登录    |    注册

您好,欢迎来到中国测试科技资讯平台!

首页> 《中国测试》期刊 >本期导读>基于Chernoff face的机器人焊钳性能评估

基于Chernoff face的机器人焊钳性能评估

147    2021-11-23

¥0.50

全文售价

作者:刘锋, 高忠林, 郭锦华, 翟宝亮, 徐昊

作者单位:中船重工第七零七研究所,天津 300131


关键词:多传感器;机器人焊钳;贝叶斯决策;数据融合;性能评估


摘要:

为更好地评估设备性能,建立一种可视化的、可靠的机器人焊钳性能评估方法,与传统的性能评估方法不同,该方法将多传感器采集的多参数特征信息通过代数运算进行高精度融合,并绘制Chernoff face图像。同时设计一种有效的Chernoff face图像模式特征矩阵提取方法,将Chernoff face图像转换为二值图像,并且每个二值图像可存储为一个二进制特征矩阵。利用贝叶斯决策建立机器人焊钳性能分类器,通过样本模式特征矩阵最终获得设备性能的有效描述。分类性能测试结果表明,该方法显著提高Chernoff face技术在机器人焊钳性能评估中的适用性和效率,具有可行性、有效性和可靠性。


Performance evaluation of robot welders based on Chernoff face
LIU Feng, GAO Zhonglin, GUO Jinhua, ZHAI Baoliang, XU Hao
NO. 707 Research Institute of CSIC, Tianjin 300131, China
Abstract: To better evaluate the performance of the equipment, a visual and reliable performance evaluation method for robot welders is developed, which is different from the traditional performance evaluation method in that the multi-parametric feature information collected from multiple sensors is fused with high precision through algebraic operations and the Chernoff face image is plotted. An effective Chernoff face image pattern feature matrix extraction method is designed, which converts the Chernoff face image into a binary image, and each binary image can be stored as a binary feature matrix. Bayesian decision is used to build a robot welder performance classifier, and the sample pattern feature matrices are used to obtain an effective description of the device performance. The classification performance test results show that the method significantly improves the applicability and efficiency of the Chernoff face technique in the performance evaluation of robot welders, with feasibility, validity and reliability.
Keywords: multi-sensor;robot welders;Bayesian decision;data fusion;performance evaluation
2021, 47(11):53-58  收稿日期: 2020-12-11;收到修改稿日期: 2021-01-11
基金项目:
作者简介: 刘锋(1994-),男,河北保定市人,助理工程师,硕士,主要研究方向为信息采集与性能评估
参考文献
[1] 林瑀, 陈日成, 金涛. 面向复杂信息系统的多源异构数据融合技术[J]. 中国测试, 2020, 46(7): 1-7+23
[2] 璩晶磊, 李少波, 张成龙. 基于模糊证据理论的多传感器数据融合算法[J]. 仪表技术与传感器, 2017(10): 118-122
[3] 俞昆, 谭继文, 李善. 基于多传感器信息融合的滚动轴承故障诊断研究[J]. 仪表技术与传感器, 2016(7): 97-102+107
[4] 任子强, 司小胜, 胡昌华, 等. 融合多传感器数据的发动机剩余寿命预测方法[J]. 航空学报, 2019, 40(12): 134-145
[5] 周卫琪, 齐翔. 基于多传感器信息融合的汽车行驶状态估计[J]. 汽车工程, 2019, 41(1): 7-13+20
[6] 任子强, 司小胜, 胡昌华, 等. 融合多源数据的非线性退化建模与剩余寿命预测[J]. 中国测试, 2020, 46(2): 1-8
[7] 王宽, 李盘文, 祁晓鹏. 特征信息加权融合的进气道斜板故障诊断[J]. 中国测试, 2020, 46(11): 43-47+58
[8] 庄园, 张宁宁, 马龙博, 等. 液体流量标准装置流量控制系统设计[J]. 中国测试, 2020, 46(11): 126-131
[9] 王中立, 牛颖. 基于多传感器信息融合的机器人障碍物检测[J]. 中国测试, 2017, 43(8): 80-85
[10] ZHANG H, WANG F, XI T, et al. A novel quality evaluation method for resistance spot welding based on the electrode displacement signal and the chernoff faces technique[J]. Mechanical Systems and Signal Processing, 2015, 62: 431-443
[11] ZHANG H, HOU Y, ZHAO J, et al. Automatic welding quality classification for the spot welding based on the Hopfield associative memory neural network and Chernoff face description of the electrode displacement signal features[J]. Mechanical Systems and Signal Processing, 2017, 85: 1035-1043
[12] 高伟, 林宇华, 何宗源, 等. 基于特征指标的回路非线性检测与性能评价[J]. 中国测试, 2020, 46(8): 137-142