Jaydeep Karandikar Email & Phone Number

Knoxville, Tn, Us

Knoxville, Tennessee Area

Intelligent Machine Tool Research Group at the Manufacturing Demonstration Facility (MDF) at ORNL1. Physics-guided machine learning for machining process modeling2. Closed-loop control for automated stability boundary identification

Niskayuna, Ny

1. Developed algorithms for total machining (milling, turning, and drilling) process cost optimization considering trade-offs between cycle time and tool life using machine learning methods for data-driven tool life modeling. The algorithms are integrated in a web-application that allows users to run simulations, save results to a database, and share results with different sites. Realized 30% average cost reduction across 200+ operations resulting in ~$20 million annualized savings for GE Aviation. 2. Developed machining process analytics to quantify machining process performance, identify key drivers for machining inefficiencies, and make recommendations to programmer/ME to improve machining process performance and machine utilization, using machine control and sensor data. 3. Developed a framework for optimal manufacturing process selection considering various process uncertainties and their dependencies, associated costs, user risk references.4. Collaborated with Prof. Tony Schmitz at UNC Charlotte on National Science Foundation (NSF) Grant Opportunities for Academic Liaison with Industry (GOALI) projecton the application of process damping and period-n bifurcations for reducing milling costs in production environments. 5. Collaborated with Prof. Tony Schmitz, UNC Charlotte, and Prof. Noel Greis, UNC Chapel-Hill on Manufacturing-Uber. The idea is to use “floating” operators, who can move where and when they’re needed depending on the machine intervention required. The M-Uber “smart” assignment tool also considers any pending problems with other machines, and the estimated time to fix the problem, in real time. 6. Methods and tools for qualification and monitoring of vibratory super-finishing process.

Atlanta

1. Developed an adaptive sampling for freeform surface metrology. The adaptive algorithm iteratively optimizes the number of measurements and measurement locations to assess the conformity of the freeform surface using a value of information method. 2. Application of surrogate model based global optimization for machining cost minimization. The goal is to optimize the experimental design to identify the optimum machining parameters, tool geometry and tool materials for minimizing machining cost.3. Manufacturing process optimization for circumferential turbine blades operation (in collaboration with GE Power & Water, Duluth, GA). The optimization was performed on two directions: 1) machining parameters considering machine dynamics and tool life and 2) overall process operations.

Charlotte, North Carolina Area

1. Application of Bayesian inference and decision theory to milling process optimization under uncertainty for machining hard-to-machine materials; results show a 90% decrease in machining cost.2. Bayesian updating using the Markov Chain Monte Carlo (MCMC) method for milling force modeling.3. Developed a novel algorithm for predicting remaining useful life using Bayesian inference. The applications include cutting tool life and fatigue-damaged structures.

Sheffield, United Kingdom

1. Tool condition monitoring using Bayesian classifier and Hidden Markov Models.2. Remaining useful tool life predictions using Bayesian inference.

Gainesville, Florida Area

1. Combining tool wear, stability, surface location error and uncertainty analysis in high-speed machining performance prediction.

Sheffield, United Kingdom

1. Develop a sensor-based monitoring system for machining aerospace alloys. 2. Design a Bayesian network inference methodology for tool condition monitoring using Bayesian classifiers.

Design Engineer - Control valves, Pressure Reducing and Desuperheating systems.

Ph.D., Mechanical Engineering

Activities and Societies: Tau Beta PiDissertation: The fundamental application of decision analysis for milling optimization under.

Ms, Mechanical Engineering

Thesis: Combining tool wear and dynamics in high-speed machining performance prediction.

B.S., Mechanical Engineering