BiVi-GAN: Bivariate Vibration GAN.

In the domain of prognosis and health management (PHM) for rotating machinery, the criticality of ensuring equipment reliability cannot be overstated. With developments in artificial intelligence (AI) and deep learning, there have been numerous attempts to use those methodologies in PHM. However, there are challenges to applying them in practice because they require huge amounts of data. This study explores a novel approach to augment vibration data-a primary component in traditional PHM methodologies-using a specialized generative model. Recognizing the limitations of deep learning models, which often fail to capture the intrinsic physical characteristics vital for vibration analysis, we introduce the bivariate vibration generative adversarial networks (BiVi-GAN) model. BiVi-GAN incorporates elements of a physics-informed neural network (PINN), emphasizing the specific vibration characteristics of rotating machinery. We integrate two types of physical information into our model: order analysis and cross-wavelet transform, which are crucial for dissecting the vibration characteristics of such machinery. Experimental findings show the effectiveness of our proposed model. With the incorporation of physics information (PI) input and PI loss, the BiVi-GAN showed a 70% performance improvement in terms of JS divergence compared with the baseline biwavelet-GAN model. This study maintains the potential and efficacy of complementary domain-specific insights with data-driven AI models for more robust and accurate outcomes in PHM.

Constructing Physics-Informed Neural Networks with Architecture Based on Analytical Modification of Numerical Methods by Solving the Problem of Modelling Processes in a Chemical Reactor.

A novel type of neural network with an architecture based on physics is proposed. The network structure builds on a body of analytical modifications of classical numerical methods. A feature of the constructed neural networks is defining parameters of the governing equations as trainable parameters. Constructing the network is carried out in three stages. In the first step, a neural network solution to an equation corresponding to a numerical scheme is constructed. It allows for forming an initial low-fidelity neural network solution to the original problem. At the second stage, the network with physics-based architecture (PBA) is further trained to solve the differential equation by minimising the loss function, as is typical in works devoted to physics-informed neural networks (PINNs). In the third stage, the physics-informed neural network with architecture based on physics (PBA-PINN) is trained on high-fidelity sensor data, parameters are identified, or another task of interest is solved. This approach makes it possible to solve insufficiently studied PINN problems: selecting neural network architecture and successfully initialising network weights corresponding to the problem being solved that ensure rapid convergence to the loss function minimum. It is advisable to use the devised PBA-PINNs in the problems of surrogate modelling and modelling real objects with multi-fidelity data. The effectiveness of the approach proposed is demonstrated using the problem of modelling processes in a chemical reactor. Experiments show that subsequent retraining of the initial low-fidelity PBA model based on a few high-accuracy data leads to the achievement of relatively high accuracy.

Predicting the Early-Age Time-Dependent Behaviors of a Prestressed Concrete Beam by Using Physics-Informed Neural Network.

This paper proposes a physics-informed neural network (PINN) for predicting the early-age time-dependent behaviors of prestressed concrete beams. The PINN utilizes deep neural networks to learn the time-dependent coupling among the effective prestress force and the several factors that affect the time-dependent behavior of the beam, such as concrete creep and shrinkage, tendon relaxation, and changes in concrete elastic modulus. Unlike traditional numerical algorithms such as the finite difference method, the PINN directly solves the integro-differential equation without the need for discretization, offering an efficient and accurate solution. Considering the trade-off between solution accuracy and the computing cost, optimal hyperparameter combinations are determined for the PINN. The proposed PINN is verified through the comparison to the numerical results from the finite difference method for two representative cross sections of PSC beams.

Variable-Order Fractional Models for Wall-Bounded Turbulent Flows.

Modeling of wall-bounded turbulent flows is still an open problem in classical physics, with relatively slow progress in the last few decades beyond the log law, which only describes the intermediate region in wall-bounded turbulence, i.e., 30-50 y+ to 0.1-0.2 R+ in a pipe of radius R. Here, we propose a fundamentally new approach based on fractional calculus to model the entire mean velocity profile from the wall to the centerline of the pipe. Specifically, we represent the Reynolds stresses with a non-local fractional derivative of variable-order that decays with the distance from the wall. Surprisingly, we find that this variable fractional order has a universal form for all Reynolds numbers and for three different flow types, i.e., channel flow, Couette flow, and pipe flow. We first use existing databases from direct numerical simulations (DNSs) to lean the variable-order function and subsequently we test it against other DNS data and experimental measurements, including the Princeton superpipe experiments. Taken together, our findings reveal the continuous change in rate of turbulent diffusion from the wall as well as the strong nonlocality of turbulent interactions that intensify away from the wall. Moreover, we propose alternative formulations, including a divergence variable fractional (two-sided) model for turbulent flows. The total shear stress is represented by a two-sided symmetric variable fractional derivative. The numerical results show that this formulation can lead to smooth fractional-order profiles in the whole domain. This new model improves the one-sided model, which is considered in the half domain (wall to centerline) only. We use a finite difference method for solving the inverse problem, but we also introduce the fractional physics-informed neural network (fPINN) for solving the inverse and forward problems much more efficiently. In addition to the aforementioned fully-developed flows, we model turbulent boundary layers and discuss how the streamwise variation affects the universal curve.

Tissue-specific regulation of alternative polyadenylation represses expression of a neuronal ankyrin isoform in C. elegans epidermal development.

Differential mRNA polyadenylation plays an important role in shaping the neuronal transcriptome. In C. elegans, several ankyrin isoforms are produced from the unc-44 locus through alternative polyadenylation. Here, we identify a key role for an intronic polyadenylation site (PAS) in temporal- and tissue-specific regulation of UNC-44/ankyrin isoforms. Removing an intronic PAS results in ectopic expression of the neuronal ankyrin isoform in non-neural tissues. This mis-expression underlies epidermal developmental defects in mutants of the conserved tumor suppressor death-associated protein kinase dapk-1 We have previously reported that the use of this intronic PAS depends on the nuclear polyadenylation factor SYDN-1, which inhibits the RNA polymerase II CTD phosphatase SSUP-72. Consistent with this, loss of sydn-1 blocks ectopic expression of neuronal ankyrin and suppresses epidermal morphology defects of dapk-1 These effects of sydn-1 are mediated by ssup-72 autonomously in the epidermis. We also show that a peptidyl-prolyl isomerase PINN-1 antagonizes SYDN-1 in the spatiotemporal control of neuronal ankyrin isoform. Moreover, the nuclear localization of PINN-1 is altered in dapk-1 mutants. Our data reveal that tissue and stage-specific expression of ankyrin isoforms relies on differential activity of positive and negative regulators of alternative polyadenylation.

A Compact Memristor Model Based on Physics-Informed Neural Networks.

Memristor devices have diverse physical models depending on their structure. In addition, the physical properties of memristors are described using complex differential equations. Therefore, it is necessary to integrate the various models of memristor into an unified physics-based model. In this paper, we propose a physics-informed neural network (PINN)-based compact memristor model. PINNs can solve complex differential equations intuitively and with ease. This methodology is used to conduct memristor physical analysis. The weight and bias extracted from the PINN are implemented in a Verilog-A circuit simulator to predict memristor device characteristics. The accuracy of the proposed model is verified using two memristor devices. The results show that PINNs can be used to extensively integrate memristor device models.

Physics-informed NN-based adaptive backstepping terminal sliding mode control of buck converter for PEM electrolyzer.

This paper proposes an advanced control approach to controlling a DC-DC buck converter for a proton exchange membrane (PEM) electrolyzer within the framework of a direct current (DC) microgrid. The proposed adaptive backstepping terminal sliding mode control (ABTSMC) leverages a physics-informed neural network (PINN) to accurately estimate and compensate for system uncertainty. The composite controller achieves finite-time convergence of the tracking error by combining backstepping control and terminal sliding mode control (TSMC). The proposed PINN aims to optimize the unconstrained parameters by utilizing observed training points from the solution, ensuring the network accurately interpolates a limited portion of the solution. The efficacy of the proposed hybrid control method is validated using a hardware-in-the-loop (HIL) implementation under various test settings, ensuring the preservation of the actual performance of the PEM electrolyzer during testing. The experimental verification results demonstrate that the proposed control method exhibits greater benefits, such as a faster dynamic response and greater robustness against parameter uncertainties than improved sliding mode-based controllers. In situations where operational conditions change, a rapid response is achieved within a mere 0.025s of settling time, exhibiting a minimal percentage overshoot of about 17.5% and presenting minimal fluctuations.

Enforcing Dirichlet boundary conditions in physics-informed neural networks and variational physics-informed neural networks.

In this paper, we present and compare four methods to enforce Dirichlet boundary conditions in Physics-Informed Neural Networks (PINNs) and Variational Physics-Informed Neural Networks (VPINNs). Such conditions are usually imposed by adding penalization terms in the loss function and properly choosing the corresponding scaling coefficients; however, in practice, this requires an expensive tuning phase. We show through several numerical tests that modifying the output of the neural network to exactly match the prescribed values leads to more efficient and accurate solvers. The best results are achieved by exactly enforcing the Dirichlet boundary conditions by means of an approximate distance function. We also show that variationally imposing the Dirichlet boundary conditions via Nitsche's method leads to suboptimal solvers.

Effective data sampling strategies and boundary condition constraints of physics-informed neural networks for identifying material properties in solid mechanics.

Material identification is critical for understanding the relationship between mechanical properties and the associated mechanical functions. However, material identification is a challenging task, especially when the characteristic of the material is highly nonlinear in nature, as is common in biological tissue. In this work, we identify unknown material properties in continuum solid mechanics via physics-informed neural networks (PINNs). To improve the accuracy and efficiency of PINNs, we develop efficient strategies to nonuniformly sample observational data. We also investigate different approaches to enforce Dirichlet-type boundary conditions (BCs) as soft or hard constraints. Finally, we apply the proposed methods to a diverse set of time-dependent and time-independent solid mechanic examples that span linear elastic and hyperelastic material space. The estimated material parameters achieve relative errors of less than 1%. As such, this work is relevant to diverse applications, including optimizing structural integrity and developing novel materials.

Physics Informed Neural Networks (PINN) for Low Snr Magnetic Resonance Electrical Properties Tomography (MREPT).

Electrical properties (EPs) of tissues facilitate early detection of cancerous tissues. Magnetic resonance electrical properties tomography (MREPT) is a technique to non-invasively probe the EPs of tissues from MRI measurements. Most MREPT methods rely on numerical differentiation (ND) to solve partial differential Equations (PDEs) to reconstruct the EPs. However, they are not practical for clinical data because ND is noise sensitive and the MRI measurements for MREPT are noisy in nature. Recently, Physics informed neural networks (PINNs) have been introduced to solve PDEs by substituting ND with automatic differentiation (AD). To the best of our knowledge, it has not been applied to MREPT due to the challenges in using PINN on MREPT as (i) a PINN requires part of ground-truth EPs as collocation points to optimize the network's AD, (ii) the noisy input data disrupts the optimization of PINNs despite the noise-filtering nature of NNs and additional denoising processes. In this work, we propose a PINN-MREPT model based on a canonical analytic MREPT model. A reference padding layer with known EPs was added to surround the region of interest for providing additive collocation points. Moreover, an optimizable diffusion coefficient was embedded in the analytic MREPT model used in the PINN-MREPT. The noise robustness of the proposed PINN-MREPT for single-sample reconstruction was tested by using numerical phantoms of human brain with extra tumor-like tissues at different noise levels. The results of numerical experiments show that PINN-MREPT outperforms two typical numerical MREPT methods in terms of reconstruction accuracy, sensitivity to the extra tissues, and the correlations of line profiles in the regions of interest. The advantage of the PINN-MREPT is shown by the results of an experiment on phantom measurement, too. Moreover, it is found that the diffusion term plays an important role to achieve a noise-robust PINN-MREPT. This is an important step moving forward to a clinical application of MREPT.

Dr. Vivian Pinn: a woman pioneer & leader.

The Women's Health Institute in collaboration with the Journal of Women's Midlife Health hosted a national roundtable with Dr. Vivian Pinn via Zoom to honor her for her achievements in the areas of women's health, wellness, and research. The panelists included Gloria A. Bachmann, MD, MMS, Sherri-Ann Burnett-Bowie, MD, MPH, and Sioban D. Harlow, PhD.

The Old and the New: Can Physics-Informed Deep-Learning Replace Traditional Linear Solvers?

Physics-Informed Neural Networks (PINN) are neural networks encoding the problem governing equations, such as Partial Differential Equations (PDE), as a part of the neural network. PINNs have emerged as a new essential tool to solve various challenging problems, including computing linear systems arising from PDEs, a task for which several traditional methods exist. In this work, we focus first on evaluating the potential of PINNs as linear solvers in the case of the Poisson equation, an omnipresent equation in scientific computing. We characterize PINN linear solvers in terms of accuracy and performance under different network configurations (depth, activation functions, input data set distribution). We highlight the critical role of transfer learning. Our results show that low-frequency components of the solution converge quickly as an effect of the F-principle. In contrast, an accurate solution of the high frequencies requires an exceedingly long time. To address this limitation, we propose integrating PINNs into traditional linear solvers. We show that this integration leads to the development of new solvers whose performance is on par with other high-performance solvers, such as PETSc conjugate gradient linear solvers, in terms of performance and accuracy. Overall, while the accuracy and computational performance are still a limiting factor for the direct use of PINN linear solvers, hybrid strategies combining old traditional linear solver approaches with new emerging deep-learning techniques are among the most promising methods for developing a new class of linear solvers.

EP-PINNs: Cardiac Electrophysiology Characterisation Using Physics-Informed Neural Networks.

Accurately inferring underlying electrophysiological (EP) tissue properties from action potential recordings is expected to be clinically useful in the diagnosis and treatment of arrhythmias such as atrial fibrillation. It is, however, notoriously difficult to perform. We present EP-PINNs (Physics Informed Neural Networks), a novel tool for accurate action potential simulation and EP parameter estimation from sparse amounts of EP data. We demonstrate, using 1D and 2D in silico data, how EP-PINNs are able to reconstruct the spatio-temporal evolution of action potentials, whilst predicting parameters related to action potential duration (APD), excitability and diffusion coefficients. EP-PINNs are additionally able to identify heterogeneities in EP properties, making them potentially useful for the detection of fibrosis and other localised pathology linked to arrhythmias. Finally, we show EP-PINNs effectiveness on biological in vitro preparations, by characterising the effect of anti-arrhythmic drugs on APD using optical mapping data. EP-PINNs are a promising clinical tool for the characterisation and potential treatment guidance of arrhythmias.

Outcomes Following Isolated Posterior Interosseous Nerve Neurectomy: A Systematic Review.

BACKGROUND: Posterior interosseous nerve neurectomies (PINN) are an option in the treatment of chronic dorsal wrist pain. However, the literature describing PINN consists primarily of small case series, and the procedure is typically done as an adjunct treatment; therefore, the outcomes of the PINN itself are not well known. We performed a systematic review of the literature to provide characteristics of patients following a PINN. METHODS: A systematic review of the literature was performed. Papers published in the PubMed database in English on isolated PINN were included. Articles in which a PINN was performed as an adjunct were excluded. Primary outcomes were return to work, patient satisfaction, pain/function scores, wrist range of motion, complications, and pain recurrence. Weighted averages were used to calculate continuous data, whereas categorical data were noted in percentages. RESULTS: The search yielded 427 articles including 6 studies and 135 patients (136 cases). The average age was 43.6 years (range, 17-75), and most patients were female (54.1%). At an average final follow-up of 51 months, 88.9% of patients were able to return to work. After initial improvement, a recurrence of pain occurred in 25.5% of patients at an average of 12.3 months. Excluding recurrence of pain, the complication rate was 0.9%, including 1 reflex sympathetic dystrophy. Overall, 88.4% of patients experienced a subjective improvement and were satisfied with the procedure. CONCLUSIONS: Isolated PINN have shown excellent clinical outcomes, with few patients experiencing recurrent pain at long-term follow-up. PINN can provide relief in patient's chronic wrist pain.

Single-Bundle Anterior Cruciate Ligament Reconstruction with Semitendinosus Tendon Using the PINN-ACL CrossPin System: Minimum 4-Year Follow-up.

PURPOSE: This study evaluated mid-term results of anterior cruciate ligament (ACL) reconstruction using the PINN-ACL CrossPin system that allowed for short graft fixation. MATERIALS AND METHODS: Forty-three patients underwent single-bundle ACL reconstruction with a 4-strand semitendinosus tendon graft using the PINN-ACL CrossPin system. Femoral fixation was done using the PINN-ACL CrossPin system, and the tibial side was fixed with post-tie and a bioabsorbable interference screw. The mean follow-up period was 50 months. Evaluation was done using the Lachman test, pivot-shift test, International Knee Documentation Committee (IKDC) score and grade. Anterior displacement was assessed. RESULTS: There was improvement in the Lachman test and pivot-shift test at final follow-up, form grade II (n=40) or III (n=3) to grade I (n=3) or 0 (n=40) and from grade I (n=20) or II (n=10) to grade I (n=8) or 0 (n=22), respectively. The mean IKDC score was 88.7, and grade A and B were 93.0% at final follow-up. Side-to-side difference was improved from 6.7 mm to 2.1 mm at final follow-up. Complications occurred in 3 patients, a re-ruptured due to trauma at 2 years after surgery and a deep infection and a superficial infection. CONCLUSIONS: The mid-term follow-up results of ACL reconstruction with the PINN-ACL CrossPin system were satisfactory. The PINN-ACL CrossPin can be considered as a useful instrument for short graft fixation.

ACL Reconstruction with Autologous Hamstring Tendon: Comparison of Short Term Clinical Results between Rigid-fix and PINN-ACL Cross Pin.

PURPOSE: To compare the short term clinical results of anterior cruciate ligament (ACL) reconstruction with autologous hamstring tendon between Rigid-fix and PINN-ACL Cross Pin for femoral side fixation. MATERIALS AND METHODS: 127 patients who underwent arthroscopic ACL reconstruction using autologous hamstring tendon and had been followedup for over than one year were enrolled for the present study. Rigid-fix was used in 71 cases (group 1), and PINN-ACL Cross Pin was used in 56 cases (group 2). Clinical and radiological results, operation time, and perioperative complications were compared amongst the two groups. RESULTS: The International Knee Documentation Committee subjective score and Lysholm score were 94 and 95 in group 1 and 87 and 91 in group 2, with no statistical difference (p=0.892, p=0.833), respectively. However, significant difference was observed in one-leg hop test between the two groups (p=0.032). Five cases in group 1 and 40 cases in group 2 were found to be associated with perioperative complications with statistical difference (p<0.0001). CONCLUSIONS: There was no resultant difference between the employment of PINN-ACL Cross Pin and Rigid-fix as femoral graft fixation for ACL reconstruction with hamstring tendon. However, PINN-ACL Cross Pin led to complications with extensive operation times. Hence, it needs further improvement of tools for minimization of complications.