基于模糊C均值聚类的电动尾门防夹算法研究  

Research on Anti-pinch Algorithm of Power Liftgate Based on Fuzzy C -means Clustering

作　　者：周树杰 李涛[1] 吕艳 张元良[1] ZHOU Shujie;LI Tao;LYU Yan;ZHANG Yuanliang(School of Mechanical Engineering,Dalian University of Technology,Dalian 116024,China;School of Mechanical Engineering and Automation,Dalian Polytechnic University,Dalian 116034,China)

机构地区：[1]大连理工大学机械工程学院,辽宁大连116024 [2]大连工业大学机械工程与自动化学院,辽宁大连116034

出　　处：《机械与电子》2024年第11期70-75,共6页Machinery & Electronics

基　　金：辽宁省教育厅2021年度科学研究经费面上项目(LJKZ0526);2021年度辽宁省自然科学基金资助计划项目(2021-MS-300)。

摘　　要：针对汽车电动尾门在关闭过程中由于机构运行阻力而引起的误防夹问题,研究常规防夹控制中发生误防夹动作机理,提出了基于模糊C均值聚类的电动尾门防夹控制算法。搭建基于模糊C均值聚类的防夹算法模型,采集多组正常关闭过程中尾门电机输出脉冲宽度数据进行模糊C均值聚类,提取脉冲宽度特征矩阵,与测试数据进行夹紧力评估,将评估的夹紧力和防夹阈值比较判断是否触发防夹。实验结果表明,该算法能够实现尾门防夹判断,有效减少由于机构运行阻力的影响而产生的误防夹现象,且防夹力小于100 N。To address false anti-pinch issues in the car power liftgate's closing process due to mechanical resistance,the mechanism of false anti-pinch action in the conventional anti-pinch control is studied,and an anti-pinch control algorithm based on fuzzy C-means clustering is proposed.The anti-pinching algorithm model based on fuzzy C-means clustering was built,and the output pulse width data of multiple groups of liftgate motors in the normal closing process was collected for fuzzy C-means clustering,the pulse width feature matrix was extracted,and the anti-pinching force was evaluated with the test data,and the evaluated anti-pinching force and anti-pinching threshold were compared to determine whether the anti-pinching was triggered.After experimental verification,it can realize the anti-pinching of the liftgate,effectively reduce the phenomenon of false anti-pinching caused by the influence of the mechanism running resistance,and the anti-pinching force is less than 100 N.

关 键 词：误防夹 模糊C均值 防夹控制 电动尾门 

分 类 号：TP271[自动化与计算机技术—检测技术与自动化装置]