基于K-means聚类的汽车天窗防夹算法研究

Research on Anti-pinch Algorithm of Automobile Sunroof Based onK-means Clustering

针对天窗起翘机构阻力变化剧烈引起的天窗误防夹问题,提出了基于K-means聚类的汽车天窗防夹算法。首先对多组关闭过程未遇加持物的霍尔脉冲宽度数据进行K-means聚类获取每个位置对应的脉冲宽度的K组质心,通过将待测数据与K组质心分别做距离计算保留最短距离的方法降低机构阻力变化对霍尔脉宽产生的影响,然后对上步所得最短距离进行差分计算,对差分结果进行限幅滤波后,再进行近似积分计算,最后将积分面积与阈值进行比较做出是否防夹的判断。通过MATLAB进行模型验证,验证结果表明,提出的方法能够准确检测出夹紧力大小,且相较于传统方法,能有效降低机构阻力变化对防夹判断产生的影响。将其移植到天窗控制器中,对天窗做防夹测试试验,测试结果均未出现误防夹现象,且防夹力大小保持在60~80 N之间,符合国家标准GB 11552中的规定。

Aiming at the problem of false anti-pinch of sunroof caused by the drastic change of the resistance of the sunroof tilt mechanism,an anti-pinch algorithmof automobile sunroof based on K-means clustering was proposed.Firstly,the algorithm performed K-means clustering on the multiple sets of Hall pulse width data that did not encounter the blessing during the closing process to obtain the K groups of centroids of the pulse width corresponding to each position.By calculating the distance between the data to be measured and the center of mass of the K group and leaving the shortest distance to reduce the influence of the resistance change of the mechanism on the Hall pulse width.Then,the difference calculation was performed on the data obtained in the previous step,and then the difference result was subjected to limit filtering,and then the approximate integral calculation was performed.Finally,the integral area was compared with the threshold value to make a judgment on whether to prevent pinch.The model was verified by MATLAB,and the verification results show that the method can accurately detect the clamping force,and compared with the traditional method,this method could effectively reduce the influence of the mechanism resistance change on the anti-pinch judgment.The method was transplanted into the skylight controller,and the anti-pinch test was carried out on the skylight.The test results showed no false anti-pinch phenomenon,and the anti-pinch force was maintained between 60 and 80N,which was in line with the national standard GB 11552.