微间隙焊缝磁光成像NN-KF跟踪算法分析
NN-KF of magneto-optical imaging for micro-gap seam tracking
-
摘要: 针对紧密对接微间隙焊缝，分析基于磁光成像的神经网络补偿卡尔曼滤波（kalman filtering compensated by neural network，NN-KF）跟踪算法，建立焊缝位置测量模型并运用卡尔曼滤波对焊缝位置偏差进行最优预测.卡尔曼滤波进行最优估计需建立准确的系统模型和观测模型，而在焊缝跟踪过程中，系统噪声具有非先验性.对于针对测量模型误差、过程噪声和测量噪声对卡尔曼滤波结果的影响，运用反向传播（back propagation，BP）神经网络对卡尔曼滤波结果进行修正，补偿模型误差及噪声统计不确定性造成的滤波误差.结果表明，BP神经网络补偿卡尔曼滤波算法能有效抑制滤波发散，减小噪声干扰影响，提高焊缝跟踪精度.Abstract: An algorithm of Kalman filtering compensated by neural network(NN-KF) of magneto-optical imaging is researched for detecting micro-gap weld joint. A motion model is proposed and the Kalman filter is applied to predict the weld position deviation optimally. To accomplish the optimal estimation by using Kalman filter, an accurate system model and an observation model need to be established. However, the system noise has the characteristic of non-apriority in seam tracking process. Considering the influence of the motion model error, the process noise and the measurement noise on Kalman filtering, a BP neural network was employed to amend the Kalman filtering results through compensating for the filtering error caused by model error and the uncertainty of noise statistic characteristics. Experimental results demonstrate that Kalman filter compensated by a BP neural network can effectively restrain the divergence of Kalman filtering, reduce the influence of noise, and improve the seam tracking accuracy.
-
Keywords:
- magneto-optical imaging /
- seam tracking /
- Kalman filter /
- neural network
-
-
[1] Gao Xiangdong, You Deyong, Katayama Seiji. Seam tracking monitoring based on adaptive Kalman filter embedded elman neural network during high power fiber laser welding[J]. IEEE Transactions on Industrial Electronics, 2012, 59(11):4315-4325. [2] 邹怡蓉, 都东, 曾锦乐, 等. 基于多视觉特征获取与信息融合的焊道识别方法[J]. 焊接学报, 2013, 34(5):33-36. Zou Yirong, Du Dong, Zeng Jinle, et al. Visual method for weld seam recognition based on multi-feature extraction and information fusion[J]. Transactions of the China Welding Institution, 2013, 34(5):33-36. [3] Gao Xiangdong, Liu Yonghua, You Deyong. Detection of micro-weld joint by magneto-optical imaging[J]. Optics & Laser Technology, 2014, 62:141-151. [4] Schuhmann T, Hofmann W, Werner R. Improving operational performance of active magnetic bearings using Kalman filter and state feedback control[J]. IEEE Transactions on Industrial Electronics, 2012, 59(2):821-829. [5] 张轲, 金鑫, 吴毅雄. 基于卡尔曼滤波的焊缝偏差实时最优估计[J]. 焊接学报, 2009, 32(12):1-4. Zhang Ke, Jin Xin, Wu Yixiong. Optimal estimation algorithm for real-time welding deviation based on Kalman filtering[J]. Transactions of the China Welding Institution, 2009, 32(12):1-4. -
期刊类型引用(3)
1. 马波，林少铎，张南峰，高向东. 斜率表征与卡尔曼滤波的焊缝跟踪方法研究. 机电工程. 2020(02): 206-210 . 
百度学术
2. 孟祥宾，朱军，李紫豪，刘炳辰. 多重自适应卡尔曼滤波PMLSM无传感控制. 软件. 2018(08): 18-23 . 百度学术
3. 董航，丛明，Zhang Yuming，陈和平. 基于KF-GPR的熔池关键特征建模方法. 焊接学报. 2018(12): 49-52+131 . 本站查看
其他类型引用(5)
计量
- 文章访问数: 556
- HTML全文浏览量: 6
- PDF下载量: 598
- 被引次数: 8
下载:
