A Machine Learning Approach for Energy-Efficient Intelligent Transportation Scheduling Problem in a Real-World Dynamic Circumstances

This paper provides a novel intelligent scheduling strategy for a real-world transportation dynamic scheduling case from an engine workshop of general motor company (GMEW), which is a key production line throughout the manufacturing process. In order to reduce the carbon emission in the scheduling p...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on intelligent transportation systems Ročník 24; číslo 12; s. 15527 - 15539
Hlavní autori: Mou, Jianhui, Gao, Kaizhou, Duan, Peiyong, Li, Junqing, Garg, Akhil, Sharma, Rohit
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.12.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Carbon
Clustering
Completion time
Crossovers
Dynamic scheduling
Emissions
Energy consumption
energy-efficient
Evolution
fuzzy random chance-constrained programming
Genetic algorithms
Heuristic algorithms
Inverse scheduling
Job shop scheduling
Machine learning
Populations
Production lines
real-life application
Scheduling
Sociology
Statistics
Transportation
Workshops
ISSN:1524-9050, 1558-0016
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper provides a novel intelligent scheduling strategy for a real-world transportation dynamic scheduling case from an engine workshop of general motor company (GMEW), which is a key production line throughout the manufacturing process. In order to reduce the carbon emission in the scheduling process and make up for ignoring the energy consumption of each part in the scheduling when optimizing the carbon emission of the workshop and the factory. This paper first formulates a fuzzy random chance-constrained programming model of inverse scheduling problem (ISP) with energy consumption. A multi-strategy parallel genetic algorithm based on machine learning (RL-MSPGA) is proposed, which uses machine learning to improve the genetic algorithm. First, the parallel idea is developed to accelerate the process of evolution of genetic algorithm, and the initial population is divided into clusters by <inline-formula> <tex-math notation="LaTeX">k </tex-math></inline-formula>-means clustering algorithm. Second, similar individuals are evenly distributed to different sub-populations to ensure the diversity and uniformity of sub-populations. Third, in the process of evolution, the sub-populations communicate with each other, and extend the excellent individuals to replace the poor ones in other populations, so as to improve the overall quality of the population. Fourth, the self-learning of the crossover probability is realized by the self-learning of the self-sensing environment, which makes the crossover probability adapt to the evolutionary process according to experience. Finally, the real instance is used to validate the different algorithms. It can effectively adjust the completion time and the proportion of energy consumption, thus providing the possibility for the production of energy-saving enterprises. This implies that the suggested model is reasonable and the provided algorithm can effectively solve the inverse shop scheduling problem.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1524-9050
1558-0016
DOI:10.1109/TITS.2022.3183215