2022年 05期

基于改进支持向量机的飞机空气循环系统仿真模型及故障分析

Simulation Model and Fault Analysis of Aircraft Air Circulation Systems Based on Improved Support Vector Machine


摘要(Abstract):

为了有效地识别飞机空气循环系统组件是否发生故障,区分故障类型,并作出对应的维修策略,提出一种基于改进支持向量机的飞机空气循环系统故障诊断方法;首先建立飞机空气循环系统仿真模型,然后将支持向量机运用于飞机空气循环系统,引入蚱蜢优化算法、位置随机偏移机制和模拟退火算法,对支持向量机进行参数优化,最后参考最优参数对飞机空气循环系统仿真模型进行训练。结果表明,建立的飞机空气循环系统仿真模型可以模拟不同情况下飞机空气循环系统主要组件的出口温度以及故障发生时的出口状态,加入蚱蜢优化算法等优化方式的支持向量机系统达到了简化调节参数、加快收敛、提高收敛精度的目的,可以根据多样本数据进行训练,完成故障分析。

关键词(KeyWords): 空气循环系统控制;故障分析;支持向量机;参数优化

基金项目(Foundation): 国家自然科学基金项目(62073157)

作者(Author):吴会咏,靳舒春,金铸

DOI: 10.13349/j.cnki.jdxbn.20220526.002

参考文献(References):

[1] 杨燕辉.飞机引气系统的建模与故障机理研究[D].天津:中国民航大学,2013.

[2] 石旭东,蒋贵嘉,张宇,等.基于联合仿真的飞机空调系统故障影响[J].航空学报,2020,41(8):295-303.

[3] 钞迪.飞机温度控制系统故障模拟与影响分析[D].天津:中国民航大学,2019.

[4] SUN J Z,WANG F Y,NING S G.Aircraft air conditioning system health state estimation and prediction for predictive maintenance[J].Chinese Journal of Aeronautics,2020,33(3):947-955.

[5] 耿振翔,王利辉,刘慎洋,等.基于TRNSYS的飞机空调保障装备送风特性仿真研究[J].数学的实践与认识,2019,49(9):117-123.

[6] 曹国刚,李梦雪,陈颖,等.改进支持向量机分类方法及其在原发性肝癌筛查中的应用[J].应用科学学报,2021,39(3):481-494.

[7] 赵楠,李洁.基于LSTM-SVM的隧道围岩位移预测[J].公路,2021,66(6):404-407.

[8] 宫毓斌,滕欢.基于GOA-SVM的短期负荷预测[J].电测与仪表,2019,56(14):12-16.

[9] 亓晓燕,刘恒杰,侯秋华,等.融合LSTM和SVM的钢铁企业电力负荷短期预测[J].山东大学学报(工学版),2021,51(4):91-98.

[10] VELáSQUEZ R M A.Support vector machine and tree models for oil and Kraft degradation in power transformers[J].Engineering Failure Analysis,2021,127:105488.

[11] AHMED N,RABBI S,RAHMAN T,et al.Traffic sign detection and recognition model using support vector machine and histogram of oriented gradient[J].International Journal of Information Technology and Computer Science,2021,13(3):61-73.

[12] 马婷婷,杨志霞,叶俊佑.鲁棒双参数化间隔支持向量机[J].计算机工程与应用,2022,58(9):74-82

[13] LAMESKI P,ZDRAVEVSKI E,MINGOV R,et al.SVM parameter tuning with grid search and its impact on reduction of model over-fitting[C]// Rough Sets,Fuzzy Sets,Data Mining,and Granular Computing:Vol 9437.Cham:Springer,2015:464-474.

[14] DO T N,POULET F.Parallel learning of local SVM algorithms for classifying large datasets[C]//Transactions on Large-Scale Data- and Knowledge-Centered Systems:Volume 10140.Berlin:Springer,2017:67-93.

[15] SAREMI S,MIRJALILI S,LEWIS A.Grasshopper optimisation algorithm:theory and application[J].Advances in Engineering Software,2017,105:30-47.

[16] WANG Z Y,YAO L G,CAI Y W.Rolling bearing fault diagnosis using generalized refined composite multiscale sample entropy and optimized support vector machine[J].Measurement,2020,156:107574.

[17] GU P,FENG Y Z,ZHU L,et al.Unified classification of bacterial colonies on different agar media based on hyperspectral imaging and machine learning[J].Molecules,2020,25(8):1797.

[18] SAYED G I,SOLIMAN M,HASSANIEN A E.Modified optimal foraging algorithm for parameters optimization of support vector machine[C]//The International Conference on Advanced Machine Learning Technologies and Applications (AMLTA2018),February 22-24,2018,Cairo,Egypt:Vol 723.Cham:Springer,2018:23-32.

[19] WU K P,WANG S D.Choosing the kernel parameters for support vector machines by the inter-cluster distance in the feature space [J].Pattern Recognition,2009,42(5):710-717.

[20] QIN H S,WEI Y,ZENG S H.Parameter optimization for SVM classification based on NGA[C]//Proceedings of the International Conference on Information Engineering and Applications (IEA) 2012,October 26-28,2012,Chongqing,China:Vol 216.London:Springer,2013:579-586.

[21] 周伟,谢利娟,杨晗,等.基于高光谱的三江源区土壤有机质含量反演[J].土壤通报,2021,52(3):564-574.

[22] 张育凡.基于蚱蜢优化和最小二乘支持向量机的电力负荷预测研究[D].兰州:兰州大学,2018.

[23] 王生生,张伟,董如意,等.改进蚱蜢算法在电动汽车充换电站调度中的应用[J].东北大学学报(自然科学版),2020,41(2):170-175.

[24] 崔东文,郭荣.基于GOA-PP模型的区域水资源红黄绿分区管理识别[J].华北水利水电大学学报(自然科学版),2018,39(1):68-76.

[25] 吕赵明,张颖江.基于改进GOA-SVM算法的异常流量识别[J].湖南科技大学学报(自然科学版),2019,34(4):90-96.