Rajib Mukherjee
Process Analytics Engineer
Hire this person
Send a job offer directly to this candidate
About
Rajib Mukherjee, PhD is a Process Analytics Engineer at Bristol Myers Squibb (BMS). Prior to joining BMS, he worked as Assistant Professor in the Department of Chemical Engineering at The University of Texas Permian Basin (UTPB). He has held research positions including Assistant Research Engineer at the Gas and Fuels Research Center, Texas A&M Engineering Experiment Station, Research Associate at Texas A&M Energy Institute, Visiting Assistant Professor, Department of Mechanical Engineering at Texas A&M University, ORISE Postdoctoral Research Fellow at US Environmental Protection Agency (US EPA), Postdoctoral Research Associate at Center for Computational Science, Tulane University (CCS, Tulane), and Project Engineer at National Metallurgical Laboratory, India (NML, India).
He has a doctorate in Chemical Engineering, graduated from the Process Systems Engineering Laboratory at Louisiana State University, Department of Chemical Engineering. His present work includes (a) developing multivariate statistical models for real time process monitoring (upstream and downstream); (b) process variability analysis using chemometrics; (c) developing algorithm for digital twin of chemical process for real time operations and control using advanced machine learning algorithms including deep learning. He has over fifteen years of experience in first principle based and data driven modeling, statistical algorithm development, stochastic optimization algorithm development with uncertain variables, application of machine learning algorithms for design, real time monitoring and control of chemical process systems.
Experience
Bristol Myers Squibb, Devens, MA (Feb 2022 - Present)
Process Analytics Engineer at Manufacturing Science & Technology
- Develop advanced multivariate analysis models for real-time multivariate process monitoring
- SIMCA® and SIMCA®-online for multivariate model development and online implementation of the models for process monitoring
- Maintain the existing modeling platforms
- Model updates with changing process conditions
- Develop advanced data analytics methods to transform manufacturing/lab data into actionable proactive insights.
- Root cause analysis to identify process yield variation among batches.
- Data engineering, data analysis, data visualization, modeling, and prediction
- Deep Learning algorithms for digital twin of chromatographic separation processes
Assistant Professor: Department of Chemical Engineering
- Courses taught: Chemical Engineering Fluid Operation, Chemical Engineering Analysis, Heat Transfer Operations, Chemical Engineering Thermodynamics, Chemical Engineering Mass Transfer, Advanced Engineering Analysis, Gas and Petroleum Processing, Senior Design, Chemical Engineering Plant Design
- Research: Natural Gas Processing, Optimal Sensor Networks, Water-Energy Nexus
Research Associate, Texas A&M Energy Institute
- Data driven modeling and simulation for the SUPERFUND project. Application of Machine Learning (ML) algorithms including Deep Learning (DL) for spatiotemporal data analysis.
- Developing SUPERFUND, a python Django based tool for environmental and bio data analysis
- Teaching “MATLAB® for Engineers”, “Applied Statistics for Engineers” to the visiting students in Chem Engg Department
- Energy and water network optimization under uncertainty.
- Reliability assessment of Eco-Industrial Park (EIP) under uncertain process conditions.
- Selection of sustainable chemical process with multivariate statistical algorithms.
- Teaching MEEN 357-501 Engineering Analysis for Mechanical Engineers
Research Engineer, Center for Uncertain Systems: Tools for Optimization and Management (VRI-CUSTOM)
- Development of stochastic optimization algorithms for sensor placement in water network systems, environmental pollution monitoring, coal power plant
- Computer aided molecular design (CAMD) of novel functional materials
ORISE postdoctoral research fellow at Office of Research and Development/National Risk Management Research Lab (NRMRL), Sustainable Technology Division.
- Advancing Chemical Process Engineering by integrating sustainable technologies in process design.
- Developing GREENSCOPE, a tool for sustainability evaluation of chemical process
- Data analytics with multivariate statistics (PCA, PLS) to select sustainability indicators.
Postdoctoral research associate of Louisiana Alliance for Simulation-Guided Materials Applications (LASiGMA) at the Center for Computational Science (CCS), Tulane University.
- Supercomputing, application of novel tools for distributed high-performance computing (HPC).
- Molecular Simulations, Molecular Dynamics (MD) simulations of biomolecular systems.
- Data Analysis, application of multivariate statistics for analyzing structure and dynamics of biomolecular systems.
Dissertation from Process Systems Engineering Laboratory, Department of Chemical Engineering.
- Statistical Process Monitoring, image Analysis using multiresolution (wavelet) and multivariate (PCA), cluster and Fourier analysis.
- Multiscale Modeling and Stochastic Simulation, mesoscale lattice based modeling and important sampling Monte Carlo (MC) and Kinetic Monte Carlo (KMC) simulations of polymer solution systems for dynamics of phase separation
- Graduate Teaching Assistant in the Department of Chemical Engineering for:
- Advanced Process Control, Optimization, Mathematical Methods in Chemical Engineering, Advanced Mathematics in Chemical Engineering, Process Dynamics & Control.
Project Engineer
- Numerical Analysis, solution of simultaneous Ordinary Differential Equations (ODE) obtained from mass and energy balance inside blast furnace reactor.
Systems Engineer
Education
Technical Skills
- OSI PI, SeeQ® for process data analytics
- SIMCA®, JMP for multivariate statistical model development with continuous (time series) and discrete data.
- Chemical process simulator: Aspen Plus®, CHEMCAD, ProMax®
- MATLAB®, R, XLStat for Statistical Analysis
- Python, MATLAB®, R for Machine Learning Algorithms, Deep Learning
- MATLAB® for image processing
- Programming language: FORTRAN, Visual Basic, C, C++, JAVA, Python
- Database: MySQL, SQLite
- Distributed supercomputing for simulation and data analysis across various supercomputers (XSEDE, LONI).
- Developing tool with JAVA, Python Django
- GAMS, LINGO and MATLAB® for optimization
- Simulation package: NAMD, CPMD
- Visualization package: VMD, RasMol, Visio®
- Operating Systems: UNIX, Linux, Mac OS X, Windows.
