论文部分内容阅读
针对超声波检测信号存在衰减大、指向性差、传播路径复杂,以及构成复杂的特点,提出一种基于多分辨率奇异熵的混凝土缺陷智能无损检测算法。该算法利用小波算法,将超声波信号分解为多个尺度下的高、低频分量,针对各个分量进行奇异谱分解,同时利用信息熵理论,计算奇异熵作为缺陷检测的特征值,利用GA-SVM算法对奇异熵进行训练,从而达到辨识混凝土缺陷的目的。仿真实验结果表明表明采用该方法能够有效的提升混凝土缺陷辨识的精确度,提供了一种新的辨识混凝土缺陷的有效途径。
Aiming at the characteristics of large attenuation, poor directivity and complicated propagation path of ultrasonic detection signals and the complex structure, an intelligent nondestructive detection algorithm for concrete defects based on multi-resolution singular entropy is proposed. The algorithm uses wavelet algorithm to decompose the ultrasonic signal into high and low frequency components at multiple scales and performs singular spectral decomposition for each component. At the same time, using the information entropy theory, singular entropy is calculated as the eigenvalue of defect detection. By GA-SVM algorithm The singular entropy training, so as to achieve the purpose of identification of concrete defects. Simulation results show that this method can effectively improve the accuracy of identification of concrete defects and provide a new effective way to identify concrete defects.