the degradation of an oxygen concentrator. The findings indicate that the multivariate autoregressive integrated moving average (ARIMA) model with HP filtering improves prediction accuracy by 98.20%, 81.21%, and 77.87%, respectively, when compared to the univariate ARIMA model, single-stage multivariate ARIMA model, and multi-stage dynamic regression model.
-
Key words:
- degradation modeling /
- oxygen concentrator /
- health factor /
- fuzzy C-means /
- multi-stage model
-
图 1 氧气浓缩器退化试验硬件连接
Figure 1. Hardware connection of oxygen concentrator degradation test
图 3 氧气浓缩器退化数据全寿命时序
Figure 3. Lifetime sequence of oxygen concentrator degradation data
图 4 不同输入压力氧分压时序
Figure 4. Time series of oxygen partial pressure at different input pressures
图 5 不同输入压力氧体积分数时序
Figure 5. Time series of oxygen concentration at different input pressures
图 6 氧分压健康因子时序
Figure 6. Time series of health indicators based on oxygen partial pressure
图 7 氧体积分数健康因子时序
Figure 7. Time series of health indicators based on oxygen concentration
表 1 模型对比
Table 1. Model comparison
方法 RMSE ARIMA 3.113 ARIMAX 0.298 HP-ARIMA 0.247 HP-ARIMAX 0.180 FCM-ARIMAX(第1阶段) 0.350 FCM-ARIMAX(第2阶段) 0.164 FCM-ARIMAX(第3阶段) 0.188 HP-FCM-ARIMAX(第1阶段) 0.087 HP-FCM-ARIMAX(第2阶段) 0.055 HP-FCM-ARIMAX(第3阶段) 0.011 
下载: 导出CSV
-
[1] 杨立乾, 赵金楼, 李根. 基于性能退化的船舶关键部件视情维修策略[J]. 哈尔滨工程大学学报, 2020, 41(4): 613-618.Yang L Q, Zhao J L, Li G. Condition-based maintenance strategy for critical ship components based on performance degradation[J]. Journal of Harbin Engineering University, 2020, 41(4): 613-618(in Chinese). [2] Dhariyal B, Le Nguyen T, Ifrim G. Scalable classifier-agnostic channel selection for multivariate time series classification[J]. Data Mining and Knowledge Discovery, 2023, 37(2): 1010-1054. [3] Zhai Q Q, Ye Z S. A multivariate stochastic degradation model for dependent performance characteristics[J]. Technometrics, 2023, 65(3): 315-327. [4] 孔雪峰, 潘骏, 钱萍, 等. 机械产品多变量相依退化建模方法研究综述[J]. 机械工程学报, 2023, 59(20): 470-488.Kong X F, Pan J, Qian P, et al. Review of multivariate dependent degeneration modeling methods for mechanical products[J]. Journal of Mechanical Engineering, 2023, 59(20): 470-488(in Chinese). [5] Li X G, Xue P. Multivariate storage degradation modeling based on copula function[J]. Advances in Mechanical Engineering, 2014, 6: 503407. [6] Peng W W, Li Y F, Mi J H, et al. Reliability of complex systems under dynamic conditions: a Bayesian multivariate degradation perspective[J]. Reliability Engineering & System Safety, 2016, 153: 75-87. [7] Barraza-Barraza D, Tercero-Gómez V G, Beruvides M G, et al. An adaptive ARX model to estimate the RUL of aluminum plates based on its crack growth[J]. Mechanical Systems and Signal Processing, 2017, 82: 519-536. [8] Sun F Q, Liu J C, Li X Y, et al. Reliability analysis with multiple dependent features from a vibration-based accelerated degradation test[J]. Shock and Vibration, 2016, 2016: 2315916. [9] Song S L, Coit D W, Feng Q M, et al. Reliability analysis for multi-component systems subject to multiple dependent competing failure processes[J]. IEEE Transactions on Reliability, 2014, 63(1): 331-345. [10] Zhang J X, Hu C H, He X, et al. A novel lifetime estimation method for two-phase degrading systems[J]. IEEE Transactions on Reliability, 2019, 68(2): 689-709. [11] Li Z X, Wu D Z, Hu C, et al. An ensemble learning-based prognostic approach with degradation-dependent weights for remaining useful life prediction[J]. Reliability Engineering & System Safety, 2019, 184: 110-122. [12] Xiao Y C, Hua Z. Misalignment fault prediction of wind turbines based on combined forecasting model[J]. Algorithms, 2020, 13(3): 56. [13] Wang C S, Lu N Y, Cheng Y H, et al. A data-driven aero-engine degradation prognostic strategy[J]. IEEE Transactions on Cybernetics, 2021, 51(3): 1531-1541. [14] Zhang J X, Si X S, Du D B, et al. Lifetime estimation for multi-phase deteriorating process with random abrupt jumps[J]. Sensors, 2019, 19(6): 1472. [15] 刘君强, 胡东斌, 潘春露, 等. 基于超统计的多阶段航空发动机剩余寿命预测[J]. 北京航空航天大学学报, 2021, 47(1): 56-64.Liu J Q, Hu D B, Pan C L, et al. Remaining useful life prediction of multi-stage aero-engine based on super statistics[J]. Journal of Beijing University of Aeronautics and Astronautics, 2021, 47(1): 56-64(in Chinese). [16] Feng J, Kvam P, Tang Y Z. Remaining useful lifetime prediction based on the damage-marker bivariate degradation model: a case study on lithium-ion batteries used in electric vehicles[J]. Engineering Failure Analysis, 2016, 70: 323-342. [17] Tique S, Noureen S, Roy V, et al. Forecasting of total daily solar energy generation using ARIMA: a case study[C]//Proceedings of the 2019 IEEE 9th Annual Computing and Communication Workshop and Conference. Piscataway: IEEE Press, 2019: 114-119. [18] 潘晋新, 景博, 焦晓璇, 等. 多应力耦合条件下氧气浓缩器退化建模[J]. 北京航空航天大学学报, 2023, 49(2): 472-481.Pan J X, Jing B, Jiao X X, et al. Degradation modeling of oxygen concentrator in multiple stress coupling condition[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(2): 472-481(in Chinese). [19] 李娟, 景博, 羌晓清, 等. 基于样本分位数的机载燃油泵故障状态特征提取及实验研究[J]. 航空学报, 2016, 37(9): 2851-2863.Li J, Jing B, Qiang X Q, et al. Fault states feature extraction and experimental study for airborne fuel pumps based on sample quantile[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(9): 2851-2863(in Chinese). [20] Choudhary M, Ali M, Hanif M N, et al. On smoothing macroeconomic time series using the modified HP filter[J]. Applied Economics, 2014, 46(19): 2205-2214. [21] Enders W. Applied econometric time series[M]. 4th ed. Hoboken: Wiley, 2015: 305-306. [22] 黄崧琳, 景博, 潘晋新, 等. 基于退化阶段识别与LSTM-fine-tune的氧气浓缩器多阶段退化预测[J]. 电子测量与仪器学报, 2022, 36(7): 136-143.Huang S L, Jing B, Pan J X, et al. Multistage degradation prediction of oxygen concentrator based on degradation pattern recognition and LSTM-fine-tune[J]. Journal of Electronic Measurement and Instrumentation, 2022, 36(7): 136-143(in Chinese). -
下载:
点击查看大图
计量
- 文章访问数: 206
- HTML全文浏览量: 111
- PDF下载量: 19
- 被引次数: 0
