An Indicative End-Milling Condition Decision Support System Using Data-Mining for Difficult-to-Cut Materials Based on Comparison with Irregular Pitch and Lead End-Mill and General Purpose End-Mill

2013 ◽  
Vol 797 ◽  
pp. 177-182
Author(s):  
Hiroyuki Kodama ◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
Keiji Ogawa
Keyword(s):  
Data Mining ◽  
End Milling ◽  
General Purpose ◽  
Shape Parameters ◽  
End Mill ◽  
Variable Cluster ◽  
Tool Shape ◽  
Milling Condition ◽  
Using Data

Data-mining methods using hierarchical and non-hierarchical clustering are proposed that will help engineers determine appropriate end-milling conditions. We have constructed a system that uses clustering techniques and tool catalog data to support the determination of end-milling conditions for different types of difficult-to-cut materials such as austenitic stainless steel, Ni-base superalloy, and titanium alloy. Variable cluster analysis and the K-means method were used together to identify tool shape parameters that have a linear relationship with the end-milling conditions listed in the catalogs. The response surface method and significant tool shape parameters obtained by clustering were used to derive end-milling condition decision equations, which were used to determine the indicative end-milling conditions for each material. Comparison with the conditions recommended by toolmakers demonstrated that our proposed system can be used to determine the cutting speeds for various difficult-to-cut materials.

An End-Milling Condition Decision Support System Using Data-Mining for Difficult-to-Cut Materials

2012 ◽  
Vol 565 ◽  
pp. 472-477 ◽  
Author(s):  
Hiroyuki Kodama ◽  
Masatoshi Shindou ◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
Keiji Ogawa
Keyword(s):  
Data Mining ◽  
Decision Support ◽  
Decision Support System ◽  
Support System ◽  
End Milling ◽  
Shape Parameters ◽  
Clustering Methods ◽  
Tool Shape ◽  
Hierarchical Clustering Methods ◽  
Milling Condition

We proposed the data-mining methods using hierarchical and non-hierarchical clustering methods to help engineers decide appropriate end-milling conditions. The aim of our research is to construct a system that uses clustering techniques and tool catalog data to support the decision of end-milling conditions for difficult-to-cut materials. We used variable cluster analysis and the K-means method to find tool shape parameters that had a linear relationship with the end-milling conditions listed in the catalog. We used the response surface method and significant tool shape parameters obtained by clustering to derive end-milling condition. Milling experiments using a square end mill under two sets of end-milling conditions (conditions derived from the end-milling condition decision support system and conditions suggested by expert engineers) for difficult-to-cut materials (austenite stainless steel) showed that catalog mining can be used to derive guidelines for deciding end-milling conditions.

Proposal of Ball End-Milling Condition Decision Methodology Using Data-Mining from Tool Catalog Data

2012 ◽  
Vol 523-524 ◽  
pp. 386-391 ◽  
Author(s):  
Hiroyuki Kodama ◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
Keiji Ogawa ◽  
Hiroaki Hukasawa
Keyword(s):  
Data Mining ◽  
End Milling ◽  
Cutting Tools ◽  
Tool Selection ◽  
Machining Center ◽  
Nc Program ◽  
Tool Shape ◽  
End Mills ◽  
Milling Condition ◽  
Using Data

Machining is often performed by a machining center using various cutting tools and conditions for different shapes and materials. Recent improvements in CAM system make it easier for even unskilled engineers to generate NC programs. In the NC program, the end-milling conditions are decided by engineers. However, engineers need to decide the order of the process, cutting tool selection, and the end-milling conditions on the basis of their expertise and background knowledge because the CAM system cannot automatically decide. Data-mining methods were used to support decisions about end-milling conditions. Our aim was to extract new knowledge by applying data-mining techniques to a tool catalog. We used both hierarchical and non-hierarchical clustering of catalog data and also used applied multiple regression analysis. We focused on the shape element of catalog data and we visually grouped ball end-mills from the viewpoint of tool shape, which here meant the ratio of dimensions, by using the k-means method. We also found an expression for calculating end-milling conditions, and we compared the calculated with the catalog values.

scholarly journals Proposal of Ball End-milling Condition Decision Methodology Using Data-mining from Tool Catalog Data

2013 ◽  
Vol 79 (10) ◽  
pp. 964-969 ◽  
Author(s):  
Hiroyuki KODAMA ◽  
Toshiki HIROGAKI ◽  
Eiichi AOYAMA ◽  
Keiji OGAWA
Keyword(s):  
Data Mining ◽  
End Milling ◽  
Ball End Milling ◽  
Milling Condition ◽  
Using Data

Investigation of End-Milling Condition Decision Methodology Based on Data Mining for Tool Catalog Database

2012 ◽  
Vol 6 (1) ◽  
pp. 61-74 ◽  
Author(s):  
Hiroyuki Kodama ◽  
◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
Keiji Ogawa ◽  
...  
Keyword(s):  
Data Mining ◽  
Decision Making ◽  
Expert Knowledge ◽  
End Milling ◽  
New Knowledge ◽  
Tool Shape ◽  
End Mills ◽  
Milling Condition ◽  
Clustering Data ◽  
Nonhierarchical Clustering

Data mining supports decision making about reasonable end-milling conditions. Our research objective is to excavate new knowledge with mining effect by applying data mining techniques to a tool catalog. We use hierarchical and nonhierarchical clustering data mining with catalog data by applying multiple regression analysis and focusing on the catalog data shape element. We visually grouped end-mills on the basis of tool shape, considering the ratio of tool shape dimensions, by employing the K-means method. We found that factors related to blade length and full length ratio are effective in for making end-milling condition decisions. These factors have not previously been singled out through background knowledge or expert knowledge, but they were noticed as a data mining effect.

Use of Catalog Mining to Extract Valuable New Knowledge Hidden in Trivial Parameters

2013 ◽  
Author(s):  
Hiroyuki Kodama ◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
Keiji Ogawa
Keyword(s):  
Data Mining ◽  
End Milling ◽  
Cutting Speed ◽  
Principal Component Regression ◽  
Principal Component ◽  
Clustering Methods ◽  
New Knowledge ◽  
Tool Shape ◽  
Milling Condition ◽  
Criterion Variables

We have developed a process that uses both hierarchical and non-hierarchical clustering methods to mine data in tool catalogs. Principal component regression is used for quantifying the correlation between the predictor and criterion variables, and multiple regression analysis is used for creating an end-milling condition determinant matrix for each cluster. We fixed the outside diameter of the tool shape parameter as a constant trivial value and examined the correlation between the other tool shape parameters and the end-milling conditions. We thereby extracted valuable new knowledge hidden in trivial parameters and built a hypothesis in regards to data-mining effect. We found that cutting speed is the most important of the criterion variables and that the number of determination coefficient is no less important for determining prediction accuracy of end-milling condition decision equations. End-milling condition decision determinants derived from our data-mining process are important indicators for adjusting end-milling conditions on the basis of end-milling efficiency and tool life.

Aid of End-Milling Condition Decision Using Data Mining from Tool Catalog Data for Rough Processing

2011 ◽  
Vol 325 ◽  
pp. 345-350
Author(s):  
Hiroyuki Kodama ◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
Keiji Ogawa
Keyword(s):  
Data Mining ◽  
Cluster Analysis ◽  
End Milling ◽  
Hierarchical Cluster ◽  
Cutting Conditions ◽  
New Knowledge ◽  
End Mills ◽  
Milling Condition ◽  
Mining Methods ◽  
Using Data

The uses of data mining methods to support workers decide on reasonable cutting conditions has been investigated in this work. The aim of our research is to find new knowledge by applying data mining techniques to a tool catalog. Hierarchical and non-hierarchical clustering of catalog data as well as multiple regression analysis was used. The K-means method was used and on the shape presented in the catalog data and grouped end mills from the viewpoint of the tool's shape, which here means the ratio of dimensions has been focused. The numbers of variables were decreased using hierarchical cluster analysis. In addition, an expression for calculating the better cutting conditions was found and the calculated values were compared with the catalog values. There were three cutting conditions: conditions recommended in the catalog, conditions derived by data mining, and proven cutting conditions for die machining (rough processing).

Experimental Verification of End-Milling Condition Decision Support System Using Data-Mining for Difficult-to-Cut Materials

2014 ◽  
Vol 1017 ◽  
pp. 334-339
Author(s):  
Hiroyuki Kodama ◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
Keiji Ogawa ◽  
Koichi Okuda
Keyword(s):  
Data Mining ◽  
Decision Support ◽  
Decision Support System ◽  
Support System ◽  
End Milling ◽  
Present Report ◽  
Cutting Speed ◽  
System A ◽  
Milling Condition ◽  
Using Data

Data-mining methods using hierarchical and non-hierarchical clustering are proposed, which could help manufacturing engineers determine guidelines for deciding end-milling conditions. We have constructed a novel system that uses clustering techniques and tool catalog data to support the determination of end-milling conditions for different types of recent difficult-to-cut materials. In the present report, we especially focus on the cutting speed to estimate the performance of this system. A comparison with the conditions recommended by famous tool makers in Japan, reveals that our proposed system can be used to determine the cutting speeds for various difficult-to-cut materials. That is, milling experiments using a square end mill under two sets of end-milling conditions (conditions derived from the end-milling condition decision support system and conditions suggested by expert engineers) for difficult-to-cut materials (austenite stainless steel; JIS SUS310) showed that the catalog mining method is effective for deriving guidelines for deciding end-milling conditions at the beginning of the manufacturing stage.

Investigation of Drilling Conditions of Printed Circuit Board Based on Data Mining Method from Tool Catalog Data-Base

2014 ◽  
Vol 939 ◽  
pp. 547-554 ◽  
Author(s):  
Hisaya Haneda ◽  
Hiroyuki Kodama ◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
Keiji Ogawa
Keyword(s):  
Data Mining ◽  
Printed Circuit Board ◽  
Circuit Board ◽  
Shape Parameters ◽  
Printed Wiring Boards ◽  
Variable Cluster ◽  
Mining Conditions ◽  
Tool Shape ◽  
Drilling Condition ◽  
Drilling Conditions

Data-mining methods using hierarchical and non-hierarchical clustering are proposed that will help engineers determine appropriate drilling conditions. We have constructed a system that uses clustering techniques and tool catalog data to support the determination of drilling conditions for printed wiring boards (PWBs). Variable cluster analysis and the K-means method were used together to identify tool shape parameters that have a linear relationship with the drilling conditions listed in the catalogs. The response surface method and significant tool shape parameters obtained by clustering were used to derive drilling condition decision equations, which were used to determine the indicative drilling conditions for PWBs. Comparison of the conditions recommended by toolmakers demonstrated that our proposed system can be used to determine the drilling condition for PWBs. We carried out the drilling experiments in accordance with the catalog conditions and mining conditions, and estimated the board temperature around a drilled hole, the drilling forces, and the roughness of the drilled hole wall.

Aiding of Micro End-Milling Condition Decision Using Data-Mining from Tool Catalog Data

2018 ◽  
Vol 12 (2) ◽  
pp. 238-245
Author(s):  
Hiroyuki Kodama ◽  
Koichi Okuda ◽  
Kazuhiro Tanaka ◽  
◽  
Keyword(s):  
Data Mining ◽  
End Milling ◽  
Early Stage ◽  
Characteristic Size ◽  
Clustering Methods ◽  
End Mill ◽  
Workpiece Material ◽  
Micro End Mill ◽  
Tool Shape ◽  
Micro End Milling

When the minor diameter of an end-mill is 1.0 mm or less, handling of tools becomes difficult because of the influence of the characteristic size effect and bending of the cutting edge. Furthermore, it is hard for engineers to derive the cutting conditions that can serve as indexes in the early stage of micro end-milling. In this study, a system that can make instantaneous decisions was developed, on the basis of workpiece material-characteristics and tool shape parameters, by applying data mining techniques together with non-hierarchical and hierarchical clustering methods on micro end-mill catalog data. Slotting experiments using cemented carbide square micro end-mill were carried out to investigate the practicability of derived mining conditions under slotting of A7075 (JIS). We found that catalog mining can be used to derive the guidelines for deciding the micro end-milling conditions.

Sign in / Sign up

Export Citation Format

Share Document