本研究在探討一個建築領域的新趨勢，是否可以將工業物聯網的先進技術應用於智慧建築/社區/城市(Smart Buildings/Communities/Cities)，例如故障偵測與診斷技術(Fault Detection and Diagnosis)就是一個很好的典範轉移議題。深度學習的卷積神經網絡(Convolutional Neural Network, CNN )被廣泛作為一種數據驅動的方法，可應用振動信號形式的機械故障特徵辨識。但是對未知故障類別部分，CNN的識別效率低且不夠準確，故本文提出了一種新穎的故障診斷方法，此方法為基於概率置信度 CNN 遷移學習的模型(Transfer Probability Confidence CNN, TPCCNN)，特別針對旋轉機械的故障特徵建模並進行故障診斷。 TPCCNN包括三大模塊：(1) 進行特徵工程，針對一系列數據預先處理和特徵提取；(2)將異構數據集的學習特徵轉移到不同的數據集上，使模型訓練具有更好的通用性，可以節省建模和參數調校優化的時間；(3)建立一個(Probability Confidence CNN, PCCNN)模型來分類已知和未知不同故障類別。該模型使用開源數據集CWRU和Ottawa進行了驗證，實驗結果顯示出異構數據集的特徵遷移對於已知和未知類別，平均準確率分別可達99.2%和93.8%，並且證明TPCCNN 在訓練及驗証異構數據集方面是有效的。同時，應用類似的特徵集將預測模型的訓練時間減少34%和68%。從政府的長期推動建築智慧化和人工智慧物聯網(Artificial Intelligence and Internet of Things, AIoT)技術的進步，可以發現不再限於安全防災、建築節能或設施管理等自動化工程和服務模式。 目前，全球先進國家都在積極部署智慧建築/社區/城市，在可見的未來智慧建築/社區/城市必定在資源系統和生活場景的前提條件下，將人、資通訊技術(ICT)、建築三要素平衡建構且完美融合。

This study explores a new trend in construction that is whether advanced technologies of the Industrial Internet of Things (IIOT) can be applied to smart buildings/communities/cities for use of fault detection and diagnosis. It could be an excellent paradigm-shifting topic. Deep learning convolutional neural networks (CNNs) are widely used as a data-driven approach to apply with the mechanical fault feature recognition based on vibration signals. However, for unknown fault categories, the recognition efficiency of CNN is inefficient and inaccurate enough. Therefore, this dissertation proposes a new fault diagnosis method that used a model based on Transfer Learning of Probabilistic Confidence CNN (TPCCNN) for predicting the unknown fault categories. TPCCNN is especially suitable for fault feature modeling and troubleshooting of rotating machinery. The TPCCNN includes three modules: (1) Perform feature engineering, which performs a series of data preprocessing and feature extraction; (2) Transfer the learned features of heterogeneous datasets to different datasets, making model training more general and saving modeling and parameter tuning time; (3) Build a Probability Confidence CNN (PCCNN) model to classify different known and unknown fault categories. The model is validated using open-source datasets, Case Western Reserve University (CWRU) Dataset and Ottawa Mendeley Dataset. The experimental results show that the average accuracy of feature transfer on heterogeneous datasets for known and unknown categories is 99.2% and 93.8%, respectively, and the effect of TPCCNN on training and validation of heterogeneous datasets is remarkable. At the same time, it is also observed that a similar feature set will significantly reduce the training time of the prediction model by 34% and 68%.
From the government's long-term promotion of smart buildings/communities/cities and the progress of Artificial Intelligence and Internet of Things (AIoT) technology, it can be found that it is not limited to automation engineering and service models such as safety and disaster prevention, building energy conservation, or facility management. At present, smart communities in advanced countries around the world are actively deploying. In the foreseeable future, smart communities must be perfectly integrated with people, ICT technology, and architecture under resource systems and life scenarios.

References
[1] W. Zhou, B. Lu, T. G. Habetler, and R. G. Harley, “Incipient Bearing Fault Detection via Motor Stator Current Noise Cancellation Using Wiener Filter,” IEEE Transactions on Industry Applications, vol. 45, no. 4, pp. 1309–1317, Aug. 2009, doi: 10.1109/TIA.2009.2023566.
[2] J. Sun, C. Yan, and J. Wen, “Intelligent Bearing Fault Diagnosis Method Combining Compressed Data Acquisition and Deep Learning,” IEEE Transactions on Instrumentation and Measurement, vol. 67, no. 1, pp. 185–195, Jan. 2018, doi: 10.1109/TIM.2017.2759418.
[3] T.-H. Meen and C.-C. Kuo, “Special Issue on Application of Electronic Devices on Intelligent System,” Electronics, vol. 10, no. 13, 2021, doi: 10.3390/electronics10131506.
[4] X. Zhou, S. Mao, and M. Li, “A Novel Anti-Noise Fault Diagnosis Approach for Rolling Bearings Based on Convolutional Neural Network Fusing Frequency Domain Feature Matching Algorithm,” Sensors, 2021, vol. 21, no. 16. doi: https://doi.org/10.3390/s21165532.
[5] S. Xiong et al., “A Novel End-To-End Fault Diagnosis Approach for Rolling Bearings by Integrating Wavelet Packet Transform into Convolutional Neural Network Structures,” Sensors, vol. 20, no. 17, p. 4965, Sep. 2020, doi: 10.3390/s20174965. [Online]. Available: https://www.mdpi.com/1424-8220/20/17/4965. [Accessed: Sep. 12, 2022]
[6] R. Zhao, R. Yan, Z. Chen, K. Mao, P. Wang, and R. X. Gao, “Deep Learning and Its Applications to Machine Health Monitoring: A Survey.” arXiv, Dec. 15, 2016 [Online]. Available: http://arxiv.org/abs/1612.07640. [Accessed: Jun. 19, 2022]
[7] X. Wang, D. Qiao, K. Han, X. Chen, and Z. He, “Research on Predicting Remain Useful Life of Rolling Bearing Based on Parallel Deep Residual Network,” Applied Sciences, vol. 12, no. 9, 2022, doi: 10.3390/app12094299.
[8] C.-C. Kuo, C.-H. Liu, H.-C. Chang, and K.-J. Lin, “Implementation of a Motor Diagnosis System for Rotor Failure Using Genetic Algorithm and Fuzzy Classification,” Applied Sciences, vol. 7, no. 1, 2017, doi: 10.3390/app7010031.
[9] G. Nassajian and S. Balochian, “Multi-model estimation using neural network and fault detection in unknown time continuous fractional order nonlinear systems,” Transactions of the Institute of Measurement and Control, vol. 43, no. 3, pp. 497–509, Feb. 2021, doi: 10.1177/0142331220932376. [Online]. Available: https://doi.org/10.1177/0142331220932376. [Accessed: Sep. 09, 2022]
[10] Z. Xu et al., “A Text-Driven Aircraft Fault Diagnosis Model Based on a Word2vec and Priori-Knowledge Convolutional Neural Network,” Aerospace, vol. 8, no. 4, p. 112, Apr. 2021, doi: 10.3390/aerospace8040112. [Online]. Available: https://www.mdpi.com/2226-4310/8/4/112. [Accessed: Sep. 12, 2022]
[11] J. Zhou, X. Yang, and J. Li, “Deep Residual Network Combined with Transfer Learning Based Fault Diagnosis for Rolling Bearing,” Applied Sciences, vol. 12, no. 15, 2022, doi: 10.3390/app12157810.
[12] J. Chuya-Sumba, L. M. Alonso-Valerdi, and D. I. Ibarra-Zarate, “Deep-Learning Method Based on 1D Convolutional Neural Network for Intelligent Fault Diagnosis of Rotating Machines,” Applied Sciences, vol. 12, no. 4, 2022, doi: 10.3390/app12042158.
[13] B. Ma, W. Cai, Y. Han, and G. Yu, “A Novel Probability Confidence CNN Model and Its Application in Mechanical Fault Diagnosis,” IEEE Trans. Instrum. Meas., vol. 70, pp. 1–11, 2021, doi: 10.1109/TIM.2021.3077965. [Online]. Available: https://ieeexplore.ieee.org/document/9424584/. [Accessed: Jun. 08, 2022]
[14] H.-C. Chang, Y.-C. Wang, Y.-Y. Shih, and C.-C. Kuo, “Fault Diagnosis of Induction Motors with Imbalanced Data Using Deep Convolutional Generative Adversarial Network,” Applied Sciences, vol. 12, no. 8, 2022, doi: 10.3390/app12084080.
[15] H.-C. Yan, J.-H. Zhou, and C. K. Pang, “New types of faults detection and diagnosis using a mixed soft & hard clustering framework,” in 2016 IEEE 21st International Conference on Emerging Technologies and Factory Automation (ETFA), Berlin, Germany, Sep. 2016, pp. 1–6, doi: 10.1109/ETFA.2016.7733738.
[16] R. Liu, B. Yang, and A. G. Hauptmann, “Simultaneous Bearing Fault Recognition and Remaining Useful Life Prediction Using Joint-Loss Convolutional Neural Network,” IEEE Transactions on Industrial Informatics, vol. 16, no. 1, pp. 87–96, Jan. 2020, doi: 10.1109/TII.2019.2915536.
[17] R. Yan, F. Shen, C. Sun, and X. Chen, “Knowledge Transfer for Rotary Machine Fault Diagnosis,” IEEE Sensors Journal, vol. 20, no. 15, pp. 8374–8393, Aug. 2020, doi: 10.1109/JSEN.2019.2949057.
[18] H. Zheng, Y. Yang, J. Yin, Y. Li, R. Wang, and M. Xu, “Deep Domain Generalization Combining A Priori Diagnosis Knowledge Toward Cross-Domain Fault Diagnosis of Rolling Bearing,” IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1–11, 2021, doi: 10.1109/TIM.2020.3016068.
[19] Z. Ye and J. Yu, “Deep morphological convolutional network for feature learning of vibration signals and its applications to gearbox fault diagnosis,” Mechanical Systems and Signal Processing, vol. 161, p. 107984, Dec. 2021, doi: 10.1016/j.ymssp.2021.107984. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0888327021003794
[20] P. Cao, S. Zhang, and J. Tang, “Preprocessing-Free Gear Fault Diagnosis Using Small Datasets With Deep Convolutional Neural Network-Based Transfer Learning,” IEEE Access, vol. 6, pp. 26241–26253, 2018, doi: 10.1109/ACCESS.2018.2837621.
[21] H.-M. Lin, C.-Y. Lin, H.-Y. Lu, C.-H. Wang, and M.-J. Tsai, “A Study of Ultra-Wideband Low Noise Device by Edge AI Technology for SVMD Solution of Rotating Equipment,” presented at the Artificial Intelligence Technology and Application, Taichung, Taiwan, 20 May 2022, p. 48.
[22] S. J. Pan and Q. Yang, “A Survey on Transfer Learning,” IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345–1359, Oct. 2010, doi: 10.1109/TKDE.2009.191.
[23] Y. Wei, Y. Zheng, and Q. Yang, “Transfer Knowledge between Cities,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco California USA, Aug. 2016, pp. 1905–1914, doi: 10.1145/2939672.2939830 [Online]. Available: https://dl.acm.org/doi/10.1145/2939672.2939830. [Accessed: Oct. 28, 2022]
[24] F. Yang, W. Zhang, L. Tao, and J. Ma, “Transfer Learning Strategies for Deep Learning-based PHM Algorithms,” Applied Sciences, vol. 10, no. 7, 2020, doi: 10.3390/app10072361.
[25] M. Sun, H. Wang, P. Liu, S. Huang, P. Wang, and J. Meng, “Stack Autoencoder Transfer Learning Algorithm for Bearing Fault Diagnosis Based on Class Separation and Domain Fusion,” IEEE Transactions on Industrial Electronics, vol. 69, no. 3, pp. 3047–3058, Mar. 2022, doi: 10.1109/TIE.2021.3066933.
[26] H.-M. Lin, C.-Y. Lin, C.-H. Wang, and M.-J. Tsai, “A Novel Mechanical Fault Diagnosis Based on Transfer Learning with Probability Confidence Convolutional Neural Network Model,” Applied Sciences, vol. 12, no. 19, p. 9670, Sep. 2022, doi: 10.3390/app12199670. [Online]. Available: https://www.mdpi.com/2076-3417/12/19/9670. [Accessed: Oct. 30, 2022]
[27] H.-M. Lin, C.-H. Wang, M.-J. Tsai, and C.-Y. Lin, “A Novel Mechanical Fault Diagnosis Based on Transfer Learning in Probabilistic Confidence CNN Model,” in 2022 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2022, Hsinchu, Taiwan, Jul. 2022.
[28] J. Lee, F. Wu, W. Zhao, M. Ghaffari, L. Liao, and D. Siegel, “Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications,” Mechanical Systems and Signal Processing, vol. 42, pp. 314–334, Jan. 2014, doi: 10.1016/j.ymssp.2013.06.004.
[29] G. W. Vogl, B. A. Weiss, and M. Helu, “A review of diagnostic and prognostic capabilities and best practices for manufacturing,” J Intell Manuf, vol. 30, no. 1, pp. 79–95, Jan. 2019, doi: 10.1007/s10845-016-1228-8. [Online]. Available: http://link.springer.com/10.1007/s10845-016-1228-8. [Accessed: Jun. 08, 2022]
[30] “What is Industrial Internet of Things (IIoT)?,” TIBCO Software Inc. [Online]. Available: https://www.tibco.com/zh-hant/reference-center/what-is-industrial-internet-of-things-iiot
[31] H. Boyes, B. Hallaq, J. Cunningham, and T. Watson, “The industrial internet of things (IIoT): An analysis framework,” Computers in Industry, vol. 101, pp. 1–12, Oct. 2018, doi: 10.1016/j.compind.2018.04.015. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0166361517307285
[32] S. A. Boyer, Supervisory Control and Data Acquisition, 2nd ed. ISA (International Society of Automation), 1999 [Online]. Available: https://dl.acm.org/doi/abs/10.5555/520758
[33] M. Hermann, T. Pentek, and B. Otto, “Design Principles for Industrie 4.0 Scenarios,” in 2016 49th Hawaii International Conference on System Sciences (HICSS), Koloa, HI, USA, Jan. 2016, pp. 3928–3937, doi: 10.1109/HICSS.2016.488.
[34] S. ALAmri, F. ALAbri, and T. Sharma, “Artificial Intelligence Deployment to Secure IoT in Industrial Environment,” in Quality Control - An Anthology of Cases, Dr. Leo Dimitrios Kounis, Ed. Rijeka: IntechOpen, 2022. [Online]. Available: https://doi.org/10.5772/intechopen.104469. [Accessed: Dec. 18, 2022]
[35] J. Liu, D. Yu, Y. Hu, H. Yu, W. He, and L. Zhang, “CNC Machine Tool Fault Diagnosis Integrated Rescheduling Approach Supported by Digital Twin-Driven Interaction and Cooperation Framework,” IEEE Access, vol. 9, pp. 118801–118814, 2021, doi: 10.1109/ACCESS.2021.3106797.
[36] G. Darling, “What is edge computing?,” IBM, Mar. 21, 2022 [Online]. Available: https://developer.ibm.com/articles/what-is-edge-computing/
[37] H. G. Abreha, M. Hayajneh, and M. A. Serhani, “Federated Learning in Edge Computing: A Systematic Survey,” Sensors, vol. 22, no. 2, 2022, doi: 10.3390/s22020450.
[38] “ISO/IEC JTC 1/SC 41 Internet of things and digital twin.” [Online]. Available: https://www.iso.org/committee/6483279.html
[39] D. Novikov, Cybernetics: from Past to Future, 1st ed. Springer, 2015.
[40] H.-M. Lin, S.-H. Chen, J. Kao, Y.-M. Lee, G. L.-K. Hsiao, and C.-Y. Lin, “Applying Active Dynamic Signage System in Complex Underground Construction,” International Journal of Scientific & Engineering Research, vol. 8, Feb. 2017.
[41] Y. Himeur et al., “AI-big data analytics for building automation and management systems: a survey, actual challenges and future perspectives,” Artificial Intelligence Review, Oct. 2022, doi: 10.1007/s10462-022-10286-2. [Online]. Available: https://doi.org/10.1007/s10462-022-10286-2
[42] H.-M. Lin, C.-Y. Lin, J.-C. Ko, and Y.-S. Wu, “Risk Factors of Post-earthquake Fire for Constructions Using the Analytic Hierarchy Process Approach,” in Proceedings of the 2016 International Conference on Architectural Engineering and Civil Engineering (AECE2016, Shanghai, China, Dec. 2016, pp. 1–4, doi: 10.2991/aece-16.2017.1 [Online]. Available: https://doi.org/10.2991/aece-16.2017.1
[43] I. Petri, S. Kubicki, Y. Rezgui, A. Guerriero, and H. Li, “Optimizing Energy Efficiency in Operating Built Environment Assets through Building Information Modeling: A Case Study,” Energies, vol. 10, no. 8, 2017, doi: 10.3390/en10081167.
[44] B. Gates, How to Avoid a Climate Disaster: The Solutions We Have and the Breakthroughs We Need. United States: Alfred A. Knopf, 2021.
[45] A. Grilo and R. Jardim-Goncalves, “Value proposition on interoperability of BIM and collaborative working environments,” Automation in Construction, vol. 19, no. 5, pp. 522–530, Aug. 2010, doi: 10.1016/j.autcon.2009.11.003. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0926580509001733
[46] M.-H. Tsai, M. Mom, and S.-H. Hsieh, “Developing critical success factors for the assessment of BIM technology adoption: part I. Methodology and survey,” Journal of the Chinese Institute of Engineers, vol. 37, no. 7, pp. 845–858, Oct. 2014, doi: 10.1080/02533839.2014.888811.[Online].Available: https://doi.org/10.1080/02533839.2014.888811
[47] B. Succar, “Building information modelling framework: A research and delivery foundation for industry stakeholders,” Automation in Construction, vol. 18, no. 3, pp. 357–375, May 2009, doi: 10.1016/j.autcon.2008.10.003. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0926580508001568
[48] Y. Arayici, P. Coates, L. Koskela, M. Kagioglou, C. Usher, and K. O’Reilly, “Technology adoption in the BIM implementation for lean architectural practice,” Automation in Construction, vol. 20, no. 2, pp. 189–195, Mar. 2011, doi: 10.1016/j.autcon.2010.09.016. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0926580510001457
[49] “Level of Development Specification, BIMForum,” BIMForum, Jun. 28, 2022. [Online].Available:https://bimforum.org/resource/%EF%BF%BC%EF%BF%BClevel-of-development-specification/
[50] “LOD Spec Survey,” BIMForum, Oct. 22, 2022. [Online]. Available: https://bimforum.org/lod-spec-survey/
[51] SPACEWELL INTERNATIONAL., “BIM for FM or how to facilitate building maintenance during the operational phase.” [Online]. Available: https://spacewell.com/resources/blog/bim-for-fm-or-how-to-facilitate-building-maintenance-during-the-operational-phase/
[52] A. M. Turing, “Computing Machinery and Intelligence,” Mind, 2007. [Online].Available: https://doi.org/10.1093/mind/LIX.236.433
[53] J. LEE, Industrial AI: Applications with Sustainable Performance, Springer, 2020.
[54] D. C. Montgomery, E. A. Peck, and G. G. Vining, Introduction to Linear Regression Analysis, 6th Edition. Wiley, 2021.
[55] S. Sperandei, “Understanding logistic regression analysis,” Biochem Med (Zagreb), vol. 24(1), pp. 12–18, Feb. 2014, doi: doi: 10.11613/BM.2014.003. [Online]. Available: https://doi.org/10.11613/BM.2014.003
[56] D. W. Hosmer Jr, S. Lemeshow, and R. X. Sturdivant, Applied Logistic Regression, Third Edition. 2013 [Online]. Available: DOI: 10.1002/9781118548387
[57] L. Rokach and O. Maimon, Decision Trees. 2005 [Online]. Available: https://doi.org/10.1007/0-387-25465-X_9
[58] L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, Oct. 2001, doi: 10.1023/A:1010933404324. [Online]. Available: https://doi.org/10.1023/A:1010933404324
[59] G. Ke et al., “LightGBM: A Highly Efficient Gradient Boosting Decision Tree,” in NIPS’17, Long Beach, California, USA, Dec. 2017, pp. 3149–3157.
[60] O. Kramer, “K-Nearest Neighbors,” in Dimensionality Reduction with Unsupervised Nearest Neighbors, O. Kramer, Ed. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013, pp. 13–23 [Online]. Available: https://doi.org/10.1007/978-3-642-38652-7_2
[61] P. Cichosz, “Naïve bayes classifier,” 2015.
[62] S.-L. Lin, “Application of Machine Learning to a Medium Gaussian Support Vector Machine in the Diagnosis of Motor Bearing Faults,” Electronics, vol. 10, no. 18, 2021, doi: 10.3390/electronics10182266.
[63] L. Wang, Support vector machines: theory and applications, vol. 177. Springer Science & Business Media, 2005.
[64] K. P. Sinaga and M.-S. Yang, “Unsupervised K-means clustering algorithm,” IEEE access, vol. 8, pp. 80716–80727, Apr. 2020, doi: DOI: 10.1109/ACCESS.2020.2988796.
[65] L. P. Kaelbling, M. L. Littman, and A. W. Moore, “Reinforcement learning: A survey,” Journal of artificial intelligence research, vol. 4, pp. 237–285, 1996.
[66] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” nature, vol. 521, no. 7553, pp. 436–444, 2015.
[67] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016 [Online]. Available: http://www.deeplearningbook.org
[68] A. Xu et al., “A Hybrid Deep Learning Model for Malicious Behavior Detection,” in 2020 IEEE 6th Intl Conference on Big Data Security on Cloud (BigDataSecurity), IEEE Intl Conference on High Performance and Smart Computing, (HPSC) and IEEE Intl Conference on Intelligent Data and Security (IDS), Baltimore, MD, USA, May 2020, pp. 55–59, doi: 10.1109/BigDataSecurity-HPSC-IDS49724.2020.00021.
[69] L. Alzubaidi et al., “Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions,” Journal of big Data, vol. 8, no. 1, pp. 1–74, 2021.
[70] T. Mikolov, M. Karafiát, L. Burget, J. Cernocký, and S. Khudanpur, “Recurrent neural network based language model.,” in Interspeech, Sep. 2010, vol. 2, no. 3, pp. 1045–1048.
[71] K. Weiss, T. M. Khoshgoftaar, and D. Wang, “A survey of transfer learning,” Journal of Big data, vol. 3, no. 1, pp. 1–40, 2016.
[72] F. Zhuang et al., “A comprehensive survey on transfer learning,” Proceedings of the IEEE, vol. 109, no. 1, pp. 43–76, 2020.
[73] “ISO10816 Charts.” [Online]. Available: https://www.vibsens.com/index.php/knowledge-base/iso10816-iso7919-charts/iso10816-charts
[74] J. Pellegrino, M. Justiniano, A. Raghunathan, and B. A. Weiss, “Measurement Science Roadmap for Prognostics and Health Management for Smart Manufacturing Systems,” National Institute of Standards and Technology, NIST AMS 100-2, Sep. 2016 [Online]. Available: https://nvlpubs.nist.gov/nistpubs/ams/NIST.AMS.100-2.pdf. [Accessed: Nov. 02, 2022]
[75] 莊哲嘉, 周家祿, 盧銘駿, 洪男雄, and 陳勇龍, “Cooling system for optimization control and automatic control method thereof , Patent Number: TWI640387B, https://patents.google.com/patent/TWI640387B/en?oq=TWI640387B,” TWI640387B [Online]. Available: https://patents.google.com/patent/TWI640387B/en?oq=TWI640387B
[76] C.-C. CHUANG, “TSMC successfully developed the industry’s first optimized energy-saving control program for ice water systems.” [Online]. Available: https://esg.tsmc.com/ch/update/greenManufacturing/caseStudy/6/index.html
[77] G.-T. Liu and H.-P. Cheng, “The Research of Remote Monitoring and Abnormal Operation Diagnosis of Refrigeration Cycle System,” Master Thesis, National Taipei University of Technology (Taipei Tech), 2013 [Online]. Available: https://hdl.handle.net/11296/k2w3xh
[78] E. Sala-Cardoso, M. Delgado-Prieto, K. Kampouropoulos, and L. Romeral, “Predictive chiller operation: A data-driven loading and scheduling approach,” Energy and Buildings, vol. 208, p. 109639, Feb. 2020, doi: 10.1016/j.enbuild.2019.109639. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0378778819322327
[79] T.-S. Lee and W.-C. Lu, “An evaluation of empirically-based models for predicting energy performance of vapor-compression water chillers,” Applied Energy, vol. 87, no. 11, pp. 3486–3493, Nov. 2010, doi: 10.1016/j.apenergy.2010.05.005. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0306261910001595
[80] A. Rafati, H. R. Shaker, and S. Ghahghahzadeh, “Fault Detection and Efficiency Assessment for HVAC Systems Using Non-Intrusive Load Monitoring: A Review,” Energies, vol. 15, no. 1, 2022, doi: 10.3390/en15010341.
[81] Y. Chang and K.-H. Yang, “Fault Detection and Diagnostic Expert Systems in HVAC Applications,” Master Thesis, Sun Yat-Sen University, 2006 [Online]. Available: https://hdl.handle.net/11296/yh999j
[82] K. Verbert, R. Babuka, and B. De Schutter, “Combining Knowledge and Historical Data for System-Level Fault Diagnosis of HVAC Systems,” Eng. Appl. Artif. Intell., vol. 59, no. C, pp. 260–273, Mar. 2017, doi: 10.1016/j.engappai.2016.12.021. [Online]. Available: https://doi.org/10.1016/j.engappai.2016.12.021
[83] Y.-C. Li and M.-J. Tsai, “The Discharge Performance Analysis of Ice Storage Systems by Adopting Gray Theory Prediction,” Master Thesis, National Taiwan University of Science and Technology, 2005 [Online]. Available: https://hdl.handle.net/11296/6pzrmr
[84] Lamyaa Sadouk ED1 - Chun-Kit Ngan, “CNN Approaches for Time Series Classification,” in Time Series Analysis, Rijeka: IntechOpen, 2018, p. Ch. 4 [Online]. Available: https://doi.org/10.5772/intechopen.81170. [Accessed: Jul. 06, 2022]
[85] W. A. Smith and R. B. Randall, “Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study,” Mechanical Systems and Signal Processing, vol. 64–65, pp. 100–131, Dec. 2015, doi: 10.1016/j.ymssp.2015.04.021. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0888327015002034
[86] H. Huang and N. Baddour, “Bearing vibration data collected under time-varying rotational speed conditions,” Data in Brief, vol. 21, pp. 1745–1749, Dec. 2018, doi: 10.1016/j.dib.2018.11.019. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2352340918314124
[87] Taiwan Artificial Intelligence Association [Online]. Available: https://www.aiatw.org/
[88] Harbor Technology Solutions Co., Ltd. (Taiwan) [Online]. Available: https://www.harbortech.com.tw/
[89] Chimes AI, Inc. [Online]. Available: https://chimes.ai/
[90] The Society of Taiwan Women in Science and Technology [Online]. Available: https://www.twist.org.tw/