Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

researchmap

Publishing type：Research paper (international conference proceedings)  

In recent years, the needs associated with the development of new technologies in the manufacturing industry that utilize big data typified by the Internet-of-Things (IoT) and artificial intelligence (AI) have been increasing. Recent computer-aided manufacturing (CAM) systems have evolved so that unskilled technicians can create tool paths relatively easily with numerically controlled (NC) programs, but tool-cutting conditions used for machining cannot be automatically determined. Therefore, many unskilled technicians often set the cutting conditions based on the recommended conditions described in the tool catalog. However, given that the catalog contains large-scale data on machining technology, setting the proper conditions becomes a time-consuming and inefficient process. In this study, we aimed to construct a system to support unskilled technicians to determine the optimum machining conditions. To this end, we constructed a prediction model using a random forest machine learning method to predict the cutting conditions. It was confirmed that the prediction with the random forest method can be performed with high accuracy based on the cutting conditions recommended by the tool maker. Thus, the effectiveness of this method was verified.

DOI： 10.1115/DETC2020-22126

Scopus

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.20965/ijat.2019.p0756

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：The Japan Society for Precision Engineering  

<p>A novel datamining method has been needed because the IoT (Internet of things) is spread over various kinds of industrial fields. We therefore propose to apply a data mining method to tool catalog data-base to improve the manufacturing technologies with machine tools because it is considered to include a useful information derived from tool manufacturing technology as a big-data. In the present report, we look at MIC (Maximal Information Coefficient) as a novel processing method to search for a new knowledge in tool data data-base, and construct a hierarchical clustering method based on MIC as a data mining method. Comparing a predicting equation derived from the conventional catalog mining method based on a traditional statistics with one based on MIC processing method, we investigate a function of MIC in data mining for end milling conditions. As a result, it can be seen that a constructed method (MIC data mining method) makes it feasible efficiently to find out essential variables in the radius end mill database because a derived practical formula has less interactions than conventional one with keeping the same prediction accuracy.</p>

DOI： 10.2493/jjspe.85.260

CiNii Article

researchmap

Language：Japanese   Publisher：The Japan Society of Mechanical Engineers  

<p>We attempt to construct a novel technology development utilizing big data such as Deep Learning in the manufacturing industry. Especially, we look at the data mining method and the tool catalog as a useful big data base which is updated by tool makers because it is easy for CAD/CAM engineers and machine tool operators to obtain it in the manufacturing fields. In the present report, we proposed the visualization and consideration of cutting condition determination process based on a decision tree method which is one type of statistical analysis method for radius-endmill data base. We also developed a cutting condition prediction system with a random forest which is a type of machine learning method applying a decision tree. Moreover, we performed a case study in endmilling under deriving cutting conditions by the proposed method, which is an unknown and expanded cutting condition based on tool catalog data base. As a result, it is demonstrated that the support based on machine learning is found to be effective to select a cutting condition including an unknown cutting condition in tool catalog data base.</p>

DOI： 10.1299/transjsme.19-00215

CiNii Article

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

© ISAAT 2018 - 21st International Symposium on Advances in Abrasive Technology. All rights reserved. In this study, the ring shaped SiC ceramics applied to sliding components are selected as specimens. In the surface of SiC ceramics, many scratches penetrating the inner edge to outer one are generated in random direction by conventional lapping. The scratches affect the surface functions in prevention of fluid exuding from the outer side to the inner side of SiC ring and have low friction force on the finished surface as a sliding material. In this study, the concentric mutual lapping is proposed to remove the scratches by conventional lapping. Then, the surface topography is evaluated quantitatively by the white light interferometer and proposed the vectorial and quantitative analysis of surface profile. As a result, the concentric mutual lapping can remove scratches quickly by the conventional lapping. And then circumferential scratches along a lapping direction were generated. In addition, we analyzed effect of surface topography on the surface function as a sliding material by sliding tests. From the investigation, it turned out that the concentric mutual lapping suppressed the difference in surface functions depending on the sliding direction.

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

© 2018 CURRAN-CONFERENCE. All rights reserved. In the grinding wheel catalog data-set, the recommended grinding conditions are shown in reference to five factors (abrasive grain, grain size, grade, structure, and bonding material) of the three main elements (abrasive grain, bonding material, and pore). Since systematic arrangement is not made, grinding conditions (cutting speed, table feed, depth of cut) have to be decided on the basis of an experienced engineer's information or experience. Moreover, although the setting of the five factors of the three elements of a grinding wheel is important parameter that affects the surface quality and grinding efficiency, it is difficult to determine the optimal combination of workpiece materials and grinding conditions. In this research, a support system for effectively deciding the desired grinding wheel was built by using a decision tree technique, which is one of the data-mining techniques. This system extracts a significant tendency of grinding wheel conditions from catalog data. As a result, a visualization process was proposed in correspondence to the action of the grinding wheel elements and their factors to the material characteristics of the workpiece material.

Scopus

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.20965/ijat.2018.p0238

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.20965/ijat.2017.p0084

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：AMER SOC MECHANICAL ENGINEERS  

As electronic devices and products are being miniaturized, the printed wiring boards (PWBs) within them are also being miniaturized. Therefore, it is becoming increasingly difficult to decide the drilling conditions required for producing small-diameter and high-density holes. We have been focusing on drilling conditions recommended in drill catalogs and have been attempting to gather knowledge that drilling experts use to decide the drilling conditions. In this study, we classify drills using the relationship between the diameter and the flute length and hence show that the methods used for setting the cutting conditions are different in different regions of a PWB. In addition, by using a catalog of microdrills that use alloy steel as the work material, we discuss how unique drilling conditions can be set for PWBs.

DOI： 10.1115/DETC2017-67680

Web of Science

Scopus

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/ISFA.2016.7790146

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.4028/www.scientific.net/MSF.874.481

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

This paper deals with the characteristics of tool wear in small end milling of nickel-titanium alloy which is used as a medical material. Cutting experiments were carried out by varying the axial relief angle of an end mill of a diameter of 0.5 mm from 0 to 15 degrees with a step of 5 degrees, and tool wear and surface roughness was evaluated. The result revealed that tool wear of a small end mill with an axial relief angle of 0 degree was smaller by 60% than that of 15 degrees, suggesting that tool wear is reduced more with a smaller axial relief angle.

DOI： 10.4028/www.scientific.net/MSF.874.429

Scopus

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.4028/www.scientific.net/AMR.1136.265

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.17265/2159-5275/2015.11.002

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.4028/www.scientific.net/AMR.1136.162

researchmap

Publishing type：Research paper (international conference proceedings)  

As electronic devices and products are being miniaturized, Printed Wiring Boards (PWBs) within them are also being miniaturized. Therefore, drilling conditions for small and high density holes have become more difficult to decide. We focused on drilling conditions recommended in drill catalogs and attempted to find out the knowledge that experts of drilling use to decide drilling conditions. In this paper, we focused on web thickness, one of the drill parameters, and qualitative variables written in the catalogs. The results clarified the importance of web thickness in drilling conditions and meaning of qualitative variables.

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.4028/www.scientific.net/KEM.625.213

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.4028/www.scientific.net/KEM.656-657.164

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Trans Tech Publications Ltd  

Since demands for Carbon Fiber Reinforced Plastics (CFRP) are increasing, the number of the studies on machining of CFRP is also increasing. However, since there are already reports on a trimming of a surplus portion or a drilling, we focus on a face machining and a generating the step shape with several cutting tools. Problems in the machining of CFRP include an occurrence of the burr and delamination. Therefore, in this report, we investigate these problems in face milling. And, the machining behavior (Cutting temperature, Cutting force) during the machining is estimated.

DOI： 10.4028/www.scientific.net/AMR.1017.310

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：TRANS TECH PUBLICATIONS LTD  

Chatter vibration in cutting processes usually leads to surface finish degradation, tool damage, cutting noise, energy loss, etc. Self-excited vibration particularly seems to be a problem that is easily increased to large vibration. The regenerative effect is considered as one of the causes of chatter vibration. Although the chatter vibration occurs in various types of processing, the end-milling is a typical process that seems to cause the chatter vibration due to a lack of rigidity of one or more parts of the machine tools, cutting tool, and work-piece. The aim of our research is to propose a simple method to control chatter vibration of the end-milling process on the basis of a coupling model integrating the related various elements. In this study, hammering tests were carried out to measure the transfer function of a machine tool and cutting tool system, which seems to cause vibration. By comparing these results, finite elemental method (FEM) analysis models were constructed. Additionally, cutting experiments were carried out to confirm the chatter vibration frequencies in end-milling with a machining center. In the hammering tests, impulse hammer and multiple acceleration pick-ups are connected to a multi-channel FFT analyzer and estimate the natural frequencies and natural vibration modes. A simplified FEM model is proposed by circular section stepped beam elements on the basis of the hammering test results, considering a coupling effect. In comparisons of the calculated results and hammering test results, the vibration modes are in good agreement. As a result, the proposed model accurately predicts the chatter vibration considering several effects among the relating elements in end-milling. Moreover, it can be seen that the chatter vibration is investigated from a viewpoint of the integrating model of the end-milling process. © (2014) Trans Tech Publications, Switzerland.

DOI： 10.4028/www.scientific.net/AMR.939.201

Web of Science

Scopus

researchmap

Language：Japanese   Publisher：The Japan Society for Abrasive Technology  

In this study, we performed end-mill processing of a difficult-to-cut material (JIS SUS310 stainless steel) and observed it with high-performance infrared thermography. We discuss the relationship between the tool temperature and difference in number of teeth and tool diameter. The tool temperature distribution can be analyzed at each rotating tool position in the end-mill process from images, considering the relationship between the duration of each frame and the rotating speed of the end-mill tool. Moreover, we examined the validity by comparing the results of unsteady temperature analysis by the finite element method (FEM) and the measurement results.

DOI： 10.11420/jsat.58.457

CiNii Article

CiNii Books

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Trans Tech Publications Ltd  

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.

DOI： 10.4028/www.scientific.net/AMR.1017.334

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：AMER SOC MECHANICAL ENGINEERS  

We previously proposed data-mining system to derive useful information from the data and attempt to determine the ball-nose end-milling conditions in a rapid prototype manufacturing system. Practical end-milling condition decision equations are derived to determine the end-milling conditions at each cluster by using response surface method. End-millings of hardened die steel JIS SKD61 (HRC53) and DH31S were carried out to investigate the practicability of derived mining conditions under contour line milling. As a result, our catalogmining system was found to be effective in selecting the endmilling conditions as the first trial condition. Catalog mining can derive indicative cutting conditions for unskilled engineers.

DOI： 10.1115/IMECE2014-36971

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：TRANS TECH PUBLICATIONS LTD  

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. © (2014) Trans Tech Publications, Switzerland.

DOI： 10.4028/www.scientific.net/AMR.939.547

Web of Science

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：The Japan Society for Precision Engineering  

Machining is often performed by a machining center using various cutting tools and end-milling 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 them. Data-mining methods were attracted attention 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 methods and also principal component regression. We focused on the shape element of catalog data and we visually clustered ball end-mills from the viewpoint of tool shape, which here meant the ratio of dimensions, by using the k - means method. Expressions for calculating end-milling conditions were derived from response surface method. We conducted end-milling experiments to validate the availability of calculated values.

DOI： 10.2493/jjspe.79.964

Scopus

CiNii Article

CiNii Books

researchmap

Language：Japanese   Publisher：The Japan Society for Abrasive Technology  

This paper describes micro-drilling processes of printed wiring boards (PWBs) containing high-hardness and high-thermal conduction fillers. When processing these PWBs, drill tools show severe wear because the filler has high hardness. Therefore, we examined the characteristics of drill wear and showed the usefulness of diamond-coated drills. The diamond-coated drill is effective against PWBs with higher filler filling rate. Moreover, we investigated the cutting force and PWB temperature during drilling. Macroscopically, cutting force was seen to be more significantly influenced by drill wear compared to material physical properties. On the other hand, microscopically the PWB temperature during drilling was significantly influenced by material physical properties.

DOI： 10.11420/jsat.57.27

CiNii Article

CiNii Books

researchmap

Other Link： https://jlc.jst.go.jp/DN/JALC/10013686603?from=CiNii

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：TRANS TECH PUBLICATIONS LTD  

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. © (2013) Trans Tech Publications, Switzerland.

DOI： 10.4028/www.scientific.net/AMR.797.177

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：AMER SOC MECHANICAL ENGINEERS  

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. Endmilling condition decision determinants derived from our datamining process are important indicators for adjusting endmilling conditions on the basis of end-milling efficiency and tool life. Copyright © 2013 by ASME.

DOI： 10.1115/IMECE2013-63371

Web of Science

Scopus

researchmap

Language：Japanese   Publisher：Doshisha University  

Nowadays, manufacturing companies have been demanded to develop new technologies to determine the machining conditions in agile and trial manufacturing fields. We therefore attempt to develop an estimating method for end-mill processes by an infrared imagery. In the present paper, we establish to monitor these processes with an infrared thermography and investigate the relationship between tool temperature and milling condition. As a result, this method is found to be effective to estimate an influence of material removal rate (MRR) on the tool temperature in the end-mill process.

DOI： 10.14988/pa.2017.0000012829

CiNii Article

CiNii Books

researchmap

Other Link： https://doors.doshisha.ac.jp/duar/repository/ir/15459/?lang=0

Publishing type：Research paper (scientific journal)  

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.

DOI： 10.20965/ijat.2012.p0061

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：TRANS TECH PUBLICATIONS LTD  

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. © (2012) Trans Tech Publications, Switzerland.

DOI： 10.4028/www.scientific.net/AMR.565.472

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：AMER SOC MECHANICAL ENGINEERS  

Choosing cutting tools and end-milling conditions depends on expert engineersâTM knowledge and experience, and often a lengthy process of trial and error is required before they obtain appropriate cutting conditions. We have previously proposed data-mining methods to make decisions about end-milling conditions on the basis of catalog data. We cut hardened die steel JIS SKD61 under three kinds of end-milling conditions: catalog recommended conditions, conditions derived from datamining (mined conditions), and expert engineer conditions. We used LCA to evaluate quantitatively the environmental impact resulting from these conditions. We designed an index model of the environmental burden in the technical mastering process under the three condition. The results show that unskilled engineers could decrease the cumulative environmental burden by working under the mined condition in the initial stage. Recommending the use of the mined condition in the initial stage is therefore considered best. Copyright © 2012 by ASME.

DOI： 10.1115/DETC2012-70843

Web of Science

Scopus

researchmap

Language：Japanese   Publisher：The Japan Society for Abrasive Technology  

Data-mining methods were used to support decisions about reasonable cutting conditions. The aim of our research was to extract valuable new knowledge by applying data-mining techniques to a tool catalog. We used both hierarchical and non-hierarchical clustering of catalog data, and also applied multiple regression analysis. We fixed the outside diameter D of the tool shape parameter as a constant trivial value in this data-mining method. We examined the influence rate of other tool shape parameters to extract valuable new knowledge hidden in trivial parameters.

DOI： 10.11420/jsat.56.173

CiNii Article

CiNii Books

researchmap

Language：Japanese   Publisher：The Japan Society for Abrasive Technology  

This paper describes the micro-drilling process of printed wiring boards (PWBs) containing high hardness and high thermal conductive fillers. When processing these PWBs, the drill tools undergo severe wear due to the high hardness of the filler. Therefore, we examined the characteristics of drill wear and derived practical formulas of drill wear from these results. These equations are similar to Taylor's tool life equation. Moreover, we investigated the effects of thermal conductivity on temperature during the drilling process. The temperature around the drill hole was shown to be a complex phenomenon according to increasing filler content of PWBs.

DOI： 10.11420/jsat.56.244

CiNii Article

CiNii Books

researchmap

Language：Japanese   Publisher：The Japan Society for Abrasive Technology  

We investigated the use of data mining methods to help engineers decide on end-milling conditions. The aim of our research is to find new knowledge by applying data mining techniques to a tool catalog data. We used hierarchical and non-hierarchical clustering methods as well as principal component analysis and multiple regression analysis. We used the K-means method and focused on the shape presented in the catalog data, and grouped end-mills from the viewpoint of the tool shape, i.e., the ratios of its dimensions. We decreased the number of variables by variable cluster analysis. In addition, we found an expression for calculating cutting conditions and compared the calculated values with those in the catalog. There were three end-milling conditions: conditions recommended in the catalog, conditions derived by data mining, and proven cutting conditions for die machining (rough processing).

DOI： 10.11420/jsat.56.824

CiNii Article

CiNii Books

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：TRANS TECH PUBLICATIONS LTD  

This paper describes micro-drilling processes for printed circuit boards (PCBs) containing fillers with high hardness and high thermal conductivity. Inspired primarily by devices such as digital cameras, laptop computers, and wireless communications devices, the electronics field today is continuously demanding smaller, lighter, and more technologically advanced high performance devices. However, that the increase in semiconductor-generated heat tends to affect such devices negatively. Additionally, from the viewpoint of environmental problems, electric vehicles and LEDs are being developed actively. PCBs are one of the principal components for building such devices. In recent years, PCBs containing alumina fillers with high thermal conductivity have been developed and begun to be widely used. However, when processing these PCBs, the drill tools become severely worn because of the filler's high hardness. We therefore examined the drill wear characteristics. The results show the filler is the main factor that causes drill wear, while the increase in cutting force does not affect it. The cutting force increases with the drill wear linearly. Moreover, the characteristic of PCBs with higher filler content rates is close to that of inorganic material like ceramics. © (2012) Trans Tech Publications, Switzerland.

DOI： 10.4028/www.scientific.net/AMR.565.442

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：AMER SOC MECHANICAL ENGINEERS  

This paper describes micro-drilling processes for Printed Circuit Boards (PCBs) containing fillers with high hardness and high thermal conductivity. Powered primarily by devices such as digital cameras, laptop computers, and wireless communications devices, current the electronics field today is continuously demanding smaller, lighter, and more technologically advanced high performance devices. It has been a problem from such a tendency that the increase in amount of semiconductor-generated heat has a undesirable influence on such devices. Additionally, from a viewpoint of environmental problems, electric vehicles and LEDs are developed actively. One of the principal components for building such devices is Printed Circuit Boards (PCBs). In recent years, PCBs containing alumina fillers with high thermal conductivity have been developed and begun to be widely used. However, when processing these PCBs, the drill tools severely wear because of the filler's high hardness. We therefore examined the drill wear characteristics and derived the practical drill wear formulas from the results to develop a suitable CAM system. It can be seen that these equations are similar to Taylor's tool life equation. We also investigated the thermal conductivity effect on temperature during drilling processes. The temperature around the drill hole was shown to be a complex phenomenon according to increasing filler content to PCBs. Copyright © 2012 by ASME.

DOI： 10.1115/ISFA2012-7214

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：TRANSACTION PUBLISHERS  

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. © (2012) Trans Tech Publications, Switzerland.

DOI： 10.4028/www.scientific.net/KEM.523-524.386

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：ELSEVIER SCIENCE INC  

The purpose of the present study is to apply data-mining methods to support the decision of reasonable cutting conditions. Although an enormous amount of information is listed in a catalog, it is not possible to know all of it. Seen from the viewpoint of the user, this enormous amount of information becomes a hindrance. For example, even if an expert worker does not look at a catalog, in end-mill processing, he can decide the appropriate processing condition efficiently from experience; however, this type of situation creates difficult problems for an unskilled worker or a skilled worker with little experience. The recommended cutting condition for every type of material is listed in a catalog together with the appropriate tool, but it takes much time and labor to search and examine the catalog to find the right tool, and this process is inefficient. The main subject of our research was to support the processing condition of the end-mill for each precision tool efficiently based on end-mill clusters. Our research applied the techniques of data mining, in particular, non-hierarchy clustering and hierarchy clustering, to catalog data. With these techniques, we applied multiple regression analysis and reached the following main conclusions. As a first step, we paid attention to the shape element of catalog data. In addition to using conventional mining processes, we grouped end-mills from the viewpoint of tool shape, which meant the ratio of dimensions, visually by applying the K-means method. We applied variable cluster analysis next to each cluster and extracted an predictor variable to represent each cluster, and we performed multiple regression analysis and derived a cutting condition decision formula. The cutting condition decision formula provided high accuracy. The accuracy was higher than the results achieved through mining of all data. A more highly precise processing condition decision formula was derived by doing mining again, excluding the peculiar data clusters such as small diameter end-mill. We understood what was effective for cutting condition decision to be factors related to blade length and the ratio of the full length, factors which have not been singled out through background knowledge or expert knowledge, but were noticed as an effect of catalog mining. © 2010 Elsevier Inc. All rights reserved.

DOI： 10.1016/j.precisioneng.2010.11.005

Web of Science

Scopus

researchmap

Language：Japanese   Publisher：The Japan Society of Mechanical Engineers  

DOI： 10.11522/pscjspe.2011S.0.255.0

CiNii Article

CiNii Books

researchmap

Publishing type：Research paper (international conference proceedings)  

The aim of our research was to extract new knowledge by applying data mining techniques to machine tool maker catalogs. We cut a SKD61 under three types of cutting conditions: those recommended in tool maker catalogs, those derived from data mining, and those recommended by veteran engineers. Conditions derived from data mining were found to be more stable than those recommended in tool maker catalogs. We fed back based on the catalog mining process. We found improvement accuracy of cutting conditions by calculating the corrective coefficient. As a result, these cutting conditions decision formulas were found to be highly accurate.

Scopus

researchmap

Publishing type：Research paper (international conference proceedings)  

Choosing cutting tools and conditions depends on expert engineers' knowledge and experience, and often a lengthy process of trial and error is required before they obtain appropriate end-milling conditions. We have previously proposed data mining methods to make decisions about end-milling conditions on the basis of catalog data. We cut hardened die steel JIS SKD61 under three kinds of end-milling conditions: catalog conditions, mined conditions, expert engineer conditions. We used LCA to quantitatively evaluate the environmental impact resulting from these conditions. Results showed that the mined condition is environmentally superior to the catalog conditions.

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：TRANS TECH PUBLICATIONS LTD  

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). © (2011) Trans Tech Publications, Switzerland.

DOI： 10.4028/www.scientific.net/AMR.325.345

Web of Science

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：AMER SOC MECHANICAL ENGINEERS  

Data-mining methods were used to support decisions about reasonable cutting conditions. The aim of our research 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 end mills from the viewpoint of tool shape, which here meant the ratio of dimensions, by using the k-means method. We then decreased the number of variables by using hierarchical cluster analysis. We also found an expression for calculating the best cutting conditions, and we compared the calculated values with the catalog values. We did 15 minutes of cutting work using three kinds of cutting conditions: conditions recommended in the catalog, conditions derived by data-mining, and proven cutting conditions for die machining (rough processing). © 2010 by ASME.

DOI： 10.1115/MSEC2010-34199

Web of Science

Scopus

researchmap

J-GLOBAL

researchmap

Event date： 2016.10.2 - 2016.10.5

Language：English   Presentation type：Oral presentation (general)  

Venue：Stockholm, Sweden  

researchmap

Event date： 2016.8.1 - 2016.8.3

Language：English   Presentation type：Oral presentation (general)  

Venue：Cleveland, USA  

researchmap

Event date： 2016.5.30 - 2016.6.3

Language：English   Presentation type：Poster presentation  

Venue：Nottingham, UK  

researchmap

Event date： 2015.10.18 - 2015.10.22

Language：English   Presentation type：Oral presentation (general)  

Venue：Kyoto, Japan  

researchmap

Event date： 2015.10.4 - 2015.10.7

Language：English   Presentation type：Oral presentation (general)  

Venue：Jeju, Korea  

researchmap

Event date： 2015.6.1 - 2015.6.5

Language：English   Presentation type：Poster presentation  

Venue：Leuven, Belgium  

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap