检索结果-内蒙古大学图书馆

The Value of Device Characterization for the optimization of Organic Solar Cells

Advanced Energy Materials 2025年第0期

作者： Christen, Leonard Urbano, Barbara Krause, Anne Hartnagel, Paula Kirchartz, Thomas IMD3-Photovoltaik Forschungszentrum Jülich Jülich52425 Germany Faculty of Engineering and CENIDE University of Duisburg-Essen Carl-Benz-Str. 199 Duisburg47057 Germany

In addition to achieving record efficiencies of ≈20%, organic photovoltaics (OPV) has to overcome several additional challenges. These include researching environmentally friendly solvents, improving stability, yield, and scaling up to industrial standards in terms of cell size and mass production. However, identifying the optimal candidates from the countless material combinations and determining the exact process parameters is like looking for a needle in a haystack. Process optimization usually comprises phases such as device fabrication, measurement, and evaluation, concluding with the experimental design of the next round of device making. Given the extent of the process parameter space, this optimization process can be extremely time-consuming. However, as optimization algorithms mainly based on mathematical models become more prevalent in automated laboratories, the question arises of how to include physics domain knowledge based on device characterization of the samples into the algorithmic optimization process. To address this question, a benchmark function is created using experimental solar cell data originating from hundreds of organic solar cells prepared with different processing conditions. This benchmark function is used to test and compare different optimization approaches to quantify under which conditions physical domain knowledge can improve the speed of process optimization in an experimental laboratory. © 2025 The Author(s). Advanced Energy Materials published by Wiley-VCH GmbH.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A Performance-Optimized Deep Learning-Based Plant Disease Detection Approach for Horticultural Crops of New Zealand

引用

IEEE ACCESS 2022年 10卷 89798-89822页

作者： Saleem, Muhammad Hammad Potgieter, Johan Arif, Khalid Mahmood Massey Univ Sch Food & Adv Technol Dept Mech & Elect Engn Auckland 0632 New Zealand Massey Univ Massey AgriFood Digital Lab Palmerston North 4472 New Zealand

Deep learning-based plant disease detection has gained significant attention from the scientific community. However, various aspects of real horticultural conditions have not yet been explored. For example, the disease should be considered not only on leaves, but also on other parts of plants, including stems, canes, and fruits. Furthermore, the detection of multiple diseases in a single plant organ at a time has not been performed. Similarly, plant disease has not been identified in various crops in the complex horticultural environment with the same optimized/modified model. To address these research gaps, this research presents a dataset named NZDLPlantDisease-v1, consisting of diseases in five of the most important horticultural crops in New Zealand: kiwifruit, apple, pear, avocado, and grapevine. An optimized version of the best obtained deep learning (DL) model named region-based fully convolutional network (RFCN) has been proposed to detect plant disease using the newly generated dataset. After finding the most suitable DL model, the data augmentation techniques were successively evaluated. Subsequently, the effects of image resizers with interpolators, weight initializers, batch normalization, and DL optimizers were studied. Finally, performance was enhanced by empirical observation of position-sensitive score maps and anchor box specifications. Furthermore, the robustness/practicality of the proposed approach was demonstrated using a stratified k-fold cross-validation technique and testing on an external dataset. The final mean average precision of the RFCN model was found to be 93.80%, which was 19.33% better than the default settings. Therefore, this research could be a benchmark step for any follow-up research on automatic control of disease in several plant species.

关键词： Diseases Crops Deep learning Detection algorithms optimization Convolutional neural networks Plants Convolutional neural networks deep learning optimization algorithms cross-validation plant disease detection

来源：评论

学校读者我要写书评

暂无评论

An efficient hybrid evolutionary algorithm for solving the traveling salesman problem 28th

An efficient hybrid evolutionary algorithm for solving the t...

引用

28th International Conference on Knowledge Based and Intelligent information and Engineering Systems, KES 2024

作者： Jedrzejowicz, Piotr Keller, Krzysztof Skakovski, Aleksander Department of Information Systems Gdynia Maritime University str. Morska 83F Gdynia81-225 Poland

The paper proposes an effective hybrid ACO-GA evolutionary algorithm combining the best features of the Ant Colony optimization and Genetic algorithm. The algorithm was tested on benchmark instances of the traveling salesman problem from TSPLIB and compared to several algorithms described in the scientific literature solving the same instances. The comparison results allow us to perceive the proposed ACO-GA as an attractive compromise between the quality of solutions and the time to find a solution. © 2024 The Authors.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A GRO metaheuristic algorithm for Parameters identification of a single diode in a photovoltaic model 6

A GRO metaheuristic algorithm for Parameters identification ...

引用

6th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2024

作者： Ydir, Brahim Choulli, Imade Saadaoui, Driss Hmamou, Dris Ben Elyaqouti, Mustapha Arjdal, El Hanafi Lahlou, Houda Laboratory of Materials Signals Systems and Physical Modeling Faculty of Science University Ibn Zohr Agadir Morocco

ISBN: (纸本)9798331529987

The identification of parameters for photovoltaic (PV) models as an optimization problem has garnered significant interest in the scientific literature. In this context, this article explores the performance of the Gold Rush Optimizer (GRO) algorithm for extracting the parameters of the single-diode model. To this end, we evaluated the GRO's ability to extract all parameters of the single-diode model of the R.T.C. solar cell, using the Root Mean Square Error (RMSE) and standard deviation (std) as performance measures. The performance of the GRO was compared with other algorithms such as JAYA and Particle Swarm optimization (PSO). The results show that our algorithm achieves the lowest Root Mean Square Error of 9.8602E-04 and the lowest standard deviation of 9.4593E-14. These results demonstrate that this optimization approach outperforms competing methods in terms of accuracy, efficiency, and stability. Thus, the GRO method proves to be particularly effective and reliable for the accurate estimation of PV model parameters. © 2024 IEEE.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Novel Selection Indexes for Additional Selection of Non-dominated Sorting Genetic algorithms

Novel Selection Indexes for Additional Selection of Non-domi...

引用

2024 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2024

作者： Hagihara, Leo Ohki, Makoto Faculty of Engineering Tottori University 101 4 Tottori680-0947 Japan

ISBN: (纸本)9798331533137

In this paper, we propose two new ranking indexes for solution set in many-objective optimization evolutionary algorithms. A non-dominated ranking allows selection pressure to perform effectively in Many-objective optimization Problems (MaOPs). NSGA is one of the algorithms that effectively incorporates non-dominated sorting for solving MaOPs. In MaOPs with a large number of objectives, most of the solutions in solution set of NSGA become non-dominated to one another. In such cases, NSGA no longer rank solutions with the non-dominated sorting, and is forced to optimize based only on additional selection indexes, for example, which is crowding distance in NSGA-II. It is well known that the additional selection with crowding distance does not effectively solve MaOP. NSGA-III allows niche selection by means of a large number of uniformly distributed reference points to realize the additional selection. While the niche selection yields high diversity in the solution set and improves the optimization, it requires huge computational cost for calculate the relation ship between the solutions and reference lines. To avoid these problems on conventional NSGAs, this paper proposes a new selection indexes to effectively solve MaOPs with the equivalent computational cost as NSGA-II, where the proposed indexes are based on the hyper volume difference and the hyper conical volume of each point in certain front set. These proposed indexes are implemented with significantly smaller computational costs than the niche selection of NSGA-III. NSGAs with the two proposed selection indexes are applied to several test MaOPs for comparing with the conventional NSGA-II and NSGA-III as numerical experiments. The experimental results showed that NSGA-III has been the most effective, but the proposed indexes demonstrated more effective optimization than NSGA-II. ©2024 IEEE.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Robustness Analysis of RSGBWPSO Algorithm over Noisy Objective Functions 1

Robustness Analysis of RSGBWPSO Algorithm over Noisy Objecti...

引用

1st International Conference on Pioneering Developments in Computer Science and Digital Technologies, IC2SDT 2024

作者： Kumar, Lalit Pandey, Manish Ahirwal, Mitul Kumar Maulana Azad National Institute of Technology M.P. Bhopal India

ISBN: (纸本)9798350365016

Metaheuristic algorithms' (MAs) ability in dealing with noisy objective functions is very important for their usability in practical situations. optimization algorithms experiences problem caused by noisy environment which added uncertainties. Researchers gets attracted by intrinsic flexibility and perturbations to these algorithms because of their inherent adaptability and flexibility in practical situations. In this paper a novel method, namely Range Selection Global Best-Worst Particle Swarm optimization (RSGBWPSO), is proposed that splits the search space and uses optimal partitions selectively to ensure noise resilience and optimization performance. The RSGBWPSO algorithm balances exploration and exploitation inside the search space to optimize ranges and divides the total population with strategy to increase the quality of the global solution. Furthermore, by including range selection and repeated exploration-exploitation strategies, the suggested algorithm overcomes the drawbacks of MAs, including algorithmic delay and premature convergence. The goal of these improvements is to raise the general caliber of the algorithm's produced global solutions. Experiments on the Generalized Moving Peaks Benchmark (GMPB) functions verify the stability of RSGBWPSO and demonstrate its ability to consistently traverse through noisy settings and converge to optimal solutions. The outcomes show that RSGBWPSO is a dependable optimization technique that may be applied to resolve difficult and unclear optimization issues that emerge in real-world circumstances. © 2024 IEEE.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Improving DNSGA-II based on Transfer Learning of Population Feature 8

Improving DNSGA-II based on Transfer Learning of Population ...

引用

8th International Conference on Electrical, Mechanical and Computer Engineering, ICEMCE 2024

作者： Xue, Tongxia Shi, Xuhua Tongxia Xue Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China

ISBN: (纸本)9798331506230

Dynamic multi-objective optimization problems (DMOPs) are common in real-world applications. To effectively address these problems, algorithms are required to maintain solution diversity and quickly adapt to environmental changes. Transfer learning is a promising approach for tackling dynamic multi-objective optimization. In this paper, a transfer learning evolutionary optimization method based on population distribution characteristics is proposed for solving DMOPs. First, mutual information is used to calculate the correlation between the optimal solutions from two consecutive environments before the environmental change. Then, the distribution characteristics of the highly correlated population individuals are extracted as valuable knowledge for the transfer process. This information is employed to guide the generation of new population individuals, which are then randomly introduced into the initial population generated by the DNSGA-II-A algorithm in the new environment, forming an improved initial population. Experimental results demonstrate that, the proposed DMOEA-TLF exhibits significant advantages in convergence and diversity in most cases. © 2024 IEEE.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Safe Priority Path Planning for Robots Based on Improved A∗ Algorithm 11

Safe Priority Path Planning for Robots Based on Improved A∗...

引用

11th International Forum on Electrical Engineering and Automation, IFEEA 2024

作者： Huang, Chen Luo, Lihong Wei, Xiaojie Chen, Junfeng School of Computer Science and Technology Guangdong University of Technology Guangzhou China School of Art and Design Guangdong University of Technology Guangzhou China

ISBN: (纸本)9798331516611

Aiming at the problems of too many redundant points and paths too close to obstacles generated by the traditional A∗ algorithm path planning, an improved A∗ path planning algorithm is proposed. Firstly, an algorithm is designed to adaptively expand the obstacles of the grid map so that there is enough safe distance between the planned path and the obstacles. Secondly, the algorithm is used to smooth the generated paths to reduce redundant points. In addition, as the optimisation algorithm reduces the search efficiency, the heuristic function of the algorithm is improved to increase the search efficiency. Finally, the search neighbourhood of the algorithm is transformed from 8-neighbourhood to mixed neighbourhood to further improve the search efficiency. Experimental results show that the proposed improved A∗ algorithm can effectively reduce the number of visited nodes, improve the path smoothness, and increase the path safety. © 2024 IEEE.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Scenario Model Predictive Control for Data-Based Energy Management in Plug-In Hybrid Electric Vehicles

引用

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY 2022年第6期30卷 2522-2533页

作者： East, Sebastian Cannon, Mark Univ Bristol Dept Aerosp Engn Bristol BS8 1TR Avon England Univ Oxford Dept Engn Sci Oxford OX1 3JP England

One of the major limitations of optimization-based strategies for allocating the power flow in hybrid powertrains is that they rely on predictions of future power demand. These predictions are inherently uncertain as they are dependent on complex human behaviors that are challenging to model accurately. This article proposes a data-based scenario model predictive control (MPC) framework, where the inputs are determined at each control update by optimizing the power allocation over multiple previous examples of a route being driven. The proposed energy management optimization is convex, and results from scenario optimization are used to bound the confidence that the one-step-ahead optimization will be feasible with given probability. It is shown through numerical simulation that scenario MPC obtains the same reduction in fuel consumption as nominal MPC with full preview of future driver behavior and that the scenario MPC optimization can be solved efficiently using a tailored optimization algorithm.

关键词： optimization Vehicles Engines Energy management Batteries Fuels Predictive models Hybrid and electric vehicles optimization algorithms predictive control for nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Q-DADAM: A Quantized Distributed Online optimization Algorithm With Adaptive Momentum

引用

IEEE Transactions on Control of Network Systems 2025年

作者： Li, Yantao Chen, Chen Zhang, Keke Li, Dong Lu, Qingguo Deng, Shaojiang Li, Huaqing Chongqing University College of Computer Science Chongqing400044 China Southwest University College of Electronic and Information Engineering Chongqing400715 China

This paper investigates distributed online optimization for a group of agents communicating on undirected networks. The objective is to collaboratively minimize the sum of locally known convex cost functions while overcoming the communication bandwidth limitations. To tackle this challenge, we propose the Q-DADAM algorithm, a quantized distributed adaptive momentum method that ensures agents interact with neighbors to optimize the global cost function collectively. Unlike many existing distributed online optimization algorithms that overlook communication bandwidth constraints, the Q-DADAM algorithm involves random quantization to effectively reduce the data transmission volume, making it more practical for applications with limited channel capacity. Different from existing algorithms that neglect adaptive momentum methods, the Q-DADAM algorithm incorporates these adaptive momentum methods, contributing to improved convergence and superior performance. Theoretical analysis demonstrates that the QDADAM algorithm with appropriate step size and quantization level can reduce communication traffic and achieve sublinear dynamic regret. Simulation experiments validate the practicality and effectiveness of the Q-DADAM algorithm. In addition, we discuss the impacts on the convergence of the Q-DADAM algorithm under different quantization levels and the number of agents. © 2014 IEEE.

关键词： optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：