| abstract |
The invention relates to the detection field in the underground pipeline construction industry, in particular to an underground pipeline crack detection device and identification method based on deep learning; comprising a main shaft (1), a stepping motor (2), a ball screw (3), a spring The crank (4) and the track wheel (5) are supported, the stepper motor (2) is installed at one end of the main shaft (1), and the output end of the stepper motor (2) is supported by the spring through the ball screw (3) and the crank ( 4) Connection, a crawler wheel (5) is installed on the spring support crank (4), a sensor module (6) is also installed on the main shaft (1), and a battery pack is built in the crawler wheel (5); Effectively reduces the labor cost of pipeline inspection, and provides a safe transmission environment for power and communication; through the deep learning algorithm to identify pipeline cracks, as a means of judging pipeline cracks, it effectively reduces the probability of manual misjudgment and missed judgment, greatly Improved detection efficiency. |