http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Arshad, Muhammad Zeeshan,Nawaz, Javeria Muhammad,Hong, Sang Jeen Korea Information Processing Society 2014 Journal of information processing systems Vol.10 No.3
In this paper, we investigated the use of seasonal autoregressive integrated moving average (SARIMA) time series models for fault detection in semiconductor etch equipment data. The derivative dynamic time warping algorithm was employed for the synchronization of data. The models were generated using a set of data from healthy runs, and the established models were compared with the experimental runs to find the faulty runs. It has been shown that the SARIMA modeling for this data can detect faults in the etch tool data from the semiconductor industry with an accuracy of 80% and 90% using the parameter-wise error computation and the step-wise error computation, respectively. We found that SARIMA is useful to detect incipient faults in semiconductor fabrication.
( Muhammad Zeeshan Arshad ),( Javeria Muhammad Nawaz ),( Sang Jeen Hong ) 한국정보처리학회 2014 Journal of information processing systems Vol.10 No.3
In this paper, we investigated the use of seasonal autoregressive integrated moving average (SARIMA) time series models for fault detection in semiconductor etch equipment data. The derivative dynamic time warping algorithm was employed for the synchronization of data. The models were generated using a set of data from healthy runs, and the established models were compared with the experimental runs to find the faulty runs. It has been shown that the SARIMA modeling for this data can detect faults in the etch tool data from the semiconductor industry with an accuracy of 80% and 90% using the parameter-wise error computation and the step-wise error computation, respectively. We found that SARIMA is useful to detect incipient faults in semiconductor fabrication.
In-Situ Detection Method of Abnormal Plasma Discharge in Plasma-Assisted Deposition Processes
Muhammad Zeeshan Arshad,홍상진 한국전기전자재료학회 2018 Transactions on Electrical and Electronic Material Vol.19 No.2
Arc is an abnormal discharge in a plasma-processing chamber that results in high current discharge marks and particles onwafers. However, it is diffi cult to identify or observe it during an ongoing process. In this study, we report on the observationsof plasma arcs during various plasma processes through a non-invasive optical plasma monitoring system devised forthe in situ detection of abnormal discharge. The employed optical monitoring based arc detection system provides valuableindications of particle generation resulting from a charge imbalance in the chamber. The devised non-invasive and real-timemethod can detect such disturbances down to the order of tens of microseconds. Successful monitoring of arcs that appearin various types of plasma-assisted deposition processes are presented in this paper. We also present examples of detectedarcs in various plasma processes, such as plasma-enhanced chemical vapor deposition, high density plasma-chemical vapordeposition, amorphous carbon layer deposition, and plasma-enhanced atomic layer deposition. The suggested method playsan important role for the next level of arc-detection research and plasma diagnostics applications.
Fault Diagnosis in Semiconductor Etch Equipment Using Bayesian Networks
Javeria Muhammad Nawaz,Muhammad Zeeshan Arshad,Sang Jeen Hong 대한전자공학회 2014 Journal of semiconductor technology and science Vol.14 No.2
A Bayesian network (BN) based fault diagnosis framework for semiconductor etching equipment is presented. Suggested framework contains data preprocessing, data synchronization, time series modeling, and BN inference, and the established BNs show the cause and effect relationship in the equipment module level. Statistically significant state variable identification (SVID) data of etch equipment are preselected using principal component analysis (PCA) and derivative dynamic time warping (DDTW) is employed for data synchronization. Elman’s recurrent neural networks (ERNNs) for individual SVID parameters are constructed, and the predicted errors of ERNNs are then used for assigning prior conditional probability in BN inference of the fault diagnosis. For the demonstration of the proposed methodology, 300 mm etch equipment model is reconstructed in subsystem levels, and several fault diagnosis scenarios are considered. BNs for the equipment fault diagnosis consists of three layers of nodes, such as root cause (RC), module (M), and data parameter (DP), and the constructed BN illustrates how the observed fault is related with possible root causes. Four out of five different types of fault scenarios are successfully diagnosed with the proposed inference methodology.
Zamurrad Arshad,Muhammad Ali Nasir,Yasir Baig,Muhammad Zeeshan,Rizwan Ahmed Malik,Khubab Shaker,Azhar Hussain,M. Latif,Maryam Sattar,Hussein Alrobei 한국고분자학회 2020 폴리머 Vol.44 No.5
This work focuses on the synthesis of a novel hybrid composite, fabricated by utilizing jute and carbon fibers reinforced epoxy composites through hand layup technique to replace pure carbon-epoxy fiber composites. The mechanical properties were evaluated by drop weight impact and tension-tension fatigue tests. The tension-tension fatigue test was conducted to monitor the dynamic stiffness and fatigue life degradation of hybrid composite materials by varying the layers of jute fiber. The maximum peak load during the impact test was observed as 1081.7 N in case of carbon/jute/ carbon/jute/carbon (CJCJC) stacking sequence composite materials. Finally, the surface morphology of hybrid composite materials was studied with scanning electron microscopy (SEM) after mechanical tests to check the delamination, fiber pull-out and matrix cracks. It can be concluded from the obtained mechanical results that the newly developed composite with 15% jute/carbon-epoxy hybrid materials has the potential to swap carbon-epoxy composite without much loss of fatigue life along with relatively enhanced ductility as well as impact strength.
Fault Diagnosis in Semiconductor Etch Equipment Using Bayesian Networks
Nawaz, Javeria Muhammad,Arshad, Muhammad Zeeshan,Hong, Sang Jeen The Institute of Electronics and Information Engin 2014 Journal of semiconductor technology and science Vol.14 No.2
A Bayesian network (BN) based fault diagnosis framework for semiconductor etching equipment is presented. Suggested framework contains data preprocessing, data synchronization, time series modeling, and BN inference, and the established BNs show the cause and effect relationship in the equipment module level. Statistically significant state variable identification (SVID) data of etch equipment are preselected using principal component analysis (PCA) and derivative dynamic time warping (DDTW) is employed for data synchronization. Elman's recurrent neural networks (ERNNs) for individual SVID parameters are constructed, and the predicted errors of ERNNs are then used for assigning prior conditional probability in BN inference of the fault diagnosis. For the demonstration of the proposed methodology, 300 mm etch equipment model is reconstructed in subsystem levels, and several fault diagnosis scenarios are considered. BNs for the equipment fault diagnosis consists of three layers of nodes, such as root cause (RC), module (M), and data parameter (DP), and the constructed BN illustrates how the observed fault is related with possible root causes. Four out of five different types of fault scenarios are successfully diagnosed with the proposed inference methodology.