Multichannel mobile non-destructive ultrasonic testing system with artificial neural networks

摘要

An embodiment of the present invention relates to an ultrasonic flaw inspection system, and the technical problem to be solved is to accurately analyze the defect of the inspection object by inputting the received ultrasound signal to an artificial neural network, and also accurately predict the lifespan of the inspection object. An object of the present invention is to provide a multi-channel mobile non-destructive ultrasound inspection system having an artificial neural network. To this end, the present invention provides a multi-channel ultrasonic transducer for transmitting ultrasonic waves to a target object and receiving reflected ultrasonic waves; a multi-channel ultrasonic flaw detector that transmits a pulse signal to the multi-channel ultrasonic probe, receives a reflected signal reflected from the multi-channel ultrasonic probe, processes the received reflected signal and stores the received data as data; a signal processor for receiving data from the multi-channel ultrasonic flaw detector in real time, and processing the received data to provide ultrasonic flaw data of the target object; And it provides a multi-channel movable non-destructive ultrasonic flaw inspection system, including an artificial neural network unit for performing learning using the ultrasonic flaw data obtained from the signal processing unit, and detecting a defect based on the learned result.