Use Of Metamodels Research Articles

Improving Computation Time for Optimization Runs of Modelica-Based Energy Systems

Mathematical optimization is a widespread method in order to improve, for instance, the efficiency of energy systems. A simulation approach based on partial differential equations can typically not be formulated as an optimization problem, thus requiring interfacing to an external optimization environment. This is, among others, also true for the programming language Modelica. Because of high computation time, such coupled approaches are often limited to small-scale optimization problems. Since simulation models tend to get more complex, simulation time and, in turn, associated optimization time rise significantly. To enable proper sampling of the search space, individual optimization runs need to be solved in acceptable times. This paper addresses the search for a proper optimization approach and tool to couple with Modelica/Dymola. The optimization is carried out on an exemplary power plant model from the ClaRa-Library using an evolutionary algorithm (SPEA2-based) with Ansys optiSlang. To verify and evaluate the results, a comparison with the standard Dymola optimization library is performed. Both parallelization and indirect optimization with surrogate models achieved a significant runtime reduction by a factor of up to 5.4. The use of meta models is particularly advantageous for repetitive optimization runs of the same optimization problem but may lead to deviations due to the calculated approximations.

A review on the applicability of machine learning techniques to the metamodeling of energy systems

The use of physics-based models for the development and optimization of energy systems is popular due to their versatility. However, their inherent complexity often makes these simulations computationally prohibitive, despite the current computational power available nowadays. This problem is aggravated when considering renewable energy systems, which are subjected to intermittent weather conditions and must be operated in connection with a grid of variable demand. In that sense, the use of metamodels has shown immense potential in the simulation, analysis, and optimization of energy systems. Therefore, this review presents a comprehensive analysis of the extensive application of metamodeling techniques in energy systems. After conducting a careful search using the Scopus database while targeting a well-defined group of keywords, 474 articles published from 2013 to 2023 were obtained in the present literature review. With a rigorous filtering and screening process, the first pool of articles was reduced to 126. The resulting articles were then separated in two main groups, reviews and research articles. Each of these groups was further organized in terms of the energy system studied, as well as the applicability, machine learning technique and error indicator. The results indicate a steady and significant growth in the number of publications associated with energy systems and different types of metamodeling techniques. The reasons are arguably twofold, reduction of computational time provided by the metamodels and their good accuracy. Nevertheless, and as reported by other studies, the review also identified the need to develop a standardized method for evaluating the error analysis of these models and a comparison between their actual efficiency, which includes accuracy and time. Furthermore, no clear relation was found between specific types of metamodels and specific energy systems.

AN EFFICIENT HYBRID IMPACT SWELL INUNDATION SYSTEM FOR SMALL ISLANDS

Coastal flooding events generated by the combination of different simultaneous Meteorological and Oceanographic processes that occur at different spatial and temporal scales, are a big concern for Pacific nations. Although for many applications, the full wave directional spectra aggregated into its bulk parameters (i.e., significant wave height, peak period and mean or peak direction) is used, this is especially unsuitable for islands located in large ocean basins where concurrent seas and swells approaching from every direction are common and including the directional complexity of the full spectrum becomes crucial. Moreover, when attempting to assess coastal flooding, it is imperative to analyze the setup and the energy released by infragravity waves at the coast in a high spatial and temporal resolution in order to generate the adequate conditions to force a flooding model. However, dynamically simulating the propagation of wave spectral energy to the coast in order to obtain setup and infragravity waves to feed a flooding model is a very computationally expensive task, particularly for Small Island Developing States (SIDS) where computational resources are often limited. For this reason, we propose the use of metamodels that combine statistical and numerical modeling to efficiently downscale waves and obtain the flooding extents needed to assess the impact associated to a particular event.

Categorical surrogation of agent‐based models: A comparative study of machine learning classifiers

AbstractAgent‐based modelling has gained recognition in the last years because it provides a natural way to explore the behaviour of social systems. However, agent‐based models usually have a considerable number of parameters that make it computationally prohibitive to explore the complete space of parameter combinations. A promising approach to overcome the computational constraints of agent‐based models is the use of machine learning‐based surrogates or metamodels, which can be used as efficient proxies of the original agent‐based model. As the use of metamodels of agent‐based simulations is still an incipient area of research, there are no guidelines on which algorithms are the most suitable candidates. In order to contribute to filling this gap, we conduct here a systematic comparative analysis to evaluate different machine learning‐based approaches to agent‐based model surrogation. A key innovation of our work is the focus on classification methods for categorical metamodeling, which is highly relevant because agent‐based simulations are very often validated in a qualitative way. To analyse the performance of the classifiers we use three types of indicators—measures of correctness, efficiency, and robustness—and compare their results for different datasets and sample sizes using an agent‐based artificial market as a case study.

Metamodelling of the load-displacement response of offshore piles in sand

The paper illustrates the development of metamodels of the response of steel piles driven in sand and subjected to pull-out. The metamodels are created for the prediction of the pile tensile capacity and secant stiffness. They were developed using the results of finite element analyses, which made use of finite element models of robustness assessed employing a selection of available data from large-scale model pile tests. Four hundred finite element analyses allowed for the calibration of very accurate metamodels, which were also demonstrated to closely track the outputs of the experimental results. Once calibrated, the metamodels can be used independently from the finite element models they stemmed from. The outcomes of the study show that metamodels of piles response can yield very accurate results within a wide and realistic range of soil-pile configuration, avoiding the laborious implementation and computational cost which underpins the use of finite element models. As the use of metamodels in this context is new, the paper relies on particularly simplified problem, but the procedure could be extended to accommodate modelling features of higher complexity.

Metamodels to enable renewable energy system consideration within thermal and electrical systems optimization

Emerging infrastructure systems requiring both thermal and electrical energy will be powered by both renewable and conventional energy sources. To consider competitive energy subsystem designs concurrently within the design of a complete infrastructure system, high speed energy subsystem analysis tools and optimization approaches are required. This work demonstrates the use of metamodels for enabling this concurrent design approach. A renewable energy system model is presented for estimating the performance, cost, greenhouse gas emissions, and water consumption of photovoltaic, wind, concentrated solar power, battery, grid, and steam systems for a given location. High-speed metamodel representations of this model are successfully constructed. A few case studies are presented wherein the optimization time and outcomes are compared between the complete model and the metamodels. Both systems identify cheaper, less emitting, and more water efficient systems by deploying renewable energy sources. The metamodels identify competitive systems exceptionally faster than the complete model, four seconds compared to an hour on average, at no detriment to the cost of the identified system. Therefore, metamodels may be used to enable the preliminary concurrent design of emerging infrastructure systems in a computationally manageable way.

Gaussian process metamodels for floating offshore wind turbine platforms

The dynamics of floating offshore wind turbines (FOWT) are quite complex as it involves interactions in multiple domains. The dynamic response of FOWT is numerically evaluated using coupled aero-hydro-servo-elastic analysis. In the design stages, the dynamic analysis of FOWT is carried out for different environmental conditions. These analyses can be time-consuming and computationally expensive. This paper proposes the use of metamodels based on the Gaussian process for representing the hydrodynamics and structural dynamics of the floating platform. The input to Gaussian process metamodels is taken as wave elevation, forces and moments at the interface of the tower and platform. The output of the metamodels is the displacements (surge, sway and heave) and the rotations (roll, pitch and yaw) of the platform. Three different Gaussian process metamodels are considered in this paper — Standard Gaussian Process, Variational Heteroscedastic Gaussian Process and Sparse Spectrum Gaussian Process. The construction of the metamodels is demonstrated for an NREL 5MW turbine supported on an ITI barge platform. The performance of the Gaussian metamodels is compared in terms of evaluation indices, convergence, residuals and computational efficiency. The sensitivity analysis of the metamodels is carried out to verify that the interdependence between the variables is captured accurately. All three Gaussian process metamodels are found to be effective in emulating the response of the platform. These models can be effectively used in situations where simple and computationally inexpensive models are required.

Performance Investigation of Airfoils for Axial Flow Fans in Low Solidity Cascades Operating at High Inlet Flow Angles

Abstract Axial flow fans are usually characterized by blade sections with low solidity and high inlet flow angles. Two main approaches are followed in the preliminary design phase, to take into account blade interaction effects: the use of available airfoil cascades data (or related correlations) and that of isolated airfoil data together with interference coefficients. The working conditions of low solidity airfoil cascades with highly tangential inflow are not widely studied in the literature, leaving the designer the possibility to rely on limited cascade data or often on the use of isolated airfoil data, with the assumption of negligible interference effects. A systematic investigation of the above working conditions for airfoil cascades is performed with Reynolds-averaged Navier–Stokes simulations. Three different airfoils are used to evaluate the influence of the design lift coefficient and maximum blade thickness. The results provide a better insight into the aerodynamic behavior of airfoil sections in such operating conditions, showing that interactions cannot be neglected. The use of metamodeling coupled with computational fluid dynamics (CFD) simulations is presented as a suitable tool for treating interference effects within the fan design process. The main findings of the present work can be used as a support for design choices as well as for developing design strategies both for the fan blades and for the airfoil sections.

Алгоритм нейролінгвістичної маніпуляції у політичному прогнозуванні на прикладі моделі Мілтона

The scientific article investigates techniques and models of neurolinguistic programming. Particular attention is paid to the Milton’s popular metamodel, which is often used in politics. The manipulative nature of modern NLP expert techniques during election campaigns increasingly indicates the use of metamodels in politics. The relevance of the research topic is due to the great need to study the manipulative technologies used during election races, in particular the linguistic system of manipulation. The aim of the research is to study the basic techniques of neurolinguistic programming used in politics. Objectives: to analyze the linguistic elements of Milton’s metamodel on specific examples; to find out the theoretical basis and the basis of the metamodel; explore the strategies and stages of Milton’s model. Research methods: a set of methods is used in the work, namely: synthesis and analysis in clarifying the basic terminology used in the field of neurolinguistic programming; comparative analysis in the study of NLP models; discourse analysis in the application of Milton’s model on specific examples. To achieve the goals in the work, discourse analysis is chosen as the main research method. Additionally, general scientific and special scientific methods, classification and grouping, system-structural, hermeneutic, prognostic were used. Research has attempted to investigate, analyze, and structure neurolinguistic programming techniques, namely Milton’s models. This paper substantiates the theoretical and practical foundations of NLP technologies on the example of use in politics. The practical significance of the obtained results of the work is that they can be used in research for further research on this topic, as well as used for NLP analysis for other political campaigns. The study presents the main suggestion strategies used in Milton’s model, as well as analyzed linguistic techniques. Techniques and techniques of linguistic manipulations are considered on concrete examples (speeches, slogans of politicians and political campaigns). The psychological features of Milton’s model and inverse metamodel are indicated. The main stages of inversion and patterns of indirect detection are studied. The article is devoted to the algorithm of linguistic manipulation in politics on the example of Milton’s model. The concept of Milton’s inverse metamodel, its advantages and place in the political sphere are revealed, the material on the main subsets of information of Milton’s model and their subcategories is presented.

Use of metamodels for rapid discovery of narrow bandgap oxide photocatalysts

SummaryNew photocatalysts are traditionally identified through trial-and-error methods. Machine learning has shown considerable promise for improving the efficiency of photocatalyst discovery from a large potential pool. Here, we describe a multi-step, target-driven consensus method using a stacking meta-learning algorithm that robustly predicts bandgaps and H2 evolution activities of photocatalysts. Trained on small datasets, these models can rapidly screen a large space (>10 million materials) to identify promising, non-toxic compounds as candidate water splitting photocatalysts. Two effective compounds and two controls possessing optimal bandgap values (∼2 eV) but not photoactivity as predicted by the models were synthesized. Their experimentally measured bandgaps and H2 evolution activities were consistent with the predictions. Conspicuously, the two compounds with strong photoactivities under UV and visible light are promising visible-light-driven water splitting photocatalysts. This study demonstrates the power of machine learning and the potential of big data to accelerate discovery of next-generation photocatalysts.

Evolutionary Learning Based Simulation Optimization for Stochastic Job Shop Scheduling Problems

Simulation Optimization (SO) techniques refer to a set of methods that have been applied to stochastic optimization problems, structured so that the optimizer(s) are integrated with simulation experiments. Although SO techniques provide promising solutions for large and complex stochastic problems, the simulation model execution is potentially expensive in terms of computation time. Thus, the overall purpose of this research is to advance the evolutionary SO methods literature by researching the use of metamodeling within these techniques. Accordingly, we present a new Evolutionary Learning Based Simulation Optimization (ELBSO) method embedded within Ordinal Optimization. In ELBSO a Machine Learning (ML) based simulation metamodel is created using Genetic Programming (GP) to replace simulation experiments aimed at reducing computation. ELBSO is evaluated on a Stochastic Job Shop Scheduling Problem (SJSSP), which is a well known complex production planning problem in most industries such as semiconductor manufacturing. To build the metamodel from SJSSP instances that replace simulation replications, we employ a novel training vector to train GP. This then is integrated into an evolutionary two-phased Ordinal Optimization approach to optimize an SJSSP which forms the ELBSO method. Using a variety of experimental SJSSP instances, ELBSO is compared with evolutionary optimization methods from the literature and typical dispatching rules. Our findings include the superiority of ELBSO over all other algorithms in terms of the quality of solutions and computation time. Furthermore, the integrated procedures and results provided within this article establish a basis for future SO applications to large and complex stochastic problems.

Online Ensemble Topology Selection in Expensive Optimization Problems

Simulation-driven optimization problems are often computationally-expensive, an aspect which has motivated the use of metamodels as they provide approximate function values more economically. To further improve the prediction accuracy the use of ensembles has been explored in which predictions from multiple metamodels are combined. However, the optimal ensemble topology, namely, which types of metamodels it includes, is typically not known, while using a fixed topology may degrade the prediction accuracy and search effectiveness. To address this issue this paper proposes a metamodel-assisted algorithm which autonomously adapts the ensemble topology online during the search such that an optimal topology is used throughout. An extensive performance analysis shows the effectiveness of the proposed algorithm and approach.

A spatial kernel approach for topology optimization

This paper introduces a spatial kernel approach for topology optimization. This kernel influences the material distribution in the final design. The resulting spatial variables not only have physical meaning – such as the mass of the part, a stiffness gradient, or a local strengthening; but the spatial variables can also tailor the structural performances – such as the occupant protection – of the resulting design. This means only a few spatial variables are needed to represent a design otherwise described using millions of topology design variables. This ability to restate the problem in terms of the spatial variables unlocks new design schemes. Here we use a few spatial variables to address (i) constrained topology design optimization, (ii) to compute the derivatives of the constraints using numerical finite differences, and (iii) to build metamodels to the topology design optimization results. A significant benefit is therefore that complex design problems can be considered: the mechanics can include highly nonlinear events, while the use of metamodels allows a diversity of design optimization studies. Examples, including a simplified side impact occupant protection problem, are used to demonstrate.

METAMODEL ENGINEERING FOR SUPPORTING FUZZY KNOWLEDGE BASE SYNTHESIS

The paper is devoted to fuzzy knowledge base engineering problem. The effectiveness of this process can be improved by automated generation of source codes and analysis of data presented in different forms, in particular, in the form of conceptual models describing a certain subject domain. The knowledge base code generation is based on the transformation of conceptual models from the model-based approach and the use of metamodels. The metamodeling provides the description of the source and target formalisms of conceptual modeling and knowledge representation. We present an approach for fuzzy knowledge base engineering based on model transformations. In particular, metamodels for describing fuzzy rule-based models and fuzzy ontologies and method for automated metamodel generation are presented.

Підтримка обліку і використання спроможностей організації

One approach to improving an organization’s activities is an approach aimed at regulating its capabili-ties. This approach is applied in many fields of activity, but most extensively and consistently in the defense sphere of developed countries, NATO, and recently in Ukraine. The scale and complexity of the tasks that need to be addressed within the capability-based approach make it necessary to support these activities with appropriate tools. In this paper, we propose a conceptual model of accounting and use of capabilities. This model, the principal feature of which is the distinction between nominal and actual activity plans, has two components: static and dynamic. The static component of the model is a set of entities, relationships between them, as well as attributes of entities and relationships between entities. The main entities are capability and carrier of capability. There are nominal carriers of capabilities (exist only on paper) and actual carriers (instances of nominal carrier, for which, at a minimum, the coordi-nates of their location can be specified). The division into types, as well as the use of metamodels for describing capabilities and carriers of capabilities are supposed. The requirements to both the capability and the carrier of the capability can be advanced. Both actual carriers of capabilities as a whole and their (actual) capabilities are subject to assessment. Dynamic component of the model – the activity support-ed by the model – breaks up into accounting and use of capabilities. The model is supplemented by a component that allows to record the requirements and assessments of the capability carrier with distri-bution to various components of its resource (DOTMLPF-distribution). The proposed model can be used as the basis for creating the appropriate information technology.

Robust metamodels for accurate quantitative estimation of turbulent flow in pipe bends

Pipe bends are inevitable in industrial piping systems, turbomachinery, heat exchangers, etc. Computational fluid dynamics (CFD), which is commonly employed to understand the flow behavior in such systems has very accurate estimation but is computationally cost intensive. Thus, in this paper, an efficient computational approach for such computationally expensive problems is presented. Using genetic programming (GP), metamodels are built using a small number of samples points from the CFD data. These GP metamodels are then shown to be able to replace the actual CFD models with considerable accuracy. The applicability and suitability of the GP metamodels are validated using a variety of statistical metrics on the training as well as independent test data. It is shown that the use of metamodels leads to significant savings in computational cost.

Accelerated optimization method for low-embodied energy concrete box-girder bridge design

Structural optimization is normally carried out by means of conventional heuristic optimization due to the complexity of the structural problems. However, the conventional heuristic optimization still consumes a large amount of time. The use of metamodels helps to reduce the computational cost of the optimization and, along these lines, kriging-based heuristic optimization is presented as an alternative to carry out an accelerated optimization of complex problems. In this work, conventional heuristic optimization and kriging-based heuristic optimization will be applied to reach the optimal solution of a continuous box-girder pedestrian bridge of three spans with a low embodied energy. For this purpose, different penalizations and different initial sample sizes will be studied and compared. This work shows that kriging-based heuristic optimization provides results close to those of conventional heuristic optimization using less time. For the sample size of 50, the best solution differs about 2.54% compared to the conventional heuristic optimization, and reduces the computational cost by 99.06%. Therefore, the use of a kriging model in structural design problems offers a new means of solving certain structural problems that require a very high computational cost and reduces the difficulty of other problems.

Common Metamodel of Questionnaire Model and Decision Tree Model

The subject of this paper is metamodeling and its application in the field of scientific research. The main goal is to explore the possibilities of integration of two methods: questionnaires and decision trees. The questionnaire method was established as one of the methods for data collecting, while the decision tree method represents an alternative way of presenting and analyzing decision making situations. These two methods are not completely independent, but on the contrary, there is a strong natural bond between them. Therefore, the result reveals a common meta-model that over common concepts and with the use of metamodeling connects the methods: questionnaires and decision trees. The obtained results can be used to create a CASE tool or create repository that can be suitable for exchange between different systems. The proposed meta-model is not necessarily the final product. It could be further developed by adding more entities that will keep some other data.

Implementation of a tribology-based process control system for deep drawing processes

Modern deep drawn parts have complex designs and are driven to the limits of the material formability in order to reduce costs. This leads to small process windows and unstable forming processes with high scrap rates. Especially at the beginning of a batch, when the tools are warming up, high scrap rates can occur due to the changing friction behaviour of the system tool – lubricant – metal sheet. To make processes independent from user experience and know-how, process control systems that can compensate for the transient behaviour of the process are desired. In this work, a process control system that is based on the numerical simulation of the friction behaviour of the deep drawing process is presented. The system makes use of numerical simulations of the transient behaviour during warming up of the tools. These simulations are used to generate metamodels of the process, which are used to design and optimize the control algorithm. The control system is tested with an automotive part from Opel. The control system itself consists of two parts: a feed forward controller and a feedback loop. In the feedforward loop the in-line acquired temperature will be used as an indicator for the friction conditions. It will make use of metamodels generated based on numerical simulations in order to depict the process behaviour. The feedback loop will use the in-line measured draw-in as a state variable in order to account for all other process influences. Simulation results, the generation of metamodels, as well as the first off-line tests of the process control are shown in this contribution.

Multidisciplinary Optimization of Unmanned Aircraft Considering Radar Signature, Sensors, and Trajectory Constraints

This paper presents a multidisciplinary design optimization framework applied to the development of unmanned aerial vehicles with a focus on radar signature and sensor performance requirements while simultaneously considering the flight trajectory. The primary emphasis herein is on the integration and development of analysis models for the calculation of the radar cross section and sensor detection probability, whereas traditional aeronautical disciplines such as aerodynamics and mission simulation are also taken into account in order to ensure a flyable concept. Furthermore, this work explores the effect of implementing trajectory constraints as a supplementary input to the multidisciplinary design optimization process and presents a method that enables the optimization of the aircraft under a three-dimensional flight scenario. To cope with the additional computational cost of the high-fidelity radar cross section and sensor calculations, the use of metamodels is also investigated and an efficient development methodology that can provide high-accuracy approximations for this particular problem is proposed. Overall, the operation and performance of the framework are evaluated against five surveillance scenarios, and the obtained results show that the implementation of trajectory constraints in the optimization has the potential to yield better designs by 12–25% when compared to the more “traditional” problem formulations.