A neural network job-shop scheduler

Weckman, Gary R.; Ganduri, Chandrasekhar; Koonce, David A.

doi:10.1007/s10845-008-0073-9

Cited by 86 publications

(63 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supervised learning techniques such as decision tree [107,127], logistic regression [57], support vector machines [129], and artificial neural networks [32,138] have also been investigated in the literature for automated design of production scheduling heuristics. For supervised learning, optimal decisions from solving small instances with exact optimisation methods or from the historical data are needed to build the training set.…”

Section: Machine Learningmentioning

confidence: 99%

“…As compared to other hyper-heuristics based on supervised learning such as decision tree [107,127], logistic regression [57], support vector machine [129], and artificial neural networks [32,138], genetic programming (GP) has shown a number of key advantages. First, GP has flexible representations which allow various heuristics to be represented as different computer programs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Genetic programming for production scheduling: a survey with a unified framework

Nguyen

Mei

Zhang

2017

Complex Intell. Syst.

214

101

View full text Add to dashboard Cite

Genetic programming has been a powerful technique for automated design of production scheduling heuristics. Many studies have shown that heuristics evolved by genetic programming can outperform many existing heuristics manually designed in the literature. The flexibility of genetic programming also allows it to discover very sophisticated heuristics to deal with complex and dynamic production environments. However, as compared to other applications of genetic programming or scheduling applications of other evolutionary computation techniques, the configurations and requirements of genetic programming for production scheduling are more complicated. In this paper, a unified framework for automated design of production scheduling heuristics with genetic programming is developed. The goal of the framework is to provide the researchers with the overall picture of how genetic programming can be applied for this task and the key components. The framework is also used to facilitate our discussions and analyses of existing studies in the field. Finally, this paper shows how knowledge from machine learning and operations research can be employed and how the current challenges can be addressed.

show abstract

Section: Machine Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Genetic programming for production scheduling: a survey with a unified framework

Nguyen

Mei

Zhang

2017

Complex Intell. Syst.

214

101

View full text Add to dashboard Cite

show abstract

“…Neural networks are used for modelling complex relationships or for data mining; i.e. the search for a previously unknown function which we cannot determine analytically [21,22]. In this article, we are going to schedule the orders in a workshop using a hybrid algorithm which is a combination of the heuristic algorithm with priority rules, discrete event simulation and genetic algorithms.…”

Section:  Departure Of the Ordersmentioning

confidence: 99%

Hybrid Algorithm Based on Priority Rules for Simulation of Workshop Production

Zupan¹,

Herakovič²,

Starbek³

2016

Int. j. simul. model.

View full text Add to dashboard Cite

The proposed hybrid algorithm is a combination of heuristic algorithm extended with priority rules, discrete event simulation and genetics algorithm. It takes into account 11 different priority rules and scenarios, is based on the assumption that for a realistic workshop scheduling of orders, it is necessary to consider real throughput times of the operations, otherwise the obtained scheduling of orders is not suitable for the industrial environment. The simulation result for the proposed model is the optimal sequence of selected orders for the selected time interval while taking into account three criteria: the minimum flow time of all orders, the maximum average utilization of workplaces, and the minimum waiting time of the orders. Because the mentioned criteria are usually mutually exclusive the advantage of the proposed model is that we can find the optimum with respect to all three criteria. In the paper, an example of the application of the proposed model is shown.

show abstract

“…Some of them include priority dispatching rules [12,13], and the mobile bottle neck algorithm [14,15]. Recent researches have mostly focused on more advanced heuristic algorithms, better known as "metaheuristics", which propose several approaches like the tabu search [16][17][18][19], simulated annealing [20][21][22], ant colony optimization [23][24][25][26], particle swarm optimization [27][28][29][30], neuronal network [31,32], and genetic algorithms (GA). In particular, the GA are based on Darwin's evolutionary theory, and they have been employed to provide successful solutions to various combinatorial problems (JSP included [33][34][35][36]) since they allow exploring in an efficient way the solution space; nevertheless, they may converge prematurely.…”

Section: Introductionmentioning

confidence: 99%

“…The basis of the MA lays on individual enhancements of the solutions of agents that interrelate one to another in a process that contains stages of cooperation and population competition. The MA has been successfully used in different areas and combinatorial problems, such as the knapsack problem [38][39][40], routing problems [41][42][43], quadratic assignment [44][45], and spanning tree [32,46], among others. In order to give a solution to the JSP, some studies [1,[47][48][49][50] have proposed a MA, where the global search given by the GA is combined with a neighborhood structure based on Nowicki and Smutnicki [51], which allows the leading of the local search and the efficient exploitation of the solution space with the generation of three adjacent solutions for each initial solution; all of this with the final goal of minimizing the makespan.…”

Section: Introductionmentioning

confidence: 99%

A memetic algorithm for minimizing the makespan in the Job Shop Scheduling problem

Lamos-Díaz¹,

Aguilar-Imitola²,

Pérez-Díaz³

et al. 2017

Rev. Fac. Ing.

View full text Add to dashboard Cite

The Job Shop Scheduling Problem (JSP) is a combinatorial optimization problem cataloged as type NP-Hard. To solve this problem, several heuristics and metaheuristics have been used. In order to minimize the makespan, we propose a Memetic Algorithm (MA), which combines the exploration of the search space by a Genetic Algorithm (GA), and the exploitation of the solutions using a local search based on the neighborhood structure of Nowicki and Smutnicki. The genetic strategy uses an operation-based representation that allows generating feasible schedules, and a selection probability of the best individuals that are crossed using the JOX operator. The results of the implementation show that the algorithm is competitive with other approaches proposed in the literature.

show abstract

A neural network job-shop scheduler

Cited by 86 publications

References 15 publications

Genetic programming for production scheduling: a survey with a unified framework

Genetic programming for production scheduling: a survey with a unified framework

Hybrid Algorithm Based on Priority Rules for Simulation of Workshop Production

A memetic algorithm for minimizing the makespan in the Job Shop Scheduling problem

Contact Info

Product

Resources

About