[ 1 ] United Nations Economic Commission for Europe (UNECE). Life cycle assessment of electricity generation options [Internet]. Geneva: UNECE; [cited 2022 Mar 10]. Available from: https://unece.‍org/sed/documents/2021/10/reports/life-cycle-assessment-electricity-generation-options. link1

[ 2 ] [Current situation and prospects of industrial furnaces in China] [Internet]. [cited 2022 Mar 21]. Available from: https://www.‍renrendoc.‍com/paper/176144656.html?aggId=fNCMGs9lI3GN@pygDVr6a1U. Chinese. link1

[ 3 ] [Industrial enterprises are major energy consumers, and the scale prediction of China’s industrial energy-saving market] [Internet]. [cited 2022 Mar 15]. Available from: https://www.‍chinairn.‍com/news/20220107/181056197.‍shtml. Chinese. link1

[ 4 ] Srdic S, Nedeljkovic M, Vukosavic SN, Radakovic Z. Fast and robust predictive current controller for flicker reduction in DC arc furnaces. IEEE Trans Ind Electron 2016;63(7):4628‒40. link1

[ 5 ] Ghiormez L, Panoiu M, Panoiu C, Muscalagiu I. Proportional regulator-based approach for a three-phase electric arc furnace. IOP Conf Ser: Mater Sci Eng 2019;477:012016. link1

[ 6 ] Biegler LT. New directions for nonlinear process optimization. Curr Opin Chem Eng 2018;21:32‒40. link1

[ 7 ] Khong SZ, Nešic´ D, Tan Y, Manzie C. Unified frameworks for sampled-data extremum seeking control: global optimisation and multi-unit systems. Automatica 2013;49(9):2720‒33. link1

[ 8 ] Zhou SH, Du WL. Modeling of ethylene cracking furnace yields based on transfer learning. CIESC J 2014;65(12):4921‒8. Chinese.

[ 9 ] Jiang CH, Yin JP, Gui WH, Yand CH. Prediction for blast furnace silicon content in hot metal based on composite differential evolution algorithm and extreme learning machine. Control Theory Appl 2016;33(8):1089‒95. Chinese.

[10] Chai TY, Qin SJ, Wang H. Optimal operational control for complex industrial processes. Annu Rev Contr 2014;38(1):81‒92. link1

[11] Chai TY, Ding JL, Wu F. Hybrid intelligent control for optimal operation of shaft furnace roasting process. Control Eng Pract 2011;19(3):264‒75. link1

[12] Zhou P, Chai TY, Sun J. Intelligence-based supervisory control for optimal operation of a DCS-controlled grinding system. IEEE Trans Control Syst Technol 2013;21(1):162‒75. link1

[13] Chen TWC, Vassiliadis VS. Inequality path constraints in optimal control: a finite iteration e-convergent scheme based on pointwise discretization. J Process Contr 2005;15(3):353‒62. link1

[14] Fu J, Faust JMM, Chachuat B, Mitsos A. Local optimization of dynamic programs with guaranteed satisfaction of path constraints. Automatica 2015;62:184‒92. link1

[15] Graciano JEA, Jäschke J, Le Roux GAC, Biegler LT. Integrating self-optimizing control and real-time optimization using zone control MPC. J Process Contr 2015;34:35‒48. link1

[16] Chai TY. Development directions of industrial artificial intelligence. Acta Autom Sinic 2020;46(10):2005‒12. Chinese.

[17] Gil Y, Greaves M, Hendler J, Hirsh H. Amplify scientific discovery with artificial intelligence. Science 2014;346(6206):171‒2. link1

[18] systemsCyber‒physical. Program solicitation NSF 08-611 [Internet]. Arlington: The National Science Foundation; [cited 2022 Mar 10]. Available from: https://www.nsf.gov/pubs/2008/nsf08611/nsf08611.pdf. link1

[19] Executive Office of the President of the United States. Artificial intelligence, automation, and the economy. Washington, DC: Executive Office of the President of the United States; 2016.

[20] Executive Office of the President of the United States, National Science and Technology Council, Committee on Technology. Preparing for the future of artificial intelligence. Washington, DC: The White House, Office of Science and Technology Policy; 2016.

[21] Carter WA, Kinnucan E, Elliot J, Crumpler W, Lloyd K. A national machine intelligence strategy for the United States. Washington, DC: Center for Strategic and International Studies; 2018.

[22] Jordan MI, Mitchell TM. Machine learning: trends, perspectives, and prospects. Science 2015;349(6245):255‒60. link1

[23] National Science and Technology Council, Networking and Information Technology Research and Development Subcommittee. The national artificial intelligence research and development strategic plan. Washington, DC: The White House, Office of Science and Technology Policy; 2016.

[24] The White House, Office of Science and Technology Policy. Summary of the 2018 White House summit on Artificial Intelligence for American Industry. Washington, DC: Executive Office of the President of the United States; 2018.

[25] National Science FoundationUS. Statement on Artificial Intelligence for American Industry [Internet]. Alexandria: US National Science Foundation; 2018 May 10 [cited 2022 Mar 10]. Available from: https://www.nsf.gov/news/news_summ.jsp?org=NSF&cntn_id=245418&preview=false. link1

[26] The State Council of the People’s Republic of China. [Development plan for the new generation of artificial intelligence] [Internet]. Beijing: The State Council of the People’s Republic of China; 2017 Jul 20 [cited 2022 Mar 10]. Available from: https://www.‍gov.‍cn/zhengce/content/2017-07/20/content_5211996.htm. Chinese. link1

[27] Kusiak A. Smart manufacturing must embrace big data. Nature 2017;544(7648):23‒5. link1

[28] Chai TY, Liu Q, Ding JL, Lu SW, Song YJ, Zhang YJ. Perspectives on industrialinternet-driven intelligent optimized manufacturing mode for process industries. Sci Sin Technol 2022;52(1):14‒25. Chinese. link1

[29] Chai TY, Zhang JW, Yang T. Demand forecasting of the fused magnesia smelting process with system identification and deep learning. IEEE Trans Industr Inform 2021;17(12):8387‒96. link1

[30] Wang WZ, Wu ZW, Chai TY. PID control with output compensation for the fused magnesia smelting process. Acta Autom Sinic 2018;44(7):1282‍‒‍92. Chinese.

[31] Wu ZW, Wu YJ, Chai TY, Sun J. Data-driven abnormal condition identification and self-healing control system for fused magnesium furnace. IEEE Trans Ind Electron 2015;62(3):1703‒15. link1

[32] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput 1997;9(8):1735‒80. link1