在製造業複雜多變的生產條件下，廠務設備提供接近最適的生產環境以提升生產效率。然而，影響廠務設備運作的原因複雜且多變，應用專家經驗進行設備參數調控是目前常見的作法；不過此調控方法需耗費人力及無法確保設備於高效率狀態下執行。可解釋人工智慧(XAI)協助人們理解人工智慧模型的決策過程和預測結果，自動化定義了影響廠務設備運行效率的關鍵特徵與特徵條件。啟發式演算法中的基因演算法(GA)和粒子群最佳化演算法(PSO)可做為解決複雜的最佳化問題的方法，尋優出最適的廠務設備參數。本文採用XAI結合GA和PSO為核心工具來發展基於XAI之廠務調控系統(FCSXAI)；透過XAI識別出廠務設備於高效率的運行條件，並以此做為啟發式演算法進行尋優的限制條件，確保廠務設備皆能在高效率的情況下運轉，實現了在降低能源消耗時亦能同時考量減少碳排放量。此外，由於本FCSXAI系統可自動化地定義高效率的特徵條件，可以有效地取代以往的專家經驗，讓使用者能快速調整設備參數以符合當下的生產排程和節省時間與成本，進而提高產線效率。而且，本FCSXAI系統可以配合需量反應的情境，當電力公司需要平衡電力供求和減輕尖峰負載時，本FCSXAI系統可以在符合最佳生產環境的條件下進行廠務設備的降載，以增加能源系統的穩定性。透過兩個實際案例分析，驗證本FCSXAI系統確可以有效地調控出最佳的設備參數，並能一併完成節能與減碳的目標。

Under the complicated manufacturing conditions, the facility provides the nearly optimal production environment to enhance efficiency. However, the factors influencing the operation of the facility are complex and varied. The commonly used approach is to adopt expert experience for parameter adjustments. Nonetheless, this approach requires human efforts and does not ensure the operation can be at a high-efficiency level. Explainable Artificial Intelligence (XAI) can help to better understand AI decision-making procedures and prediction results. By automating this approach, it can define the crucial features and conditions affecting the efficiency of the facility. Heuristic algorithms like Genetic Algorithms (GA) and Particle Swarm Optimization (PSO) serve as the methods for solving complex optimization problems and identifying optimal facility parameters. This study combines XAI with GA and PSO as core tools to develop an XAI-based Facility Control System (FCSXAI). By applying FCSXAI, the high-efficiency operating conditions of facility are identified as the constraints for heuristic algorithm optimization to ensure that facility can operate at high efficiency, thereby reducing energy consumption and carbon emissions. Moreover, this FCSXAI system automatically defines feature conditions of high efficiency to replace traditional expert experience; as such, users can quickly adjust facility parameters to align with the current production schedule, save time and cost, as well as enhance production line efficiency. Additionally, the FCSXAI system can be applied in demand response scenarios. When power companies need to balance electricity supply and demand as well as alleviate peak loads, the FCSXAI system can reduce the load of the facility under optimal production conditions and enhance energy system stability.

[1] Fankhauser, S., Smith, S.M., Allen, M. et al., “The meaning of net zero and how to get it right,” Nature Climate Chang, vol.12, pp. 15–21, Dec. 2021.
[2] J. Deutch, “Is Net Zero Carbon 2050 Possible?” Joule, vol.4, no. 11, pp. 2237–2240, Nov. 2020.
[3] Y.-C. Lin, M.-H. Hung, H.-C. Huang, C.-C. Chen, Y.-S. Hsieh, and F.-T. Cheng, “Development of advanced manufacturing cloud of things (AMCoT) - a smart manufacturing platform,” IEEE Robotics and Automation Letters, vol. 2, no. 3, pp. 1809-1816, Jan. 2016. doi:10.1109/LRA.2017.2706859.
[4] F.-T. Cheng et al., Industry 4.1: Intelligent Manufacturing with Zero Defects, ISBN: 9781119739890, Publisher: Wiley-IEEE Press, Hoboken, New Jersey, U.S.A., October 2021.
[5] F.-T. Cheng, C.-A. Kao, C.-F. Chen, and W.-H. Tsai, “Tutorial on applying the VM technology for TFT-LCD manufacturing,” IEEE Trans. Semicond. Manuf, vol. 28, no. 1, pp. 55–69, Feb. 2015. doi: 10.1109/TSM.2014.2380433.
[6] F. -T. Cheng, Y. -S. Hsieh, J. -W. Zheng, S. -M. Chen, R. -X. Xiao, and C. -Y. Lin, “A scheme of high-dimensional key-variable search algorithms for yield improvement,” IEEE Robot. Autom. Lett, vol. 2, no. 1, pp. 179–186, Jan. 2017. doi: 10.1109/LRA.2016.2584143.
[7] C. -Y. Lin, Y. -M. Hsieh, F. -T. Cheng, H. -C. Huang, and M. Adnan, “Time Series Prediction Algorithm for Intelligent Predictive Maintenance,” IEEE Robotics and Automation Letters, vol. 4, no. 3, pp. 2807-2814, Jul. 2019. doi: 10.1109/LRA.2019.2918684.
[8] T. -H. Tsai, B. Yan, P. B. Luh, H. -C. Yang, M. A. Bragin and F. -T. Cheng, “Near-Optimal Scheduling for IC Packaging Operations Considering Processing-Time Variations and Factory Practices,” in IEEE Robotics and Automation Letters, doi: 10.1109/LRA.2023.3265594.
[9] F.-T. Cheng, H. Tieng, H.-C. Yang, M.-H. Hung, Y.-C. Lin, C.-F. Wei, and, Z.-Y. Shieh, “Industry 4.1 for wheel machining automation,” in IEEE Robotics and Automation Letters, vol.1, no.1, pp. 332-339, Jan. 2016.
[10] H. Tieng, T. -C. Ou, T. -H. Tsai, Y. -Y. Li, M. -H. Hung and F. -T. Cheng, “I4.2-GiM: A Novel Green Intelligent Manufacturing Framework for Net Zero,” in IEEE Transactions on Automation Science and Engineering, Dec. 2023. doi: 10.1109/TASE.2023.3340149.
[11] Alan P. Rossiter and Beth P. Jones, “Energy Management and Efficiency for the Process Industries”, ISBN: 9781118838259, Publisher: Wiley-AIChE, May 2015.
[12] K. Deng et al., “Model Predictive Control of Central Chiller Plant With Thermal Energy Storage Via Dynamic Programming and Mixed-Integer Linear Programming,” in IEEE Transactions on Automation Science and Engineering, vol. 12, no. 2, pp. 565-579, April 2015, doi: 10.1109/TASE.2014.2352280.
[13] Y. -C. Chang, T. -S. Chan, and W. -S. Lee, “Economic dispatch of chiller plant by gradient method for saving energy,” Applied Energy, vol.87, no. 4, pp.1096-1101, Apr. 2010, doi: 10.1016/j.apenergy.2009.05.004.
[14] Y. -C. Chang, W. -H. Chen, C -Y. Lee, and C. -N. Huang, “Simulated annealing based optimal chiller loading for saving energy,” Energy Conversion and Management, vol.47, no. 15, pp.2044-2058, Sep. 2006, doi: 10.1016/j.enconman.2005.12.022.
[15] Y. He, Q. Xu, D. Li, S. Mei, Z. Zhang and Q. Ji, “Energy-saving method and performance analysis of chiller plants group control based on Kernel Ridge Regression and Genetic Algorithm,” Science and Technology for the Built Environment, vol.29, pp.545-559, Feb. 2023, doi: 10.1080/23744731.2023.2179304.
[16] S. Xing and J. Zhang, “Chiller-pump system optimization method for minimum energy operation based on multi-objective evolutionary algorithm,” Applied Thermal Engineering, vol.208, Art. May. 2022, doi: 10.1016/j.applthermaleng.2022.118150.
[17] C.-M. Lin, C.-Y. Wu, K.-Y. Tseng, C.-C. Ku, and S.-F. Lin, “Applying Two-Stage Differential Evolution for Energy Saving in Optimal Chiller Loading,” Energies, vol. 12, no. 4, p. 622, Feb. 2019, doi: 10.3390/en12040622.
[18] Q. Deng, L. Xu, T. Zhao, X. Hong, X. Shan, and Z. Ren, “Cooperative Optimization of A Refrigeration System with A Water-Cooled Chiller and Air-Cooled Heat Pump by Coupling BPNN and PSO,” Energies, vol. 15, no. 19, p. 7077, Sep. 2022, doi: 10.3390/en15197077.
[19] D. -S. Lee, Y. -T. Chen, and S. -L. Chao, “Universal workflow of artificial intelligence for energy saving,” Energy Reports, vol.8, pp.1602-1633, Nov. 2022, doi: 10.1016/j.egyr.2021.12.066.
[20] E. S. Cardoso, M. D. Prieto, K. Kampouropoulos and L. Romeral, “Predictive chiller operation: A data-driven loading and scheduling approach,” Energy Build, vol. 208, no.1, Feb. 2020, doi: 10.1016/j.enbuild.2019.109639.
[21] F. Jabari, M. Mohammadpourfard and B. Mohammadi-Ivatloo, “Energy efficient hourly scheduling of multi-chiller systems using imperialistic competitive algorithm,” Computers & Electrical Engineering, vol. 82, Article 106550, Mar. 2020, doi: doi.org/10.1016/j.compeleceng.2020.106550.
[22] C. -F. Chien, Y. -J. Chen, Y. -T. Han, and Y. -C. Wu, “Industry 3.5 for optimizing chiller configuration for energy saving and an empirical study for semiconductor manufacturing,” Resources, Conservation and Recycling, vol. 168, Article 105247, May. 2021, doi: 10.1016/j.resconrec.2020.105247.
[23] M. B. Awan, K. Li, Z. Li, and Z. Ma. “A data driven performance assessment strategy for centralized chiller systems using data mining techniques and domain knowledge.” Journal of Building Engineering, vol.41, Art. no. 102751, Sep. 2021.
[24] C. -W. Chen, C. -C. Li, and C. -Y. Lin. “Combine Clustering and Machine Learning for Enhancing the Efficiency of Energy Baseline of Chiller System.” Energies, vol.13, no.17, p.43-68, Aug. 2020.
[25] T. Cheng, F. Harrou, Y. Sun and T. Leiknes, “Monitoring Influent Measurements at Water Resource Recovery Facility Using Data-Driven Soft Sensor Approach,” in IEEE Sensors Journal, vol. 19, no. 1, pp. 342-352, Jan. 2019, doi: 10.1109/JSEN.2018.2875954.
[26] Y. Liao and G. Huang, “A hybrid predictive sequencing control for multi-chiller plant with considerations of indoor environment control, energy conservation and economical operation cost,” Sustainable Cities and Society, vol. 49, Article 101616, Aug. 2019, doi: 10.1016/j.scs.2019.101616.
[27] D. Gunning, M. Stefik, J. Choi, T. Miller, S. Stumpf, and G. -Z. Yang. “XAI-Explainable artificial intelligence.” Science Robotics, vol. 4, no. 37, Dec. 2019, doi: 10.1126/scirobotics. aay7120.
[28] M. T. Ribeiro, S. Singh, and C. Guestrin. “Why Should I Trust You? : Explaining the Predictions of Any Classifier.” Association for Computing Machinery, New York, USA, pp.1135–1144, doi: 2016 10.18653/v1/N16-3020.
[29] J. Moon, S. Rho and S. W. Baik, “Toward explainable electrical load forecasting of buildings: A comparative study of tree-based ensemble methods with Shapley values,” Sustainable Energy Technologies and Assessments, vol. 54, Article 102888, Dec. 2022, doi: 10.1016/j.seta.2022.102888.
[30] K. Zhang, J. Zhang, P. -D. Xu, T. Gao and D. W. Gao, “Explainable AI in Deep Reinforcement Learning Models for Power System Emergency Control,” in IEEE Transactions on Computational Social Systems, vol. 9, no. 2, pp. 419-427, April 2022, doi: 10.1109/TCSS.2021.3096824.
[31] S. Srinivasan, P. Arjunan, B. Jin, A. L. Sangiovanni-Vincentelli, Z. Sultan and K. Poolla, “Explainable AI for Chiller Fault-Detection Systems: Gaining Human Trust,” in Computer, vol. 54, no. 10, pp. 60-68, Oct. 2021, doi: 10.1109/MC.2021.3071551.
[32] D. Chakraborty, A. Alam, S. Chaudhuri, H. Basagaoglu, T. Sulbaran and S. Langar, “Scenario-based prediction of climate change impacts on building cooling energy consumption with explainable artificial intelligence,” in Applied Energy, vol. 291, Article 116807, Jun. 2021, doi: 10.1016/j.apenergy.2021.116807.
[33] M. Kuzlu, U. Cali, V. Sharma and Ö. Güler, “Gaining Insight Into Solar Photovoltaic Power Generation Forecasting Utilizing Explainable Artificial Intelligence Tools,” in IEEE Access, vol. 8, pp. 187814-187823, 2020, doi: 10.1109/ACCESS.2020.3031477.
[34] N. O’Connell, P. Pinson, H. Madsen and M. O’Malley, “Benefits and challenges of electrical demand response: A critical review,” Renewable and Sustainable Energy Reviews, vol.39, pp.686-699, Nov. 2014, doi: 10.1016/j.rser.2014.07.098.
[35] P. Siano, “Demand response and smart grids-A survey,” Renewable and Sustainable Energy Reviews, vol.30, pp.461-478, Nov. 2014, doi: 10.1016/j.rser.2013.10.022.
[36] X. Kou et al., “Model-Based and Data-Driven HVAC Control Strategies for Residential Demand Response,” in IEEE Open Access Journal of Power and Energy, vol. 8, pp. 186-197, 2021, doi: 10.1109/OAJPE.2021.3075426.
[37] D. Azuatalam, W. -L. Lee, F. D. Nijs, and A. Liebman, “Reinforcement learning for whole-building HVAC control and demand response,” in Energy and AI, vol. 2, Article 100020, Nov. 2020, doi: 10.1016/j.egyai.2020.100020.
[38] M. M. Saritas and A. Yasar, “AutoClass: A Bayesian Classification System,” Journal of Intelligent Systems and Applications in Engineering, vol. 7, pp. 88-91, 2019, doi: 10.18201//IJISAE.2019252786.
[39] A. Mathur and G. M. Foody, “Multiclass and Binary SVM Classification: Implications for Training and Classification Users,” in IEEE Geoscience and Remote Sensing Letters, vol. 5, no. 2, pp. 241-245, Apr. 2008, doi: 10.1109/LGRS.2008.915597.
[40] S. D. Jadhav and H. P. Channe. “Comparative study of K-NN, naive Bayes and decision tree classification techniques.” International Journal of Science and Research, vol. 5, no. 1, pp. 1842-1845, 2016.
[41] J. L. Speiser, M. E. Miller, J. Tooze, and E. Ip. “A Comparison of Random Forest Variable Selection Methods for Classification Prediction Modeling.” Expert Systems with Applications, vol. 134, pp. 93-101, Nov. 2019. doi:10.1016/j.eswa.2019.05.028.
[42] R. Santhanam, N. Uzir, S. Raman and S. Banerjee. “Experimenting XGBoost Algorithm for Prediction and Classification of Different Datasets,” International Journal of Control Theory and Applications, vol. 9, no.40, pp. 651-662, 2016.
[43] John H. Holland. “Genetic Algorithms.” Scientific American, vol. 267, no. 1, pp. 66-73, 1992.
[44] J. Kennedy and R. Eberhart, “Particle swarm optimization,” Proceedings of ICNN'95 - International Conference on Neural Networks, Perth, WA, Australia, 1995, pp. 1942-1948 vol.4, doi: 10.1109/ICNN.1995.488968.
[45] J. Yin, X. Liu, B.Guan, and T. Zhang, “Performance and improvement of cleanroom environment control system related to cold-heat offset in clean semiconductor fabs,” Energy and Buildings, vol.224, Article 110294, Oct. 2020, doi: 10.1016/j.enbuild.2020.110294.
[46] R. Machlev, L. Heistrene, M. Perl, K. Y. Levy, J. Belikov, S. Mannor and Y. Levron, “Explainable Artificial Intelligence (XAI) techniques for energy and power systems: Review, challenges and opportunities,” Energy and AI, vol. 9, p. 100169, Aug. 2022, doi: 10.1016/j.egyai.2022.100169.
[47] F. Acerbi, M. Rampazzo, and G. De Nicolao, “An Exact Algorithm for the Optimal Chiller Loading Problem and Its Application to the Optimal Chiller Sequencing Problem,” Energies, vol. 13, no. 23, p. 6372, Dec. 2020, doi: 10.3390/en13236372.