0
Research Papers

Development of a Fast Operation Algorithm of a Small-Scale Fuel Cell System With Solar Reforming

[+] Author and Article Information
Shin’ya Obara

Department of Mechanical Engineering, Tomakomai National College of Technology, 443 Nishikioka, Tomakomai, Hokkaido 0591275, Japanobara@indigo.plala.or.jp

Itaru Tanno

Department of Mechanical Engineering, Tomakomai National College of Technology, 443 Nishikioka, Tomakomai, Hokkaido 0591275, Japan

J. Dyn. Sys., Meas., Control 131(3), 031005 (Mar 19, 2009) (12 pages) doi:10.1115/1.3072148 History: Received September 13, 2007; Revised October 28, 2008; Published March 19, 2009

The small-scale bioethanol steam reforming system (FBSR), using sunlight applied to a heat source, is a very clean method, which can supply fuel to a fuel cell. However, it is difficult to analyze the operation planning of this system with high precision. If such an analytical algorithm is developed, the optimum operation of this system will be realized by the command of the control device. However, the difficulty of weather forecasts, such as solar radiation and outside-air-temperature, to date has made it difficult to achieve rapid and highly precise results and to analyze the system operation. In this paper, an algorithm, which analyzes the operation planning of the FBSR on arbitrary days, is developed using the neural network. The weather pattern for the past 1 year is input into this algorithm, and the operation planning of the FBSR, based on the same weather pattern, is given as a training signal. In this paper, the operation results of the system obtained via genetic algorithm (GA) were used as the training signal for the neural network. Operation planning (the amount of hydrogen production and the amount of exhaust heat storage) of the system on arbitrary days could be obtained rapidly by ensuring that input data (the weather and energy-demand patterns) are channeled into the learned neural network following this study. Moreover, in order to investigate the accuracy of the operational analysis via the proposed algorithm, it is compared with the analysis result of operation planning using the GA.

Copyright © 2009 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Fuel cell system with bioethanol solar reforming system (FBSR)

Grahic Jump Location
Figure 2

Fuel cell microgrid with FBSR

Grahic Jump Location
Figure 3

Procedure of the FBSR prediction algorithm

Grahic Jump Location
Figure 4

Layered neural network of the proposed system

Grahic Jump Location
Figure 5

Input and output of the neuron

Grahic Jump Location
Figure 6

Analysis flow of the NN learning process

Grahic Jump Location
Figure 7

Input data to the neural network program

Grahic Jump Location
Figure 9

Analysis flow of the training signal using GA

Grahic Jump Location
Figure 10

Operation plan of a representative day

Grahic Jump Location
Figure 11

Cell stack power output

Grahic Jump Location
Figure 12

Relation between load factor and power output of the cell stack

Grahic Jump Location
Figure 13

Meteorological pattern and energy-demand pattern in Sapporo in 2006: (a) outside-air-temperature, (b) amount of global-solar-radiation, (c) power demand of individual house, and (d) heat demand of individual house

Grahic Jump Location
Figure 14

Meteorological data in 2007: (a) outside-air-temperature in January and (b) outside-air-temperature in August

Grahic Jump Location
Figure 15

Analysis results of the operation plan using GA in 2006: (a) solar collector with condensing, and (b) rate of solar energy to energy demand

Grahic Jump Location
Figure 16

The meteorological data in representative day J1: (a) outside-air-temperature and (b) the amount of global-solar-radiation

Grahic Jump Location
Figure 17

Analysis result of the FBSR dynamic operation in representative day J1: (a) prediction 1 h after, (b) prediction 3 h after, and (c) prediction 6 h after

Grahic Jump Location
Figure 18

Prediction error in representative day J1: (a) prediction 1 h after, (b) prediction 3 h after, and (c) prediction 6 h after

Grahic Jump Location
Figure 19

The meteorological data in representative day J2: (a) outside-air-temperature and (b) the amount of global-solar-radiation

Grahic Jump Location
Figure 20

Analysis result of the FBSR dynamic operation in representative day J2: (a) prediction 3 h after and (b) prediction 6 h after

Grahic Jump Location
Figure 21

Prediction error in representative day J2: (a) prediction 3 h after and (b) prediction 6 h after

Grahic Jump Location
Figure 22

The prediction results of 6 h after in August 15, 2007 (representative day A1): (a) outside-air-temperature, (b) the amount of global-solar-radiation, (c) operation schedule, and (d) prediction error

Grahic Jump Location
Figure 23

The analysis results of 6 h after in August 25, 2007 (representative day A2): (a) outside-air-temperature, (b) the amount of global-solar-radiation, (c) operation schedule, and (d) prediction error

Grahic Jump Location
Figure 24

Relation between input data and analysis error. Each result was compared with the average value of the weather condition and the energy-demand characteristic in January, 2006.

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In