• Journal of Powder Materials
• /
• v.31 no.2
• /
• pp.137-145
• /
• 2024

In order to predict the process window of laser powder bed fusion (LPBF) for printing metallic components, the calculation of volumetric energy density (VED) has been widely calculated for controlling process parameters. However, because it is assumed that the process parameters contribute equally to heat input, the VED still has limitation for predicting the process window of LPBF-processed materials. In this study, an explainable machine learning (xML) approach was adopted to predict and understand the contribution of each process parameter to defect evolution in Ti alloys in the LPBF process. Various ML models were trained, and the Shapley additive explanation method was adopted to quantify the importance of each process parameter. This study can offer effective guidelines for fine-tuning process parameters to fabricate high-quality products using LPBF.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.31 no.1
• /
• pp.15-24
• /
• 2006

In simulation input modeling, it is important to identify a probability distribution to represent the input process of interest. In this paper, an appropriate sample size is determined for parameter estimation associated with some typical probability distributions frequently encountered in simulation input modeling. For this purpose, a statistical measure is proposed to evaluate the effect of sample size on the precision as well as the accuracy related to the parameter estimation, square rooted mean square error to parameter ratio. Based on this evaluation measure, this sample size effect can be not only analyzed dimensionlessly against parameter's unit but also scaled regardless of parameter's magnitude. In the Monte Carlo simulation experiments, three continuous and one discrete probability distributions are investigated such as ; 1) exponential ; 2) gamma ; 3) normal ; and 4) poisson. The parameter's magnitudes tested are designed in order to represent distinct skewness respectively. Results show that ; 1) the evaluation measure drastically improves until the sample size approaches around 200 ; 2) up to the sample size about 400, the improvement continues but becomes ineffective ; and 3) plots of the evaluation measure have a similar plateau pattern beyond the sample size of 400. A case study with real datasets presents for verifying the experimental results.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.12
• /
• pp.1-11
• /
• 1993

This paper concentrates on models useful for analyzing the error performance of ML(Maximum Likelihood) estimators of a single unknown signal parameter: that is the error intensity model. We first develop the point process representation for the estimation error and the conditional distribution of the estimator as well as the distribution of error candidate point process. Then the error intensity function is defined as the probability dessity of the estimate and the general form of the error intensity function is derived. We then develop several intensity models depending on the way we choose the candidate error locations. For each case, we compute the explicit form of the intensity function and discuss the trade-off among models as well as the extendability to the case of multiple parameter estimation.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.3-7
• /
• 1995

Force generated during grinding process causes elastic defomation. The effect of this deforms a workpiecs. So grinding system is explainable using the concept of macining elasticity phenomenon. Machining elasticity is defined as ratio between the true depth of c ut, and an importnat factor to affect material removal mchanism and productivity. Generally, to produce accurate surface and dimensionally precise components operators depend on their experiences. Because of these, productivity is reduced and time is wasted. The objective of this reserch is to study the effect of grinding conditions, such as table speed, depth of cut on the machining elasticity parameter.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.6 no.3
• /
• pp.77-84
• /
• 2007

As a life cycle of product bas shortend, Rapid prototypiug has come into the spotlight to shortened the time of producint a prototype. But It followed in laminated directivity and of the prototype production which is decided the interference which Beccuase of invisible rough surface, some inferences have occured during an assembly hour. Consequently, This study on rapid prototyping has parameter to determine surface roughness and surface form precision of total shape. In order to improve Surface form precision, it can control parameters which are Laminate Height, Layer Hatch Overcue, Fill Cure Depth. In addition, we found the parameter which have a deep effect on surface roughness among various parameters, and then, tried to reduce the interference that can be occurred by surface roughness during assembly.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.766-771
• /
• 1992

The hydrodynamic coefficients estimation problem is important to develop an underwater vehicle and design a controller for it. In this paper, an identification theory, the Extended Kalman Filter, is applied to this parameter estimation problem. In the case that a process noise is not used, all of the parameters are almost exactly converged to the true values respectively. When a process noise is used, all of the parameters are converged to the true values, too, although some parameter estimates are slightly biased. The comparisons of the two trajectories between those generated by the true parameters and those by the estimated parameters show that the parameter estimation problem is well-solved.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.11 no.4
• /
• pp.31-38
• /
• 2012

In this paper, we selected primary cutting parameters that influence on surface roughness of cut bottom surface in end-milling for SM25C material. Those are overhang, depth of cut, feed rate and spindle speed. And then performed orthogonal array experiment and ANOVA by Taguchi method to determine that improved level combination of cutting parameters for betterment of working efficiency and surface roughness one of quality characteristics. And we verified a advisability of prediction model by verification test about level combination. From the results, main cutting parameter influences on surface roughness is spindle speed and the next is feed rate.

• Journal of Korean Society for Quality Management
• /
• v.27 no.2
• /
• pp.218-236
• /
• 1999

The purpose of parameter design is to determine optimal settings of design parameters of a product or a process such that the performance characteristics of a product exhibit small variabilities around their target values. Taguchi made significant contributions in this area. However, his analysis of the problem focused on only one performance characteristic or response, although in product and process design, multiple characteristics are more common. The critical problem in dealing with multiple characteristics is how to compromise the conflict among the selected levels of the design parameters for each individual characteristic. In this paper, Methodology using SN ratio optimized by univariate technique is proposed and a parameter design procedure to achieve the optimal balance among several different response variables is developed. Existing case studies are solved by the proposed method and the results are compared with ones by the sum of SN ratios, the expected weighted loss, the desirability function, and EXTOPSIS model.

• Journal of Korean Association for Spatial Structures
• /
• v.17 no.3
• /
• pp.75-82
• /
• 2017

The Kingery-Bulmash equation is the most common equation to calculate blast load. However, the Kingery-Bulmash equation is complicated. In this paper, a modified equation for surface blast load is proposed. The equation is based on Kingery-Bulmash equation. The proposed equation requires a brief calculation process, and the number of coefficients is reduced under 5. As a result, each parameter obtained by using the modified equation has less than 1% of error range comparing with the result by using Kingery-Bulmash equation. The modified equation may replace the original equation with brief process to calculate.

• Membrane and Water Treatment
• /
• v.10 no.6
• /
• pp.417-429
• /
• 2019

Poly Sulfone nanofibers were electrospun to fabricate membranes of different characteristics. To fabricate the fiber mats, polymer concentration, flowrate, and current density were determined as the most influencing factors affecting the overall performance of the membranes and studied through Response Surface Methodology. The Box-Behnken Design method (three factors at three levels) was used to design, analyze, and optimize the parameters to achieve the best possible performance of the electrospun membranes in forward osmosis process. Also, internal concentration polarization that characterizes the efficiency of the forward osmosis membranes was determined to better assess the overall performance of the fabricated electrospun membranes. Water flux to reverse salt flux was considered as the main response to assess the performance of the membranes. As confirmed experimentally, best membrane performance with the minimal structural parameter value could be achieved when predicted optimal values were used to fabricate the membranes through electrospinning process.