Method and system for deformation intelligent monitoring of precast flexural member forming process

Abstract

The application provides a precast bending member forming process deformation intelligent monitoring method and system, relates to the technical field of deformation intelligent monitoring, and the method comprises the following steps: obtaining an interference fringe image of a precast bending member surface, performing phase synthesis and integral processing to generate a displacement gradient field, then performing phase unwrapping and denoising processing to obtain a reconstructed displacement field; synchronously collecting strain data and temperature data, and interpolating and reconstructing into a multi-physical quantity field; then, based on the multi-physical quantity field, the displacement signal in the reconstructed displacement field is decomposed into an intrinsic modal function component by using a variational modal decomposition algorithm, then recombination is performed to obtain a sub-deformation field, and the sub-deformation field is superimposed with a strain characteristic field and a temperature characteristic field to form a multi-modal characteristic tensor; finally, a complex-valued convolutional neural network is used to extract complex domain features, and the complex domain features are matched with a deformation database to identify the deformation category in the forming process. The application can accurately monitor the slight deformation of the precast member under the action of multiple fields.

Images