Attention eLearning Users

We are upgrading our learning platform! As a result, if you have a course in progress, you'll need to complete it by December 24, 2021. Otherwise, you will need to restart the course beginning January 5, 2022 on our new platform. Repurchasing will not be necessary. Contact customer service with any questions.

Utilization of Advanced Analytics to Monitor Catalyst Health in an Ethylene Oxide Reactor

Source: AIChE
  • Checkout

    Checkout

    Do you already own this?

    Pricing


    Individuals

    AIChE Member Credits 0.5
    AIChE Members $19.00
    AIChE Graduate Student Members Free
    AIChE Undergraduate Student Members Free
    Non-Members $29.00
  • Type:
    Conference Presentation
  • Conference Type:
    AIChE Annual Meeting
  • Presentation Date:
    November 18, 2020
  • Duration:
    14 minutes
  • Skill Level:
    Intermediate
  • PDHs:
    0.20

Share This Post:

Ethylene oxide (EO), a precursor to ethylene glycol (EG), is produced through elective oxidation of ethylene and oxygen in the presence of an Ag supported α-Al2O3 catalyst in the EO/EG plant located in the Petkim Petrochemical Holding complex in Aliaga, Turkey. The EO process takes place in two parallel, fixed-bed multi-tubular reactors at a temperature and pressure range of 240–260 °C and 17–18 bar, respectively. Both ethylene epoxidation and EO combustion take place in the reactors and only the former is desirable. Side reactions result in a reduction of EO yield and an increase in CO2 emission from the plant. Thus, the optimization of the catalyst exploitation continuance becomes an important concern to maximize the primary reaction for product quality and plant profitability.

In this presentation, machine learning methods are utilized in the characterization and monitoring of the industrial catalyst used in the EO reactors. Estimation of the catalyst activity and other indicators has major importance during production due to the five-year lifetime with high catalyst cost and the EO product quality. In order to make accurate estimates, a vast quantity of data is collected from the plant and is processed using several statistical methods in order to capture the major driving signals that provide significant implications. Principal component analysis (PCA) is used for dimensional reduction and to categorize the measurements. The performances of various machine learning algorithms are compared for the prediction of that catalyst status. The machine learning model provides a good insight into the causes of rapid catalyst deactivation. Once these insights are obtained, the operating policies and process conditions that will maximize the catalyst lifetime and other desirable properties of the catalyst in the plant will be discussed in detail.

Presenter(s): 
Once the content has been viewed and you have attested to it, you will be able to download and print a certificate for PDH credits. If you have already viewed this content, please click here to login.

Checkout

Checkout

Do you already own this?

Pricing


Individuals

AIChE Member Credits 0.5
AIChE Members $19.00
AIChE Graduate Student Members Free
AIChE Undergraduate Student Members Free
Non-Members $29.00
Language: