應用於智慧製造之網宇實體系統訓練資料異常檢知;Anomaly Detection of Training Data for Cyber-Physical System in Intelligent Manufacturing

NCUIR > Engineering College > Graduate Institute of Mechanical Engineering > Electronic Thesis & Dissertation > Item 987654321/93570

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/93570

Title:	應用於智慧製造之網宇實體系統訓練資料異常檢知;Anomaly Detection of Training Data for Cyber-Physical System in Intelligent Manufacturing
Authors:	黃鈺淳;Huang, Yu-Tsun
Contributors:	機械工程學系
Keywords:	網宇實體系統;異常資料過濾;自動編碼器;集成學習;Cyber physical system;anomaly data filter;Autoencoder;Ensemble learning
Date:	2022-11-15
Issue Date:	2024-09-19 17:20:09 (UTC+8)
Publisher:	國立中央大學
Abstract:	網宇實體系統會在雲端建立預測用的數值模型，再利用由工廠自動收集的資料訓練該數值模型，並且持續追隨實體的情況更新模型。為了避免異常資料混入正常資料中導致更新後之數值模型資料汙染，進而造成的預測不準確。因此需要異常資料過濾器將資料進行過濾，以維護網宇實體系統的性能。本研究之過濾器由自動編碼器與分類器構成。先使用正常資料訓練前端的自動編碼器，使其能夠初步辨識正常資料與異常資料。接著在後端建立用於分辨資料正確性之分類器，由支援向量機、隨機森林、K-近鄰演算法與集成式學習構成。分類器的輸入資料包含自動編碼器之輸入與輸出，也可以加入兩者差異的量化指標。最後，分類器會將資料區分成正確或錯誤二類，只有正常資料可以用於更新網宇實體系統之數值模型，避免異常資料影響其性能。本研究使用二個製程案例對研究方法進行驗證及調整;第一個案例是使用文獻上的雷射金屬沉積製程優化案例，第二個案例是使用 3D 生物列印之製程優化案例。先評估資料汙染程度對數值模型的影響，再利用本研究發展之方法過濾異常資料，並且分析分類的情況;其中真陽性與偽陽性是影響資料汙染的關鍵指標。結果顯示本研究分類的正確率大於 94.7％，錯誤率小於 3.3％，所以本研究提出之方法可確實避免網宇實體模型受到資料汙染的影響。 ;The cyber-physical system of the manufacturing industry will build a numerical model for prediction in the cloud, and then will train the numerical model with the data collected automatically from the factory, and continuously update the model. To avoid the inaccurate predictions caused by the data poisoning of the updated numerical model due to the mixing of the wrong data with the correct data, an error data filter is needed to classify the data and maintain the performance of the cyber-physical system. The filter in this study consists of Auto-Encoder and a classifier. First, use the correct data to train the front-end Auto-Encoder so that it can initially identify correct and incorrect data. Then, the classifier is built at the back-end to distinguish the correctness of the data, which consists of Support Vector Machines, Random Forest, a K-Nearest Neighbor and Ensemble Learning. The input data of the classifier includes the input and output of the Auto-Encoder, and can also include quantifiers of the difference between them. Finally, the classifier classifies the data into correct or incorrect categories. Only correct data can be used for updating the numerical model of the cyber-physical system. In this study, two process cases are used to validate and adapt the research method; the first case is Laser Direct Metal Deposition, and the second case is Modeling and Parameter Optimization of 3D Printing Process with Bio-material. The impact of data poisoning on the numerical model was evaluated, and then the method developed in this study was used to filter out the wrong data and analyze the classification; true positive and false positive were the key indicator of data poisoning. The results show that the classification accuracy rate of this study is greater than 94.7%, and the error rate is less than 3.3%. Therefore, the method proposed in this study can indeed avoid the influence of data poisoning on the cyber-physical model.
Appears in Collections:	[Graduate Institute of Mechanical Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	3	View/Open

社群 sharing

Loading...