Dataset:

Documents used for the applications in the paper

Paper:

Zhong S., Scarinci A.,  Cicirello A., Natural Language Processing for Systems Engineering: Automatic Generation of Systems Modelling Language Diagrams, Knowledge-Based Systems, 2023.

Open access:  https://doi.org/10.1016/j.knosys.2022.110071 

Code:

Probabilistic Generative models in Engineering investigating disentangled and invariant representation learning for grounding VAE to the known physics.

• encoder, decoder and latent space of the VAE semantically and functionally separated into data-driven and physics-grounded branches. 

• Regularization method based on the GRL is used to constrain the data-driven components, resulting in a model that preferentially utilizes the known physics.

•  Interpretable and intuitive hyperparameter is used to specify the strength of GRL, and whether the model is trained in a collaborative or adversarial manner. 

• Strategy for quantifying the type and relative amount of information encoded in different sets of latent variables 

Dataset:

Synthetic dataset on three synthetic case studies:

• Euler-Bernoulli beam

• Damped oscillator 

• Bridge case study

Paper:

Koune I., Cicirello A., Adversarial Disentanglement by Backpropagation with Physics-Informed Variational Autoencoder.

Preprint: https://arxiv.org/abs/2506.13658 

Code:

Variational autoencoder example applied to a beam case study

Dataset:

Synthetic dataset

Presentation by Jan: https://drive.google.com/file/d/1NNT02daIRjnIWiUI-gtx3bzJfk63z3nI/view

Fundamentals of the work presented in:

Koune I., Cicirello A., Disentangled representation learning with physics-informed variational autoencoder for structural health monitoring. EWSHM 2024 - available here

Code:

PhI-SINDY implementation for tackling non-smooth nonlinearities identification in SDOF, MDOF, multiple friction contacts.

Dataset:

Both synthetic and experimental dataset involving friction contacts

Paper:

Lathourakis C., Cicirello, A., Physics Enhanced Sparse Identification of Dynamical Systems with Discontinuous Nonlinearities.Nonlinear Dynamics, 2024.

https://doi.org/10.1007/s11071-024-09652-2

Code:

Switching Gaussian Process Latent Force model implementation for tackling non-smooth nonlinearity identification in a SDOF with one friction contact

Dataset:

Both synthetic and experimental dataset involving friction contacts

Paper:

Marino L., Cicirello A., A switching Gaussian process latent force model for the identification of mechanical systems with a discontinuous nonlinearity, Data-Centric Engineering, 2023.

Open access: https://doi.org/10.1017/dce.2023.12 

Code:

Gaussian Problem Latent Force model implementation for virtual sensing applications

Dataset:

Synthetic dataset  (MDOF cantilever)

Paper:

Zou J., Lourens E., Cicirello A., Virtual sensing of subsoil strain response in monopile-based offshore wind turbines via Gaussian process latent force models,  Mechanical System and Signal Processing, 2023.

https://doi.org/10.1016/j.ymssp.2023.110488 

Code:

Single- and multi-agent DRL architectures are considered, trained through double deep Q-network and proximal policy optimization, while the updating of the uncertain continuous-value environment parameters, is performed through Hamiltonian Markov Chain Monte Carlo (HMCMC) with no U-turn sampling. 

Dataset:

Synthetic data 

Paper:

Lathourakis C., Andriotis C., Cicirello, A., Inference and Maintenance Planning of Monitored Structures through Markov Chain Monte Carlo and Deep Reinforcement Learning, 14th International Conference of Application of Statistics and Probability in Civil Engineering (ICASP14), Dublin, 9th-13th July 2023. available here

Codes and experimental Dataset:

cal_angle.m

experimental_modal_analysis.m

influence_leg_schematic.m

jointfig.m

jointfig_transpose_xspace.m

mass_inertia_influence.m

modal_identification_data.mat

plotcube.m

plotcube_linestyle.m

readme.docx

sort_comp_eigen2.m

span_angle_influence.m

spider_model_withleg.m

springdamper_3D_vertical.m

stiffness_damping_influence.m

wavespeed_influence.m

Paper:

Wu J., Miller T. E., Cicirello A., Mortimer B., Spider dynamics under vertical vibration and its implications for biological vibration sensing, Royal Society Interface, 2023.
Open access:  https://doi.org/10.1098/rsif.2023.0365 

Code:

Real-time-failure detection  - self-supervised classification strategy automatically extracting info from reports and from measurements. 

Dataset:

Real failure generated on arduino boards with several sensors connected. Measurements, metadata and reports generated by hand (before ChatGPT!)

Papers:

Oncescu A-M., Cicirello A., A self-supervised classification algorithm for sensor fault identification for robust Structural Health Monitoring, 10th European Workshop on Structural Health Monitoring  (EWSHM  2022), Palermo, Italy, 2022.
https://doi.org/10.1007/978-3-031-07254-3_57 

Oncescu A-M., Cicirello A., Sensor Fault Label Identification for Robust Structural Health Monitoring. Proceedings of the 4th ECCOMAS thematic conference on Uncertainty Quantification in Computational Sciences and Engineering (UNCECOMP 2021), 2021.

Code:

Efficient probabilistic model updating when dealing with spatial and temporal correlation

Dataset:

Synthetic dataset 

Paper:

Koune I., Rozsas I.,  Slobbe A.,  Cicirello A., Bayesian system identification for structures considering spatial and temporal correlation. Data Centric Engineering, 2023.

https://doi.org/10.1017/dce.2023.18

Code:

Efficient probabilistic model updating when dealing inference of time-varying model parameters - Sequential Ensemble Markov Chain Monte Carlo implementation 

Dataset:

Synthetic and experimental dataset for time-varying friction identification problem 

Paper:

Lye A., Marino L., Cicirello, A, Patelli E., Sequential Ensemble Monte Carlo sampler for on-line Bayesian inference of time-varying model parameters in engineering applications, ASME J. Risk Uncertainty Part B, 2023.

https://doi.org/10.1115/1.4056934 

Code:

Efficient probabilistic model updating - Transitional Ensemble Markov Chain Monte Carlo implementation 

Dataset:

Synthetic and experimental dataset  (Aluminum frame problem)

Paper:

Lye A., Cicirello A., Patelli E., An efficient and robust sampler for Bayesian inference: Transitional Ensemble Markov Chain Monte Carlo,  Mechanical System and Signal Processing, 2022

https://doi.org/10.1016/j.ymssp.2021.108471 

Code:

Codes for tutorial paper on Bayesian inference 

Dataset:

Synthetic dataset  

Paper:

Lye A., Cicirello A., Patelli E., Sampling Methods for solving Bayesian Model Updating Problems: A Tutorial, Mechanical System and Signal Processing, 2021.

https://doi.org/10.1016/j.ymssp.2021.107760