Application of intelligent data analysis methods to the problem of predicting the results of industrial testing of structural elements based on tensometry data

Abstract

The article presents the results of a study of three intelligent data analysis methods for solving the problem of predicting the results of industrial testing of structural elements according to strain gauge data. As an object of study, an I-beam was considered, for which a series of experiments was carried out with loading and recording the values of its stress-strain state. The obtained experimental values were used to study and predict the strength in real time. The scientific novelty of the work lies in the proposal of both the author's method for predicting the stress-strain state of the beam depending on the environmental parameters, and a tool based on the use of data mining methods. As a result of the work, an information system was implemented, a distinctive feature of which is the ability to quickly process large amounts of experimental, that is, raw data in real time, which is achieved through the use of data mining methods. In the course of the work, environmental parameters were identified and analyzed both from the side of the stand and from the side of the microclimate, which affect the accuracy of measurements. Due to this, experimental data can be corrected at any time when certain characteristics change.