检索结果-内蒙古大学图书馆

Multi-objective Optimization of Adhesive Bonding Process in Constrained and Noisy Settings 6th

学校读者我要写书评

暂无评论

Multi-objective Optimization of Adhesive Bonding Process in...

6th International Conference on Optimization and Learning, OLA 2023

作者： Morales-Hernández, Alejandro Van Nieuwenhuyse, Inneke Rojas Gonzalez, Sebastian Jordens, Jeroen Witters, Maarten Van Doninck, Bart Flanders Make@UHasselt Faculty of Science Hasselt University Diepenbeek3590 Belgium Data Science Institute Hasselt University Diepenbeek3590 Belgium Surrogate Modeling Lab Ghent University Ghent9000 Belgium CoDesignS Flanders Make Lommel3920 Belgium

ISBN: (纸本)9783031340192

Finding the optimal process parameters for an adhesive bonding process is challenging: the optimization is inherently multi-objective (aiming to maximize break strength while minimizing cost), constrained (the process should not result in any visual damage to the materials, and stress tests should not result in adhesive failures), and uncertain (measuring the same process parameters several times lead to different break strength). Real-life physical experiments in the lab are expensive to perform (∼ 6 h of experimentation and subsequent production costs);traditional evolutionary approaches are then ill-suited to solve the problem, due to the prohibitive amount of experiments required for evaluation. In this research, we successfully applied specific machine learning techniques (Gaussian Process Regression and Logistic Regression) to emulate the objective and constraint functions based on a limited amount of experimental data. The techniques are embedded in a Bayesian optimization algorithm, which succeeds in detecting Pareto-optimal process settings in a highly efficient way (i.e., requiring a limited number of experiments). © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Multiobjective optimization

Pseudo-rigid body networks: learning interpretable deformable object dynamics from partial observations

学校读者我要写书评

暂无评论

Pseudo-rigid body networks: learning interpretable deformabl...

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Shamil Mamedov A. René Geist Jan Swevers Sebastian Trimpe MECO Research Team KU Leuven and Flanders Make@KU Leuven Institute for Data Science in Mechanical Engineering RWTH Aachen University

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Accurately predicting deformable linear object (DLO) dynamics is challenging, especially when the task requires a model that is both human-interpretable and computationally efficient. In this work, we draw inspiration from the pseudo-rigid body method (PRB) and model a DLO as a serial chain of rigid bodies whose internal state is unrolled through time by a dynamics network. This dynamics network is trained jointly with a physics-informed encoder that maps observed motion variables to the DLO's hidden state. To encourage the state to acquire a physically meaningful representation, we leverage the forward kinematics of the PRB model as a decoder. We demonstrate in robot experiments that the proposed DLO dynamics model provides physically interpretable predictions from partial observations while being on par with black-box models regarding prediction accuracy. The project code is available at: ***/prb-networks

关键词： Deformable models Polyethylene System dynamics Computational modeling Dynamics Aluminum Neural networks Kinematics Predictive models Intelligent robots

Pseudo-rigid body networks: Learning interpretable deformable object dynamics from partial observations

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Mamedov, Shamil René Geist, A. Swevers, Jan Trimpe, Sebastian MECO Research Team KU Leuven Flanders Make@KU Leuven Belgium Institute for Data Science in Mechanical Engineering RWTH Aachen University Germany

关键词： Dynamics

Enabling Machine Learning in Software Architecture Frameworks

学校读者我要写书评

暂无评论

Enabling Machine Learning in Software Architecture Framework...

AI Engineering - Software Engineering for AI (WAIN), IEEE/ACM Workshop on

作者： Armin Moin Atta Badii Stephan Günnemann Moharram Challenger Tech. Univ. of Munich (TUM) & Univ. of Antwerp Germany & Belgium University of Reading United Kingdom Munich Data Science Institute TUM & MDSI Germany Univ. of Antwerp & Flanders Make Belgium

Several architecture frameworks for software, systems, and enterprises have been proposed in the literature. They have identified various stakeholders and defined architecture viewpoints and views to frame and address stakeholder concerns. However, the Machine Learning (ML) and data science-related concerns of data scientists and data engineers are yet to be included in existing architecture frameworks. We interviewed 65 experts from around 25 organizations in over ten countries to devise and validate the proposed framework that addresses the mentioned shortcoming.

关键词：

Synthesizing Efficiently Monitorable Formulas in Metric Temporal Logic

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Raha, Ritam Roy, Rajarshi Fijalkow, Nathanaël Neider, Daniel Pérez, Guillermo A. University of Antwerp Flanders Make Belgium LaBRI University of Bordeaux Bordeaux France Max Planck Institute for Software Systems Kaiserslautern Germany Technical University of Dortmund Germany Center for Data Science and Security University Alliance Ruhr Germany

In runtime verification, manually formalizing a specification for monitoring system executions is a tedious and error-prone process. To address this issue, we consider the problem of automatically synthesizing formal specifications from system executions. To demonstrate our approach, we consider the popular specification language Metric Temporal Logic (MTL) which is particularly tailored towards specifying temporal properties for cyber-physical systems (CPS). Most of the classical approaches for synthesizing temporal logic formulas aim at minimizing the size of the formula. However, for efficiency in monitoring, along with the size, the amount of "lookahead" required for the specification becomes relevant, especially for safety-critical applications. We formalize this notion and devise a learning algorithm that synthesizes concise formulas having bounded lookahead. To do so, our algorithm reduces the synthesis task to a series of satisfiability problems in Linear Real Arithmetic (LRA) and generates MTL formulas from their satisfying assignments. The reduction uses a novel encoding of a popular MTL monitoring procedure using LRA. Finally, we implement our algorithm in a tool called TEAL and demonstrate its ability to synthesize efficiently monitorable MTL formulas in a CPS application. © 2023, CC BY.

关键词： Specification languages

Constrained multi-objective optimization of process design parameters in settings with scarce data: an application to adhesive bonding

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Morales-Hernández, Alejandro Gonzalez, Sebastian Rojas Van Nieuwenhuyse, Inneke Couckuyt, Ivo Jordens, Jeroen Witters, Maarten Van Doninck, Bart Flanders Make@UHasselt and Data Science Institute Hasselt University Agoralaan Diepenbeek3590 Belgium Computational Mathematics Faculty of Sciences Hasselt University Agoralaan Diepenbeek3590 Belgium Surrogate Modeling Lab Ghent University-IMEC Technologiepark-Zwijnaarde Ghent9052 Belgium CoDesignS Flanders Make Oude Diestersebaan Lommel3920 Belgium

Adhesive joints are increasingly used in industry for a wide variety of applications because of their favorable characteristics such as high strength-to-weight ratio, design flexibility, limited stress concentrations, planar force transfer, good damage tolerance, and fatigue resistance. Finding the optimal process parameters for an adhesive bonding process is challenging: the optimization is inherently multi-objective (aiming to maximize break strength while minimizing cost), constrained (the process should not result in any visual damage to the materials, and stress tests should not result in failures that are adhesion-related), and uncertain (testing the same process parameters several times may lead to different break strengths). Real-life physical experiments in the lab are expensive to perform. Traditional evolutionary approaches (such as genetic algorithms) are then ill-suited to solve the problem, due to the prohibitive amount of experiments required for evaluation. Although Bayesian optimization-based algorithms are preferred to solve such expensive problems, few methods consider the optimization of more than one (noisy) objective and several constraints at the same time. In this research, we successfully applied specific machine learning techniques (Gaussian Process Regression) to emulate the objective and constraint functions based on a limited amount of experimental data. The techniques are embedded in a Bayesian optimization algorithm, which succeeds in detecting Pareto-optimal process settings in a highly efficient way (i.e., requiring a limited number of physical experiments). © 2021, CC BY-NC-ND.

关键词： Multiobjective optimization

Enabling Automated Machine Learning for Model-Driven AI Engineering

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Moin, Armin Wattanavaekin, Ukrit Lungu, Alexandra Challenger, Moharram Badii, Atta Günnemann, Stephan Department of Informatics Technical University of Munich Germany Department of Computer Science University of Antwerp Flanders Make Belgium Department of Computer Science University of Reading United Kingdom Department of Informatics Munich Data Science Institute Technical University of Munich Germany

Developing smart software services requires both Software Engineering and Artificial Intelligence (AI) skills. AI practitioners, such as data scientists often focus on the AI side, for example, creating and training Machine Learning (ML) models given a specific use case and data. They are typically not concerned with the entire software development life-cycle, architectural decisions for the system and performance issues beyond the predictive ML models (e.g., regarding the security, privacy, throughput, scalability, availability, as well as ethical, legal and regulatory compliance). In this manuscript, we propose a novel approach to enable Model-Driven Software Engineering and Model-Driven AI Engineering. In particular, we support Automated ML, thus assisting software engineers without deep AI knowledge in developing AI-intensive systems by choosing the most appropriate ML model, algorithm and techniques with suitable hyper-parameters for the task at hand. To validate our work, we carry out a case study in the smart energy domain. © 2022, CC BY-NC-SA.

关键词： Regulatory compliance

MDE for Machine Learning-Enabled Software Systems: A Case Study and Comparison of MontiAnna & ML-Quadrat

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kirchhof, Jörg Christian Moin, Armin Badii, Atta Günnemann, Stephan Challenger, Moharram Evgeny Kusmenko Jonas Ritz Bernhard Rumpe Software Engineering RWTH Aachen University Germany School of Computation Information and Technology Technical University of Munich University of Antwerp & Flanders Make Germany Belgium Department of Computer Science University of Reading United Kingdom School of Computation Information and Technology Technical University of Munich Munich Data Science Institute Germany Department of Computer Science University of Antwerp Flanders Make Belgium

In this paper, we propose to adopt the MDE paradigm for the development of Machine Learning (ML)-enabled software systems with a focus on the Internet of Things (IoT) domain. We illustrate how two state-of-the-art open-source modeling tools, namely MontiAnna and ML-Quadrat can be used for this purpose as demonstrated through a case study. The case study illustrates using ML, in particular deep Artificial Neural Networks (ANNs), for automated image recognition of handwritten digits using the MNIST reference dataset, and integrating the machine learning components into an IoT-system. Subsequently, we conduct a functional comparison of the two frameworks, setting out an analysis base to include a broad range of design considerations, such as the problem domain, methods for the ML integration into larger systems, and supported ML methods, as well as topics of recent intense interest to the ML community, such as AutoML and MLOps. Accordingly, this paper is focused on elucidating the potential of the MDE approach in the ML domain. This supports the ML-engineer in developing the (ML/software) model rather than implementing the code, and additionally enforces reusability and modularity of the design through enabling the out-of-the-box integration of ML functionality as a component of the IoT or cyber-physical systems. © 2022, CC BY-NC-SA.

关键词： Internet of things

Preface for the 3rd Edition of the International Knowledge Graph Construction Workshop 3

学校读者我要写书评

暂无评论

Preface for the 3rd Edition of the International Knowledge G...

3rd International Workshop on Knowledge Graph Construction, KGCW 2022

作者： Chaves-Fraga, David Dimou, Anastasia Heyvaert, Pieter Priyatna, Freddy Sequeda, Juan KU Leuven Department of Computer Science Sint-Katelijne-Waver Belgium Universidad Politécnica de Madrid Campus de Montegancedo Boadilla del Monte Spain Flanders Make DTAI-FET United States Leuven.AI KU Leuven Institute for AI LeuvenB-3000 Belgium IDLab Dept of Electronics and Information Systems Ghent University Imec Belgium Olive AI EEUU Data.world EEUU