Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

model order reduction --- dynamic iteration --- magneto-quasistatic systems --- differential algebraic equations --- finite element method

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

The use of machine learning in mechanics is booming. Algorithms inspired by developments in the field of artificial intelligence today cover increasingly varied fields of application. This book illustrates recent results on coupling machine learning with computational mechanics, particularly for the construction of surrogate models or reduced order models. The articles contained in this compilation were presented at the EUROMECH Colloquium 597, « Reduced Order Modeling in Mechanics of Materials », held in Bad Herrenalb, Germany, from August 28th to August 31th 2018. In this book, Artificial Neural Networks are coupled to physics-based models. The tensor format of simulation data is exploited in surrogate models or for data pruning. Various reduced order models are proposed via machine learning strategies applied to simulation data. Since reduced order models have specific approximation errors, error estimators are also proposed in this book. The proposed numerical examples are very close to engineering problems. The reader would find this book to be a useful reference in identifying progress in machine learning and reduced order modeling for computational mechanics.

parameter-dependent model --- surrogate modeling --- tensor-train decomposition --- gappy POD --- heterogeneous data --- elasto-viscoplasticity --- archive --- model reduction --- 3D reconstruction --- inverse problem plasticity --- data science --- model order reduction --- POD --- DEIM --- gappy POD --- GNAT --- ECSW --- empirical cubature --- hyper-reduction --- reduced integration domain --- computational homogenisation --- model order reduction (MOR) --- low-rank approximation --- proper generalised decomposition (PGD) --- PGD compression --- randomised SVD --- nonlinear material behaviour --- machine learning --- artificial neural networks --- computational homogenization --- nonlinear reduced order model --- elastoviscoplastic behavior --- nonlinear structural mechanics --- proper orthogonal decomposition --- empirical cubature method --- error indicator --- symplectic model order reduction --- proper symplectic decomposition (PSD) --- structure preservation of symplecticity --- Hamiltonian system --- reduced order modeling (ROM) --- proper orthogonal decomposition (POD) --- enhanced POD --- a priori enrichment --- modal analysis --- stabilization --- dynamic extrapolation --- computational homogenization --- large strain --- finite deformation --- geometric nonlinearity --- reduced basis --- reduced-order model --- sampling --- Hencky strain --- microstructure property linkage --- unsupervised machine learning --- supervised machine learning --- neural network --- snapshot proper orthogonal decomposition

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

With increasing power levels and power densities in electronics systems, thermal issues are becoming more and more critical. The elevated temperatures result in changing electrical system parameters, changing the operation of devices, and sometimes even the destruction of devices. To prevent this, the thermal behavior has to be considered in the design phase. This can be done with thermal end electro-thermal design and simulation tools. This Special Issue of Energies, edited by two well-known experts of the field, Prof. Marta Rencz, Budapest University of Technology and Economics, and by Prof. Lorenzo Codecasa, Politecnico di Milano, collects twelve papers carefully selected for the representation of the latest results in thermal and electro-thermal system simulation. These contributions present a good survey of the latest results in one of the most topical areas in the field of electronics: The thermal and electro-thermal simulation of electronic components and systems. Several papers of this issue are extended versions of papers presented at the THERMINIC 2018 Workshop, held in Stockholm in the fall of 2018. The papers presented here deal with modeling and simulation of state-of-the-art applications that are highly critical from the thermal point of view, and around which there is great research activity in both industry and academia. Contributions covered the thermal simulation of electronic packages, electro-thermal advanced modeling in power electronics, multi-physics modeling and simulation of LEDs, and the characterization of interface materials, among other subjects.

thermal conductivity --- niobium pentoxide --- structure function --- time domain thermoreflectance --- thin film --- electronic packages --- JEDEC metrics --- model-order reduction --- thermal simulation --- LED --- compact thermal model --- boundary condition independent --- LED compact thermal models --- heating and optical power --- Cauer RC ladder --- dynamic thermal compact model --- LED --- silicone dome --- phosphor light conversion --- structure function --- thermal transient analysis --- thermal characterization --- multiple heat source --- secondary heat path --- power semiconductor devices --- IGBT --- modelling --- transient analysis --- SPICE --- switching --- thermal phenomena --- light emitting diodes --- power LEDs --- multi-domain modelling --- LED luminaire design --- DC–DC converters --- ferromagnetic cores --- modeling --- power losses --- thermal management --- carbon nanotubes --- thermal interface material --- reliability --- thermal aging --- LED digital twin --- design flow --- multi-domain compact model --- tool agnostic --- multi-LED --- thermal transient testing --- non-destructive testing --- thermal testability --- in-situ characterization --- electric aircraft --- motor cooling --- thermal management

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This book was established after the 6th International Workshop on Numerical and Evolutionary Optimization (NEO), representing a collection of papers on the intersection of the two research areas covered at this workshop: numerical optimization and evolutionary search techniques. While focusing on the design of fast and reliable methods lying across these two paradigms, the resulting techniques are strongly applicable to a broad class of real-world problems, such as pattern recognition, routing, energy, lines of production, prediction, and modeling, among others. This volume is intended to serve as a useful reference for mathematicians, engineers, and computer scientists to explore current issues and solutions emerging from these mathematical and computational methods and their applications.

genetic programming --- driving scoring functions --- driving events --- risky driving --- intelligent transportation systems --- mixture experiments --- single component constraints --- genetic algorithm --- IV-optimality criterion --- multiobjective optimization --- optimal control --- model order reduction --- model predictive control --- location routing problem --- rubber --- modify differential evolution algorithm --- vehicle routing problem --- differential evolution algorithm --- crop planning --- economic crops --- improvement differential evolution algorithm --- averaged Hausdorff distance --- evolutionary multi-objective optimization --- power means --- metric measure spaces --- performance indicator --- Pareto front --- surrogate-based optimization --- numerical simulations --- shape morphing --- bulbous bow --- open-source framework --- U-shaped assembly line balancing --- basic differential evolution algorithm --- improved differential evolution algorithm --- optimal solutions --- Genetic Programming --- Bloat --- NEAT --- Local Search --- EvoSpace --- improved differential evolution algorithm --- flexible job shop scheduling problem --- local search and jump search --- evolutionary computation --- multi-objective optimization --- decision space diversity