Working as Senior Product Engineer in the Semi Truck team
(Dec 23-)
Leading the effort to mitigate and tackle current challenges in Semi Truck
Addressing the feature enhancement via driver's feedback
Use fleet analytics to regulate and monitor fleet-wide concerns
Collaborate with various engineering teams to perform field quality checks for establishing the root cause and failure/corrective analysis.
Perform DFMEA to establish the path to success in future products.
SANTA CLARA, CALIFORNIA, USA
Application Deployment, Big Data and Cloud Application Engineer
Spearheaded seamless application deployment processes, ensuring efficient and reliable transitions for clients utilizing MathWorks solutions.
Specialized in integrating MathWorks applications with cloud computing platforms, optimizing performance and scalability for diverse client needs.
Led initiatives to leverage big data technologies in MathWorks applications, enhancing data processing capabilities and enabling clients to derive actionable insights.
Collaborated closely with cross-functional teams to design and implement robust application architectures, ensuring alignment with industry best practices.
Acted as a key liaison between customers and development teams, gathering requirements and providing expert guidance on deploying MathWorks applications in varied environments.
Stayed abreast of industry trends and emerging technologies in application deployment, cloud computing, and big data, contributing to the continuous improvement of MathWorks solutions.
Cell Engineering and Mechanical Modeling intern
(Jan 22-Aug22)
Battery Modeling and Technology Division: Lifetime forecasting, Mechanical modeling and Data analytics intern
Battery design of Tesla Bot
Executed semi-empirical modeling to forecast battery life of Tesla Bot considering charging and discharging.
Partnered with the Mechanical Design team to optimize the robot’s thermal performance based on operation time, State of Charge (SoC), and Depth of Discharge (DoD) of the battery.
Cell Lifetime forecasting
Matured statistical physics model for forecasting lifetime of vendor cells across multiple form factors of 1865/2170/4680 to be used in Tesla Model 3 and Model Y.
Implemented least-square nonlinear algorithm using MATLAB for modeling modified Arrhenius loss equation to analyze energy decay and capacity loss of a cell.
Worked in collaboration with Cell Characterization and Cell Qualification Labs to develop a visualization tool for Lithium Iron Phosphate (LFP) cells.
Statistical analysis to calculate error & confidence in forecasting model & identification of failure point
Improved the performance and working of pre-existing lifetime models by analyzing datasets with over a million entries and by introducing statistical errors and confidence intervals.
Proposed and implemented a method to benchmark the cycle life of a cell, based on 610 different cells.
Designed a slope tracing algorithm to identify a sudden change in cell capacity thereby letting the experimental team know about the throughput cutoff point.
Introduced statistical failure points for different cell types, forecasting battery packs replacement time.
Mechanical modeling and validation
Performed material card validations using commercial FEA software, such as ABAQUS and LS-DYNA
Developed ABAQUS post processing tool by scripting with MATLAB and Python enabling the study of cell mechanical simulation results
Validated the cell mechanical models using the high-resolution CT image data
Assisted the mechanical lab tests and developed MATLAB scripts for post-processing raw test data
Powerwall and Megapack reliability
Ensured 70% post-test capacity retention checks for vendor cells under High-Temperature Humidity Endurance (HTHE) and Powered Thermal Cycling Endurance (PTCE) conditions.
Forecasted Megapack lifetime based on extreme weather conditions ensuring selection of correct chemistry for the proposed class of vendor cells.
Inhouse cell development
Built a framework to analyze the lifespan of Tesla’s high energy density inhouse cells to be used in Power Wall, Cyber Truck, and Semi.
Teamed with Tesla’s cell manufacturing facility at Kato, California to develop a control protocol for charging and discharging test and source cells for various State of Charge (SoC).
Worked as Thermal and Fluid intern in Aftertreament system integration and control division
(May'21 -Aug'21)
Analyzed field performance data and developed a feedforward network model with engine parameters.
Investigated various Artificial Intelligence-based Neural Network models to predict turbine outlet temperature.
Implemented Nonlinear Autoregressive (NARX) model to forecast the exhaust temperature for several time horizons.
Developed internal flow pipe model to estimate Aftertreatement inlet temperature from exhaust temperature.
Supervisor: Professor Dmitry. V. Feoktistov, Department of theoretical and industrial heating equipment
Modeled working of closed vertical thermosiphon computationally using ANSYS (FLUENT) 18.0.
Structured flow for various fill-in ratio and heat fluxes, optimizing the efficiency of the experimental model
Amassed working principles of heat exchangers in parallel flow, cross flow, and counter flows
Analyzed numerical data and grasped concept of heat profile and turbulent mixing between multi-phase flows
Coordinated with industry personnel towards data collection of heat transfer across liquor tanks
The work can be read here