基于BSO-ELM的涡轴发动机加速过程性能参数预测

doi:10.12305/j.issn.1001-506X.2021.08.20

摘要/Abstract

摘要：

建立精度和实时性均满足要求的航空发动机性能参数预测模型是实现发动机性能优化和实时监控的基础。极限学习机(extreme learning machine, ELM)对复杂的非线性航空发动机系统具有良好的适应性, 本文提出了利用头脑风暴优化算法(brain storm optimization, BSO)优化ELM的网络参数以提高其性能。并提出以发动机的台架试车加速过程数据为训练和验证样本, 利用BSO-ELM算法回归辨识得到涡轴发动机加速过程性能参数预测模型。结果表明预测参数燃气发生器转速n_g、燃气发生器出口温度T₄和增压比π_c的两项精度指标均优于BSO算法优化的反向传播神经网络和粒子群优化算法优化的ELM方法得到的预测模型, 表明了BSO-ELM预测模型的可行性与优越性; 在相同仿真环境下, BSO-ELM算法可大幅提高计算效率使预测模型的实时性更优。

关键词: 涡轴发动机, 加速过程, 头脑风暴优化算法, 极限学习机, 模型辨识, 性能参数预测

Abstract:

It is the basis of engine performance optimization and real-time monitoring to establish the prediction model of aeroengine performance parameters which can meet the requirements of both accuracy and real-time. Extreme learning machine (ELM) has good adaptability to the complex nonlinear aeroengine system. In this paper, a brain storm optimization (BSO) algorithm is proposed to optimize the network parameters of ELM for improving its performance. The acceleration process data of the engine on the bench test are used as training and verification samples, and the performance parameter prediction model of the turboshaft engine acceleration process is obtained by regression identification using BSO-ELM algorithm. The results show that the prediction parameters of output parameter gas generator speed n_g, gas generator outlet temperature T₄ and pressure ratio π_c are better than the prediction models obtained by backpropagation neural network optimized with BSO algorithm and ELM method optimized with particle swarm optimization, which indicates the feasibility and superiority of the BSO-ELM prediction model. In the same simulation environment, the BSO-ELM algorithm can greatly improve the computational efficiency and improve the real-time performance of the prediction model.

Key words: turboshaft engine, acceleration process, brain storm optimization, extreme learning machine, model identification, performance parameters prediction

中图分类号:

V231.3

董庆, 李本威, 闫思齐, 钱仁军. 基于BSO-ELM的涡轴发动机加速过程性能参数预测[J]. 系统工程与电子技术, 2021, 43(8): 2181-2188.

Qing DONG, Benwei LI, Siqi YAN, Renjun QIAN. Prediction of turboshaft engine acceleration process performance parameters based on BSO-ELM[J]. Systems Engineering and Electronics, 2021, 43(8): 2181-2188.

图/表 11

图1

图2

图3

表1

图4

图5

图6

表2

图7

表3

图8

参考文献 32

1	廉筱纯, 吴虎. 航空发动机原理[M]. 西安: 西北工业大学出版社, 2005.
	LIAN X C , WU H . Principle of aero engine[M]. Xi'an: Northwestern Polytechnical University Press, 2005.
2	韩文俊, 李家瑞, 王军. 基于实时模型的涡扇发动机加速供油规律设计方法[J]. 航空发动机, 2015, 41 (2): 5- 9.
	HAN W J , LI J R , WANG J , et al. Design method of fuel supply law for turbofan engien acceleration bsaed on a real-time model[J]. Aeroenign, 2015, 41 (2): 5- 9.
3	ASGARI H , VENTURINI M , CHEN X Q , et al. Modeling and simulation of the transient behavior of an industrial power plant gas turbine[J]. Journal of Engineering for Gas Turbines and Power, 2014, 136 (6): 061601. doi: 10.1115/1.4026215
4	郑斐华. 基于系统辨识的航空发动机建模研究[D]. 北京: 中国科学院大学, 2018.
	ZHENG F H. Aeroengine modeling research based on system identification[D]. Beijing: University of Chinese Academy of Sciences, 2018.
5	YU B , SHU W J , CAO C . A novel modeling method for aircraft engine using nonlinear autoregressive exogenous (NARX) models based on wavelet neural networks[J]. International Journal of Turbo & Jet-Engines, 2018, 35 (2): 161- 169.
6	ASGARI H , CHEN X Q , MENHAJ M B , et al. Artificial neural network-based system identification for a single-shaft gas turbine[J]. Journal of Engineering for Gas Turbines and Power, 2013, 135 (9): 169- 175.
7	王冠超, 杨春, 徐波, 等. 基于改进PSO-SVM参数优化的发动机起动过程辨识[J]. 燃气涡轮试验与研究, 2011, 24 (1): 35- 41. doi: 10.3969/j.issn.1672-2620.2011.01.007
	WANG G C , YANG C , XU B , et al. Engine start identification based on parameter optimization of improved PSO-SVM[J]. Gas Turbine Experiment and Research, 2011, 24 (1): 35- 41. doi: 10.3969/j.issn.1672-2620.2011.01.007
8	ZHOU D , ZHUANG X , ZUO H F , et al. Hazard identification and prediction system for aircraft electrical system based on SRA and SVM[J]. Proceedings of the Institution of Mechanical Engineers, 2020, 234 (4): 1014- 1026. doi: 10.1177/0954410019894121
9	BERGHOUT T , MOUSS L H , KADRI O , et al. Aircraft engines remaining useful life prediction with an improved online sequential extreme learning machine[J]. Applied Sciences, 2020, 10 (3): 1062. doi: 10.3390/app10031062
10	ZHANG S S , LEI D . A dynamic ensemble extreme learning machine model for aircraft engine health condition prediction[J]. Journal of Aerospace Power, 2014, 29 (9): 2085- 2090.
11	耿宏, 任道先, 杜鹏. 基于NARX神经网络航空发动机参数动态辨识模型[J]. 计算机工程与应用, 2017, 53 (12): 241- 248. doi: 10.3778/j.issn.1002-8331.1601-0268
	GENG H , REN D X , DU P . Dynamic parameter identification model of aircraft engine based on NARX neural network[J]. Computer Engineering and Applications, 2017, 53 (12): 241- 248. doi: 10.3778/j.issn.1002-8331.1601-0268
12	ZHENG Q G , ZHANG H B , LI Y J , et al. Aero-engine on-board dynamic adaptive MGD neural network model with-in a large flight envelope[J]. IEEE Access, 2018, 6, 45755- 45761. doi: 10.1109/ACCESS.2018.2789935
13	曹惠玲, 王冉. 基于滑动时窗策略自适应优化支持向量机的航空发动机性能参数在线预测[J]. 推进技术, 2020, 41 (8): 1887- 1894.
	CAO H L , WANG R . Adaptively optimized support vector machine onlineprediction of aeroengine performance parameters based on sliding time window strategy[J]. Journal of Propulsion Technology, 2020, 41 (8): 1887- 1894.
14	皮骏, 黄江博, 黄磊, 等. 基于改进QPSO-SVR的航空发动机排气温度预测[J]. 振动.测试与诊断, 2019, 39 (2): 267- 272, 440.
	PI J , HUANG J B , HUANG L , et al. Aeroengine exhaust gas temperature prediction based on IQPSO-SVR[J]. Journal of Vibration, Measurement & Diagnosis, 2019, 39 (2): 267- 272, 440.
15	HUANG G B , ZHOU H , ZHANG R , et al. Extreme learning machine for regression and multiclass classification[J]. IEEE Trans.on systems, man, and cybernetics, Part B. (Cybernetics), 2012, 42 (2): 513- 529. doi: 10.1109/TSMCB.2011.2168604
16	伍恒, 李本威, 张赟, 等. 基于QPSO-ELM的某型涡轴发动机起动过程模型辫识[J]. 航空学报, 2018, 39 (11): 178- 188.
	WU H , LI B W , ZHANG Y , et al. Dynamic model identification of starting process of aturbo-shaft engine based on QPSO-ELM[J]. Acta Aeronauticaet Astronautica Sinica, 2018, 39 (11): 178- 188.
17	DUAN M X , LI K L , YANG C Q , et al. A hybrid deep learning CNN-ELM for age and gender classification[J]. Neurocomputing, 2018, 275, 448- 461. doi: 10.1016/j.neucom.2017.08.062
18	XU Y , ZHANG M Q , YE L , et al. A novel prediction intervals method integrating an error and self-feedback extreme learning machine with particle swarm optimization for energy consumption robust prediction[J]. Energy, 2018, 164, 137- 146. doi: 10.1016/j.energy.2018.08.180
19	KARAMI H , KARIMI S , BONAKDARI H , et al. Predicting discharge coefficient of triangular labyrinth weir using extreme learning machine, artificial neural network and genetic programming[J]. Neural Computing and Applications, 2018, 29 (11): 983- 989. doi: 10.1007/s00521-016-2588-x
20	SHI Y H . An optimization algorithm based on brainstorming process[J]. International Journal of Swarm Intelligence Research, 2011, 2 (4): 35- 62. doi: 10.4018/ijsir.2011100103
21	CHENG S , QIN Q D , CHEN J F , et al. Brain storm optimization algorithm: a review[J]. Artificial Intelligence Review, 2016, 46 (4): 445- 458. doi: 10.1007/s10462-016-9471-0
22	吴亚丽, 付玉龙, 李国婷, 等. 高维多目标头脑风暴优化算法[J]. 控制理论与应用, 2020, 37 (1): 196- 207.
	WU Y L , FU Y L , LI G T . Many-objective brain storm optimization algorithm[J]. Control Theory and Applications, 2020, 37 (1): 196- 207.
23	周恒俊. 智能优化算法及其在图像检索中的应用研究[D]. 济南: 山东大学, 2016.
	ZHOU H J. Research on intelligent optimization algorithm and its application in image retrieval[D]. Jinan: Shandong University, 2016.
24	ASGARI H , CHEN X Q , MORINI M , et al. NARX models for simulation of the start-up operation of a single-shaft gas turbine[J]. Applied Thermal Engineering, 2015, 93, 368- 376.
25	樊思齐, 刘清波, 荣向军, 等. 利用飞行试验信号对发动机模型辨识的研究[J]. 航空学报, 1993, 14 (8): 399- 423.
	FAN S Q , LIU Q B , RONG X J . Identification investlgation of engine model using flight test signals[J]. Acta Aeronauticaet Astronautica Sinica, 1993, 14 (8): 399- 423.
26	陈山, 宋樱, 房胜男, 等. 基于头脑风暴优化算法的Wiener模型参数辨识[J]. 控制与决策, 2017, 32 (12): 2291- 2295.
	CHEN S , SONG Y , FANG S N , et al. Parameter identification of wiener systems using brain storm optimization algorithm[J]. Control and Decision, 2017, 32 (12): 2291- 2295.
27	LIU J A , PENG H , WU Z J , et al. Multi-strategy brain storm optimization algorithm with dynamic parameters adjustment[J]. Applied Intelligence, 2020, 50 (4): 1289- 1315. doi: 10.1007/s10489-019-01600-7
28	ZHANG W Q , ZHANG Y , PENG C . Brain storm optimization for feature selection using new individual clustering and updating mechanism[J]. Applied Intelligence, 2019, 49 (12): 4294- 4302. doi: 10.1007/s10489-019-01513-5
29	FIGUEIREDO E M N , LUDERMIR T B . Investigating the use of alternative topologies on performance of the PSO-ELM[J]. Neurocomputing, 2014, 12 (7): 4- 12.
30	李明军, 王均星, 王亚洲. 基于改进粒子群优化算法和极限学习机的混凝土坝变形预测[J]. 天津大学学报(自然科学与工程技术版), 2019, 52 (11): 1136- 1144.
	LI M J , WANG J X , WANG Y Z , et al. Deformation prediction of concrete dam based on improved particle swarm optimization algorithm and extreme learning machine[J]. Journal of Tianjin University(Science and Technology), 2019, 52 (11): 1136- 1144.
31	梁晓萍, 郭振军, 朱昌洪. 基于头脑风暴优化算法的BP神经网络模糊图像复原[J]. 电子与信息学报, 2019, 41 (12): 2980- 2986. doi: 10.11999/JEIT190261
	LIANG X P , GUO Z J , ZHU C H , et al. BP neural network fuzzy image restoration based on brain storming optimization algorithm[J]. Journal of Electronics & Information Technology, 2019, 41 (12): 2980- 2986. doi: 10.11999/JEIT190261
32	PENG J , LI P Z . Research and application of a new hybrid wind speed forecasting model on BSO algorithm[J]. Journal of Energy Engineering, 2017, 143 (1): 04016019. doi: 10.1061/(ASCE)EY.1943-7897.0000362

绝对时间	样本参数
绝对时间	T₀/℃	W_f/(L·h^-1)	q_*_ma/(kg·s^-1)	n_g/%	T₄/℃	π_c/%
8:34:10.062	12.774	162.996	2.981	60.191	436.663	2.174
8:34:10.362	12.773	164.567	2.967	60.272	438.068	2.179
8:38:01.062	12.511	226.499	4.451	75.149	448.180	3.274

预测参数	精度指标
	第1验证组		第2验证组		第3验证组
	A	B	A	B	A	B
n_g/%	0.126	0.19	0.152	0.25	0.165	0.32
T₄/℃	0.722	0.16	2.833	0.64	1.351	0.31
π_c/%	0.004 6	0.17	0.005 9	0.21	0.006 2	0.24

精度指标	算法
精度指标	BSO-ELM	PSO-ELM	BSO-BP
A	0.163	0.985	1.64
B	0.31	1.09	1.97

[1]	高永琪, 马威强, 张林森, 王鹏, 赵苗. 分布式多AUV协同搜索方法[J]. 系统工程与电子技术, 2022, 44(5): 1670-1676.
[2]	杨占刚, 徐海义, 成博源, 石旭东. 基于FWA-DBN的航空发电机偏心故障诊断[J]. 系统工程与电子技术, 2022, 44(5): 1757-1764.
[3]	张捷, 杨丽花, 聂倩. 新型的基于堆栈式ELM的时变信道预测方法[J]. 系统工程与电子技术, 2022, 44(2): 662-667.
[4]	马威强, 高永琪, 赵苗. 基于全局最优和差分变异的头脑风暴优化算法[J]. 系统工程与电子技术, 2022, 44(1): 270-278.
[5]	史朝卫, 孟相如, 康巧燕, 苏玉泽. 基于混合流量预测的虚拟网络拓扑重构方法[J]. 系统工程与电子技术, 2021, 43(5): 1382-1388.
[6]	杨凌, 程丽, 韩琴, 赵傲男. 基于卡尔曼滤波的极限学习机在线盲均衡算法[J]. 系统工程与电子技术, 2021, 43(3): 623-630.
[7]	王坤, 侯树贤, 王力. 基于自适应变异PSO-SVM的APU性能参数预测模型[J]. 系统工程与电子技术, 2021, 43(2): 526-536.
[8]	方浩, 李艾华, 潘玉龙, 王学进, 何川, 吴元江. 基于自学习框架的红外场景仿真效果评价[J]. 系统工程与电子技术, 2019, 41(2): 266-272.
[9]	时维国, 许超. 基于相空间重构与鲁棒极限学习机的时延预测[J]. 系统工程与电子技术, 2019, 41(2): 416-421.
[10]	徐西蒙, 杨任农, 符颖, 赵雨. 基于ELM_AdaBoost强预测器的空战目标威胁评估[J]. 系统工程与电子技术, 2018, 40(8): 1760-1768.
[11]	张东东, 孙锐, 高隽. 基于极限学习机和boosting多核学习的目标跟踪算法[J]. 系统工程与电子技术, 2017, 39(9): 2149-2156.
[12]	杜占龙, 李小民, 席雷平, 张金中, 刘新海. 多分类概率极限学习机及其在剩余使用寿命预测中的应用[J]. 系统工程与电子技术, 2015, 37(12): 2777-2784.
[13]	于湘涛，魏超，武志忠，张兰，刘松. 基于PSVR的加速度计组合温控系统被控对象建模[J]. 系统工程与电子技术, 2014, 36(9): 1833-1837.
[14]	张文博，姬红兵，王磊，朱明哲. 多隐层输出矩阵极限学习机[J]. 系统工程与电子技术, 2014, 36(8): 1656-1659.
[15]	邓科，丛爽，孔德杰，沈宏海，尚伟伟. 陀螺稳定平台中速度环的非线性实验建模[J]. Journal of Systems Engineering and Electronics, 2013, 35(4): 807-811.