SEARCH · Search NASA
Results for “Jacobian matrices”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Impact of Reordering on the LU Factorization Performance of Bordered Block-Diagonal Sparse Matrix
Power engineers rely on computer-based simulation tools to assess grid performance and ensure security. At the core of these tools are solvers for sparse linear equations. When transformed into a bordered block-diagonal (BBD) structure, part of the sparse linear equation solving can be parallelized. This work focuses on using the Schur-complement-based method for LU factorization on BBD matrices, specifically, Jacobian matrices from large-scale systems. Our findings show that the natural ordering method outperforms the default ordering method in computational performance for each block of the BBD matrix. This observation is validated using synthetic 25k-bus and 70k-bus cases, showing a speedup of up to 38% when using natural ordering without permutation. Additionally, the impact of the number of partitions is studied, and the result shows that computational performance improves with more, smaller partitions in the BBD matrices.
A projection-based analytical Jacobian framework for chemical kinetics applications
A major challenge in simulating complex combustion systems with detailed chemical kinetic models is the cost of integrating the chemical source terms, often done using stiff ODE solvers that require frequent Jacobian evaluations. Using analytically derived Jacobian matrices instead of divided-difference-based numerical Jacobian approximations can significantly reduce the associated computational cost. However, ambiguities arise in the formulation of analytical Jacobians because the chemical state of the system, or state vector, can be expressed in multiple ways, involving variables that are typically not independent from one another. Here, in this work, the consequences of those ambiguities on practical calculations are characterized in detail, and a generalized, projection-based framework is proposed as a mitigation strategy. Performances are assessed in a series of test cases involving a variety of configurations and numerical solution approaches. Results show that with proper treatment, commonly used analytical Jacobian formulations can be considered as equivalent for practical purposes, thereby alleviating concerns that the state vector chosen to express the governing equations and corresponding analytical Jacobian may significantly impact the accuracy of the simulations.
A low rank approach to automatic differentiation.
This manuscript introduces a new approach for increasing the efficiency of automatic differentiation (AD) computations for estimating the first order derivatives comprising the Jacobian matrix of a complex large-scale computational model. The objective is to approximate the entire Jacobian matrix with minimized computational and storage resources. This is achieved by finding low rank approximations to a Jacobian matrix via the Efficient Subspace Method (ESM). Low rank Jacobian matrices arise in many of today's important scientific and engineering problems, e.g. nuclear reactor calculations, weather climate modeling, geophysical applications, etc. A low rank approximation replaces the original Jacobian matrix J (whose size is dictated by the size of the input and output data streams) with matrices of much smaller dimensions (determined by the numerical rank of the Jacobian matrix). This process reveals the rank of the Jacobian matrix and can be obtained by ESM via a series of r randomized matrix-vector products of the form: Jq, and J{sup T} {omega} which can be evaluated by the AD forward and reverse modes, respectively.
Marker ReDistancing/Level Set Method for High-Fidelity Implicit Interface Tracking
A hybrid of the Front-Tracking (FT) and the Level-Set (LS) methods is introduced, combining advantages and removing drawbacks of both methods. The kinematics of the interface is treated in a Lagrangian (FT) manner, by tracking markers placed at the interface. The markers are not connected – instead, the interface topology is resolved in an Eulerian (LS) framework, by wrapping a signed distance function around Lagrangian markers each time the markers move. For accuracy and efficiency, we have developed a high-order “anchoring” algorithm and an implicit PDE-based re-distancing. We have demonstrated that the method is 3rd-order accurate in space, near the markers, and therefore 1st-order convergent in curvature; in contrast to traditional PDE-based re-initialization algorithms, which tend to slightly relocate the zero Level Set and can be shown to be non-convergent in curvature. The implicit pseudo-time discretization of the re-distancing equation is implemented within the Jacobian-Free Newton Krylov (JFNK) framework combined with ILU(k) preconditioning. We have demonstrated that the steady-state solutions in pseudo-time can be achieved very efficiently, with iterations (CFL ), in contrast to the explicit re-distancing which requires 100s of iterations with CFL . The most cost-effective algorithm is found to be a hybrid of explicit and implicit discretizations, in which we apply first 10-15 iterations with explicit discretization (to bring the initial guess to the ball of convergence for the Newton’s method) and then finishing with 2-3 implicit steps, bringing the re-distancing equation to a complete steady-state. The eigenscopy of the JFNK-ILU(k) demonstrates the efficiency of the ILU(k) preconditioner, which effectively cluster eigenvalues of the otherwise extremely ill-conditioned Jacobian matrices, thereby enabling the Krylov (GMRES) method to converge with iterations, with only a few levels of ILU fill-ins. Importantly, due to the Level Set localization, the bandwidth of the Jacobian matrix is nearly constant, and the ILU preconditioning scales as , which implies efficiency and good scalability of the overall algorithm. The numerical examples include the well-established tests for interface kinematics under translational, rotational and tearing/stretching motion. We have shown that the mass conservation is not an issue anymore, as demonstrated using the Rider&Kothe’s time-reversed tests with extreme deformation. We are able to stretch interface structures to the under-resolved/subgrid (on the chosen Eulerian mesh) scales, and recover them back without any change in shape/loss of mass.
Robust Iterative Method for Symmetric Quantum Signal Processing in All Parameter Regimes
Here, this paper addresses the problem of solving nonlinear systems in the context of symmetric quantum signal processing (QSP), a powerful technique for implementing matrix functions on quantum computers. Symmetric QSP focuses on representing target polynomials as products of matrices in SU(2) that possess symmetry properties. We present a novel Newton’s method tailored for efficiently solving the nonlinear system involved in determining the phase factors within the symmetric QSP framework. Our method demonstrates rapid and robust convergence in all parameter regimes, including the challenging scenario with ill-conditioned Jacobian matrices, using standard double precision arithmetic operations. For instance, solving symmetric QSP for a highly oscillatory target function α cos(1000x) (polynomial degree ≈ 1433) takes 6 iterations to converge to machine precision when α = 0.9, and the number of iterations only increases to 18 iterations when α = 1 – 10 -9 with a highly ill-conditioned Jacobian matrix. Leveraging the matrix product state structure of symmetric QSP, the computation of the Jacobian matrix incurs a computational cost comparable to a single function evaluation. Moreover, we introduce a reformulation of symmetric QSP using real-number arithmetics, further enhancing the method’s efficiency. Extensive numerical tests validate the effectiveness and robustness of our approach, which has been implemented in the QSPPACK software package.
Target Formulation and Construction in Mesh Quality Improvement
In the Target-matrix Optimization Paradigm (TMOP), it’s long been understood that one must create a set of target matrices before the mesh can be optimized. But there is still no general method to create correct, effective targets in response to a specific mesh quality improvement goal. The TMOP literature describes how certain sets of target matrices can be used to control the shape or size of mesh elements, but those examples address only a fraction of the problems that can occur in mesh quality improvement and were not derived from a general framework for target matrix construction. In this work, a general method of target construction is introduced based on an independent set of geometric parameters which are intrinsic to the Jacobian matrices upon which TMOP is based. The parameters enable a systematic approach to target definition and construction. The approach entails two parts. The first part defines correspondences between available raw data (stuff about the mesh and/or the physical solution) and intermediate data (e.g., a field of error estimates). Once the correspondences are established, the raw data is processed into intermediate field data existing on mesh sample points. The second part is to create a model that represents the values of the geometric target parameters as functions of the intermediate data. The model is then tested numerically to establish model constants and effectiveness. This systematic approach to target construction is illustrated in a set of examples to show how it can be applied to common problems in mesh optimization such as equidistribution of geometric properties, preservation of existing good quality, and adaptation of the mesh to the solution. The result is a systematic method of target construction for TMOP which can be applied to a wide variety of planar and volume mesh quality improvement tasks.
Bison Robustness and Performance Improvements
In last year’s Bison robustness report, the authors demonstrated that improving the Jacobian matrix can drastically increase solution convergence rates. The development of an automatic differentiation (AD) capability in the MOOSE framework has created the possibility of having exact Jacobian matrices for all of our material models. A large focus in this year’s report is the application of AD to MOOSE physics modules, such as the tensor mechanics module, and the application to Bison fuel and cladding material models. A second main focus in this year’s report is the investigation of a set of algorithmic solver changes to improve the robustness and performance of Bison LWR simulations. Beyond providing increased solver robustness, the ability to solve strongly coupled multiphysics problems, and solving large deformation problems with ease, these automatically generated perfect Jacobians also drastically reduce development time for new models. In models converted to AD, Jacobian computation made up the majority of the code base. With this code removed, both readability and maintainability of the MOOSE/Bison code base are improved. The work documented here significantly improved the robustness of the Bison LWR assessment case suite. Through algorithmic changes in solver infrastructure, such as the application of predictors and improvements in timestepping, tangible improvements in performance were observed. These improvements are documented using a new standard set of metrics that are collected in all assessment cases, and a suite of statistical analysis tools developed for this report.
Quantum Dynamical Behaviour in Complex Systems - A Semiclassical Approach
One of the biggest challenges in Chemical Dynamics is describing the behavior of complex systems accurately. Classical MD simulations have evolved to a point where calculations involving thousands of atoms are routinely carried out. Capturing coherence, tunneling and other such quantum effects for these systems, however, has proven considerably harder. Semiclassical methods such as the Initial Value Representation (SC-IVR) provide a practical way to include quantum effects while still utilizing only classical trajectory information. For smaller systems, this method has been proven to be most effective, encouraging the hope that it can be extended to deal with a large number of degrees of freedom. Several variations upon the original idea of the SCIVR have been developed to help make these larger calculations more tractable; these range from the simplest, classical limit form, the Linearized IVR (LSC-IVR) to the quantum limit form, the Exact Forward-Backward version (EFB-IVR). In this thesis a method to tune between these limits is described which allows us to choose exactly which degrees of freedom we wish to treat in a more quantum mechanical fashion and to what extent. This formulation is called the Tuning IVR (TIVR). We further describe methodology being developed to evaluate the prefactor term that appears in the IVR formalism. The regular prefactor is composed of the Monodromy matrices (jacobians of the transformation from initial to finial coordinates and momenta) which are time evolved using the Hessian. Standard MD simulations require the potential surfaces and their gradients, but very rarely is there any information on the second derivative. We would like to be able to carry out the SC-IVR calculation without this information too. With this in mind a finite difference scheme to obtain the Hessian on-the-fly is proposed. Wealso apply the IVR formalism to a few problems of current interest. A method to obtain energy eigenvalues accurately for complex systems is described. We proposed the use of a semiclassical correction term to a preliminary quantum calculation using, for instance, a variational approach. This allows us to increase the accuracy significantly. Modeling Nonadiabatic dynamics has always been a challenge to classical simulations because the multi-state nature of the dynamics cannot be described accurately by the time evolution on a single average surface, as is the classical approach. We show that using the Meyer-Miller-Stock-Thoss (MMST) representation of the exact vibronic Hamiltonian in combination with the IVR allows us to accurately describe dynamics where the non Born-Oppenheimer regime. One final problem that we address is that of extending this method to the long time regime. We propose the use of a time independent sampling function in the Monte Carlo integration over the phase space of initial trajectory conditions. This allows us to better choose the regions of importance at the various points in time; by using more trajectories in the important regions, we show that the integration can be converged much easier. An algorithm based loosely on the methods of Diffusion Monte Carlo is developed that allows us to carry out this time dependent sampling in a most efficient manner.
The compressed state Kalman filter for nonlinear state estimation: Application to large-scale reservoir monitoring
Reservoir monitoring aims to provide snapshots of reservoir conditions and their uncertainties to assist operation management and risk analysis. These snapshots may contain millions of state variables, e.g., pressures and saturations, which can be estimated by assimilating data in real time using the Kalman filter (KF). However, the KF has a computational cost that scales quadratically with the number of unknowns, m, due to the cost of computing and storing the covariance and Jacobian matrices, along with their prod-ucts. The compressed state Kalman filter (CSKF) adapts the KF for solving large-scale monitoring problems. The CSKF uses N preselected orthogonal bases to compute an accurate rank-N approximation of the covari-ance that is close to the optimal spectral approximation given by SVD. The CSKF has a computational cost that scales linearly in m and uses an efficient matrix-free approach that propagates uncertainties using N + 1 forward model evaluations, where N << m. Here in this paper we present a generalized CSKF algorithm for nonlin-ear state estimation problems such as CO 2 monitoring. For simultaneous estimation of multiple types of state variables, the algorithm allows selecting bases that represent the variability of each state type. Through synthetic numerical experiments of CO 2 monitoring, we show that the CSKF can reproduce the Kal-man gain accurately even for large compression ratios (m/N). For a given computational cost, the CSKF uses a robust and flexible compression scheme that gives more reliable uncertainty estimates than the ensemble Kalman filter, which may display loss of ensemble variability leading to suboptimal uncertainty estimates.
Rapid multiphase-field model development using a modular free energy based approach with automatic differentiation in MOOSE/MARMOT
In this paper, we present a novel rapid phase-field model development capability using a modular free energy based approach in the finite element based MOOSE framework. The phase-field equations are implemented in a general form as separate code form the model specific data such as the thermodynamic free energy density and mobility functions. This isolates researchers from complicated code and allows them to focus on implementing new material models. In addition, using a native symbolic differentiation algorithm, all required derivatives of the free energy density are automatically determined, removing sources for potential human error, and guaranteeing optimally preconditioned equation systems through fully populated Jacobian matrices. Free energy terms contributing to a phase-field model are abstracted into self contained objects that can be combined at will at simulation run time. Combining multiple chemical and mechanical free energy contributions allows the construction of coupled phase-field, mechanics, and multiphase models. Through just-in-time compilation, we greatly reduce the computational time required to evaluate the differentiated expressions. Lastly, we demonstrate the new capability on a variety of example simulations.
Simulation-driven optimization of high-order meshes in ALE hydrodynamics
Here we propose tools for high-order mesh optimization and demonstrate their benefits in the context of multi-material Arbitrary Lagrangian-Eulerian (ALE) compressible shock hydrodynamic applications. The mesh optimization process is driven by information provided by the simulation which uses the optimized mesh, such as shock positions, material regions, known error estimates, etc. These simulation features are usually represented discretely, for instance, as finite element functions on the Lagrangian mesh. The discrete nature of the input is critical for the practical applicability of the algorithms we propose and distinguishes this work from approaches that strictly require analytical information. Our methods are based on node movement through a high-order extension of the Target-Matrix Optimization Paradigm (TMOP). The proposed formulation is fully algebraic and relies only on local Jacobian matrices, so it is applicable to all types of mesh elements, in 2D and 3D, and any order of the mesh. We discuss the notions of constructing adaptive target matrices and obtaining their derivatives, reconstructing discrete data in intermediate meshes, node limiting that enables improvement of global mesh quality while preserving space-dependent local mesh features, and appropriate normalization of the objective function. The adaptivity methods are combined with automatic ALE triggers that can provide robustness of the mesh evolution and avoid excessive remap procedures. The benefits of the new high-order TMOP technology are illustrated on several simulations performed in the high-order ALE application BLAST.
Fully-Implicit Orthogonal Reconstructed Discontinuous Galerkin for Fluid Dynamics with Phase Change
A new reconstructed Discontinuous Galerkin (rDG) method, based on orthogonal basis/test functions, is developed for fluid flows on unstructured meshes. Orthogonality of basis functions is essential for enabling robust and efficient fully-implicit Newton-Krylov based time integration. The method is designed for generic partial differential equations, including transient, hyperbolic, parabolic or elliptic operators, which are attributed to many multiphysics problems. We demonstrate the method’s capabilities for solving compressible fluid-solid systems (in the low Mach number limit), with phase change (melting/solidification), as motivated by applications in Additive Manufacturing (AM). We focus on the method’s accuracy (in both space and time), as well as robustness and solvability of the system of linear equations involved in the linearization steps of Newton-based methods. The performance of the developed method is investigated for highly-stiff problems with melting/solidification, emphasizing the advantages from tight coupling of mass, momentum and energy conservation equations, as well as orthogonality of basis functions, which leads to better conditioning of the underlying (approximate) Jacobian matrices, and rapid convergence of the Krylov-based linear solver.
3-D decoupled inversion of complex conductivity data in the real number domain
Complex conductivity inversion, aslo called spectral induced polarization inversion, involves estimating the frequency dependent complex electrical conductivity distribution of the subsurface. The superior diagnostic capabilities provided by complex conductivity spectra have driven advancements in mechanistic understanding of complex conductivity as well as modelling and inversion appraoches over the past several decades. In this work, we demonstrate the theory and application for an approach to three-dimensional modeling and inversion of complex conductivity data in the real number domain. Beginning from first principles, we demonstrate how the equations for the real and imaginary components of the complex potential may be decoupled. This leads to a description of the real and imaginary source current terms, and a corresponding assessment of error arising from an assumption necessary complete the decoupled modeling. We show that for most earth materials, which exhibit relatively small phases (e.g. less than 0.2 radians) in complex conductivity, these errors become insignificant. For higher phase materials, the errors may be quantified and corrected through an iterative procedure. We demonstrate the accuracy of numerical forward solutions by direct comparison to corresponding analytic solutions. We demonstrate the inversion using both synthetic and field examples with data collected over a waste infiltration trench, at frequencies ranging from 0.5 to 7.5 Hz. In addition to insight provided by the decoupled equations, we see three primary advantages of the decoupled inversion in comparison to fully coupled inversion in complex number domain. First, memory requirements are reduced by a factor of two because it is unnecessary to simultaneously store both the real and complex components and associated Jacobian matrices. Second, data noise is specified separately for the real and imaginary components of potential (or magnitude and phase), which removes the ambiguity in data misfit residuals that exists in the complex number domain, thereby enabling the inversion to appropriately fit the data. Final, except for the source current terms, the modeling and inversion algorithms are equivalent to the direct current electrical resistivity tomography counterpart. In conclusion, this enables direct application of advancements and approaches developed originally for electrical resistivity tomography.
Extracting and Interpreting Electrochemical Impedance Spectra (EIS) from Physics-Based Models of Lithium-Ion Batteries
This paper implements a highly efficient algorithm to extract electrochemical impedance spectra (EIS) from physics-based battery models (e.g., a P2D model). The mathematical approach is different from how EIS is practiced experimentally. Experimentally, the voltage (current) is harmonically perturbed over a wide range of frequencies and the amplitude and phase shift of the corresponding current (voltage) is measured. The experimental approach can be implemented in simulation software, but is computationally expensive. The approach here is to determine locally linear state-space models from the full physical model. The four Jacobian matrices that are the basis of the state-space models can be derived by numerical differentiation of the physical model. The EIS is then extracted from the state-space model using computationally efficient matrix-manipulation techniques. The algorithm can evaluate the full EIS at an instant in time during a transient, independent of whether the battery is in a stationary state. The approach is also able to separate the full-cell impedance to evaluate partial EIS, such as for a battery anode alone. Although such partial EIS is difficult to measure experimentally, the partial EIS provides valuable insights in interpreting the full-cell EIS.
TChem
The TChem toolkit is a software library that enables numerical simulations using complex chemistry and facilitates the analysis of detailed kinetic models. The toolkit provide capabilities for thermodynamic properties based on NASA polynomials and species production and consumption rates. It incorporates methods that can selectively modify reaction parameters for sensitivity analysis and uncertainty quantification. The library also contains several functions that provide analytically computed Jacobian matrices necessary for the efficient time advancement and analysis of detailed kinetic models.
TChem - A Software Toolkit for the Analysis of Complex Kinetic Models
The TChem toolkit is a software library that enables numerical simulations using complex chemistry and facilitates the analysis of detailed kinetic models. The toolkit provide capabilities for thermodynamic properties based on NASA polynomials and species production/consumption rates. It incorporates methods that can selectively modify reaction parameters for sensitivity analysis. The library contains several functions that provide analytically computed Jacobian matrices necessary for the efficient time advancement and analysis of detailed kinetic models.
Fully-Implicit Orthogonal Reconstructed Discontinuous Petrov-Galerkin Method for Multiphysics Problems
This document is focussed on the development of reconstructed discontinuous Galerkin (RDG P n P m ) method, based on orthogonal basis functions. Orthogonality of basis functions is essential for enabling robust and efficient fully-implicit Newton-Krylov based time discretization. The method is designed for generic partial differential equations, including transient hyperbolic, parabolic and/or elliptic operators, which are attributed to many multiphysics problems. Our driving application of interest is additive manufacturing, which requires simulations of fluid-solid-gas systems, with compressibility effects and phase change (melting/ solidification). Thus, we demonstrate the method capabilities for solving nonlinear heat conduction equation coupled with multi-material Navier-Stokes based compressible fluid (in low Mach number limit) systems. We focus our attention to the method accuracy (in both time and space), as well as solvability of linear algebra involved in linear steps of the Newton-based solver. We demonstrate the accuracy and efficacy of the method, emphasizing the advantages from the orthogonality of basis functions, which makes better conditioning of underlying (approximate) Jacobian matrices, and rapid convergence of Krylov methods. iii