Research

Decision making

Our engineering systems are exposed to adverse conditions during their life-cycle, with deterioration and hazards posing a threat to reliability and resilience. Optimal decision-making for such systems is concerned with controlling the extent and consequences of this exposure through efficient plans, from predictive maintenance to post-disaster recovery. To be successful, decision optimization must tackle complexities related to the dimensionality of heterogeneous multi-component systems; long-horizon sequencing of interventions; epistemic and aleatoric uncertainties; operational constraints; the presence of multiple agents; and efficient integration of physics-based digital models within the loop of optimization. This line of research studies solutions to the above challenges through novel frameworks within of stochastic optimal control, systems reliability, and artificial intelligence.

Selected works

Andriotis, C.P., and Papakonstantinou, K.G., 2019. “Managing engineering systems with large state and action spaces through deep reinforcement learning”, Reliability Engineering & System Safety, 191 (11), 106483.
Andriotis, C.P., and Papakonstantinou, K.G., 2021. “Deep reinforcement learning driven inspection and maintenance planning under incomplete information and constraints”, Reliability Engineering & System Safety, 212, 107551.
Saifullah, M., Papakonstantinou, K.G., Andriotis, C.P., Stoffels, S., 2024. “Decentralized stochastic optimal inspection and maintenance control solutions in multi-asset transportation networks”, arXiv preprint arXiv:2401.12455.
Morato, P.G., Andriotis, C.P., Papakonstantinou, K.G., and Rigo, P., 2023. “Inference and dynamic decision-making for deteriorating systems with probabilistic dependencies through Bayesian networks and deep reinforcement learning”, Reliability Engineering & System Safety, 109144.
Papakonstantinou K.G., Andriotis C.P., and Shinozuka M., 2018. “POMDP and MOMDP solutions for structural life-cycle cost minimization under partial and mixed observability”, Structure and Infrastructure Engineering, 14 (7), 869-882.
van Remmerden, J., Kenter, M., Roijers, D.M., Andriotis, C.P., Zhang, Y., Bukhsh, Z., 2025. “Deep multi-objective reinforcement learning for utility-based infrastructural maintenance optimization”, Neural Computing and Applications, pp.1-24.
Bhustali, P. and Andriotis, C.P., 2023. Assessing the optimality of decentralized inspection and maintenance policies for stochastically degrading engineering systems. In Benelux Conference on Artificial Intelligence (pp. 236-254). Cham: Springer Nature Switzerland.

Risk & reliability

Quantification of uncertainties in models and data constitutes the fundamental basis for assessing risk, thus being able to make informed engineering decisions. Uncertainties associated with chronic stressors (such as corrosion or fatigue) as well as with hazards (such as earthquakes) need to be efficiently quantified, either directly, based on data, or indirectly, through physics-based models. The goal is to estimate their effect on certain probabilistic quantities of interest. Probabilistic modeling in this regard must accommodate high-dimensional feature spaces, as well as the presence of correlations and dependencies at spatial and temporal scales. This research line studies risk & reliability methods as these pertain to probabilistic performance-based engineering, structural fragility, Bayesian inference and model updating, and probabilistic machine learning.

Selected works

Andriotis, C.P., and Papakonstantinou, K.G., 2018. “Extended and generalized fragility functions”, Journal of Engineering Mechanics, 144 (9), 04018087.
Morato, P.G., Papakonstantinou, K.G., Andriotis, C.P., Nielsen, J.S., and Rigo, P., 2022. “Optimal inspection and maintenance planning for deteriorating structural components using dynamic Bayesian networks and Markov decision”, Structural Safety, 94, 102140.
Molaioni, F., Andriotis, C.P., and Rinaldi, Z., 2025. "Life-cycle fragility analysis of aging reinforced concrete bridges: A dynamic Bayesian network approach", Structural Safety, p.102654.
Andriotis, C.P., Papakonstantinou, K.G., and Chatzi, E.N., 2021. “Value of structural health information in partially observable stochastic environments”, Structural Safety, 93, 102072.
Yi, S., Papakonstantinou, K.G., Andriotis, C.P., and Song, J., 2022. “Appraisal and mathematical properties of fragility analysis methods”, 13th International Conference on Structural Safety & Reliability (ICOSSAR), Shanghai, China.
Koniari, A.M., Andriotis, C.P., Bianchi, S., Morato, P.G., Khademi, S., Overend, M., 2025. Predicting building operational energy at urban level under material degradation and climate uncertainty: A sensitivity analysis. 6th International Conference on Uncertainty Quantification in Computational Science and Engineering.

Design & mechanics

Extreme loads force structural systems to their limit. Limit states are often manifested through large inelastic displacements and rotations that defy linear predictions. Efficient assessment of responses in materially and geometrically nonlinear regimes is indispensable, especially in cases where risk assessment and decision-making are ultimate goals. This line of research studies computational approaches for constitutive material modeling, structural element formulations under material and geometric nonlinearities, and design optimization. It is a research that links computational structural mechanics with optimization, as this relates to how nonlinear programming concepts can be integrated with analysis to tame computational complexity, and, reversely, to how nonlinear simulators can be integrated with optimization algorithms for optimal design.

Selected works

Andriotis, C.P., Papakonstantinou, K.G., and Koumousis, V.K., 2018. “Nonlinear programming hybrid beam-column element formulation for large displacement elastic and inelastic analysis”, Journal of Engineering Mechanics, 144 (10), 04018096.
Jewett, J.L., Koniari, A.M., Andriotis, C.P., Oikonomopoulou, F., Bristogianni, T. and Carstensen, J.V., 2025. “More with less: topology optimization strategies for structural glass design”, Glass Structures & Engineering, 10(2), pp.1-18.
Koniari, A.M., Andriotis, C.P., and Oikonomopoulou, F., 2023. “Minimum mass cast glass structures under performance and manufacturability constraints”, 20th International Conference on Computer-Aided Architectural Design Futures (CAAD Futures), Delft, The Netherlands.
Bianchi, S., Andriotis, C.P., Klein, T. and Overend, M., 2024. "Multi-criteria design methods in façade engineering: State-of-the-art and future trends", Building and Environment, 250, p.111184.
Lyritsakis, C.M., Andriotis, C.P., and Papakonstantinou, K.G., 2021. “Geometrically exact hybrid beam element based on nonlinear programming”, International Journal for Numerical Methods in Engineering 122 (13), 3273-3299.
Andriotis, C.P., Gkimousis, I., and Koumousis, V.K., 2016. “Modeling reinforced concrete structures using smooth plasticity and damage models”, Journal of Structural Engineering, vol. 142, no. 2, p. 04015105.

Conctact

Faculty of Architecture & Built Environment

Delft University of Technology

Julianalaan 134, 2628 BL, Delft

email: c [dot] andriotis [at] tudelft [dot] nl

Page updated

Google Sites

Report abuse