The stochastic optimal control problem of an ordinary non-linear discrete stochastic system is considered. The quality of control is estimated by the mathematical expectation of the Boltz type functional to be minimiz...
The stochastic optimal control problem of an ordinary non-linear discrete stochastic system is considered. The quality of control is estimated by the mathematical expectation of the Boltz type functional to be minimized. Considering that the control domain is open, first and second orders stochastic type necessary optimality criterions are formulated and proved, including stochastic Euler equation.
Lattice boom cranes are usually used to lift heavy loads with the optimized lattice structure of the boom structure. Considering the huge mass of the payload and the crane itself, the flexibility of the crane boom str...
详细信息
In many practical applications like rescues, the morphing quadrotors perform better than conventional quadrotors in complex and variable environments, such as traveling through narrow gaps. However, their dynamic prop...
详细信息
An intelligent system for monitoring the integrity of operating pipelines is presented. The software package is designed to assess the corrosion rate and calculate the residual life of pipelines, which takes into acco...
详细信息
ISBN:
(数字)9798331532178
ISBN:
(纸本)9798331532185
An intelligent system for monitoring the integrity of operating pipelines is presented. The software package is designed to assess the corrosion rate and calculate the residual life of pipelines, which takes into account the parameters of climatic and transported environments, the characteristics of pipelines and their insulating coatings. The complex allows us to consider different types of corrosion: atmospheric, electrochemical and mechanical. A functional structure is proposed that describes the operating principle of the software package, calculation results and examples of intelligent system interfaces are presented.
In this paper, we explore the use of Reinforcement Learning (RL) to improve the control of cooling equipment in Data Centers (DCs). DCs are inherently complexsystems, and thus challenging to model from first principl...
详细信息
ISBN:
(数字)9781665451420
ISBN:
(纸本)9781665451420
In this paper, we explore the use of Reinforcement Learning (RL) to improve the control of cooling equipment in Data Centers (DCs). DCs are inherently complexsystems, and thus challenging to model from first principles. Machine learning offers a way to address this by instead training a model to capture the thermal dynamics of a DC. In RL, an agent learns to control a system through trial-and-error. However, for systems such as DCs, an interactive trial-and-error approach is not possible, and instead, a high-fidelity model is needed. In this paper, we develop a DC model using Computational Fluid Dynamics (CFD) based on the Lattice Boltzmann Method (LBM) Bhatnagar-Gross-Krook (BGK) algorithm. The model features transient boundary conditions for simulating the DC room, heat-generating servers, and Computer Room Air Handlers (CRAHs) as well as rejection components outside the server room such as heat exchangers, compressors, and dry coolers. This model is used to train an RL agent to control the cooling equipment. Evaluations show that the RL agent can outperform traditional controllers and also can adapt to changes in the environment, such as equipment breaking down.
The proceedings contain 42 papers. The special focus in this conference is on Joint internationalconference of the international Symposium on Science of Mechanisms and Machines and internationalconference on Robotic...
ISBN:
(纸本)9783031256547
The proceedings contain 42 papers. The special focus in this conference is on Joint internationalconference of the international Symposium on Science of Mechanisms and Machines and internationalconference on Robotics. The topics include: Study of Vibrations of a Cantilever Beam with Uniformly Distributed Mass;considerations on the Proper Selection of Sensors for Vibroacoustic Study of the Vehicles;experimental Identification of Singularities in Parallel Manipulators;requirements and problems for Space Berthing System;A Kinematic Analysis of the TORVEastro Astronaut Robot Arm;Evaluation by Numerical Simulation of Friction Forces in Spherical Joints of a 6-DOF Parallel Topology Robot;comparative Analysis of Four Solutions for Command and control Applied to Anthropomorphic Grippers for Robots;Model-Free Reaching of a 2-DOF Robotic Arm Using Neural Networks;inverse Dynamic modeling of a Parallel Robot for Lower Limb Rehabilitation;a Study of Feasibility of a Mechanism for Rib-Vertebra-Sternum Prosthesis;kinematic and Dynamic Analysis of an Exoskeleton Robotic System;design and Operation of a Cable-Driven Robot for Lower-Limb Rehabilitation;a State of Art Overwiew on Wrist Rehabilitation Exoskeletons;design of an Exoskeleton for Rehabilitation Ankle Joint;requirements and Characteristics of Finger Motion Assistance;development of a Force Feedback control for Robotic Assisted Liver Cancer Treatment;Perspectives on Originally Designed Eco-Friendly Robotic Cell for PCB Dismantling;cloud-Based Digital Twin for Robot Health Monitoring and Integration in Cyber-Physical Production systems;a Novel Design of a Robotic System for Biological Fluid Aliquoting;multimodal Perceptual Cues for Context-Aware Human-Robot Interaction;a Review on Mechanisms Used for the Reconfigurable Wheelchairs.
Success in examining the dynamics of any controlled object is determined to a decisive degree by the complexity of the study, which primarily depends on the quality of modeling. Analytical mechanics offers a wide rang...
详细信息
ISBN:
(数字)9798331532178
ISBN:
(纸本)9798331532185
Success in examining the dynamics of any controlled object is determined to a decisive degree by the complexity of the study, which primarily depends on the quality of modeling. Analytical mechanics offers a wide range of coordinate types to describe the dynamics of mechanical components of mechatronic systems. modeling of the dynamics of systems with geometrical constraints requires a rigor which is unusual for technical practice. This is determined by the necessity of taking into account not only linear but also at least quadratic terms in the expansion of nonlinear constraint equations when identifying the first approximation of the equations of perturbed motion in stability and stabilization problems. The method of rigorous modeling of the dynamics of systems with geometric constraints is presented in detail in the article. Possible simplifications of the study are substantiated on the basis of these results. The effectiveness of the proposed approach is demonstrated by considering two variants of the stand Ball & Beam equilibrium.
In this paper, a mathematical model is given for the polymerization process, taking into account the process features, such as polycentrality and the dynamics of active centers. Direct and inverse kinetic problems are...
详细信息
ISBN:
(数字)9798331532178
ISBN:
(纸本)9798331532185
In this paper, a mathematical model is given for the polymerization process, taking into account the process features, such as polycentrality and the dynamics of active centers. Direct and inverse kinetic problems are set. Features of the solution method are indicated. The results of the computational experiment are given in the form of graphs for the main molecular characteristics.
The problem of budgeting costs for the strategic development of a transport complex in conditions of change is considered. A concept for such budgeting is proposed based on the decomposition of the global strategic ta...
详细信息
ISBN:
(数字)9798331532178
ISBN:
(纸本)9798331532185
The problem of budgeting costs for the strategic development of a transport complex in conditions of change is considered. A concept for such budgeting is proposed based on the decomposition of the global strategic task of diminishing transport complex expenses into local tasks, with the subsequent formation of a cost-effective strategic adaptive mechanism for minimizing costs for solving each of the local tasks. A modular approach has been developed to build a cost-effective adaptive budgeting mechanism for the strategic development of the transport complex in conditions of change, based on actual costs and cost norns. The cost-effective mechanisms of the modules used are based on digital learning procedures. Optimal synthesis of the cost-effective mechanism of the “Pupil” module is considered.
This article proposes a novel approach to clustering called eCauchy, which is based on the Cauchy density function. This method is similar to the well-known possibilistic c-means clustering (PCM), which was developed ...
详细信息
暂无评论