安全仪表系统设计的多目标优化

安全仪表系统在过程工业中日益受到更多关注,为满足安全仪表系统多目标优化问题对于安全完整性等级的综合要求,提出一种改进的多目标遗传优化方法.首先研究了安全仪表系统多目标优化中存在的问题,然后结合安全仪表系统优化问题的特殊性提出了一种更加适合用于安全仪表系统多目标优化的方法,最后将该方法应用于一个实例.结果表明:改进的方法能够解决安全仪表系统优化对于安全完整性等级要求的优化偏好问题,所得到的解比原有方法的解更具参考价值.     

基于RFID和遗传算法的实时炸药仓储优化操作

针对炸药仓储过程管理的优化问题,提出基于RFID和遗传算法的在线炸药仓储优化操作方法,使炸药仓储管理过程更具高效化、信息化、安全化和智能化。利用RFID技术实时获取炸药仓库信息,提出了炸药仓库库位分区策略。通过对炸药仓储工作特点及要求分析,建立炸药仓储的优化数学模型,并运用遗传算法求解模型得到优化解。实验仿真结果表明,该方法能够提高仓库的空间利用率,优化炸药存取过程的行走路径,较好地解决了受炸药有效期等约束的优化操作问题。     

经济效益下电力物资仓储业务多目标优化模型

为了在良好经济效益作用下,实现对电力物资仓储业务的多目标优化处理,提出一种基于博弈相关性特征分析的经济效益下电力物资仓储业务多目标优化模型。首先在关联规则集中提取经济效益下的电力物资仓储业务;然后通过模糊关联规则多目标优化方法进行电力物资仓储业务的特征分解与优化提取,完成既定仓储业务的集中性多目标优化;再采用博弈相关性特征分析方法进行经济效益下电力物资仓储业务的自适应分块匹配;最后结合深度学习方法,实现经济效益下电力物资仓储业务的多目标优化决策。实验结果表明,应用新型优化模型后,电力物资仓储业务的多目标决策评估水平明显提升,从根本上提高了经济效益下电力物资仓储业务的调度能力。     

煤矿生产物流系统安全资源配置研究

针对煤矿生产物流系统安全资源配置问题,在构建基于安全风险及安全成本的安全资源指标体系基础上,运用回归分析法拟合了安全风险与安全成本目标函数,并构建了煤矿生产物流系统安全资源配置多目标优化模型,采用自适应进化粒子群算法对该模型进行优化求解。实例结果表明,采用自适应进化粒子群算法能够得出满足煤矿生产物流系统安全资源配置多目标优化要求的不同可行解。     

响应动态约束条件的多目标货位优化算法研究

针对自动化立库货位决策与优化问题,考虑到优化目标多样、托盘使用状态及可分配货位动态变化等因素,提出了一种响应动态约束条件的多目标货位优化算法。以巷道作业均衡、货架重心稳定及作业路径最短建立多目标优化模型,基于变异系数自适应差分进化算法,使用货位随机数编码,根据实时货位可行域进行个体解码,以响应动态货位约束条件。提出了基于层次分析的Pareto解评价方法,从而获得多批作业货位持续优化的目标权重,为仓储货位决策提供合理方案。多批作业算法实验结果表明:所提算法效果显著优于多目标简单加权算法,能够有效应用于动态货位决策与优化。     

面向大型工程多安全指标的解析可追溯安全控制方法

安全控制是开展一系列大型工程的重要前提之一,但大型工程往往受多种因素影响且同时需要考虑多个安全指标,对此,提出一种基于置信规则库(belief rule base, BRB)的具有解析和可追溯特征的多目标安全控制方法.首先,面向多个安全指标建立多个BRB;其次,计算各影响因素对各安全指标的贡献度,根据贡献度值得到面向单个安全指标的关键因素序列;再次,综合获得面向多个安全指标的关键因素序列;最后,仅针对面向多安全指标的关键因素开展多目标优化.以隧道施工过程中地面沉降值和建筑斜率作为目标开展安全控制.实例结果表明,所提出方法能够精准识别关键因素,通过优化关键因素可以有效降低地面沉降值和建筑斜率.此外,还进一步研究了关键因素数量对安全控制过程和结果的影响.     

多模态多目标优化综述

随着工业生产和日常生活需求的多样化,单个解决方案已经无法满足生产生活的需求.多模态优化可以为决策者提供多个可行方案,但是早期对多模态优化的研究局限在单目标优化中.在多目标优化中也存在多模态优化问题,其存在多个全局或局部帕累托最优解集,找到这些最优解集具有重大的理论和实际意义.鉴于此,首先,介绍多模态多目标优化问题的特点和求解难点;其次,综述求解此类问题的主要方法,总结这些方法的优缺点;再次,介绍常用的多模态多目标优化标准测试函数集和性能评价指标;最后,给出多模态多目标优化的应用领域及未来的研究方向.     

基于多任务强化学习的堆垛机调度与库位推荐

堆垛机调度是物流仓储自动化中的重要任务,任务中的出入库效率、货物存放等情况影响仓储系统的整体效益。传统调度方法在面对较大规模调度问题时,因处理大状态空间从而导致性能受限和收益降低。与此同时,库位优化与调度运行联系密切,但现有多数工作在处理调度问题时未能考虑到库位优化问题。为解决仓储中堆垛机调度问题,提出一种基于深度强化学习算法的近端策略优化调度方法。将调度问题视为序列决策问题,通过智能体与环境的持续交互进行自我学习,以在不断变化的环境中优化调度。针对调度中伴生的库位优化问题,提出一种基于多任务学习的调度、库位推荐联合算法,并基于调度网络构建适用于库位推荐的Actor网络,通过与Critic网络进行交互反馈,促进整体的联动和训练,从而提升整体效益。实验结果表明,与原算法模型相比,该调度方法的累计回报值指标平均提升了33.6%,所提的多任务学习的联合算法能有效地应对堆垛机调度和库位优化的应用场景,可为该类多任务问题提供可行的解决方案。     

基于个人偏好的多目标优化问题目标权重计算方法

针对多目标优化过程中如何根据个人偏好确定各目标权重的问题,提出一种约束优化方法以获得各目标的最佳权重.首先,将目标权重计算问题转化为综合适应度最大方差计算问题;然后,将个人偏好转化为最大方差问题不等式约束条件;最后,利用遗传算法和梯度投影法求解约束优化问题以获得最佳的目标权重.在电力机车故障维修策略决策过程中应用该算法计算各部件经济性、安全性等目标权重,实验结果验证了所提出方法能够获得满足个人偏好的最佳目标权重.     

基于灰色综合关联分析的多目标优化方法

针对现有多目标优化方法存在的搜索性能弱、效率低等问题,提出一种基于灰色综合关联分析的多目标优化方法.该多目标优化方法采用单目标优化算法构建高质量的参考序列,计算参考序列与优化解的目标函数值序列之间的灰色综合关联度,定义基于灰色综合关联度的解支配关系准则,将灰色综合关联度作为多目标优化算法的适应度值.以带顺序相关调整时间的多目标流水车间调度问题作为应用对象,建立总生产成本、最大完工时间、平均流程时间及机器平均闲置时间的多目标函数优化模型.提出基于灰色关联分析的多目标烟花算法,对所建立的多目标优化模型进行优化求解.仿真实验表明,所提出多目标烟花算法的性能优于3种基于不同多目标优化方法的烟花算法及两种经典多目标算法,验证了所提出的多目标优化方法及多目标算法的可行性和有效性.     

Multi-objective optimization of electronic product goods location assignment in stereoscopic warehouse based on adaptive genetic algorithm

Storage is an important part of commodity circulation. A certain amount of material must be stored to meet the needs of social production and consumption within a certain time to maintain the smooth process of social reproduction. This study focuses on warehousing optimization and goods location assignment when electronic products are stored in a stereoscopic storehouse. Moreover, this study is based on a theoretical study on genetic algorithm. On the basis of the background of the current warehouse management and cargo distribution of LCM module products warehouse belonging to W company, this study uses the dynamic goods location assignment strategy of stochastic inventory, and builds a multi-objective goods location assignment model of a stereoscopic warehouse. To simplify the calculations and improve the efficiency, we conduct a Matlab simulation on the basis of practical data by adopting a modified genetic operator and converting multi-objective optimization by the changing weight coefficient. The adaptive genetic algorithm can be used to make a multi-objective goods location assignment model that efficiently converges to the optimal solution.     

Multi-objective optimal scheduling of reconfigurable assembly line for cloud manufacturing

We propose a multi-objective optimization scheduling model to improve the production efficiency of a reconfigurable assembly line. We aim to minimize the costs of assembly line reconstruction, achieve the production load equalization, and minimize the delayed workload using this model. However, the proposed multi-objective optimization model is significantly complex for conventional mathematical optimization methods. Thus, we present an efficient solution approach based on a distance sorting particle swarm optimization. Finally, a case study is conducted to illustrate the feasibility and efficiency of the proposed method. Experimental results indicate that our proposed approach can significantly improve the production efficiency (i.e. increased production load balance, minimized reconstruction cost, and minimized delayed workload).     

Multi-objective simulation optimization for uncertain resource assignment and job sequence in automated flexible job shop

In this study a multi-objective problem considering uncertainty and flexibility of job sequence in an automated flexible job shop (AFJS) is considered using manufacturing simulation. The AFJS production system is considered as a complex problem due to automatic elements requiring planning and optimization. Several solution approaches are proposed lately in different categories of meta-heuristics, combinatorial optimization and mathematically originated methods. This paper provides the metamodel using simulation optimization approach based on multi-objective efficiency. The proposed metamodel includes different general techniques and swarm intelligent technique to reach the optimum solution of uncertain resource assignment and job sequences in an AFJS. In order to show the efficiency and productivity of the proposed approach, various experimental scenarios are considered. Results show the optimal resources assignment and optimal job sequence which cause efficiency and productivity maximization. The makespan, number of late jobs, total flow time and total weighted flow time minimization have been resulted in an automated flexible job shop too.     

QPSO算法求解无约束多目标优化问题

在分析了用基于目标加权的PSO算法(WAPSO)的基础上,研究了利用基于量子行为的微粒群优化算法(QPSO)来解决多目标优化问题.提出了基于目标加权的QPSO算法(WAQPSO),利用WAQPSO算法解决无约束的多目标优化问题,通过典型的多目标测试函数实验,验证了该算法解决无约束多目标问题的有效性.     

基于DTC-MOPSO算法的焊接机器人路径规划

点焊机器人在汽车白车身焊接中的应用大大提高了企业的生产效率,本文从焊接路径长度和能量两方面进行焊接机器人多目标路径规划．为了很好地解决这个问题,本文对一种新型多目标粒子群算法（三态协调搜索多目标粒子群优化算法）进行改进,得到适合于求解离散多目标优化问题的离散化三态协调搜索多目标粒子群算法（DTC-MOPSO）．通过和两个经典的优化算法比较,DTC-MOPSO算法在分散性和收敛性方面都有很好的优化性能．最后运用Matlab机器人工具箱对机器人的运动学、逆运动学以及逆动力学进行分析以求解机器人的路径长度和能耗,并将改进的算法应用于焊接机器人路径规划中,结果显示规划后的路径明显优于另外两种算法.     

网络社区发现的多目标分解粒子群优化算法

通过分析社会网络中社区发现问题的优化目标,构造了社区发现的多目标优化模型,提出一种网络社区发现的多目标分解粒子群优化算法。该算法采用切比雪夫法将多目标优化问题分解为多个单目标优化子问题,使用粒子群优化(PSO)算法对社区结构进行挖掘,并引入了一种新颖的基于局部搜索的变异策略以提高算法的搜索效率和收敛速度,该算法克服了单目标优化算法存在的解单一以及难以发现社区层次结构的缺陷。人工网络及真实网络上的实验结果表明,该算法能够快速准确地挖掘网络社区并揭示社区的层次结构。     

Constrained multi-objective optimization algorithms: Review and comparison with application in reinforced concrete structures

Engineering design problems are often multi-objective in nature, which means trade-offs are required between conflicting objectives. In this study, we examine the multi-objective algorithms for the optimal design of reinforced concrete structures. We begin with a review of multi-objective optimization approaches in general and then present a more focused review on multi-objective optimization of reinforced concrete structures. We note that the existing literature uses metaheuristic algorithms as the most common approaches to solve the multi-objective optimization problems. Other efficient approaches, such as derivative-free optimization and gradient-based methods, are often ignored in structural engineering discipline. This paper presents a multi-objective model for the optimal design of reinforced concrete beams where the optimal solution is interested in trade-off between cost and deflection. We then examine the efficiency of six established multi-objective optimization algorithms, including one method based on purely random point selection, on the design problem. Ranking and consistency of the result reveals a derivative-free optimization algorithm as the most efficient one.     

Mixed-model assembly line balancing using a multi-objective ant colony optimization approach

Mixed-model assembly lines are production systems at which two or more models are assembled sequentially at the same line. For optimal productivity and efficiency, during the design of these lines, the work to be done at stations must be well balanced satisfying the constraints such as time, space and location. This paper deals with the mixed-model assembly line balancing problem (MALBP). The most common objective for this problem is to minimize the number of stations for a given cycle time. However, the problem of capacity utilization and the discrepancies among station times due to operation time variations are of design concerns together with the number of stations, the line efficiency and the smooth production. A multi-objective ant colony optimization (MOACO) algorithm is proposed here to solve this problem. To prove the efficiency of the proposed algorithm, a number of test problems are solved. The results show that the MOACO algorithm is an efficient and effective algorithm which gives better results than other methods compared.     

Harmony search-based multi-objective optimization model for multi-site order planning with multiple uncertainties and learning effects

This paper addresses a multi-objective multi-site order planning problem in make-to-order manufacturing with the consideration of various real-world features such as production uncertainties and learning effects. A novel harmony search-based multi-objective optimization model, mainly integrating a harmony search based Pareto optimization (HSPO) process and a Monte Carlo simulation process, is developed to tackle this problem. A series of experiments are conducted to evaluate the effectiveness of the proposed model based on real industrial data. Results demonstrate that (1) the proposed model can effectively solve the problem investigated; and (2) the HSPO process can generate the optimization performance superior to those generated by a multi-objective genetic algorithm (NSGA-II)-based process and an industrial method.