论文部分内容阅读
为了提高红外热波无损检测的定量识别精度,提出一种改进神经网络的红外热波无损检测方法。该方法将最佳检测时间、最佳温差等因素作为红外热波无损检测定量识别的输入,表现缺陷的深度和直径作为BP神经网络的期望输出,通过搜索优化算法优化BP神经网络对输入和输出之间关系进行拟合,并进行了多次测试实验,结果表明,本文方法可以降低红外热波无损检测定量识别的误差。
In order to improve the quantitative identification accuracy of nondestructive testing of infrared thermal waves, an improved nondestructive testing method of infrared thermal wave based on neural network is proposed. The method takes the best detection time, the best temperature difference and other factors as the input for the quantitative identification of the infrared thermal wave non-destructive testing. The depth and the diameter of the defect are used as the expected output of the BP neural network, and the BP neural network is optimized for the input and output The results show that this method can reduce the error of quantitative identification of the infrared thermal wave nondestructive testing.