智能制造系统基于数据驱动的车间实时调度

智能制造系统采用大量先进的信息技术,为车间实时调度提供技术基础.各类信息技术在生产制造过程中的广泛应用使得制造系统积累了大量与生产调度相关的数据,因此,通过利用历史生产调度数据和智能装备收集到的实时生产数据,建立基于数据驱动的生产实时调度方法成为新型制造环境下实现高效调度的新思路.针对智能制造环境下的混合流水车间实时调度问题,提出基于BP神经网络的数据驱动的实时调度方法,从历史近优的调度方案中提取用于调度知识挖掘的样本数据,通过BP神经网络训练学习获取生产系统状态与调度规则的映射关系网络,并将其应用于生产在线实时调度.数值实验表明,所提出的方法优于固定单一调度规则,在不同的调度性能指标下其效果均稳定且良好.     

Study of stochastic sequence-dependent flexible flow shop via developing a dispatching rule and a hybrid GA

A flexible flow shop is a generalized flow shop with multiple machines in some stages. This system is fairly common in flexible manufacturing and in process industry. In most practical environments, scheduling is an ongoing reactive process where the presence of real time information continually forces reconsideration of pre-established schedules. This paper studies a flexible flow shop system considering non-deterministic and dynamic arrival of jobs and also sequence dependent setup times. The problem objective is to determine a schedule that minimizes average tardiness of jobs. Since the problem class is NP-hard, a novel dispatching rule and hybrid genetic algorithm have been developed to solve the problem approximately. Moreover, a discrete event simulation model of the problem is developed for the purpose of experimentation. The most commonly used dispatching rules from the literature and two new methods presented in this paper are incorporated in the simulation model. Simulation experiments have been conducted under various experimental conditions characterized by factors such as shop utilization, setup time level and number of stages. The results indicate that methods proposed in this study are much better than the traditional dispatching rules.     

Real-time scheduling for reentrant hybrid flow shops: A decision tree based mechanism and its application to a TFT-LCD line

A reentrant hybrid flow shop, typically found in the electronics industry, is an extended system of the ordinary flow shop in such a way that there exist one or more parallel machines at each serial stage and each job has the reentrant product flow, i.e., a job may visit a stage several times. Among the operational issues in reentrant hybrid flow shops, we focus on the scheduling problem that determines the allocation of jobs to the machines at each stage as well as the sequence of the jobs assigned to each machine. Unlike the theoretical approach on reentrant hybrid flow shop scheduling, we suggest a real-time scheduling mechanism with a decision tree when selecting appropriate dispatching rules. The decision tree, one of the commonly used data mining techniques, is adopted to eliminate the computational burden required to carry out simulation runs to select dispatching rules. To illustrate the mechanism suggested in this study, a case study was performed on a thin film transistor-liquid crystal display (TFT-LCD) manufacturing line and the results are reported for various system performance measures.     

基于Agent的混合流水车间动态调度系统

针对敏捷制造调度环境的不确定性、动态性以及混合流水车间（HFS）调度问题的特点,设计了一种基于多Agent的混合流水车间动态调度系统,系统由管理Agent、策略Agent、工件Agent和机器Agent构成。首先提出一种针对混合流水车间环境的插值排序（HIS）算法并集成于策略Agent中,该算法适用于静态调度和多种动态事件下的动态调度。然后,设计了各类Agent间的协调机制,在生产过程中所有Agent根据各自的行为逻辑独立工作并互相协调。在发生动态事件时,策略Agent调用HIS算法根据当前车间状态产生工件序列,随后各Agent根据生成的序列继续进行协调直到完成生产。最后进行了发生机器故障、订单插入情况下的重调度以及在线调度等动态调度的实例仿真,结果表明对于这些问题,HIS算法的求解效果均优于调度规则,特别是在故障重调度中,HIS算法重调度前后的Makespan一致度达97.6%,说明系统能够灵活和有效地处理混合流水车间动态调度问题。     

动态车间作业调度问题中调度规则算法研究综述

调度规则是解决实际生产中的动态车间作业调度问题的有效方法,但它一般只在特定调度环境下性能较好,当环境发生变化时,就需要进行实时选择和评价。对调度规则的实时选择和评价方法进行综述,以研究实际生产中动态车间的实时调度问题。对调度规则的发展、分类以及特点进行了概述,并对调度规则的选择和评价方法进行了总结。详细介绍了调度规则的选择方法,包括使用较多的稳态仿真方法和表现较好的人工智能方法,并给出了仿真方法、专家系统、机器学习方法以及人工神经网络方法,用于调度规则的选择时所取得的研究成果和结论。此外,还介绍了调度规则的评价指标及评价方法。最后针对调度规则存在的不足,指出了未来的研究方向。     

Learning-based multi-pass adaptive scheduling for a dynamic manufacturing cell environment

Because the essential attributes are uncertain in a dynamic manufacturing cell environment, to select a near-optimal subset of manufacturing attributes to enhance the generalization ability of knowledge bases remains a critical, unresolved issue for classical artificial neural network-based (ANN-based) multi-pass adaptive scheduling (MPAS). To resolve this problem, this study develops a hybrid genetic /artificial neural network (GA/ANN) approach for ANN-based MPAS systems. The hybrid GA/ANN approach is used to evolve an optimal subset of system attributes from a large set of candidate manufacturing system attributes and, simultaneously, to determine configuration and learning parameters of the ANN according to various performance measures. In the GA/ANN-based MPAS approach, for a given feature subset and the corresponding topology and learning parameters of an ANN decoded by a GA, an ANN was applied to evaluate the fitness in the GA process and to generate the MPAS knowledge base used for adaptive scheduling control mechanisms. The results demonstrate that the proposed GA/ANN-based MPAS approach has, according to various performance criteria, a better system performance over a long period of time than those obtained with classical machine learning-based MPAS approaches and the heuristic individual dispatching rules.     

An AIS-based hybrid algorithm with PDRs for multi-objective dynamic online job shop scheduling problem

The dynamic online job shop scheduling problem (JSSP) is formulated based on the classical combinatorial optimization problem – JSSP with the assumption that new jobs continuously arrive at the job shop in a stochastic manner with the existence of unpredictable disturbances during the scheduling process. This problem is hard to solve due to its inherent uncertainty and complexity. This paper models this class of problem as a multi-objective problem and solves it by hybridizing the artificial intelligence method of artificial immune systems (AIS) and priority dispatching rules (PDRs). The immune network theory of AIS is applied to establish the idiotypic network model for priority dispatching rules to dynamically control the dispatching rule selection process for each operation under the dynamic environment. Based on the defined job shop situations, the dispatching rules that perform best under specific environment conditions are selected as antibodies, which are the key elements to construct the idiotypic network. Experiments are designed to demonstrate the efficiency and competitiveness of this model.     

Real-time scheduling for hybrid flowshop in ubiquitous manufacturing environment

This paper discusses the implementation of RFID technologies, which enable the shop floor visibility and reduce uncertainties in the real-time scheduling for hybrid flowshop (HFS) production. In the real-time HFS environment, the arriving of new jobs is dynamic, while the processes in work stages are not continuous. The decision makers in shop floor level and stage level have different objectives. Therefore, classical off-line HFS scheduling approaches cannot be used under these situations. In this research, two major measures are taken to deal with these specific real-time features. Firstly, a ubiquitous manufacturing (UM) environment is created by deploying advanced wireless devices into value-adding points for the collection and synchronization of real-time shop floor data. Secondly, a multi-period hierarchical scheduling (MPHS) mechanism is developed to divide the planning time horizon into multiple shorter periods. The shop floor manager and stage managers can hierarchically make decisions for their own objectives. Finally, the proposed MPHS mechanism is illustrated by a numerical case study.     

Multi-objective scheduling of dynamic job shop using variable neighborhood search

Dynamic job shop scheduling that considers random job arrivals and machine breakdowns is studied in this paper. Considering an event driven policy rescheduling, is triggered in response to dynamic events by variable neighborhood search (VNS). A trained artificial neural network (ANN) updates parameters of VNS at any rescheduling point. Also, a multi-objective performance measure is applied as objective function that consists of makespan and tardiness. The proposed method is compared with some common dispatching rules that have widely used in the literature for dynamic job shop scheduling problem. Results illustrate the high effectiveness and efficiency of the proposed method in a variety of shop floor conditions.     

时间约束混合流水车间调度问题综述

车间调度是智能制造领域中的核心问题之一, 在经典流水车间调度中, 所有工件按照相同的加工顺序在指 定机床上加工. 混合流水车间调度(HFS)作为流水车间调度的特例, 相比前者增加了机床选择的灵活性, 可以显著 优化系统目标, 但同时也增加了问题求解的难度. 由于时间约束HFS相比基本HFS问题更贴近实际生产过程, 近年 来, 综合考虑各类时间相关约束的HFS问题得到了深入研究. 因此, 本文围绕基本HFS、有限等待时间HFS、带准备 时间HFS、模糊/随机加工时间HFS、多时间约束HFS、时间约束相关多目标HFS等问题开展研究. 针对每一类时间 约束HFS问题, 按照问题规模对当前研究成果进行分类描述, 按照确定性算法、启发式方法、元启发式方法、算法混 合对相关成果进行算法分类, 按照实际工业应用对文献进行归类分析. 另一方面, 围绕交货期、能耗、成本等3类性 能指标, 分析了在各类时间约束HFS问题中的多目标优化相关成果. 最后详细分析了带时间约束HFS问题在问题层 面、算法层面和应用层面存在的挑战性问题和未来研究的方向.     

Using simulation and multi-criteria methods to provide robust solutions to dispatching problems in a flow shop with multiple processors

Dispatching rules are important to the performance of a manufacturing system. Selective applications of different priority rules at different processing stages in a multiple workstation manufacturing system have a positive impact on shop performance. This type of problem is a combinatorial dispatching decision. However, no dispatching rule can consistently produce better performance than all other rules under a variety of operating conditions and criteria. It is the purpose of this study to provide a robust solution for a dispatching decision that will have ‘good’ performance under different operating scenarios. In this paper a simulation case of a flow shop with multiple processors is proposed, specifically a multi-layer ceramic capacitor manufacturing system. Two multiple criteria decision-making methods – techniques for order preference by similarity to ideal solution (TOPSIS) and an analytic hierarchy process (AHP) – in combination with Taguchi orthogonal array are used to find the most suitable dispatching rule for every workstation. The results show that for 15 production scenarios and 4 criteria this combinatorial dispatching rule is robust, in the sense that it outperforms other commonly employed strategies.     

Dispatching rule selection using artificial neural networks for dynamic planning and scheduling

To schedule a job shop, the first task is to select an appropriate scheduling algorithm or rule. Because of the complexity of scheduling problems, no general algorithm sufficient for solving all scheduling problems has yet been developed. Most job-shop scheduling systems offer alternative algorithms for different situations, and experienced human schedulers are needed to select the best dispatching rule in these systems. This paper proposes a new algorithm for job-shop scheduling problems. This algorithm consists of three stages. First, computer simulation techniques are used to evaluate the efficiency of heuristic rules in different scheduling situations. Second, the simulation results are used to train a neural network in order to capture the knowledge which can be used to select the most efficient heuristic rule for each scheduling situation. Finally, the trained neural network is used as a dispatching rule selector in the real-time scheduling process. Research results have shown great potential in using a neural network to replace human schedulers in selecting an appropriate approach for real-time scheduling. This research is part of an ongoing project of developing a real-time planning and scheduling system.     

Hybrid monkey search algorithm for flow shop scheduling problem under makespan and total flow time

This paper addresses a sub-population based hybrid monkey search algorithm to solve the flow shop scheduling problem which has been proved to be non-deterministic polynomial time hard (NP-hard) type combinatorial optimization problems. Minimization of makespan and total flow time are the objective functions considered. In the proposed algorithm, two different sub-populations for the two objectives are generated and different dispatching rules are used to improve the solution quality. To the best of our knowledge, this is the first application of monkey search algorithm to solve the flow shop scheduling problems. The performance of the proposed algorithm has been tested with the benchmark problems addressed in the literature. Computational results reveal that the proposed algorithm outperforms many other heuristics and meta-heuristics addressed in the literature.     

Improved cuckoo search algorithm for hybrid flow shop scheduling problems to minimize makespan

The multistage hybrid flow shop (HFS) scheduling problems are considered in this paper. Hybrid flowshop scheduling problems were proved to be NP-hard. A recently developed cuckoo search (CS) metaheuristic algorithm is presented in this paper to minimize the makespan for the HFS scheduling problems. A constructive heuristic called NEH heuristic is incorporated with the initial solutions to obtain the optimal or near optimal solutions rapidly in the improved cuckoo search (ICS) algorithm. The proposed algorithm is validated with the data from a leading furniture manufacturing company. Computational results show that the ICS algorithm outperforms many other metaheuristics.     

Integration of priority dispatching and due-date assignment in a job shop

A simulation study to investigate the effect on missed due-dates and job flow-time is discussed by combining the job dispatching and due-date assignment decisions in job shop scheduling. A ‘semi-local’ due-date-oriented dispatching rule is designed which is able to monitor the progress of jobs closely. The performance of the dispatching rule is enhanced by a rational due-date assignment procedure which takes account of both job content and shop status information in determining due-dates. The simulation results show that the combined scheduling procedure performs better than some common simple dispatching rules which are used with the total-work-content (TWK) due-date assignment method.     

Dynamic scheduling of manufacturing job shops using genetic algorithms

Most job shop scheduling methods reported in the literature usually address the static scheduling problem. These methods do not consider multiple criteria, nor do they accommodate alternate resources to process a job operation. In this paper, a scheduling method based on genetic algorithms is developed and it addresses all the shortcomings mentioned above. The genetic algorithms approach is a schedule permutation approach that systematically permutes an initial pool of randomly generated schedules to return the best schedule found to date.A dynamic scheduling problem was designed to closely reflect a real job shop scheduling environment. Two performance measures, namely mean job tardiness and mean job cost, were used to demonstrate multiple criteria scheduling. To span a varied job shop environment, three factors were identified and varied between two levels each. The results of this extensive simulation study indicate that the genetic algorithms scheduling approach produces better scheduling performance in comparison to several common dispatching rules.     

Distributed Reinforcement Learning Control for Batch Sequencing and Sizing in Just-In-Time Manufacturing Systems

This paper presents an approach that is suitable for Just-In-Time (JIT) production for multi-objective scheduling problem in dynamically changing shop floor environment. The proposed distributed learning and control (DLC) approach integrates part-driven distributed arrival time control (DATC) and machine-driven distributed reinforcement learning based control. With DATC, part controllers adjust their associated parts' arrival time to minimize due-date deviation. Within the restricted pattern of arrivals, machine controllers are concurrently searching for optimal dispatching policies. The machine control problem is modeled as Semi Markov Decision Process (SMDP) and solved using Q-learning. The DLC algorithms are evaluated using simulation for two types of manufacturing systems: family scheduling and dynamic batch sizing. Results show that DLC algorithms achieve significant performance improvement over usual dispatching rules in complex real-time shop floor control problems for JIT production.     

周期性和事件驱动的JobShop滚动调度策略

为了适应加工的连续性及环境的变化，借用了预测控制中的滚动优化思想提出了周期性和事件驱动的滚动调度策略。调度算法将遗传算法和分派规则相结合，以此来处理与操作序列有关的工件安装时 间和工件到期时间约束的复杂调度问题。     

Job shop bottleneck detection based on orthogonal experiment

A new prior-to-run bottleneck detection method based on orthogonal experiment (BD–OE) is proposed for job shop from the perspective of scheduling. It is built according to a new bottleneck definition which is proposed based on the principle of “Bottlenecks determine the performance of manufacturing systems” in TOC. The method takes the scheduling objective as estimated index, and constructs orthogonal trials by orthogonal array and dispatching rules to detect the bottleneck machine which has the greatest effect on the estimated index. It can detect the bottleneck machine before manufacturing systems run, and guide the following production process for the improvement of the performance of manufacturing systems. In order to evaluate the performance of the proposed method, different scales of job shop scheduling instances and two existing bottleneck detection methods are selected for simulation. The results show that the prior-to-run bottleneck detection method is feasible, efficient and easily implemented.     

Job shop scheduling for missed due-date performance

Relatively little job shop scheduling research has focused on the missed due-date performance. In this paper, we investigate how two important decision factors, namely dispatching rules and due-date assignment methods, affect the missed due-date performance in job shop scheduling. A new dispatching rule and two new due-date setting models are developed in order to improve the performance criteria based on missed due dates. The new due-date models are capable of adjusting dynamically the flowtime estimation by using feedback information about current shop load conditions. Simulation results show that the proposed dynamic due-date models are significantly better than their static counterparts. The best missed due-date performance is observed when a combination of a dynamic due-date setting model and an appropriate due-date-dependent dispatching rule is employed. In addition, the new models are simple and easy to implement without preliminary runs for parameter estimation.