Font Size: a A A

On-line Data Processing For Automatic Settlement Monitoring

Posted on:2018-01-19Degree:MasterType:Thesis
Country:ChinaCandidate:F G WangFull Text:PDF
GTID:2322330515971189Subject:Surveying the science and technology
Abstract/Summary:PDF Full Text Request
With the development of sensor technology,automated monitoring technology has been widely used.Automated settlement monitoring technology is the main development direction of building settlement monitoring,the key problem is the online processing of data.Therefore,this paper aims to study the automatic settlement monitoring data online processing methods to improve the accuracy of the settlement obtained for future engineering applications to provide a basis.Firstly,the sliding window is established for the automatic on-line detection of the automatic settlement monitoring data,and the settlement anomaly detection method based on the prediction model is proposed.This method reduces the false alarm rate of anomaly detection,thus improving the accuracy of detection anomaly.Then,the sensitivity of the method is tested by simulation data,and the parameters such as the appropriate sliding window size are determined,and the detected anomalies are repaired to ensure the continuity of the data and to meet the accuracy of the monitoring data.Then,in the automatic settlement monitoring data processing,it is necessary to convert the automatic settlement monitoring data signal into the corresponding settlement of the engineering entity.Due to the difference of the automatic settlement monitoring data in the sliding window,the single threshold and the fitting model can not adapt well to the data in the window.In order to improve the accuracy of the settlement,a data processing method based on wavelet and fitting is proposed.The method selects the threshold and the fitting model dynamically based on the root mean square error and the SNR of the data in the window.Experiments show that the method can not only meet the requirements of artificial monitoring,but also can improve the accuracy of the settlement,and the difference between the settlement amount obtained by manual monitoring is about 0.1-0.4mm.Finally,in order to realize the on-line processing of the automatic settlement monitoring data,an online processing scheme based on the sliding window is proposed.The scheme embeds the exception processing and the data processing method based on the wavelet and the fit,so that the data can be processed online.Through the experiment,we can get the online processing of the automatic settlement monitoring data,and get the settlement curve and the settlement rate.The difference between the monitoring results and the online processing results is 0.9mm and the minimum is 0.3mm.The settlement amount obtained is basically the same as that of the artificial monitoring data.
Keywords/Search Tags:automatic monitoring, automated settlement sensor, exception handling, fitting, manual monitoring
PDF Full Text Request
Related items