The intelligent inspection robot is a special robot

which is mostly used for equipment defect detection in industrial areas such as the power distribution room. An intelligent patrol car system for abnormal detection of distribution equipment is constructed

through the perception of environmental information and its own speed

position

posture and other information by sensors

the patrol car processes the sensing information and makes correct decision and behavior control. A defect detection method based on an improved cascaded network is presented

Faster-RCNN is improved by adding support vector machine after region proposal network to improve classification accuracy on the foreground and background images. Faster-RCNN

SSD algorithms are introduced for comparison

it is proved that the detection accuracy

detection rate and training time by the method are better in the identifi cation for copper bar in power distribution room.