An integrated data-driven surrogate model and thermofluid network-based model of a 620 MW e utility-scale boiler

被引:2
|
作者
Rawlins, Brad Travis [1 ]
Laubscher, Ryno [2 ]
Rousseau, Pieter [1 ]
机构
[1] Univ Cape Town, Dept Mech Engn, Appl Thermofluid Proc Modelling Res Unit, ZA-7700 Cape Town, South Africa
[2] Stellenbosch Univ, Dept Mech Engn, Stellenbosch, South Africa
关键词
Computational fluid dynamics; coupled simulation data-driven surrogate modelling; mixture density network; COAL; CFD; OPTIMIZATION; NOX;
D O I
10.1177/09576509221148231
中图分类号
O414.1 [热力学];
学科分类号
摘要
An integrated data-driven surrogate model and one-dimensional (1-D) process model of a 620 [MWe] utility scale boiler is presented. A robust and computationally inexpensive computational fluid dynamic (CFD) model of the utility boiler was utilized to generate the solution dataset for surrogate model training and testing. Both a standard multi-layer perceptron (MLP) and mixture density network (MDN) machine learning architectures are compared for use as a surrogate model to predict the furnace heat loads and the flue gas inlet conditions to the convective pass. A hyperparameter search was performed to find the best MLP and MDN architecture. The MDN was selected for surrogate model integration since it showed comparable accuracy and provides the ability to predict the associated uncertainties. Validation of the integrated model against plant data was performed for a wide range of loads, and critical results were predicted within 5-8% of the measured results. The validated model was subsequently used to investigate the effects of using a poor-quality fuel for the 100% maximum continuous rating load case. The uncertainties predicted by the surrogate model were propagated through the integrated model using the Monte Carlo technique, adding valuable insight into the operational limits of the power plant and the uncertainties associated with it.
引用
收藏
页码:1061 / 1079
页数:19
相关论文
共 50 条
  • [41] Optimizing the homogeneity and efficiency of a solid oxide electrolysis cell based on multiphysics simulation and data-driven surrogate model
    Chi, Yingtian
    Yokoo, Kentaro
    Nakajima, Hironori
    Ito, Kohei
    Lin, Jin
    Song, Yonghua
    JOURNAL OF POWER SOURCES, 2023, 562
  • [42] Block structure optimization in PEMFC flow channels using a data-driven surrogate model based on random forest
    Zheng, Jiayang
    Qin, Yanzhou
    Guo, Qiaoyu
    Dong, Zizhe
    Zhu, Changrong
    Wang, Yulin
    INTERNATIONAL JOURNAL OF GREEN ENERGY, 2023, 20 (08) : 816 - 822
  • [43] Online Data-Driven Integrated Prediction Model for Ship Motion Based on Data Augmentation and Filtering Decomposition and Time-Varying Neural Network
    Gao, Nan
    Chuang, Zhenju
    Hu, Ankang
    JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2024, 12 (12)
  • [44] Data-driven forecasting with model uncertainty of utility-scale air-cooled condenser performance using ensemble encoder-decoder mixture-density recurrent neural networks
    Raidoo, Renita
    Laubscher, Ryno
    ENERGY, 2022, 238
  • [45] Data-Driven Deepfake Forensics Model Based on Large-Scale Frequency and Noise Features
    Lan, Guipeng
    Xiao, Shuai
    Wen, Jiabao
    Chen, Desheng
    Zhu, Yong
    IEEE INTELLIGENT SYSTEMS, 2024, 39 (01) : 29 - 35
  • [46] DATA-DRIVEN SKILL-BASED PID CONTROL OF A PILOT-SCALE HELICOPTER MODEL
    Yamamoto, Toru
    Mori, Shinnosuke
    Sakaguchi, Akihiro
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2008, 4 (12): : 3349 - 3358
  • [47] Data driven surrogate model-based operation quality control strategy of an urban transmission network
    Duan X.
    Zou W.
    Li Y.
    He R.
    Long C.
    Su T.
    Liu Y.
    Dianli Xitong Baohu yu Kongzhi/Power System Protection and Control, 2021, 49 (02): : 65 - 73
  • [48] A Data-Driven Based Framework of Model Optimization and Neural Network Modeling for Microbial Fuel Cells
    Ma, Fengying
    Yin, Yankai
    Pang, Shaopeng
    Liu, Jiaxun
    Chen, Wei
    IEEE ACCESS, 2019, 7 : 162036 - 162049
  • [49] Hybrid Data-Driven Learning-Based Internet of Things Network Intrusion Detection Model
    Alimi, Oyeniyi Akeem
    2024 IEEE 5TH ANNUAL WORLD AI IOT CONGRESS, AIIOT 2024, 2024, : 0496 - 0501
  • [50] Data-Driven Risk Warning Model for Pension Financial System Based on Fuzzy Neural Network
    Zhang, Xiaoying
    Yan, Wei
    JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2025,