Two-phase imperialist competitive algorithm for energy-efficient flexible job shop scheduling

Guo, Jiong; Lei, Deming; Li, Ming

doi:10.3233/jifs-210198

Cited by 7 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The FJSP problem has also been studied by researchers. In order to ensure green production while maximising production efficiency, Gong et shop scheduling means that any machine can be selected for the entire production and processing of the product [18,19]. Biassed flexible job-shop scheduling allows for the selection of machines for some procedures.…”

Section: Related Workmentioning

confidence: 99%

A Study of Deep Learning Neural Network Algorithms and Genetic Algorithms for FJSP

Shang

2023

Journal of Applied Mathematics

View full text Add to dashboard Cite

Flexible job-shop scheduling problem (FJSP) is a new research hotspot in the field of production scheduling. To solve the multiobjective FJSP problem, the production of flexible job shop can run normally and quickly. This research takes into account various characteristics of FJSP problems, such as the need to ensure the continuity and stability of processing, the existence of multiple objectives in the whole process, and the constant complexity of changes. It starts with deep learning neural networks and genetic algorithms. Long short-term memory (LSTM) and convolutional neural networks (CNN) are combined in deep learning neural networks. The new improved algorithm is based on the combination of deep learning neural networks LSTM and CNN with genetic algorithm (GA), namely, CNN-LSTM-GA algorithm. Simulation results showed that the accuracy of the CNN-LSTM-GA algorithm was between 85.2% and 95.3% in the test set. In the verification set, the minimum accuracy of the CNN-LSTM-GA algorithm was 84.6%, both of which were higher than the maximum accuracy of the other two algorithms. In the FJSP simulation experiment, the AUC value of the CNN-LSTM-GA algorithm was 0.92. After 40 iterations, the F1 value of the CNN-LSTM-GA algorithm remained above 0.8, which was significantly higher than the other two algorithms. CNN-LSTM-GA is superior to the other two algorithms in terms of prediction accuracy and overall performance of FJSP. It is more suitable for solving the discrete manufacturing job scheduling problem with FJSP characteristics. This study significantly raises the utilisation rate of the assembly shop’s equipment, optimises the scheduling of FJSP, and fully utilises each processing device’s versatile characteristics, which are quite useful for the production processes of domestic vehicle manufacturing companies.

show abstract

Section: Related Workmentioning

confidence: 99%

A Study of Deep Learning Neural Network Algorithms and Genetic Algorithms for FJSP

Shang

2023

Journal of Applied Mathematics

View full text Add to dashboard Cite

show abstract

“…In the related literature, various models of energy consumption processes by machines [5] and types of shop floors are analyzed. The models are classified according to computational complexity, such as scheduling individual machines [8][9][10][11][12][13], flow shops [1,2,6,14,15], job shops [16][17][18], and flexible job shops [19], as well as hybrid systems for specific issues [20][21][22]. No-wait flow shop scheduling is a hot topic in academic research due to its wide applicability in industrial domains [6].…”

Section: Introductionmentioning

confidence: 99%

A Discrete-Time Queueing Model of a Bottleneck with an Energy-Saving Mechanism Based on Setup and Shutdown Times

Kempa,

Paprocka

2024

Symmetry

View full text Add to dashboard Cite

Producers are encouraged to reduce their energy consumption of manufacturing systems by applying less-energy-intensive modern technologies and advanced machine tools and operating methods at the system level. In the paper, organizational and analytical solutions are combined to model the sustainable production system. Managers can study the behavior of a production system organized using energy-saving rules by changing key parameters of the input model (arrival intensity, bottleneck service rate, buffer size, setup and shutdown time) to analyze the queue size of the production system and therefore performance. A discrete-time queueing model of a single-bottleneck production line with a finite input buffer capacity is proposed. Jobs occur according to a binomial process and are processed individually, one by one, according to the natural FIFO service discipline, with a general discrete-type cumulative distribution function. The total number of jobs present in the system is bounded by a non-random fixed value N. Every time the system becomes empty, an energy-saving mechanism is started: the processing machine (server) is turned off during a geometrically distributed shutdown time. Similarly, the first job arriving into the empty system initializes a geometrically distributed setup time. Identifying renewal moments in the evolution of the model, a system of difference equations is built for the transient queue-size distribution conditioned by the state of the system at the opening. The solution is obtained explicitly in terms of probability-generating functions. In addition, the Drum-Buffer-Rope concept is proposed to reduce the energy consumption of the production line. The throughput of the production system is maximized by adjusting the time between the order arrivals and the size of the input buffer to the capacity of the bottleneck. Turning off a machine under certain conditions and slowing down non-critical machines are strategies to reduce energy consumption. A detailed illustrating numerical and simulation study of the considered model is attached as well, in which the sensitivity of the queue-size behavior to changes of the key input model parameters is investigated.

show abstract

Efficient multi-objective meta-heuristic algorithms for energy-aware non-permutation flow-shop scheduling problem

Goli

Ala

Hajiaghaei–Keshteli

2023

Expert Systems with Applications

View full text Add to dashboard Cite

Two-phase imperialist competitive algorithm for energy-efficient flexible job shop scheduling

Cited by 7 publications

References 38 publications

A Study of Deep Learning Neural Network Algorithms and Genetic Algorithms for FJSP

A Study of Deep Learning Neural Network Algorithms and Genetic Algorithms for FJSP

A Discrete-Time Queueing Model of a Bottleneck with an Energy-Saving Mechanism Based on Setup and Shutdown Times

Efficient multi-objective meta-heuristic algorithms for energy-aware non-permutation flow-shop scheduling problem

Contact Info

Product

Resources

About