钟信,冯磊华,何金奇,杨锋

• 1:长沙理工大学能源与动力工程学院
• 2:陕西高业能源科技有限公司
• 3:华自科技股份有限公司

摘要(Abstract)：

新能源大量并网，超临界火电机组参与调峰容易造成中间点过热度较大波动，从而导致过热蒸汽超温等问题。为较好控制中间点过热度达到稳定，提出了一种基于双深度输入凸神经网络多模型（muti-DDICNN model）的中间点过热度预测方法，分别训练了不同预测步长下子模型，构建了中间点过热度状态预测网络（SPNN）和误差预测网络（EPNN）。利用此预测网络凸性质，设计了一种基于双深度输入凸神经网络多模型预测控制器（DDICNN-MPC），将控制问题转化为凸优化问题，求取控制矩阵对目标函数的雅可比矩阵，采用梯度下降法计算控制矩阵最优解。仿真结果表明，DDICNN-MPC能快速平稳地跟踪中间点过热度设定值，且稳态误差较小，具有较好的调节能力。

关键词(KeyWords)： 中间点过热度;输入凸神经网络;模型预测控制;梯度下降法;凸优化

Abstract:

Keywords:

基金项目(Foundation): 湖南省自然科学基金项目（2018JJ3552）~~

作者(Author): 钟信,冯磊华,何金奇,杨锋

DOI: 10.19666/j.rlfd.202305088

参考文献(References)：

• [1]马汀山,王妍,吕凯,等.“双碳”目标下火电机组耦合储能的灵活性改造技术研究进展[J].中国电机工程学报, 2022, 42(增刊1):136-148.MA Tingshan, WANG Yan, LYU Kai, et al. Research progress on flexibility transformation technology of coupled energy storage for thermal power units under the“dual-carbon” goal[J]. Proceedings of CSEE, 2022,42(Suppl.1):136-148.
• [2]牟春华,居文平,黄嘉驷,等.火电机组灵活性运行技术综述与展望[J].热力发电, 2018, 47(5):7-13.MU Chunhua, JU Wenping, HUANG Jiasi, et al. Review and prospect of technologies of enhancing the flexibility of thermal power units[J]. Thermal Power Generation,2018, 47(5):7-13.
• [3]林俐,田欣雨.基于火电机组分级深度调峰的电力系统经济调度及效益分析[J].电网技术, 2017, 41(7):2255-2263.LIN Li, TIAN Xinyu. Analysis of deep peak regulation and its benefit of thermal units in power system with large scale wind power integrated[J]. Power System Technology, 2017, 41(7):2255-2263.
• [4]张学延,何国安,曾立飞,等.“双碳”目标下火电机组故障及应对措施综述[J].热力发电, 2022, 51(12):10-17.ZHANG Xueyan, HE Guoan, ZENG Lifei, et al.Overview of thermal power units’ faults and the countermeasures under the target of “carbon neutrality and carbon peaking”[J]. Thermal Power Generation, 2022,51(12):10-17.
• [5]谷俊杰,王鹏,白智中,等.超超临界机组一次调频动作中间点过热度动态特性研究[J].中国电机工程学报,2017, 37(12):3525-35341.GU Junjie, WANG Peng, BAI Zhizhong, et al. Study on superheat degree dynamic response of ultra supercritical unit’s intermediate point caused by primary frequency regulation[J]. Proceedings of the CSEE, 2017, 37(12):3525-3534.
• [6] FAN H, SU Z G, WANG P H, et al. A dynamic nonlinear model for a wide-load range operation of ultrasupercritical once-through boiler-turbine units[J]. Energy,2021, 226:120425.
• [7] FAN H, ZHANG Y F, SU Z G, et al. A dynamic mathematical model of an ultra-supercritical coal fired once-through boiler-turbine unit[J]. Applied Energy,2017, 189:654-666.
• [8]刘萌,王印松,牟文彪,等.基于多策略分区勘探粒子群算法的主蒸汽温度优化控制[J].热力发电, 2021,50(7):23-30.LIU Meng, WANG Yinsong, MOU Wenbiao, et al.Optimization control of main steam temperature system based on multi strategy partition exploration particle swarm optimization algorithm[J]. Thermal Power Generation, 2021, 50(5):23-30.
• [9]李炳楠,朱峰,燕志伟,等.超临界火电机组协调系统建模及模型预测控制算法研究[J].热能动力工程,2020, 35(2):117-125.LI Bingnan, ZHU Feng, YAN Zhiwei, et al. Research on modeling and model predictive control algorithm for supercritical thermal power unit coordination system[J].Journal of Engineering for Thermal Energy and Power,2020, 35(2):117-125.
• [10]马增辉,徐慧仪.基于间隙度量的主汽温多模型Smith预估控制[J].热能动力工程, 2020, 35(9):148-153.MA Zenghui, XU Huiyi. Multiple model smith predictor control of main steam temperature based on gap metric[J].Journal of Engineering for Thermal Energy and Power,2020, 35(9):148-153.
• [11] WANG G L, YAN W W, CHEN S H, et al. Multi-model predictive control of ultra-supercritical coal-fired power unit[J]. Chinese Journal of Chemical Engineering, 2014,22:782-787.
• [12]郭嘉曦,刘长良,刘帅,等.基于数字孪生模型的主汽温预测控制策略[J/OL].华北电力大学学报:1-9.(2022-11-22)[2023-05-10] https://kns.cnki.net/kcms/detail/13.1212.tm.20221121.1021.002.html.GUO Jiaxi, LIU Changliang, LIU Shuai, et al. Main steam temperature predictive control strategy based on digital twin[J/OL]. Journal of North China Electric Power University:1-9.(2022-11-22)[2023-05-10] https://kns.cnki.net/kcms/detail/13.1212.tm.20221121.1021.002.html.
• [13] AMOS B, XU L, KOLTER J Z. Input convex neural networks[C]. Proceedings of the 34th International Conference on Machine Learning, 2017:146-155.
• [14]刘友波,王天翔,邱高,等.嵌入输入凸神经网络的静态电压稳定控制替代建模方法及其解析算法[J].电力自动化设备, 2023, 43(2):151-159.LIU Youbo, WANG Tianxiang, QIU Gao, et al. Surrogate modeling method and its analytical algorithm for static voltage stability control embedded with input convex neural network[J]. Electric Power Automation Equipment, 2023, 43(2):151-159.
• [15] YANG S, BEQUETTE B W. Optimization-based control using input convex neural networks[J]. Computers&Chemical Engineering, 2021, 144:107143-107151.
• [16] BüNNING F, SCHALBETTER A, ABOUDONIA A,et al. Input convex neural networks for building MPC,Proc[J]. Proceedings of Machine Learning Research,2021, 144:251-262.
• [17] ZHU H Y, TAN P, HE Z Q, et al. Nonlinear model predictive control of USC boiler-turbine power units in flexible operations via input convex neural network[J].Energy, 2022, 255:124486.
• [18] FANG C, GU Y H, ZHANG W Z, et al. Convex formulation of overparameterized deep neural networks[J]. IEEE Transactions on Information Theory,2022, 68(8), 5340-5352.
• [19] CHEN Y, SHI Y, ZHANG B. Data-driven optimal voltage regulation using input convex neural networks[J]. Electric Power System, 2020, 189:106741.
• [20]?AWRY?CZUK M. Input convex neural networks in nonlinear predictive control:a multi-model approach[J].Neurocomputing, 2022, 513:273-293.
• [21]谷俊杰,秦达飞,曹晓威,等.超临界锅炉中间点温度增益切换控制方法[J].中国电机工程学报, 2014,34(14):2274-2280.GU Junjie, QIN Dafei, CAO Xiaowei, et al. A control method based on gain-switching for intermediate point temperature of supercritical pressure boiler[J].Proceedings of the CSEE, 2014, 34(14):2274-2280.
• [22]陈伟华,姜兆迪.基于输入凸神经网络的IPT系统输出电压预测控制[J].控制工程, 2022, 29(11):2010-2017.CHEN Weihua, JIANG Zhaodi. Predictive control for output voltage of IPT system based on input convex neural network[J]. Control Engineering of China, 2022,29(11):2010-2017.
• [23] BOYD S, VANDENBERGHE L. Convex optimization[M]. Cambridge University Press, 2004:260.
• [24]郭磊.基于金属蓄热动态的直流炉控制模型研究[D].北京:华北电力大学, 2016:1.GUO Lei. Research on control model of once-through boilers based on dynamic heat storage[D]. Beijing:North China Electric Power University, 2016:1
• [25]曾德良,高珊,胡勇. MPS型中速磨煤机建模与仿真[J].动力工程学报, 2015, 35(1):55-61.ZENG Deliang, GAO Shan, HU Yong. Modeling and simulation of MPS medium speed coal mills[J]. Journal of Chinese Society of Power Engineering, 2015, 35(1):55-61.