首页|基于GA-BP神经网络的工业CT缺陷检测

基于GA-BP神经网络的工业CT缺陷检测

扫码查看
为了提高工业CT缺陷检测精度,本文提出一种基于GA-BP神经网络的CT缺陷检测方法.采用遗传算法,对BP神经网络的权值和阈值进行优化,建立基于GA-BP神经网络的工业CT缺陷检测模型;采用工业CT图片组成实验数据进行仿真分析,并与卷积神经网络和支持向量机的监测效果进行对比.结果表明:该方法可使GA-BP神经网络模型误检测次数更少,精度高达96.67%,且效果更好,具有较好的可行性和实用性.
Industrial CT Defect Detection Based on GA-BP Neural Network
In order to improve the accuracy of industrial CT defect detection,this paper presents a CT defect detec-tion method based on GA-BP neural network.Using genetic algorithm,the weights and thresholds of BP neural network were optimized,and an industrial CT defect detection model based on GA-BP neural network was estab-lished.Industrial CT images were used to compose the experimental data for simulation analysis,and the monitoring effect was compared with that of convolutional neural network and support vector machine.The results show that this method can reduce the number of false detection of GA-BP neural network model,the accuracy is up to 96.67%,and the effect is better,and it has good feasibility and practicability.

industrial CTdefect detectiongenetic algorithmBP neural networkaccuracy

李文、周海蔚

展开 >

广州市机电技师学院

工业CT 缺陷检测 遗传算法 BP神经网络 正确率

2024

计量与测试技术
成都市计量监督检定测试所

计量与测试技术

影响因子:0.175
ISSN:1004-6941
年,卷(期):2024.51(3)
  • 8