Pair your accounts.

Export articles to Mendeley

Get article recommendations from ACS based on references in your Mendeley library.

Pair your accounts.

Export articles to Mendeley

Get article recommendations from ACS based on references in your Mendeley library.

You’ve supercharged your research process with ACS and Mendeley!

STEP 1:
Click to create an ACS ID

Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

MENDELEY PAIRING EXPIRED
Your Mendeley pairing has expired. Please reconnect
ACS Publications. Most Trusted. Most Cited. Most Read
My Activity
CONTENT TYPES

Figure 1Loading Img

Data-Driven Dynamic Modeling and Control of a Surface Aeration System

View Author Information
Institute of Chemical Technology, Matunga, Mumbai-400 019, India, and Chemical Engineering & Process Development Division, National Chemical Laboratory, Pune-411008, India
Cite this: Ind. Eng. Chem. Res. 2007, 46, 25, 8607–8613
Publication Date (Web):May 15, 2007
https://doi.org/10.1021/ie0700765
Copyright © 2007 American Chemical Society

    Article Views

    218

    Altmetric

    -

    Citations

    LEARN ABOUT THESE METRICS
    Other access options
    Supporting Info (1)»

    Abstract

    In this study we have developed a support vector regression (SVR) based data-driven model for predicting two important design parameters of surface aerators, namely, the volumetric mass transfer coefficient (kLa) and fractional gas hold-up (εG). The dynamical state of the surface aerator system was captured by acquiring pressure fluctuation signals (PFSs) at various design and operating conditions. The most informative features from PFS were extracted using the chaos analysis technique, which includes estimation of Lyapunov exponent, correlation dimensions, and Kolmogorov entropy. At similar conditions the values of kLa and εG were also measured. Two different SVR models for predicting the volumetric mass transfer coefficient (kLa) and overall gas hold-up (εG) as a function of chaotic invariants, design parameters, and operating parameters were developed showing test accuracies of 98.8% and 97.1%, respectively. Such SVM based models for the surface aerator can be potentially useful on a commercial scale for online monitoring and control of desired process output variables.

    Read this article

    To access this article, please review the available access options below.

    Get instant access

    Purchase Access

    Read this article for 48 hours. Check out below using your ACS ID or as a guest.

    Recommended

    Access through Your Institution

    You may have access to this article through your institution.

    Your institution does not have access to this content. You can change your affiliated institution below.

     Institute of Chemical Technology.

     National Chemical Laboratory.

    *

     To whom correspondence should be addressed. Tel:  +91-20-5893095. Fax:  +91-20-5893041. E-mail:  [email protected].

    Supporting Information Available

    ARTICLE SECTIONS
    Jump To

    List of SVs and corresponding Lagrange multipliers (weights) are available for SVR based kLa and εG models, respectively (PDF). This material is available free of charge via Internet at http://pubs.acs.org.

    b = bias term

    C = impeller clearance/distance between the impeller and the reactor bottom

    C = cost function

    CC = correlation coefficient

    C(r) = correlation integral

    CD = correlation dimension

    D = impeller diameter

    DT = disc type impeller

    ETrn = RMSE for training set

    ETst = RMSE for test set

    F = high dimensional feature space

    f(x) = regression function

    H = Heaviside function

    HL = liquid height

    k = first positive Lyapunov exponents

    K(xi, xj) = kernel function

    K = Kolmogorov entropy

    kLa= volumetric mass transfer coefficient

    L = lagrangian function (dual form)

    m = embedding dimensions

    Nimp = impeller speed

    N = number of training data points

    Np = number of vector data points constituting attractor

    Nsv = number of support vectors

    P = number of recorded pressure data points

    PBTU = pitched blade turbine up flow

    PBTD = pitched blade turbine down flow

    p(n) = one-dimension pressure data

    r = radius of m-dimension hyper-space

    rps = impeller revolutions per second

    ℛ = input space

    RMSE = root-mean-square error

    T = tank diameter

    xi = ith input vector

    w = weight vector

    yi = target output corresponding to the ith vector

    y(n) = m-dimension pressure vector

    Greek Letters εG = overall gas hold-up

    τ = time delay

    λ = Lyapunov exponent

    φ(xi) = feature space for ith input vector x

    ξi(*) = slack variables

    αi,j(*) = Lagrange multipliers

    ε = precision parameter

    σ = width of radial basis function (RBF) kernel

    γ = 1/2σ2

    ∞ = infinity

    Subscripts G = gas phase

    Terms & Conditions

    Most electronic Supporting Information files are available without a subscription to ACS Web Editions. Such files may be downloaded by article for research use (if there is a public use license linked to the relevant article, that license may permit other uses). Permission may be obtained from ACS for other uses through requests via the RightsLink permission system: http://pubs.acs.org/page/copyright/permissions.html.

    Cited By

    This article is cited by 7 publications.

    1. Swetha Saraswathi K., Hrushikesh Bhosale, Prasad Ovhal, Naren Parlikkad Rajan, Jayaraman Krishnamoorthy Valadi. Random Forest and Autoencoder Data-Driven Models for Prediction of Dispersed-Phase Holdup and Drop Size in Rotating Disc Contactors. Industrial & Engineering Chemistry Research 2021, 60 (1) , 425-435. https://doi.org/10.1021/acs.iecr.0c04149
    2. Yi Liu, Zengliang Gao, Ping Li, and Haiqing Wang . Just-in-Time Kernel Learning with Adaptive Parameter Selection for Soft Sensor Modeling of Batch Processes. Industrial & Engineering Chemistry Research 2012, 51 (11) , 4313-4327. https://doi.org/10.1021/ie201650u
    3. Yi Liu, Wenlu Chen, Haiqing Wang, Zengliang Gao, and Ping Li . Adaptive Control of Nonlinear Time-Varying Processes Using Selective Recursive Kernel Learning Method. Industrial & Engineering Chemistry Research 2011, 50 (5) , 2773-2780. https://doi.org/10.1021/ie100634k
    4. Yi Liu, Naiping Hu, Haiqing Wang and Ping Li . Soft Chemical Analyzer Development Using Adaptive Least-Squares Support Vector Regression with Selective Pruning and Variable Moving Window Size. Industrial & Engineering Chemistry Research 2009, 48 (12) , 5731-5741. https://doi.org/10.1021/ie8012709
    5. Liang Dong, Jiawei Liu, Houlin Liu, Cui Dai, Dmitry Vladimirovich Gradov. Study on the internal two-phase flow of the inverted-umbrella aerator. Advances in Mechanical Engineering 2019, 11 (8) , 168781401987173. https://doi.org/10.1177/1687814019871731
    6. Narasimhan Desigan, Nirav Bhatt, Madhuri A. Shetty, Gopala Krishna Pillai Sreekumar, Niranjan Kumar Pandey, Uthandi Kamachi Mudali, Rajamani Natarajan, Jyeshtharaj B. Joshi. Dissolution of nuclear materials in aqueous acid solutions. Reviews in Chemical Engineering 2019, 35 (6) , 707-734. https://doi.org/10.1515/revce-2017-0063
    7. A.B. Gandhi, J.B. Joshi, A.A. Kulkarni, V.K. Jayaraman, B.D. Kulkarni. SVR-based prediction of point gas hold-up for bubble column reactor through recurrence quantification analysis of LDA time-series. International Journal of Multiphase Flow 2008, 34 (12) , 1099-1107. https://doi.org/10.1016/j.ijmultiphaseflow.2008.07.001