請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/83567完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 吳政鴻(Cheng-Hung Wu) | |
| dc.contributor.author | Hsin-Ping Liao | en |
| dc.contributor.author | 廖心平 | zh_TW |
| dc.date.accessioned | 2023-03-19T21:10:42Z | - |
| dc.date.copyright | 2022-10-08 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-08-29 | |
| dc.identifier.citation | A. Nagabandi, G. Kahn, R. S. Fearing and S. Levine. (2018). Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning. IEEE, pp. 7559-7566. Albert, B. A. (2020). Deep Learning From Limited Training Data: Novel Segmentation and Ensemble Algorithms Applied to Automatic Melanoma Diagnosis. IEEE Access, 8, pp. 31254-31269. Almasan, P., Galm?s, M.F., Pailliss?, J., Su?rez-Varela, J., Perino, D., L?pez, D.R., Perales, A.A., Harvey, P., Ciavaglia, L., Wong, L., Ram, V.R., Xiao, S., Shi, X., Cheng, X., Cabellos-Aparicio, A., & Barlet-Ros, P. (2022). Digital Twin Network: Opportunities and Challenges. ArXiv, abs/2201.01144. Alon, G., Kroese, D.P., Raviv, T., & Rubinstein, R.Y. (2005). Application of the Cross-Entropy Method to the Buffer Allocation Problem in a Simulation-Based Environment. Annals of Operations Research, 134, pp. 137-151. Amaran, S., Sahinidis, N.V., Sharda, B., & Bury, S.J. (2016). Simulation optimization: a review of algorithms and applications. Annals of Operations Research, 240, pp. 351-380. Azouzi, R., M. Guillot. (1996). Control and optimization of the turning process using a neural network. B. Zhang et al. (2020). Constructing a PM2. 5 concentration prediction model by combining auto-encoder with bi-LSTM neural networks. Bo Zhang, Guojian Zou, Dongming Qin, Yunjie Lu, Yupeng Jin, Hui Wang. (2021). A novel Encoder-Decoder model based on read-first LSTM for air pollutant prediction. Boer, P.T., Kroese, D.P., Mannor, S., & Rubinstein, R.Y. (2005). A Tutorial on the Cross-Entropy Method. . Annals of Operations Research, 134, pp. 19-67. Bui, T. C., Le, V. D., Cha, S. K. (2018). A Deep Learning Approach for Air Pollution Forecasting in South Korea Using Encoder-Decoder Networks & LSTM. Chen, Y., Shi, Y., & Zhang, B. (2019). Optimal Control Via Neural Networks: A Convex Approach. arXiv: Optimization and Control. Cheng, C., Sa-ngasoongsong, A., Beyca, O.F., Le, T.Q., Yang, H., Kong, Z.J., & Bukkapatnam, S.T. (2015). Time series forecasting for nonlinear and non-stationary processes: a review and comparative study. IIE Transactions, 47, pp. 1053 - 1071. Cho, K., Merrienboer, B.V., G?l?ehre, ?., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. EMNLP. Chollet, F. (2018). Keras: The Python Deep Learning library. D. R. Song et al. (2019). Model Predictive Control Using Multi-Step Prediction Model for Electrical Yaw System of Horizontal-Axis Wind Turbines. IEEE Transactions on Sustainable Energy, pp. 2084-2093. Draeger, A., Engell, S., & Ranke, H.D. (1995). Model predictive control using neural networks. IEEE Control Systems Magazine, 15, 61-66. Du, S., Li, T., Horng, S. J. (2018). Time series forecasting using sequence-to-sequence deep learning framework. F. Tao, H. Zhang, A. Liu and A. Y. C. Nee. (2019). Digital Twin in Industry: State-of-the-Art. IEEE Transactions on Industrial Informatics, vol. 15, no. 4, pp. 2405-2415. Foucquier, A., Robert, S., Suard, F., St?phan, L., & Jay, A. (2013). State of the art in building modelling and energy performances prediction: A review. Renewable & Sustainable Energy Reviews , pp. 272-288. Frank Hutter, Holger Hoos, Kevin Leyton-Brown. (2014). An Efficient Approach for Assessing Hyperparameter Importance. Ghiassi, M., Saidane, H., & Zimbra, D. (2005). A dynamic artificial neural network model for forecasting time series events. International Journal of Forecasting, 21, 341-362. Glorot, X., & Bengio, Y. . (2010). Understanding the difficulty of training deep feedforward neural networks. AISTATS. Haber, R.E., Toro, R.M., & Gajate, A. . (2010). Optimal fuzzy control system using the cross-entropy method. A case study of a drilling process. Inf. Sci., 180, pp. 2777-2792. Hamza?ebi, C., Akay, D., & Kutay, F. (2009). Comparison of direct and iterative artificial neural network forecast approaches in multi-periodic time series forecasting. ISSN 0957-4174, pp. 3839-3844. Hochreiter, S., & Bengio, Y. . (2001). Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies. Hosen, M.A., Hussain, M.A., & Mjalli, F.S. (2011). Control of polystyrene batch reactors using neural network based model predictive control (NNMPC): An experimental investigation. Control Engineering Practice, 19, pp. 454-467. Ioffe, S., & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. ICML. Kao, I., Zhou, Y., Chang, L., & Chang, F. (2020). Exploring a Long Short-Term Memory based Encoder-Decoder framework for multi-step-ahead flood forecasting. Journal of Hydrology, 583, 124631. Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., & Tang, P.T. (2017). On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima. . ArXiv, abs/1609.04836. Kingma, D.P., & Ba, J. (2015). Adam: A Method for Stochastic Optimization. CoRR, abs/1412.6980. Kontschieder, P., Fiterau, M., Criminisi, A., & Bul?, S.R. . (2015). Deep Neural Decision Forests. 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1467-1475. Kritzinger, W., Karner, M., Traar, G., Henjes, J., & Sihn, W. . (2018). Digital Twin in manufacturing: A categorical literature review and classification. IFAC-PapersOnLine, 51, pp. 1016-1022. Kyunghyun Cho, Bart van Merrienboer, Dzmitry Bahdanau, Yoshua Bengio. (2014). On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. Lee, T.-L. (2006). Neural network prediction of a storm surge. ISSN 0029-8018, pp. 483-494. Li Qingyong, He Bing, Zhang Xianyang, Zhu Xiaoyu, Liu Gang. (2021). Encoder-Decoder Multi-Step Trajectory Prediction Technology Based on LSTM. Aero Weaponry, 2021, 28(2), pp. 49-54. Lipton, Z.C. (2015). A Critical Review of Recurrent Neural Networks for Sequence Learning. ArXiv, abs/1506.00019. Lu, Y., Tian, Z., Zhou, R., & Liu, W. . (2021). Multi-step-ahead prediction of thermal load in regional energy system using deep learning method. Energy and Buildings. Lyu, P., Chen, N., Mao, S., & Li, M. (2020). LSTM based encoder-decoder for short-term predictions of gas concentration using multi-sensor fusion. Process Safety and Environmental Protection, 137, pp. 93-105. M. D. Odom, R. Sharda. (1990). A neural network model for bankruptcy prediction. M. D. Odom, R. Sharda. (1990). A neural network model for bankruptcy prediction. Matteo Sangiorgio, Fabio Dercole. (2020). Robustness of LSTM neural networks for multi-step forecasting of chaotic time series. Mu, R., & Zeng, X. (2019). A Review of Deep Learning Research 13. KSII Trans. Internet Inf. Syst., pp. 1738-1764. Nagabandi, Anusha, et al.Nagabandi, A., Kahn, G., Fearing, R.S., & Levine, S. (2018). Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. IEEE International Conference on Robotics and Automation, pp. 7559-7566. Nguyen, H.H., Chan, C.W. (2004). Multiple neural networks for a long term time series forecast. Neural Comput & Applic. Nils Reimers, Iryna Gurevych. (2017). Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging. P. P. C. Yip, Yoh-Han Pao. (1994). A recurrent neural net approach to one-step ahead control problems. Paisan Kittisupakorn, Piyanuch Thitiyasook, M.A. Hussain, Wachira Daosud. (2009). Paisan Kittisupakorn, Piyanuch Thitiyasook, M.A. Hussain, Wachira Daosud. ISSN, pp. 579-590. Pankaj Malhotra, Vishnu TV, Anusha Ramakrishnan, Gaurangi Anand, Lovekesh Vig, Puneet Agarwal, Gautam Shroff. (2016). Multi-Sensor Prognostics using an Unsupervised Health. Park, J., Yi, D., & Ji, S. . (2020). A Novel Learning Rate Schedule in Optimization for Neural Networks and It’s Convergence. Symmetry, 12, p. 660. Pieter-Tjerk de Boer,Dirk P. Kroese,Shie Mannor,Reuven Y. Rubinstein. (2003). A Tutorial on the Cross-Entropy Method. Pingyang Lyu, Ning Chen, Shanjun Mao, Mei Li. (2020). LSTM based encoder-decoder for short-term predictions of gas concentration using multi-sensor fusion. R. Karim, T.H. Rafi. (2020). An automated LSTM-based air pollutant concentration estimation of Dhaka City. Reimers, N., & Gurevych, I. . (2017). Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging. . EMNLP. Ross, I.M., & Fahroo, F. . (2002). A Direct Method for Solving Nonsmooth Optimal Control Problems. IFAC Proceedings Volumes, 35, pp. 479-484. Ruihui, M., & Xiaoqin, Z. . (2019). Ruihui, M., & Xiaoqin, Z. ( 2019). A Review of Deep Learning Research. 13 (4) Korean Society for Internet Information. KSII Transactions on Internet and Information Systems (TIIS). S. Du, T. Li, Y. Yang, X. Gong and S. -J. Horng. (2019). An LSTM based Encoder-Decoder Model for MultiStep Traffic Flow Prediction. pp. 1-8. Schwartz, J.D., Wang, W., & Rivera, D.E. (2006). Simulation-based optimization of process control policies for inventory management in supply chains. Autom., 42, , pp. 1311-1320. Shengdong Du; Tianrui Li; Yan Yang; Xun Gong; Shi-Jinn Horng. (2019). An LSTM based Encoder-Decoder Model for MultiStep Traffic Flow Prediction. International Joint Conference on Neural Networks (IJCNN), pp. 1-8. Shengdong Du; Tianrui Li; Yan Yang; Xun Gong; Shi-Jinn Horng. (2019). An LSTM based Encoder-Decoder Model for MultiStep Traffic Flow Prediction. IEEE. Shuhua Wang,Zan Chen,Shengnan Chen. (2019). Applicability of deep neural networks on production forecasting in Bakken shale reservoirs. Smyl, S., & Kuber, K. (2016, June). Data preprocessing and augmentation for multiple short time series forecasting with recurrent neural networks. Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. . J. Mach. Learn. Res., 15, pp. 1929-195. Sze, V., Chen, Y., Yang, T., & Emer, J.S. (2017). Efficient Processing of Deep Neural Networks: A Tutorial and Survey. Proceedings of the IEEE, 105, pp. 2295-2329. Takase, T., Oyama, S., & Kurihara, M. (2018). Effective neural network training with adaptive learning rate based on training loss. . Neural networks: the official journal of the International Neural Network Society, 101, pp. 68-78. Tang, Y., Wang, Z., Lu, J., Feng, J., & Zhou, J. (2019). Multi-Stream Deep Neural Networks for RGB-D Egocentric Action Recognition. IEEE Transactions on Circuits and Systems for Video Technology, 29, 3001-3015, (pp. 3001-3015). Tang, Z., Almeida, C.D., & Fishwick, P.A. (1991). Time series forecasting using neural networks vs. Box-Jenkins methodology. Simulation, 57,, pp. 303 - 310. Terzi, E., Bonassi, F., Farina, M., & Scattolini, R. (2021). Learning model predictive control with long short-term memory networks. Terzi, E., Bonassi, F., Farina, M., & Scattolini, R. (2021). Learning model predictive control with long short?term memory networks. International Journal of Robust and Nonlinear Control, 31, 8877 - 8896. Terzi, E., Fagiano, L., Farina, M., & Scattolini, R. . (2018). Learning multi-step prediction models for receding horizon control. 2018 European Control Conference (ECC), pp. 1335-1340. Tim Hill, Marcus O'Connor, William Remus. (1996). Neural Network Models for Time Series Forecasts. Management Science, pp.:1082-1092. Vach?lek, J., Bartalsk?, L., Rovn?, O., Sismisov?, D., Morh??, M., & Lok??k, M. (2017). The digital twin of an industrial production line within the industry 4.0 concept. 2017 21st International Conference on Process Control (PC), (pp. 258-262). Wang, S., Chen, Z., & Chen, S. (2019). Applicability of deep neural networks on production forecasting in Bakken shale reservoirs. Journal of Petroleum Science and Engineering. Wang, S., Chen, Z., & Chen, S. (2019). Applicability of deep neural networks on production forecasting in Bakken shale reservoirs. Journal of Petroleum Science and Engineering. Weyer, S., Meyer, T., Ohmer, M., Gorecky, D., & Z?hlke, D. (2016). Future Modeling and Simulation of CPS-based Factories: an Example from the Automotive Industry. IFAC-PapersOnLine, 49, pp. 97-102. Xavier Glorot,Yoshua Bengio. (2010). Understanding the difficulty of training deep feedforward neural networks. Xu, J., Huang, E., Hsieh, L.Y., Lee, L.H., Jia, Q., & Chen, C. . (2016). Simulation optimization in the era of Industrial 4.0 and the Industrial Internet . Journal of Simulation, 10, pp. 310-320. Yan, L., Zhen, T., Kong, J., Wang, L., & Zhou, X. (2020). Walking Gait Phase Detection Based on Acceleration Signals Using Voting-Weighted Integrated Neural Network. Complex., 2020, 4760297:1-4760297:14. Yu, Y., Adu, K., Tashi, N., Anokye, P., Wang, X., & Ayidzoe, M.A. (2020). RMAF: Relu-Memristor-Like Activation Function for Deep Learning. IEEE Access, 8, pp. 72727-72741. Zachary C. Lipton, David C. Kale, Charles Elkan, Randall Wetzel. (2015). Learning to Diagnose with LSTM Recurrent Neural Networks. Zeiler, M. (2012). ADADELTA: An Adaptive Learning Rate Method. . ArXiv, abs/1212.5701. Zhang, B., Zou, G., Qin, D., Lu, Y.L., Jin, Y., & Wang, H. (2021). A novel Encoder-Decoder model based on read-first LSTM for air pollutant prediction. The Science of the total environment, 765, 144507. ?明山,張仁達. (2007). ??經網?於 MIMO 半導體製程控制的應用. Journal of Science and Engineering Technology, Vol. 3, No. 4, pp. 57-67. 李瑞?,康銳. (2008). 基於神經網路的故障率預測方法. 航空學報. 沈子暄. (2020). 機器學習與模擬最佳化之製程控制-以鋼鐵業為例. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/83567 | - |
| dc.description.abstract | 本研究以數位分身(Digital Twin)概念出發，以深度神經網路模型作為虛擬軋機模擬實際軋延系統，由於在軋延製程受到機器參數、控制參數、鋼板特性、過往軋延結果等因子影響，無法直接以物理或數學模型進行分析、實驗，我們將軋機內部視為黑盒子，建立AI模型作為虛擬系統，經由過往蒐集的大量數據，學習機器特性、了解出入口關係，進而精準預測出口板形。 現行軋機由內漸模糊控制系統控制，時常發生控制不到位的問題，我們結合虛擬軋機與模擬最佳化模型計算出在不同軋延情況及目標下最適合的控制參數，使得最終出口板形接近目標板形，提升製程品質及效率。 考量控制參數由油壓輥控制，作動速度緩慢，加上模擬最佳化模型計算耗時，不符合實時控制的需求。在蒐集足夠多資料後，我們建立基於長短期神經網路的編碼器-解碼器模型，學習面對不同入口板形及目標板形的最佳控制方式，省去模擬最佳化計算時間，並可以在偵測到入口板形後立即預測未來多步的最佳控制方式，使控制器能提早移動最佳控制位置，利用模型預測控制方法提升實際產線的實作可行性並優化製程品質。 | zh_TW |
| dc.description.abstract | Based on the concept of Digital Twin, we build a deep neural network as a virtual rolling mill to simulate the operation of reversing cold rolling mill. The rolling process is affected by machine parameters, control parameters, raw materials, previous rolling, and so on. Therefore, the rolling process can’t be interpreted by mathematical or physical models. We assume that the interaction of the rolling mill is a black box and establish an AI model as a virtual system which can precisely predict the shape after rolling. The current control method of the reversing cold rolling mill is based on the built-in fuzzy control system, which often results in a gap between the exit shape and the target shape. Based on the virtual rolling mill, simulation optimization model to calculate the appropriate control parameters under different target shape and environments, which optimize the output shape and improve the process quality. Consider that the control parameters are controlled by hydraulic controllers which moves slowly compared with the strip and that simulation optimization model takes long time on calculation. We establish LSTM based Encoder-Decoder model to predict multi-steps ahead optimal control actions. Consequently, the controllers can move to optimized position. The results for the neural network model predictive control (NNMPC) overall show better performance in the control of the system over the original one. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T21:10:42Z (GMT). No. of bitstreams: 1 U0001-2208202212513200.pdf: 4491395 bytes, checksum: 401593ed5e08cf1d6a2bbe58722e8de7 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | 誌謝 I 中文摘要 II Abstract III 目錄 IV 圖目錄 VI 表目錄 VIII Chapter 1 前言 1 1.1 研究背景與動機 1 1.2 研究目的 5 1.3 研究方法與流程 5 Chapter 2 文獻回顧 8 2.1 應用Digital Twin優化製程 8 2.2 模擬最佳化優化製程品質 10 2.3 非線性製程控制 11 2.4 非平穩過程的時間序列預測 14 2.5 小結 16 Chapter 3 深層神經網路之虛擬軋機 17 3.1 資料蒐集 17 3.2 Multi-stream Deep Neural Network 21 Chapter 4 模擬最佳化模型優化控制參數 29 4.1 Cross-Entropy演算法 29 4.2 模擬最佳化模型結構及限制 30 4.3 實時控制軋延製程之限制 33 Chapter 5 多步提前預測最佳控制參數 34 5.1 DNN預測最佳控制參數 34 5.2 LSTM-ED預測多步最佳控制參數 47 Chapter 6 最佳控制參數預測結果與討論 55 6.1 14個最佳控制參數預測成果 55 6.2 隨軋延時間變化之模型預測成果 56 6.3 最佳控制參數軋延成果 61 6.4 板形優化成果 65 Chapter 7 結論與未來研究方向 68 7.1 結論 68 7.2 未來研究方向 68 REFERENCE 70 附錄 79 | |
| dc.language.iso | zh-TW | |
| dc.title | 利用循環神經網路之製程預測控制最佳化 | zh_TW |
| dc.title | Predictive Process Control Using Recurrent Neural Networks | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 周育樂(Ywh-Leh Chou),楊洋(Yang Yang),張浩元(Hao-Yuan Chang) | |
| dc.subject.keyword | 數位分身,模擬最佳化,神經網路預測控制,編碼器-解碼器, | zh_TW |
| dc.subject.keyword | Digital Twin,simulation optimization,neural network model predictive control,Encoder-Decoder, | en |
| dc.relation.page | 128 | |
| dc.identifier.doi | 10.6342/NTU202202640 | |
| dc.rights.note | 未授權 | |
| dc.date.accepted | 2022-08-30 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 工業工程學研究所 | zh_TW |
| 顯示於系所單位： | 工業工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2208202212513200.pdf 目前未授權公開取用 | 4.39 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。