One of the main problems of the national civil construction sector is the need for mechanisms that con-tribute to the temperature regulation of internal spaces in situations of low thermal capacity levels, and in the ...
详细信息
One of the main problems of the national civil construction sector is the need for mechanisms that con-tribute to the temperature regulation of internal spaces in situations of low thermal capacity levels, and in the composition of frames, especially when it comes to light constructions. A technology used to over-come the such situation is Phase Change Materials, which is currently applied in the composition of frames of buildings in different climatic contexts around the world, where high temperatures make mate-rials go into a melting phase, storing latent heat as it liquefies, whereas low temperatures make materials go into a freezing phase, releasing latent heat into environments as it freezes. This work presents a review of PCM technologies for application in civil construction, as well as an analysis of the use of these tech-nologies in a residence with light composition, for Brazilian Bioclimatic Zones (BZ) 1, 2, and 3. With the consideration of an evolutionary analysis by simulation, the results obtained show that the best solutions were more impactful in buildings with a low level of thermal insulation in BZ3 and with a high level of thermal insulation in BZ1, obtaining reductions of up to 65% in energy demands with air conditioning. In all tested scenarios, the addition of PCM contributed positively to improving the energy efficiency of the building. (c) 2023 Elsevier B.V. All rights reserved.
We report on laser drilling borehole arrays using ultrashort pulsed lasers with a particular focus on reducing the inadvertent heat accumulation across the workpiece by optimizing the drilling sequence. For the optimi...
详细信息
We report on laser drilling borehole arrays using ultrashort pulsed lasers with a particular focus on reducing the inadvertent heat accumulation across the workpiece by optimizing the drilling sequence. For the optimization, evolutionary algorithms are used and their results are verified by thermal simulation using Comsol and experimentally evaluated using a thermal imaging camera. To enhance process efficiency in terms of boreholes drilled per second, multi-spot approaches are employed using a spatial light modulator. However, as higher temperatures occur across the workpiece when using simultaneous multi-spot drilling as compared to a single-spot process, a subtle spatial distribution and sequence of the multi-spot approach has to be selected in order to limit the resulting local heat input over the processing time. Different optimization approaches based on evolutionary algorithms aid to select those drilling sequences which allow for the combination of a high efficiency of multi-spot profiles, a low-generated process temperature and a high-component quality. In particular, using a 4 x 4 laser spot array allows for the drilling of 40,000 boreholes in less than 76 s (526 boreholes/s) with a reduced temperature increase by about 35%, as compared to a single spot process when employing an optimized drilling sequence.
Multi-agent Reinforcement Learning (MARL) has made significant progress in addressing coordination problems, but two key challenges persist in environments with partial observability: limited exploration and inaccurat...
详细信息
ISBN:
(纸本)9798400714269
Multi-agent Reinforcement Learning (MARL) has made significant progress in addressing coordination problems, but two key challenges persist in environments with partial observability: limited exploration and inaccurate evaluation of individual agents. To address these challenges, we propose a novel MARL framework that integrates evolutionary algorithms (EAs), episodic learning, and curiosity-driven exploration to optimize the coordination of joint policies using graph-based methods, named EECG. EAs are employed for their global optimization capabilities, particularly through population diversity and a gradient-free search mechanism, to enhance policy exploration. Initially, multiple agent teams explore and learn independently while sharing a common experience pool to enable data diversity. During the evolution phase, new joint policies are generated through crossover, mutation, and pareto-based selection. During the RL phase, diverse data is used to model and update the relationships among agents via Graph Neural Networks (GNNs), which help evaluate the effectiveness of individual agents' behaviors. GNNs treat agents as nodes and their interactions as edges, capturing coordination relationships effectively while dynamically assigning representations to nodes and edges. Furthermore, curiosity-based exploration motivates teams to discover new states, while a memory system stores high-reward experiences. We evaluated EECG on several benchmarks, including StarCraft II, SUMO autonomous driving, and the Multi-Agent Particle Environment. Our empirical results show that EECG consistently outperforms current baselines, with its components significantly contributing to faster convergence, especially by improving exploration and agent coordination. Our code is available: https://***/MercyM/EECG.
The maximin optimisation problem, inspired by Von Neumann’s work (von Neumann 1928) and widely applied in adversarial optimisation, has become a key research area in machine learning. Gradient Descent Ascent (GDA) is...
详细信息
Randomized search heuristics have been applied successfully to a plethora of problems. This success is complemented by a large body of theoretical results. Unfortunately, the vast majority of these results regard prob...
详细信息
We apply a hybrid evolutionary algorithm to minimize the depth of circuits in quantum computing. More specifically, we evaluate two different variants of the algorithm. In the first approach, we combine the evolutiona...
详细信息
Despite the large overall beneficial effects of endovascular treatment in patients with acute ischemic stroke, severe disability or death still occurs in almost one-third of patients. These patients, who might not ben...
详细信息
Despite the large overall beneficial effects of endovascular treatment in patients with acute ischemic stroke, severe disability or death still occurs in almost one-third of patients. These patients, who might not benefit from treatment, have been previously identified with traditional logistic regression models, which may oversimplify relations between characteristics and outcome, or machine learning techniques, which may be difficult to interpret. We developed and evaluated a novel evolutionary algorithm for fuzzy decision trees to accurately identify patients with poor outcome after endovascular treatment, which was defined as having a modified Rankin Scale score (mRS) higher or equal to 5. The created decision trees have the benefit of being comprehensible, easily interpretable models, making its predictions easy to explain to patients and practitioners. Insights in the reason for the predicted outcome can encourage acceptance and adaptation in practice and help manage expectations after treatment. We compared our proposed method to CART, the benchmark decision tree algorithm, on classification accuracy and interpretability. The fuzzy decision tree significantly outperformed CART: using 5-fold cross-validation with on average 1090 patients in the training set and 273 patients in the test set, the fuzzy decision tree misclassified on average 77 (standard deviation of 7) patients compared to 83 (+/- 7) using CART. The mean number of nodes (decision and leaf nodes) in the fuzzy decision tree was 11 (+/- 2) compared to 26 (+/- 1) for CART decision trees. With an average accuracy of 72% and much fewer nodes than CART, the developed evolutionary algorithm for fuzzy decision trees might be used to gain insights into the predictive value of patient characteristics and can contribute to the development of more accurate medical outcome prediction methods with improved clarity for practitioners and patients.
The makespan scheduling problem is an extensively studied NP-hard problem, and its simplest version is aim to find an allocation approach for a set of jobs with deterministic processing time to two identical machines ...
详细信息
暂无评论