Coordinating batching decisions in manufacturing networks

Family-based dispatching heuristics aim for improving job flow times by reducing time spent on set-ups. They realise set-up efficiencies by batching similar types of jobs. By their intuitiveness and the simplicity of their decision logic, they may contribute to an easy to implement and viable strategy in many practical settings. Similar to common dispatching rules most existing family-based dispatching heuristics are myopic, i.e. their decision scope is restricted to a single manufacturing stage. Hence, they neglect opportunities for improving shop performance by coordinating batching decisions with other manufacturing stages. Case examples from industry underpin the need for exploring these opportunities. We do so by studying a simple two-stage flow shop, entailing a serial and a batch stage. To facilitate shop coordination we propose extensions to existing family-based dispatching heuristics. Extended heuristics seek to further increase set-up efficiencies by allowing for upstream job re-sequencing, and pro-active set-ups, i.e. set-ups that may be initiated prior to the arrival of a job. Outcomes of an extensive simulation study indicate significant performance gains for extended heuristics vs. existing heuristics. Performance gains are largest for moderate and high set-up to run-time ratios.     

蚁群系统结合指派规则求解HFS调度问题

以NP-难的最小化时间表长为目标的混合流水车间调度问题为研究对象。把工件在第1阶段开始加工的排序问题转化为旅行商问题,采用蚁群系统求得初始排序;在第1阶段后各阶段采用工件先到先服务规则选择工件、最先空闲机器优先规则选择机器以构建初始工件的机器指派与排序;充分利用已知的机器布局和工件加工时间特点,确定工件加工瓶颈阶段,并以此为基础对工件的机器指派与排序进行改进。用Carlier和Neron设计的Benchmark算例仿真后与著名的NEH算法比较,表明这种算法是有效的。     

Family based dispatching in manufacturing networks

Intrinsic to family based dispatching is the grouping of similar types of jobs in front of a machine for joint processing. Machine flow times may be improved in this way, as less time is spent on set-ups. Our observations in practice, however, suggest that family based dispatching may result in a bulky arrival pattern for successor manufacturing stages, thereby causing additional delay. So far, literature seems to neglect this effect. To explore this issue we develop queuing theoretical approximations of flow times for a simple two-stage shop. It appears that the optimal batch size for the shop is typically smaller than the optimal batch size for the batch machine. Furthermore, we propose extensions to existing dispatching rules by using information on successor stages. Existing and new extended rules are tested by an extensive simulation study. In line with the queuing theoretical analysis the outcomes indicate that exhaustive rules – assuming batch size to be equal to family queue length – are clearly outperformed by non-exhaustive rules – allowing for smaller batches. Moreover, results show that the inclusion of local information on successor stages in rule decision making improves shop flow times.     

Scheduling a dynamic flexible flow line with sequence-dependent setup times: a simulation analysis

This paper presents a simulation-based experimental study of scheduling rules for scheduling a dynamic flexible flow line problem considering sequence-dependent setup times. A discrete-event simulation model is presented as well as eight adapted heuristic algorithms, including seven dispatching rules and one constructive heuristic, from the literature. In addition, six new proposed heuristics are implemented in the simulation model. Simulation experiments are conducted under various conditions such as setup time ratio and shop utilisation percentage. One of the proposed rules performs better for the mean flow time measure and another one performs better for the mean tardiness measure. Finally, multiple linear regression based meta-models are developed for the best performing scheduling rules.     

Solving multi-objective rescheduling problems in dynamic permutation flow shop environments with disruptions

In multi-objective optimisation problems, optimal decisions need to be made in the presence of trade-offs among conflicting objectives which may sometimes be expressed in different units of measure. This makes it difficult to reduce the problem to a single-objective optimisation. Furthermore, when disruptive changes emerge in manufacturing environments, such as the arrival of new jobs or machine breakdowns, the scheduling system should be adapted by responding quickly. In this paper, we propose a rescheduling architecture for solving the problem based on a predictive-reactive strategy and a new method to calculate the reactive schedule in each rescheduling period. Additionally, we developed a methodology that allows the use of multi-objective performance metrics to evaluate dispatching rules. These rules are applied at a benchmark specifically designed for this paper considering three objective functions: makespan, total weighted tardiness and stability. Three types of disruptions are also considered: arrivals of new jobs, machine breakdowns and variations in job processing times. Results showed that the RANDOM rule provides a better behaviour compared to other evaluated rules and a lower ratio of non-dominated solutions compared to ATC (apparent tardiness cost) and FIFO (first-in-first-out) rules. Moreover, the behaviour of the hypervolume metric depends on the problem dimensions.     

Family-based dispatching with parallel machines

Family-based dispatching heuristics seek to lower set-up frequencies by grouping similar types of jobs for joint processing. Hence, job flow times may be improved as less time is spent on set-ups. So far, family-based dispatching with parallel machines received little attention in literature. We address the perceived gap by proposing extensions to existing family-based dispatching heuristics. Main extensions concern improved rules for family priority settings and for coordinating the number of machines in use by a single family. Extended heuristics are tested by an extensive simulation study. Significant performance gains for extended heuristics vs. existing heuristics are found. Performance gains are largest for high set-up to run-time ratios.     

New scheduling algorithms and digital tool for dynamic permutation flowshop with newly arrived order

The permutation flowshop scheduling problem has been widely studied under static environment by assuming machines and jobs are available at the time of zero. However, in reality, new orders arrive at production systems randomly, which leads to sheer complexity in scheduling due to the dynamic changes given various constraints of resources. Previous studies simply attach new orders directly after the existing schedule. Recent study shows mixing jobs of old and new orders could result in better scheduling solutions. But the heuristic algorithms are still lacking to implement the job mixing policy. To address this problem, a novel scheduling strategy is herein proposed by integrating match-up strategy and real-time strategy (MR) in order to make use of the remaining time before the old order due date. Based on the new MR strategy, eleven new heuristics are introduced with ten existing and one new priority rules. Computational results illustrate the effectiveness of the new heuristics. A digital tool is developed for ease of application of these heuristics, and it is validated by case studies.     

An adaptive scheduling algorithm for a parallel machine problem with rework processes

The development of a scheduling methodology for a parallel machine problem with rework processes is presented in this paper. The problem is to make a schedule for parallel machines with rework probabilities, due-dates, and sequence dependent setup times. Two heuristics are developed based on a dispatching algorithm and problem-space-based search method. In order to evaluate the efficacy of the proposed algorithms, six performance indicators are considered: total tardiness, maximum lateness, mean flow-time, mean lateness, the number of tardy jobs, and the number of reworks. This paper shows how these algorithms can adaptively capture the characteristics of manufacturing facilities for enhancing the performance under changing production environments. Extensive experimental results show that the proposed algorithms give very efficient performance in terms of computational time and each objective value.     

On the beat of the drum: improving the flow shop performance of the Drum–Buffer–Rope scheduling mechanism

One of the main elements of the theory of constraints is its Drum–Buffer–Rope (DBR) scheduling (or release) mechanism that controls the release of jobs to the system. Jobs are not released directly to the shop floor – they are withheld in a backlog and released in accordance with the output rate of the bottleneck (i.e. the drum). The sequence in which jobs are considered for release from the backlog is determined by the schedule of the drum, which also determines in which order jobs are processed or dispatched on the shop floor. In the DBR literature, the focus is on the urgency of jobs and the same procedure is used both for backlog sequencing and dispatching. In this study, we explore the potential of using different combinations of rules for sequencing and dispatching to improve DBR performance. Based on controlled simulation experiments in a pure and general flow shop we demonstrate that, although the original procedure works well in a pure flow shop, it becomes dysfunctional in a general flow shop where job routings vary. Performance can be significantly enhanced by switching from a focus on urgency to a focus on the shortest bottleneck processing time during periods of high load.     

Order sequencing and capacity balancing in synchronous manufacturing

Synchronous manufacturing aims at achieving the benefits of intermittent production lines in production situations that operate without lines. Benefits such as short and constant throughput times and predictable capacity loading can be acquired through an appropriate design of the synchronous manufacturing system and its control system. The order release mechanism is an essential part of this control system. It determines the sequence in which orders are released to the shop floor. As orders may differ in the amount and distribution of their capacity requirements over subsequent production stages, total capacity load may vary over time. If the available capacity per period is not flexible, capacity balancing becomes an issue in the order release decision. In practice, heuristics or rules of thumb are used to solve this problem, but their effectiveness is questioned. This paper examines the effectiveness of some new heuristics that are based on insights from assembly system design and work load control, and compare their performance with an optimal solution approach. The approaches are evaluated in a rolling schedule environment, and under different levels of capacity fluctuations and problem sizes. The results show that the performance of the heuristic solutions deteriorates if capacity fluctuations between the stages increase. If we measure both the amount and frequency of shortages over a long period of time in a rolling schedule environment, a quite simple rule that only takes the available capacity during the first stage into account outperforms more intelligent rules.     

Scheduling in a cellular manufacturing system: a simulated annealing approach

The problem of scheduling in a cellular manufacturing system is considered with the objective of minimizing the sum of completion times (or total flow time) of jobs. A correct formulation of recursive equation for the flowline-based cellular manufacturing system is first proposed. Subsequently a heuristic is developed to obtain a sequence that minimizes total flow time in a flowline cell. The proposed heuristic makes use of the simulated annealing technique and is developed in two stages. A good initial heuristic seed sequence obtained in the first stage is improved upon by a proposed new variant of the simulated annealing technique wherein three different perturbation schemes have been experimented with. One of the perturbation schemes is newly proposed in this paper and is called the Adjacent interchange scheme. The proposed simulated annealing algorithm has been compared with the existing heuristics for minimizing flow time and has shown consistently good and superior solutions.     

Dispatching rules for scheduling in assembly jobshops - Part 1

Research on jobshop scheduling has tended to concentrate on the development of dispatching rules for jobs that are independent, i.e. single-component jobs. However, in real-life situations, many jobs involve assembly operations that require scheduling of multiple components through the jobshop where both serial and parallel operations take place. In this two-part paper, we consider the problem of scheduling in assembly jobshops, i.e. jobshops that manufacture multi-level assembly jobs. The development of new and efficient dispatching rules with a view to address various measures of performance related to flowtime and staging delay of jobs is first undertaken. A new concept, called 'operation synchronization date' is introduced and made use of in the new dispatching rules. The best existing dispatching rules and the proposed dispatching rules are relatively evaluated by an exhaustive simulation study. The results indicate that the proposed rules emerge to be superior to the existing ones for most measures of performance.     

Lot streaming multiple jobs with values exponentially deteriorating over time in a job-shop environment

The main issue in lot streaming (LS) is determining the means by which to split jobs into sub-jobs to improve the makespan (or some other criterion). However, LS has been overlooked in most studies dealing with scheduling problems associated with specific kinds of job shops, where the job value exponentially deteriorates over time. The current study attempts to determine whether the expected benefits of LS would be evident in the job-shop scheduling problem (JSP) with the objective of maximising the total value of jobs. This study comprised two stages. In the first stage, we studied the influence of a fixed number of sub-jobs on the performance of the LS by systematically varying this parameter using the fixed number job splitting (FNJS) approach. We considered a total of 12 dispatching rules for the analysis of relative performance. Simulation results suggest that dividing each job into several sub-jobs increases the total value of jobs. In addition, dispatching rules incorporating information related to job value perform better than those without this information. In the second stage of the study, we proposed a genetic algorithm-based job splitting (GAJS) approach. The simulation results led us to conclude that the GAJS approach is superior to the FNJS approach in terms of the total value of the jobs and the average number of sub-jobs generated.     

Learning dispatching rules using random forest in flexible job shop scheduling problems

In this paper, we address the flexible job-shop scheduling problem (FJSP) with release times for minimising the total weighted tardiness by learning dispatching rules from schedules. We propose a random-forest-based approach called Random Forest for Obtaining Rules for Scheduling (RANFORS) in order to extract dispatching rules from the best schedules. RANFORS consists of three phases: schedule generation, rule learning with data transformation, and rule improvement with discretisation. In the schedule generation phase, we present three solution approaches that are widely used to solve FJSPs. Based on the best schedules among them, the rule learning with data transformation phase converts them into training data with constructed attributes and generates a dispatching rule with inductive learning. Finally, the rule improvement with discretisation improves dispatching rules with a genetic algorithm by discretising continuous attributes and changing parameters for random forest with the aim of minimising the average total weighted tardiness. We conducted experiments to verify the performance of the proposed approach and the results showed that it outperforms the existing dispatching rules. Moreover, compared with the other decision-tree-based algorithms, the proposed algorithm is effective in terms of extracting scheduling insights from a set of rules.     

Unrelated parallel machine scheduling with job splitting

Scheduling jobs on unrelated parallel machines is an activity that is very much a part of industrial scheduling. We report a methodology for minimizing the total weighted tardiness of all jobs intended to be processed on unrelated parallel machines in the presence of dynamic job releases and dynamic machine availability. More importantly, the mixed (binary) integer linear programming model formulated for the problem incorporates a couple of “hard” operational constraints to ensure that just-in-time manufacturing practices are followed by controlling the work-in-process and/or finished goods inventories generated by split jobs mandated by a tight due date, a high priority, and/or a high workload. Four different methods based on simple and composite dispatching rules are used to identify an initial solution, which is then used by the tabu-search-based heuristic solution algorithm to ultimately find the best solution. Incorporating the various tabu search features led to the development of six different heuristics that were tested on eight small problem instances to compare the quality of their solutions to the optimal solutions. The results show that the proposed heuristics are capable of obtaining solutions of good quality in a remarkably short computation time with the best performer among them recording a percentage deviation of only 1.18%. A factorial experiment based on a split-plot design is performed to test the performance of the heuristics on problem structures, ranging from nine jobs and three machines to 60 jobs and 15 machines. The results show that the newly developed composite dispatching heuristic, referred to as the modified apparent tardiness cost, is capable of obtaining initial solutions that significantly accelerate the tabu-search-based heuristics to attain the best solution. The use of a long-term memory function is proven to be advantageous in solving all problem structures. In addition, the variable tabu list size is preferred for solving the small problem structure, while the fixed tabu list size is preferred as the problem size grows from small to medium and then large.     

Scheduling of wafer test processes in semiconductor manufacturing

This research focuses on solving a common wafer test scheduling problem in semiconductor manufacturing. During wafer testing, a series of test processes are conducted on wafers using computer-controlled test stations at various temperatures. The test processes are conducted in a specified order on a wafer lot, resulting in precedence constraints for the schedule. Furthermore, the assignment of the wafer lots to test stations and the sequence in which they are processed affects the time required to set up the test operations. Thus, the set-up times are sequence dependent. Four heuristics are developed to solve the test scheduling problem with the aim of minimizing the makespan required to test all wafers on a set of test stations. The heuristics generate a sorted list of wafer lots as a dispatching sequence and then schedule the wafer lots on test stations in order of appearance on the list. An experimental analysis and two case studies are presented to validate the proposed solution approaches. In the case studies, the heuristics are applied to actual data from a semiconductor manufacturing facility. For both case studies, the proposed solution approaches decrease the makespan by 23–45% compared with the makespan of the actual schedule executed in the manufacturing facility.     

基于规则和仿真的多机并行作业车间生产调度研究

资源分派和能力分派是作业车间生产调度中的重要问题,路径选择规则和分派规则是解决上述问题的有效途径。采用基于规则的仿真研究多机并行作业车间资源分派和能力分派问题,分析工件加工时间、到达率以及机器加工速率对调度结果的影响,以平均完工时间、平均延迟交货率以及平均资源利用率为评价指标,通过对4种路径选择规则和6种分派规则的仿真试验,确定不同性能指标下最佳的调度规则。仿真研究表明:调度规则的选用取决于车间资源配置和调度目标,应避免仅凭借经验或偏好选择规则的调度方法。     

The Sensitivity of the Relative Effectiveness of Job Shop Dispatching Rules with Respect to Various Arrival Distributions

The study investigates the effects which various arrival rate distributions may have on the relative success of implementing various job shop heuristic dispatching rules. Sixteen different arrival rate distributions are tested on ten dispatching rules. General conclusions imply that the distribution with respect to shape and range of the arrival rate for incoming jobs is not a significant variable in evaluating the relative effectiveness of dispatching rules.     

Job shop scheduling heuristics and frequency of scheduling

This paper presents a job scheduling problem. Two important aspects are included in the subsequent analysis. The first is the dynamic nature whereby new jobs arrive to be included intermittently through time. The second is the uncertainty, or error in estimating process times, and the likelihood of machine breakdown. An experiment is presented which shows the performance of a number of heuristics in the form of dispatching disciplines under different scheduling conditions which are determined by the scheduling period and the level of uncertainty in the process times and machine breakdowns. Various different measures of performance which could be of importance to management are considered. These include mean ratio of flow time to process time, mean queueing time, mean lateness, percentage of jobs late and net CPU times required to generate schedules in the simulation process.

Results are presented showing the relationship between the performance of the heuristics relative to the different measures and the rescheduling period. These are discussed in the more general managerial context.     

Heuristics for minimizing total weighted tardiness in complex job shops

Semi-conductor manufacturing is arguably one of the most complex manufacturing processes in existence today. A semi-conductor wafer fabrication facility is comprised of batching machines, parallel machines, machines with sequence-dependent set-ups, and re-circulating product flow. The individual job release times and due dates combine with the other processing environment characteristics to form a ‘complex’ job shop scheduling problem. We first present a mixed-integer program (MIP) to minimize total weighted tardiness in a complex job shop. Since the problem is NP-hard, we compare a heuristic based on the MIP (MIP heuristic) with both a tuned version of a modified shifting bottleneck heuristic (SB heuristic) and three dispatching rules using random problem instances of a representative model from the literature. While the MIP heuristic typically produces superior schedules for problem instances with a small number of jobs, the SB heuristic consistently outperforms the MIP heuristic for larger problem instances. The SB heuristic's superior performance as compared to additional dispatching rules is also demonstrated for a larger, ‘real world’ dataset from the literature.