Prediction Method of Monitoring Data Based on Data Correlation in Civil Engineering. Issue 1 (September 2020)

• Record Type: Journal Article
• Authors: Qiao, Shengfang; Zhu, Yi; Tang, Mengxiong; Hu, Hesong; Chen, Hang; Hu, Han
• Is Part Of: IOP conference series. Volume 567:Issue 1(2020)
• Publication Date: 2020-09
• Subjects: Earth sciences -- Periodicals; Environmental sciences -- Congresses; Environmental sciences -- Periodicals; 550.5
• DOI: 10.1088/1755-1315/567/1/012017
• Languages: English
• ISSNs: 1755-1307

Abstract

Abstract: Wireless intelligent health monitoring has been widely used in civil engineering. However, ill-conditioned data could be generated due to the vulnerability to external interference sometimes. The ill-conditioned data have great influence on damage identification and condition assessment. Hence, the prediction method of monitoring data based on data correlation was presented in this paper. The correlation degree between multi-channels data was established by BP neural network. Then the ill-conditioned data was predicted and corrected by the correlation degree between the data, and verified by the measured data. The results indicated that high accuracy and engineering requirement could be achieved using BP neural network prediction method considering the correlation degree between multi-channels data.