Physics-guided Deep Learning Research Articles

Online Dynamic Security Assessment: Using Hybrid Physics-Guided Deep Learning Models

Online Dynamic Security Assessment: Using Hybrid Physics-Guided Deep Learning Models

Physics-guided deep learning-based real-time image reconstruction of Fourier-domain optical coherence tomography

In this paper, we introduce a physics-guided deep learning approach for high-quality, real-time Fourier-domain optical coherence tomography (FD-OCT) image reconstruction. Unlike traditional supervised deep learning methods, the proposed method employs unsupervised learning. It leverages the underlying OCT imaging physics to guide the neural networks, which could thus generate high-quality images and provide a physically sound solution to the original problem. Evaluations on synthetic and experimental datasets demonstrate the superior performance of our proposed physics-guided deep learning approach. The method achieves the highest image quality metrics compared to the inverse discrete Fourier transform (IDFT), the optimization-based methods, and several state-of-the-art methods based on deep learning. Our method enables real-time frame rates of 232 fps for synthetic images and 87 fps for experimental images, which represents significant improvements over existing techniques. Our physics-guided deep learning-based approach could offer a promising solution for FD-OCT image reconstruction, which potentially paves the way for leveraging the power of deep learning in real-world OCT imaging applications.

Dynamic Physics-Guided Deep Learning for Long-Term Production Forecasting in Unconventional Reservoirs

Summary Neural network predictive models are popular for production forecasting in unconventional reservoirs due to their ability to learn complex relationships between well properties and production responses from extensive field data. The intricate flow behavior in hydraulically fractured unconventional reservoirs, which remains poorly understood, makes these statistical models particularly useful. Various neural network variants have been developed for production prediction in these reservoirs, each offering predictive capability of varying levels of granularity, accuracy, and robustness against noisy and incomplete data. Neural network predictive models that integrate physical principles are especially useful for subsurface systems, as they provide predictions that adhere to physical laws. This work introduces a new dynamic physics-guided deep learning (DPGDL) model that incorporates physical functions into neural networks and employs residual learning to compensate for the imperfect description of the physics, under variable data support. The new formulation allows for dynamic residual correction, avoids unintended bias due to less-than-ideal input data, and provides robust long-term predictions. The DPGDL model improves upon a static formulation by utilizing a masked loss function to enable learning from wells with varying production lengths and by improving the results when partially-observed timesteps are present. In addition, a sequence-to-sequence residual model has been developed to correct additional biases in the long-term predictions from the physics-constrained neural networks. Several synthetic data sets with increasing complexity as well as a field data set from the Bakken are used to demonstrate the performance of the new DPGDL model.

Physics-guided deep learning based on modal sensitivity for structural damage identification with unseen damage patterns

Recently, wide attention has been paid to develop deep learning-based models for structural damage identification. However, in most of the studies, the pure deep learning-based structural damage identification methods lack physical interpretability and scientific consistency for generalization. Therefore, although such methods can achieve good damage identification results when data with similar damage patterns used for training and testing the network model, they usually give poor predictions in the unseen domain, i.e., the network’s extrapolation ability is limited. In this research, a physics-guided deep learning neural network (PGDLNN) is proposed by incorporating the physical loss constructed by structural modal parameters sensitivity analysis into the original Convolutional Neural Network (CNN) for structural damage identification. The model’s physical interpretability is improved, which can lead to more accurate damage identification results, especially in the domain with unseen damage patterns in training the network model. Numerical and experimental studies on simply supported beams are carried out to demonstrate the feasibility and effectiveness of the proposed method. The influences of measurement noise and incomplete measurements are also investigated. The results show that the incorporation of physical knowledge to deep learning model can enhance the generalization of the network, and hence improve the accuracy of damage severity quantification. This study not only performs damage localization and quantification simultaneously using the physics-guided deep learning neural network, but also demonstrates the superiority of incorporating physical knowledge into data-driven deep learning models for structural health monitoring.

Learning dynamical systems from data: An introduction to physics-guided deep learning

Modeling complex physical dynamics is a fundamental task in science and engineering. Traditional physics-based models are first-principled, explainable, and sample-efficient. However, they often rely on strong modeling assumptions and expensive numerical integration, requiring significant computational resources and domain expertise. While deep learning (DL) provides efficient alternatives for modeling complex dynamics, they require a large amount of labeled training data. Furthermore, its predictions may disobey the governing physical laws and are difficult to interpret. Physics-guided DL aims to integrate first-principled physical knowledge into data-driven methods. It has the best of both worlds and is well equipped to better solve scientific problems. Recently, this field has gained great progress and has drawn considerable interest across discipline Here, we introduce the framework of physics-guided DL with a special emphasis on learning dynamical systems. We describe the learning pipeline and categorize state-of-the-art methods under this framework. We also offer our perspectives on the open challenges and emerging opportunities.

Physics-Guided Deep Learning Method for Tool Condition Monitoring in Smart Machining System

Physics-Guided Deep Learning Method for Tool Condition Monitoring in Smart Machining System

Large-scale 3D non-Cartesian coronary MRI reconstruction using distributed memory-efficient physics-guided deep learning with limited training data.

To enable high-quality physics-guided deep learning (PG-DL) reconstruction of large-scale 3D non-Cartesian coronary MRI by overcoming challenges of hardware limitations and limited training data availability. While PG-DL has emerged as a powerful image reconstruction method, its application to large-scale 3D non-Cartesian MRI is hindered by hardware limitations and limited availability of training data. We combine several recent advances in deep learning and MRI reconstruction to tackle the former challenge, and we further propose a 2.5D reconstruction using 2D convolutional neural networks, which treat 3D volumes as batches of 2D images to train the network with a limited amount of training data. Both 3D and 2.5D variants of the PG-DL networks were compared to conventional methods for high-resolution 3D kooshball coronary MRI. Proposed PG-DL reconstructions of 3D non-Cartesian coronary MRI with 3D and 2.5D processing outperformed all conventional methods both quantitatively and qualitatively in terms of image assessment by an experienced cardiologist. The 2.5D variant further improved vessel sharpness compared to 3D processing, and scored higher in terms of qualitative image quality. PG-DL reconstruction of large-scale 3D non-Cartesian MRI without compromising image size or network complexity is achieved, and the proposed 2.5D processing enables high-quality reconstruction with limited training data.

A physics-guided deep learning model for predicting the magneto-induced mechanical properties of magnetorheological elastomer: Small experimental data-driven

Magnetorheological elastomer (MRE) is a novel intelligent material, which shows excellent potential in vibration control applications. Previous researches have fully demonstrated that the magneto-induced shear storage modulus of MRE largely determines the vibration control effect. However, both existing theoretical and experimental ways to measure the magneto-induced shear storage modulus of MRE face their own shortage. Therefore, a novel physics-guided deep learning model is proposed to efficient predict the magneto-induced mechanical properties of MRE based on Magnetic Dipole theory and data-driven methods. A small database is built by collecting the magneto-induced shear storage modulus of MRE with different material ratios tested on a special shear rheometer. The proposed model trained with small training samples and its prediction results fit well with experimental values (average R2 of 0.99) which is superior to existing constitutive models. The training only takes 25 s, which significantly shortens the time compared to the experiment. Furthermore, the proposed model effectively predicts the magneto-induced storage modulus of MRE and has good generalization and superior transfer performance.

Physics-Guided Deep Learning for Plate Permeability Estimation With Single to Multiple Frequency Transformation of Eddy-Current Testing

Physics-Guided Deep Learning for Plate Permeability Estimation With Single to Multiple Frequency Transformation of Eddy-Current Testing

Physics-guided deep learning for driving force estimation in synchronous tunnel boring machines under missing cylinders

To solve the problems of high-dimensional under-constraint and state unknowability in the segment assembly process, this study develops a physics-guided deep learning approach to estimate the hydraulic cylinder driving force and promote the system stability in the synchronous excavation and segment assembly tunnel boring machines (S-TBMs). The Newton's law and the Lagrange multiplier method are used to analyze the force boundary of the S-TBM, where the constraint equations are embedded into the deep learning model. The basic model adopts the multi-head attention deep neural network (MD) architecture, which can capture the extreme data of the cylinder through the attention mechanism. The results show that: (1) The proposed physics-guided deep learning can effectively predict driving force of the cylinder and generate high R2 values which is 0.977. (2) By incorporating the physical laws and simulation data, the model accuracy of R2, RMSE, MAE, and EVS is increased by 9.04%, 53.96%, 55.91%, and 9.89%, respectively. (3) The estimation approach has good robustness, and there is no obvious deviation in the estimation results for 16 cylinders. The novelty to be highlighted is the development of the cylinder driving forces estimation approach with the physical laws incorporated, which is helpful in effectively improving the stability during the excavation and segment assembly process.

Physics-guided deep learning for damage detection in CFRP composite structures

Structural health monitoring of carbon fiber reinforced plastics composite structures based on deep learning usually builds on black box models for damage detection. However, the lack of physics knowledge limits its application into real-world problems where structural property or environmental condition varies. To overcome this limitation, we propose a physics-guided deep learning framework to integrate physics into data-driven models. This physics-guided convolutional neural network leverages structural degradation trend and physical consistency by combining the output of the physical model with the observed feature in a hybrid model. This hybrid model uses an additional branch to observe the information of stiffness degradation, which is the input into the physical model to describe the damage growth in structures by establishing a relationship with the power spectral density change in the guided wave signals. Additionally, the physics-based loss function is designed as part of the learning objective to ensure the model outputs satisfy the existing physics and maintain physical consistency. Experiment results show that our method demonstrates great generalizability that by training on data of only one particular CFRP composite structure, the PGCNN model can expand its great performance on all other CFRP layups in the NASA-published CFRP Dataset with over 90% accuracy.

Sensorless End-to-End Freehand Three-dimensional Ultrasound Reconstruction with Physics Guided Deep Learning

Sensorless End-to-End Freehand Three-dimensional Ultrasound Reconstruction with Physics Guided Deep Learning

Physics-Guided Deep Learning Enabled Surrogate Modeling for Pneumatic Soft Robots

Physics-Guided Deep Learning Enabled Surrogate Modeling for Pneumatic Soft Robots

Physics-guided deep learning 3D inversion based on magnetic data

Physics-guided deep learning 3D inversion based on magnetic data

Loading condition monitoring of high-strength bolt connections based on physics-guided deep learning of acoustic emission data

Aiming at life-cycle condition monitoring of high-strength bolt connections, a physics-guided deep learning framework integrating supervised and unsupervised learning was developed to diagnose manifold damage mechanisms and identify different loading stages using acoustic emission (AE) data. For data preprocessing, empirical wavelet transform (EWT) was introduced to provide adaptive and compact time–frequency representations of AE signals where diverse damage mechanisms behaved with various energy distributions. A convolutional neural network (CNN) model was first built to extract damage-related features from multiscale EWT matrices of AE data labeled by the loading stages I, II-III, and IV that were redefined according to their dominant damage mechanisms. Stage I (static friction) could be identified directly, which was characterized by the distinct damage mechanism of plastic deformation of asperities. After that, Gaussian mixture model (GMM) was applied to cluster the extracted feature vectors of AE data induced by multiple damage mechanisms overlapped among stages II (sliding), III (confined), and IV (failure). With the help of Bayesian information criterion (BIC), three damage mechanisms were recognized, including abrasive wear of asperities, adhesive wear of asperities, and plastic deformation and cracking of screw, which were validated by their EWT components. Finally, based on the proportions of AE data corresponding to diverse damage mechanisms, the rules were established for identifying the four loading stages of high-strength bolt connections. Experimental results demonstrated that the three-class CNN model with data labeled by the redefined loading stages achieved a higher accuracy than the four-class CNN model with data straightforwardly labeled by the original loading stages. Not only the critical damage states of static friction failure (looseness) and shear failure, but the four loading stages of high-strength bolt connections and their overlapped damage mechanisms were successfully identified by the physics-guided CNN-GMM framework.

A Physics-Guided Deep Learning Approach for Functional Assessment of Cardiovascular Disease in IoT-Based Smart Health

The rapid development of the Internet of Things (IoT) widely supports the smart healthcare system. IoT-based smart health has significant importance for the diagnosis of cardiovascular disease in clinical practice. Combined with advanced artificial intelligence techniques, IoT-based smart health provides valuable and accurate diagnosis information remotely for cardiovascular disease. The functional assessment of cardiovascular disease is an essential task in clinical practice. It aims to determine the extent of myocardial ischemia through the measurement of the hemodynamic parameters of the coronary artery. However, the clinical adoption of the hemodynamic parameters is limited due to the potential risks and high health costs during measurements. Recent advances in artificial intelligence have enabled the computation of hemodynamic parameters based on the anatomical features of coronary arteries. However, the existing methods still lack explainability in the prediction. To address this issue, we present a physics-guided deep learning network for the functional assessment of cardiovascular disease in an IoT-based manner. We specifically design an attentive network to determine the effective features by considering the importance of coronary artery anatomy features and artery segments. To obtain the functional assessment with explainability, we incorporate physical knowledge related to the blood flow into the loss function. It can ensure that functional assessment follows the physical laws. Extensive experiments are performed on a synthetic dataset and a real-world clinical dataset. The results show that our approach can achieve accurate and physically consistent assessment. Moreover, our method promotes deeper adoption of IoT and deep learning in the field of smart health.

Physics-Guided Deep Learning for Prediction of Energy Production from Geothermal Reservoirs

Predictive models are traditionally used for the development and management of geothermal reservoirs. While field operation optimization based on physics-based simulations offers dependable strategies, simulation models require detailed descriptions of reservoir conditions and properties and entail extensive computational efforts. As efficient alternatives to traditional physics-based simulation, data-driven predictive models such as deep learning-based models can provide fast predictions to facilitate complex iterative tasks that otherwise entail high computation time. However, purely data-driven models that are trained using limited data often provide physically inconsistent predictions and fail to generalize beyond the training data. This has important consequences in optimization applications where, during optimization, the well control strategies are likely to fall beyond the training data. These limitations undermine the suitability and strength of data-driven models in scientific and engineering applications, where the amount of data is typically limited but physical laws are well-established and frequently used. To address the above challenges, we propose a novel physics-guided machine learning model by incorporating the general structure of the physics-based equations into deep learning models. A typical approach for incorporating physics is adding physics-based constraints in the loss function to regularize the trainable parameters. However, this approach does not exploit or adapt the architecture of the neural network. In this work, the architecture of the proposed recurrent neural networks (RNN) is designed to represent the differential equations of the subsurface flow system. We present the physics-guided RNN models in detail and demonstrate their connection to the underlying differential equations describing the fluid flow physics. We investigate the prediction performance of the proposed models by first applying them to controlled example to evaluate their extrapolation power, before using them with simulated and field datasets.

Predicting Ocean Temperature in High-Frequency Internal Wave Area with Physics-Guided Deep Learning: A Case Study from the South China Sea

Higher-accuracy long-term ocean temperature prediction plays a critical role in ocean-related research fields and climate forecasting (e.g., oceanic internal waves and mesoscale eddies). The essential component of traditional physics-based numerical models for ocean temperature prediction is solving partial differential equations (PDEs), which has immense challenges in terms of parameterization, initial values, and boundary conditions setting. Moreover, the existing machine learning models for ocean temperature prediction have “black box” problems, and the influence of external dynamic factors is not considered. Moreover, it is hard to judge whether the model satisfies certain physical laws. In this paper, we propose a physics-guided spatio-temporal data analysis model based on the widely used ConvLSTM model to achieve long-term ocean temperature prediction and adopt two schemes to train the model in vector output and multiple parallel input and multi-step output. Meanwhile, considering the spatio-temporal correlation, physical information such as oceanic stable stratification is introduced to guide the model training. We evaluate our proposed approach on several popular deep learning models in different timesteps and data volumes in the northern coast of the South China Sea, where the frequent occurrence of internal waves leads to an intensity trend of a local transformation of sea temperature. The results show higher prediction accuracy compared with the traditional LSTM, and ConvLSTM models, and the introduction of physical laws can improve data utilization while enhancing the physical consistency of the model.

High-fidelity Database-free Deep Learning Reconstruction for Real-time Cine Cardiac MRI.

Real-time cine cardiac MRI provides an ECG-free free-breathing alternative to clinical gold-standard ECG-gated breath-hold segmented cine MRI for evaluation of heart function. Real-time cine MRI data acquisition during free breathing snapshot imaging enables imaging of patient cohorts that cannot be imaged with segmented or breath-hold acquisitions, but requires rapid imaging to achieve sufficient spatial-temporal resolutions. However, at high acceleration rates, conventional reconstruction techniques suffer from residual aliasing and temporal blurring, including advanced methods such as compressed sensing with radial trajectories. Recently, deep learning (DL) reconstruction has emerged as a powerful tool in MRI. However, its utility for free-breathing real-time cine MRI has been limited, as database-learning of spatio-temporal correlations with varying breathing and cardiac motion patterns across subjects has been challenging. Zero-shot self-supervised physics-guided deep learning (PG-DL) reconstruction has been proposed to overcome such challenges of database training by enabling subject-specific training. In this work, we adapt zero-shot PG-DL for real-time cine MRI with a spatio-temporal regularization. We compare our method to TGRAPPA, locally low-rank (LLR) regularized reconstruction and database-trained PG-DL reconstruction, both for retrospectively and prospectively accelerated datasets. Results on highly accelerated real-time Cartesian cine MRI show that the proposed method outperforms other reconstruction methods, both visibly in terms of noise and aliasing, and quantitatively.

A Space-Time Partial Differential Equation Based Physics-Guided Neural Network for Sea Surface Temperature Prediction

Sea surface temperature (SST) prediction has attracted increasing attention, due to its crucial role in understanding the Earth’s climate and ocean system. Existing SST prediction methods are typically based on either physics-based numerical methods or data-driven methods. Physics-based numerical methods rely on marine physics equations and have stable and explicable outputs, while data-driven methods are flexible in adapting to data and are capable of detecting unexpected patterns. We believe that these two types of method are complementary to each other, and their combination can potentially achieve better performances. In this paper, a space-time partial differential equation (PDE) is employed to form a novel physics-based deep learning framework, named the space-time PDE-guided neural network (STPDE-Net), to predict daily SST. Comprehensive experiments for SST prediction were conducted, and the results proved that our method could outperform the traditional finite-difference forecast method and several state-of-the-art deep learning and physics-guided deep learning methods.