杨炎,高炜,杨胜强,田建艳,高云松.基于模糊聚类和案例推理的滚抛磨块优选模型[J].表面技术,2019,48(9):315-320.
YANG Yan,GAO Wei,YANG Sheng-qiang,TIAN Jian-yan,GAO Yun-song.Optimal Model of Abrasive Blocks Based on Fuzzy Clustering and Case-based Reasoning[J].Surface Technology,2019,48(9):315-320 |
| 基于模糊聚类和案例推理的滚抛磨块优选模型 |
| Optimal Model of Abrasive Blocks Based on Fuzzy Clustering and Case-based Reasoning |
| 投稿时间：2018-11-16 修订日期：2019-09-20 |
| DOI：10.16490/j.cnki.issn.1001-3660.2019.09.038 |
| 中文关键词: 案例推理 模糊C均值聚类 E-R图 滚磨光整加工 滚抛磨块优选 |
| 英文关键词:case-based reasoning Fuzzy C-means clustering E-R diagram barrel finishing optimization of the abrasive blocks |
| 基金项目:山西省回国留学人员科研资助项目（2017-032）；山西省自然科学基金重点项目（201801D111002）；国家自然科学基金（U1510118） |
|
|
| Author | Institution |
| YANG Yan | 1.a.Schoolof Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan 030024, China |
| GAO Wei | 1.b.School of Machinery and Vehicle Engineering, Taiyuan University of Technology, Taiyuan 030024, China |
| YANG Sheng-qiang | 1.b.School of Machinery and Vehicle Engineering, Taiyuan University of Technology, Taiyuan 030024, China |
| TIAN Jian-yan | 1.a.Schoolof Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan 030024, China |
| GAO Yun-song | 2.North Tianyu Electromechanical Technology Co., Ltd, Langfang 065000, China |
|
| 摘要点击次数: |
| 全文下载次数: |
| 中文摘要: |
| 目的 实现滚磨光整加工工艺制定过程中滚抛磨块快速、准确地优选。方法 在分析滚磨光整加工工艺特点的基础上，根据滚抛磨块优选的E-R图构建案例库，建立基于案例推理的滚抛磨块优选模型。针对不同案例特征属性的数据类型，选择合适的特征属性相似度计算方法；通过层次分析法确定案例特征属性的权重，采用加权最近邻居法计算案例间的综合相似度，并通过案例处理获得新问题的优选磨块。采用模糊C均值聚类算法对案例库中的冗余案例进行处理，实现案例库的动态优化。最后，采用实际的不同零件类型的不同数据进行仿真。结果 大量仿真结果表明，采用模糊C均值聚类算法，处理案例库中的冗余案例，可以有效提高案例推理的检索效率和精度；针对实际的新问题，基于模型并通过案例检索、修正，可以从案例库中快速提取出新问题的相似案例，验证了模型的可行性和有效性，重要的是能够为新问题的磨块优选提供决策指导。结论 基于模糊聚类的案例推理技术可以用于滚磨光整加工工艺实施时的滚抛磨块优选。 |
| 英文摘要: |
| The work aims to achieve fast and accurate optimization of the abrasive blocks during formulation of the barrel finishing process. Based on the analysis of the characteristics of the barrel finishing process, the case base was constructed according to the E-R diagram of the optimization of the abrasive blocks, and the optimal model of the abrasive blocks based on case-based reasoning was established. According to the data types of different case feature attributes, the appropriate feature attribute similarity calculation method was selected. The weight of case feature attribute was determined by the analytic hierarchy process, and the weighted nearest neighbor method was used to calculate the comprehensive similarity between cases. The optimal abrasive block of new problem was obtained by case processing. The fuzzy C-means clustering algorithm was used to deal with redundant cases to realize the dynamic optimization of the case base. Finally, different data of different parts types were used for simulation. The results of a large number of simulation studies demonstrated that the fuzzy C-means clustering algorithm could be used to deal with the redundant cases in the case base, which could effectively improve the retrieval efficiency and accuracy of case-based reasoning. For the actual new problems, based on the model and through case retrieval and correction, similar cases of new problem were quickly extracted from the case base, thus verifying the feasibility and effectiveness of the model. It was important to provide decision guidance for the optimization of the abrasive blocks of the new problem. The case-based reasoning technique based on fuzzy clustering can be used to optimize the abrasive blocks during the implementation of the barrel finishing process. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|
渝公网安备 50010702501715号