Physics-Guided Deep Learning for Dynamical Systems: A Survey

Wang, Rui; Yu, Rose

doi:10.48550/arxiv.2107.01272

Cited by 17 publications

(18 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, ML models may lead to physically inconsistent results, may fail to generalize to unseen scenarios, and rely on the availability of big data. However, Physical-driven mod- [356] and Wang and Yu [353] classify and describe PGML works developed in different domains in the last years. In his thesis, Stender [357] develops a data science process for mechanical vibrations explicitly considering physics aspects in all steps of the process, namely obtain, pre-process, transform, model, and explain (OPTME).…”

Section: Physics Guided Machine Learningmentioning

confidence: 99%

A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic

Cunha¹,

Droz²,

Zine³

et al. 2022

Preprint

View full text Add to dashboard Cite

The use of Machine Learning (ML) has rapidly spread across several fields, having encountered many applications in Structural Dynamics and Vibroacoustic (SD&V). The increasing capabilities of ML to unveil insights from data, driven by unprecedented data availability, algorithms advances and computational power, enhance decision making, uncertainty handling, patterns recognition and real-time assessments. Three main applications in SD&V have taken advantage of these benefits. In Structural Health Monitoring, ML detection and prognosis lead to safe operation and optimized maintenance schedules. System identification and control design are leveraged by ML techniques in Active Noise Control and Active Vibration Control. Finally, the so-called ML-based surrogate models provide fast alternatives to costly simulations, enabling robust and optimized product design. Despite the many works in the area, they have not been reviewed and analyzed. Therefore, to keep track and understand this ongoing integration of fields, this paper presents a survey of ML applications in SD&V analyses, shedding light on the current state of implementation and emerging opportunities. The main methodologies, advantages, limitations, and recommendations based on scientific knowledge were identified for each of the three applications. Moreover, the paper considers the role of Digital Twins and Physics Guided ML to overcome current challenges and power future research progress. As a result, the survey provides a broad overview of the present landscape of ML applied in SD&V and guides the reader to an advanced understanding of progress and prospects in the field.

show abstract

Section: Physics Guided Machine Learningmentioning

confidence: 99%

A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic

Cunha¹,

Droz²,

Zine³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Physics-aware models The dynamics models obtained from machine learning often struggle with generalization and generally do not verify important physical principles such as conservation laws. Therefore, there have been efforts to bring together machine learning and first principles to learn physics-aware models; see Wang & Yu (2021) for an overview on this approach in deep learning. In general, there are two takes on including physical knowledge in datadriven models.…”

Section: Learning Dynamical Systemsmentioning

confidence: 99%

Recognition Models to Learn Dynamics from Partial Observations with Neural ODEs

Buisson-Fenet¹,

Morgenthaler²,

Trimpe³

et al. 2022

Preprint

View full text Add to dashboard Cite

Identifying dynamical systems from experimental data is a notably difficult task. Prior knowledge generally helps, but the extent of this knowledge varies with the application, and customized models are often needed. We propose a flexible framework to incorporate a broad spectrum of physical insight into neural ODE-based system identification, giving physical interpretability to the resulting latent space. This insight is either enforced through hard constraints in the optimization problem or added in its cost function. In order to link the partial and possibly noisy observations to the latent state, we rely on tools from nonlinear observer theory to build a recognition model. We demonstrate the performance of the proposed approach on numerical simulations and on an experimental dataset from a robotic exoskeleton.

show abstract

“…Consequently, there is an active, expansive literature on deep learning (DL) methods for accelerating or replacing numerical simulations (Wang 2021;Willard et al 2020). For example, deep dynamics models can approximate highdimensional spatiotemporal dynamics by directly forecasting future states, bypassing numerical integration (Wang et al 2020;Wang, Walters, and Yu 2021;de Bezenac, Pajot, and Gallinari 2018).…”

Section: Relevance Of Ai To Applicationmentioning

confidence: 99%

Latent Space Simulation for Carbon Capture Design Optimization

Bartoldson

Wang

et al. 2022

AAAI

Self Cite

View full text Add to dashboard Cite

The CO2 capture efficiency in solvent-based carbon capture systems (CCSs) critically depends on the gas-solvent interfacial area (IA), making maximization of IA a foundational challenge in CCS design. While the IA associated with a particular CCS design can be estimated via a computational fluid dynamics (CFD) simulation, using CFD to derive the IAs associated with numerous CCS designs is prohibitively costly. Fortunately, previous works such as Deep Fluids (DF) (Kim et al., 2019) show that large simulation speedups are achievable by replacing CFD simulators with neural network (NN) surrogates that faithfully mimic the CFD simulation process. This raises the possibility of a fast, accurate replacement for a CFD simulator and therefore efficient approximation of the IAs required by CCS design optimization. Thus, here, we build on the DF approach to develop surrogates that can successfully be applied to our complex carbon-capture CFD simulations. Our optimized DF-style surrogates produce large speedups (4000x) while obtaining IA relative errors as low as 4% on unseen CCS configurations that lie within the range of training configurations. This hints at the promise of NN surrogates for our CCS design optimization problem. Nonetheless, DF has inherent limitations with respect to CCS design (e.g., limited transferability of trained models to new CCS packings). We conclude with ideas to address these challenges.

show abstract

Physics-Guided Deep Learning for Dynamical Systems: A Survey

Cited by 17 publications

References 37 publications

A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic

A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic

Recognition Models to Learn Dynamics from Partial Observations with Neural ODEs

Latent Space Simulation for Carbon Capture Design Optimization

Contact Info

Product

Resources

About