Drainage pipeline fracture defect detection and grade evaluation method

Abstract

The invention discloses a drainage pipeline fracture defect detection and grade evaluation method, which comprises the following steps: acquiring a video or an image in a drainage pipeline, and marking structural defect features offline; constructing a structural defect Mask R-CNN model, detecting, segmenting and acquiring video or image defects, identifying structural defects of the drainage pipeline, and outputting fracture defect confidence, a fracture defect bounding box and a fracture defect mask; calculating characteristic parameters of the fracture defects; calculating a fracture defect rating parameter, a radial coverage ratio and a fracture defect circumferential coverage range; and rating the fracture defect. The method can detect and identify the structural defect of the drainage pipeline based on images or videos, grade the degree of the fracture defect of the drainage pipeline, and is effectively applied to the structural defect detection and identification work of the drainage pipeline; by adopting the method, the working intensity is reduced, the detection efficiency and accuracy of the drainage pipeline are improved, and the method has great practical engineering application value.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to View More

AI Technical Summary

Benefits of technology

The technical effect that this technology can detect when there are cracks caused by damage during construction without requiring expensive equipment such as ultrasonic waves for leak monitoring purposes. This helps save time and money while ensuring safety measures are being taken properly.

Problems solved by technology

Technological Problem addressed by this patented technical problem relates to accurately inspecting or testing drainages pipeline systems without being overwhelmed with environmental hazards caused during their construction stages. Current manual techniques require significant effort and involve long hours of working underground due to complexities involved. Different machines like cameras that use different sensors may also cause damage when used alone. Therefore, an improved system called Deep Learning Imager Based System (DLIS), described earlier in previous research works, proposes a solution involving combining multiple datasets from various sources to improve its performance and reduce human error factors associated with manually analyzed assessments.

Images