隨著工業 4.0 的概念逐漸在各行業中普及，針對人工智慧相關技術應用於廢水處理相關領域的研究似乎也開始搭上了這股熱潮，國際上類似主題的文獻研究數量在近年來快速地成長。本研究以台灣某工業區的聯合廢水處理廠為實廠案例，探討該廠規畫「廢水處理 4.0」（Wastewater Treatment 4.0）的藍圖，說明其中大數據與人工智慧系統在個案廠內開發導入的過程，並量化分析系統啟用後對於營運成本的影響。
個案所架構的「廢水處理 4.0」藍圖包含了六個構面、八大應用，六個構面分別為大數據、人工智慧、物聯網、雲端科技、沉浸體驗與數位安全共 6 項技術與工具，八大應用則為操作管理、維護保養、巡查稽核、教育訓練、即時監控、參訪導覽、能源管理、智慧防災，以期提升廠務營運效率，將傳統的廢水廠，升級改造為智慧化的「廢水處理 4.0」。在大數據的應用，個案廢水廠彙整收集 2019 年全廠的處理各單元的水質濃度、水量、操作參數、環境變數等，合計共 281 項大數據應用 KNN機器學習演算法（K Nearest Neighbor）建置資料庫並進行資料探勘。大數據資料庫透過皮爾森積動差相關（Pearson Correlation）分析探討不同參數之間的相關性，而系統其中一個分析結果顯示，二期二階工程生物除氮程序甲醇的加藥量可能尚有優化的空間。針對生物除氮系統，個案廢水處理廠運用類神經網路（ANNs, Artificial Neural Networks）技術開發人工智慧輔助操作，輸入的參數包括相關處理單元的水量、水質濃度、化藥加藥量、鼓風機曝氣量、迴流量等，取得處理水質、化藥使用及能源消耗三者之間的平衡。
然而智慧化系統的導入仍面臨了許多挑戰，例如為了確保輸入參數的可靠度，必需額外投入人力針對增設的水質線上監測儀器執行保養校正。此外，初期階段為了驗證人工智慧系統的穩定性，個案廢水廠在研究期間並未直接讓系統接管生物除氮程序的自動控制，而是採行由系統給操作建議，再由人工調整操作參數的方式推行。本研究彙整個案廢水廠人工智慧系統啟動前後共 18 個月（自2020 年 7 月至 2021 年 12 月）的綜合成果，在人工智慧輔助操作系統啟用後氨氮去除率約增加 3.9%、總氮去除率約降低 4.3%、甲醇加藥量減少 43.4%、用電量增加 1.5%。也就是人工智慧輔助操作系統在處理水質及用電量沒有明顯影響的前提下（差異均小於 5%），達成節省用藥的成效，推估每年可節省約 527 萬操作費用。

The concept of Industry 4.0 is widely spread to different kinds of industry. Recently, it seems that it’s trend in relation of wastewater treatment applied with artificial intelligence, as well as the number of publications for the said subject. This case study is for a full-scale wastewater treatment plant in Taiwan. The blueprint of “Wastewater Treatment 4.0” was described, including the process for big data and artificial intelligence system setting up. Further analysis was conducted regarding the cost effect of plant operation.
The blueprint for “Wastewater Treatment 4.0” of case wastewater treatment plant is involved 6 main parts which are big data, artificial intelligence, internet of things, cloud technology, immersive experience and cyber security. These tools and technologies are planned to be applied for 8 practices, which including operation management, maintenance, inspection and audit, employee training, on-line monitoring, site visit, power management and smart safety. The improvement for the performance of wastewater treatment plant will be expected, and the intellectualized “Wastewater Treatment 4.0” will be established from traditional wastewater treatment plant.
Totally 281 items of data generated during year 2019 in the case wastewater treatment plant were collected, including water quality, amount of wastewater, operation parameters and environmental variables. The machine learning algorithm KNN (K Nearest Neighbor) was applied for database establishment and the further data mining of big data. The Pearson Correlation analysis was applied for the relationship of different parameters. One of the results of big data analysis showed that it might have room for operation optimization regarding the methanol dosing of biological nitrogen removal process in the Phase II Stage II of case wastewater treatment plant.
For biological nitrogen removal process, the ANNs (Artificial Neural Networks) was applied for the auxiliary operation of case wastewater treatment plant. The inputs of artificial intelligence system were including the amount of wastewater, water quality, chemical dosing, the flowrate of blower, sludge reflux and nitrification reflux. The output of this AI system was for the balance between effluence waste quality, chemical utilization and power consumption.
However, the establishment for AI system of case wastewater treatment plant was facing lots of challenge. For example, in order to make sure the reliability of input data, the extra human resources were required for the maintenance and calibration of on-line water quality detectors. Furthermore, instead of the automatic control for biological nitrogen removal process, operation parameters suggested from AI system and then adjusted manually was conducted before the certification for the stability of the AI system.
This study summarized the operational performance of 18 months, from July 2020 to December 2021, before and after the AI system starting up. The average ammonia nitrogen removal rate, total nitrogen removal rate, methanol dosing and power utilization were difference by around + 3.9%, -4.3%, -43.4% and +1.5% respectively. It means that substantial chemical saving was observed under the precondition without significant effect of water quality and power consumption for the AI system applied in the wastewater treatment process. Around 5.27 million Taiwan dollar per year of operational cost saving was estimated in this study.

侯淨鋌 （2014） 新穎生物硝化脫氮程序之特性研究 （碩士 ） 國立成功大學，環境工程研究所
林翰璘 （2016） 深入了解啟動與運轉Anammox反應器: 透過規模放大的顆粒污泥反應器處理煉焦廢水三級處理水的研究案例 （博士 ） 國立成功大學，環境工程研究所
林郁賢 （2013） 兩段式(部分硝化/厭氧氨氧化)生物除氮實驗室及模廠程序應用在高氮廢水處理之研究 （碩士 ） 國立成功大學，環境工程研究所
楊雅斐 （2004） 三段生物程序中好氧硝化槽功能評估與分生檢測生態研究 （碩士 ） 國立成功大學，環境工程研究所
簡福裕 （2021） 以多元線性迴歸開發減少染整工業水洗廢水預測模組之研究 （碩士 ） 國立雲林科技大學，環境與安全衛生工程研究所
黃淑君 （2006） 不織布薄膜反應槽好氧生物分解TFT-LCD製程有機廢水程序功能及生態變化之研究 （碩士 ） 國立成功大學，環境工程研究所
黃郁雯 （2012） 有效控制部分硝化串聯厭氧氨氧化程序處理高氮廢水之研究 （碩士 ） 國立成功大學，環境工程研究所
Abiodun, O. I., Jantan, A., Omolara, A. E., Dada, K. V., Mohamed, N. A., & Arshad, H. (2018). State-of-the-art in artificial neural network applications: A survey. Heliyon, 4(11), e00938.
Alabi, M., Telukdarie, A., & van Rensburg, N. J. (2019). Water 4.0: An integrated business model from an industry 4.0 approach. Paper presented at the 2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM).
Asadi, A., Verma, A., Yang, K., & Mejabi, B. (2017). Wastewater treatment aeration process optimization: A data mining approach. Journal of Environmental Management, 203, 630-639.
Bilan, Y., Rubanov, P., Vasylieva, T. A., & Lyeonov, S. (2019). The influence of industry 4.0 on financial services: Determinants of alternative finance development. Polish Journal of Management Studies.
Camargo, J. A., & Alonso, Á. (2006). Ecological and toxicological effects of inorganic nitrogen pollution in aquatic ecosystems: a global assessment. Environment International, 32(6), 831-849.
Delwiche, C. C. (1970). The nitrogen cycle. Scientific American, 223(3), 136-147.
Drury, C., Yang, X., Reynolds, W., & Tan, C. (2004). Influence of crop rotation and aggregate size on carbon dioxide production and denitrification. Soil and Tillage Research, 79(1), 87-100.
Fijani, E., Barzegar, R., Deo, R., Tziritis, E., & Skordas, K. (2019). Design and implementation of a hybrid model based on two-layer decomposition method coupled with extreme learning machines to support real-time environmental monitoring of water quality parameters. Science of the Total Environment, 648, 839-853.
Fowler, D., Coyle, M., Skiba, U., Sutton, M. A., Cape, J. N., Reis, S., Sheppard, L. J., Jenkins, A., Grizzetti, B., & Galloway, J. N. (2013). The global nitrogen cycle in the twenty-first century. Philosophical Transactions of the Royal Society B: Biological Sciences, 368(1621), 20130164.
Galloway, J. N., Dentener, F. J., Capone, D. G., Boyer, E. W., Howarth, R. W., Seitzinger, S. P., Asner, G. P., Cleveland, C. C., Green, P., & Holland, E. A. (2004). Nitrogen cycles: past, present, and future. Biogeochemistry, 70(2), 153-226.
Gingras, J.-F., & Charette, F. (2017). FP innovations forestry 4.0 initiative. Paper presented at the Bangor: 2017 Council on Forest Engineering Annual Meeting.
Glibert, P. M., Seitzinger, S., Heil, C. A., Burkholder, J. M., Parrow, M. W., Codispoti, L. A., & Kelly, V. (2005). Eutrophication. Oceanography, 18(2), 198.
Heo, S., Nam, K., Tariq, S., Lim, J. Y., Park, J., & Yoo, C. (2021). A hybrid machine learning–based multi-objective supervisory control strategy of a full-scale wastewater treatment for cost-effective and sustainable operation under varying influent conditions. Journal of Cleaner Production, 291, 125853.
Huang, M., Ma, Y., Wan, J., Wang, Y., Chen, Y., & Yoo, C. (2014). Improving nitrogen removal using a fuzzy neural network-based control system in the anoxic/oxic process. Environmental Science and Pollution Research, 21(20), 12074-12084.
Huang, Y., & Chen, M. (2015). Artificial neural network modeling of thin layer drying behavior of municipal sewage sludge. Measurement, 73, 640-648.
Hussin, A. A. (2018). Education 4.0 made simple: Ideas for teaching. International Journal of Education and Literacy Studies, 6(3), 92-98.
Ibarra, D., Ganzarain, J., & Igartua, J. I. (2018). Business model innovation through Industry 4.0: A review. Procedia Manufacturing, 22, 4-10.
Kijak, R. (2020). Water 4.0: Enhancing climate resilience. The Palgrave Handbook of Climate Resilient Societies, 1-39.
Klerkx, L., Jakku, E., & Labarthe, P. (2019). A review of social science on digital agriculture, smart farming and agriculture 4.0: New contributions and a future research agenda. NJAS-Wageningen Journal of Life Sciences, 90, 100315.
Lasi, H., Fettke, P., Kemper, H.-G., Feld, T., & Hoffmann, M. (2014). Industry 4.0. Business & Information systems Engineering, 6(4), 239-242.
Lauterbach, A., & Bonim, A. (2016). Artificial intelligence: A strategic business and governance imperative. NACD Directorship, 54-57.
Lee, J.-W., Suh, C., Hong, Y.-S. T., & Shin, H.-S. (2011). Sequential modelling of a full-scale wastewater treatment plant using an artificial neural network. Bioprocess and Biosystems Engineering, 34(8), 963-973.
Li, Y., Nuamah, L. A., Pu, Y., Zhang, H., Norgbey, E., Nwankwegu, A. S., Banahene, P., & Bofah, R. (2022). A radial basis function neural network based multi-objective optimization for simultaneously enhanced nitrogen and phosphorus removal in a full-scale integrated surface flow treatment wetland–pond system. Bioresource Technology, 344, 126336.
Ly, Q. V., Truong, V. H., Ji, B., Nguyen, X. C., Cho, K. H., Ngo, H. H., & Zhang, Z. (2022). Exploring potential machine learning application based on big data for prediction of wastewater quality from different full-scale wastewater treatment plants. Science of the Total Environment, 832, 154930.
Nag, S., Mondal, A., Roy, D. N., Bar, N., & Das, S. K. (2018). Sustainable bioremediation of Cd (II) from aqueous solution using natural waste materials: kinetics, equilibrium, thermodynamics, toxicity studies and GA-ANN hybrid modelling. Environmental Technology & Innovation, 11, 83-104.
Paul, R., Kenway, S., & Mukheibir, P. (2019). How scale and technology influence the energy intensity of water recycling systems-An analytical review. Journal of Cleaner Production, 215, 1457-1480.
Rennung, F., Luminosu, C. T., & Draghici, A. (2016). Service provision in the framework of Industry 4.0. Procedia-Social and Behavioral Sciences, 221, 372-377.
Rittmann, B. E., & McCarty, P. L. (2001). Environmental Biotechnology: Principles and Applications: McGraw-Hill Education.
Ruan, J., Zhang, C., Li, Y., Li, P., Yang, Z., Chen, X., Huang, M., & Zhang, T. (2017). Improving the efficiency of dissolved oxygen control using an on-line control system based on a genetic algorithm evolving FWNN software sensor. Journal of Environmental Management, 187, 550-559.
Sedlak, D. (2014). Water 4.0. In Water 4.0: Yale University Press.
Sharma, B., & Ahlert, R. (1977). Nitrification and nitrogen removal. Water Research, 11(10), 897-925.
Singh, A., & Agrawal, M. (2007). Acid rain and its ecological consequences. Journal of Environmental Biology, 29(1), 15.
Smith, V. H., & Schindler, D. W. (2009). Eutrophication science: where do we go from here? Trends in Ecology & Evolution, 24(4), 201-207.
Söderlund, R., & Rosswall, T. (1982). The nitrogen cycles. In The Natural Environment and the Biogeochemical Cycles (pp. 61-81): Springer.
Soleymani, A. R., & Moradi, M. (2018). Performance and modeling of UV/persulfate/Ce (IV) process as a dual oxidant photochemical treatment system: Kinetic study and operating cost estimation. Chemical Engineering Journal, 347, 243-251.
Spieck, E., & Bock, E. (2006). Nitrifying bacteria. Bergey’s Manual® of Systematic Bacteriology: The Proteobacteria, 2, 137-140.
Stevens, C. J., Duprè, C., Dorland, E., Gaudnik, C., Gowing, D. J., Bleeker, A., Diekmann, M., Alard, D., Bobbink, R., & Fowler, D. (2011). The impact of nitrogen deposition on acid grasslands in the Atlantic region of Europe. Environmental Pollution, 159(10), 2243-2250.
Sun, S., Bao, Z., Li, R., Sun, D., Geng, H., Huang, X., Lin, J., Zhang, P., Ma, R., Fang, L., Zhang, X.-H., & Zhao, X. (2017). Reduction and prediction of N2O emission from an Anoxic/Oxic wastewater treatment plant upon DO control and model simulation. Bioresource Technology, 244, 800--809. doi:10.1016/j.biortech.2017.08.054
Thuemmler, C., & Bai, C. (2017). Health 4.0: How Virtualization and Big Data Are Revolutionizing Healthcare: Springer.
Wiesmann, U. (1994). Biological nitrogen removal from wastewater. Biotechnics/Wastewater, 113-154.
Xu, R., Cao, J., Fang, F., Feng, Q., Yang, E., & Luo, J. (2021). Integrated data-driven strategy to optimize the processes configuration for full-scale wastewater treatment plant predesign. Science of the Total Environment, 785, 147356.
Yaqub, M., Asif, H., Kim, S., & Lee, W. (2020). Modeling of a full-scale sewage treatment plant to predict the nutrient removal efficiency using a long short-term memory (LSTM) neural network. Journal of Water Process Engineering, 37, 101388.
Ye, Z., Yang, J., Zhong, N., Tu, X., Jia, J., & Wang, J. (2020). Tackling environmental challenges in pollution controls using artificial intelligence: a review. Science of the Total Environment, 699, 134279.
Zaghloul, M. S., & Achari, G. (2022). Application of machine learning techniques to model a full-scale wastewater treatment plant with biological nutrient removal. Journal of Environmental Chemical Engineering, 10(3), 107430.
Zhang, L., Cui, B., Yuan, B., Zhang, A., Feng, J., Zhang, J., Han, X., Pan, L., & Li, L. (2021). Denitrification mechanism and artificial neural networks modeling for low-pollution water purification using a denitrification biological filter process. Separation and Purification Technology, 257, 117918.
Zhao, L., Dai, T., Qiao, Z., Sun, P., Hao, J., & Yang, Y. (2020). Application of artificial intelligence to wastewater treatment: A bibliometric analysis and systematic review of technology, economy, management, and wastewater reuse. Process Safety and Environmental Protection, 133, 169-182. doi:10.1016/j.psep.2019.11.014
Zumft, W. G. (1997). Cell biology and molecular basis of denitrification. Microbiology and Molecular Biology Reviews, 61(4), 533-616.
台灣環保署網頁. (2022). 主管法規查詢系統：放流水標準. Retrieved from https://oaout.epa.gov.tw/law/