HAN Yi;ZHANG Qiyue;DUAN Lunbo;WANG Yankai;YU Yingli;FU Xuchen;RONG Jun;SUN Shichao;Inner Mongolia Electric Power Research Institute Branch,Inner Monglia Electric Power (Group)Co.,Ltd.;Key Laboratory of Energy Thermal Conversion and Control,Ministry of Education,Southeast University;

Abstract：

Coal power is an important supporting and regulating power supply in the clean and low-carbon transformation of power system. However, the technical output of thermal power units is hindered due to factors such as low-quality coal combustion, which seriously affects the safe operation of power grid and new energy power consumption. In view of this, a projection model building method based on the integration of mechanism simulation and data drive was presented in this paper. The sample space of boiler thermal system was constructed by mechanism simulation, and the unit output prediction was carried out based on mathematical projection. Considering the theoretical accuracy of mechanism simulation and the strong generalization of mathematical projection, the dynamic boundary output prediction of circulating fluidized bed units and the analysis of output blocking factors were realized under the condition of multi-factor coupling. The test results of 300 MWe demonstration unit shows that: considering the three influencing factors of auxiliary machine limitation, heating surface parameter overrun and key parameter overrun, the alarm values for exceeding the limit of operating parameters such as coal feeder, induced draft fan, slag cooler, bed temperature, screen wall temperature and fluidization wind speed are set respectively. The maximum deviation of mechanism simulation is 3 ℃,and the error rate is less than 2%. The BP neural network model with 7 inputs and 1 outputs is screened and designed based on the principal component analysis method. After network optimization by genetic algorithm, the network training and prediction are carried out by using 32 training samples and 5 test samples. The relative error of model training is within ±1.2%,the relative error of model prediction is within ±1.5%,ind icating that there is high accuracy, generalization ability, and worth reference.

Key Words： data drive;output prediction;circulating fluidized bed boiler;mathematical model;principal component analysis method;genetic algorithm

Abstract:

Keywords:

Foundation: 国家重点研发计划资助项目(2019YFE0100100-08)

Authors: HAN Yi;ZHANG Qiyue;DUAN Lunbo;WANG Yankai;YU Yingli;FU Xuchen;RONG Jun;SUN Shichao;Inner Mongolia Electric Power Research Institute Branch,Inner Monglia Electric Power (Group)Co.,Ltd.;Key Laboratory of Energy Thermal Conversion and Control,Ministry of Education,Southeast University;

DOI: 10.13226/j.issn.1006-6772.21061701

References：

• [1] 高正平，涂安琪，李天新，等.面向零碳电力的氨燃烧技术研究进展[J].洁净煤技术，2022,28(3):173-184.GAO Zhengping,TU Anqi,LI Tianxin,et al.Recent advances on ammonia combustion technology for zero-carbon power[J].Clean Coal Technology,2022,28(3):173-184.
• [2] 雒青，王伟，范庆伟，等.火电机组快速变负荷的锅炉动态响应分析[J].热能动力工程，2019,34(6):78-84.LUO Qing,WANG Wei,FAN Qingwei,et al.Study on the dynamic characteristics of boiler during fast load regulation[J].Journal of Engineering for Thermal Energy and Power,2019,34(6):78-84.
• [3] 张奇月.蒙西电网火电机组变煤质最大出力预测研究[D].南京：东南大学，2020:17-18.
• [4] 刘大同，郭凯，王本宽，等.数字孪生技术综述与展望[J].仪器仪表学报，2018,39(11):1-10.LIU Datong,GUO Kai,WANG Benkuan,et al.Summary and perspective survey on digital twin technology[J].Chinese Journal of Scientific Instrument,2018,39(11):1-10.
• [5] 付忠广，刘炳含，王鹏凯，等.基于数据挖掘的燃煤机组能耗敏感性分析[J].热力发电，2018,47(9):15-21.FU Zhongguang,LIU Binghan,WANG Pengkai,et al.Sensitivity analysis of energy consumption of coal-fired units based on data mining[J].Thermal Power Generation,2018,47(9):15-21.
• [6] 徐游波.火电机组动态边界特性的研究[D].南京：东南大学，2015:17-18.
• [7] 于浩洋，高明明，张缦，等.循环流化床机组深度调峰性能分析与评价[J].热力发电，2020,49(5):65-72.YU Haoyang,GAO Mingming,ZHANG Man,et al.Performance analysis and evaluation of deep peak-regulating for circulating fluidized bed units[J].Thermal Power Generation,2020,49(5):65-72.
• [8] 林正根，姚杰，庄柯，等.基于PCA-LMBP神经网络模型的SCR脱硝催化剂工艺特性预测[J].热力发电，2019,48(11):108-114.LIN Zhenggen,YAO Jie,ZHUANG Ke,et al.Process characteristics forecasting for SCR denitration catalyst based on PCA-LMBP neural network model[J].Thermal Power Generation,2019,48(11):108-114.
• [9] 孙栓柱，江叶峰，代家元，等.燃煤机组网源互动可调出力在线监测模型研究与应用[J].中国电力，2016,49(12):81-85.SUN Shuanzhu,JIANG Yefeng,DAI Jianyuan,et al.Research and application of online monitoring model of coal-fired units in the coordinated interaction of large power grid[J].Electric Power,2016,49(12):81-85.
• [10] 袁东辉，孙世超，郑秀平，等.CFB锅炉可调效率的旋风分离器性能数值模拟研究[J].洁净煤技术，2020,26(6):159-167.YUAN Donghui,SUN Shichao,ZHENG Xiuping,et al.Numerical simulation of the performance of cyclone separator with adjustable efficiency in CFB boiler[J].Clean Coal Technology,2020,26(6):159-167.
• [11] 孙世超，周镇港，袁东辉，等.风幕代替中心筒的旋风分离器性能研究[J].洁净煤技术，2022,28(4):183-190.SUN Shichao,ZHOU Zhengang,YUAN Donghui,et al.Performance of cyclone separator replacing vortex finder with air curtain[J].Clean Coal Technology,2022,28(4):183-190.
• [12] 钟崴，任庆，尹冬年，等.基于机理仿真拓展的电厂热力系统数据代理映射模型构建方法[J].中国电机工程学报，2021,41(2):416-423.ZHONG Wei,REN Qing,YING Dongnian,et al.A data surrogate mapping model construction method for power plant thermal system based on mechanism simulation extension[J].Proceedings of the CSEE,2021,41(2):416-423.
• [13] 荣俊，蔡斌，韩义，等.330 MW循环流化床机组锅炉技术出力受限因素分析及处理[J].内蒙古电力技术，2020 38(4):47-52.RONG Jun,CAI Bin,HAN Yi,et al.Analysis and treatment of limited output factors for 330 MW circulating fluidized bed boiler[J].Inner Mongolia Electric Power,2020,38(4):47-52.
• [14] 李明超.电厂热力系统稳态建模仿真软件开发及应用[D].杭州：浙江大学，2020.
• [15] 潘庆先，董红斌，韩启龙，等.一种基于BP神经网络的属性重要性计算方法[J].中国科学技术大学学报，2017,47(1):18-25.PAN Qingxian,DONG Hongbin,HAN Qilong,et al.A method for attribute importance calculation based on BP neural network[J].Journal of University of Science and Technology of China,2017,47(1):18-25.
• [16] 陈彬，王小东，王戎骁，等.融合机理与数据的灰箱系统建模方法研究[J].系统仿真学报，2019,31(12):2575-2583.CHEN Bin,WANG Xiaodong,WANG Rongxiao,et al.Research on fusion mechanism and data modeling method of grey box system[J].Journal of System Simulation,2019,31(12):2575-2583.
• [17] 陈永辉，李志强，蒋志庆，等.基于电锅炉的火电机组灵活性改造技术研究[J].热能动力工程，2020,35(1):261-266.CHEN Yonghui,LI Zhiqiang,JIANG Zhiqing,et al.Research on flexible transformation tchnology of thermal power unit based on electric boiler[J].Journal of Engineering for Thermal Energy and Power,2020,35(1):261-266.
• [18] 阎永亮，查健锐，段伦博，等.应用不同机器学习算法预测化学链中氧载体性能[J].洁净煤技术，2021,27(1):220-224.YAN Yongliang,CHA Jianrui,DUAN Lunbo,et al.Applying different machine learning algorithms to predict the performance of oxygen carriers in chemical-looping[J].Clean Coal Technology,2021,27(1):220-224.
• [19] 韩义，孙奇月，王研凯，等.基于BP神经网络的300 MW循环流化床机组出力预测[J].华电技术，2020,42(12):1-6.HAN Yi,ZHANG Qiyue,WANG Yankai,et al.Output prediction of 300 MW circulating fluidized bed unit based on BP neural network[J].Huadian Technology,2020,42(12):1-6.
• [20] 刘继伟.基于大数据的多尺度状态监测方法及应用[D].北京：华北电力大学，2013:17-18.
• [21] 刘龙龙，李雪峰，陈云，等.优化尾部受热面降低600 MW亚临界锅炉排烟温度的热力计算研究[J].锅炉技术，2017,48(1):1-5.LIU Longlong,LI Xuefeng,CHEN Yun,et al.Thermodynamic calculation for the tail heating surface optimization used to reduce the exhaust gas temperature of a 600 MW sub-critical boiler[J].Boiler Technology,2017,48(1):1-5.
• [22] 沈沉，赵文灿，施金海，等.多隐层BP神经网络在模式预报中的简化应用[J].气象与环境科学，2019,42(4):127-132.SHEN Chen,ZHAO Wencan,SHI Jinhai,et al.Simplified application of multi-hidden layer BP neural network in model forecasting[J].Meteorological and Environmental Sciences,2019,42(4):127-132.