Jie-Ren Shie

Optimization of Dry Machining Parameters for High-Purity Graphite in End-Milling Process

The machining factors affecting the tool wear and surface finish produced in the end milling process are generally the cutting speed, the feed rate, the depth of cut, etc. This paper describes a study that identifies the influence of the machining parameters on the groove width and the surface roughness average for the end-milling of high-purity graphite under dry machining conditions. The experiments are based on an orthogonal arrays and grey relational analysis method is then applied to determine an optimal machining parameter setting. The dimensional accuracy of the groove width and the surface roughness average are selected as the quality targets. In this study, the feed rate is the most significant controlled factors for the machining process according to the weighted sum grade of the Δ and the R a .

Optimization on selective laser sintering of metallic powder via design of experiments method

Purpose – The objective of this study is to investigate the effect of various parameters on rapid prototyping parts for processes of sintering metallic powder by using Nd:YAG laser via the design of experiments (DOE) method.Design/methodology/approach – Experiments based on the DOE method were utilized to determine an optimal parameter setting for achieving a minimum amount of porosities in specimens during the selective laser sintering (SLS) process. Analysis of variance (ANOVA) was further conducted to identify significant factors.Findings – A regression model predicting percentages of porosities under various conditions was developed when the traditional Taguchis approach failed to identify a feasible model due to strong interactions of controlled factors. The significant factors to the process were identified by ANOVA.Research limitations/implications – Four controlled factors including pulse frequencies and pulse durations of laser beams, times of strikes of a pulse applying on a single laser spot a...

Optimization of Dry Machining Parameters for High-Purity Graphite in End-Milling Process by Artificial Neural Networks: A Case Study

The machining factors affecting the tool wear and the surface roughness produced in the end-milling process are generally the cutting speed, the feed rate, the depth of cut, etc. This article focused on finding an optimal cutting parameter setting of high-purity graphite under dry machining conditions by an artificial neural network and the Sequential Quadratic Programming method [1]. This algorithm yielded better performance than the traditional methods such as the Taguchi method and the Design of Experiments (DOE) approach. Additionally, the tool worn surfaces after machining were examined with tool electron microscopy (TEM) to observe the tool wear mechanisms.

Using an artificial neural network prediction model to optimize work-in-process inventory level for wafer fabrication

A proper selection of a work-in-process (WIP) inventory level has great impact onto the productivity of wafer fabrication processes, which can be properly used to trigger the decision of when to release specific wafer lots. However, the selection of an optimal WIP is always a tradeoff amongst the throughput rate, the cycle time and the standard deviation of the cycle time. This study focused on finding an optimal WIP value of wafer fabrication processes by developing an algorithm integrating an artificial neural network (ANN) and the sequential quadratic programming (SQP) method. With this approach, it offered an effective and systematic way to identify an optimal WIP level. Hence, the efficiency of finding the optimal WIP level was greatly improved.

A Study of Taguchi and Design of Experiments Method in Injection Molding Process for Polypropylene Components

This study analyzes contour distortions, wear mass losses and tensile properties of polypropylene (PP) composite components applied to the interior coffer of automobiles. The specimens are prepared under different injection molding conditions by changing melting temperatures, injection speeds, and injection pressures via three computer-controlled progressive strokes. The contour distortions, wear and tensile properties are selected as quality targets. The arrangement of sixteen experiments is based on an orthogonal array table. Both the Taguchi method and the design of experiments (DOE) method are applied to determine an optimal parameter setting. In addition, a side-by-side comparison of two different approaches is provided. In this study, regression models that link the controlled parameters and the targeted outputs are developed, and the mathematic models can be utilized to predict the contour distortions, wear and tensile properties at various injection molding conditions.

Optimization of Injection Molding Process for Contour Distortions of Polypropylene Composite Components via Design of Experiments Method

This study analyzes the contour distortions of polypropylene (PP) composite components, which are applied to the interior coffer of automobiles. The specimens are prepared under different injection molding conditions by varying the parameters, namely, melting temperature, injection speed, and injection pressure via three computer-controlled progressive strokes. The contour distortions are adopted as the quality targets. Experiments of sixteen experimental runs are based on an orthogonal array table, and apply the design of experiments (DOE) method to determine an optimal parameter setting. In this study, regression models are developed, and the models can be utilized to predict the contour distortions at each location under different injection molding conditions.

Optimization of reflow soldering process for BGA packages by artificial neural network

Purpose – This investigation applied a hybrid method combining a trained artificial neural network (ANN) and the sequential quadratic programming (SQP) method to determine an optimal parameter setting for a reflow soldering process of ball grid array packages in printed circuit boards.Design/methodology/approach – Nine experiments based on an orthogonal array table with three‐controlled inputs and average shear forces of solder spheres as a quality target were utilized to train the ANN and then the SQP method was implemented to search for an optimal setting of parameters.Findings – The ANN can be utilized successfully to predict the shear force under different reflow soldering conditions after being properly trained and the identified optimal parameter setting are capable of striking the balance between the average shear forces and the manufacturing cycle time.Practical implications – The reflow time and the peak temperature were found to be the most significant factors for the reflow process via analysis...

Optimization of a Wear Property of Die Cast AZ91D Components via a Neural Network

This study integrated a trained general regression neural network (GRNN) and a sequential quadratic programming (SQP) method to determine an optimal parameter setting for a die casting process of AZ91D. Nine experiments were prepared under different die casting processes by selecting slurry pressure, the fusion slurry velocity and the mold temperature as three controlled parameters and the wear mass loss as a quality target. A field-emission scanning electron microscope (FE-SEM) was applied to realize wear mechanisms and AZ91D components with a low wear mass loss showed a low friction coefficient as well as small scratching marks and delamination on the worn surfaces.