I'm a data scientist and engineer at Applied Materials, putting the power of artificial intelligence and machine learning at the edge of the Industrial Internet of Things, Industry 4.0, and next-generation Smart Factory Automation. I specialize in early failure detection for machinery, prognostic analysis, dashboards, visualization, and exploratory data analysis. I’m looking to collaborate on data science projects, machine learning, and applications of data science in other fields
- Building predictive models for semiconductor equipment to predict failures before they impact production
- Writing a book on Practical Prognostics with Python (Stay tuned!)
- Developing stock trading algorithms to reduce volatility exposure and beat common index returns
The Vega shrink-wrapper from OCME is deployed in large production lines in the food and beverage industry. The machine groups loose bottles or cans into set package sizes, wraps them in plastic film and then heat-shrinks the plastic film to combine them into a package. The plastic film is fed into the machine from large spools and is then cut to the length needed to wrap the film around a pack of goods. The cutting assembly is an important component of the machine to meet the high availability target. Therefore, the blade needs to be set-up and maintained properly. Furthermore, the blade can not be inspected visually during operation due to the blade being enclosed in a metal housing and its fast rotation speed. Monitoring the cutting blades degradation will increase the machines reliability and reduce unexpected downtime caused by failed cuts.
Remaining Useful Life, or RUL, is a metric used to define the number of cycles or timeframe machinery, systems, or components have before maintenance should be performed. Accurately predictive RUL plays a critical role in equipment health management, or EHM. With the dawn of IoT and Industry 4.0, it is now possible to more accurately calculate RUL and, by doing so, only performing maintenance when appropriate, saving time, money and resources. The dataset for this project was used for the prognostic challenge competetion at the International Conference on Prognostics and Health Management (PHM08). The dataset consists of several multivariate time series observations that demonstrate the degredation several different engines under different operating conditions, simulated using Commercial Modular Aero-Propulsion System Simulation software (C-MAPSS). Each engine starts with different degrees of initial wear and manufacturing variation which is unknown. The data contains sensor data contaminated with noise for the following engine attributes.
Using data science and deep learning, predicting inventory consumption and asset levels of warehouses can improve logistical capabilities of several industries. This allows for increased turnaround time for parts delivery, boosted efficiency and productivity, and an overall reduction of overhead caused by priority shipping from unexpected demand. Thanks to the Internet of Things, WiFi capable sensors can track the location and movement of assets in a facility, increasing efficiency of logistics teams.-
University At Buffalo - Digital Manufacturing & Design Technology Specialization
- Digital Manufacturing & Design
- Digital Thread: Components
- Digital Thread: Implementation
- Advanced Manufacturing Process Analysis
- Intelligent Machining
- Advanced Manufacturing Enterprise
- Cyber Security in Manufacturing
- MBSE: Model-Based Systems Engineering
- Roadmap to Success in Digital Manufacturing & Design
-
Technical University of Munich - Digitalization in Aeronautics and Space Specialization
- Data Scientist
- November 2014 - Present
- Research Assistant
- June 2013 - July 2014