基于径向基神经网络的粒子群表面缺陷识别算法

doi:10.16180/j.cnki.issn1007-7820.2019.05.018

摘要/Abstract

摘要：

金属部件表面缺陷识别问题是模式识别领域的研究热点,高效、可靠的表面缺陷识别方法能够有效提高生产效率、维护生产安全。针对这一问题,文中提出了一种利用径向基(RBF)神经网络和粒子群优化(PSO)算法相结合的表面缺陷识别算法。采用PSO算法确定和改进RBF神经网络的权值参数,同时对PSO算法中的惯性权重进行线性处理,有效消除了PSO算法中的最优解局部振荡现象。针对金属部件表面常见的几种缺陷对RBF-PSO表面缺陷识别算法进行网络训练,并进行相应的实际测试。文中提出的RBF-PSO表面识别算法识别准确率可达96%,相比于传统的神经网络算法具有明显的性能提升。

关键词: 径向基, 粒子群, 优化算法, 表面缺陷识别

Abstract:

Surface defect recognition of metal parts is a hot topic in the field of pattern recognition. Efficient and reliable surface defect identification method can effectively improve production efficiency and maintain production safety. To solve this problem, a surface defect recognition algorithm based on radial basis function (RBF) neural network and particle swarm optimization (PSO) algorithm was proposed. The weight parameters of RBF neural network were determined and improved by PSO algorithm, and the inertia weight of PSO algorithm was processed linearly. The local oscillation of the optimal solution in PSO algorithm was effectively eliminated. The RBF-PSO surface defect recognition algorithm was trained by network aiming at several common defects on the surface of metal parts, and the corresponding actual test was carried out. The recognition accuracy of RBF-PSO surface recognition algorithm proposed in this paper could reach 96%. Compared with traditional neural network algorithm, it had obvious performance improvement.

Key words: radial basis, particle swarm optimization, optimization algorithm, surface defect recognition

中图分类号:

TP394

蓝机满. 基于径向基神经网络的粒子群表面缺陷识别算法[J]. 电子科技, 2019, 32(5): 92-95.

LAN Jiman. Particle Swarm Optimization Surface Defect Recognition Algorithm Based on Radial Basis Neural Network[J]. Electronic Science and Technology, 2019, 32(5): 92-95.

图/表 4

参考文献 11

[1]	李慧, 周维博, 刘博洋 , 等. 基于粒子群优化算法的RBF神经网络在径惠渠灌区地下水位埋深预测中的应用[J]. 水电能源科学, 2014(8):127-130.
	Li Hui, Zhou Weibo, Liu Boyang , et al. Application of RBF neural network based on particle swarm optimization algorithm in prediction of groundwater table depth in ruihui channel irrigation area[J]. Hydropower and Energy Science, 2014(8):127-130.
[2]	Vasilic S, Hocenski Z. The edge detecting methods in ceramic tiles defects detection[C]. Boise:Proceeding of IEEE International Symposium on Industrial Electronics,IEEE, 2006.
[3]	范伟 . 基于机器视觉的汽车车身零部件表面划痕检测的研究[D]. 南京:南京理工大学, 2016.
	Fan Wei . Research on scratch detection of automobile body parts based on machine vision[D]. Nanjing:Nanjing University of Technology, 2016.
[4]	何志勇, 孙立宁, 苗延年 . 一种微小表面缺陷的机器视觉检测方法[J]. 应用科学学报, 2012. 30(5):531-537. doi: 10.3969/j.issn.0255-8297.2012.05.015
	He Zhiyong, Sun Lining, Miao Yannian . A machine vision detection method for micro surface defects[J]. Journal of Applied Sciences, 2012,30(5):531-537. doi: 10.3969/j.issn.0255-8297.2012.05.015
[5]	Fkhar K, Aroussi M E, Saidi M N , et al. Fuzzy pattern recognition-based approach to biometric score fusion problem[J]. Fuzzy Sets and Systems, 2016,30(5):149-159.
[6]	杨艺, 虎恩典 . 基于S函数的BP神经网络PID控制器及Simulink仿真[J]. 电子设计工程, 2014,22(4):29-31.
	Yang Yi, Hu Endian . BP neural network PID controller based on S function and simulink simulation[J]. Electronic Design Engineering, 2014,22(4):29-31.
[7]	孙雪晨, 姜肖楠, 傅瑶 , 等. 基于机器视觉的凸轮轴表面缺陷检测系统[J]. 红外与激光工程, 2013,42(6):1647-1653.
	Sun Xuechen, Jiang Xiaonan, Fu Yao , et al. Camshaft surface defect detection system based on machine vision[J]. Infrared and Laser Engineering, 2013,42(6):1647-1653.
[8]	王丽梅, 左莹莹 . 基于RBF神经滑模的XY平台迭代交叉耦合控制[J]. 沈阳工业大学学报, 2014,36(1):1-6.
	Wang Limei, Zuo Yingying . Iterative cross-coupling control of XY platform based on RBF neural sliding mode[J]. Journal of Shenyang University of Technology, 2014,36(1):1-6.
[9]	包沁昕, 宋威 . 基于群体划分优化的gap-rbf神经网络学习算法[J]. 计算机应用与软件, 2016(11):215-220.
	Bao Qinxin, Song Wei . Gap-rbf neural network learning algorithms based on group partition optimization[J]. Computer Applications and Software, 2016(11):215-220.
[10]	陈汉武, 米建锋, 阮越 , 等. 带交叉算子的量子粒子群优化算法[J]. 东南大学学报:自然科学版, 2016,46(1):23-29.
	Chen Hanwu, Mi Jianfeng, Ruan Yue , et al. Quantum particle swarm optimization algorithm with crossover operator[J]. Journal of Southeast University:Natural Science Edition, 2016,46(1):23-29.
[11]	张聪, 汤伟 . 基于粒子群优化算法与形态学的纸病图像检测方法[J]. 造纸科学与技术, 2014,33(2):60-64.
	Zhang Cong, Tang Wei . Paper disease image detection method based on particle swarm optimization and morphology[J]. Paper Science and Technology, 2014,33(2):60-64.

[1]	刘晨旻,王亚刚. 基于连续空间的萤火虫算法改进[J]. 电子科技, 2022, 35(2): 40-45.
[2]	李娜,高博,谢宗甫. 分层异构信号处理平台调度方法研究[J]. 电子科技, 2022, 35(2): 7-13.
[3]	冯先丁,魏镜弢,吴张永,钱杰,浦友尚. 基于PCA-PSO-SVM的球磨机负荷预测研究[J]. 电子科技, 2022, 35(1): 29-34.
[4]	修晓波,李伯全,周峰. 基于遗传算法的温度传感器布置优化[J]. 电子科技, 2021, 34(9): 17-23.
[5]	何忠霖,周萍. 基于径向基神经网络退役锂电池分选研究[J]. 电子科技, 2021, 34(2): 38-44.
[6]	朱成名,魏云冰,蒋成成,朱健安. 基于PSO-BP神经网络的风电功率备用容量估计模型[J]. 电子科技, 2021, 34(12): 36-41.
[7]	朱健安,魏云冰,朱鹏杰,蒋成成,朱成名. 基于优化灰色傅里叶残差修正的中长期负荷预测[J]. 电子科技, 2021, 34(12): 49-55.
[8]	陈强,王宇嘉,林炜星,陈万芬. 改进粒子群算法求解分布式柔性车间调度问题[J]. 电子科技, 2021, 34(10): 63-68.
[9]	赵仕艳, 谢子殿, 丁康康, 崔含晴. 粒子群优化BP-PID的矿井提升机调速系统[J]. 电子科技, 2021, 34(1): 43-49.
[10]	陆欢. 基于约束优化提升并联充电器效率的研究[J]. 电子科技, 2020, 33(8): 53-58.
[11]	吴强,张伟,杨慧婷,汪朝盈. 基于天牛须算法的粒子群算法在PID参数整定上的应用[J]. 电子科技, 2020, 33(6): 18-23.
[12]	李康. 多模态特征融合的网络安全态势评估[J]. 电子科技, 2020, 33(12): 28-31.
[13]	张晋维,李国平. 微电网多目标鲁棒优化运行[J]. 电子科技, 2019, 32(3): 26-31.
[14]	吕腾飞,陈世平,王磊. 基于包簇概念的云资源分配成本优化模型[J]. 电子科技, 2019, 32(3): 31-36.
[15]	陆乐,陈世平. 基于包簇框架的云计算能耗优化算法[J]. 电子科技, 2019, 32(3): 61-66.