Dynamic scheduling system utilizing machine learning as a knowledge acquisition tool

Dynamic selection of scheduling rules during real operations has been recognized as a promising approach to the scheduling of the production line. For this strategy to work effectively, sufficient knowledge is required to enable prediction of which rule is the best to use under the current line status. In this paper, a new learning algorithm for acquiring such knowledge is proposed. In this algorithm, a binary decision tree is automatically generated using empirical data obtained by iterative production line simulations, and it decides in real time which rule to be used at decision points during the actual production operations. The configuration of the developed dynamic scheduling system and the learning algorithm are described in detail. Simulation results on its application to the dispatching problem are discussed with regard to its scheduling performance and learning capability.     

A study on the performance of scheduling rules in buffer-constrained dynamic flowshops

Most studies on scheduling in manufacturing systems using dispatching rules deal with jobshops, while there are only few reports dealing with dynamic flowshops. It is known that the performance of many dispatching rules in dynamic jobshops is different from that in dynamic flowshops. Moreover, many research reports assume that there are no buffer constraints in the shop, and even those reports dealing with buffer-constrained shops present the evaluation of existing dispatching rules for unconstrained shops in the context of buffer constraints with the consideration of a limited number of objectives of scheduling. In this study, we deal with the problem of scheduling in dynamic flowshops with buffer constraints. With respect to different time-based objectives, the best dispatching rules for scheduling in unconstrained shops have been identified from the existing literature. In addition, two new dispatching rules specially designed for flowshops with buffer constraints are proposed. All dispatching rules under consideration are evaluated in dynamic flowshops with buffer constraints on the basis of an extensive simulation study covering different levels of buffer constraints, shop load or utilization, and missing operations in flowshops. The proposed rules are found to perform better than the existing dispatching rules in buffer-constrained flowshops with respect to many measures of performance.     

Performance evaluation of dynamic scheduling approaches in vehicle-based internal transport systems

This paper studies the performance of static and dynamic scheduling approaches in vehicle-based internal transport (VBIT) systems and is one of the first to systematically investigate under which circumstances, which scheduling method helps in improving performance. In practice, usually myopic dispatching heuristics are used, often using look-ahead information. We argue more advanced scheduling methods can help, depending on circumstances. We introduce three basic scheduling approaches (insertion, combined and column generation) for the static problem. We then extend these to a dynamic, real-time setting with rolling horizons. We propose two further real-time scheduling approaches: dynamic assignment with and without look-ahead. The performances of the above five scheduling approaches are compared with two of the best performing look-ahead dispatching rules known from the literature. The performance of the various approaches depends on the facility layout and work distribution. However, column generation, the combined heuristic, and the assignment approach with look-ahead consistently outperform dispatching rules. Column generation can require substantial calculation time but delivers very good performance if sufficient look-ahead information is available. For large scale systems, the combined heuristic and the dynamic assignment approach with look ahead are recommended and have acceptable calculation times.     

A learning-based methodology for dynamic scheduling in distributed manufacturing systems

To enhance productivity in a distributed manufacturing system under hierarchical control, we develop a framework of dynamic scheduling scheme that explores routeing flexibility and handles uncertainties. We propose a learning-based methodology to extract scheduling knowledge for dispatching parts to machines. The proposed methodology includes three modules: discrete-event simulation, instance generation, and incremental induction. First, a sophisticated simulation module is developed to implement a dynamic scheduling scheme, to generate training examples, and to evaluate the methodology. Second, the search for training examples (good schedules) is successfully fulfilled by the genetic algorithm. Finally, we propose a tolerance-based learning algorithm that does not only acquire general scheduling rules from the training examples, but also adapts to any newly observed examples and thus facilitates knowledge modification. The experimental results show that the dynamic scheduling scheme significantly outperforms the static scheduling scheme with a single dispatching rule in a distributed manufacturing system.     

A beam search-based algorithm and evaluation of scheduling approaches for flexible manufacturing systems

This paper presents a new algorithm for the flexible manufacturing system (FMS) scheduling problem. The proposed algorithm is a heuristic based on filtered beam search. It considers finite buffer capacity, routing and sequence flexibilities and generates machine and automated guided vehicle (AGV) schedules for a given scheduling period. A new deadlock resolution mechanism is also developed as an integral part of the proposed algorithm. The performance of the algorithm is compared with several machine and AGV dispatching rules using mean flow time, mean tardiness and makespan criteria. It is also used to examine the effects of scheduling factors (i.e., machine and AGV load levels, routing and sequence flexibilities, etc.) on the system performance. The results indicate that the proposed scheduling algorithm yields considerable improvements in system performance over dispatching rules under a wide variety of experimental conditions.     

Dynamic adjustment of dispatching rule parameters in flow shops with sequence-dependent set-up times

Decentralised scheduling with dispatching rules is applied in many fields of production and logistics, especially in highly complex manufacturing systems. Since dispatching rules are restricted to their local information horizon, there is no rule that outperforms other rules across various objectives, scenarios and system conditions. In this paper, we present an approach to dynamically adjust the parameters of a dispatching rule depending on the current system conditions. The influence of different parameter settings of the chosen rule on the system performance is estimated by a machine learning method, whose learning data is generated by preliminary simulation runs. Using a dynamic flow shop scenario with sequence-dependent set-up times, we demonstrate that our approach is capable of significantly reducing the mean tardiness of jobs.     

A real-time scheduling mechanism for a flexible manufacturing system: Using simulation and dispatching rules

This paper presents a real-time scheduling methodology which uses simulation and dispatching rules for flexible manufacturing systems. We develop a scheduling mechanism in which job dispatching rules vary dynamically based on information from discrete event simulation that is used for evaluating candidate dispatching rules. In this paper, we improve and extend a previous research on simulation-based real-time scheduling by suggesting a more systematic framework for the scheduling mechanism through refinement of functions of modules in the mechanism, and by presenting and analysing various scheduling strategies used to operate the mechanism. The strategies are formed by combining two factors that might influence the performance of the mechanism: type of simulation model which is used in the mechanism and points of time when new dispatching rules are selected. In order to compare performance of the scheduling strategies, computational experiments are performed and results are reported.     

An optimised dynamic bottleneck dispatching policy for semiconductor wafer fabrication

A dynamic bottleneck dispatching (DBD) policy is designed in this paper to detect bottlenecks in a timely way and make adaptive dispatching decisions of semiconductor wafer fabrication systems according to the real-time conditions. Control parameters of the proposed DBD algorithm are optimised by response surface methodology (RSM) and desirability functions. Numerical results show that DBD outperforms common scheduling rules such as CR?+?FIFO, EDD, SRPT, SPT, SPNB and an existing dynamic bottleneck dispatching method.     

Performance-based dynamic scheduling model for flexible manufacturing systems

A performance-based dynamic scheduling model for random flexible manufacturing systems (FMSs) is presented. The model is built on the mathematical background of supervisory control theory of discrete event systems. The dynamic FMS scheduling is based on the optimization of desired performance measures. A control theory-based system representation is coupled with a goal programming-based multi-criteria dynamic scheduling algorithm. An effectiveness function, representing a performance index, is formulated to enumerate the possible outputs of future schedules. Short-term job scheduling and dispatching decisions are made based on the values obtained by optimizing the effectiveness function. Preventive actions are taken to reduce the difference between actual and desired target values. To analyse the real-time performance of the proposed model, a software environment that included various Visual Basic Application® modules, simulation package Arena®, and Microsoft Access® database was developed. The experimentation was conducted (a) to determine the optimum look-ahead horizons for the proposed model and (b) to compare the model with conventional scheduling decision rules. The results showed that the proposed model outperformed well-known priority rules for most of the common performance measures.     

A hybrid computer simulation-artificial neural network algorithm for optimisation of dispatching rule selection in stochastic job shop scheduling problems

Industrial systems are constantly subject to random events with inevitable uncertainties in production factors, especially in processing times. Due to this stochastic nature, selecting appropriate dispatching rules has become a major issue in practical problems. However, previous research implies that using one dispatching rule does not necessarily yield an optimal schedule. Therefore, a new algorithm is proposed based on computer simulation and artificial neural networks (ANNs) to select the optimal dispatching rule for each machine from a set of rules in order to minimise the makespan in stochastic job shop scheduling problems (SJSSPs). The algorithm contributes to the previous work on job shop scheduling in three significant ways: (1) to the best of our knowledge it is the first time that an approach based on computer simulation and ANNs is proposed to select dispatching rules; (2) non-identical dispatching rules are considered for machines under stochastic environment; and (3) the algorithm is capable of finding the optimal solution of SJSSPs since it evaluates all possible solutions. The performance of the proposed algorithm is compared with computer simulation methods by replicating comprehensive simulation experiments. Extensive computational results for job shops with five and six machines indicate the superiority of the new algorithm compared to previous studies in the literature.     

Multi-criteria optimisation-based dynamic scheduling for controlling FMS

This study deals with controlling flexible manufacturing systems (FMS) operating in volatile production environments. Most studies that address this issue use some sort of adaptive scheduling that enables the FMS to cope with the randomness and variability efficiently. The methods presented in the literature are usually based on heuristics and use simple dispatching rules. They do not consider changing the decision criteria dynamically as the system conditions change. In contrast to previous studies, the present study focuses on developing a control mechanism for dynamic scheduling that is based on incremental optimisation. This means that each time a scheduling decision is made, the local optimisation problem is solved such that the next jobs to be processed on machines are selected. The objective function (dominant decision criterion) for this optimisation problem is selected dynamically based on production order requirements, actual shop-floor status and system priorities. The proposed multi-criteria optimisation-based dynamic scheduling methodology was evaluated and compared with some known scheduling rules/policies. The results obtained demonstrate the superiority of the suggested methodology as well as its capability to cope with a multi-criteria environment.     

A constraint-based perspective in resource constrained project scheduling

In this study, a new heuristic approach to the resource constrained project scheduling problem is introduced. This approach, which is called local constraint based analysis (LCBA), is more robust than the dispatching rules found in the literature, since it does not depend on an a priori insight as do the dispatching rules. LCBA consists of the application of local essential conditions which respect the current temporal and resource constraints to generate a necessary sequence of activities at a scheduling decision time point in a single-pass parallel scheduling algorithm. LCBA is a time efficient procedure due to the localized aspect with which the activities are handled. Only the activities which are schedulable at the current scheduling time are considered for the application of the essential conditions. LCBA is tested against well-known rules from the literature and some recently developed rules. This testing is done using a set of problems of a special design and also a set of optimally solved problems from a recent benchmark in the literature. It is observed that near optimal time efficient solutions are obtained by LCBA and the procedure's performance is considerably better than that of the dispatching rules.     

Data-mining-based dynamic dispatching rule selection mechanism for shop floor control systems using a support vector machine approach

The purpose of this paper is to develop a data-mining-based dynamic dispatching rule selection mechanism for a shop floor control system to make real-time scheduling decisions. In data mining processes, data transformations (including data normalisation and feature selection) and data mining algorithms greatly influence the predictive accuracy of data mining tasks. Here, the z-scores data normalisation mechanism and genetic-algorithm-based feature selection mechanism are used for data transformation tasks, then support vector machines (SVMs) is applied for the dynamic dispatching rule selection classifier. The simulation experiments demonstrate that the proposed data-mining-based approach is more generalisable than approaches that do not employ a data-mining-based approach, in terms of accurately assigning the best dispatching strategy for the next scheduling period. Moreover, the proposed SVM classifier using the data-mining-based approach yields a better system performance than obtained with a classical SVM-based dynamic dispatching rule selection mechanism and heuristic individual dispatching rules under various performance criteria over a long period.     

An experimental study of human decision-making in computer-based scheduling of flexible manufacturing system

This paper describes a study which explores human decision-making abilities in scheduling and dispatching of a flexible manufacturing system (FMS) An experiment is described, using an FMS, in which subjects make scheduling and dispatching decisions using a real-time interactive computer-simulation based system. The experimental results demonstrate that human decision-making is superior to general dispatching rules. An explanation of these results and an analysis of subjects' behaviour is presented in the light of information obtained from verbal protocol data     

Dynamic job shop scheduling using variable neighbourhood search

In this paper a scheduling method based on variable neighbourhood search (VNS) is introduced to address a dynamic job shop scheduling problem that considers random job arrivals and machine breakdowns. To deal with the dynamic nature of the problem, an event-driven policy is selected. To enhance the efficiency and effectiveness of the scheduling method, an artificial neural network with a back propagation error learning algorithm is used to update parameters of the VNS at any rescheduling point according to the problem condition. The proposed method is compared with some common dispatching rules that have been widely used in the literature for the dynamic job shop scheduling problem. Results illustrate the high efficiency and effectiveness of the proposed method in a variety of shop floor conditions.     

Performance of an ant colony optimisation algorithm in dynamic job shop scheduling problems

The goal of the current study is to identify appropriate application domains of Ant Colony Optimisation (ACO) in the area of dynamic job shop scheduling problem. The algorithm is tested in a shop floor scenario with three levels of machine utilisations, three different processing time distributions, and three different performance measures for intermediate scheduling problems. The steady-state performances of ACO in terms of mean flow time, mean tardiness, total throughput on different experimental environments are compared with those from dispatching rules including first-in-first-out, shortest processing time, and minimum slack time. Two series of experiments are carried out to identify the best ACO strategy and the best performing dispatching rule. Those two approaches are thereafter compared with different variations of processing times. The experimental results show that ACO outperforms other approaches when the machine utilisation or the variation of processing times is not high.     

An integrated scheduling and material-handling approach for complex job shops: a computational study

We suggest an extension of the shifting bottleneck heuristic for complex job shops that takes the operations of automated material-handling systems (AMHS) into account. The heuristic is used within a rolling horizon approach. The job-shop environment contains parallel batching machines, machines with sequence-dependent setup times, and re-entrant process flows. Jobs are transported by an AMHS. Semiconductor wafer fabrication facilities (wafer fabs) are typical examples for manufacturing systems with these characteristics. Our primary performance measure is total weighted tardiness (TWT). The shifting bottleneck heuristic (SBH) uses a disjunctive graph to decompose the overall scheduling problem into scheduling problems for single machine groups and for transport operations. The scheduling algorithms for these scheduling problems are called subproblem solution procedures (SSPs). We consider SSPs based on dispatching rules. In this paper, we are also interested in how much we can gain in terms of TWT if we apply more sophisticated SSPs for scheduling the transport operations. We suggest a Variable Neighbourhood Search (VNS) based SSP for this situation. We conduct simulation experiments in a dynamic job-shop environment in order to assess the performance of the suggested algorithms. The integrated SBH outperforms common dispatching rules in many situations. Using near to optimal SSPs leads to improved results compared with dispatching based SSPs for the transport operations.     

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.     

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.     

Co-evolutionary genetic algorithm for multi-machine scheduling: Coping with high performance variability

Optimizing dispatching policy in a networked, multi-machine system is a formidable task for both field experts and operations researchers due to the problem's stochastic and combinatorial nature. This paper proposes an innovative variation of co-evolutionary genetic algorithm (CGA) for acquiring the adaptive scheduling strategies in a complex multi-machine system. The task is to assign each machine an appropriate dispatching rule that is harmonious with the rules used in neighbouring machines. An ordinary co-evolutionary algorithm would not be successful due to the high variability (i.e. noisy causality) of system performance and the ripple effects among neighbouring populations. The computing time for large enough populations to avoid premature convergence would be prohibitive. We introduced the notion of derivative contribution feedback (DCF), in which an individual rule for a machine takes responsibility for the first-order change of the overall system performance according to its participation in decisions. The DCFCGA effectively suppressed premature convergence and produced dispatching rules for spatial adaptation that outperformed other heuristics. The required time for knowledge acquisition was also favourably compared with an efficient statistical method. The DCF-CGA method can be utilized in a wide variety of genetic algorithm application problems that have similar characteristics and difficulties.