scholarly journals INTELLIGENT HEALTH STATUS DETECTION METHOD FOR LOCOMOTIVE FUEL CELL BASED ON DATA-DRIVEN TECHNIQUES

10.6036/10290 ◽  
2021 ◽  
Vol 96 (6) ◽  
pp. 633-639
Author(s):  
Shiyong Tao ◽  
Weirong Chen ◽  
Shuna Jiang ◽  
Xinyu Liu ◽  
Jiaxi Yu
Keyword(s):  
Neural Network ◽  
Health Status ◽  
Fuel Cell ◽  
Detection Method ◽  
Cell System ◽  
Data Driven ◽  
General Regression Neural Network ◽  
Fuel Cell System ◽  
Cell Systems ◽  
General Regression

Main drawbacks of fuel cell systems, namely, high cost, poor reliability, and short lifespan, limit the large-scale commercial application of fuel cell systems. The health status detection of fuel cell systems for locomotives is of great significance to the safe and stable operation of locomotives. To identify the failure modes of the fuel cell system accurately and quickly, this study proposed an intelligent health status detection method for locomotive fuel cells based on data-driven techniques. In this study, the actual test data of a 150-kW fuel cell system for locomotives was analyzed. The t-distributed stochastic neighbor embedding (t-SNE) algorithm was combined with the general regression neural network (GRNN) to intelligently detect the health status of the fuel cell system for locomotives. Specifically, t-SNE was used to process the high-dimensionality and strong coupling raw data of health status, enabling the dimensional reduction of the raw data to reflect essential features. Then, GRNN was used to identify the feature data to achieve the fast and accurate detection of the health status of the fuel cell system. Results show that the proposed method can effectively detect four health conditions, namely, normal state, high inlet coolant temperature, low air pressure, and low spray pump pressure, with a diagnostic accuracy of 98.75%. This study is applicable to the analysis of the actual measurement data of high-power level fuel cell systems and provides a reference for the health status detection of fuel cell systems for locomotives. Keywords: fuel cell system for locomotive; data-driven; general regression neural network; t-distributed stochastic neighbor embedding; health status detection

Development of a Performance Rating Standard for Residential Fuel Cell Systems

2006 ◽  
Author(s):  
Michael W. Ellis ◽  
Mark W. Davis ◽  
A. Hunter Fanney ◽  
Brian P. Dougherty ◽  
Ian Doebber
Keyword(s):  
Fuel Cell ◽  
Performance Standards ◽  
Cell System ◽  
Fuel Cell System ◽  
Experimental Procedure ◽  
Cell Systems ◽  
Load Following ◽  
System A ◽  
Experimental Apparatus ◽  
Using Data

Fuel cell systems for residential applications are an emerging technology for which specific consumer-oriented performance standards are not well defined. This paper presents a proposed experimental procedure and rating methodology for evaluating residential fuel cell systems. In the proposed procedure, residential applications are classified as grid independent load following; grid connected constant power; grid connected thermal load following; and grid connected water heating. An experimental apparatus and procedures for steady state and simulated use tests are described for each type of system. A rating methodology is presented that uses data from these experiments in conjunction with standard residential load profiles to quantify the net effect of a fuel cell system on residential utility use. The experiments and rating procedure are illustrated using data obtained from a currently available grid connected thermally load following system.

Implementation of a Fuel Cell System Model Into Building Energy Simulation Software IDA-ICE

2006 ◽  
Vol 4 (4) ◽  
pp. 511-515 ◽  
Author(s):  
Teemu Vesanen ◽  
Krzysztof Klobut ◽  
Jari Shemeikka
Keyword(s):  
Fuel Cell ◽  
Cell Model ◽  
Building Energy ◽  
Cell System ◽  
System Model ◽  
System Level ◽  
Fuel Cell System ◽  
Cell Systems ◽  
Level Model ◽  
System Level Model

Due to constantly increasing electricity consumption, networks are becoming overloaded and unstable. Decentralization of power generation using small-scale local cogeneration plants becomes an interesting option to improve economy and energy reliability of buildings in terms of both electricity and heat. It is expected that stationary applications in buildings will be one of the most important fields for fuel cell systems. In northern countries, like Finland, efficient utilization of heat from fuel cells is feasible. Even though the development of some fuel cell systems has already progressed to a field trial stage, relatively little is known about the interaction of fuel cells with building energy systems during a dynamic operation. This issue could be addressed using simulation techniques, but there has been a lack of adequate simulation models. International cooperation under IEA/ECBCS/Annex 42 aims at filling this gap, and the study presented in this paper is part of this effort. Our objective was to provide the means for studying the interaction between a building and a fuel cell system by incorporating a realistic fuel cell model into a building energy simulation. A two-part model for a solid-oxide fuel cell system has been developed. One part is a simplified model of the fuel cell itself. The other part is a system level model, in which a control volume boundary is assumed around a fuel cell power module and the interior of it is regarded as a “black box.” The system level model has been developed based on a specification defined within Annex 42. The cell model (programed in a spreadsheet) provides a link between inputs and outputs of the black box in the system model. This approach allows easy modifications whenever needed. The system level model has been incorporated into the building simulation tool IDA-ICE (Indoor Climate and Energy) using the neutral model format language. The first phase of model implementation has been completed. In the next phase, model validation will continue. The final goal is to create a comprehensive but flexible model, which could serve as a reliable tool to simulate the operation of different fuel cell systems in different buildings.

Partial Validation of a Proposed Rating Methodology for Residential Fuel Cell Systems

2006 ◽  
Author(s):  
Mark W. Davis ◽  
Michael W. Ellis ◽  
Brian P. Dougherty ◽  
A. Hunter Fanney
Keyword(s):  
Fuel Cell ◽  
Thermal Load ◽  
Electrical Power ◽  
Cell System ◽  
Hot Water ◽  
Electrical Load ◽  
Climate Data ◽  
Fuel Cell System ◽  
Cell Systems ◽  
Load Following

The National Institute of Standards and Technology (NIST), in conjunction with Virginia Tech, has developed a rating methodology for residential-scale stationary fuel cell systems. The methodology predicts the cumulative electrical production, thermal energy delivery, and fuel consumption on an annual basis. The annual performance is estimated by representing the entire year of climate and load data into representative winter, spring/fall, and summer days for six different U.S. climatic zones. It prescribes a minimal number of steady state and simulated use tests, which provide the necessary performance data for the calculation procedure that predicts the annual performance. The procedure accounts for the changes in performance resulting from changes in ambient temperature, electrical load, and, if the unit provides thermal as well as electrical power, thermal load. The rating methodology addresses four different types of fuel cell systems: grid-independent electrical load following, grid-connected constant power, grid-connected thermal load following, and grid-connected water heating. This paper will describe a partial validation of the rating methodology for a grid-connected thermal load following fuel cell system. The rating methodology was validated using measured data from tests that subjected the fuel cell system to domestic hot water and space heating thermal loads for each of the three representative days. The simplification of a full year’s load and climate data into three representative days was then validated by comparing the rating methodology predictions with the prediction of each hour over the full year in each of the six cities.

Residential Experience with Proton Exchange Membrane Fuel Cell Systems for Combined Heat and Power

2005 ◽  
Vol 2 (4) ◽  
pp. 263-267 ◽  
Author(s):  
Darrell D. Massie ◽  
Daisie D. Boettner ◽  
Cheryl A. Massie
Keyword(s):  
Fuel Cell ◽  
Natural Gas ◽  
Heat Recovery ◽  
Proton Exchange Membrane ◽  
Waste Heat ◽  
Cell System ◽  
Proton Exchange ◽  
Fuel Cell System ◽  
Cell Systems ◽  
Exchange Membrane

As part of a one-year Department of Defense demonstration project, proton exchange membrane fuel cell systems have been installed at three residences to provide electrical power and waste heat for domestic hot water and space heating. The 5kW capacity fuel cells operate on reformed natural gas. These systems operate at preset levels providing power to the residence and to the utility grid. During grid outages, the residential power source is disconnected from the grid and the fuel cell system operates in standby mode to provide power to critical loads in the residence. This paper describes lessons learned from installation and operation of these fuel cell systems in existing residences. Issues associated with installation of a fuel cell system for combined heat and power focus primarily on fuel cell siting, plumbing external to the fuel cell unit required to support heat recovery, and line connections between the fuel cell unit and the home interior for natural gas, water, electricity, and communications. Operational considerations of the fuel cell system are linked to heat recovery system design and conditions required for adequate flow of natural gas, air, water, and system communications. Based on actual experience with these systems in a residential setting, proper system design, component installation, and sustainment of required flows are essential for the fuel cell system to provide reliable power and waste heat.

A Comparison Between Life Cycle Assessment of an MCFC System, An LFG-MCFC System, and Traditional Energy Conversion Systems

2004 ◽  
Author(s):  
U. Desideri ◽  
P. Lunghi ◽  
F. Zepparelli
Keyword(s):  
Life Cycle Assessment ◽  
Fuel Cell ◽  
Environmental Impact ◽  
Energy Conversion ◽  
Landfill Gas ◽  
Electric Energy ◽  
Cell System ◽  
Fuel Cell System ◽  
Cell Systems ◽  
Energy Conversion Systems

The present work aims at evaluating the environmental impact caused by fuel cell systems in the production of electric energy. The very low pollutant emission levels in fuel cells makes them an attractive alternative in ultra clean energy conversion systems. Actually, to truly understand the environmental impact related to fuel cells, it is necessary to study their “cradle-to-grave” life, from the construction phase, during the conversion of primary fuel into hydrogen, to its disposal. The tool used in this analysis is the Life Cycle Assessment approach; in particular the environmental impact of a fuel cell system has been simulated through the software SimaPro 5.0. Thanks to this approach, once the critical process regarding the production of energy by fuel cell system, (i.e. the production of hydrogen by natural gas steam reforming), has been determined, an analysis of the use of landfill gas as a renewable source to produce hydrogen was done. Finally, the production of electric energy by fuel cell systems was compared to that by some conventional energy conversion systems. A second comparison was done between the Molten Carbonate Fuel Cell (MCFC) fuelled by landfill gas and natural gas.

Experimental Investigation of a Novel Combined Rapid Compression-Ignition Combustion and Solid Oxide Fuel Cell System Format Operating on Diesel

2021 ◽  
Author(s):  
Andrew Ahn ◽  
Thomas Stone Welles ◽  
Benjamin Akih-Kumgeh ◽  
Ryan J. Milcarek
Keyword(s):  
Fuel Cell ◽  
Internal Combustion Engines ◽  
Cell System ◽  
Solid Oxide ◽  
Compression Ignition ◽  
Oxide Fuel ◽  
Fuel Cell System ◽  
Cell Systems ◽  
Fuel Reformation ◽  
Rapid Compression

Abstract Climate change concerns have forced the automotive industry to develop more efficient powertrain technologies, including the potential for fuel cell systems. Solid oxide fuel cells (SOFCs) demonstrate exceptional fuel flexibility and can operate on conventional, widely available hydrocarbon fuels with limited requirements for fuel reformation. Current hybrid powertrains combining fuel cell systems with internal combustion engines (ICEs) fail to mitigate the disadvantages of requiring fuel reformation by placing the engine downstream of the fuel cell system. This work, thus investigates the upstream placement of the engine, eliminating the need for fuel processing catalysts and the heating of complex fuel reformers. The ICE burns a fuel-rich mixture through rapid compression ignition, performing partial oxidation fuel reformation. To test the feasibility of a fuel cell system operating on such ICE exhaust, chemical kinetic model simulations were performed, creating model exhaust containing ∼43.0% syngas. A micro-tubular SOFC (μT-SOFC) was tested for power output with this exhaust, and generated ∼730 mW/cm2 (∼86% of its maximum output obtained with pure hydrogen fuel). Combustion testing was subsequently performed in a test chamber, and despite insufficient equipment limiting the maximum pressure of the combustion chamber, began to validate the model. The exhaust from these tests contained all of the predicted chemical species and, on average, ∼21.8% syngas, but would have resembled the model more closely given higher pressures. This work examines the viability of a novel combined ICE and fuel cell hybrid system, displaying potential for a more cost-effective/efficient solution than current fuel cell systems.

Gain-Scheduled Control for an Automotive Traction PEM Fuel Cell System

2007 ◽  
Author(s):  
Ahmed A. Al-Durra ◽  
Stephen Yurkovich ◽  
Yann Guezennec
Keyword(s):  
Fuel Cell ◽  
Nonlinear Model ◽  
Internal Combustion Engines ◽  
Air Flow ◽  
Transient Behavior ◽  
Cell System ◽  
Fuel Cell System ◽  
Cell Systems ◽  
Hydrogen Flow ◽  
Gain Scheduled

To be practical in automotive traction applications, fuel cell systems must provide power output levels of performance that rival that of typical internal combustion engines. In so doing, transient behavior is one of the keys for success of fuel cell systems in vehicles. From a model-based control perspective, regulation of the fuel cell system through transients is critical, where the response of a fuel cell system depends on the air and hydrogen (flow and pressure regulation) and heat and water management. The focus of this paper is on the air/fuel supply subsystem in tracking an optimum variable pressurization and air flow for maximum system efficiency during load transients. The control-oriented model developed for this study considers electrochemistry, thermodynamics, and fluid flow principles for a 13-state, nonlinear model of a pressurized fuel cell system. For control purposes, a model reduction is performed by converting some of the model dynamics to simple algebraic relationships. A single reference input, the power demanded by the user, is utilized to produce a corresponding reference air flow and back-pressure valve opening, after passing through a static calculation and a tabulated map. Because of the complexity of the full nonlinear model (used in simulation as the truth model), where several maps are used rather than functional forms, two different control techniques are examined separately, each using a feedforward component. The first technique uses an observer-based linear optimum control which combines a feed-forward approach based on the steady state plant inverse response, coupled to a multi-variable LQR feedback control. An extension of that approach, for control in the full nonlinear range of operation, leads to the second technique, nonlinear gain-scheduled control.

Sign in / Sign up

Export Citation Format

Share Document