The application discloses a kind of complex stratum dual-mode shield construction rock
debris particle size distribution evaluation method and
system, comprising: obtaining rock debris image and pretreatment denoising, obtain the first image;Utilize
deep learning algorithm to identify rock debris edge, separate overlapping rock debris, obtain the second image;Through morphological
parameter analysis rock debris shape, carry out three-dimensional reconstruction correction to non-spherical particle, obtain the third image;In combination with
laser particle size
analysis data, data fusion is carried out to the third image, and preliminary
particle size distribution is obtained;For fine
particle adhesion phenomenon, adopt detection
algorithm to correct
particle size distribution;According to the change of crushing mechanism when shield mode switches, dynamically update
particle size distribution;Through
mutation detection
algorithm analysis non-linear
mutation in complex stratum, carry out data
smoothing processing;Finally, error accumulation model is used to analyze error, if exceed threshold value, then reprocess, until error meets requirements.The application significantly improves the accuracy and reliability of rock
debris particle size distribution evaluation.