Prediction of Bubble Sizes in Bubble Columns with Machine Learning Methods
نویسندگان
چکیده
Two Machine Learning algorithms – LASSO and Random Forest are applied to derive regression models for the prediction of gas bubble diameters using supervised learning techniques. Experimental data obtained from wire-mesh sensor (WMS) measurements in a deionized water/air system serve as base. Python libraries used extract features characterizing WMS measurement signals single passing bubbles. Prediction accuracy is largely increased with models, compared well-established methods predict sizes based on measurements.
منابع مشابه
Determination of Bubble Size Distributions in Bubble Columns Using LDA
A new method is developed for the determination of bubble size distributions from experimental laser Doppler anemometry (LDA) data through simultaneous measurement of only two orthogonal velocity components and the intermittent time gaps arising out of bubbles passing through the measurement point. An experimentally verifiable assumption of axisymmetry allowed the calculation of the three-dimen...
متن کاملAcoustic and visual study of bubble formation processes in bubble columns staged with fibrous catalytic layers
High-speed images of bubbly flow coupled with simultaneous passive acoustic measurements were carried out in a bubble column staged with structured fibrous catalysts. Local observations made with a high-speed camera system allow a detailed understanding of the influence of fabric structure on bubble formation processes and the determination of the Sauter bubble diameter. With acoustic measureme...
متن کاملBubble Pressure Prediction of Reservoir Fluids using Artificial Neural Network and Support Vector Machine
Bubble point pressure is an important parameter in equilibrium calculations of reservoir fluids and having other applications in reservoir engineering. In this work, an artificial neural network (ANN) and a least square support vector machine (LS-SVM) have been used to predict the bubble point pressure of reservoir fluids. Also, the accuracy of the models have been compared to two-equation stat...
متن کاملIntegration of Particle to Bubble Adhesion Model in Design and Scale-Up of Slurry Bubble Columns
In slurry bubble column reactors, catalyst particles may adhere to gas bubbles. Thus, mass transfer limited reactions can be significantly improved either by increasing G-L mass transfer coefficient kL or specific surface area a. The scope of this work is to study the influence of model parameters on coalescence and G-L mass transfer, in order to develop new rules for design and scale-up of slu...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Chemie Ingenieur Technik
سال: 2021
ISSN: ['0009-286X', '1522-2640']
DOI: https://doi.org/10.1002/cite.202100157