http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
An Inference Time Efficient 3D Printer Fault Detection using CNN
Mark Verana,Cosmas Ifeanyi Nwakanma,Jae Min Lee,Dong Seong Kim 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.6
The rapid engagement of 3D printing in the in-dustry, manufacturing, and medicine provides advantages for fewer waste materials. However, the increasing use of 3D printing leads to failure in the performance of the 3D printers. In this research we implement a convolutional neural network (CNN) fault diagnosis in a 3D printer is proposed. We used an online repository of a set of data streams collected from 3D printers. The CNN was used to detect, process, and classify the anomalies in 3D printing. The proposed CNN outperformed the peer methods in terms of classification accuracy and inference time.
Machine Learning-based 3D Printer Fault Detection on Edge Device
Mark Verana,Made Adi Paramartha Putra,Revin Naufal Alief,Dong-Seong Kim,Jae-Min Lee 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.11
The 3D printer is a new manufacturing technique that becoming popular in the fields of industry. However, the rapid development of 3D printing technology needs fault detection in the printing process. In this paper, a fault detection based on stacked convolutional neural network (CNN) for 3D printer is proposed. Moreover, a dataset of 3D printer for fault diagnosis is also provided. The result presented in this paper shows that, a stacked-CNN is better than the single CNN and the other methods for fault detection.
Intelligent Fault Classification of 3D Printers using Long Short-Term Memory
Mark Verana,Made Adi Paramartha Putra,Love Allen Ahakonye,Dong-Seong Kim,Jae-Min Lee 한국통신학회 2022 한국통신학회 학술대회논문집 Vol.2022 No.2
3D printing is one of the promising tools in the industry because of its ability to fabricate complex shapes. With the rapid development of 3D printing, it is susceptible to a fault. In this paper, we focus to develop an intelligent fault classification of 3D printers based on long-short term memory (LSTM) to classify and detect malicious, prevent production losses, and lessen human involvement for quality checks. The dataset we used in this experiment is gathered in the actual 3D printers and we also leveraged an online repository of data collected for comparison. The LSTM was used to classify and detect the faults in the 3D printing with considerable accuracy in the results. The effectiveness of the proposed LSTM is evaluated based on the real damages and achieves an average accuracy of 98.2% which outperforms several state-of-the-art models and improves the diagnosis performance compared with other deep learning models.
Fault Detection in 3D Printers using an Improved YOLOv5 with Hyperparameter Tuning
Made Adi Paramartha Putra,Mark Verana,Revin Naufal Alief,Dong-Seong Kim,Jae-Min Lee 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.11
In this study, a modification of you only look once version 5 (YOLOv5) is presented to detect an error during the printing process of the fused filament fabrication (FDM) 3D printer. The improvement has been made in hyperparameter selection. The existing YOLOv5 uses the COCO dataset as the default hyperparameter, which is unsuitable for the 3D printing process. Therefore, we captured the image dataset using an FDM 3D printer to improve the detection result generated by the YOLOv5 model. The results show that the improved YOLOv5 with hyperparameter tuning is better than the traditional version of YOLOv5 based on the mean absolute precision (mAP).
Performance Evaluation of 3D Printer Fault Detection Based on Machine Learning Approach
Revin Naufal Alief,Muhammad Rasyid Redha,Mark Verana,Made Adi Paramartha Putra,Jae-Min Lee,Dong-Seong Kim 한국통신학회 2021 한국통신학회 학술대회논문집 Vol.2021 No.11
In the additive manufacturing technologies, 3D Printing become one of the most widely known and used for constructing prototypes from a geometry form. As the usage of 3D Printing increase in industrial area especially manufacturing, the needs to detect the fault in 3D Printer process is also increasing. Through this paper, fault detection methods based on accelerometer sensor data using machine learning approach is proposed. Several machine learning fault detection’s result are compared to decide the most suitable machine learning methods for 3D printing fault detection using accelerometer’s sensor data.
Towards Delay Aware Data Recovery using Deep Learning in Embedded IoT Application
Made Adi Paramartha Putra,Adinda Riztia Putri,Mark Verana,Dong-Seong Kim,Jae-Min Lee 한국통신학회 2022 한국통신학회 학술대회논문집 Vol.2022 No.2
Data recovery technique in internet of things (IoT) network able to improve the devices longevity by reducing data retransmission. Most of existing research mainly focused on improving the prediction accuracy based on simulation work. Therefore, this study evaluate the data recovery in real world environment using deep learning (DL) and embedded devices by considering the processing time delay. The main goals is to ensure the low latency by applying data recovery in IoT network with low computational resource. A low complexity of deep neural network (DNN), convolutional neural network (CNN), and long short-term memory (LSTM) network were compared. Based on experimental results, the DNN network model is able to maintain low processing delay with average of 5.18 ms and 98.85% accuracy to recover single missing data.