Prof. (asst. TUD) Dr. Manuel Arias Chao

Work at ZHAW

Position

• Senior Lecturer & Researcher
• Director of studies CAS Maintenance Management

Teaching

• Master Course "AI for Anomaly Detection in Complex Systems: a Hands-On Tutorial.
• Bachelor Course "Fundamental Principles of Maintenance"
• Bachelor Course "Traffic Systems Operations"
• Certificate of Advanced Studies (CAS) in Predictive Maintenance
• Certificate of Advanced Studies (CAS) Maintenance Management

Experience

• Assistant Professor at the Facualty of Aerospace, Operation and Environment Group
  Delft University of Technology
  05 / 2025 - today
• Visiting Researcher, Operation and Environment Group
  Delft University of Technology
  10 / 2022 - 04 / 2025
• PhD Candidate/Scientific Assistant on Predictive Maintenance
  ETH Zurich
  07 / 2017 - 08 / 2021
• Visiting Scientist, Diagnostics & Prognostics Group
  NASA Ames Research Center
  01 / 2019 - 03 / 2019
• Research Associate, Predictive Maintenance
  Zurich University of Applied Sciences
  07 / 2017 - 09 / 2018
• Lead Engineer, Thermo-Economic Optimization
  GE Power
  11 / 2016 - 06 / 2017
• Lead Engineer, Gas Turbine Thermodynamics
  GE Power
  11 / 2015 - 11 / 2016
• R&D Performance Owner / Work Package Coordinator
  ALSTOM Power Ltd
  10 / 2013 - 11 / 2015
• R&D Performance Engineer
  ALSTOM Power Ltd
  10 / 2008 - 10 / 2013
• Computational Fluid Dynamics (CFD) Engineer
  FLUENT France SAS
  07 / 2006 - 09 / 2007
• Aero-engine Maintenance Engineer
  Industria de Turbopropulsores S.A.
  08 / 2005 - 08 / 2006

Education and Continuing education

Education

• Doctor of Science (Dr. sc.)
  ETH Zurich
  2017 - 2021
• CAS in Risk Management for Banking and Finance
  University of Zurich
  2015 - 2016
• MSc. in Thermal Power
  Cranfield University
  2007 - 2008

Network

Awards

• Best Paper Award at PHM Society Conference 2023 in Salt Lake City
  Prognostics and Health Management Society
  10 / 2023
• Early Career Award at PHM Society Conference 2022 in Nashville
  Prognostics and Health Management Society
  11 / 2022
• Best Paper Award 2021
  Journal "Data" by MDPI
  09 / 2021
• Best Papers Award at 2015 Turbo Expo in Montreal
  Structures & Dynamics Probabilistic Methods Committee.
  06 / 2015

Social media

Linkedin

Projects

• AI-Enhanced Acoustic Monitoring for Pumps and Transformer Components / Project leader / ongoing
• Hybrid Aircraft Maintenance Program / Project leader / ongoing
• AI-based Health Prognostics for Battery Energy Storage Systems with Operational Condition Monitoring Data / Deputy project leader / ongoing
• Condition Monitoring of Generators / Deputy project leader / completed
• An end-to-end fault prognostics solution for reliable power grids using acoustic sensors / Project leader / completed
• Smart Maintenance Nuclear Power Plants / Project leader / completed
• ZHAW-PARC Hybrid Prognostics Research / Project leader / completed

Publications

Articles in scientific journal, peer-reviewed

• Navidi, S. et al. (2025) 'Forecasting battery capacity for second-life applications using physics-informed recurrent neural networks', eTransportation, 25(100432). doi: 10.1016/j.etran.2025.100432.
• Pierre, D. et al. (2025) 'Analytical health indices : towards reliability-informed deep learning for PHM', International Journal of Prognostics and Health Management, 16(2). doi: 10.36001/ijphm.2025.v16i2.4262.
• Llasag Rosero, R. et al. (2025) 'Label synchronization strategies for hybrid federated learning', Reliability Engineering & System Safety, 256(110751). doi: 10.1016/j.ress.2024.110751.
• Basora, L. et al. (2025) 'A benchmark on uncertainty quantification for deep learning prognostics', Reliability Engineering & System Safety, 253(110513). doi: 10.1016/j.ress.2024.110513.
• Bajarunas, K. et al. (2024) 'Health index estimation through integration of general knowledge with unsupervised learning', Reliability Engineering & System Safety, 251(110352). doi: 10.1016/j.ress.2024.110352.

Written conference contributions, peer-reviewed

• Goglio, D., Zarouchas, D. and Arias Chao, M. (2025) 'PhD Symposium : Interpretable and uncertainty-aware hybrid prognostics using multimodal knowledge for RUL prediction', in Kulkarni, C. S. and Orchard, M. E. (eds) Proceedings of the Annual Conference of the PHM Society 2025. New York, NY: PHM Society. doi: 10.36001/phmconf.2025.v17i1.4605.
• Käslin, B. et al. (2025) 'Integrated stochastic optimization of maintenance scheduling and tail assignment with health-aware models in aviation', in Annual Conference of the PHM Society. PHM Society. doi: 10.36001/phmconf.2025.v17i1.4610.
• Chawla, P., Kulkarni, C. and Arias Chao, M. (2025) 'Ensuring UAS airworthiness : deep learning-based acoustic health monitoring of motor health'. EUROCONTROL. doi: 10.5281/zenodo.20159666.
• Goren Huber, L., Palmé, T. and Arias Chao, M. (2023) 'Physics-informed machine learning for predictive maintenance : applied use-cases', in 2023 10th IEEE Swiss Conference on Data Science (SDS). IEEE, pp. 66–72. doi: 10.1109/SDS57534.2023.00016.

Other publications

Goren Huber, L., Palmé, J. T. and Arias Chao, M. (2023) 'Hybride Instandhaltung : wie fliesst das Fachwissen in die KI?', fmpro service, 2023(6), pp. 5–7. doi: 10.21256/zhaw-29515.

Publications before appointment at the ZHAW

• M. Arias Chao, C. Kulkarni, K. Goebel, O. Fink (2022). Fusing Physics-based and Deep Learning Models for Prognostics, Reliability Engineering & System Safety 217, p. 107961. issn: 0951-8320.
• Y. Tian, M. Arias Chao, C. Kulkarni, K. Goebel, O. Fink (2022). Real-Time Model Calibration with Deep Reinforcement Learning, Mechanical Systems and Signal rocessing. 165, p. 108284. issn: 0888-3270
• M. Arias Chao (2021). Combining Deep Learning and Physics-Based Performance Models for Diagnostics and Prognostics. Diss. ETH Zurich, 2021.
• L. Biggio, A. Wieland, M. Arias Chao, I. Kastanis, O. Fink, Iason Kastanis, and Olga Fink (2021). Uncertainty-Aware Prognosis via Deep Gaussian Process, IEEE Access 9, pp. 123517–123527
• U. Unagar, Y. Tian, M. Arias Chao, O. Fink (2021). Learning to Calibrate Battery Models in Real-Time with Deep Reinforcement Learning. Energies, 14, 1361. https://doi.org/10.3390/en14051361
• M. Arias Chao, C. Kulkarni, K. Goebel, O. Fink (2021). Aircraft Engine Run-to-Failure Dataset under Real Flight Conditions for Prognostics and Diagnostics. Data, 6, 5. https://doi.org/10.3390/data6010005
• M. Arias Chao, B. T. Adey, O. Fink (2021). Implicit supervision for fault detection and segmentation of emerging fault types with Deep Variational Autoencoders, Neurocomputing. issn: 0925-2312
• L. Biggio, M. Arias Chao, O. Fink (2020). Uncertainly-aware Remaining Useful Life Predictors, NeurIPS 2020 Workshop on Machine Learning for Engineering Modeling, Simulation and Design
• M. Arias Chao, C. Kulkarni, K. Goebel, O. Fink (2019). Hybrid Deep Fault Detection and Isolation: Combining Deep Neural Networks and System Performance Models, International Journal of Prognostics and health Management, 10, 033
• M. Arias Chao, W. Reiter, and D. S. Lilley (2017). Method for operating a power plant. U.S. Patent Application 15/241,269, filed February 23, 2017.
• M. Arias Chao, B. Wippel, C. Balmer, and R. Jakoby (2017). Method for operating a gas turbine plant and gas turbine plant for implementing the method. U.S. Patent 9,752,504, issued September 5, 2017.
• M. Arias Chao, P. Mathé, et al. (2015). Calibration and Uncertainty Quantification of Gas Turbines Performance Models, ASME paper GT2015-42392
• M. Arias Chao, A. Nemet, U. R. Steiger, and D. S. Lilley (2015). Method for determining at least one firing temperature for controlling a gas turbine and gas turbine for performing the method. U.S. Patent Application 14/491,172, filed 2015.
• R. C. Payne, M. Arias Chao, V. Stefanis (2014). A Novel Intake Concept for Flue Gas Recirculation to Enhance CCS in an Industrial Gas Turbine, ASME paper GT2014-25469
• L. Gallar, M. Arias Chao, V. Pachidis, R. Singh (2011). Stochastic Axial Compressor Variable Geometry Schedule Optimisation, Aerospace Science and Technology, 15 (5) 366-374
• L. Gallar, M. Arias Chao, V. Pachidis, P. Pilidis (2009). Compressor Variable Geometry Schedule Optimisation Using Genetic Algorithms, ASME paper GT2009-60049

go back