基于Hopfield神经网络求解作业车间调度问题的新方法

对作业车间调度问题的换位矩阵表示方法进行了改进,给出新的作业车间调度问题的Hopfield神经网络计算能量函数表达式,然后提出改进的Hopfield神经网络作业车间调度方法。为了避免Hopfield神经网络容易收敛到局部极小的缺点,将模拟退火算法应用于Hopfield神经网络求解,提出随机神经网络作业车间调度方法。与已有算法相比,改进算法能够保证神经网络稳态输出为可行的作业车间调度方案。     

基于神经网络的Job-Shop类调度问题

提出了将Hopfield神经网络与模拟退火相结合以求解Job-Shop类调度问题的算法.该算法给出了Job-Shop类调度问题的约束条件,并且直接把问题的各种约束条件表示为Hopfield神经网络的能量函数项.为避免Hopfield神经网络容易收敛到局部极小解而产生非法调度解的缺点,将模拟退火算法应用于Hopfield神经网络求解,使Hopfield神经网络收敛到能量函数的全局最优解,从而保证神经网络输出是一个可行的调度方案.通过仿真实例验证了该算法的可行性.     

HIGH-ACCURACY SYNCHRONIZATION CONTROL WITH HYBRID NEURAL NETWORKS

A novel nonlinear control algorithm based on hybrid neural networks is presented to cope with the high-accuracy synchronization control problem for a dual-actuator electrohydraulic drive system which plays an important role for the development of elastomeric launchers. A new objective function for better synchronization performance is introduced and a learning algorithm to adjust the weights of the neural network, based on the gradient descent algorithm, is also derived. The hybrid neural network control algorithm guarantees high-accuracy synchronization performance of two motion cylinders and fast dynamic response as well as good stability of the control system. Prototype test results on the dual-actuator electrohydraulic drive system verifys the effectiveness of the proposed approach.     

基于Pearson关联度BP神经网络的时间序列预测

针对BP神经网络存在的过拟合问题,提出了基于Pearson关联度的神经网络预测模型。将传统的基于误差反向传播的BP神经网络中的误差函数替换为Pearson关联度函数,利用梯度上升法对训练过程中神经网络的连接权重和阈值的调整量进行了推导,并为调整量添加了动量项用于提高神经网络收敛速度,然后建立了关联度反向传播预测模型,并对其权重进行了阈值限制以及增加学习率来防止过拟合。对通用数据集进行时间序列预测实验,通过与改进的RBF和BP神经网络对比,表明对于多因素时间序列的预测Pearson关联度BP神经网络的预测误差精度RMSE降低了4.02,收敛次数减少1 690代。实现了将关联分析与BP神经网络的结合,能够在保证效率的同时,解决过拟合问题,提高预测精度。     

A flexible artificial neural network–fuzzy simulation algorithm for scheduling a flow shop with multiple processors

One of the most popular approaches for scheduling manufacturing systems is dispatching rules. Different types of dispatching rules exist, but none of them is known to be globally the best. A flexible artificial neural network–fuzzy simulation (FANN–FS) algorithm is presented in this study for solving the multiattribute combinatorial dispatching (MACD) decision problem. Artificial neural networks (ANNs) are one of the commonly used metaheuristics and are a proven tool for solving complex optimization problems. Hence, multilayered neural network metamodels and a fuzzy simulation using the α-cuts method were trained to provide a complex MACD problem. Fuzzy simulation is used to solve complex optimization problems to deal with imprecision and uncertainty. The proposed flexible algorithm is capable of modeling nonlinear, stochastic, and uncertain problems. It uses ANN simulation for crisp input data and fuzzy simulation for imprecise and uncertain input data. The solution quality is illustrated by two case studies from a multilayer ceramic capacitor manufacturing plant. The manufacturing lead times produced by the FANN–FS model turned out to be superior to conventional simulation models. This is the first study that introduces an intelligent and flexible approach for handling imprecision and nonlinearity of scheduling problems in flow shops with multiple processors.     

基于模糊机会约束规划的再制造装配车间调度优化方法

针对再制造零部件质量的不确定性导致工位装配时间波动范围大和调度模型难以准确描述的问题,采用基于可信性测度的模糊变量表示再制造零部件的装配时间,建立基于置信水平下的模糊机会约束规划调度模型,并提出求解该模型的混合智能优化算法：应用模糊模拟技术产生样本数据;利用反向传播算法训练多层前向神经网络逼近不确定函数;将训练后的神经网络与遗传算法相结合,以优化再制造装配车间调度问题。实例验证了该模型和算法的可行性。     

粒子群算法在工程优化设计中的应用

将粒子群算法与惩罚函数法相结合,建构一种离散粒子群算法,解决工程上非线性约束离散变量优化设计问题。为实现离散变量与连续变量的转化,构造了相应的扩张函数,提出惩罚因子的确定策略。通过容器设计算例验证,粒子群算法方法优于文献所列方法。应用粒子群算法、惩罚函数法及所提出的策略对波纹管工程实例进行优化设计,其单位重量下整体波纹管的补偿量比在用产品提高了79.96%,与理论解接近,进一步证明了离散粒子群算法及策略在处理工程非线性约束离散优化设计问题时的有效性,其为工程上类似优化设计提供借鉴。     

不确定信息条件下的车间调度策略研究

为了在不确定的车间信息环境下做出正确的调度策略,提出了一种支持多目标和多优先级车间调度策略的随机规划模型,并给出了求解算法。该模型的求解通过包含3个步骤的混合智能算法来实现,首先利用随机仿真生成近似的样本数据,然后利用神经网络进行不确定目标和约束函数的逼近,并用遗传算法最终完成对多目标优化解的搜索。最后,通过一个汽车企业模具制造车间中调度问题的实例,验证了该模型和算法的有效性及实用性。     

扩展拉格朗日乘子粒子群算法解决工程优化问题

工程上很多优化问题,如容器设计、波纹管、板翅式换热器的结构优化设计等,皆为非线性约束优化设计问题,常采用惩罚函数法处理约束条件;为获得问题最优解,该方法需要合理确定初始惩罚因子,且需要动态惩罚因子无穷大。扩展拉格朗日乘子法是一种改进的惩罚函数法,可以克服惩罚函数法的不足,获得全局最优解,但目前对其研究和应用有限。对拉格朗日乘子法与粒子群算法相结合处理非线性约束问题进行研究,提出惩罚因子更新策略,确定扩展拉格朗日乘子粒子群算法合理的操作过程。标准测试函数结果显示：提出的方法及策略实现了扩展拉格朗日乘子粒子群算法解决非线性约束问题,并得到了问题的全局最优解;其在容器及波纹管系列优化设计中的应用进一步显示,提出的方法在处理非线性约束工程实际问题时,运行稳定可靠,可快捷获得问题的全局最优解或近似最优解。     

A neural network meta-model for identification of optimal combination of priority dispatching rules and makespan in a deterministic job shop scheduling problem

Selection of appropriate priority dispatching rules (PDRs) is a major concern in practical scheduling problems. Earlier research implies that using one PDR does not necessarily yield to an optimal schedule. Hence, this paper puts forward a novel approach based on discrete event simulation (DES) and artificial neural networks (ANNs) to decide on the optimal PDR for each machine from a set of rules so as to minimize the makespan in job shop scheduling problems. Non-identical PDRs are considered for each machine. Indeed, for a given number of machines, all permutations of PDRs are taken into account which could lead to nondeterministic polynomial-time hardness of the problem when the number of machines increases. To address this issue, DES and ANNs are employed as a meta-model. First, the problem is modeled and quite a number of feasible solutions are obtained from DES on its own. Afterward, a back-propagation neural network is developed in accordance with the results of DES to calculate the makespan based on all potential permutations of PDRs. The performance of the proposed approach is investigated through a set of test-bed problems.     

Job Shop调度问题的Minimax模型及双空间协同遗传算法

针对工序加工时间不确定环境下的Job Shop调度问题,为了预估最差调度工况及其对应的调度性能指标边界,采用一类保守、稳健的Minimax分析方法,建立了基于提前/拖期惩罚成本的Minimax调度模型;为了解决传统基于遍历或枚举方法存在的搜索空间巨大的问题,提出并证明了给定调度顺序条件下,关于内层Max优化过程的凸函数定理,并依此定理提出了一种工序加工时间搜索空间过滤机制。针对Minimax调度问题存在的双空间寻优特性,在分析调度顺序种群和工序加工时间种群的交替进化机制的基础上,设计了一种高效的双空间协同遗传算法。最后通过仿真算例验证了该过滤机制和双空间协同遗传算法的有效性。     

互替机床提前/延期惩罚调度问题的启发式算法

对以作业提前或延期惩罚因素之和最小为目标函数的互替机床调度问题进行了描述，提出和阐述了一种四段式启发式算法，并通过大量不同规模的问题仿真对该算法进行了评价分析，结果表明该算法可行、有效。     

Group shop scheduling with uncertain data and a general cost objective

In this paper, a stochastic group shop scheduling problem with a due date-related objective is studied. The group shop scheduling problem provides a general formulation including two other shop scheduling problems, the job shop and the open shop. Both job release dates and processing times are assumed to be random variables with known distributions. Moreover, earliness and tardiness of jobs are penalized at different rates. The objective is to minimize the expected maximum completion cost among all jobs. A lower bound on the objective function is proposed, and then, a hybrid approach following a simulation optimization procedure is developed to deal with the problem. An ant colony optimization algorithm is employed to construct good feasible solutions, while a discrete-event simulation model is used to estimate the performance of each constructed solution that, taking into account its lower bound, may improve the best solution found so far. The proposed approach is then evaluated through computational experiments.     

Single-machine scheduling with simple linear deterioration to minimize earliness penalties

We consider a single-machine scheduling problem with deteriorating jobs in which the due dates are determined by the equal slack method. In this model, the processing time of a job is defined as a simple linear function of its starting time. The objective is to minimize the total weighted earliness penalty subject to no tardy jobs. We prove that two special cases of the problem remain polynomially solvable. The first case is the problem with equally weighted monotonous penalty objective function and the other case is the problem with weighted linear penalty objective function.     

A generalization for single-machine scheduling with deteriorating jobs to minimize earliness penalties

We consider a single-machine scheduling problem with deteriorating jobs in which the due dates are determined by the equal slack (SLK) method. By a deteriorating job, we mean that the job’s processing time is an increasing function of its starting time. We model job deterioration as a function that is proportional to a linear function of time. The objective is to minimize the total weighted earliness penalty subject to no tardy jobs. We prove that two special cases of the problem remain polynomially solvable. The first case is the problem with equally weighted monotonous penalty objective function and the other case is the problem with weighted linear penalty objective function.     

Scheduling optimization of flexible manufacturing system using cuckoo search-based approach

In the present work, a cuckoo search (CS)-based approach has been developed for scheduling optimization of a flexible manufacturing system by minimizing the penalty cost due to delay in manufacturing and maximizing the machine utilization time. To demonstrate the application of cuckoo search (CS)-based scheme to find the optimum job, the proposed scheme has been applied with slight modification in its Levy flight operator because of the discrete nature of the solution on a standard FMS scheduling problem containing 43 jobs and 16 machines taken from literature. The CS scheme has been implemented using Matlab, and results have been compared with other soft computing-based optimization approaches like genetic algorithm (GA) and particle swarm optimization found in the literature. The results shown by CS-based approach have been found to outperform the results of existing heuristic algorithms such as GA for the given problem.     

异构无线传感器网络中基于POMDP的实时调度算法

针对异构无线传感器网络节点性能存在差异和易受环境影响的特点,提出一种基于部分可观察Markov决策过程(partially observable markov decision process,POMDP)的实时休眠调度算法,使用状态转移函数和观察函数表示系统完成用户请求任务中存在的环境噪声和传输冲突等不确定性,使用回报函数表示采用不同调度策略对异构网络感知准确度和能量消耗的影响,采用基于当前信念点的在线求解算法求取最优策略。仿真结果表明:该算法能够平衡数据准确性与能量消耗,延长网络生存时间。     

A dispatching rule-based hybrid genetic algorithm focusing on non-delay schedules for the job shop scheduling problem

Job shop scheduling is an important decision process in contemporary manufacturing systems. In this paper, we aim at the job shop scheduling problem in which the total weighted tardiness must be minimized. This objective function is relevant for the make-to-order production mode with an emphasis on customer satisfaction. In order to save the computational time, we focus on the set of non-delay schedules and use a genetic algorithm to optimize the set of dispatching rules used for schedule construction. Another advantage of this strategy is that it can be readily applied in a dynamic scheduling environment which must be investigated with simulation. Considering that the rules selected for scheduling previous operations have a direct impact on the optimal rules for scheduling subsequent operations, Bayesian networks are utilized to model the distribution of high-quality solutions in the population and to produce the new generation of individuals. In addition, some selected individuals are further improved by a special local search module based on systematic perturbations to the operation processing times. The superiority of the proposed approach is especially remarkable when the size of the scheduling problem is large.     

面向航空发动机装配线的知识化制造自适应优化调度

为了解决不确定生产环境下的航空发动机装配调度问题,设计了一种面向航空发动机装配线的知识化制造自适应优化调度算法。算法采用强化学习和过程仿真相结合的调度策略求解方式,以最小化提前期惩罚费用和完工时间成本为调度目标,给出了航空发动机装配的Q学习自适应调度模型;针对装配调度问题定义了四个新的调度规则,定义了航空发动机装配的四个状态特征用于对系统状态进行描述,并针对调度目标设计了合理的回报函数。仿真实验结果表明,在调度过程中,采用提出的Q学习方法在多数情况下都远优于其他规则,尤其在装配任务到达频繁的情况下,总体上表现出更好的优势,显示了良好的自适应性能。     

Artificial neural network based on genetic algorithm for emissions prediction of a SI gasoline engine

This paper proposes a hybrid learning of artificial neural network (ANN) with the nondominated sorting genetic algorithm-II (NSGAII) to improve accuracy in order to predict the exhaust emissions of a four stroke spark ignition (SI) engine. In the proposed approach, the genetic algorithm (GA) determines initial weights of local linear model tree (LOLIMOT) neural networks. A multi-objective optimization problem is determined. A sensitivity analysis is performed on NSGA-II parameters in order to provide better solutions along the optimal Pareto front. Then, a fuzzy decision maker and the technique for order preference by similarity to ideal solution (TOPSIS) are employed to select compromised solutions among the obtained Pareto solutions. The LOLIMOT-GA responses are compared with the provided by radial basis function (RBF) and multilayer perceptron (MLP) neural networks in terms of correlation coefficient R ².