the proceedings contain 139 papers. the topics discussed include: multi-agent assignment via state augmented reinforcement learning;learning flow functions of spiking systems;continual learning of multi-modal dynamics...
the proceedings contain 139 papers. the topics discussed include: multi-agent assignment via state augmented reinforcement learning;learning flow functions of spiking systems;continual learning of multi-modal dynamics with external memory;CACTO-SL: using Sobolev learning to improve continuous actor-critic with trajectory optimization;finite-time complexity of incremental policy gradient methods for solving multi-task reinforcement learning;from raw data to safety: reducing conservatism by set expansion;an investigation of time reversal symmetry in reinforcement learning;PDE control Gym: a benchmark for data-driven boundary control of partial differential equations;and real-world fluid directed rigid body control via deep reinforcement learning.
Air pollution is a significant threat to human health and the environment. Accurate air quality forecasting is essential for effective mitigation strategies, including public health advisories, emission control measur...
详细信息
In the pursuit of sustainable electricity generation from offshore wind and wave energy, the combination of Floating Offshore Wind Turbines (FOWTs) and Oscillating Water Columns (OWCs) has emerged as a promising solut...
详细信息
the proceedings contain 73 papers. the special focus in this conference is on Advanced Manufacturing Processes. the topics include: Economic Justification of High-Rotational Submersible Pumps Development for Water Sup...
ISBN:
(纸本)9783031827457
the proceedings contain 73 papers. the special focus in this conference is on Advanced Manufacturing Processes. the topics include: Economic Justification of High-Rotational Submersible Pumps Development for Water Supply Facilities;analysis of Power Consumption of a Wheeled Robot Actuated by a Centrifugal Vibration Exciter;development of a Six-Spindle Turret Head of a Multioperational Machine with a Modernized Drive;composite Impeller for Centrifugal Compressors;increasing the Service Life of the Pressure Block of the Planetary Hydraulic Motor;the Concept of Digital Description of Structural Elements of Technical Systems;optimal Geometrical Dimensions of Drainless Vortex Chamber Ejector of Homogeneous Medium;efficiency Improvement of the Jet-Slit Homogenizer in the Food Engineering;substantiation of the Spring-Cam Retarder Brake Design and Its Main Parameters Determination;application of Modified Kinematic Graphs to Analyze the Structures of Passive Relaxation Shock Absorbers;the Impact of the dynamics of Multi-spindle Finishing Boring Machines on the Machining Accuracy;a Combined Approach for Determining Tool Cutting Part States Using Machine learning Models;increasing the Accuracy of Part Obtained by Selective Laser Sintering by Shrinkage Compensation;A Simulation Study of DDMRP and MRP Manufacturing Planning and control Systems;analysis of the Surface Layer of Aluminium Alloy Castings at their Machining by the Surface Homogeneity Criterion;Strain in ANSYS Simulation and Real Testing;using Plasma Coatings to Increase Equipment Reliability at Agribusiness Enterprises;vacuum Technology for Magnesium Alloys During Die Casting of Radiators;reliability Prediction for Robotic Machines with Parallel Kinematics;study of the Roughness of A36 Steel with TiAlN Coated Inserts.
Air pollution is a significant threat to human health and the environment. Accurate air quality forecasting is essential for effective mitigation strategies, including public health advisories, emission control measur...
详细信息
ISBN:
(数字)9798331522667
ISBN:
(纸本)9798331522674
Air pollution is a significant threat to human health and the environment. Accurate air quality forecasting is essential for effective mitigation strategies, including public health advisories, emission control measures, and policy interventions. this research focuses on the development of an advanced air quality forecasting system using machine learning techniques. the system uses historical data on pollutants such as PM2.5, NO2, and O3, along with meteorological parameters, to predict future air quality levels. the model is enhanced withthe inclusion of sophisticated machine learning algorithms to better capture the intricate spatiotemporal patterns and enhance the accuracy of forecasting. the system may potentially provide real-time air quality forecasts that enable proactive measures for protecting public health and inform decisions for environmental policy. this research contributes to sustainable and resilient urban environments by providing valuable insights into air quality dynamics and supporting effective air pollution mitigation strategies.
Certainty equivalence adaptive controllers are analysed using a "data-driven Riccati equation", corresponding to the model-free Bellman equation used in Q-learning. the equation depends quadratically on data...
详细信息
Certainty equivalence adaptive controllers are analysed using a "data-driven Riccati equation", corresponding to the model-free Bellman equation used in Q-learning. the equation depends quadratically on data correlation matrices. this makes it possible to derive simple sufficient conditions for stability and robustness to unmodeled dynamics in adaptive systems. the paper is concluded by short remarks on how the bounds can be used to quantify the interplay between excitation levels and robustness to unmodeled dynamics.
this work proposes a data-driven approach for bifurcation analysis in nonlinear systems when the governing differential equations are not available. Specifically, regularized regression with barrier terms is used to l...
详细信息
this work proposes a data-driven approach for bifurcation analysis in nonlinear systems when the governing differential equations are not available. Specifically, regularized regression with barrier terms is used to learn a homeomorphism that transforms the underlying system to a reference linear dynamics - either an explicit reference model with desired qualitative behavior, or Koopman eigenfunctions that are identified from some system data under a reference parameter value. When such a homeomorphism fails to be constructed with low error, bifurcation phenomenon is detected. A case study is performed on a planar numerical example where a pitchfork bifurcation exists.
We analyze the convergence properties of a robust adaptive model predictive control algorithm used to control an unknown nonlinear system. We show that by employing a standard quadratic stabilizing cost function, and ...
详细信息
We analyze the convergence properties of a robust adaptive model predictive control algorithm used to control an unknown nonlinear system. We show that by employing a standard quadratic stabilizing cost function, and by recursively updating the nominal model through kinky inference, the resulting controller ensures convergence of the true system to the origin, despite the presence of model uncertainty. We illustrate our theoretical findings through a numerical simulation.
A robust Model Predictive control algorithm is proposed for learning-based control with model represented by an affine combination of basis functions. the online optimization is formulated as a sequence of convex prog...
详细信息
A robust Model Predictive control algorithm is proposed for learning-based control with model represented by an affine combination of basis functions. the online optimization is formulated as a sequence of convex programming problems derived by linearizing concave components of the dynamic model. A tube-based approach ensures satisfaction of constraints on control variables and model states while avoiding conservative bounds on linearization errors. the linear dependence of the model on unknown parameters is exploited to allow safe online parameter adaptation. the resulting algorithm is recursively feasible and provides closed loop stability and performance guarantees. Numerical examples are provided to illustrate the approach.
In this paper, we present a Q-learning algorithm to solve the optimal output regulation problem for discrete-time LTI systems. this off-policy algorithm only relies on using persistently exciting input-output data, me...
详细信息
In this paper, we present a Q-learning algorithm to solve the optimal output regulation problem for discrete-time LTI systems. this off-policy algorithm only relies on using persistently exciting input-output data, measured offline. No model knowledge or state measurements are needed and the obtained optimal policy only uses past input-output information. Moreover, our formulation of the proposed algorithm renders it computationally efficient. We provide conditions that guarantee the convergence of the algorithm to the optimal solution. Finally, the performance of our method is compared to existing algorithms in the literature.
暂无评论