Improving Exploration in Policy Gradient Search: Application to Symbolic Optimization
Explore the source record for details and available documents.
Mathematics and Computing, Computer science↗
SEARCH · Search NASA
Results for “Symbolic optimization applications”
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.
AutoTG: Reinforcement Learning-Based Symbolic Optimization for AI-Assisted Power Converter Design
Power converters are pervasive in modern electronic component design. They can be found in all electronic devices from household appliances and cellphone chargers to vehicles. Currently, designing new circuit topologies is hard because it requires human expertise based on experience and is difficult to automate. However, artificial-intelligence-assisted design can significantly facilitate the development of new power converters and/or improve the final result. Intelligently designed highly efficient power converters can have a significant effect on many important attributes, such as power efficiency, layout size, cost, heat dissemination, energy requirements, etc. We propose Autonomous Topology Generator (AutoTG), a reinforcement-learning-based framework that generates power converter topology candidates based on user specifications, optimized for user preferences. By modeling power converter design as a symbolic optimization problem, we sequentially sample components in an autoregressive manner until new topologies are formed, providing both the topology specification and the sizing (magnitude of each component parameter) of the proposed power converter. Here, we provide an empirical evaluation and show that AutoTG is able to generate varied high-efficiency topologies within component restrictions based on user input and show that previously unknown topologies can be found for further evaluation.
(AI)-based design↗
Multibody for Everybody (M4E): A Symbolic Dynamics Modeling Tool with Applications in Simulation, Control, and Optimization
Developing the analytical model of a multibody system is often the initial step in control and optimization. The analytical model (equations of motion) describes a system’s time evolution under specified forcing conditions. Although developing these equations is easy for simple systems, this process becomes more complex for systems composed of multiple bodies. Deriving equations of motion for complex multibody systems requires specialized expertise in multibody dynamics, is time-consuming, and is susceptible to error. To address this issue, this paper presents an open-source, easy-to-use, systematic framework to derive symbolic equations of motion in both Python and MATLAB using the joint coordinate formulation. This formulation results in a set of ordinary differential equations that use the minimum set of coordinates needed to model a system. The symbolic representation provides better insight into the influence of design parameters on system performance, facilitates sensitivity analysis and parameter studies, and supports direct implementation of control and optimization routines. The tool enables numerical simulation for specified parameter sets, is modular for straightforward integration with other tools and libraries, and allows incorporation of hydrodynamics, mooring, and other external forces. The result is a reproducible, extensible pipeline for modeling, simulation, and design of complex multibody systems. The proposed tool is versatile and can be applied to domains such as robotics, control, and design. In addition, we integrated external libraries that provide capabilities for modeling offshore systems such as underwater robots and marine energy converters.
16 TIDAL AND WAVE POWER↗
Language model-accelerated deep symbolic optimization
Symbolic optimization methods have been used to solve varied challenging and relevant problems such as symbolic regression and neural architecture search. However, the current state of the art typically learns each problem from scratch and is unable to leverage pre-existing knowledge and datasets that are available for many applications. Here, inspired by the similarity between sequence representations learned in natural language processing and the formulation of symbolic optimization as a discrete sequence optimization problem, we propose language model-accelerated deep symbolic optimization (LA-DSO), a method that leverages language models to learn symbolic optimization solutions more efficiently. We demonstrate LA-DSO in two tasks: symbolic regression, which allows us to perform extensive experimentation due to its low computation requirements, and computational antibody optimization, which shows that our proposal accelerates learning in challenging real-world problems.
97 MATHEMATICS AND COMPUTING↗
On the symbolic manipulation and code generation for elasto-plastic material matrices
A computerized procedure for symbolic manipulations and FORTRAN code generation of elastoplastic material matrix for finite element applications is presented. Special emphasis is placed on expression simplifications during intermediate derivations, optimal code generation, and interface with the main program. A systematic procedure is outlined to avoid redundant algebraic manipulations. Symbolic expressions of the derived material stiffness matrix are automatically converted to RATFOR code which is then translated into FORTRAN statements through a preprocessor. To minimize the interface problem with the main program, a template file is prepared so that the translated FORTRAN statements can be merged into the file to form a subroutine (or a submodule). Three constitutive models; namely, von Mises plasticity, the Drucker-Prager model, and a concrete plasticity model, are used as illustrative examples.
Chang, T. Y.↗
Trends in computerized structural analysis and synthesis; Proceedings of the Symposium, Washington, D.C., October 30-November 1, 1978
The subjects considered are related to future directions of structural applications and potential of new computing systems, advances and trends in data management and engineering software development, advances in applied mathematics and symbolic computing, computer-aided instruction and interactive computer graphics, nonlinear analysis, dynamic analysis and transient response, structural synthesis, structural analysis and design systems, advanced structural applications, supercomputers, numerical analysis, and trends in software systems. Attention is given to the reliability and optimality of the finite element method, computerized symbolic manipulation in structural mechanics, a standard computer graphics subroutine package, and a drag method as a finite element mesh generation scheme.
Noor, A. K.↗
On the symbolic manipulation and code generation for elasto-plastic material matrices
A computerized procedure for symbolic manipulations and FORTRAN code generation of an elasto-plastic material matrix for finite element applications is presented. Special emphasis is placed on expression simplifications during intermediate derivations, optimal code generation, and interface with the main program. A systematic procedure is outlined to avoid redundant algebraic manipulations. Symbolic expressions of the derived material stiffness matrix are automatically converted to RATFOR code which is then translated into FORTRAN statements through a preprocessor. To minimize the interface problem with the main program, a template file is prepared so that the translated FORTRAN statements can be merged into the file to form a subroutine (or a submodule). Three constitutive models; namely, von Mises plasticity, Drucker-Prager model, and a concrete plasticity model, are used as illustrative examples.
Chang, T. Y.↗
Design consideration in constructing high performance embedded Knowledge-Based Systems (KBS)
As the hardware trends for artificial intelligence (AI) involve more and more complexity, the process of optimizing the computer system design for a particular problem will also increase in complexity. Space applications of knowledge based systems (KBS) will often require an ability to perform both numerically intensive vector computations and real time symbolic computations. Although parallel machines can theoretically achieve the speeds necessary for most of these problems, if the application itself is not highly parallel, the machine's power cannot be utilized. A scheme is presented which will provide the computer systems engineer with a tool for analyzing machines with various configurations of array, symbolic, scaler, and multiprocessors. High speed networks and interconnections make customized, distributed, intelligent systems feasible for the application of AI in space. The method presented can be used to optimize such AI system configurations and to make comparisons between existing computer systems. It is an open question whether or not, for a given mission requirement, a suitable computer system design can be constructed for any amount of money.
Dalton, Shelly D.↗
Application of Variable Data Rate (VDR) Towards Channel Optimization
Recognizing the vagaries of channel impediments, one way to optimize aggregate channel information throughput is to maintain a constant symbol rate but vary the modulation scheme and/or the codec rate. The CCSDS VCM and ACM standards promulgation relies upon this kind of an approach. We offer a considerably simpler alternative for spacecraft that are not parked in geo-stationary orbit, one that can rely upon conventional spacecraft housekeeping schedules to change spacecraft and ground operations and will minimize the possibility of requiring any spacecraft hardware accommodations to incorporate. We suggest the use of varying the physical symbol rate within the channel to both initiate acquisition earlier in a pass and retain the link longer as the pass tends toward loss of signal. There is nothing new in what we propose, just a recognition of what has been successful in the past and employed in multiple missions. Integrating over the periodicity of orbit repetition, we shall show that any link that is dependent primarily on a varying range from spacecraft to ground only requires a maximum of five symbol rate transitions in order to optimize total information throughput. By applying these symbol rate transitions using almost rigid rules, we anticipate doubling the information throughput for conventional LEO sun-synchronous orbits. We provide other examples as well.
variable data rate↗
Application of Variable Data Rate (VDR) Towards Channel Optimization
Recognizing the vagaries of channel impediments, one way to optimize aggregate channel information throughput is to maintain a constant symbol rate but vary the modulation scheme and/or the codec rate. The CCSDS VCM and ACM standards promulgation relies upon this kind of an approach. We offer a considerably simpler alternative for spacecraft that are not parked in geo-stationary orbit, one that can rely upon conventional spacecraft housekeeping schedules to change spacecraft and ground operations and will minimize the possibility of requiring any spacecraft hardware accommodations to incorporate. We suggest the use of varying the physical symbol rate within the channel to both initiate acquisition earlier in a pass and retain the link longer as the pass tends toward loss of signal. There is nothing new in what we propose, just a recognition of what has been successful in the past and employed in multiple missions. Integrating over the periodicity of orbit repetition, we shall show that any link that is dependent primarily on a varying range from spacecraft to ground only requires a maximum of five symbol rate transitions in order to optimize total information throughput. By applying these symbol rate transitions using almost rigid rules, we anticipate doubling the information throughput for conventional LEO sun-synchronous orbits. We provide other examples as well.
Variable Data Rate↗
Simultaneous Development and Robust Optimization of a Microstructure Dependent Material
Recent microstructure characterization techniques combined with Symbolic Regression(SR)analysis has been proven to generate white box plasticity models well suited for incorporation into FEA software.The current work builds upon those efforts and demonstrates the applicability of Sequential Monte-Carlo (SMC) methods within SR analysis to condense model development and robust optimization into a single, co-dependent process. In this project, SMC methods provide a mechanism through which the observed microstructure features and associated variability can be incorporated into the discovery phase of model development and simultaneously recover approximate parameter distributions through SR analysis. The demonstration utilized a data set consisting of tensile test results from a limited number of sample specimens with corresponding EBSD data from which microstructure features were characterized.The maximum threshold stress model in the Visco-Plastic Self-Consistent (VPSC) code developed by Los Alamos National Laboratories was calibrated using mechanical test data.Synthetic volume elements with statistically equivalent microstructure were generated with DREAM3Dbased on the observed EBSD data. VPSC was used to simulate the corresponding tensile test response for each of the synthetic volume elements. The simulated microstructure and tensile test data was used astraining datafor SMC-SR algorithm and the resulting model was validated with data from the original empirical data set.
Karl Garbrecht↗
Quasi-optimal decoding of linear block codes using soft decision detection
A simple but effective decoding procedure, applicable to any (n,k) linear block code with symbols from GF(q), is described. The technique involves a transformation of the parity check equations which focuses the code's correction power on the soft symbol set while still retaining the capability to correct one symbol error from outside this set. The soft symbol set is defined to be the n-k least reliably detected code symbol positions whose parity check row-spaces are linearly independent. The process generates a number of error vector screening candidates, each a solution to the parity check equations, and the maximum-likelihood candidate is accepted.
Greene, E. P.↗
Baseflow Identification via Explainable AI With Kolmogorov‐Arnold Networks
Abstract Hydrological models often involve constitutive laws that may not be optimal in every application. We propose to replace such laws with the Kolmogorov‐Arnold networks (KANs), a class of neural networks designed to identify symbolic expressions. We demonstrate KAN's potential on the problem of baseflow identification, a notoriously challenging task plagued by significant uncertainty. KAN‐derived functional dependencies of the baseflow components on the aridity index outperform their original counterparts; they demonstrate that water availability, rather than potential evapotranspiration, drives baseflow by constraining actual evapotranspiration under arid conditions. On a test set, they increase the Nash‐Sutcliffe efficiency (NSE) by 65%, decrease the root mean squared error by 29%, and increase the Kling‐Gupta efficiency by 34%. This superior performance is achieved while reducing the number of fitting parameters from three to two. Next, we use data from 378 catchments across the continental United States to refine the water‐balance equation at the mean‐annual scale. The KAN‐derived equations based on the refined water balance outperform both the current aridity index model, with up to a 105% increase in NSE, and the KAN‐derived equations based on the original water balance. While the performance of our model and tree‐based machine learning methods is similar, KANs offer the advantage of simplicity and transparency and require no specific software or computational tools. This case study focuses on the aridity index formulation, but the approach is flexible and transferable to other hydrological processes. Plain Language Summary Equations used in hydrologic model are often suboptimal, resulting in reduced prediction accuracy and efficiency. We implemented Kolmogorov‐Arnold networks (KAN), a machine learning algorithm for deriving symbolic formulations, to estimate groundwater recharge and showed that it outperforms an existing state‐of‐the‐art semi‐empirical formulation. In hydrology, Nash‐Sutcliffe efficiency (NSE), root mean squared error (RMSE), and Kling‐Gupta efficiency (KGE) are commonly used to evaluate model performance. Higher NSE and KGE values indicate better performance, while lower RMSE values are preferable. Our results show that NSE increased by 71%, RMSE decreased by 32%, and KGE improved by 25%. In addition, KAN identifies an optimal functional form and can be used to derive new analytical formulas using the prior knowledge. The KAN‐inspired equation outperformed the original formulation and reduced the fitting parameters. Furthermore, we refined the water‐balance equation at the mean‐annual scale and showed that, based on the new water‐balance equation, KAN can derive new formulations that are superior to the original aridity index formulations (up to 105% increase in NSE) and KAN‐derived equations based on the original water balance. These findings highlight the significant potential of KAN to advance the scientific understanding of a wide range of hydrologic processes. Key Points Kolmogorov‐Arnold networks (KANs) enhance interpretability of machine‐learned hydrological models KAN‐derived symbolic formulations outperform state‐of‐the‐art semi‐empirical aridity indices KAN‐identified functional form yields an analytical index with fewer fitting parameters and improved performance
baseflow↗
Machine Learning Techniques in Optimal Design
Many important applications can be formalized as constrained optimization tasks. For example, we are studying the engineering domain of two-dimensional (2-D) structural design. In this task, the goal is to design a structure of minimum weight that bears a set of loads. A solution to a design problem in which there is a single load (L) and two stationary support points (S1 and S2) consists of four members, E1, E2, E3, and E4 that connect the load to the support points is discussed. In principle, optimal solutions to problems of this kind can be found by numerical optimization techniques. However, in practice [Vanderplaats, 1984] these methods are slow and they can produce different local solutions whose quality (ratio to the global optimum) varies with the choice of starting points. Hence, their applicability to real-world problems is severely restricted. To overcome these limitations, we propose to augment numerical optimization by first performing a symbolic compilation stage to produce: (a) objective functions that are faster to evaluate and that depend less on the choice of the starting point and (b) selection rules that associate problem instances to a set of recommended solutions. These goals are accomplished by successive specializations of the problem class and of the associated objective functions. In the end, this process reduces the problem to a collection of independent functions that are fast to evaluate, that can be differentiated symbolically, and that represent smaller regions of the overall search space. However, the specialization process can produce a large number of sub-problems. This is overcome by deriving inductively selection rules which associate problems to small sets of specialized independent sub-problems. Each set of candidate solutions is chosen to minimize a cost function which expresses the tradeoff between the quality of the solution that can be obtained from the sub-problem and the time it takes to produce it. The overall solution to the problem, is then obtained by solving in parallel each of the sub-problems in the set and computing the one with the minimum cost. In addition to speeding up the optimization process, our use of learning methods also relieves the expert from the burden of identifying rules that exactly pinpoint optimal candidate sub-problems. In real engineering tasks it is usually too costly to the engineers to derive such rules. Therefore, this paper also contributes to a further step towards the solution of the knowledge acquisition bottleneck [Feigenbaum, 1977] which has somewhat impaired the construction of rulebased expert systems.
Cerbone, Giuseppe↗
STRUTEX: A prototype knowledge-based system for initially configuring a structure to support point loads in two dimensions
Only recently have engineers begun making use of Artificial Intelligence (AI) tools in the area of conceptual design. To continue filling this void in the design process, a prototype knowledge-based system, called STRUTEX has been developed to initially configure a structure to support point loads in two dimensions. This prototype was developed for testing the application of AI tools to conceptual design as opposed to being a testbed for new methods for improving structural analysis and optimization. This system combines numerical and symbolic processing by the computer with interactive problem solving aided by the vision of the user. How the system is constructed to interact with the user is described. Of special interest is the information flow between the knowledge base and the data base under control of the algorithmic main program. Examples of computed and refined structures are presented during the explanation of the system.
Robers, James L.↗
A comparison of Manchester symbol tracking loops for block 5 applications
The linearized tracking errors of three Manchester (biphase coded) symbol tracking loops are compared to determine which is appropriate for Block 5 receiver applications. The first is a nonreturn to zero (NRZ) symbol synchronizer loop operating at twice the symbol rate (NRZ x 2) so that it operates on half symbols. The second near optimally processes the mid-symbol transitions and ignores the between symbol transitions. In the third configuration, the first two approaches are combined as a hybrid to produce the best performance. Although this hybrid loop is the best at low symbol signal to noise ratios (SNRs), it has about the same performance as the NRZ x 2 loop at higher SNRs (greater than 0-dB E sub s/N sub 0). Based on this analysis, it is tentatively recommended that the hybrid loop be implemented for Manchester data in the Block 5 receiver. However, the high data rate case and the hardware implications of each implementation must be understood and analyzed before the hybrid loop is recommended unconditionally.
Holmes, J. K.↗
Deterministic symbolic regression with derivative information: General methodology and application to equations of state
Symbolic regression methods simultaneously determine the model functional form and the regression parameter values by generating expression trees. Symbolic regression can capture the complexity of real–world phenomena but the use of deterministic optimization for symbolic regression has been limited due to the complexity of the search space of existing formulations. Herein we present a novel deterministic mixed–integer nonlinear programming formulation for symbolic regression that incorporates derivative constraints through auxiliary expression trees. By applying the chain rule to mathematical operations, binary expression trees are capable of representing the calculation of first and second derivatives. We apply this formulation to illustrative examples using derivative information to show increased model discrimination capability. In addition, we perform a case study of a thermodynamic equation of state to gain insight on valid functional forms with thermodynamics–based constraints on the first and second derivatives.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
SDA: a symbolic differential algebra package in C++
Truncated Power Series Algebra (TPSA), or Differential Algebra (DA), is a well-established tool in accelerator physics, commonly used for generating high-order maps of dynamic systems, as well as in symplectic tracking, normal form analysis, verified integration, optimization, and fast multipole methods. This package is the first to perform symbolic DA computations, enabling traceability of initial condition contributions and runtime reduction for repeated DA calculations, potentially expanding DA’s applications.
97 MATHEMATICS AND COMPUTING↗