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

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.

Download Full-text

Data-driven coordinated control method for multiple systems in proton exchange membrane fuel cells using deep reinforcement learning

Energy Reports ◽

10.1016/j.egyr.2021.11.250 ◽

2022 ◽

Vol 8 ◽

pp. 290-311

Author(s):

Jiawen Li ◽

Tiantian Qian ◽

Tao Yu

Keyword(s):

Fuel Cells ◽

Reinforcement Learning ◽

Proton Exchange Membrane ◽

Control Method ◽

Coordinated Control ◽

Proton Exchange ◽

Data Driven ◽

Multiple Systems ◽

Exchange Membrane

Download Full-text

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

Energies ◽

10.3390/en13123144 ◽

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.

Download Full-text

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

Chemical Engineering Research and Design ◽

10.1016/j.cherd.2009.12.001 ◽

2010 ◽

Vol 88 (7) ◽

pp. 861-874 ◽

Cited By ~ 6

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

Download Full-text

Micro fluidic structure selection of metal mesh combinations in proton exchange membrane fuel cells for air supply enhancement

International Journal of Hydrogen Energy ◽

10.1016/j.ijhydene.2020.05.154 ◽

2020 ◽

Vol 45 (57) ◽

pp. 32808-32815

Author(s):

Chang Seob Kim ◽

Jeawoo Jung ◽

Jong Hyun Jang ◽

Hyoung-Juhn Kim ◽

Hyun S. Park ◽

...

Keyword(s):

Fuel Cells ◽

Proton Exchange Membrane ◽

Proton Exchange ◽

Metal Mesh ◽

Structure Selection ◽

Air Supply ◽

Exchange Membrane ◽

Selection Of

Download Full-text

Temperature Control of Proton Exchange Membrane Fuel Cell Based on Machine Learning

Frontiers in Energy Research ◽

10.3389/fenrg.2021.763099 ◽

2021 ◽

Vol 9 ◽

Author(s):

Jiawen Li ◽

Yaping Li ◽

Tao Yu

Keyword(s):

Fuel Cell ◽

Pid Controller ◽

Proton Exchange Membrane ◽

Proton Exchange ◽

Training Costs ◽

Learning Speed ◽

Policy Gradient ◽

Exchange Membrane ◽

Training Efficiency ◽

Working Efficiency

In order to improve the proton exchange membrane fuel cell (PEMFC) working efficiency, we propose a deep-reinforcement-learning based PID controller for realizing optimal PEMFC stack temperature. For this purpose, we propose the Improved Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, a tuner of the PID controller, which can adjust the coefficients of the controller in real time. This algorithm accelerates the learning speed of an agent by continuously changing the soft update parameters during the training process, thereby improving the training efficiency of the agent, and further reducing training costs and obtaining a robust strategy. The effectiveness of the control algorithm is verified through a simulation in which it is compared against a group of existing algorithms.

Download Full-text

Control-oriented LPV Modeling for the Air Supply System of Proton Exchange Membrane Fuel Cells

Fuel Cells ◽

10.1002/fuce.201700195 ◽

2018 ◽

Vol 18 (4) ◽

pp. 433-440 ◽

Cited By ~ 1

Author(s):

F. X. Chen ◽

J. R. Jiao ◽

S. G. Liu ◽

Y. Yu ◽

S. C. Xu

Keyword(s):

Fuel Cells ◽

Proton Exchange Membrane ◽

Supply System ◽

Proton Exchange ◽

Air Supply ◽

Exchange Membrane

Download Full-text

Experimental Study of Air-Water Interaction in Presence of Powdered Wax Inside Simulated Gas Distribution Channel of a Proton Exchange Membrane Fuel Cell

Journal of Fuel Cell Science and Technology ◽

10.1115/1.3006352 ◽

2009 ◽

Vol 6 (3) ◽

Author(s):

Abhijit Mukherjee ◽

Anthony Bourassa

Keyword(s):

Fuel Cells ◽

Fuel Cell ◽

Water Flow ◽

Proton Exchange Membrane ◽

Distribution Channel ◽

Proton Exchange ◽

Water Droplets ◽

Water Interaction ◽

Air Supply ◽

Exchange Membrane

Low temperature fuel cells such as proton exchange membrane fuel cells are being currently developed to run cars and buses. Water management in these fuel cells is a key issue that needs to be adequately addressed for rapid development of the technology. The fuel cell reaction creates water that is typically carried away by the incoming air. However, at part load operations when the required air supply is lower, water droplets may fully block the air supply channels, leading to inefficient fuel cell operation. A solution to this problem is proposed taking a cue from tiny insects known as aphids that live inside plants. They excrete a watery substance called honeydew and get rid of this water using wax by encapsulating it into tiny droplets. In the present study, air-water interaction in a minichannel is studied in the presence of powdered wax. Air is forced into the channel inlet and water is pumped through a hole on the top wall of the channel. The movement of water inside the channel at different air velocities and water flow rates is recorded using a high-speed camera. Results indicate that the water droplets and slugs formed inside the channel are removed more rapidly in the presence of powdered wax. At the highest water flow rate and lowest air velocity used in this study the unwaxed channel gets completely flooded while the slugs of water continued to move forward in the waxed channel. Different two-phase flow regimes have been identified and plotted in both the waxed and unwaxed channels.

Download Full-text