检索结果-内蒙古大学图书馆

Hybrid artificial immune algorithm for energy-efficient distributed flexible job shop in semiconductor manufacturing

引用

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2024年第3期27卷 3075-3098页

作者： Chen, Xiaolong Du, Yu Shandong Normal Univ Sch Informat Sci & Engn Jinan 250014 Peoples R China HengXing Univ Sch Informat Engn Qingdao Peoples R China Univ Jinan Sch Informat Sci & Engn Jinan 250022 Peoples R China

In semiconductor manufacturing, constraints, including multiple scheduling routes, complex production processes, and robotic transportation, particularly bring difficult challenges to production schedules. To address this issue, we investigated an energy-efficient distributed flexible job shop scheduling problem with robotic transportation. In the considered problem, two objectives, i.e., the maximum completion time and total energy consumption, are minimized simultaneously. First, two mixed integer linear programming models are constructed, including the sequence-based and position-based models. Then, a hybrid algorithm combining the artificial immune algorithm and variable neighborhood search algorithm is proposed. To generate a population with better performance and diversity, five initialization strategies and an active decoding method are designed. In addition, a novel clone mechanism and an improved suppression process are being developed to improve the exploration abilities. Furthermore, two distinct neighborhood structures and two object-oriented local search heuristics are designed to balance exploration and exploitation capabilities. Eventually, the proposed algorithm achieved better performance with the comparison of three other state-of-the-art algorithms with different scale instances.

关键词： Distributed flexible job shop scheduling problem Robotic transportation Mixed integer linear programming models artificial immune algorithm Variable neighborhood search algorithm

来源：评论

学校读者我要写书评

暂无评论

Reduced algorithm of laser measurement data for geometric parameters of ring forgings based on artificial immune algorithm

引用

MEASUREMENT 2019年 134卷 527-538页

作者： Zhang, YuCun Wu, Menglin Fu, XianBin Li, Qun Gao, JunHua Yanshan Univ Sch Elect Engn Qinhuangdao Hebei Peoples R China Hebei Univ Environm Engn Qinhuangdao Hebei Peoples R China Yanshan Univ Sch Mech Engn Qinhuangdao Hebei Peoples R China

Measuring the geometric parameters of ring forgings by laser scanner is an important way to ensure the quality of processing. However, the amount of data obtained by scanner is huge and the noise is complex. The process of data processing is slow. It is impossible to ensure the real-time quality monitoring. Therefore, an improved Quadratic Error Metric (QEM) point cloud data reduction algorithm based on artificial immune algorithm (AIA) is proposed in this study. As for AIA, the choice of antigen and antibody is the critical step. The candidate point cloud is used as the antibody. The antigen is divided into two parts. The first part is the cost function. The cost function is made up of the squares sum of the volumes for two tetrahedra. This is an improved algorithm of QEM. The second part is the optimal solution of the cost function. The antibodies are screened by using the specific reactions between antigens and antibodies, antibodies and antibodies. The point cloud data can be reduced by these specific reactions. Finally, the algorithm is applied to the experiment of measuring the geometric parameters of typical ring forging. The experimental results show that the reduced data can quickly reconstruct the model. The precision of the size parameters for the model can be ensured through the algorithm proposed in the study. Through the comparison experiments, the advantages of the reduced method of the algorithm are further proved. Meanwhile, the real-time performance of the on-line monitoring of the quality for the ring forging can be improved. The measuring method proposed is feasible according to the experimental results. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： artificial immune algorithm Laser measurement Point cloud reduction Quadric Error Metric Ring forging

来源：评论

学校读者我要写书评

暂无评论

A hybrid artificial immune algorithm for a realistic variant of job shops to minimize the total completion time

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2009年第4期56卷 1494-1501页

作者： Naderi, B. Khalili, M. Tavakkoli-Moghaddam, R. Univ Tehran Dept Ind Engn Coll Engn Tehran Iran Amirkabir Univ Technol Dept Ind Engn Tehran Iran Islamic Azad Univ Dept Ind Engn S Tehran Branch Tehran Iran

This paper investigates an extended problem of job shop scheduling to minimize the total completion time. With aim of actualization of the scheduling problems, many researchers have recently considered realistic assumptions in their problems. Two of the most applied assumptions are to consider sequence-dependent setup times and machine availability constraints (MACs). In this paper, we deal with a specific case of MACs caused by preventive maintenance (PM) operations. Contrary to the previous papers considering fixed or/and conservative policies, we consider flexible PM operations, in which PM operations may be postponed or expedited as required. A simple technique is employed to schedule production jobs along with the flexible MACs caused by PM. To solve the given problem, we present a novel meta-heuristic method based on the artificial immune algorithm (AIA) incorporating some advanced features. For further enhancement, the proposed AIA is hybridized with a simple and fast simulated annealing (SA). To evaluate the proposed algorithms, we compare our proposed AIA with three well-known algorithms taken from the literature. Finally, we find that the proposed AIA outperforms other algorithms. (C) 2008 Elsevier Ltd. All rights reserved.

关键词： Job shop scheduling Total completion time Sequence-dependent setup times Flexible machine availability artificial immune algorithm

来源：评论

学校读者我要写书评

暂无评论

An artificial immune algorithm for the flexible job-shop scheduling problem

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2010年第4期26卷 533-541页

作者： Bagheri, A. Zandieh, M. Mahdavi, Iraj Yazdani, M. Shahid Beheshti Univ GC Dept Ind Management Management & Accounting Fac Tehran Iran Mazandaran Univ Sci & Technol Dept Ind Engn Babol Sar Iran Qazvin Islamic Azad Univ Fac Ind & Mech Engn Qazvin Iran

This article addresses the flexible job-shop scheduling problem (FJSP) to minimize makespan. The FJSP is strongly NP-hard and consists of two sub-problems. The first one is to assign each operation to a machine out of a set of capable machines, and the second one deals with sequencing the assigned operations on all machines. To solve this problem, an artificial immune algorithm (AIA) based on integrated approach is proposed. This algorithm uses several strategies for generating the initial population and selecting the individuals for reproduction. Different mutation operators are also utilized for reproducing new individuals. To show the effectiveness of the proposed method, numerical experiments by using benchmark problems are conducted. Consequently, the computational results validate the quality of the proposed approach. (C) 2009 Elsevier B.V. All rights reserved.

关键词： Scheduling Flexible job-shop Makespan artificial immune algorithm

来源：评论

学校读者我要写书评

暂无评论

Feature selection optimized by the artificial immune algorithm based on genome shuffling and conditional lethal mutation

引用

APPLIED INTELLIGENCE 2023年第11期53卷 13972-13992页

作者： Zhu, Yongbin Li, Tao Lan, Xiaolong Sichuan Univ Coll Cybersecur Chengdu 610065 Peoples R China

Improving classification performance is an essential goal for various practical applications. Feature selection has become an important data preprocessing step in machine learning systems. However, many effective methods based on heuristic search strategies have the problem of high running costs. This paper proposes an efficient multiobjective feature selection method based on artificial immune algorithm optimization. It introduces a clone selection algorithm to explore the search space of optimal feature subsets. According to the target requirements of feature selection, combined with biological research results, this method introduces genome shuffling technology and a conditional lethal mutation mechanism to improve the search performance of the algorithm. Experimental comparisons are conducted on 21 benchmark datasets with 17 advanced feature selection methods in terms of classification accuracy, the number of feature subsets, and computational cost. The results show that the algorithm achieves the smallest number of selected features (only 3.26% compared to the lowest) and better average classification accuracy with a much lower average computational cost than others (only 3.62% compared to the lowest).

关键词： Feature selection Dimensionality reduction Multiobjective optimization artificial immune algorithm Classification

来源：评论

学校读者我要写书评

暂无评论

An artificial immune algorithm for ergonomic product classification using anthropometric measurements

引用

MEASUREMENT 2016年 94卷 621-629页

作者： Tavana, Madjid Kazemi, Mohammad Reza Vafadarnikjoo, Amin Mobin, Mohammadsadegh La Salle Univ Business Syst & Analyt Dept Distinguished Chair Business Syst & Analyt Philadelphia PA 19141 USA Univ Paderborn Business Informat Syst Dept Fac Business Adm & Econ D-33098 Paderborn Germany Mazandaran Univ Sci & Technol Ind Engn Dept Babol Sar Iran Allameh Tabatabai Univ Management & Accounting Dept Tehran Iran Western New England Univ Ind Engn & Engn Management Dept Springfield MA 01119 USA

Product classification using anthropometric measurements leads to ergonomic product design and user satisfaction. We propose an effective artificial immune algorithm (AIA) to classify ergonomic products with multi-criteria anthropometric measurements and tune the AIA parameters with a full factorial experimental design approach. We demonstrate the applicability and efficacy of the proposed algorithm by considering the anthropometric measurements of the hand, developing an ergonomic computer mouse, and classifying consumers into three categories. The resulting classifications are compared with expert opinions to facilitate the conformity of the computer mouse to user requirements. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Ergonomic product classification Anthropometric measurements artificial immune algorithm Ergonomic product design Meta-heuristic

来源：评论

学校读者我要写书评

暂无评论

Binary artificial immune algorithm for Adaptive Visual Detection

引用

IEEE ACCESS 2018年 6卷 51587-51597页

作者： Gao, Wei Zhang, Jinling Liu, Qiaoyuan Jiang, Longkui Wang, Yuru Yin, Minghao Zhou, Yupeng Beihang Univ Sch Astronaut Beijing 100083 Peoples R China North East Normal Univ Comp Sci & Informat Technol Changchun 130024 Jilin Peoples R China Jilin Business & Technol Coll Sch Informat Engn Changchun 130062 Jilin Peoples R China

A visual model plays an important role in developing an efficient and robust visual tracker. The visual cues employed in the state-of-the-art models are usually predefined and fixed for all the tested videos. However, the discriminative ability of features usually varies among videos. Therefore, using a fixed set is both redundant and noisy: only a subset of any fixed set will present distinct profiles for modeling. Thus, selecting a highly discriminative cue subset in visual modeling should improve the tracking accuracy. In this paper, an optimization method based on a binary artificial immune algorithm is proposed that selects an effective, discriminative feature subset that is adaptive to specific videos. Specifically, a metric is defined to measure the discriminative abilities of visual models. Then, the visual modeling problem is transformed into an optimization scheme, and a binary artificial immune algorithm is introduced and specially designed to solve the modeling problem. Moreover, to preserve the subset of visual cues that are most adaptive to the tracking condition, the selected cues are assigned adaptive weights and modeled in a Sequential Monte Carlo framework. To show its effectiveness, the proposed algorithm is tested on ten representative videos. The experimental results demonstrate the improvement in tracking performance, the improved tracker performs better or comparable with previous excellent trackers from the literature.

关键词： artificial immune algorithm binary visual model tracking

来源：评论

学校读者我要写书评

暂无评论

Effect of hybridizing Biogeography-Based Optimization (BBO) technique with artificial immune algorithm (AIA) and Ant Colony Optimization (ACO)

引用

APPLIED SOFT COMPUTING 2014年 21卷 542-553页

作者： Savsani, Poonam Jhala, R. L. Savsani, Vimal Pacific Acad Higher Educ & Res Dept Mech Engn Udaipur Rajasthan India Gujarat Technol Univ Dept Mech Engn Gandhinagar Gujarat India Pandit Deendayal Petr Univ Dept Mech Engn Gandhinagar Gujarat India

Hybridization in optimization methods plays a very vital role to make it effective and efficient. Different optimization methods have different search tendency and it is always required to experiment the effect of hybridizing different search tendency of the optimization algorithm with each other. This paper presents the effect of hybridizing Biogeography-Based Optimization (BBO) technique with artificial immune algorithm (AIA) and Ant Colony Optimization (ACO) in two different ways. So, four different variants of hybrid BBO, viz, two variants of hybrid BBO with AIA and two with ACO, are developed and experimented in this paper. All the considered optimization techniques have altogether a different search tendency. The proposed hybrid method is tested on many benchmark problems and real life problems. Friedman test and Holm-Sidak test are performed to have the statistical validity of the results. Results show that proposed hybridization of BBO with ACO and AIA is effective over a wide range of problems. Moreover, the proposed hybridization is also effective over other proposed hybridization of BBO and different variants of BBO available in the literature. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Hybrid metaheuristics Biogeography Based Optimization Ant Colony Optimization artificial immune algorithm

来源：评论

学校读者我要写书评

暂无评论

The Analysis of Blockchain Digital Currency Product Innovation Based on artificial immune algorithm

引用

IEEE ACCESS 2022年 10卷 132448-132454页

作者： Chen, Hong Su, Kecheng Gao, Wandong Guangzhou Xinhua Univ Sch Management Guangzhou 510520 Peoples R China Univ Southern Calif Marshall Business Sch Los Angeles CA 90007 USA Weifang Univ Sci & Technol Sch Econ & Management Shouguang 262700 Peoples R China

In recent years, with the rapid growth of the digital currency industry, blockchain technology has attracted wide attention, and its research mostly focuses on the protection of economic security and privacy. In order to study the application and development mechanism of currency products, this work investigates the practical application of digital currency products under blockchain technology at the present stage, and analyzes the potential security risks. The artificial immune algorithm (AIA) is an intelligent method to imitate the function of the biological immune system, which provides a new solution for solving complex distributed problems. Firstly, a blockchain digital currency product is proposed based on AIA. Secondly, taking the credit risk of innovation risk in financial currency products as an example, the Diffie-Hellman (DH) with blockchain technology is used. Finally, the generation and optimization of the plan are realized, and an innovative risk plan is proposed for blockchain digital currency products on the basis of AIA. The results show that: (1) The improved AIA implements a guided AIA with adaptive parameter update. (2) The digital signature technology using the DH algorithm has a stronger anti-attack ability than the traditional blockchain digital signature technology. It improves the security of blockchain digital currency. This work has successfully established the risk-immune system of digital currency product innovation, laying a theoretical foundation for the innovation and development of blockchain digital currency products in the future.

关键词： artificial intelligence artificial immune algorithm blockchain DH algorithm digital currency innovation risk potential risk

来源：评论

学校读者我要写书评

暂无评论

An artificial immune algorithm for multiple-route job shop scheduling problem

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2012年第1-4期63卷 77-86页

作者： Golmakani, Hamid Reza Namazi, Ali Tafresh Univ Dept Ind Engn Tehran Iran

This paper addresses the multiple-route job shop scheduling problem to minimize makespan. The problem is recognized to be extremely difficult because of its combinatorial nature of integer optimization and the large size of the real problem. The goal is, thus, to obtain near-optimal schedules in a computationally efficient manner. Mathematical formulation of the problem is first presented. Then, an approach based on artificial immune algorithm is proposed. In order to evaluate the effectiveness of the proposed approach, 30 problems in small, medium, and large size are designed and solved using the proposed approach. Problems are also solved using Lingo software and the results are compared. The computational results show that the proposed approach generates high-quality schedules in a timely fashion.

关键词： Multiple-route Job shop scheduling artificial immune algorithm Makespan

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：