1. Computationally efficient multi-objective optimization of an interior permanent magnet synchronous machine using neural networksMitja Garmut, Simon Steentjes, Martin Petrun, 2025, izvirni znanstveni članek Opis: Improving the power density of an interior permanent magnet synchronous machine requires a complex and comprehensive approach that includes electromagnetic and thermal aspects. To achieve that, a multi-objective optimization of the machine’s geometry was performed according to selected key performance indicators by using numerical and analytical models. The primary objective of this research was to create a computationally efficient and accurate alternative to a direct finite element method-based optimization. By integrating artificial neural networks as meta-models, we aimed to demonstrate their performance in comparison to existing State-of-the-Art approaches. The artificial neural network approach achieved a nearly 20-fold reduction compared with the finite element method-based approach in computation time while maintaining accuracy, demonstrating its effectiveness as a computationally efficient alternative. The obtained artificial neural network can also be reused for different optimization scenarios and for iterative fine-tuning, further reducing the computation time. To highlight the advantages and limitations of the proposed approach, a multi-objective optimization scenario was performed, which increased the power-to-mass ratio by 16.5%.
Ključne besede: interior permanent magnet synchronous machine, artificial neural network, metamodel, multi-objective optimization, finite element method
Objavljeno v DKUM: 08.08.2025; Ogledov: 0; Prenosov: 19
 Celotno besedilo (2,87 MB) |
2. A DSL for the development of software agents working within a semantic web environmentSebla Demirkol, Moharram Challenger, Sinem Getir, Tomaž Kosar, Geylani Kardas, Marjan Mernik, 2013, izvirni znanstveni članek Opis: Software agents became popular in the development of complex software systems,especially those requiring autonomous and proactive behavior. Agents interact with each other within a Multi-agent System (MAS), in order to perform certain defined tasks in a collaborative and/or selfish manner. However, the autonomous, proactive and interactive structure of MAS causes difficulties when developing such software systems. It is within this context,that the use of a Domain-specific Language (DSL) may support easier and quicker MAS development methodology. The impact of such DSL usage could beclearer when considering the development of MASs, especially those working on new challenging environments like the Semantic Web. Hence, this paper introduces a new DSL for Semantic Web enabled MASs. This new DSL is called Semantic web Enabled Agent Language (SEA_L). Both the SEA_L user-aspects and the way of implementing SEA_L are discussed in the paper. The practical use of SEA_L is also demonstrated using a case study which considers the modeling of a multi-agent based e-barter system. When considering the language implementation, we first discuss the syntax of SEA_L and we show how the specifications of SEA_L can be utilized during the code generation of real MAS implementations. The syntax of SEA_L is supported by textual modeling toolkits developed with Xtext. Code generation for the instance models are supplied with the Xpand tool.
Ključne besede: domain-specific language, DSL, metamodel, multi-agent system, semantic web
Objavljeno v DKUM: 06.07.2017; Ogledov: 1266; Prenosov: 440
Celotno besedilo (458,07 KB)
Gradivo ima več datotek! Več... |
3. Application of metamodel inference with large-scale metamodelsQichao Liu, Jeffrey G. Gray, Marjan Mernik, Barrett Richard Bryant, 2012, izvirni znanstveni članek Ključne besede: model-driven engineering, reverse engineering, gramar inference, metamodel inference, model co-evolution, model transformation
Objavljeno v DKUM: 01.06.2012; Ogledov: 1618; Prenosov: 25
 Povezava na celotno besedilo |
