MDPI - Publisher of Open Access Journals

19 pages, 3470 KiB

Open AccessArticle

Soft Sensing of LPG Processes Using Deep Learning

by Nikolaos Sifakis, Nikolaos Sarantinoudis, George Tsinarakis, Christos Politis and George Arampatzis

Sensors 2023, 23(18), 7858; https://doi.org/10.3390/s23187858 - 13 Sep 2023

Cited by 9 | Viewed by 2249

Abstract

This study investigates the integration of soft sensors and deep learning in the oil-refinery industry to improve monitoring efficiency and predictive accuracy in complex industrial processes, particularly de-ethanization and debutanization. Soft sensor models were developed to estimate critical variables such as the C2 and C5 contents in liquefied petroleum gas (LPG) after distillation and the energy consumption of distillation columns. The refinery’s LPG purification process relies on periodic sampling and laboratory analysis to maintain product specifications. The models were tested using data from actual refinery operations, addressing challenges such as scalability and handling dirty data. Two deep learning models, an artificial neural network (ANN) soft sensor model and an ensemble random forest regressor (RFR) model, were developed. This study emphasizes model interpretability and the potential for real-time updating or online learning. The study also proposes a comprehensive, iterative solution for predicting and optimizing component concentrations within a dual-column distillation system, highlighting its high applicability and potential for replication in similar industrial scenarios. Full article

(This article belongs to the Section Industrial Sensors)

► Show Figures

Figure 1

18 pages, 1479 KiB

Open AccessArticle

Quantification and Removal of Volatile Sulfur Compounds (VSCs) in Atmospheric Emissions in Large (Petro) Chemical Complexes in Different Countries of America and Europe

by Joaquín Hernández-Fernández, Heidi Cano and Susana Rodríguez-Couto

Sustainability 2022, 14(18), 11402; https://doi.org/10.3390/su141811402 - 11 Sep 2022

Cited by 7 | Viewed by 2638

Abstract

The present research was focused on the determination and removal of sulfur-containing compounds in industrial emissions of liquefied petroleum gas purification processes in petrochemical plants located in the USA, Brazil, Colombia, Spain, and Italy. For the analysis of volatile sulfur compounds (VSCs), an improved analytical methodology was implemented. The performance of the method was evaluated for eight VSCs in a linear dynamic range between 0.1 and 50 ppm. The concentrations of the eight VSCs in the deethanizer affluents ranged from 11 to 49 ppm for all the studied plants, which exceed the limits specified by institutions and administrations in occupational health and safety. The concentrations of the eight VSCs in the splitter affluents were lower than 4 ppm for all the considered plants. The emissions from each column depended upon its operating rate, with the highest concentrations estimated at 45 TM kg⁻¹ and the lowest ones at 25 TM kg⁻¹. A zeolite-packed prototype column was fitted at the outlet of the splitter and deethanizer columns to reduce the environmental effect of the examined VSCs. This technique was verified and put into practice on an industrial scale, obtaining VSC removal percentages of between 85 and 91%. Full article

(This article belongs to the Special Issue Sustainable Industrial Ecology: Reducing the Environmental Impact of an Industrial Process)

► Show Figures

Figure 1

9 pages, 2329 KiB

Open AccessCommunication

Purification for Carbon Nanotubes Synthesized by Flame Fragments Deposition via Hydrogen Peroxide and Acetone

by Asmaa H. Hammadi, Ahmed M. Jasim, Firas H. Abdulrazzak, Abdulkareem M. A. Al-Sammarraie, Yacine Cherifi, Rabah Boukherroub and Falah H. Hussein

Materials 2020, 13(10), 2342; https://doi.org/10.3390/ma13102342 - 20 May 2020

Cited by 25 | Viewed by 4260

Abstract

Carbon nanotubes (CNTs) are synthesized by the flame fragment deposition (FFD) technique using Iraqi liquefied petroleum gas (LPG) as a source of carbon in a hand-made reactor at a low temperature (160 °C) without using a catalyst. Purification of the multi-walled carbon nanotubes (MWCNTs) is carried out using a two-step process consisting of sonication in 30 wt.% hydrogen peroxide (H₂O₂) solution at room temperature to remove amorphous impurities adhering to the walls of the CNTs and carbon nanoparticles (CNPs), followed by sonication in an acetone bath to remove the polyaromatic hydrocarbons (PAH) formed during the LPG gas burning. Comprehensive characterizations such as X-ray diffraction (XRD), atomic force microscopy (AFM), thermo-gravimetric analysis (TGA), and transmission electron microscopy (TEM) were conducted to verify the efficiency of the purification process. The results clearly demonstrated that this process is promising for the purification of the synthesized CNTs. Full article

(This article belongs to the Section Carbon Materials)

► Show Figures

Figure 1

17 pages, 684 KiB

Open AccessArticle

Life Cycle Assessment of Three Safe Drinking-Water Options in India: Boiled Water, Bottled Water, and Water Purified with a Domestic Reverse-Osmosis Device

by Tirma Garcia-Suarez, Michal Kulak, Henry King, Julia Chatterton, Arunima Gupta and Skand Saksena

Sustainability 2019, 11(22), 6233; https://doi.org/10.3390/su11226233 - 7 Nov 2019

Cited by 17 | Viewed by 6244

Abstract

Indian households connected to improved water sources still need to purify their water before drinking. In this study, environmental impacts of three purification options in urban India were compared: (a) boiling water, (b) bottled, purified water, and (c) purifying the water with a domestic reverse-osmosis (RO) device. Primary data for the manufacture, distribution, and the use of the RO device were obtained directly from the manufacturer. Standard, attributional Life Cycle Assessment was performed using a suite of impact assessment methods from ReCiPe v 1.8. In addition, blue and green water consumptions were quantified using the Quantis water database. Bottled water was found to be associated with the highest impacts for all impact categories considered, mainly due to the production and the transportation of bottles. The preference between the other two systems depends on the considered impact category. Water boiled using the liquefied petroleum gas (current practice of urban consumers in India) was found to have higher impacts on climate change and fossil resource use than water from a domestic RO device. The use of the device; however, was found to have higher impacts on water resources than boiling, both in terms of quality (freshwater eutrophication) and availability (water consumption). Full article

(This article belongs to the Section Environmental Sustainability and Applications)

► Show Figures

Figure 1

Search Results (4)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI

Saved Queries

Search Filter Reset All

Years

Feature Papers

Subjects

Journals

Article Types

Countries / Regions

Search Results (4)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI