工業4.0是一個有效支援企業的體系，可用來提升企業的競爭力。虛實整合系統是工業4.0的關鍵技術之一，是一種可以控制或監控前端物理設備，並且在後端利用雲端計算實現智慧生產或服務的機制。雖然企業已經有了虛實整合系統的概念，但在實證研究上的文獻仍然甚少。因此本研究發展一套解決過度設計問題和停機問題的方法。本方法包含兩步驟，首先，用隨機森林去分析從虛實整合系統感應器收集來的數據，來確定關鍵因素。接下來利用可拓神經元網路演算法建構預測模型，以區別在後端具有更好產量的參數。找到關鍵參數後經過可拓類神經網路學習，可以變成決策參數系統供企業未來決策參考用。因此，在製造過程中，過度設計和停機的問題可以被解決。最重要的是這個系統可以自動地辨識和觀察關鍵變數指標，可以用來提供企業重要的資訊即時進行決策。經實證，可拓類神經網路有較快的學習效率。在應用上，我們將虛實整合系統拿來做為決策參數系統以用於解決過度設計與預測停機問題。此方法可應用到其他複雜系統來達到促進決策效率，協助系統自行提升改善的功效。

Industry 4.0 is known as a powerful supportive system that enterprises can enhance their competitiveness. One of critical components of industry 4.0 is Cyber-Physical System (CPS). CPS is a mechanism which can control or monitor physical equipment in the front end and utilize the cloud computing in the back end to achieve intelligent production or services. Although the concept of CPS is well-known in industries, there are few research discuss empirical studies. Therefore, this study develops a forecast model to solve the overdesign problem and the shutdown problem. This study consists of two steps. Based on the data collected from sensors of CPS, random forest (RF) is employed to figure out key factors. Next, extension neural network (ENN) method builds a forecast model to identify parameters which have better importance in the backend and to identify key variables of machine shutdown data. CPS then modify these parameters to solve the overdesign problem and the shutdown problem. Through finding out the key factor and learning from ENN, it can become a decision parameter system to make decisions for the enterprise. Correspondingly, the overdesign and shutdown issue can be solved in the manufacturing. The most important is that the system can identify and observe the key variables automatically that can provide enterprises critical information to conduct decision making issues in the timely manner. Through empirical study, it indicates that ENN has a faster learning rate. This study applies CPS to be a decision parameter system used to solve the overdesign and the shutdown problem. This method can be applied to other complex systems to boost the efficiency of making decision and assist system improving itself automatically.

Abstract II
Table of Contents IV
List of Figures V
List of Tables VI
1. Introduction 1
2. Literature Review 5
2.1 Industry 4.0 5
2.2 Cyber Physical Systems 7
2.3 Multivariate Analysis 9
2.4 Summary 13
3. Methodology 14
3.1 Phase I: Employ RF to figure out key factors 15
3.2 Phase II: utilize ENN o build a forecast model to identify parameters 18
3.2.1 Learning algorithm of the ENN 21
3.2.2 Operation phase of ENN 24
4. Case Study 27
4.1 Case study of company F 27
4.1.1 Key Factor Identification With Random Forest 29
4.1.2 Overdesign Forecast With Extension Neural Network 31
4.1.3 Sensitivity Analysis 34
4.2 Case study of company G 37
4.2.1 Key Factor Identification With Random Forest 39
4.2.2 Shutting Down Forecast With Extension Neural Network 41
4.3 Discussion 44
5. Conclusion 47
6. References 49

[1] Trappey, A. J., Trappey, C. V., Govindarajan, U. H., Chuang, A. C., & Sun, J. J. (2017). A review of essential standards and patent landscapes for the Internet of Things: A key enabler for Industry 4.0. Advanced Engineering Informatics, 33, 208-229.
[2] Akkaya, I., Derler, P., Emoto, S., & Lee, E. A. (2016). Systems engineering for industrial cyber–physical systems using aspects. Proceedings of the IEEE, 104(5), 997-1012.
[3] Almada-Lobo, F. (2016). The Industry 4.0 revolution and the future of manufacturing execution systems (MES). Journal of Innovation Management, 3(4), 16-21.
[4] Trappey, A. J., Trappey, C. V., Govindarajan, U. H., Sun, J. J., & Chuang, A. C. (2016). A review of technology standards and patent portfolios for enabling cyber-physical systems in advanced manufacturing. IEEE Access, 4, 7356-7382.
[5] Basheer, I. A., & Hajmeer, M. (2000). Artificial neural networks: fundamentals, computing, design, and application. Journal of microbiological methods, 43(1), 3-31.
[6] Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
[7] Brettel, M., Friederichsen, N., Keller, M., & Rosenberg, M. (2014). How virtualization, decentralization and network building change the manufacturing landscape: An industry 4.0 perspective. International Journal of Mechanical, Industrial Science and Engineering, 8(1), 37-44.
[8] Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)?–Arguments against avoiding RMSE in the literature. Geoscientific Model Development, 7(3), 1247-1250.
[9] Derler, P., Lee, E. A., & Vincentelli, A. S. (2012). Modeling cyber–physical systems. Proceedings of the IEEE, 100(1), 13-28.
[10] Genuer, R., Poggi, J. M., & Tuleau-Malot, C. (2010). Variable selection using random forests. Pattern Recognition Letters, 31(14), 2225-2236.
[11] Ivanov, D., Dolgui, A., Sokolov, B., Werner, F., & Ivanova, M. (2016). A dynamic model and an algorithm for short-term supply chain scheduling in the smart factory industry 4.0. International Journal of Production Research, 54(2), 386-402.
[12] Kagermann, H., Helbig, J., Hellinger, A., & Wahlster, W. (2013). Recommendations for implementing the strategic initiative INDUSTRIE 4.0: Securing the future of German manufacturing industry; final report of the Industrie 4.0 Working Group. Forschungsunion.
[13] Kopetz, H. (2011). Real-time systems: design principles for distributed embedded applications. Springer Science & Business Media.
[14] Krotofil, M., & Cárdenas, A. A. (2013). Resilience of process control systems to cyber-physical attacks. In Nordic Conference on Secure IT Systems (pp. 166-182). Springer, Berlin, Heidelberg.
[15] Lasi, H., Fettke, P., Kemper, H. G., Feld, T., & Hoffmann, M. (2014). Industry 4.0. Business & Information Systems Engineering, 6(4), 239-242.
[16] Lee, J., Bagheri, B., & Kao, H. A. (2015). A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manufacturing Letters, 3, 18-23.
[17] Lee, J., Kao, H. A., & Yang, S. (2014). Service innovation and smart analytics for industry 4.0 and big data environment. Procedia Cirp, 16, 3-8.
[18] Leitão, P., Colombo, A. W., & Karnouskos, S. (2016). Industrial automation based on cyber-physical systems technologies: Prototype implementations and challenges. Computers in Industry, 81, 11-25.
[19] Liaw, A., & Wiener, M. (2002). Classification and regression by random Forest. R news, 2(3), 18-22.
[20] Loskyll, M., Heck, I., Schlick, J., & Schwarz, M. (2012). Context-based orchestration for control of resource-efficient manufacturing processes. Future Internet, 4(3), 737-761.
[21] Sackey, S. M., & Bester, A. (2016). Industrial engineering curriculum in Industry 4.0 in a South African context. South African Journal of Industrial Engineering, 27(4), 101-114.
[22] Strobl, C., Boulesteix, A. L., Zeileis, A., & Hothorn, T. (2007). Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC bioinformatics, 8(1), 25.
[23] Tu, Y. K., Kellett, M., Clerehugh, V., & Gilthorpe, M. S. (2005). Problems of correlations between explanatory variables in multiple regression analyses in the dental literature. British dental journal, 199(7), 457-461.
[24] Wang, M. H., & Hung, C. P. (2003). Extension neural network and its applications. Neural Networks, 16(5), 779-784.
[25] Wang, M. H., & Hung, C. P. (2003, July). Extension neural network. In Neural Networks, 2003. Proceedings of the International Joint Conference on (Vol. 1, pp. 399-403). IEEE.
[26] Wang, S., Wan, J., Zhang, D., Li, D., & Zhang, C. (2016). Towards smart factory for industry 4.0: a self-organized multi-agent system with big data based feedback and coordination. Computer Networks, 101, 158-168.
[27] Chen, Y. H., Ho, P. H., & Chiu, M. C. (2017). Utilizing Cyber Physical System to Achieve Intelligent Product Design: A Case Study of Transformer. Transdisciplinary Engineering: A Paradigm Shift, 1031.
[28] Loh, W. Y. (2011). Classification and regression trees. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 1(1), 14-23.
[29] Muñoz-Romero, S., Gómez-Verdejo, V., & Parrado-Hernández, E. (2017). A novel framework for parsimonious multivariate analysis. Pattern Recognition.
[30] Roberts, S. W. (1959). Control chart tests based on geometric moving averages. Technometrics, 1(3), 239-250.
[31] Patterson, C., Vasquez, R., & Hu, F. (2013). Cyber-Physical Systems: Design Challenges. Cyber-Physical Systems: Integrated Computing and Engineering Design, 101.
[32] Wang, S., Wan, J., Li, D., & Zhang, C. (2016). Implementing smart factory of industrie 4.0: an outlook. International Journal of Distributed Sensor Networks, 12(1), 3159805.
[33] Monostori, L., Kádár, B., Bauernhansl, T., Kondoh, S., Kumara, S., Reinhart, G., ... & Ueda, K. (2016). Cyber-physical systems in manufacturing. CIRP Annals, 65(2), 621-641.
[34] Yu, X., & Xue, Y. (2016). Smart grids: A cyber–physical systems perspective. Proceedings of the IEEE, 104(5), 1058-1070.
[35] Ma, X., Zuo, H., Tian, M., Zhang, L., Meng, J., Zhou, X., ... & Liu, Y. (2016). Assessment of heavy metals contamination in sediments from three adjacent regions of the Yellow River using metal chemical fractions and multivariate analysis techniques. Chemosphere, 144, 264-272.
[36] Srivastava, S., Engelhardt, B. E., & Dunson, D. B. (2017). Expandable factor analysis. Biometrika, 104(3), 649-663.
[37] Niu, X., Liu, G., Huo, L., Zhang, J., Bai, M., Peng, Y., & Zhang, Z. (2018). Risk stratification based on components of the complete blood count in patients with acute coronary syndrome: A classification and regression tree analysis. Scientific reports, 8(1), 2838.
[38] Sridhar, S., Hahn, A., & Govindarasu, M. (2012). Cyber-Physical System Security for the Electric Power Grid. Proceedings of the IEEE, 100(1), 210-224.\
[39] Huda, S., Miah, S., Hassan, M. M., Islam, R., Yearwood, J., Alrubaian, M., & Almogren, A. (2017). Defending unknown attacks on cyber-physical systems by semi-supervised approach and available unlabeled data. Information Sciences, 379, 211-228.
[40] Siryani, J., Tanju, B., & Eveleigh, T. J. (2017). A Machine Learning Decision-Support System Improves the Internet of Things’ Smart Meter Operations. IEEE Internet of Things Journal, 4(4), 1056-1066.
[41] Schmidt, M., & Åhlund, C. (2018). Smart buildings as Cyber-Physical Systems: Data-driven predictive control strategies for energy efficiency. Renewable and Sustainable Energy Reviews, 90, 742-756.
[42] Liang, Y. C., Lu, X., Li, W. D., & Wang, S. (2018). Cyber Physical System and Big Data enabled energy efficient machining optimisation. Journal of Cleaner Production, 187, 46-62.
[43] Leinweber, D. J. (2007). Stupid data miner tricks: overfitting the S&P 500. Journal of Investing, 16(1), 15. Li, Z., Braun, T., Zhao, X., Zhao, Z., Hu, F., & Liang, H. (2018). A narrow-band indoor positioning system by fusing time and received signal strength via ensemble learning. IEEE Access, 6, 9936-9950.
[44] Shaikh, F. K., & Zeadally, S. (2016). Energy harvesting in wireless sensor networks: A comprehensive review. Renewable and Sustainable Energy Reviews, 55, 1041-1054.
[45] Kwon, C., & Hwang, I. (2018). Reachability Analysis for Safety Assurance of Cyber-Physical Systems Against Cyber Attacks. IEEE Trans. Automat. Contr., 63(7), 2272-2279.
[46] Khair, U., Fahmi, H., Al Hakim, S., & Rahim, R. (2017, December). Forecasting Error Calculation with Mean Absolute Deviation and Mean Absolute Percentage Error. In Journal of Physics: Conference Series (Vol. 930, No. 1, p. 012002). IOP Publishing.
[47] Lewis, C. D. (1982). Industrial and business forecasting methods: A practical guide to exponential smoothing and curve fitting. Butterworth-Heinemann.