This research paper explores the integration of Thermoelectric Generators (TEGs) as dual-function components in wearable devices, serving as both energy harvesters and fuzzy logic-enhanced actuators. The study present...
详细信息
The capture of nonlinearity in servo systems during operation is significant for fault diagnosis, which can greatly reduce the probability of system failure throughout the life cycle. To address the problem, a step-by...
详细信息
ISBN:
(纸本)9798350388084;9798350388077
The capture of nonlinearity in servo systems during operation is significant for fault diagnosis, which can greatly reduce the probability of system failure throughout the life cycle. To address the problem, a step-by-step identification method based on iterative optimization mutation particle swarm optimization (S-IPV-PSO) is proposed for fault diagnosis. Firstly, an iterative optimization mutation particle swarm optimization (IPV-PSO) is presented to improve convergence speed and algorithm accuracy by optimizing the learning factor and inertia weight coefficient. Secondly, a Hammerstein model is established to identify the parameters for predicting different states of the system by using the IPV-PSO algorithm, where inverse M signal is used as an output to separate between the nonlinear and linear parts of the system. Finally, a servo system simulation with dead time characteristics is built to verify the effectiveness of the proposed algorithm. Extensive experiments demonstrate that the proposed method can effectively identify fault states and has better convergence speed and recognition error.
Discrete optimization with decision diagrams is a recent approach to solve combinatorial problems that can be formulated with dynamic programming. It consists in a branch-and-bound algorithm that iteratively explores ...
详细信息
ISBN:
(数字)9783031605970
ISBN:
(纸本)9783031605963;9783031605970
Discrete optimization with decision diagrams is a recent approach to solve combinatorial problems that can be formulated with dynamic programming. It consists in a branch-and-bound algorithm that iteratively explores the search space by compiling bounded-width decision diagrams. Those decision diagrams are used both to subdivide a given problem into smaller subproblems - in a divide-and-conquer fashion - and to compute primal and dual bounds for those. It has been previously shown that pruning performed during the compilation of those decision diagrams can greatly impact the quality of the bounds, and consequently the performance of the branch-and-bound algorithm. In this paper, we study the integration of dominance rules inside the decision diagram-based optimization framework. We propose a modeling language for consistently formulating dominance rules for dynamic programming models, and describe how they can be exploited to systematically detect and prune dominated nodes during the search. Furthermore, we explain how to combine this additional filtering mechanism with caching techniques to further improve the performance of the algorithm. Dominance rules are shown to significantly reduce the number of nodes expanded and the running time of the algorithm on four optimization problems.
The proceedings contain 16 papers. The topics discussed include: computing: looking back and moving forward;hidden champions revised: towards a new conceptual framework;enhancing returns management in fashion e-commer...
ISBN:
(纸本)9789897587108
The proceedings contain 16 papers. The topics discussed include: computing: looking back and moving forward;hidden champions revised: towards a new conceptual framework;enhancing returns management in fashion e-commerce: industry insights on AI-based prediction and recommendation systems;comparative analysis of machine learning techniques for DDoS intrusion detection in IoT environments;artificial neural network model for predicting excavator downtime;framework for modeling the propagation of disturbances in smart construction sites;sentiment analysis-based chatbot system to enhance customer satisfaction in technical support complaints service for telecommunications companies;Business-RAG: information extraction for business insights;and speech recognition for inventory management in small businesses.
The proceedings contain 305 papers. The topics discussed include: loss calculation of iron core under dc bias and harmonic disturbance conditions;physics-informed conditional generative adversarial network for inverse...
ISBN:
(纸本)9798350348958
The proceedings contain 305 papers. The topics discussed include: loss calculation of iron core under dc bias and harmonic disturbance conditions;physics-informed conditional generative adversarial network for inverse electromagnetic problems;a study on the design of novel slotless axial flux motor through comparison with radial flux motor for collaborative robot;study on rotor bar loss due to space harmonics of line start synchronous reluctance motor;electromagnetic field analysis using physics informed neural network considering eddy current;characteristic analysis of two-phase stator-permanent-magnet hybrid stepping machines with radial and tangential magnetization;DC-link voltage control strategy considering vessel condition for efficiency improvement of IH cooktops with PFC rectifier;measurement uncertainty of Schumann resonances with the EFIELD experiment on board dragonfly;fast estimation system of permanent magnet magnetization using 2D-arrayed hall sensors combined with deep neural network;and simplified optimization of curved barrier in synchronous reluctance motor.
The proceedings contain 42 papers. The topics discussed include: resource-efficient sensor fusion via system-wide dynamic gated neural networks;a large-scale P2P botnet detection framework via topology and traffic co-...
ISBN:
(纸本)9798331519186
The proceedings contain 42 papers. The topics discussed include: resource-efficient sensor fusion via system-wide dynamic gated neural networks;a large-scale P2P botnet detection framework via topology and traffic co-verification;resource allocation and task offloading for slicing-based communication and computing in space-air-ground integrated networks;topology design with resource allocation and entanglement distribution for quantum networks;driving important scene detection based on user preferences;beta: a novel learning-based adaptive streaming approach with spatial and temporal optimization;scalable and distributed optimization of shared 3D object quality for large-scale hybrid-metaverses;budget-constrained traveling salesman problem: a cooperative multi-agent reinforcement learning approach;and an intelligent prefetch strategy with multi-round cell enhancement in volumetric video streaming.
In the context of the carbon neutrality goal and the rising penetration of renewable energies, the electrical power system's dependency on renewable energy sources, including photovoltaic (PV) and wind generation,...
详细信息
ISBN:
(纸本)9798350382570;9798350382563
In the context of the carbon neutrality goal and the rising penetration of renewable energies, the electrical power system's dependency on renewable energy sources, including photovoltaic (PV) and wind generation, has markedly increased. However, the generation of renewable energy is heavily dependent on climatic conditions, and its volatility can bring pressure to the power balance of the distribution network. The application of mobile energy storage system (MESS) will become a strong support for the extensive expansion of renewable energy sources. Hence, an optimal scheduling method for county-level distribution networks (CDNs) considering the multi-function reuse of MESS is proposed. Firstly, the application scenarios and necessity of multi-function reuse of MESS under the context of a significant share of renewable energy sources are analyzed. Then, an optimal scheduling method considering MESS is constructed, aiming at reducing the overall operating expenses of the CDN, as well as the constraints such as the spatiotemporal dynamic scheduling of MESS. Finally, a revised 33-bus distribution network is applied for case studies. The simulation results demonstrate that the proposed model is applicable to different scenarios of the CDN under various application functions of MESS, effectively reducing the operational costs of the CDN and ensuring the power supply for load demand.
One of the key aims of Industry 4.0 is to create more responsive systems. Responsiveness and adaptation enable coping with new market requirements or introducing new products, as demonstrated by the challenges posed b...
详细信息
ISBN:
(纸本)9781665493130
One of the key aims of Industry 4.0 is to create more responsive systems. Responsiveness and adaptation enable coping with new market requirements or introducing new products, as demonstrated by the challenges posed by COVID-19. Despite the economic and sustainability benefits, practitioners often only consider adapting their systems for limited cases. They rely on simple, intuitive estimates of adaptation metrics and do not optimize these milestone decisions, leading to missed opportunities. Currently, there are no reliable methods for measuring system adaptability, quantifying the effort required to adapt it from one state to another, or optimizing the adaptation decision. This paper proposes a comprehensive adaptation framework based on complexity index quantification, graph network estimation, and multi-objective optimization. The framework outlines three approaches for estimating efforts in adapting the physical system design, upgrading control software, and optimizing the adaptation decision. The application on a lab-sized cell demonstrates the framework's ability to estimate the adaption processes metric and generate a set of optimized cell states. The application reveals potentials for improvement and extension of the three approaches.
We propose an unsupervised beamforming neural network (BNN) to optimize transmit beamforming in downlink multiple input single output (MISO) channels. Reconfigurable intelligent surface (RIS) panels are used to assist...
详细信息
ISBN:
(纸本)9798350381566;9798350381559
We propose an unsupervised beamforming neural network (BNN) to optimize transmit beamforming in downlink multiple input single output (MISO) channels. Reconfigurable intelligent surface (RIS) panels are used to assist user equipment that does not receive sufficiently s trong s ignals f rom t he base station. To avoid frequent beam updates, the proposed BNN is based on slow-changing channel covariances and is different from most other BNNs that utilize instant channel state information. Numerical simulations show that the proposed BNN can achieve much higher sum rates than zeroforcing beamforming does when the system is heavily loaded and can drastically reduce computation time for large-scale communication systems.
The stability of the power system is important for ensuring the power grid's reliable operation. Traditional stability analysis and stabilization methods have limitations in handling the complexity and nonlinearit...
详细信息
暂无评论