A new inspection robot system for storage tank

Large chemical and petroleum product storage tanks are prone to attack by corrosion, the material and the welds need to be inspected throughout their service life for signs of damage. Many independent robotic systems have been developed, but no one can accomplish an entire inspection task without the need to empty the tanks nor the required human walk through inspection. The robotic system is comprised of a robotics crawler with the magnetic wheels, the control system, the data storage system, the inspection system and the power. The design of mechanical architecture and control architecture were also offered. A fuzzy CMAC was adopted to establish the tracking control system for improving the fine performance capacity. The neural network structure of the fuzzy CMAC was designed, and the input and output formula of each layer was deduce. Based on BP arithmetic, the associative strength, core and width of Gaussian membership function were obtained through training. The simulation of the robot tracking control system is carried out in order to check the robust of the fuzzy CMAC. The result indicates that the robot can follow the scheduled track, the stability is good, the position precision is high, and the control system can be used in the inspection robot. This type robot will avoid the happening of accidents and increase the safety of the tanks.