Engineering Commons^™

Machine Learning Based Applications For Data Visualization, Modeling, Control, And Optimization For Chemical And Biological Systems, Yan Ma

LSU Doctoral Dissertations

This dissertation report covers Yan Ma’s Ph.D. research with applicational studies of machine learning in manufacturing and biological systems. The research work mainly focuses on reaction modeling, optimization, and control using a deep learning-based approaches, and the work mainly concentrates on deep reinforcement learning (DRL). Yan Ma’s research also involves with data mining with bioinformatics. Large-scale data obtained in RNA-seq is analyzed using non-linear dimensionality reduction with Principal Component Analysis (PCA), t-Distributed Stochastic Neighbor Embedding (t-SNE), and Uniform Manifold Approximation and Projection (UMAP), followed by clustering analysis using k-Means and Hierarchical Density-Based Spatial Clustering with Noise (HDBSCAN). This report focuses …

Applications Of Cfd Simulations On Chemical Processing Equipment Designs, Gongqiang He

LSU Doctoral Dissertations

The objective of this work is to achieve process intensification by seeking optimal equipment design with CFD investigations. In this work, two projects on chemical equipment design have been discussed.

The first project is on design and optimization of fractal distributor in a novel ion-exchanger. Flow distributors are adopted extensively by chemical industry to distribute an incoming process stream uniformly to the downstream equipment. Currently, the performance of chemical equipment installed with conventional distributor is severely undermined due to poor flow distribution. For conventional distributors such as spray nozzle distributors, their design concept is based on maintaining very high pressure …

A Thermodynamic Framework For The Modeling And Optimization Of Crystallization Processes, David John Widenski

LSU Doctoral Dissertations

Crystallization is a widely used chemical engineering separation unit operation process. Since this technique can produce high purity products it is used for the industrial production of many chemical compounds, such as pharmaceuticals, agrochemicals, and fine chemicals. The production of these products is a multi-million dollar industry. Any methods to improve the production of these products would be highly valued. Thus, the main objective of this work is to target model-based optimal strategies for crystallization operations specifically targeting crystal size and crystal size distribution (CSD). In particular, take the knowledge gained and translate it into an economically and practically feasible …

Optimal Operating Strategy For Wells With Downhole Water Sink Completions To Control Water Production And Improve Performance, Ozan Arslan

LSU Doctoral Dissertations

Downhole water sink (DWS) technology is an alternative to conventional limited-entry completions to control water production in wells with bottom water drive. DWS wells comprise two completions: the bottom completion produces water and keeps the top completion open to oil inflow. The system performance depends on careful manipulation of the top and bottom rates to maximize oil productivity and produce oil-free water from the bottom completion. Conventional nodal analysis cannot provide a solution for DWS wells because the critical rates for water coning change with water drainage rate. A reservoir simulator is used to model two-phase flow to the dual …