• 반도체디스플레이기술학회지
• /
• 제16권4호
• /
• pp.25-29
• /
• 2017

In this paper, we have studied the deformation problem of the scaffold caused by the FDM type 3D printer. The Practical TRIZ technique was used to solve the deformation problem of the scaffold generated from the adhesion surface between the scaffold and the bed. The Practical TRIZ methodology was used to derive the solution and the experiment was conducted on the derived solution. As a result of evaluating the experimental results obtained for the solution, it was found that the deformation of the scaffold was much improved to the satisfactory level.

• 반도체디스플레이기술학회지
• /
• 제17권3호
• /
• pp.85-89
• /
• 2018

Temperature uniformity of a wafer in a semiconductor process is a very important factor that determines the overall yield. Therefore, it is very important to confirm the temperature characteristics of the chuck surface on which the wafer is lifted. The temperature characteristics of the chuck depend on the external heat source, the shape of the cooling channel inside the chuck, the material on the chuck surface, and so on. In this study, CFD confirms the change of temperature characteristics according to the stacking order of ceramic materials and inner coolant path on the chuck surface. Finally this study suggests the best cooling condition of electrostatic chuck.

• 반도체디스플레이기술학회지
• /
• 제20권3호
• /
• pp.125-130
• /
• 2021

Scaffold is used to produce bio sensor. Scaffold is required high dimensional accuracy. 3D printer is used to manufacture scaffold. 3D printer can't detect defect during printing. Defect detection is very important in scaffold printing. Real-time defect detection is very necessary on industry. In this paper, we proposed the method for real-time scaffold defect detection. Real-time defect detection model is produced using CNN(Convolution Neural Network) algorithm. Performance of the proposed model has been verified through evaluation. Real-time defect detection system are manufactured on hardware. Experiments were conducted to detect scaffold defects in real-time. As result of verification, the defect detection system detected scaffold defect well in real-time.

• 반도체디스플레이기술학회지
• /
• 제19권4호
• /
• pp.59-64
• /
• 2020

In this paper, we found the solution using data based machine learning regression method to check the pore shape, to solve the problem of the experiment quantity occurring when producing scaffold with the 3d printer. Through experiments, we learned secured each print condition and pore shape. We have produced the scaffold from scaffold pore shape defect prediction model using multiple linear regression method. We predicted scaffold pore shapes of unsecured print condition using the manufactured scaffold pore shape defect prediction model. We randomly selected 20 print conditions from various predicted print conditions. We print scaffold five times under same print condition. We measured the pore shape of scaffold. We compared printed average pore shape with predicted pore shape. We have confirmed the prediction model precision is 99 %.

• 반도체디스플레이기술학회지
• /
• 제20권2호
• /
• pp.109-114
• /
• 2021

When we inspect scaffold defect using sight, inspecting performance is decrease and inspecting time is increase. We need for automatically scaffold defect detection method to increase detection accuracy and reduce detection times. In this paper. We produced scaffold defect classification models using densenet, alexnet, vggnet algorithms based on CNN. We photographed scaffold using multi dimension camera. We learned scaffold defect classification model using photographed scaffold images. We evaluated the scaffold defect classification accuracy of each models. As result of evaluation, the defect classification performance using densenet algorithm was at 99.1%. The defect classification performance using VGGnet algorithm was at 98.3%. The defect classification performance using Alexnet algorithm was at 96.8%. We were able to quantitatively compare defect classification performance of three type algorithms based on CNN.

• 반도체디스플레이기술학회지
• /
• 제20권1호
• /
• pp.59-63
• /
• 2021

Upper electrode is one of core parts using plasma etching process at semiconductor. The purpose of this study is to analyze effects of cutting conditions for mechanical machining of silicon upper electrode. For this research, surface roughness of machined workpiece and depth of damage inside of silicon electrode are experimented and analyzed and different values of feed rate and depth of cut are applied for the experiments. From these experiments, it is verified that the surface roughness and internal damaged layer get worse according to take more fast feed rate. In conclusion, cutting condition is very important factor for machining. Results of this study can use to develop various parts which are made from single crystal silicon and affect various benefits to the semiconductor industry for better productivity.

• 반도체디스플레이기술학회지
• /
• 제21권3호
• /
• pp.63-68
• /
• 2022

In this study, we produced defect detection models using parallel convolution neural networks. If convolution neural networks are constructed parallel type, the model's detection accuracy will increase and detection time will decrease. We produced parallel-type defect detection models using 4 types of convolutional algorithms. The performance of models was evaluated using evaluation indicators. The model's performance is detection accuracy and detection time. We compared the performance of each parallel model. The detection accuracy of the model using AlexNet is 97 % and the detection time is 0.3 seconds. We confirmed that when AlexNet algorithm is constructed parallel type, the model has the highest performance.

• 반도체디스플레이기술학회지
• /
• 제20권4호
• /
• pp.114-118
• /
• 2021

In this research, the dimensional error of the measured specimen according to the measurement method was analyzed for the length, angle, radius of curvature and diameter using a projector which is used in industry. One-way analysis was performed on each data tested 30 times using a statistical technique. Through the experiment, it was found that an error occurred in each data when measuring the length and radius of curvature according to the measurement method, and the null hypothesis that no error occurred when measuring the angle and length was established. Based on this experimental data, the automatic measurement when measuring the projector causes less measurement error, so automatic measurement is recommended when measuring a small product. Also, an optimal measuring method is suggested for securing reliability on formulations of measurement automation.

• 반도체디스플레이기술학회지
• /
• 제22권1호
• /
• pp.54-58
• /
• 2023

In this study, we compared the detection accuracy of the parameters of the scaffold failure detection model. A detection algorithm based on convolutional neural network was used to construct a failure detection model for scaffold. The parameter properties of the model were changed and the results were quantitatively verified. The detection accuracy of the model for each parameter was compared and the parameter with the highest accuracy was identified. We found that the activation function has a significant impact on the detection accuracy, which is 98% for softmax.

• 제어로봇시스템학회논문지
• /
• 제20권7호
• /
• pp.706-712
• /
• 2014

The inverters used to drive Brushless DC motors (BLDC) include switching devices such as FETs and the faults in FETs cause severe performance degradation in systems where a BLDC acts as actuator. This paper presents a fault detection and isolation method for the FETs of an inverter for BLDC motor control systems, which is based on the EKF (Extended Kalman filter). Firstly, an equivalent circuit model for a BLDC motor plus its inverter system was derived. Secondly, a state-space equation was established, where the on-resistance of the FETs is expressed as a state variable and the EKF equation estimates the on-resistance. If the estimated resistance differs greatly from the known value, it can be asserted that there is a fault on that FET. Thirdly, the local convergence of the established EKF was proved. Finally, through the experiments, the performance of the proposed method was verified. The results show that the on-resistance is estimated close to the value specified in the FET data sheet in normal operation, whereas the estimated resistance is a much larger value than the normal one in case an FET fault occurs. Therefore, it is confirmed that the proposed fault detection and isolation method works appropriately in real systems.