基于BP神经网络算法的结构振动模态模糊控制

doi:10.6040/j.issn.1672-3961.0.2019.509

摘要/Abstract

摘要：

为了更合理、方便地控制土木工程结构地震动力反应,提出基于反向传播(back propagation, BP)神经网络的结构振动模态模糊控制算法。以结构地震动力反应数据训练神经网络建立结构分析模型,以时域模态坐标作为被控变量,实现系统降阶,使建立模态模糊控制规则所需要的模糊推理数量处于可接受范围内,并以体系能量最小作为控制目标制定控制规则。建立结构动力反应模糊控制数值模型,根据计算地震动力反应评价所提出算法的减震效果。结果表明:经过训练的BP神经网络可以准确地预测结构的地震动力反应,并可以据此建立模糊控制规则。仅对结构第一阶振型采用模态模糊控制就能达到满意的减震效果。采用主动质量驱动(active mass driver, AMD)最优控制力幅作为各楼层控制力的论域时,模态模糊控制减震效果与其存在差距;增大控制力的论域,可以得到更好的减震效果。

关键词: 神经网络, 状态变量, 模态模糊控制, 主振型, 层间位移

Abstract:

In order to control the seismic response of civil engineering structures more reasonably and conveniently, a fuzzy control algorithm based on BP neural network was proposed. The neural network was trained with the structural seismic dynamic response data to establish the structural analysis model, and the time-domain modal coordinates were taken as the controlled variables to reduce the order of the system, so that the number of fuzzy reasoning required to establish the modal fuzzy control rules was within the acceptable range, and the system energy minimum was taken as the control target to formulate the control rules. The fuzzy control numerical model of structural dynamic response was established to evaluate the damping effect of the proposed algorithm based on the calculated value of seismic dynamic response. The results showed that the trained BP neural network could accurately predict the seismic dynamic response of the structure and establish fuzzy control rules accordingly. Using mode fuzzy control only for the first mode of the structure could achieve satisfactory damping effect. When active mass driver(AMD) optimal control amplitude was used as the control domain of each floor, the damping effect of modal fuzzy control was different from it. A better damping effect could be obtained by increasing the control field.

Key words: neural network, state variables, fuzzy mode control, principle modes, inter-storey drift

中图分类号:

TU352.1

王志伟,葛楠,李春伟. 基于BP神经网络算法的结构振动模态模糊控制[J]. 山东大学学报 (工学版), 2020, 50(5): 13-19.

Zhiwei WANG,Nan GE,Chunwei LI. Fuzzy control of structure vibration mode based on BP neural network algorithm[J]. Journal of Shandong University(Engineering Science), 2020, 50(5): 13-19.

图/表 8

图1

图2

图3

图4

表1

图5

图6

图7

参考文献 19

1	欧进萍. 结构振动控制:主动,半主动,智能控制[M]. 北京: 北京科学出版社, 2003.
2	杨世浩, 瞿伟廉, 郑明燕. 用多种群遗传算法优化结构振动模糊控制器[J]. 武汉理工大学学报, 2004, 26 (10): 46- 48.
	YANG Shihao , QU Weilian , ZHENG Mingyan . Optimization of structural vibration fuzzy controller by multi-population Genetic algorithm[J]. Journal of Wuhan University of Technology, 2004, 26 (10): 46- 48.
3	HUNT K J , SHARBARO D , ZHIKOWSKI R , et al. Neural networks for control systems: a survey[J]. Automatica, 1992, 28 (6): 1083- 1112.
4	周其节, 徐建闽. 神经网络控制系统的研究与展望[J]. 控制理论与应用, 1992, 9 (6): 569- 577.
	ZHOU Qijie , XU Jianmin . Research and prospect of neural network control system[J]. Control Theory and Application, 1992, 9 (6): 569- 577.
5	阎石, 林皋, 黎海林. 人工神经网络在结构振动控制中应用[J]. 大连理工大学学报, 2000, 40 (9): 589- 592.
	YAN Shi , LIN Gao , LI Hailin . The application of artificial neural network in structural vibration control[J]. Journal of Dalian University of Technology, 2000, 40 (9): 589- 592.
6	王隆杰, 毛宗源. 利用神经网络进行推理的模糊控制器[J]. 控制理论与应用, 1994, 11 (4): 508- 512.
	WANG Longjie , MAO Zongyuan . Fuzzy controller using neural network for reasoning[J]. Control Theory and Application, 1994, 11 (4): 508- 512.
7	黄永安, 邓子辰. 基于瞬时最优控制神经网络的建筑结构主动控制研究[J]. 振动与冲击, 2005, (2): 5- 8.
	HUANG Yongan , DENG Zichen . Research on active control of building structure based on instantaneous optimal control neural network[J]. Vibration and Shock, 2005, (2): 5- 8.
8	汪权, 韩强强, 王肖东, 等. 地震作用下高层建筑结构的分散神经网络振动控制研究[J]. 计算力学学报, 2019, 36 (1): 77- 82.
	WANG Quan , HAN Qiangqiang , WANG Xiaodong , et al. Research on vibration control of high-rise building structures under earthquake action based on distributed neural network[J]. Journal of Computational Mechanics, 2019, 36 (1): 77- 82.
9	ZIZOUNI K , FALI L , SADEK Y , et al. Neural network control for earthquake structural vibration reduction using MRD[J]. Frontiers of Structural and Civil Engineering, 2019, 13 (5): 1171- 1182.
10	王耀南. 神经网络自适应模糊控制在温度控制系统中的应用[J]. 信息与控制, 1996, 25 (4): 245- 251.
	WANG Yaonan . Application of neural network adaptive fuzzy control in temperature control system[J]. Information and Control, 1996, 25 (4): 245- 251.
11	张志涌, 杨祖樱. MATLAB教程R2010a[M]. 北京: 北京航空航天大学出版社, 2011.
12	赵婷婷, 谭军, 金春峰. 谈时程分析中地震波的选取[J]. 山西建筑, 2017, 43 (14): 41- 43.
	ZHAO Tingting , TAN Jun , JIN Chunfeng . Discussion on selection of seismic wave in time history analysis[J]. Shanxi Architecture, 2017, 43 (14): 41- 43.
13	高建思, 王贵君. 基于三角形和高斯模糊化的Mamdani模糊系统表示[J]. 模糊系统与数学, 2018, 32 (2): 25- 31.
	GAO Jiansi , WANG Guijun . Representation of Mamdani fuzzy system based on triangle and gaussian fuzzification[J]. Fuzzy Systems and Mathematics, 2018, 32 (2): 25- 31.
14	宁响亮.结构振动控制的多目标优化和智能模糊控制[D].哈尔滨:哈尔滨工业大学, 2010.
	NING Xiangliang. Multi-objective optimization and intelligent fuzzy control for structural vibration control[D]. Harbin: Harbin University of Technology, 2010.
15	CLOUGH Way R , PENZIEN Joseph . Dynamics of structures[M]. London, United Kingdom: McGraw-Hill Inc, 1993.
16	葛楠, 苏幼坡, 王兴国, 等. 结构TMD控制及AMD最优控制减震效果计算研究[J]. 建筑科学, 2017, 33 (3): 7- 13.
	GE Nan , SU Youpo , WANG Xingguo , et al. Structural TMD control and AMD optimal control damping effect calculation[J]. Building Science, 2017, 33 (3): 7- 13.
17	王刚, 欧进萍. 基于系统特征响应的结构振动模糊控制规则建立与仿真分析[J]. 振动工程学报, 2002, 15 (1): 82- 85.
	WANG Gang , OU Jinping . The fuzzy control rules of structure vibration based on system characteristic response are established and simulated[J]. Journal of Vibration Engineering, 2002, 15 (1): 82- 85.
18	张微敬, 王学敏. 基于动态模糊神经网络的结构主动控制仿真分析[J]. 地震工程与工程振动, 2010, 30 (4): 132- 138.
	ZHANG Weijing , WANG Xuemin . Simulation analysis of structural active control based on dynamic fuzzy neural network[J]. Seismic Engineering and Engineering Vibration, 2010, 30 (4): 132- 138.
19	胡成宝, 王云岗, 凌道盛. 瑞利阻尼物理本质及参数对动力响应的影响[J]. 浙江大学学报(工学版), 2017, 51 (6): 1284- 1290.
	HU Chengbao , WANG Yungang , LING Daosheng . The influence of rayleigh damping physical essence and parameters on dynamic response[J]. Journal of Zhejiang University (Engineering Edition), 2017, 51 (6): 1284- 1290.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

楼层	模糊控制U_A=3				模糊控制U_A=7				无控制
楼层	层间位移/mm	层间位移减震效率/%	楼层加速度/(m·s^-2)	楼层加速度减震效率/%	层间位移/mm	层间位移减震效率/%	楼层加速度/(m·s^-2)	楼层加速度减震效率/%	层间位移/mm	楼层加速度/(m·s^-2)
1	19.81	16.13	2.88	-10.34	12.15	48.59	2.17	16.85	23.62	2.61
2	19.65	15.80	5.55	-8.53	12.11	48.13	4.05	20.79	23.34	5.12
3	19.40	15.15	7.86	-6.35	12.04	47.34	5.76	22.09	22.86	7.39
4	19.14	14.10	9.49	-0.83	11.97	46.31	7.31	22.35	22.28	9.42
5	18.92	12.53	10.62	6.57	11.82	45.33	7.70	32.19	21.63	11.36
6	18.63	10.57	11.08	14.08	11.52	44.71	7.36	42.92	20.84	12.90
7	18.55	6.48	11.54	17.56	11.11	44.00	8.50	39.25	19.83	13.99
8	18.38	1.15	11.88	19.14	10.69	42.50	10.42	29.07	18.59	14.69
9	18.02	-5.21	12.25	23.70	10.28	40.00	11.66	27.40	17.13	16.06
10	17.42	-11.92	12.52	27.46	9.83	36.85	12.21	29.25	15.57	17.25
11	16.56	-17.77	12.54	29.64	9.40	33.15	12.15	31.84	14.06	17.83
12	15.43	-18.63	13.67	23.01	9.01	30.71	11.89	33.03	13.01	17.75
13	14.07	-15.46	15.12	11.71	8.60	29.44	11.53	32.65	12.18	17.12
14	12.52	-10.82	16.27	-0.61	8.07	28.61	10.78	33.36	11.30	16.17
15	10.92	-6.49	17.16	-11.72	7.37	28.13	9.75	36.51	10.26	15.36
16	9.38	-4.21	17.79	-14.14	6.51	27.68	8.45	45.75	9.00	15.58
17	7.77	-3.28	18.16	-11.65	5.46	27.39	8.43	48.15	7.53	16.26
18	6.03	-3.21	18.47	-3.18	4.26	27.14	9.64	46.14	5.84	17.90
19	4.12	-3.33	19.48	-1.44	2.92	26.91	11.58	39.70	3.99	19.20
20	2.09	-3.43	20.24	-1.38	1.48	26.73	12.73	36.24	2.02	19.96

[1]	孙东磊,王艳,于一潇,韩学山,杨明,闫芳晴. 基于BP神经网络的短期光伏集群功率区间预测[J]. 山东大学学报 (工学版), 2020, 50(5): 70-76.
[2]	彭岩,冯婷婷,王洁. 基于集成学习的O₃的质量浓度预测模型[J]. 山东大学学报 (工学版), 2020, 50(4): 1-7.
[3]	蔡国永,贺歆灏,储阳阳. 基于空间注意力和卷积神经网络的视觉情感分析[J]. 山东大学学报 (工学版), 2020, 50(4): 8-13.
[4]	廖南星,周世斌,张国鹏,程德强. 基于类激活映射-注意力机制的图像描述方法[J]. 山东大学学报 (工学版), 2020, 50(4): 28-34.
[5]	李怡霏,郭尊华. 一种Chirplet神经网络自动目标识别算法[J]. 山东大学学报 (工学版), 2020, 50(3): 8-14.
[6]	金保明,卢光毅,王伟,杜伦阅. 基于弹性梯度下降算法的BP神经网络降雨径流预报模型[J]. 山东大学学报 (工学版), 2020, 50(3): 117-124.
[7]	宋士奇,朴燕,蒋泽新. 基于改进YOLOv3的复杂场景车辆分类与跟踪[J]. 山东大学学报 (工学版), 2020, 50(2): 27-33.
[8]	李春阳,李楠,冯涛,王朱贺,马靖凯. 基于深度学习的洗衣机异常音检测[J]. 山东大学学报 (工学版), 2020, 50(2): 108-117.
[9]	陈宁宁,赵建伟,周正华. 基于校正神经网络的视频追踪算法[J]. 山东大学学报 (工学版), 2020, 50(2): 17-26.
[10]	陈艳平,冯丽,秦永彬,黄瑞章. 一种基于深度神经网络的句法要素识别方法[J]. 山东大学学报 (工学版), 2020, 50(2): 44-49.
[11]	曹小洁,李小华,刘辉. 一类非仿射非线性大系统的结构在线扩展[J]. 山东大学学报 (工学版), 2020, 50(1): 35-48.
[12]	蔡国永,林强,任凯琪. 基于域对抗网络和BERT的跨领域文本情感分析[J]. 山东大学学报 (工学版), 2020, 50(1): 1-7,20.
[13]	杨巨成,韩书杰,毛磊,代翔子,陈亚瑞. 胶囊网络模型综述[J]. 山东大学学报 (工学版), 2019, 49(6): 1-10.
[14]	马川,刘彦呈,刘厶源,张勤进. 考虑未知死区非线性的自适应模糊神经UUV航迹跟踪控制[J]. 山东大学学报 (工学版), 2019, 49(3): 47-56.
[15]	郑店坤,许同乐,尹召杰,孟庆民. 改进PSO-BP神经网络对尾矿坝地下水位的预测方法[J]. 山东大学学报 (工学版), 2019, 49(3): 108-113.