Concrete thermodynamic parameter intelligent recognition method based on support vector machine

Abstract

The invention discloses a concrete thermodynamic parameter intelligent recognition method based on a support vector machine. The method includes firstly determining the range of inverse parameters; designing sample schemes of concrete thermodynamic parameters by an uniform design method; acquiring one temperature value of each feature point in the sample schemes through finite element forward modeling, utilizing the temperature values and corresponding thermodynamic parameters in the sample schemes as study samples, and establishing a support vector machine model; utilizing the differential evolution algorithm to perform global search, searching and acquiring each coefficient of the support vector machine, determining the nonlinear relationship between the inverse parameters and actual temperature values of monitoring points, and establishing a support vector machine prediction model; utilizing the support vector machine prediction model as a forward model, utilizing the differential evolution algorithm to perform global search for the concrete thermodynamic parameters, and searching and acquiring inverse parameters closest to the actual temperature values of the monitoring points as the optimal concrete thermodynamic parameters. The method has the advantages of rapidness in recognition and simpleness.

Description

technical field [0001] The invention relates to an intelligent identification method of concrete thermodynamic parameters based on a support vector machine, belonging to the technical field of water conservancy and hydropower engineering. Background technique [0002] In large-volume temperature control and anti-cracking, the setting of concrete thermodynamic parameters has a great impact on the accuracy of numerical calculations. At present, there are many methods in the identification of concrete thermodynamic parameters. For example, Liu Ning introduced parameter estimation into the thermodynamics of large-volume temperature field Parameter stochastic inversion analysis, Li Jun used the variable tolerance method to invert concrete thermodynamic parameters, Wang Zhenhong combined engineering practice with genetic algorithm to identify concrete thermodynamic parameters and so on. For these search algorithms, in the process of identifying thermodynamic parameters of concrete...

AI Technical Summary

Problems solved by technology

[0003] Later, in order to reduce the calculation cost, Yu Meng et al. used the neural network to back-analyze the temperature field of the concrete dam. The neural network technology can reduce the amount of calculation to a certain extent, and at the same time, the neural network calculation is easy to fall into the local minimum point.

Images