Intelligent monitoring method and system for loosening positioning of steel structure bolt group

Abstract

The invention discloses an intelligent monitoring method and system for loosening positioning of a steel structure bolt group. The method comprises the following steps: collecting multi-channel stress wave signals under different working conditions through a piezoelectric sensing monitoring device; preprocessing the stress wave signals; performing phase-space reconstruction on the preprocessed stress wave signals according to an improved multivariable recurrence plot algorithm to obtain a multivariable recurrence plot of a corresponding working condition; training a multi-attention mechanism improved convolutional neural network model through the multivariable recurrence plot of the corresponding working condition; and performing steel structure bolt group loosening positioning through the convolutional neural network model improved by the multi-head attention mechanism. A recursive analysis method is introduced into the field of piezoelectric active sensing, multi-sensor information fusion is realized, a multivariable recursive plot and an improved convolutional neural network are combined to realize steel structure bolt group loosening positioning, and the diagnosis precision of the model is improved.

Description

Technical field [0001] The present invention belongs to the field of steel structure health monitoring, and more particularly to a steel structural bolt group loose positioning monitoring and intelligent monitoring method and system. Background technique [0002] The bolt connection has the advantages of easy construction, detachable, fatigue resistance, and is currently a major connection to the steel structure. However, under the action of cyclic load, complex environment, the steel structure bolt connection is very prone to loose, and if the bolt loosening site is not discovered in time, it will have a very disadvantage of the structure, and it is likely to cause engineering accidents. [0003] Based on the method of manual testing and failure to achieve real-time monitoring, there is a need to be related to the correlation between innovative, breakthrough methods, high accuracy, good accuracy, and good real-time bolts. The monitoring method of piezoelectric active sensing has...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the present invention proposes a bolt loosening monitoring method, system, equipment, and storage medium based on a multi-head attention mechanism-improved convolutional neural network, which is used to solve the problem that the piezoelectric active sensing method is difficult to pass through the signal peak value, wavelet packet energy, etc. The problem of locating the looseness of the bolt group by conventional indicators

Images