با سلام خدمت کاربران در صورتی که با خطای سیستم پرداخت بانکی مواجه شدید از طریق کارت به کارت (6037997535328901 بانک ملی ناصر خنجری ) مقاله خود را دریافت کنید (تا مشکل رفع گردد).
ردیف | عنوان | نوع |
---|---|---|
1 |
An intelligent semantic system for real-time demand response management of a thermal grid
یک سیستم معنایی هوشمند برای مدیریت پاسخ به تقاضای زمان واقعی یک شبکه حرارتی-2020 “Demand Response” energy management of thermal grids requires consideration of a wide range of factors at
building and district level, supported by continuously calibrated simulation models that reflect real operation
conditions. Moreover, cross-domain data interoperability between concepts used by the numerous hardware and
software is essential, in terms of Terminology, Metadata, Meaning and Logic. This paper leverages domain
ontology to map and align the semantic resources that underpin building and district energy management, with a
focus on the optimization of a thermal grid informed by real-time energy demand. The intelligence of the system
is derived from simulation-based optimization, informed by calibrated thermal models that predict the network’s
energy demand to inform (near) real-time generation. The paper demonstrates that the use of semantics helps
alleviate the endemic energy performance gap, as validated in a real district heating network where 36% reduction
on operation cost and 43% reduction on CO2 emission were observed compared to baseline operational
data. Keywords: Thermal grid | Demand response | Energy optimization | Operation cost | Data interoperability | Semantic ontology |
مقاله انگلیسی |
2 |
Energy optimization of electric vehicle’s acceleration process based on reinforcement learning
بهینه سازی انرژی در روند شتاب خودروی الکتریکی بر اساس یادگیری تقویتی-2020 Under the situation of unmanned driving, the energy consumption in an electric vehicle’s acceleration
process can be reduced by controlling the driving behavior. So in this paper, a pedal control strategy
which could optimize the energy consumption of electric vehicle’s acceleration process is proposed. The
strategy is generated by the training results of reinforcement learning framework and the specific
method of building such framework is discussed in details. Based on the training results of Q-learningbased
algorithm, the relationship between the proportion of energy consumption reduction and vehicle’s
acceleration time is analyzed, which illustrates the energy-saving potential of the algorithm. In order to
improve the control effect of the strategy, an updated algorithm framework based on Deep Q-learning
(DQN) is proposed and an improved pedal’s control strategy is obtained. Compared with the strategy
obtained by Q-learning-based algorithm, the improved strategy not only achieves the same energysaving
effect, but also guarantees the stability of control effect, which is more suitable for actual use. Keywords: Unmanned driving | Electric vehicles | Pedal control stratgey | Energy optimization | Q-learning | Deep Q-learning |
مقاله انگلیسی |
3 |
Energy management of hybrid electric vehicles: A review of energy optimization of fuel cell hybrid power system based on genetic algorithm
مدیریت انرژی وسایل نقلیه الکتریکی هیبریدی: مروری بر بهینه سازی انرژی سیستم قدرت هیبریدی سلول سوختی بر اساس الگوریتم ژنتیکی-2020 Under the background of current environmental pollution and serious shortage of fossil energy, the development
of electric vehicles driven by clean new energy is the key to solve this problem, especially the hybrid electric
vehicle driven by fuel cell is the most effective solution. Many scholars have found that the output performance
of hybrid system is an important reason to determine the life of fuel cell. Unreasonable output will affect the
control characteristics of the drive system, resulting in a series of serious consequences such as the reduction of
the life of fuel cell hybrid power system. Therefore, the energy management strategy and performance optimization
of hybrid system is the key to ensure the normal operation of the system. At present, many excellent
researchers have carried out relevant research in this field. Genetic algorithm is a heuristic algorithm, which has
better optimization performance. It can easily choose satisfactory solutions according to the optimization objectives,
and make up for these shortcomings by using its own characteristics. These characteristics make genetic
algorithm have outstanding advantages in the iterative optimization of energy management strategy. This paper
analyzes and summarizes the optimization effect of genetic algorithm in various energy management strategies,
aiming to analyze and select the optimization rules and parameters, optimization objects and optimization
objectives. This paper hopes to provide guidance for the optimal control strategy and structural design of the fuel
cell hybrid power system, contribute to the research on improving the energy utilization efficiency of the hybrid
power system and extending the life of the fuel cell, and provide more ideas for the optimization of energy
management in the future. Keywords: Fuel cell hybrid electric vehicle | Energy management strategy | Hybrid power system | Genetic algorithm |Optimization parameters and objectives |
مقاله انگلیسی |
4 |
Deep Learning-Driven Particle Swarm Optimisation for Additive Manufacturing Energy Optimisation
بهینه سازی ازدحام ذرات با محوریت یادگیری عمیق برای بهینه سازی انرژی تولید افزودنی-2019 The additive manufacturing (AM) process is characterised as a high energy-consuming process, which
has a significant impact on the environment and sustainability. The topic of AM energy consumption
modelling, prediction, and optimisation has then become a research focus in both industry and academia.
This issue involves many relevant features, such as material condition, process operation, part and
process design, working environment, and so on. While existing studies reveal that AM energy
consumption modelling largely depends on the design-relevant features in practice, it has not been given
sufficient attention. Therefore, in this study, design-relevant features are firstly examined with respect
to energy modelling. These features are typically determined by part designers and process operators
before production. The AM energy consumption knowledge, hidden in the design-relevant features, is
exploited for prediction modelling through a design-relevant data analytics approach. Based on the new
modelling approach, a novel deep learning-driven particle swarm optimisation (DLD-PSO) method is
proposed to optimise the energy utility. Deep learning is introduced to address several issues, in terms
of increasing the search speed and enhancing the global best of PSO. Finally, using the design-relevant
data collected from a real-world AM system in production, a case study is presented to validate the
proposed modelling approach, and the results reveal its merits. Meanwhile, optimisation has also been
carried out to guide part designers and process operators to revise their designs and decisions in order
to reduce the energy consumption of the designated AM system under study. Keywords: Additive Manufacturing | Energy Consumption Modelling | Prediction and Optimisation | Deep Learning | Particle Swarm Optimisation |
مقاله انگلیسی |
5 |
Life cycle assessment of greenhouse gas emissions and water-energy optimization for shale gas supply chain planning based on multi-level approach: Case study in Barnett, Marcellus, Fayetteville, and Haynesville shales
ارزیابی چرخه زندگی انتشار گازهای گلخانه ای و بهینه سازی انرژی آب برای برنامه ریزی زنجیره تامین گاز شیلنگ بر اساس رویکرد چند سطحی: مطالعه موردی در برنت، مارسلوس، فایتلویل و شیل های هینسوییل-2017 This study develops a multi-level programming model from a life cycle perspective for performing shale
gas supply chain system. A set of leader-follower-interactive objectives with emphases of environmental,
economic and energy concerns are incorporated into the synergistic optimization process, named MGU
MEM-MWL model. The upper-level model quantitatively investigates the life-cycle greenhouse gas
(GHG) emissions as controlled by the environmental sector. The middle-level one focuses exclusively
on system benefits as determined by the energy sector. The lower-level one aims to recycle water to min
imize the life-cycle water supply as required by the enterprises. The capabilities and effectiveness of the
developed model are illustrated through real-world case studies of the Barnett, Marcellus, Fayetteville,
and Haynesville Shales in the US. An improved multi-level interactive solution algorithm based on satis
factory degree is then presented to improve computational efficiency. Results indicate that: (a) the end
use phase (i.e., gas utilization for electricity generation) would not only dominate the life-cycle GHG
emissions, but also account for 76.1% of the life-cycle system profits; (b) operations associated with well
hydraulic fracturing would be the largest contributor to the life-cycle freshwater consumption when gas
use is not considered, and a majority of freshwater withdrawal would be supplied by surface water; (c)
nearly 95% of flowback water would be recycled for hydraulic fracturing activities and only about 5% of
flowback water would be treated via CWT facilities in the Marcellus, while most of the wastewater gen
erated from the drilling, fracturing and production operations would be treated via underground injec
tion control wells in the other shale plays. Moreover, the performance of the MGU-MEM-MWL model
is enhanced by comparing with the three bi-level programs and the multi-objective approach. Results
demonstrate that the MGU-MEM-MWL decisions would provide much comprehensive and systematic
policies when considering the hierarchical structure within the shale-gas system.
Keywords: Multi-level programming | Life cycle | Shale gas | Greenhouse gas | Energy | Water supply |
مقاله انگلیسی |