ArticleACS omega2025
Optimal Control of Specification in LPG Blend: A Deep Learning and PSO-Driven Framework for Minimizing Off-Spec Production.
Article in ACS omega, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 1 paper.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
1 citing paper in PubMed.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Liquefied Petroleum Gas (LPG) is a crucial energy source, widely utilized in residential, industrial, agricultural, and transportation sectors, where its safe and efficient use relies on accurate product specifications. In the refining industry, LPG is produced in different process units, and final products are blended in LPG storage for sale. Due to changes in the operational parameters of LPG production units, the final product specification can vary. Detection of off-spec production occurs only when the routine sample results are available. However, as production is ongoing, by then, a significant volume of off-spec material may already be blended, posing economic risks such as downgrading or reprocessing off-spec LPG. The annual data set shows that This 10% value corresponds to thousands of tons of product loss and hundreds of thousands of dollars in economic damage. Moreover, failure to meet product specifications can lead to penalties or customer dissatisfaction. To address this challenge, a proactive two-stage approach is proposed. The first stage involves an LSTM-based deep learning model that levers the historical measurement data to predict controllable product specifications within the blending tank. This predictive capability already offers decision-makers significant value by providing early warnings for off-spec formation. However, our research extends this framework by integrating the predictive model with a particle swarm optimization stage. This second stage identifies the optimal operational parameters that can be controlled during the production of LPG in each production unit, ensuring that the off-spec risk in the final tank is effectively mitigated. The methodology uniquely accounts for the differential impacts of identical input variables across various hydrocarbon components, thereby enhancing the precision in capturing the optimal operating conditions for economic savings, ultimately enhancing production efficiency and reducing labor hours. Implementations are limited to the LPG in a particular refinery but can be extended to similar processes. Crude oil types used were not included in this research which can affect the LPG specifications but cannot be manipulated.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.