To prevent the coating damages of the cutting tools such as abrasion and chipping during machining, the influence of microstructure change on stress generation and relaxation in the coatings during machining should be clarified. However, it was generally difficult to obtain the relationship between stress and microstructure change during machining, because the typical evaluation procedures are known to destruct the cutting tools in order to conduct the microstructure observations. Therefore, the combination of non-destructive evaluation techniques by using X-ray diffraction is proposed. Those are phase identification, crystal orientation analysis, phase fraction measurement, dislocation density measurement and residual stress measurement in the target area from RT to high temperatures. In the case of a cutting tools made of a cemented carbide (K10 of JIS) with TiN coating, the following conclusions were made: the micro strain which has liner relation to dislocation density squared was decreased in TiN coating due to heating over a coating temperature of 500 ℃, and that was about half value compared with the original at a temperature of 750 ℃. The stress change in TiN coating under high temperatures was composed of three kind of factor which are the difference of thermal expansion on TiN coating and cemented carbide, the volumetric shrinkage of TiN coating by recovery of the micro strain and the tensile creep strain in cemented carbide. In order to preserve the compressive stresses in TiN coating under high temperatures, the coating process must be carried out at higher process temperatures and in low bias voltages. In addition, cemented carbides should be selected in that of the coarse WC and Co grain size, the low Co compositions and the large amount of precipitates, on account of keeping the low creep rate.

Selective laser sintering hybrid milling (SHM) is an advanced manufacturing technology that combines the flexibility of additive manufacturing with the precision of traditional machining. In SHM, instead of machining the products after they are completely formed using selective laser sintering (SLS), the milling process is conducted alternatively with the SLS. This allows direct fabrication of extremely complicated and high-precision products on the same workstation. However, shrinkage owing to SLS is a fundamental problem of this technology, because it creates significant dimensional errors in the final product. In this study, a method is proposed to calculate shrinkage error in SHM based on equations built from the data collected using FEA. Consequently, the calculation result is used to compensate the SHM shrinkage error. The experimental results of this study confirm that the error prediction model and the proposed compensation technique work efficiently in reducing SHM error.

In polymer injection molding, injection compression molding is applied to actively control the melt pressure in the mold cavity during molding process. The authors have developed an in-mold pressing molding method based on thick wall injection molding to prevent voids inside molded products. In this paper, we investigated the influence of the core block driving method during in-mold pressing molding on the flow behavior of glass fiber reinforced polyamide 66, on the following; generation of voids inside molded products, glass fiber orientation, appearance and surface roughness of molded products, and tensile strength. The results show that the core back using core block is effective for improving the appearance and surface properties of molded products, and that the compressive force generated by the core block improves the strength of molded products.

Cutting force is one of the most important information in order to know machining process and optimize cutting conditions in end milling. An external sensor like a dynamometer is widely used to measure cutting force in the most researches. However, using a dynamometer is inadequate to measure cutting force practically in factories. Thus, the sensor-less cutting force monitoring method is proposed in this study. Cutting force is predicted by the real time end milling simulator, and the predicted cutting force is synchronized with the actual cutting force in the proposed method. The required parameters for the cutting force prediction can be determined from the spindle motor toque monitored without any additional sensors, and can be determined within 10 seconds at the beginning of milling operation without any additional cutting test. The predicted milling force has good agreement with the milling force measured by a dynamometer. Therefore this method can be used practically as the sensor-less cutting force monitoring method in factories.

In this paper, we propose a new method for setting parameters on image inspection system automatically, by using the Deep Learning. Generally, an image processing software built into an image inspection device has parameters that must be set manually. That is to say, the quality of parameter setting depends on a degree of operator's skill or health condition and so on, and the quality of an inspection by an automatic visual inspection system depends on the parameters set by the operator. In other words, it is necessary to set the parameters stably. Therefore, in this study, the Deep Learning model accumulates know-how to set the parameters, and this learned model sets the parameters to the visual inspection device automatically. Especially, we deal with the comparing inspection system requiring to set parameters of a template image. In the experiment, it was confirmed that the template set by our method based on the Pix2pix Deep learning model was capable of automatic inspection of the same level as the template set by the operator.

Teleoperation is one of the technologies for supporting operators, and its development is strongly demanded. Acceleration-based four-channel Bilateral Control (ABC) is known as a method of teleoperation and achieves highly precise impedance transmission. The gain scheduling for bilateral control has basically been focused on the stability by the model-based approach. However, describing the contact motion and precise identification of some nonlinear terms are sometimes highly difficult. Moreover, the gain parameters between the master and slave tend to be set the same although the transfer function of them are different. Therefore, this paper considers the gain setting from the perspective of precise impedance transmission and proposes the evaluation index-based gain scheduling for ABC by using the experimental data. This paper also discusses the designing of gradient-descent algorithm for an actual gain setting by taking the obtained knowledge from evaluation index-based gain scheduling into consideration. The effectiveness of proposed gain scheduling and gain tuning methods were verified through experiments.