首页|基于聚类算法的自动变速箱装配模块划分研究

基于聚类算法的自动变速箱装配模块划分研究

扫码查看
自动变速箱可实现换挡变速功能,是车辆系统中传递动力的关键部件.由于其结构狭窄紧凑、零件数量繁多,导致装配复杂度大大增加.模块划分是产品模块化设计的关键步骤,可以将系统整体拆分形成若干个高内聚低耦合的模块,从而达到降低产品装配难度的目的.模糊C-均值聚类算法(FCM)是实现模块划分的传统方法,然而其对初值敏感,容易收敛到局部极值点.FCM与优化算法的结合有利于避免陷入局部最优解的情况,因此提出使用基于遗传模拟退火算法的FCM方法进行装配模块划分以获取自动变速箱模块的最佳划分方案.以重庆铁马变速箱有限公司的自动变速箱为例,使用所提方法对其进行装配模块划分,将所得模块划分结果与实际方案进行对比,证明了方法的准确性和有效性.
Research on Automatic Transmission Assembly Module Division based on the Clustering Algorithm
The automatic transmission,which could achieve the function of shifting and changing speeds,was a key component for transmitting power in the vehicle system.Due to the narrow and complex structure and the large number of parts,the assembly complexity of automatic transmissions was greatly increased.Module division was a key step in product modularization design,which could divide the entire system into several modules with high cohesion and low coupling,thereby reduced the difficulty of product assembly.The fuzzy C-means clustering algorithm(FCM)was a traditional meth-od to realize module division,but it was sensitive to initial values and easily converged to local extremum points.The com-bination of FCM and optimization algorithms was beneficial for avoiding falling into local optimal solutions.Therefore,the FCM based on the genetic simulated annealing algorithm was proposed to conduct assembly module division to obtain the optimal division scheme for the automatic transmission module.We took the automatic transmission of Chongqing Tiema Transmission Co.,Ltd.for example,the proposed method was used to divide the assembly module,and the results of the obtained module division were compared with the actual program,which proved the accuracy and effectiveness of the meth-od.

automatic transmissionsclustering algorithmgenetic algorithmsimulated annealing algorithmdesig-ning structural matrixassembly module division

谢斌、黄皓、李冬冬、吴玉、刘鹏、张文硕、张欣宇、王延忠

展开 >

北京航空航天大学机械工程及自动化学院,北京 100191

中国兵器工业新技术推广研究所,北京 100089

重庆铁马变速箱有限公司,重庆 400050

自动变速箱 聚类算法 遗传算法 模拟退火算法 设计结构矩阵 装配模块划分

国防基础科研项目

JCKY2021601B006

2024

新技术新工艺
中国兵器工业新技术推广研究所

新技术新工艺

影响因子:0.294
ISSN:1003-5311
年,卷(期):2024.434(2)
  • 10