Vol. 22, No. 3, pp. 263-274 (2026)
MEASUREMENT POINT OPTIMIZATION METHOD FOR
LARGE-SPAN SPACE STRUCTURES BASED ON STRUCTURAL
RESPONSE CORRELATION
Ren-Zhang Yan 1, *, Wei Liu 1, Yang Liu 2, Chun-Ling Yan 1 and Tao Zhu 1
1 School of Civil Engineering, Chongqing Jiaotong University, Chongqing 400074, China
2 The 9th Engineering Co., Ltd. of CCCC First Highway Engineering Co., Ltd., Guangzhou 510000, China
*(Corresponding author: E-mail:This email address is being protected from spambots. You need JavaScript enabled to view it.)
Received: 20 February 2025; Revised: 4 August 2025; Accepted: 18 August 2025
DOI:10.18057/IJASC.2026.22.3.2
 View Article |
Export Citation: Plain Text | RIS | Endnote |
ABSTRACT
The mechanical properties of large-span space structures are complicated and change greatly during its construction. So it is necessary to monitor the real time status of the structure to ensure the safety of the construction process. However, the number of monitoring points is often very large due to the space structure’s large number of members and three-dimensional forcing characteristics. An optimization method for reducing monitoring points is proposed based on the characteristics of certain correlation between different members’ mechanical responses during construction in this paper. Firstly, the comprehensive correlation matrix of structural response was established by using correlation coefficient method and grey correlation degree method, and the cluster correlation matrix with block characteristics was calculated by the bond energy algorithm, so as to construct the classification and optimization principle of reducing measuring points. Then, LSTM neural network was used to build a response prediction model, and the in-situ monitoring data was used to train and verify the prediction model. The results show that Pearson correlation coefficient and B-type grey correlation can effectively explore the similarity between the change size and trend of spatial structural responses. At the same time, LSTM neural network can learn to optimize the response correlation between the measuring points and its related measuring points, realizing the global monitoring of the structure.
KEYWORDS
Large-span space structure, Response correlation, Measurement point optimization, Neural network
REFERENCES
[1] Jiaxin Peng. Response estimation method of spatial steel structures based on correlation analysis. Thesis, Harbin Institute of Technology, China,2019.
[2] Lu W, Wen R, Teng J, et al. Data correlation analysis for optimal sensor placement using a bond energy algorithm. Measurement 2016; 91: 509-518.
[3] Liming Zhu, Yilian Chen, Si Yubian, Et al. Multi-sensor correlation analysis of bridge strain monitoring. China: MCC Building Research Institute Limited. Proceedings of the Industrial Architecture Symposium 2020 (Part 2).
[4] Beygzadeh S, Salajegheh E, Torkzadeh P, et al. An Improved Genetic Algorithm for Optimal Sensor Placement in Space Structures Damage Detection. International Journal of Space Structures. 2014; 29(3):121-136.
[5] Hui Feng. Local response correlation modeling method for Bridges based on recurrent neural networks. Thesis, Harbin Institute of Technology, China, 2019.
[6] Kaveh A, Dehkordi MR. Neural Networks for the Analysis and Design of Domes. International Journal of Space Structures. 2003;18(3):181-193.
[7] Jianxi Yang, Likai Zhang, Ren Li, et al. Damage identification of bridge structures using convolutional and long and short memory neural networks. Journal of Railway Science and Engineering 2020; 17(08): 1893-1902.
[8] Li Chao. Optimization and reconstruction of multi-type monitoring information based on correlation. Thesis, Harbin Institute of Technology, China, 2015.
[9] AlMahmoud H R, Hammo B, Faris H. A modified bond energy algorithm with fuzzy merging and its application to Arabic text document clustering. Expert Systems With Applications 2020; 159:1-24.
[10] ZHU Yinjuan, LI Haibo, et al. Method of resource combination based on relevance degree in cloud manufacturing environment. Com¬puter Engineering and Applications 2016; 52(5): 255-261.
[11] Rahimi H, Parand F A, Riahi D. Hierarchical simultaneous vertical fragmentation and allocation using modified Bond Energy Algorithm in distributed databases. Applied computing and informatics 2018; 14(2): 127-133.
[12] Jialin Dong. Research on optimal arrangement of cable force sensors based on spatial correlation and inversion prediction of whole bridge cable force. Thesis, Harbin Institute of Technology, China, 2017.
[13] Runfa Wen. Research on structure monitoring method based on measurement point correlation analysis. Thesis, Harbin Institute of Technology, China, 2014.
[14] Jiayue X, Ge O. Predicting wind-induced structural response with LSTM in transmission tower-line system. SMART STRUCTURES AND SYSTEMS 2021; 28(3):391-405.
[15] Ye Z, Wen Z, Yanlong L, et al. A deep learning prediction model of DenseNet-LSTM for concrete gravity dam deformation based on feature selection. Engineering Structures 2023; 295:1-16.
[16] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
[17] Gers, F. A., Schmidhuber, J., & Cummins, F. (2000). Learning to forget: Continual prediction with LSTM. Neural computation, 12(10), 2451-2471.
[18] Goodfellow, I., Bengio, Y., Courville, A., & Bengio, Y. (2016). Deep learning (Vol. 1, No. 2). Cambridge: MIT press.
[19] Hongtao Cui, Xiaoxu Chen, Chao Yang, etc. Subway inbound passenger flow prediction based on deep long short term memory network. Urban rail transit research 2019; 22(09): 41-45.
[20] Santurkar S, Tsipras D, Ilyas A, et al. How Does Batch Normalization Help Optimization. Canada: neural information processing systems, 2018.
[21] Yang Xiong, Shuqing Li, Hao Xu, et al. Research on short-term forecasting method of urban rail transit passenger flow. Electronic design engineering 2022; 30(01): 46-50.
[22] Xinyong Z, Liwei S, Lingtong Q. Bayesian Regularization Algorithm Based Recurrent Neural Network Method and NSGA-II for the Optimal Design of the Reflector. Machines 2022; 10(1) : 1-15.