检索结果-内蒙古大学图书馆

Mediterranean Conference on Control and automation (MED)

作者： Steve Yuwono Andreas Schwung Department of Automation Technology and Learning Systems South Westphalia University of Applied Sciences Soest Germany

In the modern era of manufacturing automation, the integration of sensor technology into the system ensures that data acquisition and analysis from complex systems become more efficient than ever. With the support of such developments, artificial intelligence-powered control in industrial control domains gains popularity and enhances the traditional human-based PLC control, where the machines can monitor themselves, learn from the experience, and make their own decisions. However, despite advances in sensor technologies, there are some limitations of the current applications of sensors in industries, for instance, sensors for observing the current status of the system often provide Boolean output data instead of continuous output. Therefore, such limitation forms a low dimensional state representation of the system, which could be problematic to develop a self-control policy, e.g. using a model-free deep reinforcement learning. In this paper, we present an effective model predictive controller with adaptive PLC-based policy on low dimensional state representation specifically for industrial control domains. First, we learn the model of the production system using the deep learning method to get the representation of the system dynamics, in case its digital representation is not available. Second, we set up a native implementation of model predictive control. Third, we enhance the model predictive control with adaptive PLC-based policy. The proposed method is implemented into a bulk good system showing its potential to self-optimize the system by satisfying the production objective without overflow and low power consumption.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Model-Based Deep learning Approach for Self-learning in Smart Production systems

A Model-Based Deep Learning Approach for Self-Learning in Sm...

引用

International Conference on Emerging Technologies and Factory automation (ETFA)

作者： Steve Yuwono Andreas Schwung Department of Automation Technology and Learning Systems South Westphalia University of Applied Sciences Soest Germany

In this research, we discuss the impact of combining model-based deep learning and game theory in dynamic games to develop a sample-efficient self-learning methodology for smart production systems. We propose a novel approach, namely Model-Based Game Theory (MBGT), by incorporating model-based deep learning into a successful self-learning strategy of State-based Potential Games. Most of the advanced self-learning approaches are established based on machine learning and artificial intelligence, including reinforcement learning and game-theoretical method. However, because of the iterative behaviour during the learning processes, the learning processes are almost impossible to be conducted directly in a real-world manufacturing environment. One potential approach is to conduct the learning processes using the digital representation of the systems, e.g. the digital twin or simulation. Nonetheless, such representations in industrial settings are not always available and developing a digital representation of a complex system is immensely challenging. Hence, this problem can be solved through model-based learning, in which deep learning models are trained to predict the dynamics of the systems with a small margin of error. Then, the trained models are deployed as virtual environments for the learning processes of the GT-based control policies, instead of learning in the real world. In this study, we implement MBGT to a bulk good system and thoroughly analyse the performances between training in the real system and virtual environment, which eventually turn out to be positive effects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mlpro 2.0 - Online Machine learning in Python

SSRN

引用

SSRN 2025年

作者： Arend, Detlef Baheti, Laxmikant Shrikant Yuwono, Steve Kumar, Syamraj Purushamparambil Satheesh Schwung, Andreas Department of Automation Technology and Learning Systems South Westphalia University of Applied Science Lübecker Ring 2 Soest59494 Germany

In this paper, we present version 2.0 of the open-source middleware MLPro for applied machine learning in Python. Notably, it introduces the new sub-framework MLPro-OA for online machine learning, focusing on standards and templates for classic and online-adaptive data stream processing (DSP/OADSP). As part of this, we provide two novel adaptation mechanisms called cascaded and reverse adaptation. The first enables event-oriented cross-stream-task adaptation, decoupled from the forward-facing DSP. The second allows stream tasks to remove obsolete stream instances from their policies that were discarded from a previous sliding window. Furthermore, we provide insights into the underlying design criteria of MLPro-OA, which were developed through extensive requirements engineering. In the practical part of this work, we demonstrate the essential functionalities of MLPro-OA using reproducible examples. © 2025, The Authors. All rights reserved.

关键词： Middleware

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Multiview Top-k Pooling with Deep-Q-Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2985-2996页

作者： Li, Zhi-Peng Su, Hai-Long Wu, Yong- Zhang, Qin-Hu Yuan, Chang-An Gribova, Valeriya Filaretov, Vladimir Fedorovich Huang, De-Shuang Eastern Institute of Technology Zhejiang Ningbo315201 China University of Science and Technology of China School of Life Sciences Anhui Hefei230026 China Tongji University Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Shanghai201804 China Guangxi Academy of Sciences Institute of Big Data and Intelligent Computing Research Center Nanning530007 China Far Eastern Branch of the Russian Academy of Sciences Institute of Automation and Control Processes Vladivostok690041 Russia

Graph neural networks (GNNs) are extensions of deep neural networks to graph-structured data. It has already attracted widespread attention for various tasks such as node classification and link prediction. Existing research focuses more on graph convolutional neural networks (GCNs). However, it is usually overlooked that graph pooling can obtain graph representations by summarizing and down-sampling node information. Meanwhile, existing graph pooling methods mainly use top-k for node selection, but most of them consider only single view information when scoring nodes, and the k values in top-k are usually selected empirically. This work proposes the hierarchical multiview top-k pooling (HMTPool) with deep-Q-networks, which scores nodes taking into account multiview information (considering graph structure and features) and does not rely on the empirical adaptive selection of the best k value. HMTPool is a two-stage process. It first uses a variant GCN and multilayer perceptron to score the nodes from structural and feature perspectives, respectively and then performs fusion operations on the multiview information scores of the nodes. In addition, to select the optimal pooling ratio of top-k, we propose a deep-Q-network-based top-k (DTop-k) node selection method, which can adaptively select the best pooling ratio without prior knowledge. Experimental results on six TUDatasets and two Benchmarking GNNs datasets demonstrate the effectiveness of our proposed approach. © 2020 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Gradient-based learning in State-based Potential Games for Self-learning Production systems

Gradient-based Learning in State-based Potential Games for S...

引用

Annual Conference of Industrial Electronics Society

作者： Steve Yuwono Marlon Löppenberg Dorothea Schwung Andreas Schwung Automation Technology and Learning Systems South Westphalia University of Applied Sciences Soest Germany Artificial Intelligence and Data Science in Automation Technology Hochschule Düsseldorf University of Applied Sciences Düsseldorf Germany

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

In this paper, we introduce novel gradient-based optimization methods for state-based potential games (SbPGs) within self-learning distributed production systems. SbPGs are recognised for their efficacy in enabling self-optimizing distributed multi-agent systems and offer a proven convergence guarantee, which facilitates collaborative player efforts towards global objectives. Our study strives to replace conventional ad-hoc random exploration-based learning in SbPGs with contemporary gradient-based approaches, which aim for faster convergence and smoother exploration dynamics, thereby shortening training duration while upholding the efficacy of SbPGs. Moreover, we propose three distinct variants for estimating the objective function of gradient-based learning, each developed to suit the unique characteristics of the systems under consideration. To validate our methodology, we apply it to a laboratory testbed, namely Bulk Good Laboratory Plant, which represents a smart and flexible distributed multi-agent production system. The incorporation of gradient-based learning in SbPGs reduces training times and achieves more optimal policies than its baseline.

关键词： Training learning systems Production systems Power demand Optimization methods Games Benchmark testing Manufacturing Convergence Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Gradient-based learning in State-based Potential Games for Self-learning Production systems

arXiv

引用

arXiv 2024年

作者： Yuwono, Steve Löppenberg, Marlon Schwung, Andreas Schwung, Dorothea Automation Technology and Learning Systems South Westphalia University of Applied Sciences Soest Germany Artificial Intelligence and Data Science in Automation Technology Hochschule Düsseldorf University of Applied Sciences Düsseldorf Germany

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Impact of Evidence Theory Uncertainty on Training Object Detection Models

arXiv

引用

arXiv 2024年

作者： Ibrahim, M. Tahasanul Shaik, Rifshu Hussain Schwung, Andreas Department of Automation Technology and Learning Systems South Westphalia University of Applied Sciences Lübecker Ring 2 North Rhine-Westphalia Soest59494 Germany

This paper investigates the use of Evidence Theory to enhance the training efficiency of object detection models by incorporating uncertainty into the feedback loop. In each training iteration, during the validation phase, Evidence Theory is applied to establish a relationship between ground truth labels and predictions. The Dempster-Shafer rule of combination is used to quantify uncertainty based on the evidence from these predictions. This uncertainty measure is then utilized to weight the feedback loss for the subsequent iteration, allowing the model to adjust its learning dynamically. By experimenting with various uncertainty-weighting strategies, this study aims to determine the most effective method for optimizing feedback to accelerate the training process. The results demonstrate that using uncertainty-based feedback not only reduces training time but can also enhance model performance compared to traditional approaches. This research offers insights into the role of uncertainty in improving machine learning work-flows, particularly in object detection, and suggests broader applications for uncertainty-driven training across other AI disciplines. © 2024, CC BY-NC-SA.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Stability-Guaranteed Control systems with Min-Max Constraints and Machine learning-Based Virtual Sensors

Stability-Guaranteed Control Systems with Min-Max Constraint...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Eric Hilgert Andreas Schwung Department of Technology and Systems Graduate School for Applied Research in North Rhine-Westphalia Bochum Germany Department of Automation Technology and Learning Systems South Westphalia University of Applied Sciences Soest Germany

In this paper, we present a comprehensive approach for designing and analyzing control systems with minmax constraint controllers and machine learning-based virtual sensors. By leveraging the Standard Nonlinear Operator Form (SNOF), we establish the necessary conditions for global asymptotic stability and demonstrate their applicability through an illustrative example based on a modified plant model from the literature. The proposed methodology effectively handles non-linearities and constraints, ensuring stability while providing a systematic procedure for constructing a well-formed SNOF by integrating the plant, virtual sensor, and controller. The successful application of this method in the example highlights its potential for addressing complex control problems involving min-max constraints and virtual sensors in real-world scenarios. This paper contributes to the growing body of knowledge in this area and sets the stage for future advancements, including the exploration of transforming other machine learning architectures into the SNOF and extending the stability analysis to accommodate different types of nonlinearities and constraints.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Data Fusion Enhanced PD Control for Precision Drone Landing in Synthetic Environments

Neural Data Fusion Enhanced PD Control for Precision Drone L...

引用

International Conference on Mechatronics (ICM)

作者： Diyar Altinses David Orlando Salazar Torres Stefan Lier Andreas Schwung Department of Automation Technology and learning systems South Westphalia University of Applied Sciences Soest Germany Department of Logistics and Supply Chain Management South Westphalia University of Applied Sciences Meschede Germany

ISBN: (数字)9798331533892

ISBN: (纸本)9798331533908

Unmanned aerial vehicles are increasingly used in applications like surveillance, mapping, and delivery, where precise and safe landings are crucial, especially on small, designated platforms in multimodal systems. However, achieving consistent landing accuracy is challenging due to sensor inaccuracies, environmental disturbances, and dynamic conditions. This paper introduces a synthetic drone simulation environment to test landing scenarios and control strategies. We propose a control framework combining a classical PD controller with a neural network-based data fusion model that corrects sensor noise, particularly in GPS and UWB data, to improve landing precision. Simulation results demonstrate that our approach enhances landing accuracy and robustness compared to traditional methods.

关键词： Thermal expansion Accuracy Noise Noise reduction Data integration Robustness Thermal noise PD control Vehicle dynamics Drones

来源：评论

学校读者我要写书评

暂无评论

Model-based Reinforcement learning for Sim-to-Real Transfer in Robotics using HTM neural networks

Model-based Reinforcement Learning for Sim-to-Real Transfer ...

引用

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： M. R. Diprasetya A. N. Pullani A. Schwung D. Schwung Department of Automation Technology and Learning Systems South Westphalia University of Applied Sciences Soest Germany Department of Artificial Intelligence and Data Science Hochschule Düsseldorf University of Applied Sciences Düsseldorf Germany

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

In this work we propose a novel approach based on model-based Reinforcement learning (RL) for the sim-to-real transfer of industrial robots. Specifically, we propose to employ a recently developed kinematics-informed, modular neural network serving as a learnable environment model within the world model framework. Using the kinematics-informed model, training of the world model is made more efficient resulting in faster training. Furthermore, the approach allows to train industrial robots on specific tasks solely within the simulation of the system thereby saving time and energy-consumption. Using simulations ensures safe and controlled training implementation and allows for parallelization to increase training speed. We conduct various experiments which underline the effectiveness of the proposed method. We show that training the RL algorithm solely within the simulation, results in a hundred percent task completion rate in both simulation and real world experiments.

关键词： Training Service robots Simulation Reinforcement learning Artificial neural networks Industrial robots Information technology

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：