Research On Optimal Model Of The Abrasive Blocks Based On Fuzzy Clustering And Case-based Reasoning

The surface quality has a great influence on the life and serviceability of parts.Barrel finishing process is an important way to improve the surface quality of the parts.It has been widely used in the surface treatment of the part,due to its low processing cost,its batch processing,and its high production efficiency,and etc.Abrasive blocks are one of the key factors affecting the processing effect and efficiency.In the barrel finishing process,the selection of the abrasive blocks needs to be directed to different processing objects and processing requirements at present.The actual machining process needs to be tested on the basis of the operator's rich experience to determine,which lacks deeper theoretical guidance.At the same time,a large number of successful historical cases using traditional paper experimental documents or electronic documents as data storage cannot play an expeditious and effective role in the new process planning.For this reason,how to use the existed case data to achieve the rapid optimization of the abrasive blocks is of great research significance.In view of the above problems,this paper proposes "Optimal model of the abrasive blocks based on fuzzy clustering and case-based reasoning".Firstly,theoptimal case base of the abrasive blocks is constructed.Then the case-based reasoning and fuzzy clustering algorithm are used to realize the fast optimization of the abrasive blocks.In order to provide users with friendly,intuitive and easy-to-operate man-machine interface,the C# language is used to design preferred platform of the abrasive blocks.The main contents of this paper are:(1)The technological process of barrel finishing process is analyzed in depth.The factors that affect the preferred parameters and the indicators of the abrasive blocks are selected to establish a optimal case base of the abrasive blocks.(2)The principle diagram for the optimization of the abrasive blocks based on case-based reasoning is designed.The weighted comprehensive similarity is used to retrieve case,the weight of case feature attribute is determined by the analytic hierarchy process,and the actual data of the factory is used for simulation research.The results show that the proposed method can quickly and accurately optimize the desired abrasive block.(3)In order to remove the redundant case of the case base,the fuzzy C-means clustering algorithm improve by subtractive clustering is used to streamline the case base.Firstly,subtractive clustering is used to determine the the upper limit of initial cluster number and initial clustering center of fuzzy C-means clustering algorithm.Then,actual factory processing data are clustered and analyzed by fuzzy C-means clustering algorithm,and the case database issimplified.The results show,the method can effectively save the storage space of the case and improve the retrieval efficiency of case reasoning.(4)Based on the existed barrel finishing database of the research group,the C# language is used to design the optimization platform of the abrasive blocks,and the optimal mode of the abrasive blocks based on fuzzy clustering and case-based reasoning is applied in the platform.An intelligent optimization platform of the abrasive blocks is built for users.In order to realize the intelligent optimization of abrasive blocks in the barrel finishing,this paper uses fuzzy C-means clustering and case-based reasoning to establish the optimization model of abrasive blocks.Using the data of the parts processed in practice to verify,this method can quickly and accurately select the abrasive block required for the parts to be processed while satisfying the processing requirements,and provides the decision guidance for the optimization of abrasive blocks in the process of barrel finishing.