系统工程与电子技术 ›› 2022, Vol. 44 ›› Issue (7): 2211-2218.doi: 10.12305/j.issn.1001-506X.2022.07.17

• 系统工程 • 上一篇    下一篇

基于改进NSGA3的焊接缺陷评估特征选择

李波1,2,*, 周家豪1,2, 刘民岷1,2, 朱品朝3   

  1. 1. 电子科技大学航空航天学院, 四川 成都 611731
    2. 飞行器集群智能感知与协同控制四川省重点实验室, 四川 成都 611731
    3. 四川成焊宝玛焊接装备工程有限公司, 四川 成都 610052
  • 收稿日期:2022-01-17 出版日期:2022-06-22 发布日期:2022-06-28
  • 通讯作者: 李波
  • 作者简介:李波(1975—), 男, 教授, 博士研究生导师, 博士, 主要研究方向为计算机建模与仿真、生产调度与过程控制、装备故障预测/诊断与维护|周家豪(1997—), 男, 硕士研究生, 主要研究方向为复杂系统集成与自动化、计算机建模与仿真|刘民岷(1973—), 男, 副教授, 硕士研究生导师, 博士, 主要研究方向为虚拟仪器技术、分布式仿真技术、机器人智能控制技术|朱品朝(1964—), 男, 高级工程师, 硕士, 主要研究方向为数字化工厂、生产线仿真模拟、大型柔性化生产线
  • 基金资助:
    科技部创新方法工作专项(2020IM020400);四川省科技厅科技计划(2020ZDZX0024);四川省科技厅科技计划(2021YFG0050)

Feature selection for welding defect assessment based on improved NSGA3

Bo LI1,2,*, Jiahao ZHOU1,2, Minmin LIU1,2, Pinchao ZHU3   

  1. 1. School of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu 611731, China
    2. Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province, Chengdu 611731, China
    3. Sichuan BMT Welding Equipment and Engineering Company Limited, Chengdu 610052, China
  • Received:2022-01-17 Online:2022-06-22 Published:2022-06-28
  • Contact: Bo LI

摘要:

在基于多源信息融合的焊接缺陷评估中, 特征选择对提高评估精度与速度发挥着重要作用。多源特征集由电弧电特征与电弧声音特征组成, 其特点在于特征集中存在冗余与互补特征。因此, 本文提出一种基于改进非支配排序遗传算法-Ⅲ(non-dominated sorting genetic algorithm-Ⅲ, NSGA3)的多目标特征选择方法, 旨在从多源特征集中找到最优特征子集。该方法首先对特征集进行相关、冗余和互补特性分析, 再以冗余性最小, 相关性与互补性最大为目标建立多目标特征选择优化模型。并基于相关、冗余和互补评价函数提出一种新的变异算子来引导变异过程, 以减少无效特征的影响, 提高收敛效率。实验采用支持向量机作为学习器来验证学习效果, 结果表明, 所提方法与其他3种方法相比, 可以在特征子集维度和预测精度方面获得更好的性能。

关键词: 改进非支配排序遗传算法-Ⅲ, 冗余, 互补, 特征选择, 变异算子

Abstract:

Feature selection plays an important role in welding defect assessment based on multi-source information fusion because of improved detection accuracy and speed. The multi-source feature set consists of arc voltage features and arc sound features and is characterized by the presence of redundant and complementary features in the feature set. Therefore, this paper proposes a multi-objective feature selection method based on the improved non-dominated sorting genetic algorithm-Ⅲ (NSGA3), aiming to find the optimal feature subset in a multi-source feature set. Firstly, the method analyses the feature set for correlation, redundancy, and complementary characteristics, and then builds a multi-objective feature selection optimization model with the objective of minimizing redundancy and maximizing correlation and complementarity. Then a new mutation operator is proposed to guide the mutation process based on redundancy and complementary evaluation functions to reduce the influence of invalid features and improve convergence efficiency. Support vector machine is used as learners to verify the learning effect in the experiments. The results show that the proposed method can achieve better performance in terms of feature subset dimension and prediction accuracy compared with the other three methods.

Key words: improved non-dominated sorting genetic algorithm-Ⅲ (NSGA3), redundancy, complementarity, feature selection, mutation operator

中图分类号: