Reception, mixture, and transfer in a crude oil terminal

Zimberg, Bernardo; Camponogara, Eduardo; Ferreira, Enrique

doi:10.1016/j.compchemeng.2015.07.012

Cited by 6 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lijie Su introduced an innovative continuous-discrete-time hybrid model that stratifies refinery planning and scheduling into hierarchical levels, focusing on multiperiod crude oil scheduling with the aim of maximizing net profits, achieving solution times that range from minutes to hours [19]. Algorithmically, solutions span from MILP-NLP decomposition to solver-integrated responses [20][21][22] and rolling horizon strategies for time-segmented problem-solving [23]. Additionally, intelligent search mechanisms like genetic algorithms have been adopted to bolster solution throughput [24][25][26][27].…”

Section: Related Workmentioning

confidence: 99%

“…Table 1 shows the different scales and corresponding performances of the calculation examples in the traditional method research of the crude oil scheduling problem. There are three distillers with nine charging tanks and a long-distance pipeline; every time, it needs to produce a 10-day schedule about 100 s-150 s MILP framework with rolling horizon strategy [23] Eight tanks, where one tank is assumed in maintenance, five crude qualities; the time horizon is 31 or 61 days (periods) less than 5 min…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

State-Space Compression for Efficient Policy Learning in Crude Oil Scheduling

Ma,

Li,

Liu

2024

Mathematics

View full text Add to dashboard Cite

The imperative for swift and intelligent decision making in production scheduling has intensified in recent years. Deep reinforcement learning, akin to human cognitive processes, has heralded advancements in complex decision making and has found applicability in the production scheduling domain. Yet, its deployment in industrial settings is marred by large state spaces, protracted training times, and challenging convergence, necessitating a more efficacious approach. Addressing these concerns, this paper introduces an innovative, accelerated deep reinforcement learning framework—VSCS (Variational Autoencoder for State Compression in Soft Actor–Critic). The framework adeptly employs a variational autoencoder (VAE) to condense the expansive high-dimensional state space into a tractable low-dimensional feature space, subsequently leveraging these features to refine policy learning and augment the policy network’s performance and training efficacy. Furthermore, a novel methodology to ascertain the optimal dimensionality of these low-dimensional features is presented, integrating feature reconstruction similarity with visual analysis to facilitate informed dimensionality selection. This approach, rigorously validated within the realm of crude oil scheduling, demonstrates significant improvements over traditional methods. Notably, the convergence rate of the proposed VSCS method shows a remarkable increase of 77.5%, coupled with an 89.3% enhancement in the reward and punishment values. Furthermore, this method substantiates the robustness and appropriateness of the chosen feature dimensions.

show abstract