The invention relates to an
underground pipeline disease intelligent detection and evaluation method and
system, and the method comprises the following steps: S1, obtaining
underground pipeline multi-source heterogeneous data, and constructing an
underground pipeline detection
knowledge graph; s2, according to the detection task instruction, based on a multi-
modal detection
robot, obtaining a pipeline multi-
modal original data set; s3, preprocessing the obtained multi-
modal original data set of the pipeline to obtain a structured
feature data set; s4, constructing an intelligent recognition model, performing defect detection, and outputting a final defect intelligent recognition result through a multi-
modal data fusion decision
algorithm; s5, performing three-dimensional space positioning on each identified defect according to an intelligent defect identification result, automatically marking the three-dimensional space on a digital
pipe network map, and quantifying an RBI
risk index of each defect; and S6, according to the RBI
risk index of each defect, calling the underground pipeline detection
knowledge graph to intelligently match the optimal trenchless repair scheme, and obtaining a detection report. According to the invention, the speed of underground pipeline
disease detection and the consistency of evaluation are effectively improved.