Flaws identification in ultrasonic testing based on evidential reasoning rule

In order to solve the problem that the accuracy of flaws identification in ultrasonic testing is not high enough due to the error in sensor information acquisition and the noise interference in the detection environment, a method of flaws identification in ultrasonic testing based on evidential reasoning rule (ER rule) is studied. Firstly, ER rule is proposed to consider the reliability and weights factors of evidence. Secondly, the method of flaws identification in ultrasonic testing is proposed, which mainly includes ultrasonic flaws feature extraction, reliability factors acquisition, identification features fusion and evidence weights optimization. Finally, the flaws data of a composite material are obtained by means of ultrasonic testing, and the proposed method is verified. The results show that this method can overcome the influence of evidence reliability on flaws identification, and improve the accuracy rate compared with the other methods.