基于深度神经网络的SOFC电堆温度场建模

武鑫; 吴万哲; 白浩; 王祺; 熊星宇

doi:10.19912/j.0254-0096.tynxb.2022-0306

PDF(2090 KB)

太阳能学报 ›› 2023, Vol. 44 ›› Issue (7) : 55-60. DOI: 10.19912/j.0254-0096.tynxb.2022-0306

基于深度神经网络的SOFC电堆温度场建模

武鑫, 吴万哲, 白浩, 王祺, 熊星宇

作者信息 +

MODELLING OF SOFC STACK TEMPERATURE FIELD BASED ON DEEP NEURAL NETWORK

Wu Xin, Wu Wanzhe, Bai Hao, Wang Qi, Xiong Xingyu

Author information +

文章历史 +

摘要

基于石英光纤温度传感器和直角坐标机械手,设计并搭建一种SOFC电堆温度场测量系统。然后应用上述系统测量模拟电堆的阴极气道温度数据。根据采集的数据,基于深度神经网络方法建立模拟电堆温度场模型,并与基于支持向量机方法的电堆温度场模型进行对比。结果显示：深度神经网络电堆温度场模型的训练时间更短,预测精度更高,其平均绝对误差和均方根误差分别为支持向量机电堆温度场模型的45.2%和47.4%,更有利于该文中电堆温度场建模。

Abstract

Based on the quartz fiber temperature sensor and the Cartesian coordinate manipulator, this paper designs and builds the SOFC stack temperature field measurement system. Then, the temperature data of the cathode port in the emulation SOFC stack are measured through the built measurement system. Based on the collected data, the emulation stack temperature field model is established based on deep neural network method, and compared with the stack temperature field model based on support vector machines （SVM）. The results show that the stack temperature field model with deep neural network owns shorter training time and higher prediction accuracy. Its mean absolute prediction error and root mean square error are 45.2% and 47.4% respectively of the stack temperature field model of support vector machines, which is more convenient for the application of SOFC stack temperature field modelling in this paper.

导出引用

武鑫, 吴万哲, 白浩, 王祺, 熊星宇. 基于深度神经网络的SOFC电堆温度场建模[J]. 太阳能学报. 2023, 44(7): 55-60 https://doi.org/10.19912/j.0254-0096.tynxb.2022-0306

Wu Xin, Wu Wanzhe, Bai Hao, Wang Qi, Xiong Xingyu. MODELLING OF SOFC STACK TEMPERATURE FIELD BASED ON DEEP NEURAL NETWORK[J]. Acta Energiae Solaris Sinica. 2023, 44(7): 55-60 https://doi.org/10.19912/j.0254-0096.tynxb.2022-0306

中图分类号： TK91

参考文献

[1] 谭媛. 固体氧化物电解池的新型氧电极研究[D]. 武汉: 华中科技大学, 2016.
TAN Y.Study on new oxygen electrode for solid oxide electrolytic cell[D]. Wuhan: Huazhong University of Science and Technology, 2016.
[2] 彭苏萍, 韩敏芳, 杨翠柏, 等. 固体氧化物燃料电池[J]. 物理, 2004, 33(2): 90-94.
PENG S P, HAN M F, YANG C B, et al.Solid oxide fuel cell[J]. Physics, 2004, 33(2): 90-94.
[3] 宋世栋, 韩敏芳, 孙再洪. 固体氧化物燃料电池平板式电池堆的研究进展[J]. 科学通报, 2014, 59(15): 1405-1416.
SONG S D, HAN M F, SUN Z H.Research progress of solid oxide fuel cell flat panel stack[J]. Science bulletin, 2014, 59(15): 1405-1416.
[4] 吴小东. 面向应用的平板式交叉流SOFC电堆的二维温度分布估计研究[D]. 武汉: 华中科技大学, 2019.
WU X D.Study on two-dimensional temperature distribution estimation of application-oriented flat plate cross flow SOFC stack[D]. Wuhan: Huazhong University of Science and Technology, 2019.
[5] AGUIAR P, ADJIMAN C S, BRANDON N P.Anode-supported intermediate temperature direct internal reforming solid oxide fuel cell. I: model-based steady-state performance[J]. Journal of power sources, 2004, 138(1-2): 120-136.
[6] 李建林, 梁忠豪, 李雅欣, 等. 锂电池储能系统建模发展现状及其数据驱动建模初步探讨[J]. 油气与新能源, 2021, 33(4): 75-81.
LI J L, LIANG Z H, LI Y X, et al.Development status in modeling of the lithium battery energy storage system and preliminary exploration of its data-driven modeling[J]. Petroleum and new energy, 2021, 33(4): 75-81.
[7] RAZBANI O, ASSADI M.Artificial neural network model of a short stack solid oxide fuel cell based on experimental data[J]. Journal of power sources, 2014, 246(1): 581-586.
[8] SORRENTINO M, MARRA D, PIANESE C, et al.On the use of neural networks and statistical tools for nonlinear modeling and on-field diagnosis of solid oxide fuel cell stacks[J]. Energy procedia, 2014, 45(1): 298-307.
[9] ZHANG Y, ZHANG Y Y, HOU G L, et al.Research of BP network based solid oxide fuel cell stack temperature model[C]//Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, Dalian, China, 2013: 1037-1040.
[10] ZHAO W Q, JIANG J H, QIN H C, et al.Machine learning based soft sensor and long-term calibration scheme: a solid oxide fuel cell system case[J]. International journal of hydrogen energy, 2021, 46(33): 17322-17342.
[11] KANG Y W, LI J, CAO Y G, et al.Dynamic temperature modeling of an SOFC using least squares support vector machines[J]. Journal of power sources, 2008, 179(2): 683-692.
[12] 吴小娟, 朱新坚, 曹广益, 等. 基于神经网络的固体氧化物燃料电池电堆建模[J]. 系统仿真学报, 2008, 20(4): 1068-1071.
WU X J, ZHU X J, CAO G Y, et al.Modeling SOFC stack via neural networks[J]. Journal of system simulation, 2008, 20(4): 1068-1071.
[13] 唐江凌. 基于支持向量回归机的燃料电池研究[D]. 重庆: 重庆大学, 2012.
TANG J L.Research of fuel cell based on support vector regression[D]. Chongqing: Chongqing University, 2012.
[14] 戴文战, 娄海川, 杨爱萍. 非线性系统神经网络预测控制研究进展[J]. 控制理论与应用, 2009, 26(5): 521-530.
DAI W Z, LOU H C, YANG A P.An overview of neural network predictive control for nonlinear systems[J]. Control theory & applications, 2009, 26(5): 521-530.
[15] LEE C Y, HSIEH W J, WU G W.Embedded flexible micro-sensors in MEA for measuring temperature and humidity in a micro-fuel cell[J]. Journal of power sources, 2008, 181(2): 237-243.
[16] CELIK S, TIMURKUTLUK B, MAHMUT D.Measurement of the temperature distribution in a large solid oxide fuel cell short stack[J]. International journal of hydrogen energy, 2013, 38(25): 10534-10541.
[17] RAZBANI O, WÆRNHUS I, ASSADI M. Experimental investigation of temperature distribution over a planar solid oxide fuel cell[J]. Applied energy, 2013, 105(2): 155-160.
[18] POHJORANTA A, HALINEN M, PENNANEN J, et al.Solid oxide fuel cell stack temperature estimation with data-based modeling-designed experiments and parameter identification[J]. Journal of power sources, 2015, 277(1): 464-473.
[19] 刘亚丽. 面向热管理的SOFC电堆动态建模与温度观测器设计[D]. 武汉: 华中科技大学, 2016.
LIU Y L.Dynamic modeling and observer design of thermal management oriented SOFC stack[D]. Wuhan: Huazhong University of Science and Technology, 2016.
[20] 王道累, 李超, 李明山, 等. 基于深度卷积神经网络的光伏组件热斑检测[J]. 太阳能学报, 2022, 43(1): 412-417.
WANG D L, LI C, LI M S, et al.Solar photovoltaic modules hot spot detection based on deep convolutional neural networks[J]. Acta energiae solaris sinica, 2022, 43(1): 412-417.
[21] 郁永静, 李良县, 熊万能, 等. 基于BP神经网络的测风塔布置方案研究[J]. 太阳能学报, 2021, 42(6): 364-368.
YU Y J, LI L X, XIONG W N, et al.Research on layout scheme of met masts based on neural network algorithms[J]. Acta energiae solaris sinica, 2021, 42(6): 364-368.
[22] 贾嵘, 李云桥, 张惠智, 等. 基于改进BP神经网络的光伏阵列多传感器故障检测定位方法[J]. 太阳能学报, 2018, 39(1): 110-116.
JIA R, LI Y Q, ZHANG H Z, et al.Multi-sensor fault detection and positioning method of photovoltaic array based on improved BP neural network[J]. Acta energiae solaris sinica, 2018, 39(1): 110-116.
[23] 王嵘冰, 徐红艳, 李波, 等. BP神经网络隐含层节点数确定方法研究[J]. 计算机技术与发展, 2018, 28(4): 31-35.
WANG R B, XU H Y, LI B, et al.Research on method determining hidden layer nodes in BP neural network[J]. Computer technology and development, 2018, 28(4): 31-35.
[24] WU X J, YE Q W.Fault diagnosis and prognostic of solid oxide fuel cells[J]. Journal of power sources, 2016, 321(1): 47-56.
[25] SONG S H, XIONG X Y, WU X, et al.Modeling the SOFC by BP neural network algorithm[J]. International journal of hydrogen energy, 2021, 46(38): 20065-20077.