scholarly journals Data-driven flooding fault diagnosis method for proton-exchange membrane fuel cells using deep learning technologies

2021 ◽  
pp. 115004
Author(s):  
Bin Zuo ◽  
Zehui Zhang ◽  
Junsheng Cheng ◽  
Weiwei Huo ◽  
Zhixian Zhong ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fuel Cells ◽  
Fault Diagnosis ◽  
Proton Exchange Membrane ◽  
Learning Technologies ◽  
Proton Exchange ◽  
Data Driven ◽  
Diagnosis Method ◽  
Exchange Membrane

scholarly journals Symbolic deep learning based prognostics for dynamic operating proton exchange membrane fuel cells

2022 ◽  
Vol 305 ◽  
pp. 117918
Author(s):  
Chu Wang ◽  
Zhongliang Li ◽  
Rachid Outbib ◽  
Manfeng Dou ◽  
Dongdong Zhao
Keyword(s):  
Deep Learning ◽  
Fuel Cells ◽  
Proton Exchange Membrane ◽  
Proton Exchange ◽  
Dynamic Operating ◽  
Exchange Membrane

scholarly journals Model-Based Data Driven Approach for Fault Identification in Proton Exchange Membrane Fuel Cell

Energies ◽  
2020 ◽  
Vol 13 (12) ◽  
pp. 3144
Author(s):  
K. V. S. Bharath ◽  
Frede Blaabjerg ◽  
Ahteshamul Haque ◽  
Mohammed Ali Khan
Keyword(s):  
Fuel Cells ◽  
Proton Exchange Membrane ◽  
Proton Exchange ◽  
Data Driven ◽  
Fault Classification ◽  
Fault Identification ◽  
Support Vector ◽  
Model Based ◽  
Data Limitations ◽  
Exchange Membrane

This paper develops a model-based data driven algorithm for fault classification in proton exchange membrane fuel cells (PEMFCs). The proposed approach overcomes the drawbacks of voltage and current density assumptions in conventional model-based fault identification methods and data limitations in existing data driven approaches. This is achieved by developing a 3D model of fuel cells (FC) based on semi empirical model, analytical representation of electrochemical model, thermal model, and impedance model. The developed model is simulated for membrane drying and flooding faults in PEMFC and their effects are identified for the action of varying temperature, pressure, and relative humidity. The ohmic, concentration, activation and cell voltage losses for the simulated faults are observed and processed with wavelet transforms for feature extraction. Furthermore, the support vector machine learning algorithm is adapted to develop the proposed fault classification approach. The performance of the developed classifier is tested for an unknown data and calibrated through classification accuracy. The results showed 95.5% training efficiency and 98.6% testing efficiency.

scholarly journals Robust fault diagnosis of proton exchange membrane fuel cells using a Takagi-Sugeno interval observer approach

2016 ◽  
Vol 41 (4) ◽  
pp. 2875-2886 ◽  
Author(s):  
Damiano Rotondo ◽  
Rosa M. Fernandez-Canti ◽  
Sebastian Tornil-Sin ◽  
Joaquim Blesa ◽  
Vicenç Puig
Keyword(s):  
Fuel Cells ◽  
Fault Diagnosis ◽  
Proton Exchange Membrane ◽  
Proton Exchange ◽  
Interval Observer ◽  
Takagi Sugeno ◽  
Exchange Membrane

Control of proton exchange membrane fuel cells using data driven state space models

2010 ◽  
Vol 88 (7) ◽  
pp. 861-874 ◽  
Author(s):  
R.N. Methekar ◽  
S.C. Patwardhan ◽  
R. Rengaswamy ◽  
R.D. Gudi ◽  
V. Prasad
Keyword(s):  
Fuel Cells ◽  
State Space ◽  
Proton Exchange Membrane ◽  
Proton Exchange ◽  
State Space Models ◽  
Data Driven ◽  
Using Data ◽  
Exchange Membrane

scholarly journals A Multi-Stage Fault Diagnosis Method for Proton Exchange Membrane Fuel Cell Based on Support Vector Machine with Binary Tree

Energies ◽  
2021 ◽  
Vol 14 (20) ◽  
pp. 6526
Author(s):  
Jiaping Xie ◽  
Chao Wang ◽  
Wei Zhu ◽  
Hao Yuan
Keyword(s):  
Fault Diagnosis ◽  
Binary Tree ◽  
Proton Exchange Membrane ◽  
Pem Fuel Cells ◽  
Proton Exchange ◽  
Support Vector ◽  
Multi Stage ◽  
Fault Features ◽  
Diagnosis Method ◽  
Exchange Membrane

The reliability and durability of the proton exchange membrane (PEM) fuel cells are vital factors restricting their applications. Therefore, establishing an online fault diagnosis system is of great significance. In this paper, a multi-stage fault diagnosis method for the PEM fuel cell is proposed. First, the tests of electrochemical impedance spectroscopy under various fault conditions are conducted. Specifically, prone recoverable faults, such as flooding, membrane drying, and air starvation, are included, and different fault degrees from minor, moderate to severe, are covered. Based on this, an equivalent circuit model (ECM) is selected to fit impedance spectroscopy by the hybrid genetic particle swarm optimization algorithm, and then fault features are determined by the analysis of each model parameter under different fault conditions. Furthermore, a multi-stage fault diagnosis model is constructed with the support vector machine with the binary tree, in which fault features obtained from the ECM are used as the characteristic inputs to realize the fault classification (including fault type and fault degree) online. The results show that the accuracy of the basic fault test and subdivided fault test can reach 100% and 98.3%, respectively, which indicates that the proposed diagnosis method can effectively identify flooding, drying, and air starvation of PEM fuel cells.

scholarly journals Data-Driven Control for Proton Exchange Membrane Fuel Cells: Method and Application

2021 ◽  
Vol 9 ◽  
Author(s):  
Jiawen Li ◽  
Kedong Zhu ◽  
Tao Yu
Keyword(s):  
Fuel Cells ◽  
Pid Controller ◽  
Proton Exchange Membrane ◽  
Control Method ◽  
Proton Exchange ◽  
Data Driven ◽  
Air Supply ◽  
Optimal Control Method ◽  
Policy Gradient ◽  
Exchange Membrane

A data-driven optimal control method for an air supply system in proton exchange membrane fuel cells (PEMFCs) is proposed with the aim of improving the PEMFC net output power and operational efficiency. Moreover, a marginal utility-based double-delay deep deterministic policy gradient (MU-4DPG) algorithm is proposed as a an offline tuner for the PID controller. The coefficients of the PID controller are rectified and optimized during training in order to enhance the controller’s performance. The design of the algorithm draws on the concept of marginal effects in Economics, in that the algorithm continuously switches between different forms of exploration noise during training so as to increase the diversity of samples, improve exploration efficiency and avoid Q-value overfitting, and ultimately improve the robustness of the algorithm. As detailed below, the effectiveness of the control method has been experimentally demonstrated.

Sign in / Sign up

Export Citation Format

Share Document