In the paper the problem of modeling of thermal processes in microcontroller system is addressed. The proposed models allow to describe thermal processes during work of an evaluation system. The temperature in critica...
详细信息
Exosuits present intriguing structural advantages compared to exoskeletons; nevertheless, accurately modeling and simulating their effectiveness when integrated with the musculoskeletal system of the user poses formid...
Exosuits present intriguing structural advantages compared to exoskeletons; nevertheless, accurately modeling and simulating their effectiveness when integrated with the musculoskeletal system of the user poses formidable challenges. As regards the upper limb, there are limited approaches and models in the literature that consider both the complexities of the musculoskeletal system and the optimization of the exosuit interface. In this work, we propose an extensive approach that considers both a mathematical model of a wrist-elbow exosuit, and simulations of a complex upper limb musculoskeletal system. The kinematic and dynamic model of the exosuit allows for the optimization of the anchor points, while the simulation provides information on muscular loading with and without assistance. In the presented results we have developed and validated personalized musculoskeletal models with kinematic, anthropometric, and electromyographic data we measured in a load-lifting task. The results of the simulations show the effectiveness of the optimized exosuit and reveal the impact of the exosuit at the level of the whole upper limb, and not limited to the actuated districts only.
In island distribution grids, the increase of renewable generation sources, whose output is stochastic in nature, implies that large amount of operating reserve must be guaranteed during the grid operation. In this pa...
详细信息
ISBN:
(数字)9781665442800
ISBN:
(纸本)9781665442800
In island distribution grids, the increase of renewable generation sources, whose output is stochastic in nature, implies that large amount of operating reserve must be guaranteed during the grid operation. In this paper, a methodology based on predictive optimal dispatch is proposed to optimize the use of energy resources taking into account operating reserve constraints. Reserve constraints are quantified through a probabilistic approach that takes into account the probabilistic distribution of forecasting errors. The methodology is applied to the distribution model of an actual Italian small island, supplied by a set of conventional diesel generators together with photovoltaic and storage resources. The performance of the proposed predictive approach is assessed considering the response of the system during different load and generation scenarios. The impacts of reserve provision is also studied considering the effect of an open-loop and a closed-loop control strategy.
The proceedings contain 50 papers. The special focus in this conference is on Web Information systems and Applications in China. The topics include: GTGNN: Global Graph and Taxonomy Tree for Graph Neural Net...
ISBN:
(纸本)9789819777068
The proceedings contain 50 papers. The special focus in this conference is on Web Information systems and Applications in China. The topics include: GTGNN: Global Graph and Taxonomy Tree for Graph Neural Network Session-Based Recommendation;dual Learning Model of Code Summary and Generation Based on Transformer;relation-Oriented Temporal Knowledge Graphs Completion Based on Recurrent Neural Network;MMPDRec: A Denoising Model for Knowledge Concepts Recommendation Using Metapaths;SPR: A Similar Projection Revisor for Complex Logical Reasoning over Knowledge Graphs;An Generative Entity Relation Extraction Model Based on UIE for Legal Text;uncertain Knowledge Graph Completion with Rule Mining;MAGAN: Mode Information and Attention-Based GAN for Realistic Time Series Data Synthesis;a study on Context-Matching-Based Joint Training for Chinese Coreference Resolution;DFCDR: Domain-Aware Feature Decoupling and Fusion for Cross-Domain Recommendation;two-stage Enhancement for Recommendation systems Based on Contrastive Learning;popularity-Aware Graph Neural Network with Global Context for Session-Based Recommendation;Enhancing Sentiment Analysis for Chinese Texts Using a BERT-Based Model with a Custom Attention Mechanism;contrastive Learning-Based Cross-Domain Data Augmentation for Aspect-Based Sentiment Analysis;a Dynamic Convergence Criterion for Fast K-means Computations;efficient p-Biclique Query on Large Bipartite Networks;high-Dimensional Nearest Neighbor Search-Based Blocking in Entity Resolution;top-k Collective Spatial Keyword Approximate Query;SMSRD: A streaming Graph Data Management system Based on Relational Database;PLIS: Persistent Learned Index for strings;dataset Construction for Fine-Grained Emotion Analysis in Catering Review Data;database Parameters Tuning via Bayesian optimization with Domain Knowledge;attribute Multiplex Network Graph Clustering: Joint Contrastive And High-Order Proximity;reliable Community Search over Dynamic Bipartite Graphs;a Hierarchica
Offshore Eastern Africa emerged as a major new petroleum province through the second decade of the 21st century. A combination of Jurassic source rocks and Cretaceous and Tertiary clastic reservoirs came together to d...
详细信息
Neural network verification aims at providing formal guarantees on the output of trained neural networks, to ensure their robustness against adversarial examples and enable deployment in safety-critical applications. ...
详细信息
ISBN:
(纸本)9783031606014;9783031605994
Neural network verification aims at providing formal guarantees on the output of trained neural networks, to ensure their robustness against adversarial examples and enable deployment in safety-critical applications. This paper introduces a new approach to neural network verification using a novel mixed-integer programming (MIP) rolling-horizon decomposition method. The algorithm leverages the layered structure of neural networks by employing optimization-based bound tightening (OBBT) on smaller sub-graphs of the original network in a rolling-horizon fashion and tightening the bounds in parallel. This strategy strikes a balance between achieving tighter bounds and ensuring the tractability of the underlying mixed-integer programs. Extensive numerical experiments, conducted on instances from the VNN-COMP benchmark library, demonstrate that the proposed approach yields significantly improved bounds compared to existing efficient bound propagation methods. Notably, the proposed method proves effective in solving open verification problems. Our code is built and released as part of the open-source mathematical modeling tool Gravity (https://***/ coin- or/Gravity), which is extended to support generic neural network models.
Explainable Artificial Intelligence and Formal Argumentation have received significant attention in recent years. Argumentation frameworks are useful for representing knowledge and reasoning on it. Counterfactual and ...
详细信息
At information age, the rapid increase of information caused Information Overload problem, which made recommendation system (RS) come into being and push forward the quick development. Nowadays RS has been widely used...
详细信息
Every day, environmental issues deteriorate further. The adoption of the industry 4.0 revolution, the use of renewable energy, advancements in control systems, and other 21st-century revolutions all call for a signifi...
详细信息
ISBN:
(纸本)9798350332117
Every day, environmental issues deteriorate further. The adoption of the industry 4.0 revolution, the use of renewable energy, advancements in control systems, and other 21st-century revolutions all call for a significant increase in power consumption. Including captive power facilities that can supply the local load is one way to address the requirement for electricity. A single renewable energy source frequently presents problems in terms of generating electricity due to the intermittent nature of renewables. Hybrid renewable energy systems are one of the most promising ways to meet the load demand. This paper focused on the modeling of large-scale hybrid renewable energy systems (HRES) with the incorporation of solar PV, wind energy conversion system (WECS), and battery energy storage system (BESS). This study also includes simulation and analysis of a large-scale hybrid renewable energy system with a DC load application. In this paper Gain Scheduling PI(GSPI) controlling technique is used for good stability and improvement of the response time of 100 kW HRES. MATLAB SIMULINK is used to evaluate the system for different combinations of supply and load.
Cyber-physical systems often require fault detection of future events in order to mitigate the fault before failure occurs. Effective on-board runtime verification (RV) will need to not only determine the system's...
详细信息
ISBN:
(纸本)9783031426254;9783031426261
Cyber-physical systems often require fault detection of future events in order to mitigate the fault before failure occurs. Effective on-board runtime verification (RV) will need to not only determine the system's current state but also predict future faults by predetermined mitigation trigger deadlines. For example, if it takes three seconds to deploy the parachute of an Unmanned Aerial system (UAS), the deployment of the parachute must be triggered three seconds before it is needed to mitigate the impending crash. To allow for the detection of future faults by deadlines, we design a real-time Model Predictive Runtime Verification (MPRV) algorithm that uniquely uses current data traces whenever possible, predicting only the minimum horizon needed to make an on-deadline evaluation. Although MPRV is extensible to other RV engines, we deploy the algorithm on the R2U2 RV engine due to R2U2's resource-aware architecture, real-time guarantees, and deployment history. We demonstrate the utility of the MPRV algorithm through a quadcopter case study and evaluate the effectiveness of our implementation by conducting memory usage and runtime performance analysis in a resource-constrained FPGA environment.
暂无评论