检索结果-内蒙古大学图书馆

Stochastic Online Optimization for Cyber-Physical and Robotic systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Hao Zeilinger, Melanie Muehlebach, Michael Learning and Dynamical Systems Group Max Planck Institute for Intelligent Systems Max-Planck-Ring 4 Tübingen Germany Department of Mechanical and Process Engineering Institute for Dynamic Systems and Control Leonhardstrasse 21 Zürich8092 Switzerland

We propose a novel gradient-based online optimization framework for solving stochastic programming problems that frequently arise in the context of cyber-physical and robotic systems. Our problem formulation accommodates constraints that model the evolution of a cyber-physical system, which has, in general, a continuous state and action space, is nonlinear, and where the state is only partially observed. We also incorporate an approximate model of the dynamics as prior knowledge into the learning process and show that even rough estimates of the dynamics can significantly improve the convergence of our algorithms. Our online optimization framework encompasses both gradient descent and quasi-Newton methods, and we provide a unified convergence analysis of our algorithms in a non-convex setting. We also characterize the impact of modeling errors in the system dynamics on the convergence rate of the algorithms. Finally, we evaluate our algorithms in simulations of a flexible beam, a four-legged walking robot, and in real-world experiments with a ping-pong playing robot. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Reliability-aware control of Power Converters in Mobility Applications

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Rezaeizadeh, Amin Zardini, Gioele Frazzoli, Emilio Mastellone, Silvia Institute of Electric Power Systems University of Applied Science Northwest Switzerland Windish Switzerland Institute for Dynamic Systems and Control Department of Mechanical and Process Engineering ETH Zürich Switzerland

This paper introduces an automatic control method designed to enhance the operation of electric vehicles, besides the speed tracking objectives, by including reliability and lifetime requirements. The research considers an automotive power converter which supplies electric power to a permanent magnet synchronous motor (PMSM). The primary control objective is to mitigate the thermal stress on the power electronic Insulate Gate Bipolar Transistors (IGBTs), while simultaneously ensuring effective speed tracking performance. To achieve these goals, we propose an extended H∞ design framework, which includes reliability models. The method is tested in two distinct scenarios: reliability-aware, and reliability-free cases. Furthermore, the paper conducts a lifetime analysis of the IGBTs, leveraging the Rainflow algorithm and temperature data. Copyright © 2023, The Authors. All rights reserved.

关键词： Reliability

Optimization of Rice Bran Protein Extraction Using Choline Chloride-Glycerol Deep Eutectic Solvent Using Response Surface Methodology (RSM) 2nd

学校读者我要写书评

暂无评论

Optimization of Rice Bran Protein Extraction Using Choline C...

2nd International Conference on Biomass Utilization and Sustainable Energy, ICoBiomasSE 2022

作者： Kamal Ramlee, Kamalea Amaleena Farhana Muhammad Nor, Intan Nurfazliyana Md Sarip, Mohd Sharizan Mohd Zainudin, Mohd Asraf Abu Bakar, Amirul Ridzuan Nawawi, Mohd Azizi Nik Daud, Nik Muhammad Azhar UniCITI Alam Campus Sungai Chuchuh Perlis Padang Besar02100 Malaysia Kompleks Pusat Pengajian Jejawi 3 Perlis Arau02600 Malaysia Division of Process Control and Process Systems Engineering Department of Chemical Engineering Kyoto University Kyotodaigau-Katsura Nishikyo-ku Kyoto-shi Kyoto615-8510 Japan Faculty of Applied Sciences Universiti Teknologi MARA Shah Alam40450 Malaysia Kompleks Pusat Pengajian Jejawi 3 Perlis Arau02600 Malaysia

ISBN: (纸本)9789819916948

A by-product of the rice milling process, rice bran contains four different types of protein: albumin, globulin, prolamin, and glutelin. These proteins are widely known for being hypoallergenic and having nutritional benefits. In order to increase the value of rice bran, the protein was extracted via deep eutectic solvent (DES). Response Surface Methodology (RSM) was used to assess the impact of three operational conditions, including temperature, extraction duration, and the ratio of rice bran to DES, on the yield of rice bran protein after the precipitates were converted into powder form by freeze drying. At optimal working conditions, which were 60 °C, 2 h, and a 1:9 ratio of rice bran to DES, the method’s results showed that the highest extracted protein of rice bran was 16.254%. Several techniques, including Fourier transform infrared spectroscopy (FTIR) and Kjeldahl studies, have been used to demonstrate the presence of protein in rice bran powder. In the rice bran protein (RBP), amine (1640.70 cm−1), alcohol (3229.74 cm−1), and alkane (2925.37 cm−1) were all detected using FTIR analysis. Furthermore, Kjeldahl analysis revealed that 15.61% of the rice bran powder’s protein content is present. In conclusion, rice bran’s value as a functional meal can be increased by adding protein through the use of a deep eutectic solvent called green solvent. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Proteins

The need for neuromorphic computing in industrial robotics

学校读者我要写书评

暂无评论

The need for neuromorphic computing in industrial robotics

Artificial Intelligence and Power engineering (AIPE), International Conference on

作者： Tapanta Bhanja Jonathan Nußbaum Khalil Abuibaid Tatjana Legler Achim Wagner Martin Ruskowski Department of Mechanical and Process Engineering Chair for Machine Tools and Control Systems University of Kaiserslautern-Landau Kaiserslautern Germany Innovative Factory Systems German Research Centre for Artificial Intelligence Kaiserslautern Germany

With Moore’s law coming to its limits, the rate of increase in compute power available for processing applications is similarly coming to a halt. This implies that the compute intensive tasks, such as robotics, artificial intelligence, and high-performance space computing need innovative ways to cater their ever-increasing compute needs. One innovative way to solve computational bottlenecks is to bring compute and memory together, as opposed to the Von Neumann computational model, with greater degree of parallelism in an event-based, asynchronous computation paradigm. Neuromorphic computing is one such paradigm that draws its inspiration from the brain. Energy and computational efficiency, asynchronous and event-based processing being its salient features, neuromorphic computing is an area worth exploring for compute intensive tasks. In this paper, the authors explore the possibilities and benefits of neuromorphic computing in robotics, and establish possible research directions that could benefit the robotics domain.

关键词：

Physics-informed neural networks for parameter learning of wildfire spreading

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Vogiatzoglou, Konstantinos Papadimitriou, C. Bontozoglou, V. Ampountolas, K. System Dynamics Laboratory Department of Mechanical Engineering University of Thessaly Volos38334 Greece Transport Processes & Process Equipment Laboratory Department of Mechanical Engineering University of Thessaly Volos38334 Greece Automatic Control & Autonomous Systems Laboratory Department of Mechanical Engineering University of Thessaly Volos38334 Greece

Wildland fires pose a terrifying natural hazard, underscoring the urgent need to develop datadriven and physics-informed digital twins for wildfire prevention, monitoring, intervention, and response. In this direction of research, this work introduces a physics-informed neural network (PiNN) designed to learn the unknown parameters of an interpretable wildfire spreading model. The considered modeling approach integrates fundamental physical laws articulated by key model parameters essential for capturing the complex behavior of wildfires. The proposed machine learning framework leverages the theory of artificial neural networks with the physical constraints governing wildfire dynamics, including the first principles of mass and energy conservation. Training of the PiNN for physics-informed parameter identification is realized using synthetic data on the spatiotemporal evolution of one- and two-dimensional firefronts, derived from a high-fidelity simulator, as well as empirical data (ground surface thermal images) from the Troy Fire that occurred on June 19, 2002, in California. The parameter learning results demonstrate the predictive ability of the proposed PiNN in uncovering the unknown coefficients of the wildfire model in one- and two-dimensional fire spreading scenarios as well as the Troy Fire. Additionally, this methodology exhibits robustness by identifying the same parameters even in the presence of noisy data. By integrating this PiNN approach into a comprehensive framework, the envisioned physics-informed digital twin will enhance intelligent wildfire management and risk assessment, providing a powerful tool for proactive and reactive strategies. Copyright © 2024, The Authors. All rights reserved.

关键词： Risk assessment

Evolutionary Algorithm-based Optimal Parametrization of Multi-objective Mixed-integer Linear Programming Scheduling Models

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2023年第2期56卷 5382-5387页

作者： Vassilios Yfantis Alexander Babskiy Bastian Dörig Thorsten Winterer Achim Wagner Martin Ruskowski Chair of Machine Tools and Control Systems Department of Mechanical and Process Engineering RPTU Kaiserslautern-Landau Kaiserslautern D-67663 Germany flexis AG Stuttgart D-70565 Germany Innovative Factory Systems German Research Center for Artificial Intelligence (DFKI) Kaiserslautern D-67663 Germany

Modern manufacturing systems strive to optimize many different key performance indicators. Additionally, mathematical programming-based scheduling models enable the explicit considerations of constraints. However, due to the ever-increasing demand for customized products it is not guaranteed that all constraints can be met at the same time. An approach to circumvent this problem of infeasibility is to replace the constraints by soft-constraints, i.e., to penalize their violation in the objective function. The presence of multiple competing objectives and soft-constraints gives rise to multi-objective optimization problems, where a decision maker has to weigh and balance the different objectives and soft-constraints according to his/her preferences and priorities. Ideally the values of all objectives and soft-constraints should lie within the same order of magnitude, making it easy to weigh them against each other. However, for heterogeneous objectives and soft-constraints with different scales and units this might be challenging. This paper presents an evolutionary algorithm for the optimal parametrization of multi-objective mixed-integer linear programming-based scheduling models. The goal of the evolutionary algorithm is to compute weights for the different terms of the objective which lead to a balanced influence on the overall objective at the optimum. Furthermore, the algorithm is extended by introducing an a priori weighing of the objectives in the fitness function of the evolutionary algorithm. The method is demonstrated on a scheduling problem in which a given set of orders has to be allocated to machines within a manufacturing environment.

关键词： Evolutionary Algorithm Multi-objective optimization Scheduling

Iterative Learning control for Ramp Metering on Service Station On-ramps

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xiang, Hongxi Cenedese, Carlo Balta, Efe C. Lygeros, John Department of Mechanical and Process Engineering ETH Zürich Zürich Switzerland Department of Information Technology and Electrical Engineering ETH Zürich Zürich Switzerland Delft Center for Systems and Control Delft University of Technology Delft Netherlands Inspire AG Zürich Switzerland

Congestion on highways has become a significant social problem due to the increasing number of vehicles, leading to considerable waste of time and pollution. Regulating the outflow from the Service Station can help alleviate this congestion. Notably, traffic flows follow recurring patterns over days and weeks, allowing for the application of Iterative Learning control (ILC). Building on these insights, we propose an ILC approach based on the Cell Transmission Model with service stations (CTM-s). It is shown that ILC can effectively compensate for potential inaccuracies in model parameter estimates by leveraging historical data. Copyright © 2024, The Authors. All rights reserved.

关键词： Traffic congestion

A low-cost gold-coated optical fiber sensor for in-situ microplastic detection in water

学校读者我要写书评

暂无评论

A low-cost gold-coated optical fiber sensor for in-situ micr...

BioSensors Conference (BioSensors), IEEE

作者： Noppasin Ajchareeyasoontorn Jade Udomkittivorakul Tatinee Changlor Chanyanut Rungchaiwattanakul Jenyuk Lohwacharin Charusluk Viphavakit International School of Engineering (ISE) Faculty of Engineering Chulalongkorn University Bangkok Thailand Department of Environmental Engineering Faculty of Engineering Chulalongkorn University Bangkok Thailand Intelligent Control Automation of Process Systems Research Unit Faculty of Engineering Chulalongkorn University Bangkok Thailand

An optical fiber-based sensor in the configuration of single-multi-single (SMS) modes structure is proposed to detect polyethylene microplastic particles inside aquatic environments via the interaction of light at the interface of optical fiber and the microplastic solutions. Microplastics negatively affect biological systems since living creatures may consume the pollutant. The data on the relationship between the transmittance spectrum and its corresponding wavelength value can be used to correlate and identify the concentration of the microplastic solution. Deposition of gold on the sensing region through sputtering is investigated to improve the sensitivity and reliability of the SMS sensor. This suggests the potential for a gold-coated SMS sensor for in-situ, low-cost and real-time microplastic sensing applications.

关键词：

Robust Event-Triggered control of Nonlinear systems Under a Global Sector-Bound Condition

学校读者我要写书评

暂无评论

Guidance, Navigation and control 2022年第2期2卷 59-79页

作者： Pengpeng Zhang Tengfei Liu Zhong-Ping Jiang Department of Control Science&Engineering Frontiers Science Center for Intelligent Autonomous SystemsTongji UniversityShanghai 201804P.R.China State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110819P.R.China Department of Electrical and Computer Engineering New York University370 Jay StreetBrooklynNY 11201USA

This paper studies an event-tniggered control problem for nonlinear systems subject to both external disturbancoes and dy namic *** is assumed that the system satisfies a global sector bound *** avold infnitely fast samplng,a novel eventriggred sampling mechanism is propoeed,which use8 not only the measuned system state but also an estimation of the inluence of the *** the propoeed design,the intersampling intervals an be lower bounded by a poeitive constant,and it is independent of botb external disturbances and dynamie ***,the doeedl loop event-tniggered system i proved to be input-torstate stable with repect to the extemal *** smalgain techmigues are;used for the stability analysis of the dloeeil-bop system.

关键词： Event-triggered control external disturbance dynamic uncertainty input-to-state stability