On-line fault diagnostic system for proton exchange membrane fuel cells

Riascos, Luis Alberto Martínez; Simões, Marcelo Godoy; Miyagi, Paulo Eigi

doi:10.1016/j.jpowsour.2007.09.010

Cited by 61 publications

(30 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From a literature review, it is observed that most fuel cell PHM studies focus on the diagnostic stage, which can be loosely divided into two groups: model-based methods and data-driven techniques. Although several studies employ a model-based method for fuel cell diagnostics, i.e., developing a fuel cell model, and identifying fuel cell faults from residuals between model outputs and actual measurements [4][5][6][7][8], there are complexities in developing an accurate fuel cell model containing complete sets of failure modes. Data-driven approaches are more widely used for fuel cell diagnostics, that is, extracting the features by applying signal processing techniques to the sensor data, and discriminating fuel cell faults with extracted features [9][10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Application of the Sensor Selection Approach in Polymer Electrolyte Membrane Fuel Cell Prognostics and Health Management

2017

View full text Add to dashboard Cite

Abstract:In this paper, the sensor selection approach is investigated with the aim of using fewer sensors to provide reliable fuel cell diagnostic and prognostic results. The sensitivity of sensors is firstly calculated with a developed fuel cell model. With sensor sensitivities to different fuel cell failure modes, the available sensors can be ranked. A sensor selection algorithm is used in the analysis, which considers both sensor sensitivity to fuel cell performance and resistance to noise. The performance of the selected sensors in polymer electrolyte membrane (PEM) fuel cell prognostics is also evaluated with an adaptive neuro-fuzzy inference system (ANFIS), and results show that the fuel cell voltage can be predicted with good quality using the selected sensors. Furthermore, a fuel cell test is performed to investigate the effectiveness of selected sensors in fuel cell fault diagnosis. From the results, different fuel cell states can be distinguished with good quality using the selected sensors.

show abstract

Section: Introductionmentioning

confidence: 99%

Application of the Sensor Selection Approach in Polymer Electrolyte Membrane Fuel Cell Prognostics and Health Management

2017

View full text Add to dashboard Cite

show abstract

“…Several mathematical models of a PEM fuel cell were proposed, for example, in the literatures [1,2,[10][11][12][13][14][15]. The models of a PEM fuel cell generally consist of thermodynamic model, electrochemistry model, and fluid flow and heat transfer model.…”

Section: Electrochemical Reactionmentioning

confidence: 99%

“…A graphical-probabilistic structure was also proposed for construction a fault diagnosis in PEM fuel cells. Riascos et al [15] developed the on-line fault diagnosis by applying Bayesian networks. The diagnosis considered 4 types of faults: fault in the air blower, fault in the refrigeration system, growth of fuel crossover and internal loss current, and fault in hydrogen pressure.…”

Section: Introductionmentioning

confidence: 99%

200W PEM Fuel Cell Stack with Online Model-Based Monitoring System

Khanungkhid¹,

Piumsomboon²

2014

View full text Add to dashboard Cite

Abstract. Although various designs have been introduced to improve the performance of a Proton Exchange Membrane Fuel Cell (PEMFC) stack system, fault conditions, such as drying or flooding, may still occur due to the complexity of the process. The development of a system which can detect these fault conditions is a key to operate PEMFC stack system effectively. In this study, a monitoring system for a 200W commercial PEMFC stack system has been developed by constructing models for determining the flooding and drying conditions inside the cell. Since the membrane resistance and pressure drop across the stack are important parameters for determining either drying or flooding conditions taking place inside the fuel cell, the online model-based monitoring system is developed by adopting existing algorithms. A number of instruments are installed to measure relevant data. The data acquisition system and mathematical models have been programmed under LabVIEW TM environment. To indicate the abnormal conditions inside the fuel cell stack, the model prediction is compared with the experimental measured values and the size of the discrepancy will be an indicator.

show abstract

“…Sahin, Yavuz, Arnavut, and Uluyol (2007) develop a fault diagnosis system for airplane engines using Bayesian network and distributed particle swarm optimization, which is used for learning the structure of the model form a large dataset. Riascos, Simoes, and Miyagi (2008) present a fault diagnosis system to diagnose different types of faults during the operation of a proton exchange membrane fuel cell based on the on-line monitoring of variables easy to measure in the machine such as voltage, electric current and temperature. CruzRamírez, Acosta-Mesa, Carrillo-Calvet, Alonso Nava-Fernández, & Barrientos-Martínez, 2007 evaluate the effectiveness of seven Bayesian network classifiers as potential tools for the diagnosis of breast cancer using two real-world database and an average accuracy of 93.04% for the former and 83.31% for the latter are obtained.…”

Section: Introductionmentioning

confidence: 99%