A Suitable Initialization Procedure for Speeding a Neural Network Job-Shop Scheduling

Yahyaoui, Amani; Fnaiech, Nader; Fnaiech, Farhat

doi:10.1109/tie.2010.2048290

Cited by 39 publications

(23 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The initial population quality has a significant impact on the performance of an evolutionary algorithm. Good initial solutions can significantly improve the convergence rate and solution quality of the algorithm [51]. In this paper, the MME algorithm, combined with the NEH [5] and MM [29] heuristic algorithms, is used to generate the initial population.…”

Section: Initial Populationmentioning

confidence: 99%

Hybrid Genetic Simulated Annealing Algorithm for Improved Flow Shop Scheduling with Makespan Criterion

Wei

Jiang

et al. 2018

Applied Sciences

View full text Add to dashboard Cite

Flow shop scheduling problems have a wide range of real-world applications in intelligent manufacturing. Since they are known to be NP-hard for more than two machines, we propose a hybrid genetic simulated annealing (HGSA) algorithm for flow shop scheduling problems. In the HGSA algorithm, in order to obtain high-quality initial solutions, an MME algorithm, combined with the MinMax (MM) and Nawaz–Enscore–Ham (NEH) algorithms, was used to generate the initial population. Meanwhile, a hormone regulation mechanism for a simulated annealing (SA) schedule was introduced as a cooling scheme. Using MME initialization, random crossover and mutation, and the cooling scheme, we improved the algorithm’s quality and performance. Extensive experiments have been carried out to verify the effectiveness of the combination approach of MME initialization, random crossover and mutation, and the cooling scheme for SA. The result on the Taillard benchmark showed that our HGSA algorithm achieved better performance relative to the best-known upper bounds on the makespan compared with five state-of-the-art algorithms in the literature. Ultimately, 109 out of 120 problem instances were further improved on makespan criterion.

show abstract

Section: Initial Populationmentioning

confidence: 99%

Hybrid Genetic Simulated Annealing Algorithm for Improved Flow Shop Scheduling with Makespan Criterion

Wei

Jiang

et al. 2018

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…SA-ANN is the combination of fast SA with combinatorial optimization (FSA-CO) and back propagation (BP) network [37], [38]. Because SA is a heuristic random search method, it is different from traditional random search method, which not only introduces adequate random factors, but pulls in the natural mechanism of physical annealing process [39].…”

Section: Improved Sa-ann Algorithmmentioning

confidence: 99%

SA-ANN-Based Slag Carry-Over Detection Method and the Embedded WME Platform

Tan

Li²,

et al. 2013

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

Slag carry-over detection technology (SCDT) is of important significance for steel continuous casting production (CCP), but has the problems with manufacture cost, service life, installation, and maintenance. Aiming at the problems, this paper brings forward a novel vibration style SCDT realization method based on simulated annealing artificial neural network (SA-ANN). According to ladle pouring process, the vibration signal of steel stream is regarded as the target signal for SCDT. Then, the time point of slag carry-over can be obtained in light of the vibration amplitude difference of pure molten steel and steel slag. Based on the fluid flow similarity principles, an embedded water model experiment (WME) platform is established. The WME platform can simulate the physical process of ladle pouring, reduce the system debugging time under formidable CCP field conditions, and improve the industrial suitability of SCDT. Using an improved SA-ANN algorithm, the status of steel stream is identified to realize automatic control for ladle pouring. WME simulated test results show that the slag detection accuracy (SDA) of this method can reach more 99%. CCP industrial field experiment proves that this method requires low cost and little rebuilding for the current CCP devices, and the practical SDA can reach more 96%.Index Terms-Embedded system, shock vibration, simulated annealing artificial neural network (SA-ANN), slag carry-over detection, water model experiment (WME).

show abstract

“…These methods mainly include dispatching priority rules [5][6][7], shifting bottleneck approach [8,9], Lagrangian relaxation [10,11], tabu search [12][13][14] and have made considerable achievement. In recent years, much attention has been devoted to meta-heuristics with the emergence of new techniques from the field of artificial intelligence such as genetic algorithm (GA) [15][16][17][18], simulated annealing (SA) [19][20][21][22], ant colony optimization (ACO) [23], particle swarm optimization (PSO) [24,25], artificial neural network (ANN) [26][27][28], bacterial foraging algorithm (BFA) [29], and so on. These meta-heuristics can be regarded as problem-independent…”

Section: Introductionmentioning

confidence: 99%

A Coevolutionary Bacterial Foraging Model Using PSO in Job-Shop Scheduling Environments

Sun¹,

Wang²,

Ge³

2016

IJGDC

View full text Add to dashboard Cite

show abstract

A Suitable Initialization Procedure for Speeding a Neural Network Job-Shop Scheduling

Cited by 39 publications

References 22 publications

Hybrid Genetic Simulated Annealing Algorithm for Improved Flow Shop Scheduling with Makespan Criterion

Hybrid Genetic Simulated Annealing Algorithm for Improved Flow Shop Scheduling with Makespan Criterion

SA-ANN-Based Slag Carry-Over Detection Method and the Embedded WME Platform

A Coevolutionary Bacterial Foraging Model Using PSO in Job-Shop Scheduling Environments

Contact Info

Product

Resources

About