Connectionists: Ph.D. position opportunity at Mondragon University (Spain): condition-based maintenance planning for wave energy technology through prognostics & health management strategies

[Joxe Inaxio Aizpurua]

Offshore renewable energy technologies have the potential to support
traditional renewable energy sources and contribute to the energy mix in
the short-medium term. Wave energy is an emerging area among the offshore
renewable energy systems, where the motion of ocean waves is converted into
electricity. Different technologies have been suggested [1], but all
include different components to convert mechanical energy into electricity
[2,3], which have a significant impact on the final performance and
maintenance of the wave energy devices. The nature of the operating
environment generates operation and maintenance challenges that hamper the
wide implementation and adoption of the wave energy technology.

There are different assets involved in the wave energy conversion and
distribution processes such as turbines, converters, generators, batteries,
transformers, cables, or circuit breakers. In the context of traditional
power grids, the operation and degradation processes of these components
are well studied [4-6]. However, in the context of wave energy, open sea
and weather conditions determine when it is possible to travel to the
offshore power plant and perform maintenance actions. These travel time
instants are known as weather windows. Accordingly, failures of system
components can result in prolonged periods of downtime and this situation
can significantly limit the benefits of wave energy applications. In this
context, effective risk management and maintenance planning are crucial
activities for the effective implementation and adoption offshore
technologies.

The objective of this project is to infer maintenance planning strategies
through monitoring the health state of the assets that take part in the
wave-to-electricity energy conversion process along with sea and weather
operation conditions. These strategies will have to evaluate the risk of
failure of components, cost of maintenance actions and weather windows, and
accordingly elicit optimal maintenance windows. This process will involve
the development and application of prognostics, and health management
techniques via engineering knowledge combined with artificial intelligence
and reliability methods, e.g. [7, 8].

The models developed in this project will be validated with the data
collected from real offshore facilities located in the Basque Country
through the collaboration with the Biscay Marine Energy Platform (BIMEP)
which owns two pioneering offshore facilities. The Mutriku Wave Power Plant
in Mutriku and the testing site located in Armintza.

The project will be developed in Mondragon Unibertsitatea within the group
of Signal Theory and communications (Joxe Aizpurua) in collaboration with
the Fluid Mechanics group (Markel Peñalba). Throughout the thesis the
student will engage continuously with industry and stays at different
universities and/or research centers will be pursued.

Interested applicants please apply here:
https://careers.talentclue.com/es/node/51514079

If you have any further questions or comments please refer to:
jiaizpurua at mondragon.edu and mpenalba at mondragon.edu

Application deadline. Review of applications will begin November 7th and
continue until the position is filled.

Requirements

• M. Sc. degree in telecommunications, electronics, computer science,
embedded systems or a related area.
• Programming skills: Matlab, Python, R, or C++
• Knowledge/experience with renewable energies is a plus.
• Knowledge/experience with reliability and/or diagnostics/health
management methods is a plus.
• Experience with artificial intelligence methods is a plus.
References

[1] Falcao, A. F. de O. (2010). Wave energy utilization: A review of the
technologies. Renewable and Sustainable Energy Reviews, 14(3), 899–918.
https://doi.org/10.1016/j.rser.2009.11.003
[2] Penalba, M., & Ringwood, J. V. (2016). A review of wave-to-wire models
for wave energy converters. Energies, 9(7), 506.
https://doi.org/10.3390/en9070506
[3] Penalba, M., & Ringwood, J. V. (2019). A high-fidelity wave-to-wire
model for wave energy converters. Renewable energy, 134, 367-378.
[4] Aizpurua, J. I., Stewart, B. G., McArthur, S. D. J., Lambert, B.,
Cross, J. G., & Catterson, V. M. (2019). Improved power transformer
condition monitoring under uncertainty through soft computing and
probabilistic health index. Applied Soft Computing, 105530.
[5] Aizpurua, J. I., Catterson, V. M., Abdulhadi, I. F., & Garcia, M. S.
(2017). A model-based hybrid approach for circuit breaker prognostics
encompassing dynamic reliability and uncertainty. IEEE Transactions on
Systems, Man, and Cybernetics: Systems, 48(9), 1637-1648.
[6] U. Garro, E. Muxika, J. I. Aizpurua and M. Mendicute (2019). FPGA-Based
Stochastic Activity Networks for On-Line Reliability Monitoring. IEEE
Transactions on Industrial Electronics.
[7] Aizpurua, J. I., Catterson, V. M., Papadopoulos, Y., Chiacchio, F., &
Manno, G. (2017). Improved dynamic dependability assessment through
integration with prognostics. IEEE Transactions on Reliability, 66(3),
893-913.
[8] Aizpurua, J. I., McArthur, S. D., Stewart, B. G., Lambert, B., Cross,
J. G., & Catterson, V. M. (2018). Adaptive power transformer lifetime
predictions through machine learning and uncertainty modeling in nuclear
power plants. IEEE Transactions on Industrial Electronics, 66(6), 4726-4737.

-- 
*Joxe Aizpurua.*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20191109/7ee9dbfa/attachment.html>