A bi-objective Genetic Algorithm for flexible flow shop scheduling: A real-world application in the electrical industry

A comparison of scheduling algorithms for flexible flow shop problems with unrelated parallel machines, setup times, and dual criteria

Research on flow shop scheduling generally ignores uncertainties in real-world production because of the inherent difficulties of the problem. Scheduling problems with stochastic machine breakdown are difficult to solve optimally by a single approach. This paper considers makespan optimization of a flexible flow shop (FFS) scheduling problem with machine breakdown. It proposes a novel decomposition based approach (DBA) to decompose a problem into several sub-problems which can be solved more easily, while the neighbouring K-means clustering algorithm is employed to group the machines of an FFS into a few clusters. A back propagation network (BPN) is then adopted to assign either the shortest processing time (SPT) or the genetic algorithm (GA) to each cluster to solve the sub-problems. If two neighbouring clusters are allocated with the same approach, they are subsequently merged. After machine grouping and approach assignment, an overall schedule is generated by integrating the solutions to the sub-problems. Computation results reveal that the proposed approach is superior to SPT and GA alone for FFS scheduling with machine breakdown.

Hybrid genetic algorithm and tabu search for finite capacity material requirement planning system in flexible flow shop with assembly operations

A parallel genetic algorithm for multi-objective flexible flowshop scheduling in pasta manufacturing

This paper aims to investigate the improvements in manufacturing efficiency. This can be realized by broadening the scope of the production scheduling which includes both the sequencing jobs and processing-time control through the deployment of the flexible resource. This study assumes an environment in which a set of jobs must be scheduled in a flow shop, where each manufacturing cell consists of a single machine. There the processing time of each operation depends on the amount of resource allocated to the machine. This study is expected to solve the static version of flow-shop flexible-resource scheduling (SFSFR) problem with genetic algorithm to minimize the weight sum of earliness and tardiness. We suggest a master-slave genetic algorithm (MSGA) that can solve the resource allocation and job sequencing together in order to avoid the defect of two-stage method, and the heuristic algorithm of shifting job completed before due date by insertion of idle time is embedded into genetic algorithm to optimize the solutions. At last, the adaptive genetic operator is applied to increase convergence rate and improve search capability. Experimental results show that the proposed master-slave genetic algorithm performed better than other related algorithms.

In textile industries, production facilities are established as multi-stage production flow shop facilities, where a production stage may be made up of parallel machines. This known as a flexible or hybrid flow shop environment. This paper considers the problem of scheduling n independent jobs in such an environment. In addition, we also consider the general case in which parallel machines at each stage may be unrelated. Each job is processed in ordered operations on a machine at each stage. Its release date and due date are given. The preemption of jobs is not permitted. We consider both sequence- and machine-dependent setup times. The problem is to determine a schedule that minimizes a convex combination of makespan and the number of tardy jobs. A 0–1 mixed integer program of the problem is formulated. Since this problem is NP-hard in the strong sense, we develop heuristic algorithms to solve it approximately. Firstly, several basic dispatching rules and well-known constructive heuristics for flow shop makespan scheduling problems are generalized to the problem under consideration. We sketch how, from a job sequence, a complete schedule for the flexible flow shop problem with unrelated parallel machines can be constructed. To improve the solutions, polynomial heuristic improvement methods based on shift moves of jobs are applied. Then, genetic algorithms are suggested. We discuss the components of these algorithms and test their parameters. The performance of the heuristics is compared relative to each other on a set of test problems with up to 50 jobs and 20 stages.

Flexible flow shop (or a hybrid flow shop) scheduling problem is an extension of classical flow shop scheduling problem. In a simple flow shop configuration, a job having ‘g’ operations is performed on ‘g’ operation centres (stages) with each stage having only one machine. If any stage contains more than one machine for providing alternate processing facility, then the problem becomes a flexible flow shop problem (FFSP). FFSP which contains all the complexities involved in a simple flow shop and parallel machine scheduling problems is a well-known NP-hard (Non-deterministic polynomial time) problem. Owing to high computational complexity involved in solving these problems, it is not always possible to obtain an optimal solution in a reasonable computation time. To obtain near-optimal solutions in a reasonable computation time, a large variety of meta-heuristics have been proposed in the past. However, tuning algorithm-specific parameters for solving FFSP is rather tricky and time consuming. To address this limitation, teaching–learning-based optimization (TLBO) and JAYA algorithm are chosen for the study because these are not only recent meta-heuristics but they do not require tuning of algorithm-specific parameters. Although these algorithms seem to be elegant, they lose solution diversity after few iterations and get trapped at the local optima. To alleviate such drawback, a new local search procedure is proposed in this paper to improve the solution quality. Further, mutation strategy (inspired from genetic algorithm) is incorporated in the basic algorithm to maintain solution diversity in the population. Computational experiments have been conducted on standard benchmark problems to calculate makespan and computational time. It is found that the rate of convergence of TLBO is superior to JAYA. From the results, it is found that TLBO and JAYA outperform many algorithms reported in the literature and can be treated as efficient methods for solving the FFSP.

Scheduling is an important process widely used in manufacturing, production, management, computer science, and so on. Appropriate scheduling can reduce material handling costs and time. Finding good schedules for given sets of jobs can thus help factory supervisors effectively control job flows and provide solutions for job sequencing. In simple flow shop problems, each machine operation center includes just one machine. If at least one machine center includes more than one machine, the scheduling problem becomes a flexible flow-shop problem. Flexible flow shops are thus generalization of simple flow shops. In this paper, we propose three algorithms to solve flexible flow-shop problems of more than two machine centers. The first one extends Sriskandarajah and Seth's method by combining both the LPT and the search-and-prune approaches to get a nearly optimal makespan. It is suitable for a medium-sized number of jobs. The second one is an optimal algorithm, entirely using the search-and-prune technique. It can work only when the job number is small. The third one is similar to the first one, except that it uses Petrov's approach (PT) to deal with job sequencing instead of searchand- prune. It can get a polynomial time complexity, thus being more suitable for real applications than the other two. Experiments are also made to compare the three proposed algorithms. A trade-off can thus be achieved between accuracy and time complexity.

Flexible flow shops can be thought of as generalizations of simple flow shops. In the past, the processing time for each job was usually assumed to be known exactly, but in many real-world applications, processing times may vary dynamically due to human factors or operating faults. In the past, we demonstrated how discrete fuzzy concepts could easily be used in the Palmer algorithm for managing uncertain flexible-flow-shop scheduling. In this paper, we generalize it to continuous fuzzy domains. We use triangular membership functions for flexible flow shops with more than two machine centers to examine processing-time uncertainties and to make scheduling more suitable for real applications. We first use the triangular fuzzy LPT algorithm to allocate jobs, and then use the triangular fuzzy Palmer algorithm to deal with sequencing the tasks. The proposed method thus provides a more flexible way of scheduling jobs than conventional scheduling methods.

In simple flow shop problems, each machine operation center includes just one machine. If at least one machine center includes more than one machine, the scheduling problem becomes a flexible flow shop problem (FFSP). Flexible flow shops are thus generalization of simple flow shops. Flexible flow shop scheduling problems have a special structure combining some elements of both the flow shop and the parallel machine scheduling problems. FFSP can be stated as finding a schedule for a general task graph to execute on a multiprocessor system so that the schedule length can be minimized. FFSP is known to be NP-hard. In this study, we present a particle swarm optimization (PSO) algorithm to solve FFSP. PSO is an effective algorithm which gives quality solutions in a reasonable computational time and consists of less numbers parameters as compared to the other evolutionary metaheuristics. Mutation, a commonly used operator in genetic algorithm, has been introduced in PSO so that trapping of solutions at local minima or premature convergence can be avoided. Logistic mapping is used to generate chaotic numbers in this paper. Use of chaotic numbers makes the algorithm converge fast towards near-optimal solution and hence reduce computational efforts further. The performance of schedules is evaluated in terms of total completion time or makespan (Cmax). The results are presented in terms of percentage deviation (PD) of the solution from the lower bound. The results are compared with different versions of genetic algorithm (GA) used for the purpose from open literature. The results indicate that the proposed PSO algorithm is quite effective in reducing makespan because average PD is observed as 2.961, whereas GA results in average percentage deviation of 3.559. Finally, influence of various PSO parameters on solution quality has been investigated.

The flexible flow shop (FFS) is defined as a multistage flow shop with multiple parallel machines. FFS scheduling problem is a complex combinatorial problem which has been intensively studied in many real world industries. In the FFS scheduling problem, each job has to be processed on any machine at each stage, but it is not considered that how the jobs are transported from one machine to another. In this study, materials are transported from one machine to another through autonomous guided vehicles (AGV) system. In this paper, we propose a genetic algorithm (GA) for solving FFS scheduling problem in which AGVs are used to transport materials. We design effective coding and decoding scheme and genetic operators including crossover and mutation. The effectiveness of the algorithm is verified by simulation experiments.

The problem of flexible hybrid flow shop scheduling with identical and non-identical parallel machines in one or more stages has been considered with the objective of minimising the makespan. A Simulated Annealing (SA) approach has been developed to select the best solutions in a flexible hybrid flow shop scheduling. The SA approach identifies the best sequences for the given set of jobs in a 2-stage/2-machine and 2-stage/3-machine hybrid flow shop problems. The extent of deviation of the performance measures owing to the flexibility in the arrangement of machines in the two stages has been analysed. The proposed SA algorithm has been applied to benchmark problems taken from Taillard (1993). A comparison of the solutions yielded by the ant-colony algorithm by Stuetzle (1998), called Max-Min Ant System (MMAS) and the SA algorithm developed in this paper, with the heuristic solutions given by Taillard is undertaken with respect to the minimisation of makespan. The comparison shows that the proposed SA algorithm performs better on the average, than the MMAS.

Flow shop scheduling is one of the most well-known production scheduling problems and a typical NP-hard combinatorial optimization problem with strong engineering background. This paper presents an order-based genetic algorithm for flow shop scheduling, which borrows the idea of ordinal optimization to reduce computation and ensure the quality of the solution found and enforces the evolutionary searching mechanism and learning capability of the genetic algorithm. With the guidance of ordinal comparison and by emphasizing the order-based search and elitist-based evolution in the proposed approach, a good enough solution can be guaranteed with high confidence level and reduced computation quantity, which is demonstrated by the numerical simulation based on some benchmarks. Moreover, some parameter sensitivities are presented and discussed.

The economic lot scheduling problem in limited-buffer flexible flow shops: Mathematical models and a discrete fruit fly algorithm

This paper deals with the development and analysis of hybrid genetic algorithms for flow shop scheduling problems with sequence dependent setup time. A constructive heuristic called setup ranking algorithm is used for generating the initial population for genetic algorithm. Different variations of genetic algorithm are developed by using combinations of types of initial populations and types of crossover operators. For the purpose of experimentation, 27 group problems are generated with ten instances in each group for flow shop scheduling problems with sequence dependent setup time. An existing constructive algorithm is used for comparing the performance of the algorithms. A full factorial experiment is carried out on the problem instances developed. The best settings of genetic algorithm parameters are identified for each of the groups of problems. The analysis reveals the superior performance of hybrid genetic algorithms for all the problem groups.