检索结果-内蒙古大学图书馆

3rd International Conference on Electrical, Control and Instrumentation Engineering (ICECIE)

作者： Liu, Haitao Geng, Zongpu Zhang, Kuangyi Yuan, Huajun Ye, Xiaoyi Nanjing Inst Technol Sch Elect Power Engn Nanjing Peoples R China

ISBN: (纸本)9781665449663

Newton method is the core algorithm in most of the multi energy flow calculation of the integrated electricity-gas system, which has initial value sensitivity problem. There is no effective initial value calculation method at present for the natural gas subsystem which is difficult to converge in the integrated energy system with flat start up. In view of this, in this paper, by combining the differential evolution algorithm with the ability of global optimization and Newton convergence law, the DE method termination condition based on parameter convergence operator is derived, and a hybrid DE-Newton method for energy flow calculation of integrated electricity-gas system is proposed. The hybrid DE-Newton method utilizes the global search ability of differential evolution algorithm, which can quickly get reasonable initial value of natural gas system with better convergence, and effectively improve the convergence problem of Newton method with flat start up while maintaining high calculation efficiency. The feasibility and superiority of the proposed method are verified by two examples of 6-node natural gas system and 15-node integrated electricity-gas system.

关键词： Integrated energy system initial value calculation energy flow calculation differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

evolutionary Generation of Test Case for Deep Neural Network Based on Coverage Guidance 3

Evolutionary Generation of Test Case for Deep Neural Network...

引用

3rd IEEE International Conference on Artificial Intelligence Testing (AITest)

作者： Hu, Liming Ji, Shunhui Dai, Qiyin Zhang, Pengcheng Hohai Univ Coll Comp & Informat Nanjing Peoples R China

ISBN: (纸本)9781665434812

In the past few years, Deep Neural Network(DNN) has made great progress. However, it is difficult to guarantee that DNN-based applications can get satisfactory results. Testing is an effective technology to improve the accuracy and robustness of DNN, in which test case generation is an important task. In this paper, we combine the differential evolution algorithm and coverage criterion which is stronger than neuron coverage to generate test cases for DNN. This method uses the prediction loss of DNN and coverage criterion as the fitness function to generate small perturbations at the pixel level between different channels of the image. Then the generated perturbations are added to the image to construct a test case. Theoretically, the test cases generated by this method can not only make the neural network produce misclassification, but also achieve higher coverage for neurons in the DNN, so that defects in DNN can be detected more comprehensively.

关键词： Deep Neural Network Test Case Generation Coverage Criterion differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive differential evolution with Elite Opposition-Based Learning and its Application to Training Artificial Neural Networks

引用

FUNDAMENTA INFORMATICAE 2019年第2-3期164卷 227-242页

作者： Choi, Tae Jong Lee, Jong-Hyun Youn, Hee Yong Ahn, Chang Wook Sungkyunkwan Univ SKKU Coll Software 2066 Seobu Ro Suwon Gyeonggi Do South Korea GIST Sch Elect Engn & Comp Sci 123 Cheomdangwagi Ro Gwangju South Korea

differential evolution (DE) algorithm is one of the popular evolutionary algorithms that is designed to find a global optimum on multi-dimensional continuous problems. In this paper, we propose a new variant of DE algorithm by combining a self-adaptive DE algorithm called dynNP-DE with Elite Opposition-Based Learning (EOBL) scheme. Since dynNP-DE algorithm uses a small number of population size in the later of the search process, the population diversity becomes low, and therefore premature convergence may occur. We have therefore extended an OBL scheme to dynNP-DE algorithm to overcome this shortcoming and improve the optimization performance. By combining EOBL scheme to dynNP-DE algorithm, the population diversity can be supplemented because not only the information of individuals but also their opposition information can be utilized. We measured the optimization performance of the proposed algorithm on CEC 2005 benchmark problems and breast cancer detection, which is a research field that has recently attracted a lot of attention. It was verified that the proposed algorithm could find better solutions than five state-of-the-art DE algorithms.

关键词： Artificial Neural Networks differential evolution algorithm Opposition-Based Learning Feed-Forward Neural Network Neural Network Training

来源：评论

学校读者我要写书评

暂无评论

No-Wait Open-Shop Scheduling Problems with Reverse Flows

Journal of Engineering Research (Kuwait)

引用

Journal of Engineering Research (Kuwait) 2024年

作者： Aghighi, Saba Mehdizadeh, Esmaeil Niaki, Seyed Taghi Akhavan Department of Industrial Engineering Faculty of Industrial and Mechanical Engineering Qazvin Branch Islamic Azad University Qazvin Iran Department of Industrial Engineering Sharif University of Technology Tehran Iran

Open shop scheduling has a special place in both production and optimization problems. This study investigates an assembly (direct flow) and disassembly (reverse flow) scheduling problem in an open shop environment where both are processed on the same machine, but only one is a no-wait operation. The objective is to minimize makespan of jobs on all machines. A mixed-integer linear program is developed. GAMS 25.1.1.2 is used to solve small size test problems. differential evolution (DE) algorithm is applied to large-scale problems. A comparison of the computing results of this algorithm and the Genetic algorithm (GA), Whale Optimization algorithm (WOA), Bat algorithm (BA), Artificial bee colony algorithm (ABC), and vibration damping optimization algorithm (VDO) is presented. Based on the results obtained, it has been found that there are no obvious differences between the performance of the algorithms, but the DE algorithm produces better solutions. © 2024 The Authors

关键词： differential evolution algorithm No-wait Open-shop Reverse Flow Scheduling

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Swarm Optimization algorithm in Temperature Compensation of Pressure Sensors

引用

SENSORS 2022年第21期22卷 8309-8309页

作者： Wang, Hexing Li, Jia Chinese Acad Sci Inst Microelect Beijing 100029 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

The main temperature compensation method for MEMS piezoresistive pressure sensors is software compensation, which processes the sensor data using various algorithms to improve the output accuracy. However, there are few algorithms designed for sensors with specific ranges, most of which ignore the operating characteristics of the sensors themselves. In this paper, we propose three temperature compensation methods based on swarm optimization algorithms fused with machine learning for three different ranges of sensors and explore the partitioning ratio of the calibration dataset on Sensor A. The results show that different algorithms are suitable for pressure sensors of different ranges. An optimal compensation effect was achieved on Sensor A when the splitting ratio was 33.3%, where the zero-drift coefficient was 2.88 x 10(-7)/degrees C and the sensitivity temperature coefficient was 4.52 x 10(-6)/degrees C. The algorithms were compared with other algorithms in the literature to verify their superiority. The optimal segmentation ratio obtained from the experimental investigation is consistent with the sensor operating temperature interval and exhibits a strong innovation.

关键词： pressure sensor temperature compensation differential evolution algorithm quantum particle swarm optimization dataset partitioning

来源：评论

学校读者我要写书评

暂无评论

A Wind Power Prediction Method Based on DE-BP Neural Network

引用

FRONTIERS IN ENERGY RESEARCH 2022年 10卷

作者： Li, Ning Wang, Yelin Ma, Wentao Xiao, Zihan An, Zhuoer Xian Univ Technol Sch Elect Engn Xian Peoples R China

With the continuous increase of installed capacity of wind power, the influence of large-scale wind power integration on the power grid is becoming increasingly apparent. Ultra-short-term wind power prediction is conducive to the dispatching management of the power grid and improves the operating efficiency and economy of the power system. In order to overcome the intermittency and uncertainty of wind power generation, this article proposes the differential evolution-back propagation (DE-BP) algorithm to predict wind power and addresses such shortcomings of the BP neural network as its falling into local optimality and slow training speed when predicting. In this article, the DE algorithm is used to find the optimal value of the initial weight and threshold of the BP neural network, and the DE-BP neural network prediction model is obtained. According to the data of a wind farm in Northwest China, the short-term wind power is predicted. Compared with the application of the BP model in wind power prediction, the results show that the accuracy of the DE-BP algorithm is improved by about 5%;compared with the genetic algorithm-BP model, the prediction time is shortened by 23.1%.

关键词： differential evolution algorithm wind power prediction BP neural network prediction time accuracy

来源：评论

学校读者我要写书评

暂无评论

A novel differential evolution algorithm for joint replenishment problem under interdependence and its application

引用

INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS 2012年第1期135卷 190-198页

作者： Wang, Lin He, Jing Wu, Desheng Zeng, Yu-Rong Univ Toronto RiskLab Toronto ON M5S 3G3 Canada Huazhong Univ Sci & Technol Sch Management Wuhan 430074 Peoples R China Hubei Univ Econ Sch Informat Management Wuhan 430205 Peoples R China

In this paper, we propose a new differential evolution (DE) algorithm for joint replenishment of inventory using both direct grouping and indirect grouping which allows for the interdependence of minor ordering costs. Since solutions to the joint replenishment problem (JRP) can be represented by integer decision variables, this makes the JRP a good candidate for the DE algorithm. The results of testing randomly generated problems in contrastive numerical examples and two extended experiments show that the DE algorithm provides close to optimal results for some problems than the evolutionary algorithm (EA), which has been proved to be an efficient algorithm. Moreover, the DE algorithm is faster than the EA for most problems. We also conducted a case study and application results suggest that the proposed model is successful in decreasing total costs of maintenance materials inventories significantly in two power companies. (C) 2011 Elsevier B.V. All rights reserved.

关键词： Joint replenishment Interdependence Minor ordering costs differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Constrained Handling Techniques of Constrained differential evolution algorithms Applied to Constrained Optimization Problems in Mechanical Engineering 3

Comparative Study of Constrained Handling Techniques of Cons...

引用

3rd Technology Innovation Management and Engineering Science International Conference (TIMES-iCON)

作者： Muangkote, Nipotepat Photong, Lersak Sukprasert, Anupong Mahasarakham Univ Mahasarakham Business Sch Dept Business Comp Maha Sarakham 44150 Thailand

ISBN: (纸本)9781538675731

Constrained optimization problems in mechanical engineering are very difficult for the optimization algorithm. In 2013, an improved version of constrained differential evolution, named ArATM-ICDE was proposed to optimize the constrained optimization problem. An archiving-based adaptive trade-off model (ArATM) was constructed to handle the constraints;resulting in an algorithm referred to as ArATM-ICDE. This paper applies ArATM-ICDE to solve constraint optimization problems in mechanical engineering. We also combine the penalty technique for constraint handling into the ICDE, named Penalty-ICDE;which compares the abilities of the constraint handling techniques. Our experiments were conducted on ten widely used constraint engineering optimization problems. The experiment results proved the ArATM-ICDE to be more reliable than the Penalty-ICDE. Additionally, ArATM-ICDE consumed a lesser number of function calls than Penalty-ICDE. This paper further compared the effectiveness of ArATM-ICDE and Penalty-ICDE with eight state-of-the-art algorithms, which revealed that ArATM-ICDE and Penalty-ICDE produced solutions of higher quality than those produced by the comparative algorithms. The ArATM-ICDE also consumed less effort in its process.

关键词： global optimization algorithm differential evolution algorithm mechanical engineering problem constrained handling techniques

来源：评论

学校读者我要写书评

暂无评论

Extension of terahertz time-domain spectroscopy: A micron-level thickness gauging technology

引用

OPTICS COMMUNICATIONS 2022年 506卷 127597-127597页

作者： Zhang, Hongzhen Shi, Lili He, Mingxia Tianjin Univ State Key Lab Precis Measuring Technol & Instrume Tianjin 300072 Peoples R China Tianjin Univ Sch Precis Instrument & Optoelect Engn Tianjin 300072 Peoples R China Nanjing Univ Sch Elect Sci & Engn Res Inst Superconductor Elect RISE Nanjing 210093 Peoples R China

There is a minimum measurable thickness when gauging micron-level coating films with time-of-flight based terahertz thickness measurement technologies. To improve this minimum measurable limit, a time-domain model of terahertz signals is derived by taking multiple reflected pulses into consideration, using the differential evolution algorithm to calibrate parameters automatically. Empirical Mode Decomposition is applied to remove noises and non-flat baselines introduced by water vapor and other structure-borne noise resources. Combining methods mentioned above, thicknesses of micron-level coating layers could be measured even if the Signal to Noise Ratio is not large enough, and the minimum measurable limit is also improved to about 40 mu m. Experiments also demonstrate that, during drying processes, the time gaps between pulses reflected from different interfaces shrink and the thicknesses change in an exponential trend, which reveals the potential of terahertz technologies in terms of monitoring coating processes.

关键词： Thickness measurement technology Empirical Mode Decomposition Terahertz time-domain spectroscopy differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimization control of hydrometallurgical leaching process based on IDE-MPC

引用

MINERALS ENGINEERING 2022年第0期176卷 107341-107341页

作者： Niu, Dapeng Liu, Xudong Liu, Yuanqing Jia, Mingxing Northeastern Univ Coll Informat Sci & Engn Shenyang Peoples R China

The utilization rate of raw materials during the hydrometallurgical leaching process has a great influence on the whole economic benefits of the hydrometallurgy plant, so it is necessary for the leaching process to improve the utilization of materials using optimization control methods. In this paper, the dynamic model for the hydrometallurgical leaching process of a gold hydrometallurgy plant is first built based on the reaction mechanism of the process. Then, the model parameters are identified using least-squares fitting. Thereafter, with the maximum economic benefit as the objective function, the steady-state economic optimization model of the leaching process is established, and an improved particle swarm optimization algorithm is used to solve the model. Taking the optimization results as the control objective, a model predictive control method based on an improved differential evolution algorithm is proposed to control the leaching process, so as to improve the intractability and anti-disturbance performance of the controller for the leaching process. The simulation results show that the proposed optimization and control methods achieve satisfactory effects.

关键词： Hydrometallurgical leaching process Optimization control Particle swarm optimization algorithm Model predictive control differential evolution algorithm

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：