scholarly journals A Data-Driven Reaction Network for the Fluid Catalytic Cracking of Waste Feeds

Processes ◽  
2018 ◽  
Vol 6 (12) ◽  
pp. 243 ◽  
Author(s):  
José Alvira ◽  
Idoia Hita ◽  
Elena Rodríguez ◽  
José Arandes ◽  
Pedro Castaño
Keyword(s):  
Catalytic Cracking ◽  
Reaction Network ◽  
Principal Component ◽  
Vacuum Gasoil ◽  
Fluid Catalytic Cracking ◽  
Data Driven ◽  
Pyrolysis Oil ◽  
Scrap Tire ◽  
Feed Composition ◽  
Operational Conditions

Establishing a reaction network is of uttermost importance in complex catalytic processes such as fluid catalytic cracking (FCC). This step is the seed for a faithful reactor modeling and the subsequent catalyst re-design, process optimization or prediction. In this work, a dataset of 104 uncorrelated experiments, with 64 variables, was obtained in an FCC simulator using six types of feedstock (vacuum gasoil, polyethylene pyrolysis waxes, scrap tire pyrolysis oil, dissolved polyethylene and blends of the previous), 36 possible sets of conditions (varying contact time, temperature and catalyst/oil ratio) and three industrial catalysts. Principal component analysis (PCA) was applied over the dataset, showing that the main components are associated with feed composition (27.41% variance), operational conditions (19.09%) and catalyst properties (12.72%). The variables of each component were correlated with the indexes and yields of the products: conversion, octane number, aromatics, olefins (propylene) or coke, among others. Then, a data-driven reaction network was proposed for the cracking of waste feeds based on the previously obtained correlations.

scholarly journals Correlating the Process Variables and Products Involved in the Fluid Catalytic Cracking of Waste Feeds

2018 ◽  
Author(s):  
José Ignacio Alvira ◽  
Idoia Hita ◽  
Elena Rodriguez ◽  
Jose M Arandes ◽  
Pedro Castaño
Keyword(s):  
Catalytic Cracking ◽  
Principal Component ◽  
Product Distribution ◽  
Vacuum Gasoil ◽  
Fluid Catalytic Cracking ◽  
Pyrolysis Oil ◽  
Scrap Tire ◽  
Feed Composition ◽  
Operational Conditions ◽  
Main Components

Associating the most influential parameters with the product distribution is of uttermost importance in complex catalytic processes such as fluid catalytic cracking (FCC). These correlations can lead to the information-driven catalyst screening, kinetic modeling and reactor design. In this work, a dataset of 104 uncorrelated experiments, with 64 variables, has been obtained in an FCC simulator using 6 types of feedstock (vacuum gasoil, polyethylene pyrolysis waxes, scrap tire pyrolysis oil, dissolved polyethylene and blends of the previous), 36 possible sets of conditions (varying contact time, temperature and catalyst/oil ratio) and 3 industrial catalysts. Principal component analysis (PCA) has been applied over the dataset, showing that the main components are associated with feed composition (27.41% variance); operational conditions (19.09%) and catalyst properties (12.72%). The variables of each component have been correlated with the indexes and yields of the products: conversion, octane number, aromatics, olefins (propylene) or coke, among others.

Scrap tires pyrolysis oil as a co-feeding stream on the catalytic cracking of vacuum gasoil under fluid catalytic cracking conditions

2020 ◽  
Vol 105 ◽  
pp. 18-26 ◽  
Author(s):  
Elena Rodríguez ◽  
Roberto Palos ◽  
Alazne Gutiérrez ◽  
José M. Arandes ◽  
Javier Bilbao
Keyword(s):  
Catalytic Cracking ◽  
Vacuum Gasoil ◽  
Fluid Catalytic Cracking ◽  
Pyrolysis Oil ◽  
Scrap Tires

Synergy in the Cracking of a Blend of Bio-oil and Vacuum Gasoil under Fluid Catalytic Cracking Conditions

2016 ◽  
Vol 55 (7) ◽  
pp. 1872-1880 ◽  
Author(s):  
Álvaro Ibarra ◽  
Elena Rodríguez ◽  
Ulises Sedran ◽  
José M. Arandes ◽  
Javier Bilbao
Keyword(s):  
Catalytic Cracking ◽  
Vacuum Gasoil ◽  
Fluid Catalytic Cracking ◽  
Bio Oil

scholarly journals Adaptable and Explainable Predictive Maintenance: Semi-Supervised Deep Learning for Anomaly Detection and Diagnosis in Press Machine Data

2021 ◽  
Vol 11 (16) ◽  
pp. 7376
Author(s):  
Oscar Serradilla ◽  
Ekhi Zugasti ◽  
Julian Ramirez de Okariz ◽  
Jon Rodriguez ◽  
Urko Zurutuza
Keyword(s):  
Anomaly Detection ◽  
Null Space ◽  
Model Performance ◽  
Principal Component ◽  
Predictive Maintenance ◽  
Data Driven ◽  
Support Vector ◽  
Operational Conditions ◽  
Detection Model ◽  
Cluster Data

Predictive maintenance (PdM) has the potential to reduce industrial costs by anticipating failures and extending the work life of components. Nowadays, factories are monitoring their assets and most collected data belong to correct working conditions. Thereby, semi-supervised data-driven models are relevant to enable PdM application by learning from assets’ data. However, their main challenges for application in industry are achieving high accuracy on anomaly detection, diagnosis of novel failures, and adaptability to changing environmental and operational conditions (EOC). This article aims to tackle these challenges, experimenting with algorithms in press machine data of a production line. Initially, state-of-the-art and classic data-driven anomaly detection model performance is compared, including 2D autoencoder, null-space, principal component analysis (PCA), one-class support vector machines (OC-SVM), and extreme learning machine (ELM) algorithms. Then, diagnosis tools are developed supported on autoencoder’s latent space feature vector, including clustering and projection algorithms to cluster data of synthetic failure types semi-supervised. In addition, explainable artificial intelligence techniques have enabled to track the autoencoder’s loss with input data to detect anomalous signals. Finally, transfer learning is applied to adapt autoencoders to changing EOC data of the same process. The data-driven techniques used in this work can be adapted to address other industrial use cases, helping stakeholders gain trust and thus promote the adoption of data-driven PdM systems in smart factories.

Reactive Hydrogen Content: A Tool to Predict FCC Yields

2003 ◽  
Vol 1 (1) ◽  
Author(s):  
Ernesto Mariaca-Dominguez ◽  
Silvano Rodríguez-Salomón ◽  
Rafael Maya Yescas
Keyword(s):  
Hydrogen Content ◽  
Main Product ◽  
Carbon Number ◽  
Fluid Catalytic Cracking ◽  
Reaction Conditions ◽  
Feed Composition ◽  
Cracking Behavior ◽  
Number Range ◽  
Operational Conditions

Fluid Catalytic Cracking is a process conceived to produce gasoline as the main product. Feed stocks to the process are vacuum gas oils (VGO) showing boiling point ranges typically between 343°C and 538°C. Since these boiling range cut points are usually fixed, the carbon number range of encountered hydrocarbons is approximately constant and this is also true for the relative amounts of paraffins, naphthenes and aromatics, regardless of changes from feed to feed. Under FCC reaction conditions, each of the above hydrocarbon groups exhibit different crackability. In order to explain the existing relationship between feed composition and yields and quality of end products, it is necessary to establish the effect of composition and operational conditions on cracking behavior of feedstocks, expressed in terms of a relation between some specific properties, or as in our case, by its Reactive Hydrogen Content (RHC). Therefore, yields should then be dependent on three factors, RHC value, as a measure of feed quality, catalysts and applied operational conditions. In this work, a RHC for a series of feeds of known composition is determined and correlated to conversion and yields obtained under different operational conditions, using the same catalyst. The resulting correlations are then applied to unknown feeds with the RHC being calculated from physical properties, and yields.

scholarly journals Co-feeding of vacuum gas oil and pinewood-derived hydrogenated pyrolysis oils in a fluid catalytic cracking pilot plant to generate olefins and gasoline

2021 ◽  
Vol 1 ◽  
pp. 143
Author(s):  
Marco Buechele ◽  
Helene Lutz ◽  
Florian Knaus ◽  
Alexander Reichhold ◽  
Robbie Venderbosch ◽  
...  
Keyword(s):  
Sulfur Content ◽  
Catalytic Cracking ◽  
Pilot Plant ◽  
Fluid Catalytic Cracking ◽  
Vacuum Gas Oil ◽  
Pyrolysis Oil ◽  
Gas Oil ◽  
Hydrocarbon Gases ◽  
Process Step ◽  
Pyrolysis Oils

Background: The Waste2Road project exploits new sustainable pathways to generate biogenic fuels from waste materials, deploying existing industrial scale processes. One such pathway is through pyrolysis of wood wastes. Methods: The hereby generated pyrolysis liquids were hydrogenated prior to co-feeding in a fluid catalytic cracking (FCC) pilot plant. So-called stabilized pyrolysis oil (SPO) underwent one mild hydrogenation step (max. 200 °C) whereas the stabilized and deoxygenated pyrolysis oil (SDPO) was produced in two steps, a mild one (maximum 250 °C) prior to a more severe process step (350 °C). These liquids were co-fed with vacuum gas oil (VGO) in an FCC pilot plant under varying riser temperatures (530 and 550 °C). The results of the produced hydrocarbon gases and gasoline were benchmarked to feeding pure VGO. Results: It was proven that co-feeding up to 10 wt% SPO and SDPO is feasible. However, further experiments are recommended for SPO due to operational instabilities originating from pipe clogging. SPO led to an increase in the hydrocarbon gas production from 45.0 to 46.3 wt% at 550 °C and no significant changes at 530 °C. SDPO led to a rise in gasoline yield at both riser temperatures. The highest amount of gasoline was produced when SDPO was co-fed at a 530 °C riser temperature, with values around 44.8 wt%. Co-feeding hydrogenated pyrolysis oils did not lead to a rise in sulfur content in the gasoline fractions. The highest values were around 18 ppm sulfur content. Instead, higher amounts of nitrogen were observed in the gasoline. Conclusions: SPO and SDPO proved to be valuable co-refining options which led to no significant decreases in product quality. Further experiments are encouraged to determine the maximum possible co-feeding rates. As a first step, 20-30 wt% for SPO are recommended, whereas for SDPO  100 wt% could be achievable.

Sign in / Sign up

Export Citation Format

Share Document