ABSTRACTS OF ARTICLES OF THE JOURNAL "INFORMATION TECHNOLOGIES".
No. 7. Vol. 27. 2021

DOI: 10.17587/it.27.350-358

V. A. Kats, Postgraduate Student, e-mail: vladislavkats1894@gmail.com, A. A. Volkov, Doctor of Technical Sc., Full Professor, e-mail: volkov@mgsu.ru, Moscow State University of Civil Engineering, Moscow, Russian Federation

A Method of Training Technical Condition Monitoring Systems in Construction

Technical condition estimation of the constructions is a relevant problem. In order to acquire comprehensive information of the testing object monitoring should be complex, providing effective and accurate estimate of the hazard class of the defects and forecasting its failure. Most of the current monitoring systems are based on acquiring and handling diagnostic via acoustic emission (AE) method. However, importantly, parameters of the acoustic emission propagated by defects depend on multiple factors such as type of the defect and its origin and the presence of noise on the testing object during data acquisition. In this regard, the problem of training the technical condition monitoring system is particularly important. In current work, we proposed a training method of monitoring systems for technical diagnostics of the constructions based on four subsequent stages: features extraction from AE data on two-time scales, features' dimensionality reduction, outliers detection and anomalies detection. Proposed method provides trained model for the detection of defects evolution in the building constructions. It has been tested on real constructions of the oil reservoir. The verification of the proposed method was provided by estimation of the accuracy metric of the trained model. Based on cross-validation, the mean error was 1.4 %. This confirms that proposed method can be effectively utilized as a part of technical condition monitoring system for more accurate forecasting hazard class of the defects and their evolution inside constructions.
Keywords: monitoring in construction, structural health monitoring, intellectual data analysis, acoustic emission, decision support systems, machine learning

P. 350–358

To the contents