基于改进ELM-Markov Model的建筑结构稳定性监测算法

doi:10.13229/j.cnki.jdxbgxb.20230783

摘要/Abstract

摘要：

针对结构稳定性直接影响建筑安全的问题，提出了基于改进ELM-Markov Model的建筑结构稳定性监测算法，首先，通过S变换获取建筑结构加速度信号时频图，采用灰度共生矩阵获取加速度信号时频图纹理特征，结合类内和类间散布矩阵生提取敏感特征向量；然后，结合极限学习机（ELM）和马尔科夫模型（Markov Model）构建ELM-Markov Model，对ELM的拟合误差进行Markov状态划分和误差预测，修正ELM预测值，再引入改进的灰狼算法寻优ELM-Markov Model状态数；最后，将敏感特征向量输入优化后的ELM-Markov Model中，实现建筑结构稳定性监测。实验结果表明：本文方法监测误差较小、鲁棒性较强、效率较高。

关键词: 极限学习机, 马尔科夫模型, 建筑结构, 稳定性监测, S变换

Abstract:

A building structure stability monitoring algorithm based on the improved ELM-Markov Model is proposed to address the direct impact of structural stability on building safety. Firstly， the time-frequency map of the building structure acceleration signal is obtained through the S-transform， and the texture features of the acceleration signal time-frequency map are obtained using the gray level co-occurrence matrix. Sensitive feature vectors are extracted by combining the intra class and inter class scatter matrices， Then， ELM Markov Model is constructed by combining Extreme learning machine （ELM） and Markov Model， and the fitting error of ELM is divided into Markov state and predicted by error， and the predicted value of ELM is revised. Then， the improved gray wolf algorithm is introduced to optimize the state number of ELM Markov Model. Finally， the sensitive feature vector is input into the optimized ELM Markov Model to realize the stability monitoring of building structures. The experimental results show that the proposed method has small monitoring error， strong robustness， and high efficiency.

Key words: extreme learning machine, Markov model, building structure, stability monitoring, S transformation

中图分类号:

TP312

刘义艳,刘兴,刘方方,代杰. 基于改进ELM-Markov Model的建筑结构稳定性监测算法[J]. 吉林大学学报(工学版), 2024, 54(11): 3351-3357.

Yi-yan LIU,Xing LIU,Fang-fang LIU,Jie DAI. Building structure stability monitoring algorithm based on improved ELM-Markov Model[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(11): 3351-3357.

图/表 5

图1

表1

图2

图3

图4

参考文献 15

1	丁俊华, 蔡继明. 现行土地制度对我国城市化进程的制约及因应之策[J]. 河南大学学报: 社会科学版, 2022, 62(1): 14-20.
	Ding Jun-hua, Cai Ji-ming. The constraints of the current land system on China´s urbanization process and the corresponding solutions[J]. Journal of Henan University (Social Science Edition), 2022, 62(1): 14-20.
2	丑亚玲, 刘文高, 乔雄, 等. 基于交通振动环境下建筑结构损伤机理及减振隔振的研究现状[J]. 地震工程学报, 2021, 43(3): 654-662.
	Ya-ling Chou, Liu Wen-gao, Qiao Xiong, et al. Research status of damage mechanism of building structures and associated vibration reduction and isolation in traffic vibration environment[J]. China Earthquake Engineering Journal, 2021, 43(3): 654-662.
3	刘宜昭, 陆阳, 刘松玉. 改性水泥土墙隔离重金属污染的服役时间分析研究[J]. 岩土工程学报, 2023, 45(4): 785-795.
	Liu Yi-zhao, Lu Yang, Liu Song-yu. Breakthrough time of amended cement-soil cutoff wall permeated by heavy metal solutions[J]. Chinese Journal of Geotechnical Engineering, 2023, 45(4): 785-795.
4	刘洋, 刘冲, 王丽霞. 基于小波包变换的框架剪力墙结构健康监测研究[J]. 工业建筑, 2022, 52(10): 211-218.
	Liu Yang, Liu Chong, Wang Li-xia. Research on health monitoring of frame shear wall structures based on wavelet packet transform[J]. Industrial Building, 2022, 52(10): 211-218.
5	谭颖轩, 陈衍茂, 汪利, 等. 基于模态修正策略和稀疏正则化的损伤识别[J]. 中山大学学报: 自然科学版, 2022, 61(3): 116-122.
	Tan Ying-xuan, Chen Yan-mao, Wang Li, et al. Damage identification using modal changes correction strategy and sparse regularization[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2022, 61(3): 116-122.
6	张帆, 杨晓忠, 吴立飞, 等. 基于短时傅里叶变换和卷积神经网络的地震事件分类[J]. 地震学报, 2021, 43(4): 463-473.
	Zhang Fan, Yang Xiao-zhong, Wu Li-fei, et al. Classification of seismic events based on short-time fourier transform and convolutional neural network[J]. Acta Seismologica Sinica, 2021, 43(4): 463-473.
7	刘宝稳, 汤容川, 马钲洲, 等. 基于S变换D-SVM AlexNet模型的GIS机械故障诊断与试验分析[J]. 高电压技术, 2021, 47(7): 2526-2538.
	Liu Bao-wen, Tang Rong-chuan, Ma Zheng-zhou, et al. GIS mechanical fault diagnosis and test analysis based on S transform D-SVM AlexNet model[J]. High Voltage Engineering, 2021, 47(7): 2526-2538.
8	高树国, 王丽丽, 田源, 等. 基于振动时频信号灰度共生矩阵的有载分接开关触头状态检测方法研究[J]. 电工电能新技术, 2022, 41(1): 69-77.
	Gao Shu-guo, Wang Li-li, Tian Yuan, et al. Research on condition monitoring of contacts in on-load tap changer based on gray level co-occurrence matrix of time-frequency vibration signal[J]. Advanced Technology of Electrical Engineering and Energy, 2022, 41(1): 69-77.
9	王小娟, 胡兵, 马燕, 等. 基于极限学习机的输水管网暗漏预测方法研究[J]. 计算机仿真, 2022, 39(10): 506-510.
	Wang Xiao-juan, Hu Bing, Ma Yan, et al. Research on prediction method of hidden leakage in water transmission network based on extreme learning machine[J]. Computer Simulation, 2022, 39(10): 506-510.
10	刘英英, 杨光, 姚灿江, 等. 基于马尔科夫模型的三工位系统的可靠性分析[J]. 高压电器, 2021, 57(9): 80-86.
	Liu Ying-ying, Yang Guang, Yao Can-jiang, et al. Reliability analysis of the three-position system based on markov model[J]. High Voltage Apparatus, 2021, 57(9): 80-86.
11	徐浩然, 王勇军, 黄志坚, 等. 基于前馈神经网络的编译器测试用例生成方法[J]. 软件学报, 2022, 33(6): 1996-2011.
	Xu Hao-ran, Wang Yong-jun, Huang Zhi-jian, et al. Compiler fuzzing test case generation with feed-forward neural network[J]. Journal of Software, 2022, 33(6): 1996-2011.
12	陈昊, 鞠昱, 韩立, 等. 相对误差最小二乘法的TDLAS气体浓度标定曲线拟合[J]. 光谱学与光谱分析, 2021, 41(5): 1580-1585.
	Chen Hao, Ju Yu, Han Li, et al. Curve fitting of TDLAS gas concentration calibration based on relative error least square method[J]. Spectroscopy and Spectral Analysis, 2021, 41(5): 1580-1585.
13	崔靖凯, 赛华阳, 张恩阳, 等. 基于灰狼算法的模块化关节摩擦辨识和补偿[J]. 光学精密工程, 2021, 29(11): 2683-2691.
	Cui Jing-kai, Hua-yang Sai, Zhang En-yang, et al. Identification and compensation of friction for modular joints based on grey wolf optimizer[J]. Optics and Precision Engineering, 2021, 29(11): 2683-2691.
14	李凯, 任炳昱, 关涛, 等. 帷幕灌浆量区间预测的Bootstrap-IGWO-SVM模型研究[J]. 水力发电学报, 2022, 41(10): 18-29.
	Li Kai, Ren Bing-yu, Guan Tao, et al. Curtain grouting cement interval prediction using Bootstrap-IGWO-SVM model[J]. Journal of Hydroelectric Engineering, 2022, 41(10): 18-29.
15	王风云, 丛龙园. 基于灰色模型的可再生能源电价补贴收支平衡[J]. 资源科学, 2021, 43(9): 1743-1751.
	Wang Feng-yun, Cong Long-yuan. Revenue and expenditure balance of renewable energy electricity price subsidies based on grey model[J]. Resources Science, 2021, 43(9): 1743-1751.

相关文章 15

[1]	高欣,何舰,兰春光,王泽强. 斜撑布设方案对高支模抗倒塌性能的影响[J]. 吉林大学学报(工学版), 2024, 54(6): 1657-1664.
[2]	邸振勇,杨新辉. 地震后建筑结构层间变形特征分布[J]. 吉林大学学报(工学版), 2024, 54(5): 1377-1384.
[3]	李博,李欣,芮红,梁媛. 基于变分模态分解和灰狼优化极限学习机的隧道口边坡位移预测[J]. 吉林大学学报(工学版), 2023, 53(6): 1853-1860.
[4]	李健,熊琦,胡雅婷,刘孔宇. 基于Transformer和隐马尔科夫模型的中文命名实体识别方法[J]. 吉林大学学报(工学版), 2023, 53(5): 1427-1434.
[5]	陈俊,王韶纤,胥卉,莫端泉,霍静思,邓旭华. 负弯矩作用下可拆卸预制装配式组合梁力学性能试验[J]. 吉林大学学报(工学版), 2022, 52(3): 604-614.
[6]	王进花,胡佳伟,曹洁,黄涛. 基于自适应变分模态分解和集成极限学习机的滚动轴承多故障诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 318-328.
[7]	许鸿奎,姜彤彤,李鑫,姜斌祥,王永雷. 结合降噪自编码与极限学习机的LTE上行干扰分析[J]. 吉林大学学报(工学版), 2022, 52(1): 195-203.
[8]	周炳海,何朝旭. 基于线边集成超市的混流装配线动态物料配送调度[J]. 吉林大学学报(工学版), 2020, 50(5): 1809-1817.
[9]	董颖, 崔梦瑶, 吴昊, 王雨后. 基于能量预测的分簇可充电无线传感器网络充电调度[J]. 吉林大学学报(工学版), 2018, 48(4): 1265-1273.
[10]	黄辉, 冯西安, 魏燕, 许驰, 陈慧灵. 基于增强核极限学习机的专业选择智能系统[J]. 吉林大学学报(工学版), 2018, 48(4): 1224-1230.
[11]	尼颖升, 孙启鑫, 马晔, 徐栋. 基于拉应力域的波形钢腹板组合梁承载力配筋计算[J]. 吉林大学学报(工学版), 2018, 48(1): 148-158.
[12]	高振海, LeDinhDat, 胡宏宇, 孙翊腾. 驾驶员无意识车道偏离识别方法[J]. 吉林大学学报(工学版), 2017, 47(3): 709-716.
[13]	张彦玲, 孙瞳, 侯忠明, 李运生. 隔板式钢-混凝土曲线组合梁弯扭性能[J]. 吉林大学学报(工学版), 2015, 45(4): 1107-1114.
[14]	王春刚, 张壮南, 赵大千, 曹宇飞. 腹板开孔Σ形复杂卷边槽钢轴压承载力试验[J]. 吉林大学学报(工学版), 2015, 45(3): 788-796.
[15]	李海锋，郭小农，罗永峰，高轩能. 索支撑柔性摩天轮结构抗倒塌性能分析[J]. 吉林大学学报(工学版), 2015, 45(2): 406-413.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

参数	梁	柱
材质	空钢管	薄钢板
截面尺寸/mm	25×25×2.5	25×4.5
体密度度/（kg·m^-3）	7 850	7 850
杨氏模量/Pa	206×10⁹	206×10⁹
惯性矩/m⁴	2.17×10^-8	2.03×10^-8